WIP

This reverts commit d6470bc963.

.dockerignore

@@ -1,18 +1,31 @@
-.git
-.github
-changedetectionio/processors/__pycache__
-changedetectionio/api/__pycache__
-changedetectionio/model/__pycache__
-changedetectionio/blueprint/price_data_follower/__pycache__
-changedetectionio/blueprint/tags/__pycache__
-changedetectionio/blueprint/__pycache__
-changedetectionio/blueprint/browser_steps/__pycache__
-changedetectionio/fetchers/__pycache__
-changedetectionio/tests/visualselector/__pycache__
-changedetectionio/tests/restock/__pycache__
-changedetectionio/tests/__pycache__
-changedetectionio/tests/fetchers/__pycache__
-changedetectionio/tests/unit/__pycache__
-changedetectionio/tests/proxy_list/__pycache__
-changedetectionio/__pycache__
+# Git
+.git/
+.gitignore
 
+# GitHub
+.github/
+
+# Byte-compiled / optimized / DLL files
+**/__pycache__
+**/*.py[cod]
+
+# Caches
+.mypy_cache/
+.pytest_cache/
+.ruff_cache/
+
+# Distribution / packaging
+build/
+dist/
+*.egg-info*
+
+# Virtual environment
+.env
+.venv/
+venv/
+
+# IntelliJ IDEA
+.idea/
+
+# Visual Studio
+.vscode/

.github/ISSUE_TEMPLATE/bug_report.md

@@ -27,6 +27,10 @@ A clear and concise description of what the bug is.
 **Version**
 *Exact version* in the top right area: 0....
 
+**How did you install?**
+
+Docker, Pip, from source directly etc
+
 **To Reproduce**
 
 Steps to reproduce the behavior:

.github/test/Dockerfile-alpine

@@ -2,32 +2,33 @@
 # Test that we can still build on Alpine (musl modified libc https://musl.libc.org/)
 # Some packages wont install via pypi because they dont have a wheel available under this architecture.
 
-FROM ghcr.io/linuxserver/baseimage-alpine:3.18
+FROM ghcr.io/linuxserver/baseimage-alpine:3.21
 ENV PYTHONUNBUFFERED=1
 
 COPY requirements.txt /requirements.txt
 
 RUN \
-  apk add --update --no-cache --virtual=build-dependencies \
+ apk add --update --no-cache --virtual=build-dependencies \
+    build-base \
     cargo \
-    g++ \
-    gcc \
+    git \
     jpeg-dev \
     libc-dev \
     libffi-dev \
-    libjpeg \
     libxslt-dev \
-    make \
     openssl-dev \
-    py3-wheel \
     python3-dev \
+    zip \
     zlib-dev && \
   apk add --update --no-cache \
+    libjpeg \
     libxslt \
-    python3 \
-    py3-pip && \
+    nodejs \
+    poppler-utils \
+    python3 && \
   echo "**** pip3 install test of changedetection.io ****" && \
-  pip3 install -U pip wheel setuptools && \
-  pip3 install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.18/ -r /requirements.txt && \
+  python3 -m venv /lsiopy  && \
+  pip install -U pip wheel setuptools && \
+  pip install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.21/ -r /requirements.txt && \
   apk del --purge \
     build-dependencies

.github/workflows/containers.yml

@@ -103,6 +103,19 @@ jobs:
 #          provenance: false
 
       # A new tagged release is required, which builds :tag and :latest
+      - name: Docker meta :tag
+        if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
+        uses: docker/metadata-action@v5
+        id: meta
+        with:
+            images: |
+                ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io
+                ghcr.io/dgtlmoon/changedetection.io
+            tags: |
+                type=semver,pattern={{version}}
+                type=semver,pattern={{major}}.{{minor}}
+                type=semver,pattern={{major}}
+
       - name: Build and push :tag
         id: docker_build_tag_release
         if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
@@ -111,11 +124,7 @@ jobs:
           context: ./
           file: ./Dockerfile
           push: true
-          tags: |
-            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:${{ github.event.release.tag_name }}
-            ghcr.io/dgtlmoon/changedetection.io:${{ github.event.release.tag_name }}
-            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:latest
-            ghcr.io/dgtlmoon/changedetection.io:latest
+          tags: ${{ steps.meta.outputs.tags }}
           platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8,linux/arm64/v8
           cache-from: type=gha
           cache-to: type=gha,mode=max

.github/workflows/pypi-release.yml

@@ -45,9 +45,12 @@ jobs:
     - name: Test that the basic pip built package runs without error
       run: |
         set -ex
-        sudo pip3 install --upgrade pip 
-        pip3 install dist/changedetection.io*.whl
+        ls -alR 
+        
+        # Find and install the first .whl file
+        find dist -type f -name "*.whl" -exec pip3 install {} \; -quit
         changedetection.io -d /tmp -p 10000 &
+        
         sleep 3
         curl --retry-connrefused --retry 6 http://127.0.0.1:10000/static/styles/pure-min.css >/dev/null
         curl --retry-connrefused --retry 6 http://127.0.0.1:10000/ >/dev/null

.github/workflows/test-only.yml

@@ -37,3 +37,10 @@ jobs:
       python-version: '3.12'
       skip-pypuppeteer: true
 
+  test-application-3-13:
+    needs: lint-code
+    uses: ./.github/workflows/test-stack-reusable-workflow.yml
+    with:
+      python-version: '3.13'
+      skip-pypuppeteer: true
+      

.github/workflows/test-stack-reusable-workflow.yml

@@ -64,14 +64,16 @@ jobs:
           echo "Running processes in docker..."
           docker ps
 
-      - name: Test built container with Pytest (generally as requests/plaintext fetching)
+      - name: Run Unit Tests
         run: |
           # Unit tests
-          echo "run test with unittest"
           docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_notification_diff'
           docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_watch_model'
           docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_jinja2_security'
-          
+          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_semver'
+
+      - name: Test built container with Pytest (generally as requests/plaintext fetching)
+        run: |
           # All tests
           echo "run test with pytest"
           # The default pytest logger_level is TRACE

.gitignore

@@ -1,14 +1,29 @@
-__pycache__
-.idea
-*.pyc
-datastore/url-watches.json
-datastore/*
-__pycache__
-.pytest_cache
-build
-dist
-venv
-test-datastore/*
-test-datastore
+# Byte-compiled / optimized / DLL files
+**/__pycache__
+**/*.py[cod]
+
+# Caches
+.mypy_cache/
+.pytest_cache/
+.ruff_cache/
+
+# Distribution / packaging
+build/
+dist/
 *.egg-info*
+
+# Virtual environment
+.env
+.venv/
+venv/
+
+# IDEs
+.idea
 .vscode/settings.json
+
+# Datastore files
+datastore/
+test-datastore/
+
+# Memory consumption log
+test-memory.log

COMMERCIAL_LICENCE.md

@@ -4,7 +4,7 @@ In any commercial activity involving 'Hosting' (as defined herein), whether in p
 
 # Commercial License Agreement
 
-This Commercial License Agreement ("Agreement") is entered into by and between Mr Morresi (the original creator of this software) here-in ("Licensor") and (your company or personal name) _____________ ("Licensee"). This Agreement sets forth the terms and conditions under which Licensor provides its software ("Software") and services to Licensee for the purpose of reselling the software either in part or full, as part of any commercial activity where the activity involves a third party.
+This Commercial License Agreement ("Agreement") is entered into by and between Web Technologies s.r.o. here-in ("Licensor") and (your company or personal name) _____________ ("Licensee"). This Agreement sets forth the terms and conditions under which Licensor provides its software ("Software") and services to Licensee for the purpose of reselling the software either in part or full, as part of any commercial activity where the activity involves a third party.
 
 ### Definition of Hosting
 

Dockerfile

@@ -32,11 +32,12 @@ RUN pip install --extra-index-url https://www.piwheels.org/simple  --target=/dep
 # Playwright is an alternative to Selenium
 # Excluded this package from requirements.txt to prevent arm/v6 and arm/v7 builds from failing
 # https://github.com/dgtlmoon/changedetection.io/pull/1067 also musl/alpine (not supported)
-RUN pip install --target=/dependencies playwright~=1.41.2 \
+RUN pip install --target=/dependencies playwright~=1.48.0 \
     || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
 
 # Final image stage
 FROM python:${PYTHON_VERSION}-slim-bookworm
+LABEL org.opencontainers.image.source="https://github.com/dgtlmoon/changedetection.io"
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
     libxslt1.1 \

MANIFEST.in

@@ -1,6 +1,8 @@
 recursive-include changedetectionio/api *
+recursive-include changedetectionio/apprise_plugin *
 recursive-include changedetectionio/blueprint *
 recursive-include changedetectionio/content_fetchers *
+recursive-include changedetectionio/conditions *
 recursive-include changedetectionio/model *
 recursive-include changedetectionio/processors *
 recursive-include changedetectionio/static *

README.md

@@ -43,7 +43,7 @@ Requires Playwright to be enabled.
 
 ### Awesome restock and price change notifications
 
-Enable the _"Re-stock & Price detection for single product pages"_ option to activate the best way to monitor product pricing.
+Enable the _"Re-stock & Price detection for single product pages"_ option to activate the best way to monitor product pricing, this will extract any meta-data in the HTML page and give you many options to follow the pricing of the product.
 
 Easily organise and monitor prices for products from the dashboard, get alerts and notifications when the price of a product changes or comes back in stock again!
 
@@ -105,13 +105,22 @@ We [recommend and use Bright Data](https://brightdata.grsm.io/n0r16zf7eivq) glob
 
 Please :star: star :star: this project and help it grow! https://github.com/dgtlmoon/changedetection.io/
 
+### Schedule web page watches in any timezone, limit by day of week and time.
+
+Easily set a re-check schedule, for example you could limit the web page change detection to only operate during business hours.
+Or perhaps based on a foreign timezone (for example, you want to check for the latest news-headlines in a foreign country at 0900 AM),
+
+<img src="./docs/scheduler.png" style="max-width:80%;" alt="How to monitor web page changes according to a schedule"  title="How to monitor web page changes according to a schedule"  />
+
+Includes quick short-cut buttons to setup a schedule for **business hours only**, or **weekends**.
+
 ### We have a Chrome extension!
 
 Easily add the current web page to your changedetection.io tool, simply install the extension and click "Sync" to connect it to your existing changedetection.io install.
 
 [<img src="./docs/chrome-extension-screenshot.png" style="max-width:80%;" alt="Chrome Extension to easily add the current web-page to detect a change."  title="Chrome Extension to easily add the current web-page to detect a change."  />](https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop)
 
-[Goto the Chrome Webstore to download the extension.](https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop)
+[Goto the Chrome Webstore to download the extension.](https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop) ( Or check out the [GitHub repo](https://github.com/dgtlmoon/changedetection.io-browser-extension) ) 
 
 ## Installation
 

changedetection.py

@@ -1,4 +1,4 @@
-#!/usr/bin/python3
+#!/usr/bin/env python3
 
 # Only exists for direct CLI usage
 

changedetectionio/__init__.py

@@ -1,8 +1,8 @@
-#!/usr/bin/python3
+#!/usr/bin/env python3
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
-__version__ = '0.46.00'
+__version__ = '0.49.4'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError
@@ -24,13 +24,15 @@ from loguru import logger
 app = None
 datastore = None
 
+def get_version():
+    return __version__
+
 # Parent wrapper or OS sends us a SIGTERM/SIGINT, do everything required for a clean shutdown
 def sigshutdown_handler(_signo, _stack_frame):
     global app
     global datastore
     name = signal.Signals(_signo).name
     logger.critical(f'Shutdown: Got Signal - {name} ({_signo}), Saving DB to disk and calling shutdown')
-    datastore.sync_to_json()
     logger.success('Sync JSON to disk complete.')
     # This will throw a SystemExit exception, because eventlet.wsgi.server doesn't know how to deal with it.
     # Solution: move to gevent or other server in the future (#2014)
@@ -160,11 +162,10 @@ def main():
                     )
 
     # Monitored websites will not receive a Referer header when a user clicks on an outgoing link.
-    # @Note: Incompatible with password login (and maybe other features) for now, submit a PR!
     @app.after_request
     def hide_referrer(response):
         if strtobool(os.getenv("HIDE_REFERER", 'false')):
-            response.headers["Referrer-Policy"] = "no-referrer"
+            response.headers["Referrer-Policy"] = "same-origin"
 
         return response
 

changedetectionio/api/api_schema.py

@@ -112,6 +112,35 @@ def build_watch_json_schema(d):
 
     schema['properties']['time_between_check'] = build_time_between_check_json_schema()
 
+    schema['properties']['browser_steps'] = {
+        "anyOf": [
+            {
+                "type": "array",
+                "items": {
+                    "type": "object",
+                    "properties": {
+                        "operation": {
+                            "type": ["string", "null"],
+                            "maxLength": 5000  # Allows null and any string up to 5000 chars (including "")
+                        },
+                        "selector": {
+                            "type": ["string", "null"],
+                            "maxLength": 5000
+                        },
+                        "optional_value": {
+                            "type": ["string", "null"],
+                            "maxLength": 5000
+                        }
+                    },
+                    "required": ["operation", "selector", "optional_value"],
+                    "additionalProperties": False  # No extra keys allowed
+                }
+            },
+            {"type": "null"},  # Allows null for `browser_steps`
+            {"type": "array", "maxItems": 0}  # Allows empty array []
+        ]
+    }
+
     # headers ?
     return schema
 

changedetectionio/api/api_v1.py

@@ -12,11 +12,10 @@ import copy
 # See docs/README.md for rebuilding the docs/apidoc information
 
 from . import api_schema
-from ..model import watch_base
+from ..model import schema as watch_schema
 
 # Build a JSON Schema atleast partially based on our Watch model
-watch_base_config = watch_base()
-schema = api_schema.build_watch_json_schema(watch_base_config)
+schema = api_schema.build_watch_json_schema(watch_schema)
 
 schema_create_watch = copy.deepcopy(schema)
 schema_create_watch['required'] = ['url']
@@ -53,12 +52,12 @@ class Watch(Resource):
         @apiSuccess (200) {JSON} WatchJSON JSON Full JSON object of the watch
         """
         from copy import deepcopy
-        watch = deepcopy(self.datastore.data['watching'].get(uuid))
+        watch = self.datastore.data['watching'].get(uuid)
         if not watch:
-            abort(404, message='No watch exists with the UUID of {}'.format(uuid))
+            abort(404, message=f'No watch exists with the UUID of {uuid}')
 
         if request.args.get('recheck'):
-            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
             return "OK", 200
         if request.args.get('paused', '') == 'paused':
             self.datastore.data['watching'].get(uuid).pause()
@@ -73,12 +72,16 @@ class Watch(Resource):
             self.datastore.data['watching'].get(uuid).unmute()
             return "OK", 200
 
-        # Return without history, get that via another API call
-        # Properties are not returned as a JSON, so add the required props manually
-        watch['history_n'] = watch.history_n
-        watch['last_changed'] = watch.last_changed
-        watch['viewed'] = watch.viewed
-        return watch
+
+        response = dict(watch.get_data())
+        
+        # Add properties that aren't included in the standard dictionary items (they are properties/attr)
+        response['history_n'] = watch.history_n
+        response['last_changed'] = watch.last_changed
+        response['viewed'] = watch.viewed
+        response['title'] = watch.get('title')
+        
+        return response
 
     @auth.check_token
     def delete(self, uuid):
@@ -113,16 +116,17 @@ class Watch(Resource):
         @apiSuccess (200) {String} OK Was updated
         @apiSuccess (500) {String} ERR Some other error
         """
-        watch = self.datastore.data['watching'].get(uuid)
-        if not watch:
-            abort(404, message='No watch exists with the UUID of {}'.format(uuid))
+
+        if not self.datastore.data['watching'].get(uuid):
+            abort(404, message=f'No watch exists with the UUID of {uuid}')
 
         if request.json.get('proxy'):
             plist = self.datastore.proxy_list
             if not request.json.get('proxy') in plist:
-                return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
+                return f"Invalid proxy choice, currently supported proxies are '{', '.join(plist)}'", 400
 
-        watch.update(request.json)
+        self.datastore.data['watching'][uuid].update(request.json)
+        self.datastore.data['watching'][uuid].save_data()
 
         return "OK", 200
 
@@ -246,7 +250,7 @@ class CreateWatch(Resource):
 
         new_uuid = self.datastore.add_watch(url=url, extras=extras, tag=tags)
         if new_uuid:
-            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
+            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
             return {'uuid': new_uuid}, 201
         else:
             return "Invalid or unsupported URL", 400
@@ -303,7 +307,7 @@ class CreateWatch(Resource):
 
         if request.args.get('recheck_all'):
             for uuid in self.datastore.data['watching'].keys():
-                self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+                self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
             return {'status': "OK"}, 200
 
         return list, 200

changedetectionio/apprise_asset.py

@@ -1,3 +1,4 @@
+from changedetectionio import apprise_plugin
 import apprise
 
 # Create our AppriseAsset and populate it with some of our new values:

changedetectionio/apprise_plugin/__init__.py

@@ -0,0 +1,98 @@
+# include the decorator
+from apprise.decorators import notify
+from loguru import logger
+from requests.structures import CaseInsensitiveDict
+
+
+@notify(on="delete")
+@notify(on="deletes")
+@notify(on="get")
+@notify(on="gets")
+@notify(on="post")
+@notify(on="posts")
+@notify(on="put")
+@notify(on="puts")
+def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
+    import requests
+    import json
+    import re
+
+    from urllib.parse import unquote_plus
+    from apprise.utils.parse import parse_url as apprise_parse_url
+
+    url = kwargs['meta'].get('url')
+    schema = kwargs['meta'].get('schema').lower().strip()
+
+    # Choose POST, GET etc from requests
+    method =  re.sub(rf's$', '', schema)
+    requests_method = getattr(requests, method)
+
+    params = CaseInsensitiveDict({}) # Added to requests
+    auth = None
+    has_error = False
+
+    # Convert /foobar?+some-header=hello to proper header dictionary
+    results = apprise_parse_url(url)
+
+    # Add our headers that the user can potentially over-ride if they wish
+    # to to our returned result set and tidy entries by unquoting them
+    headers = CaseInsensitiveDict({unquote_plus(x): unquote_plus(y)
+               for x, y in results['qsd+'].items()})
+
+    # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
+    # In Apprise, it relies on prefixing each request arg with "-", because it uses say &method=update as a flag for apprise
+    # but here we are making straight requests, so we need todo convert this against apprise's logic
+    for k, v in results['qsd'].items():
+        if not k.strip('+-') in results['qsd+'].keys():
+            params[unquote_plus(k)] = unquote_plus(v)
+
+    # Determine Authentication
+    auth = ''
+    if results.get('user') and results.get('password'):
+        auth = (unquote_plus(results.get('user')), unquote_plus(results.get('user')))
+    elif results.get('user'):
+        auth = (unquote_plus(results.get('user')))
+
+    # If it smells like it could be JSON and no content-type was already set, offer a default content type.
+    if body and '{' in body[:100] and not headers.get('Content-Type'):
+        json_header = 'application/json; charset=utf-8'
+        try:
+            # Try if it's JSON
+            json.loads(body)
+            headers['Content-Type'] = json_header
+        except ValueError as e:
+            logger.warning(f"Could not automatically add '{json_header}' header to the notification because the document failed to parse as JSON: {e}")
+            pass
+
+    # POSTS -> HTTPS etc
+    if schema.lower().endswith('s'):
+        url = re.sub(rf'^{schema}', 'https', results.get('url'))
+    else:
+        url = re.sub(rf'^{schema}', 'http', results.get('url'))
+
+    status_str = ''
+    try:
+        r = requests_method(url,
+          auth=auth,
+          data=body.encode('utf-8') if type(body) is str else body,
+          headers=headers,
+          params=params
+        )
+
+        if not (200 <= r.status_code < 300):
+            status_str = f"Error sending '{method.upper()}' request to {url} - Status: {r.status_code}: '{r.reason}'"
+            logger.error(status_str)
+            has_error = True
+        else:
+            logger.info(f"Sent '{method.upper()}' request to {url}")
+            has_error = False
+
+    except requests.RequestException as e:
+        status_str = f"Error sending '{method.upper()}' request to {url} - {str(e)}"
+        logger.error(status_str)
+        has_error = True
+
+    if has_error:
+        raise TypeError(status_str)
+
+    return True

changedetectionio/auth_decorator.py

@@ -0,0 +1,36 @@
+import os
+from functools import wraps
+from flask import current_app, redirect, request
+from loguru import logger
+
+def login_optionally_required(func):
+    """
+    If password authentication is enabled, verify the user is logged in.
+    To be used as a decorator for routes that should optionally require login.
+    This version is blueprint-friendly as it uses current_app instead of directly accessing app.
+    """
+    @wraps(func)
+    def decorated_view(*args, **kwargs):
+        from flask import current_app
+        import flask_login
+        from flask_login import current_user
+
+        # Access datastore through the app config
+        datastore = current_app.config['DATASTORE']
+        has_password_enabled = datastore.data['settings']['application'].get('password') or os.getenv("SALTED_PASS", False)
+
+        # Permitted
+        if request.endpoint and 'static_content' in request.endpoint and request.view_args and request.view_args.get('group') == 'styles':
+            return func(*args, **kwargs)
+        # Permitted
+        elif request.endpoint and 'diff_history_page' in request.endpoint and datastore.data['settings']['application'].get('shared_diff_access'):
+            return func(*args, **kwargs)
+        elif request.method in flask_login.config.EXEMPT_METHODS:
+            return func(*args, **kwargs)
+        elif current_app.config.get('LOGIN_DISABLED'):
+            return func(*args, **kwargs)
+        elif has_password_enabled and not current_user.is_authenticated:
+            return current_app.login_manager.unauthorized()
+
+        return func(*args, **kwargs)
+    return decorated_view

changedetectionio/blueprint/backups/__init__.py

@@ -0,0 +1,162 @@
+import datetime
+import glob
+import threading
+
+from flask import Blueprint, render_template, send_from_directory, flash, url_for, redirect, abort
+import os
+
+from changedetectionio.store import ChangeDetectionStore
+from changedetectionio.flask_app import login_optionally_required
+from loguru import logger
+
+BACKUP_FILENAME_FORMAT = "changedetection-backup-{}.zip"
+
+
+def create_backup(datastore_path, watches: dict):
+    logger.debug("Creating backup...")
+    import zipfile
+    from pathlib import Path
+
+    # create a ZipFile object
+    timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
+    backupname = BACKUP_FILENAME_FORMAT.format(timestamp)
+    backup_filepath = os.path.join(datastore_path, backupname)
+
+    with zipfile.ZipFile(backup_filepath.replace('.zip', '.tmp'), "w",
+                         compression=zipfile.ZIP_DEFLATED,
+                         compresslevel=8) as zipObj:
+
+        # Add the index
+        zipObj.write(os.path.join(datastore_path, "url-watches.json"), arcname="url-watches.json")
+
+        # Add the flask app secret
+        zipObj.write(os.path.join(datastore_path, "secret.txt"), arcname="secret.txt")
+
+        # Add any data in the watch data directory.
+        for uuid, w in watches.items():
+            for f in Path(w.watch_data_dir).glob('*'):
+                zipObj.write(f,
+                             # Use the full path to access the file, but make the file 'relative' in the Zip.
+                             arcname=os.path.join(f.parts[-2], f.parts[-1]),
+                             compress_type=zipfile.ZIP_DEFLATED,
+                             compresslevel=8)
+
+        # Create a list file with just the URLs, so it's easier to port somewhere else in the future
+        list_file = "url-list.txt"
+        with open(os.path.join(datastore_path, list_file), "w") as f:
+            for uuid in watches:
+                url = watches[uuid]["url"]
+                f.write("{}\r\n".format(url))
+        list_with_tags_file = "url-list-with-tags.txt"
+        with open(
+                os.path.join(datastore_path, list_with_tags_file), "w"
+        ) as f:
+            for uuid in watches:
+                url = watches[uuid].get('url')
+                tag = watches[uuid].get('tags', {})
+                f.write("{} {}\r\n".format(url, tag))
+
+        # Add it to the Zip
+        zipObj.write(
+            os.path.join(datastore_path, list_file),
+            arcname=list_file,
+            compress_type=zipfile.ZIP_DEFLATED,
+            compresslevel=8,
+        )
+        zipObj.write(
+            os.path.join(datastore_path, list_with_tags_file),
+            arcname=list_with_tags_file,
+            compress_type=zipfile.ZIP_DEFLATED,
+            compresslevel=8,
+        )
+
+    # Now it's done, rename it so it shows up finally and its completed being written.
+    os.rename(backup_filepath.replace('.zip', '.tmp'), backup_filepath.replace('.tmp', '.zip'))
+
+
+def construct_blueprint(datastore: ChangeDetectionStore):
+    backups_blueprint = Blueprint('backups', __name__, template_folder="templates")
+    backup_threads = []
+
+    @login_optionally_required
+    @backups_blueprint.route("/request-backup", methods=['GET'])
+    def request_backup():
+        if any(thread.is_alive() for thread in backup_threads):
+            flash("A backup is already running, check back in a few minutes", "error")
+            return redirect(url_for('backups.index'))
+
+        if len(find_backups()) > int(os.getenv("MAX_NUMBER_BACKUPS", 100)):
+            flash("Maximum number of backups reached, please remove some", "error")
+            return redirect(url_for('backups.index'))
+
+        zip_thread = threading.Thread(target=create_backup, args=(datastore.datastore_path, datastore.data.get("watching")))
+        zip_thread.start()
+        backup_threads.append(zip_thread)
+        flash("Backup building in background, check back in a few minutes.")
+
+        return redirect(url_for('backups.index'))
+
+    def find_backups():
+        backup_filepath = os.path.join(datastore.datastore_path, BACKUP_FILENAME_FORMAT.format("*"))
+        backups = glob.glob(backup_filepath)
+        backup_info = []
+
+        for backup in backups:
+            size = os.path.getsize(backup) / (1024 * 1024)
+            creation_time = os.path.getctime(backup)
+            backup_info.append({
+                'filename': os.path.basename(backup),
+                'filesize': f"{size:.2f}",
+                'creation_time': creation_time
+            })
+
+        backup_info.sort(key=lambda x: x['creation_time'], reverse=True)
+
+        return backup_info
+
+    @login_optionally_required
+    @backups_blueprint.route("/download/<string:filename>", methods=['GET'])
+    def download_backup(filename):
+        import re
+        filename = filename.strip()
+        backup_filename_regex = BACKUP_FILENAME_FORMAT.format("\d+")
+
+        full_path = os.path.join(os.path.abspath(datastore.datastore_path), filename)
+        if not full_path.startswith(os.path.abspath(datastore.datastore_path)):
+            abort(404)
+
+        if filename == 'latest':
+            backups = find_backups()
+            filename = backups[0]['filename']
+
+        if not re.match(r"^" + backup_filename_regex + "$", filename):
+            abort(400)  # Bad Request if the filename doesn't match the pattern
+
+        logger.debug(f"Backup download request for '{full_path}'")
+        return send_from_directory(os.path.abspath(datastore.datastore_path), filename, as_attachment=True)
+
+    @login_optionally_required
+    @backups_blueprint.route("/", methods=['GET'])
+    def index():
+        backups = find_backups()
+        output = render_template("overview.html",
+                                 available_backups=backups,
+                                 backup_running=any(thread.is_alive() for thread in backup_threads)
+                                 )
+
+        return output
+
+    @login_optionally_required
+    @backups_blueprint.route("/remove-backups", methods=['GET'])
+    def remove_backups():
+
+        backup_filepath = os.path.join(datastore.datastore_path, BACKUP_FILENAME_FORMAT.format("*"))
+        backups = glob.glob(backup_filepath)
+        for backup in backups:
+            os.unlink(backup)
+
+        flash("Backups were deleted.")
+
+        return redirect(url_for('backups.index'))
+
+    return backups_blueprint

changedetectionio/blueprint/backups/templates/overview.html

@@ -0,0 +1,36 @@
+{% extends 'base.html' %}
+{% block content %}
+    {% from '_helpers.html' import render_simple_field, render_field %}
+    <div class="edit-form">
+        <div class="box-wrap inner">
+            <h4>Backups</h4>
+            {% if backup_running %}
+                <p>
+                    <strong>A backup is running!</strong>
+                </p>
+            {% endif %}
+            <p>
+                Here you can download and request a new backup, when a backup is completed you will see it listed below.
+            </p>
+            <br>
+                {% if available_backups %}
+                    <ul>
+                    {% for backup in available_backups %}
+                        <li><a href="{{ url_for('backups.download_backup', filename=backup["filename"]) }}">{{ backup["filename"] }}</a> {{  backup["filesize"] }} Mb</li>
+                    {% endfor %}
+                    </ul>
+                {% else %}
+                    <p>
+                    <strong>No backups found.</strong>
+                    </p>
+                {% endif %}
+
+            <a class="pure-button pure-button-primary" href="{{ url_for('backups.request_backup') }}">Create backup</a>
+            {% if available_backups %}
+                <a class="pure-button button-small button-error " href="{{ url_for('backups.remove_backups') }}">Remove backups</a>
+            {% endif %}
+        </div>
+    </div>
+
+
+{% endblock %}

changedetectionio/blueprint/browser_steps/__init__.py

@@ -22,7 +22,10 @@ from loguru import logger
 
 browsersteps_sessions = {}
 io_interface_context = None
-
+import json
+import base64
+import hashlib
+from flask import Response
 
 def construct_blueprint(datastore: ChangeDetectionStore):
     browser_steps_blueprint = Blueprint('browser_steps', __name__, template_folder="templates")
@@ -85,7 +88,8 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         browsersteps_start_session['browserstepper'] = browser_steps.browsersteps_live_ui(
             playwright_browser=browsersteps_start_session['browser'],
             proxy=proxy,
-            start_url=datastore.data['watching'][watch_uuid].get('url')
+            start_url=datastore.data['watching'][watch_uuid].link,
+            headers=datastore.data['watching'][watch_uuid].get('headers')
         )
 
         # For test
@@ -159,14 +163,13 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         if not browsersteps_sessions.get(browsersteps_session_id):
             return make_response('No session exists under that ID', 500)
 
-
+        is_last_step = False
         # Actions - step/apply/etc, do the thing and return state
         if request.method == 'POST':
             # @todo - should always be an existing session
             step_operation = request.form.get('operation')
             step_selector = request.form.get('selector')
             step_optional_value = request.form.get('optional_value')
-            step_n = int(request.form.get('step_n'))
             is_last_step = strtobool(request.form.get('is_last_step'))
 
             # @todo try.. accept.. nice errors not popups..
@@ -181,16 +184,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                 # Try to find something of value to give back to the user
                 return make_response(str(e).splitlines()[0], 401)
 
-            # Get visual selector ready/update its data (also use the current filter info from the page?)
-            # When the last 'apply' button was pressed
-            # @todo this adds overhead because the xpath selection is happening twice
-            u = browsersteps_sessions[browsersteps_session_id]['browserstepper'].page.url
-            if is_last_step and u:
-                (screenshot, xpath_data) = browsersteps_sessions[browsersteps_session_id]['browserstepper'].request_visualselector_data()
-                watch = datastore.data['watching'].get(uuid)
-                if watch:
-                    watch.save_screenshot(screenshot=screenshot)
-                    watch.save_xpath_data(data=xpath_data)
 
 #        if not this_session.page:
 #            cleanup_playwright_session()
@@ -198,31 +191,35 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
         # Screenshots and other info only needed on requesting a step (POST)
         try:
-            state = browsersteps_sessions[browsersteps_session_id]['browserstepper'].get_current_state()
+            (screenshot, xpath_data) = browsersteps_sessions[browsersteps_session_id]['browserstepper'].get_current_state()
+            if is_last_step:
+                watch = datastore.data['watching'].get(uuid)
+                u = browsersteps_sessions[browsersteps_session_id]['browserstepper'].page.url
+                if watch and u:
+                    watch.save_screenshot(screenshot=screenshot)
+                    watch.save_xpath_data(data=xpath_data)
+
         except playwright._impl._api_types.Error as e:
             return make_response("Browser session ran out of time :( Please reload this page."+str(e), 401)
+        except Exception as e:
+            return make_response("Error fetching screenshot and element data - " + str(e), 401)
 
-        # Use send_file() which is way faster than read/write loop on bytes
-        import json
-        from tempfile import mkstemp
-        from flask import send_file
-        tmp_fd, tmp_file = mkstemp(text=True, suffix=".json", prefix="changedetectionio-")
+        # SEND THIS BACK TO THE BROWSER
 
-        output = json.dumps({'screenshot': "data:image/jpeg;base64,{}".format(
-            base64.b64encode(state[0]).decode('ascii')),
-            'xpath_data': state[1],
-            'session_age_start': browsersteps_sessions[browsersteps_session_id]['browserstepper'].age_start,
-            'browser_time_remaining': round(remaining)
-        })
+        output = {
+            "screenshot": f"data:image/jpeg;base64,{base64.b64encode(screenshot).decode('ascii')}",
+            "xpath_data": xpath_data,
+            "session_age_start": browsersteps_sessions[browsersteps_session_id]['browserstepper'].age_start,
+            "browser_time_remaining": round(remaining)
+        }
+        json_data = json.dumps(output)
 
-        with os.fdopen(tmp_fd, 'w') as f:
-            f.write(output)
+        # Generate an ETag (hash of the response body)
+        etag_hash = hashlib.md5(json_data.encode('utf-8')).hexdigest()
 
-        response = make_response(send_file(path_or_file=tmp_file,
-                                           mimetype='application/json; charset=UTF-8',
-                                           etag=True))
-        # No longer needed
-        os.unlink(tmp_file)
+        # Create the response with ETag
+        response = Response(json_data, mimetype="application/json; charset=UTF-8")
+        response.set_etag(etag_hash)
 
         return response
 

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -1,14 +1,15 @@
-#!/usr/bin/python3
-
 import os
 import time
 import re
 from random import randint
 from loguru import logger
 
+from changedetectionio.content_fetchers.helpers import capture_stitched_together_full_page, SCREENSHOT_SIZE_STITCH_THRESHOLD
 from changedetectionio.content_fetchers.base import manage_user_agent
 from changedetectionio.safe_jinja import render as jinja_render
 
+
+
 # Two flags, tell the JS which of the "Selector" or "Value" field should be enabled in the front end
 # 0- off, 1- on
 browser_step_ui_config = {'Choose one': '0 0',
@@ -25,11 +26,13 @@ browser_step_ui_config = {'Choose one': '0 0',
                           'Click element if exists': '1 0',
                           'Click element': '1 0',
                           'Click element containing text': '0 1',
+                          'Click element containing text if exists': '0 1',
                           'Enter text in field': '1 1',
                           'Execute JS': '0 1',
 #                          'Extract text and use as filter': '1 0',
                           'Goto site': '0 0',
                           'Goto URL': '0 1',
+                          'Make all child elements visible': '1 0',
                           'Press Enter': '0 0',
                           'Select by label': '1 1',
                           'Scroll down': '0 0',
@@ -37,6 +40,7 @@ browser_step_ui_config = {'Choose one': '0 0',
                           'Wait for seconds': '0 1',
                           'Wait for text': '0 1',
                           'Wait for text in element': '1 1',
+                          'Remove elements': '1 0',
                           #                          'Press Page Down': '0 0',
                           #                          'Press Page Up': '0 0',
                           # weird bug, come back to it later
@@ -51,6 +55,8 @@ class steppable_browser_interface():
     page = None
     start_url = None
 
+    action_timeout = 10 * 1000
+
     def __init__(self, start_url):
         self.start_url = start_url
 
@@ -96,17 +102,29 @@ class steppable_browser_interface():
         return self.action_goto_url(value=self.start_url)
 
     def action_click_element_containing_text(self, selector=None, value=''):
+        logger.debug("Clicking element containing text")
         if not len(value.strip()):
             return
         elem = self.page.get_by_text(value)
         if elem.count():
-            elem.first.click(delay=randint(200, 500), timeout=3000)
+            elem.first.click(delay=randint(200, 500), timeout=self.action_timeout)
+
+    def action_click_element_containing_text_if_exists(self, selector=None, value=''):
+        logger.debug("Clicking element containing text if exists")
+        if not len(value.strip()):
+            return
+        elem = self.page.get_by_text(value)
+        logger.debug(f"Clicking element containing text - {elem.count()} elements found")
+        if elem.count():
+            elem.first.click(delay=randint(200, 500), timeout=self.action_timeout)
+        else:
+            return
 
     def action_enter_text_in_field(self, selector, value):
         if not len(selector.strip()):
             return
 
-        self.page.fill(selector, value, timeout=10 * 1000)
+        self.page.fill(selector, value, timeout=self.action_timeout)
 
     def action_execute_js(self, selector, value):
         response = self.page.evaluate(value)
@@ -117,7 +135,7 @@ class steppable_browser_interface():
         if not len(selector.strip()):
             return
 
-        self.page.click(selector=selector, timeout=30 * 1000, delay=randint(200, 500))
+        self.page.click(selector=selector, timeout=self.action_timeout + 20 * 1000, delay=randint(200, 500))
 
     def action_click_element_if_exists(self, selector, value):
         import playwright._impl._errors as _api_types
@@ -125,7 +143,7 @@ class steppable_browser_interface():
         if not len(selector.strip()):
             return
         try:
-            self.page.click(selector, timeout=10 * 1000, delay=randint(200, 500))
+            self.page.click(selector, timeout=self.action_timeout, delay=randint(200, 500))
         except _api_types.TimeoutError as e:
             return
         except _api_types.Error as e:
@@ -172,11 +190,29 @@ class steppable_browser_interface():
         self.page.keyboard.press("PageDown", delay=randint(200, 500))
 
     def action_check_checkbox(self, selector, value):
-        self.page.locator(selector).check(timeout=1000)
+        self.page.locator(selector).check(timeout=self.action_timeout)
 
     def action_uncheck_checkbox(self, selector, value):
-        self.page.locator(selector, timeout=1000).uncheck(timeout=1000)
+        self.page.locator(selector).uncheck(timeout=self.action_timeout)
 
+    def action_remove_elements(self, selector, value):
+        """Removes all elements matching the given selector from the DOM."""
+        self.page.locator(selector).evaluate_all("els => els.forEach(el => el.remove())")
+
+    def action_make_all_child_elements_visible(self, selector, value):
+        """Recursively makes all child elements inside the given selector fully visible."""
+        self.page.locator(selector).locator("*").evaluate_all("""
+            els => els.forEach(el => {
+                el.style.display = 'block';   // Forces it to be displayed
+                el.style.visibility = 'visible';   // Ensures it's not hidden
+                el.style.opacity = '1';   // Fully opaque
+                el.style.position = 'relative';   // Avoids 'absolute' hiding
+                el.style.height = 'auto';   // Expands collapsed elements
+                el.style.width = 'auto';   // Ensures full visibility
+                el.removeAttribute('hidden');   // Removes hidden attribute
+                el.classList.remove('hidden', 'd-none');  // Removes common CSS hidden classes
+            })
+        """)
 
 # Responsible for maintaining a live 'context' with the chrome CDP
 # @todo - how long do contexts live for anyway?
@@ -244,6 +280,7 @@ class browsersteps_live_ui(steppable_browser_interface):
         logger.debug(f"Time to browser setup {time.time()-now:.2f}s")
         self.page.wait_for_timeout(1 * 1000)
 
+
     def mark_as_closed(self):
         logger.debug("Page closed, cleaning up..")
 
@@ -261,39 +298,30 @@ class browsersteps_live_ui(steppable_browser_interface):
         now = time.time()
         self.page.wait_for_timeout(1 * 1000)
 
-        # The actual screenshot
-        screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=40)
 
+        full_height = self.page.evaluate("document.documentElement.scrollHeight")
+
+        if full_height >= SCREENSHOT_SIZE_STITCH_THRESHOLD:
+            logger.warning(f"Page full Height: {full_height}px longer than {SCREENSHOT_SIZE_STITCH_THRESHOLD}px, using 'stitched screenshot method'.")
+            screenshot = capture_stitched_together_full_page(self.page)
+        else:
+            screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=40)
+
+        logger.debug(f"Time to get screenshot from browser {time.time() - now:.2f}s")
+
+        now = time.time()
         self.page.evaluate("var include_filters=''")
         # Go find the interactive elements
         # @todo in the future, something smarter that can scan for elements with .click/focus etc event handlers?
         elements = 'a,button,input,select,textarea,i,th,td,p,li,h1,h2,h3,h4,div,span'
         xpath_element_js = xpath_element_js.replace('%ELEMENTS%', elements)
+
         xpath_data = self.page.evaluate("async () => {" + xpath_element_js + "}")
         # So the JS will find the smallest one first
         xpath_data['size_pos'] = sorted(xpath_data['size_pos'], key=lambda k: k['width'] * k['height'], reverse=True)
-        logger.debug(f"Time to complete get_current_state of browser {time.time()-now:.2f}s")
-        # except
+        logger.debug(f"Time to scrape xpath element data in browser {time.time()-now:.2f}s")
+
         # playwright._impl._api_types.Error: Browser closed.
         # @todo show some countdown timer?
         return (screenshot, xpath_data)
 
-    def request_visualselector_data(self):
-        """
-        Does the same that the playwright operation in content_fetcher does
-        This is used to just bump the VisualSelector data so it' ready to go if they click on the tab
-        @todo refactor and remove duplicate code, add include_filters
-        :param xpath_data:
-        :param screenshot:
-        :param current_include_filters:
-        :return:
-        """
-        import importlib.resources
-        self.page.evaluate("var include_filters=''")
-        xpath_element_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text()
-        from changedetectionio.content_fetchers import visualselector_xpath_selectors
-        xpath_element_js = xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors)
-        xpath_data = self.page.evaluate("async () => {" + xpath_element_js + "}")
-        screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("SCREENSHOT_QUALITY", 72)))
-
-        return (screenshot, xpath_data)

changedetectionio/blueprint/check_proxies/__init__.py

@@ -1,4 +1,7 @@
+import importlib
 from concurrent.futures import ThreadPoolExecutor
+
+from changedetectionio.processors.text_json_diff.processor import FilterNotFoundInResponse
 from changedetectionio.store import ChangeDetectionStore
 
 from functools import wraps
@@ -30,7 +33,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     def long_task(uuid, preferred_proxy):
         import time
         from changedetectionio.content_fetchers import exceptions as content_fetcher_exceptions
-        from changedetectionio.processors.text_json_diff import text_json_diff
         from changedetectionio.safe_jinja import render as jinja_render
 
         status = {'status': '', 'length': 0, 'text': ''}
@@ -38,8 +40,12 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         contents = ''
         now = time.time()
         try:
-            update_handler = text_json_diff.perform_site_check(datastore=datastore, watch_uuid=uuid)
-            update_handler.call_browser()
+            processor_module = importlib.import_module("changedetectionio.processors.text_json_diff.processor")
+            update_handler = processor_module.perform_site_check(datastore=datastore,
+                                                                 watch_uuid=uuid
+                                                                 )
+
+            update_handler.call_browser(preferred_proxy_id=preferred_proxy)
         # title, size is len contents not len xfer
         except content_fetcher_exceptions.Non200ErrorCodeReceived as e:
             if e.status_code == 404:
@@ -48,7 +54,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                 status.update({'status': 'ERROR', 'length': len(contents), 'text': f"{e.status_code} - Access denied"})
             else:
                 status.update({'status': 'ERROR', 'length': len(contents), 'text': f"Status code: {e.status_code}"})
-        except text_json_diff.FilterNotFoundInResponse:
+        except FilterNotFoundInResponse:
             status.update({'status': 'OK', 'length': len(contents), 'text': f"OK but CSS/xPath filter not found (page changed layout?)"})
         except content_fetcher_exceptions.EmptyReply as e:
             if e.status_code == 403 or e.status_code == 401:

changedetectionio/blueprint/imports/__init__.py

@@ -0,0 +1,74 @@
+from flask import Blueprint, request, redirect, url_for, flash, render_template
+from changedetectionio.store import ChangeDetectionStore
+from changedetectionio.auth_decorator import login_optionally_required
+from changedetectionio.blueprint.imports.importer import (
+    import_url_list, 
+    import_distill_io_json, 
+    import_xlsx_wachete, 
+    import_xlsx_custom
+)
+
+def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMetaData):
+    import_blueprint = Blueprint('imports', __name__, template_folder="templates")
+    
+    @import_blueprint.route("/import", methods=['GET', 'POST'])
+    @login_optionally_required
+    def import_page():
+        remaining_urls = []
+        from changedetectionio import forms
+
+        if request.method == 'POST':
+            # URL List import
+            if request.values.get('urls') and len(request.values.get('urls').strip()):
+                # Import and push into the queue for immediate update check
+                importer_handler = import_url_list()
+                importer_handler.run(data=request.values.get('urls'), flash=flash, datastore=datastore, processor=request.values.get('processor', 'text_json_diff'))
+                for uuid in importer_handler.new_uuids:
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+
+                if len(importer_handler.remaining_data) == 0:
+                    return redirect(url_for('index'))
+                else:
+                    remaining_urls = importer_handler.remaining_data
+
+            # Distill.io import
+            if request.values.get('distill-io') and len(request.values.get('distill-io').strip()):
+                # Import and push into the queue for immediate update check
+                d_importer = import_distill_io_json()
+                d_importer.run(data=request.values.get('distill-io'), flash=flash, datastore=datastore)
+                for uuid in d_importer.new_uuids:
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+
+            # XLSX importer
+            if request.files and request.files.get('xlsx_file'):
+                file = request.files['xlsx_file']
+
+                if request.values.get('file_mapping') == 'wachete':
+                    w_importer = import_xlsx_wachete()
+                    w_importer.run(data=file, flash=flash, datastore=datastore)
+                else:
+                    w_importer = import_xlsx_custom()
+                    # Building mapping of col # to col # type
+                    map = {}
+                    for i in range(10):
+                        c = request.values.get(f"custom_xlsx[col_{i}]")
+                        v = request.values.get(f"custom_xlsx[col_type_{i}]")
+                        if c and v:
+                            map[int(c)] = v
+
+                    w_importer.import_profile = map
+                    w_importer.run(data=file, flash=flash, datastore=datastore)
+
+                for uuid in w_importer.new_uuids:
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+
+        # Could be some remaining, or we could be on GET
+        form = forms.importForm(formdata=request.form if request.method == 'POST' else None, datastore=datastore)
+        output = render_template("import.html",
+                                form=form,
+                                import_url_list_remaining="\n".join(remaining_urls),
+                                original_distill_json=''
+                                )
+        return output
+
+    return import_blueprint

changedetectionio/blueprint/imports/importer.py

@@ -1,10 +1,8 @@
-from abc import ABC, abstractmethod
+from abc import abstractmethod
 import time
-import validators
 from wtforms import ValidationError
 from loguru import logger
 
-from changedetectionio.forms import validate_url
 
 
 class Importer():
@@ -152,6 +150,7 @@ class import_xlsx_wachete(Importer):
         self.new_uuids = []
 
         from openpyxl import load_workbook
+        from changedetectionio.forms import validate_url
 
         try:
             wb = load_workbook(data)
@@ -241,7 +240,7 @@ class import_xlsx_custom(Importer):
             return
 
         # @todo cehck atleast 2 rows, same in other method
-        from .forms import validate_url
+        from changedetectionio.forms import validate_url
         row_i = 1
 
         try:
@@ -300,4 +299,4 @@ class import_xlsx_custom(Importer):
             row_i += 1
 
         flash(
-            "{} imported from custom .xlsx in {:.2f}s".format(len(self.new_uuids), time.time() - now))
+            "{} imported from custom .xlsx in {:.2f}s".format(len(self.new_uuids), time.time() - now))

changedetectionio/blueprint/imports/templates/import.html

@@ -0,0 +1,125 @@
+{% extends 'base.html' %}
+{% block content %}
+{% from '_helpers.html' import render_field %}
+<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<div class="edit-form monospaced-textarea">
+
+    <div class="tabs collapsable">
+        <ul>
+            <li class="tab" id=""><a href="#url-list">URL List</a></li>
+            <li class="tab"><a href="#distill-io">Distill.io</a></li>
+            <li class="tab"><a href="#xlsx">.XLSX &amp; Wachete</a></li>
+        </ul>
+    </div>
+
+    <div class="box-wrap inner">
+        <form class="pure-form" action="{{url_for('imports.import_page')}}" method="POST" enctype="multipart/form-data">
+            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
+            <div class="tab-pane-inner" id="url-list">
+                    <legend>
+                        Enter one URL per line, and optionally add tags for each URL after a space, delineated by comma
+                        (,):
+                        <br>
+                        <code>https://example.com tag1, tag2, last tag</code>
+                        <br>
+                        URLs which do not pass validation will stay in the textarea.
+                    </legend>
+                {{ render_field(form.processor, class="processor") }}
+
+                    <textarea name="urls" class="pure-input-1-2" placeholder="https://"
+                              style="width: 100%;
+                                font-family:monospace;
+                                white-space: pre;
+                                overflow-wrap: normal;
+                                overflow-x: scroll;" rows="25">{{ import_url_list_remaining }}</textarea>
+
+<div id="quick-watch-processor-type">
+
+                    </div>
+
+            </div>
+
+            <div class="tab-pane-inner" id="distill-io">
+
+
+
+                    <legend>
+                        Copy and Paste your Distill.io watch 'export' file, this should be a JSON file.<br>
+                        This is <i>experimental</i>, supported fields are <code>name</code>, <code>uri</code>, <code>tags</code>, <code>config:selections</code>, the rest (including <code>schedule</code>) are ignored.
+                        <br>
+                        <p>
+                        How to export? <a href="https://distill.io/docs/web-monitor/how-export-and-import-monitors/">https://distill.io/docs/web-monitor/how-export-and-import-monitors/</a><br>
+                        Be sure to set your default fetcher to Chrome if required.<br>
+                        </p>
+                    </legend>
+
+
+                    <textarea name="distill-io" class="pure-input-1-2" style="width: 100%;
+                                font-family:monospace;
+                                white-space: pre;
+                                overflow-wrap: normal;
+                                overflow-x: scroll;" placeholder="Example Distill.io JSON export file
+
+{
+    &quot;client&quot;: {
+        &quot;local&quot;: 1
+    },
+    &quot;data&quot;: [
+        {
+            &quot;name&quot;: &quot;Unraid | News&quot;,
+            &quot;uri&quot;: &quot;https://unraid.net/blog&quot;,
+            &quot;config&quot;: &quot;{\&quot;selections\&quot;:[{\&quot;frames\&quot;:[{\&quot;index\&quot;:0,\&quot;excludes\&quot;:[],\&quot;includes\&quot;:[{\&quot;type\&quot;:\&quot;xpath\&quot;,\&quot;expr\&quot;:\&quot;(//div[@id='App']/div[contains(@class,'flex')]/main[contains(@class,'relative')]/section[contains(@class,'relative')]/div[@class='container']/div[contains(@class,'flex')]/div[contains(@class,'w-full')])[1]\&quot;}]}],\&quot;dynamic\&quot;:true,\&quot;delay\&quot;:2}],\&quot;ignoreEmptyText\&quot;:true,\&quot;includeStyle\&quot;:false,\&quot;dataAttr\&quot;:\&quot;text\&quot;}&quot;,
+            &quot;tags&quot;: [],
+            &quot;content_type&quot;: 2,
+            &quot;state&quot;: 40,
+            &quot;schedule&quot;: &quot;{\&quot;type\&quot;:\&quot;INTERVAL\&quot;,\&quot;params\&quot;:{\&quot;interval\&quot;:4447}}&quot;,
+            &quot;ts&quot;: &quot;2022-03-27T15:51:15.667Z&quot;
+        }
+    ]
+}
+" rows="25">{{ original_distill_json }}</textarea>
+
+            </div>
+            <div class="tab-pane-inner" id="xlsx">
+            <fieldset>
+                <div class="pure-control-group">
+                {{ render_field(form.xlsx_file, class="processor") }}
+                </div>
+                <div class="pure-control-group">
+                    {{ render_field(form.file_mapping, class="processor") }}
+                </div>
+            </fieldset>
+                <div class="pure-control-group">
+                <span class="pure-form-message-inline">
+                    Table of custom column and data types mapping for the <strong>Custom mapping</strong> File mapping type.
+                </span>
+                    <table style="border: 1px solid #aaa; padding: 0.5rem; border-radius: 4px;">
+                        <tr>
+                            <td><strong>Column #</strong></td>
+                            {% for n in range(4) %}
+                                <td><input type="number" name="custom_xlsx[col_{{n}}]" style="width: 4rem;" min="1"></td>
+                            {%  endfor %}
+                        </tr>
+                        <tr>
+                            <td><strong>Type</strong></td>
+                            {% for n in range(4) %}
+                                <td><select name="custom_xlsx[col_type_{{n}}]">
+                                    <option value="" style="color: #aaa"> -- none --</option>
+                                    <option value="url">URL</option>
+                                    <option value="title">Title</option>
+                                    <option value="include_filters">CSS/xPath filter</option>
+                                    <option value="tag">Group / Tag name(s)</option>
+                                    <option value="interval_minutes">Recheck time (minutes)</option>
+                                </select></td>
+                            {%  endfor %}
+                        </tr>
+                    </table>
+                </div>
+            </div>
+            <button type="submit" class="pure-button pure-input-1-2 pure-button-primary">Import</button>
+        </form>
+
+    </div>
+</div>
+
+{% endblock %}

changedetectionio/blueprint/price_data_follower/__init__.py

@@ -1,25 +1,28 @@
 
-from changedetectionio.strtobool import strtobool
 from flask import Blueprint, flash, redirect, url_for
 from flask_login import login_required
-from changedetectionio.store import ChangeDetectionStore
-from changedetectionio import queuedWatchMetaData
 from queue import PriorityQueue
+from changedetectionio import queuedWatchMetaData
+from changedetectionio.processors.constants import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
 
-PRICE_DATA_TRACK_ACCEPT = 'accepted'
-PRICE_DATA_TRACK_REJECT = 'rejected'
 
-def construct_blueprint(datastore: ChangeDetectionStore, update_q: PriorityQueue):
+def construct_blueprint(datastore, update_q: PriorityQueue):
 
     price_data_follower_blueprint = Blueprint('price_data_follower', __name__)
-
     @login_required
     @price_data_follower_blueprint.route("/<string:uuid>/accept", methods=['GET'])
     def accept(uuid):
+
+        old_data = datastore.data['watching'][uuid].get_data()
+
+        datastore.data['watching'][uuid] = datastore.rehydrate_entity(default_dict=old_data, processor_override='restock_diff')
         datastore.data['watching'][uuid]['track_ldjson_price_data'] = PRICE_DATA_TRACK_ACCEPT
         datastore.data['watching'][uuid]['processor'] = 'restock_diff'
         datastore.data['watching'][uuid].clear_watch()
-        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
+
+        # Queue the watch for updating
+        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+
         return redirect(url_for("index"))
 
     @login_required

changedetectionio/blueprint/price_data_follower/flags.py

@@ -0,0 +1,3 @@
+
+PRICE_DATA_TRACK_ACCEPT = 'accepted'
+PRICE_DATA_TRACK_REJECT = 'rejected'

changedetectionio/blueprint/rss/__init__.py

@@ -0,0 +1,103 @@
+import time
+import datetime
+import pytz
+from flask import Blueprint, make_response, request, url_for
+from loguru import logger
+from feedgen.feed import FeedGenerator
+
+from changedetectionio.store import ChangeDetectionStore
+from changedetectionio.safe_jinja import render as jinja_render
+
+def construct_blueprint(datastore: ChangeDetectionStore):
+    rss_blueprint = Blueprint('rss', __name__)
+    
+    # Import the login decorator if needed
+    # from changedetectionio.auth_decorator import login_optionally_required
+
+    @rss_blueprint.route("/", methods=['GET'])
+    def feed():
+        now = time.time()
+        # Always requires token set
+        app_rss_token = datastore.data['settings']['application'].get('rss_access_token')
+        rss_url_token = request.args.get('token')
+        if rss_url_token != app_rss_token:
+            return "Access denied, bad token", 403
+
+        from changedetectionio import diff
+        limit_tag = request.args.get('tag', '').lower().strip()
+        # Be sure limit_tag is a uuid
+        for uuid, tag in datastore.data['settings']['application'].get('tags', {}).items():
+            if limit_tag == tag.get('title', '').lower().strip():
+                limit_tag = uuid
+
+        # Sort by last_changed and add the uuid which is usually the key..
+        sorted_watches = []
+
+        # @todo needs a .itemsWithTag() or something - then we can use that in Jinaj2 and throw this away
+        for uuid, watch in datastore.data['watching'].items():
+            # @todo tag notification_muted skip also (improve Watch model)
+            if datastore.data['settings']['application'].get('rss_hide_muted_watches') and watch.get('notification_muted'):
+                continue
+            if limit_tag and not limit_tag in watch['tags']:
+                continue
+            watch['uuid'] = uuid
+            sorted_watches.append(watch)
+
+        sorted_watches.sort(key=lambda x: x.last_changed, reverse=False)
+
+        fg = FeedGenerator()
+        fg.title('changedetection.io')
+        fg.description('Feed description')
+        fg.link(href='https://changedetection.io')
+
+        for watch in sorted_watches:
+
+            dates = list(watch.history.keys())
+            # Re #521 - Don't bother processing this one if theres less than 2 snapshots, means we never had a change detected.
+            if len(dates) < 2:
+                continue
+
+            if not watch.viewed:
+                # Re #239 - GUID needs to be individual for each event
+                # @todo In the future make this a configurable link back (see work on BASE_URL https://github.com/dgtlmoon/changedetection.io/pull/228)
+                guid = "{}/{}".format(watch['uuid'], watch.last_changed)
+                fe = fg.add_entry()
+
+                # Include a link to the diff page, they will have to login here to see if password protection is enabled.
+                # Description is the page you watch, link takes you to the diff JS UI page
+                # Dict val base_url will get overriden with the env var if it is set.
+                ext_base_url = datastore.data['settings']['application'].get('active_base_url')
+
+                # Because we are called via whatever web server, flask should figure out the right path (
+                diff_link = {'href': url_for('ui.ui_views.diff_history_page', uuid=watch['uuid'], _external=True)}
+
+                fe.link(link=diff_link)
+
+                # @todo watch should be a getter - watch.get('title') (internally if URL else..)
+
+                watch_title = watch.get('title') if watch.get('title') else watch.get('url')
+                fe.title(title=watch_title)
+
+                html_diff = diff.render_diff(previous_version_file_contents=watch.get_history_snapshot(dates[-2]),
+                                             newest_version_file_contents=watch.get_history_snapshot(dates[-1]),
+                                             include_equal=False,
+                                             line_feed_sep="<br>")
+
+                # @todo Make this configurable and also consider html-colored markup
+                # @todo User could decide if <link> goes to the diff page, or to the watch link
+                rss_template = "<html><body>\n<h4><a href=\"{{watch_url}}\">{{watch_title}}</a></h4>\n<p>{{html_diff}}</p>\n</body></html>\n"
+                content = jinja_render(template_str=rss_template, watch_title=watch_title, html_diff=html_diff, watch_url=watch.link)
+
+                fe.content(content=content, type='CDATA')
+
+                fe.guid(guid, permalink=False)
+                dt = datetime.datetime.fromtimestamp(int(watch.newest_history_key))
+                dt = dt.replace(tzinfo=pytz.UTC)
+                fe.pubDate(dt)
+
+        response = make_response(fg.rss_str())
+        response.headers.set('Content-Type', 'application/rss+xml;charset=utf-8')
+        logger.trace(f"RSS generated in {time.time() - now:.3f}s")
+        return response
+
+    return rss_blueprint

changedetectionio/blueprint/settings/__init__.py

@@ -0,0 +1,138 @@
+import os
+from copy import deepcopy
+from datetime import datetime
+from zoneinfo import ZoneInfo, available_timezones
+import secrets
+import flask_login
+from flask import Blueprint, render_template, request, redirect, url_for, flash
+
+from changedetectionio.store import ChangeDetectionStore
+from changedetectionio.auth_decorator import login_optionally_required
+
+
+def construct_blueprint(datastore: ChangeDetectionStore):
+    settings_blueprint = Blueprint('settings', __name__, template_folder="templates")
+
+    @settings_blueprint.route("/", methods=['GET', "POST"])
+    @login_optionally_required
+    def settings_page():
+        from changedetectionio import forms
+
+        default = deepcopy(datastore.data['settings'])
+        if datastore.proxy_list is not None:
+            available_proxies = list(datastore.proxy_list.keys())
+            # When enabled
+            system_proxy = datastore.data['settings']['requests']['proxy']
+            # In the case it doesnt exist anymore
+            if not system_proxy in available_proxies:
+                system_proxy = None
+
+            default['requests']['proxy'] = system_proxy if system_proxy is not None else available_proxies[0]
+            # Used by the form handler to keep or remove the proxy settings
+            default['proxy_list'] = available_proxies[0]
+
+        # Don't use form.data on POST so that it doesnt overrid the checkbox status from the POST status
+        form = forms.globalSettingsForm(formdata=request.form if request.method == 'POST' else None,
+                                        data=default,
+                                        extra_notification_tokens=datastore.get_unique_notification_tokens_available()
+                                        )
+
+        # Remove the last option 'System default'
+        form.application.form.notification_format.choices.pop()
+
+        if datastore.proxy_list is None:
+            # @todo - Couldn't get setattr() etc dynamic addition working, so remove it instead
+            del form.requests.form.proxy
+        else:
+            form.requests.form.proxy.choices = []
+            for p in datastore.proxy_list:
+                form.requests.form.proxy.choices.append(tuple((p, datastore.proxy_list[p]['label'])))
+
+        if request.method == 'POST':
+            # Password unset is a GET, but we can lock the session to a salted env password to always need the password
+            if form.application.form.data.get('removepassword_button', False):
+                # SALTED_PASS means the password is "locked" to what we set in the Env var
+                if not os.getenv("SALTED_PASS", False):
+                    datastore.remove_password()
+                    flash("Password protection removed.", 'notice')
+                    flask_login.logout_user()
+                    return redirect(url_for('settings.settings_page'))
+
+            if form.validate():
+                # Don't set password to False when a password is set - should be only removed with the `removepassword` button
+                app_update = dict(deepcopy(form.data['application']))
+
+                # Never update password with '' or False (Added by wtforms when not in submission)
+                if 'password' in app_update and not app_update['password']:
+                    del (app_update['password'])
+
+                datastore.data['settings']['application'].update(app_update)
+                datastore.data['settings']['requests'].update(form.data['requests'])
+
+                if not os.getenv("SALTED_PASS", False) and len(form.application.form.password.encrypted_password):
+                    datastore.data['settings']['application']['password'] = form.application.form.password.encrypted_password
+                    datastore.save_settings()
+                    flash("Password protection enabled.", 'notice')
+                    flask_login.logout_user()
+                    return redirect(url_for('index'))
+
+                datastore.save_settings()
+                flash("Settings updated.")
+
+            else:
+                flash("An error occurred, please see below.", "error")
+
+        # Convert to ISO 8601 format, all date/time relative events stored as UTC time
+        utc_time = datetime.now(ZoneInfo("UTC")).isoformat()
+        
+        # Get processor plugins info
+        from changedetectionio.processors import get_all_plugins_info
+        plugins_info = get_all_plugins_info()
+
+        # Process settings including plugin toggles
+        if request.method == 'POST' and form.validate():
+            # Process the main form data
+            app_update = dict(deepcopy(form.data['application']))
+            
+            # Don't update password with '' or False (Added by wtforms when not in submission)
+            if 'password' in app_update and not app_update['password']:
+                del (app_update['password'])
+
+            datastore.data['settings']['application'].update(app_update)
+            datastore.data['settings']['requests'].update(form.data['requests'])
+            datastore.save_settings()
+            flash("Settings updated.")
+
+        output = render_template("settings.html",
+                                api_key=datastore.data['settings']['application'].get('api_access_token'),
+                                available_timezones=sorted(available_timezones()),
+                                emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
+                                extra_notification_token_placeholder_info=datastore.get_unique_notification_token_placeholders_available(),
+                                form=form,
+                                hide_remove_pass=os.getenv("SALTED_PASS", False),
+                                min_system_recheck_seconds=int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 3)),
+                                plugins_info=plugins_info,
+                                settings_application=datastore.data['settings']['application'],
+                                timezone_default_config=datastore.data['settings']['application'].get('timezone'),
+                                utc_time=utc_time,
+                                )
+
+        return output
+
+    @settings_blueprint.route("/reset-api-key", methods=['GET'])
+    @login_optionally_required
+    def settings_reset_api_key():
+        secret = secrets.token_hex(16)
+        datastore.data['settings']['application']['api_access_token'] = secret
+        flash("API Key was regenerated.")
+        return redirect(url_for('settings.settings_page')+'#api')
+        
+    @settings_blueprint.route("/notification-logs", methods=['GET'])
+    @login_optionally_required
+    def notification_logs():
+        from changedetectionio.flask_app import notification_debug_log
+        output = render_template("notification-log.html",
+                               logs=notification_debug_log if len(notification_debug_log) else ["Notification logs are empty - no notifications sent yet."])
+        return output
+
+    return settings_blueprint

changedetectionio/blueprint/settings/templates/notification-log.html

@@ -0,0 +1,19 @@
+{% extends 'base.html' %}
+
+{% block content %}
+<div class="edit-form">
+     <div class="inner">
+
+         <h4 style="margin-top: 0px;">Notification debug log</h4>
+                <div id="notification-error-log">
+                <ul style="font-size: 80%; margin:0px; padding: 0 0 0 7px">
+                {% for log in logs|reverse %}
+                    <li>{{log}}</li>
+                {% endfor %}
+                </ul>
+                </div>
+
+     </div>
+</div>
+
+{% endblock %}

changedetectionio/blueprint/settings/templates/settings.html

@@ -1,18 +1,21 @@
 {% extends 'base.html' %}
 
 {% block content %}
-{% from '_helpers.html' import render_field, render_checkbox_field, render_button %}
+{% from '_helpers.html' import render_field, render_checkbox_field, render_button, render_time_schedule_form %}
 {% from '_common_fields.html' import render_common_settings_form %}
 <script>
-    const notification_base_url="{{url_for('ajax_callback_send_notification_test', mode="global-settings")}}";
+    const notification_base_url="{{url_for('ui.ui_notification.ajax_callback_send_notification_test', mode="global-settings")}}";
 {% if emailprefix %}
     const email_notification_prefix=JSON.parse('{{emailprefix|tojson}}');
 {% endif %}
 </script>
+
 <script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='plugins.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='vis.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='global-settings.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='scheduler.js')}}" defer></script>
 <div class="edit-form">
     <div class="tabs collapsable">
         <ul>
@@ -21,17 +24,25 @@
             <li class="tab"><a href="#fetching">Fetching</a></li>
             <li class="tab"><a href="#filters">Global Filters</a></li>
             <li class="tab"><a href="#api">API</a></li>
+            <li class="tab"><a href="#timedate">Time &amp Date</a></li>
             <li class="tab"><a href="#proxies">CAPTCHA &amp; Proxies</a></li>
+            <li class="tab"><a href="#plugins">Plugins</a></li>
         </ul>
     </div>
     <div class="box-wrap inner">
-        <form class="pure-form pure-form-stacked settings" action="{{url_for('settings_page')}}" method="POST">
+        <form class="pure-form pure-form-stacked settings" action="{{url_for('settings.settings_page')}}" method="POST">
             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
             <div class="tab-pane-inner" id="general">
                 <fieldset>
                     <div class="pure-control-group">
                         {{ render_field(form.requests.form.time_between_check, class="time-check-widget") }}
                         <span class="pure-form-message-inline">Default recheck time for all watches, current system minimum is <i>{{min_system_recheck_seconds}}</i> seconds (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Misc-system-settings#enviroment-variables">more info</a>).</span>
+                            <div id="time-between-check-schedule">
+                                <!-- Start Time and End Time -->
+                                <div id="limit-between-time">
+                                    {{ render_time_schedule_form(form.requests, available_timezones, timezone_default_config) }}
+                                </div>
+                        </div>
                     </div>
                     <div class="pure-control-group">
                         {{ render_field(form.requests.form.jitter_seconds, class="jitter_seconds") }}
@@ -76,7 +87,7 @@
                     </div>
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.application.form.empty_pages_are_a_change) }}
-                        <span class="pure-form-message-inline">When a page contains HTML, but no renderable text appears (empty page), is this considered a change?</span>
+                        <span class="pure-form-message-inline">When a request returns no content, or the HTML does not contain any text, is this considered a change?</span>
                     </div>
                 {% if form.requests.proxy %}
                     <div class="pure-control-group inline-radio">
@@ -155,11 +166,13 @@
                       {{ render_field(form.application.form.global_subtractive_selectors, rows=5, placeholder="header
 footer
 nav
-.stockticker") }}
+.stockticker
+//*[contains(text(), 'Advertisement')]") }}
                       <span class="pure-form-message-inline">
                         <ul>
-                          <li> Remove HTML element(s) by CSS selector before text conversion. </li>
-                          <li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
+                          <li> Remove HTML element(s) by CSS and XPath selectors before text conversion. </li>
+                          <li> Don't paste HTML here, use only CSS and XPath selectors </li>
+                          <li> Add multiple elements, CSS or XPath selectors per line to ignore multiple parts of the HTML. </li>
                         </ul>
                       </span>
                     </fieldset>
@@ -170,11 +183,11 @@ nav
                     <span class="pure-form-message-inline">Note: This is applied globally in addition to the per-watch rules.</span><br>
                     <span class="pure-form-message-inline">
                         <ul>
+                            <li>Matching text will be <strong>ignored</strong> in the text snapshot (you can still see it but it wont trigger a change)</li>
                             <li>Note: This is applied globally in addition to the per-watch rules.</li>
                             <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
                             <li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
                             <li>Changing this will affect the comparison checksum which may trigger an alert</li>
-                            <li>Use the preview/show current tab to see ignores</li>
                         </ul>
                      </span>
                     </fieldset>
@@ -192,7 +205,7 @@ nav
                     </div>
                 </div>
                 <div class="pure-control-group">
-                    <a href="{{url_for('settings_reset_api_key')}}" class="pure-button button-small button-cancel">Regenerate API key</a>
+                    <a href="{{url_for('settings.settings_reset_api_key')}}" class="pure-button button-small button-cancel">Regenerate API key</a>
                 </div>
                 <div class="pure-control-group">
                     <h4>Chrome Extension</h4>
@@ -203,12 +216,29 @@ nav
                         <a id="chrome-extension-link"
                            title="Try our new Chrome Extension!"
                            href="https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop">
-                            <img src="{{ url_for('static_content', group='images', filename='Google-Chrome-icon.png') }}" alt="Chrome">
+                            <img alt="Chrome store icon" src="{{ url_for('static_content', group='images', filename='Google-Chrome-icon.png') }}" alt="Chrome">
                             Chrome Webstore
                         </a>
                     </p>
                 </div>
             </div>
+            <div class="tab-pane-inner" id="timedate">
+                <div class="pure-control-group">
+                    Ensure the settings below are correct, they are used to manage the time schedule for checking your web page watches.
+                </div>
+                <div class="pure-control-group">
+                    <p><strong>UTC Time &amp Date from Server:</strong> <span id="utc-time" >{{ utc_time }}</span></p>
+                    <p><strong>Local Time &amp Date in Browser:</strong> <span class="local-time" data-utc="{{ utc_time }}"></span></p>
+                    <p>
+                       {{ render_field(form.application.form.timezone) }}
+                        <datalist id="timezones" style="display: none;">
+                            {% for tz_name in available_timezones %}
+                                <option value="{{ tz_name }}">{{ tz_name }}</option>
+                            {% endfor %}
+                        </datalist>
+                    </p>
+                </div>
+            </div>
             <div class="tab-pane-inner" id="proxies">
                 <div id="recommended-proxy">
                     <div>
@@ -252,9 +282,7 @@ nav
                         
                     </div>
                 </div>
-                <p>
-                    Your proxy provider may need to whitelist our IP of <code>204.15.192.195</code>
-                </p>
+
                <p><strong>Tip</strong>: "Residential" and "Mobile" proxy type can be more successfull than "Data Center" for blocked websites.
 
                 <div class="pure-control-group" id="extra-proxies-setting">
@@ -270,11 +298,37 @@ nav
                     {{ render_field(form.requests.form.extra_browsers) }}
                 </div>
             </div>
+            <div class="tab-pane-inner" id="plugins">
+              <div class="pure-control-group">
+                <h4>Registered Plugins</h4>
+                  <p>The following plugins are currently registered in the system - <a href="https://changedetection.io/plugins">Get more plugins here</a></p>
+                
+                <table class="pure-table pure-table-striped">
+                    <thead>
+                        <tr>
+                            <th>Name</th>
+                            <th>Description</th>
+                            <th>Version</th>
+                        </tr>
+                    </thead>
+                    <tbody>
+                        {% for plugin in plugins_info %}
+                        <tr>
+                            <td>{{ plugin.name }}</td>
+                            <td>{{ plugin.description }}</td>
+                            <td>{{ plugin.version }}</td>
+                        </tr>
+                        {% endfor %}
+                    </tbody>
+                </table>
+              </div>
+            </div>
+
             <div id="actions">
                 <div class="pure-control-group">
                     {{ render_button(form.save_button) }}
                     <a href="{{url_for('index')}}" class="pure-button button-small button-cancel">Back</a>
-                    <a href="{{url_for('clear_all_history')}}" class="pure-button button-small button-cancel">Clear Snapshot History</a>
+                    <a href="{{url_for('ui.clear_all_history')}}" class="pure-button button-small button-error">Clear Snapshot History</a>
                 </div>
             </div>
         </form>

changedetectionio/blueprint/tags/__init__.py

@@ -13,6 +13,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     def tags_overview_page():
         from .form import SingleTag
         add_form = SingleTag(request.form)
+
         sorted_tags = sorted(datastore.data['settings']['application'].get('tags').items(), key=lambda x: x[1]['title'])
 
         from collections import Counter
@@ -55,6 +56,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     def mute(uuid):
         if datastore.data['settings']['application']['tags'].get(uuid):
             datastore.data['settings']['application']['tags'][uuid]['notification_muted'] = not datastore.data['settings']['application']['tags'][uuid]['notification_muted']
+            datastore.data['settings']['application']['tags'][uuid].save_data()
         return redirect(url_for('tags.tags_overview_page'))
 
     @tags_blueprint.route("/delete/<string:uuid>", methods=['GET'])
@@ -104,9 +106,11 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
         default = datastore.data['settings']['application']['tags'].get(uuid)
 
-        form = group_restock_settings_form(formdata=request.form if request.method == 'POST' else None,
+        form = group_restock_settings_form(
+                                       formdata=request.form if request.method == 'POST' else None,
                                        data=default,
-                                       extra_notification_tokens=datastore.get_unique_notification_tokens_available()
+                                       extra_notification_tokens=datastore.get_unique_notification_tokens_available(),
+                                       default_system_settings = datastore.data['settings'],
                                        )
 
         template_args = {
@@ -173,7 +177,8 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
         datastore.data['settings']['application']['tags'][uuid].update(form.data)
         datastore.data['settings']['application']['tags'][uuid]['processor'] = 'restock_diff'
-        datastore.needs_write_urgent = True
+        datastore.data['settings']['application']['tags'][uuid].save_data()
+
         flash("Updated")
 
         return redirect(url_for('tags.tags_overview_page'))

changedetectionio/blueprint/tags/templates/edit-tag.html

@@ -3,7 +3,7 @@
 {% from '_helpers.html' import render_field, render_checkbox_field, render_button %}
 {% from '_common_fields.html' import render_common_settings_form %}
 <script>
-    const notification_base_url="{{url_for('ajax_callback_send_notification_test', mode="group-settings")}}";
+    const notification_base_url="{{url_for('ui.ui_notification.ajax_callback_send_notification_test', mode="group-settings")}}";
 </script>
 
 <script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
@@ -17,7 +17,6 @@
 </script>
 
 <script src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
-<!--<script src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>-->
 <script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
 
 <div class="edit-form monospaced-textarea">
@@ -58,9 +57,9 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                         {% if '/text()' in  field %}
                           <span class="pure-form-message-inline"><strong>Note!: //text() function does not work where the &lt;element&gt; contains &lt;![CDATA[]]&gt;</strong></span><br>
                         {% endif %}
-                        <span class="pure-form-message-inline">One rule per line, <i>any</i> rules that matches will be used.<br>
-
-                    <ul>
+                        <span class="pure-form-message-inline">One CSS, xPath, JSON Path/JQ selector per line, <i>any</i> rules that matches will be used.<br>
+                    <div data-target="#advanced-help-selectors" class="toggle-show pure-button button-tag button-xsmall">Show advanced help and tips</div>
+                    <ul id="advanced-help-selectors">
                         <li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
                         <li>JSON - Limit text to this JSON rule, using either <a href="https://pypi.org/project/jsonpath-ng/" target="new">JSONPath</a> or <a href="https://stedolan.github.io/jq/" target="new">jq</a> (if installed).
                             <ul>
@@ -89,11 +88,13 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                     {{ render_field(form.subtractive_selectors, rows=5, placeholder="header
 footer
 nav
-.stockticker") }}
+.stockticker
+//*[contains(text(), 'Advertisement')]") }}
                     <span class="pure-form-message-inline">
                         <ul>
-                          <li> Remove HTML element(s) by CSS selector before text conversion. </li>
-                          <li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
+                          <li> Remove HTML element(s) by CSS and XPath selectors before text conversion. </li>
+                          <li> Don't paste HTML here, use only CSS and XPath selectors </li>
+                          <li> Add multiple elements, CSS or XPath selectors per line to ignore multiple parts of the HTML. </li>
                         </ul>
                       </span>
                 </fieldset>
@@ -123,7 +124,7 @@ nav
                         {% if has_default_notification_urls %}
                         <div class="inline-warning">
                             <img class="inline-warning-icon" src="{{url_for('static_content', group='images', filename='notice.svg')}}" alt="Look out!" title="Lookout!" >
-                            There are <a href="{{ url_for('settings_page')}}#notifications">system-wide notification URLs enabled</a>, this form will override notification settings for this watch only &dash; an empty Notification URL list here will still send notifications.
+                            There are <a href="{{ url_for('settings.settings_page')}}#notifications">system-wide notification URLs enabled</a>, this form will override notification settings for this watch only &dash; an empty Notification URL list here will still send notifications.
                         </div>
                         {% endif %}
                         <a href="#notifications" id="notification-setting-reset-to-default" class="pure-button button-xsmall" style="right: 20px; top: 20px; position: absolute; background-color: #5f42dd; border-radius: 4px; font-size: 70%; color: #fff">Use system defaults</a>

changedetectionio/blueprint/ui/__init__.py

@@ -0,0 +1,309 @@
+import time
+from flask import Blueprint, request, redirect, url_for, flash, render_template, session
+from loguru import logger
+from functools import wraps
+
+from changedetectionio.store import ChangeDetectionStore
+from changedetectionio.blueprint.ui.edit import construct_blueprint as construct_edit_blueprint
+from changedetectionio.blueprint.ui.notification import construct_blueprint as construct_notification_blueprint
+from changedetectionio.blueprint.ui.views import construct_blueprint as construct_views_blueprint
+
+def construct_blueprint(datastore: ChangeDetectionStore, update_q, running_update_threads, queuedWatchMetaData):
+    ui_blueprint = Blueprint('ui', __name__, template_folder="templates")
+    
+    # Register the edit blueprint
+    edit_blueprint = construct_edit_blueprint(datastore, update_q, queuedWatchMetaData)
+    ui_blueprint.register_blueprint(edit_blueprint)
+    
+    # Register the notification blueprint
+    notification_blueprint = construct_notification_blueprint(datastore)
+    ui_blueprint.register_blueprint(notification_blueprint)
+    
+    # Register the views blueprint
+    views_blueprint = construct_views_blueprint(datastore, update_q, queuedWatchMetaData)
+    ui_blueprint.register_blueprint(views_blueprint)
+    
+    # Import the login decorator
+    from changedetectionio.auth_decorator import login_optionally_required
+
+    @ui_blueprint.route("/clear_history/<string:uuid>", methods=['GET'])
+    @login_optionally_required
+    def clear_watch_history(uuid):
+        try:
+            datastore.clear_watch_history(uuid)
+        except KeyError:
+            flash('Watch not found', 'error')
+        else:
+            flash("Cleared snapshot history for watch {}".format(uuid))
+
+        return redirect(url_for('index'))
+
+    @ui_blueprint.route("/clear_history", methods=['GET', 'POST'])
+    @login_optionally_required
+    def clear_all_history():
+        if request.method == 'POST':
+            confirmtext = request.form.get('confirmtext')
+
+            if confirmtext == 'clear':
+                for uuid in datastore.data['watching'].keys():
+                    datastore.clear_watch_history(uuid)
+
+                flash("Cleared snapshot history for all watches")
+            else:
+                flash('Incorrect confirmation text.', 'error')
+
+            return redirect(url_for('index'))
+
+        output = render_template("clear_all_history.html")
+        return output
+
+    # Clear all statuses, so we do not see the 'unviewed' class
+    @ui_blueprint.route("/form/mark-all-viewed", methods=['GET'])
+    @login_optionally_required
+    def mark_all_viewed():
+        # Save the current newest history as the most recently viewed
+        with_errors = request.args.get('with_errors') == "1"
+        for watch_uuid, watch in datastore.data['watching'].items():
+            if with_errors and not watch.get('last_error'):
+                continue
+            datastore.set_last_viewed(watch_uuid, int(time.time()))
+
+        return redirect(url_for('index'))
+
+    @ui_blueprint.route("/delete", methods=['GET'])
+    @login_optionally_required
+    def form_delete():
+        uuid = request.args.get('uuid')
+
+        if uuid != 'all' and not uuid in datastore.data['watching'].keys():
+            flash('The watch by UUID {} does not exist.'.format(uuid), 'error')
+            return redirect(url_for('index'))
+
+        # More for testing, possible to return the first/only
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
+        datastore.delete(uuid)
+        flash('Deleted.')
+
+        return redirect(url_for('index'))
+
+    @ui_blueprint.route("/clone", methods=['GET'])
+    @login_optionally_required
+    def form_clone():
+        uuid = request.args.get('uuid')
+        # More for testing, possible to return the first/only
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
+
+        new_uuid = datastore.clone(uuid)
+        if new_uuid:
+            if not datastore.data['watching'].get(uuid).get('paused'):
+                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid}))
+            flash('Cloned.')
+
+        return redirect(url_for('index'))
+
+    @ui_blueprint.route("/checknow", methods=['GET'])
+    @login_optionally_required
+    def form_watch_checknow():
+        # Forced recheck will skip the 'skip if content is the same' rule (, 'reprocess_existing_data': True})))
+        tag = request.args.get('tag')
+        uuid = request.args.get('uuid')
+        with_errors = request.args.get('with_errors') == "1"
+
+        i = 0
+
+        running_uuids = []
+        for t in running_update_threads:
+            running_uuids.append(t.current_uuid)
+
+        if uuid:
+            if uuid not in running_uuids:
+                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+                i += 1
+
+        else:
+            # Recheck all, including muted
+            for watch_uuid, watch in datastore.data['watching'].items():
+                if not watch['paused']:
+                    if watch_uuid not in running_uuids:
+                        if with_errors and not watch.get('last_error'):
+                            continue
+
+                        if tag != None and tag not in watch['tags']:
+                            continue
+
+                        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
+                        i += 1
+
+        if i == 1:
+            flash("Queued 1 watch for rechecking.")
+        if i > 1:
+            flash("Queued {} watches for rechecking.".format(i))
+        if i == 0:
+            flash("No watches available to recheck.")
+
+        return redirect(url_for('index'))
+
+    @ui_blueprint.route("/form/checkbox-operations", methods=['POST'])
+    @login_optionally_required
+    def form_watch_list_checkbox_operations():
+        op = request.form['op']
+        uuids = request.form.getlist('uuids')
+
+        if (op == 'delete'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.delete(uuid.strip())
+            flash("{} watches deleted".format(len(uuids)))
+
+        elif (op == 'pause'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.data['watching'][uuid.strip()]['paused'] = True
+                    datastore.data['watching'][uuid.strip()].save_data()
+            flash("{} watches paused".format(len(uuids)))
+
+        elif (op == 'unpause'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.data['watching'][uuid.strip()]['paused'] = False
+                    datastore.data['watching'][uuid.strip()].save_data()
+            flash("{} watches unpaused".format(len(uuids)))
+
+        elif (op == 'mark-viewed'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.set_last_viewed(uuid, int(time.time()))
+            flash("{} watches updated".format(len(uuids)))
+
+        elif (op == 'mute'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.data['watching'][uuid.strip()]['notification_muted'] = True
+                    datastore.data['watching'][uuid.strip()].save_data()
+            flash("{} watches muted".format(len(uuids)))
+
+        elif (op == 'unmute'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.data['watching'][uuid.strip()]['notification_muted'] = False
+                    datastore.data['watching'][uuid.strip()].save_data()
+            flash("{} watches un-muted".format(len(uuids)))
+
+        elif (op == 'recheck'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    # Recheck and require a full reprocessing
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+            flash("{} watches queued for rechecking".format(len(uuids)))
+
+        elif (op == 'clear-errors'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.data['watching'][uuid]["last_error"] = False
+                    datastore.data['watching'][uuid].save_data()
+            flash(f"{len(uuids)} watches errors cleared")
+
+        elif (op == 'clear-history'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.clear_watch_history(uuid)
+            flash("{} watches cleared/reset.".format(len(uuids)))
+
+        elif (op == 'notification-default'):
+            from changedetectionio.notification import (
+                default_notification_format_for_watch
+            )
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.data['watching'][uuid.strip()]['notification_title'] = None
+                    datastore.data['watching'][uuid.strip()]['notification_body'] = None
+                    datastore.data['watching'][uuid.strip()]['notification_urls'] = []
+                    datastore.data['watching'][uuid.strip()]['notification_format'] = default_notification_format_for_watch
+            flash("{} watches set to use default notification settings".format(len(uuids)))
+
+        elif (op == 'assign-tag'):
+            op_extradata = request.form.get('op_extradata', '').strip()
+            if op_extradata:
+                tag_uuid = datastore.add_tag(name=op_extradata)
+                if op_extradata and tag_uuid:
+                    for uuid in uuids:
+                        uuid = uuid.strip()
+                        if datastore.data['watching'].get(uuid):
+                            # Bug in old versions caused by bad edit page/tag handler
+                            if isinstance(datastore.data['watching'][uuid]['tags'], str):
+                                datastore.data['watching'][uuid]['tags'] = []
+
+                            datastore.data['watching'][uuid]['tags'].append(tag_uuid)
+
+            flash(f"{len(uuids)} watches were tagged")
+
+        for uuid in uuids:
+            datastore.data['watching'][uuid.strip()].save_data()
+
+        return redirect(url_for('index'))
+
+
+    @ui_blueprint.route("/share-url/<string:uuid>", methods=['GET'])
+    @login_optionally_required
+    def form_share_put_watch(uuid):
+        """Given a watch UUID, upload the info and return a share-link
+           the share-link can be imported/added"""
+        import requests
+        import json
+        from copy import deepcopy
+
+        # more for testing
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
+
+        # copy it to memory as trim off what we dont need (history)
+        watch = deepcopy(datastore.data['watching'].get(uuid))
+        # For older versions that are not a @property
+        if (watch.get('history')):
+            del (watch['history'])
+
+        # for safety/privacy
+        for k in list(watch.keys()):
+            if k.startswith('notification_'):
+                del watch[k]
+
+        for r in['uuid', 'last_checked', 'last_changed']:
+            if watch.get(r):
+                del (watch[r])
+
+        # Add the global stuff which may have an impact
+        watch['ignore_text'] += datastore.data['settings']['application']['global_ignore_text']
+        watch['subtractive_selectors'] += datastore.data['settings']['application']['global_subtractive_selectors']
+
+        watch_json = json.dumps(watch)
+
+        try:
+            r = requests.request(method="POST",
+                                 data={'watch': watch_json},
+                                 url="https://changedetection.io/share/share",
+                                 headers={'App-Guid': datastore.data['app_guid']})
+            res = r.json()
+
+            # Add to the flask session
+            session['share-link'] = f"https://changedetection.io/share/{res['share_key']}"
+
+
+        except Exception as e:
+            logger.error(f"Error sharing -{str(e)}")
+            flash(f"Could not share, something went wrong while communicating with the share server - {str(e)}", 'error')
+
+        return redirect(url_for('index'))
+
+    return ui_blueprint

changedetectionio/blueprint/ui/edit.py

@@ -0,0 +1,319 @@
+import time
+from copy import deepcopy
+import os
+import importlib.resources
+from flask import Blueprint, request, redirect, url_for, flash, render_template, make_response, send_from_directory, abort
+from loguru import logger
+from jinja2 import Environment, FileSystemLoader
+
+from changedetectionio.store import ChangeDetectionStore
+from changedetectionio.auth_decorator import login_optionally_required
+from changedetectionio.time_handler import is_within_schedule
+
+def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMetaData):
+    edit_blueprint = Blueprint('ui_edit', __name__, template_folder="../ui/templates")
+    
+    def _watch_has_tag_options_set(watch):
+        """This should be fixed better so that Tag is some proper Model, a tag is just a Watch also"""
+        for tag_uuid, tag in datastore.data['settings']['application'].get('tags', {}).items():
+            if tag_uuid in watch.get('tags', []) and (tag.get('include_filters') or tag.get('subtractive_selectors')):
+                return True
+
+    @edit_blueprint.route("/edit/<string:uuid>", methods=['GET', 'POST'])
+    @login_optionally_required
+    # https://stackoverflow.com/questions/42984453/wtforms-populate-form-with-data-if-data-exists
+    # https://wtforms.readthedocs.io/en/3.0.x/forms/#wtforms.form.Form.populate_obj ?
+    def edit_page(uuid):
+        from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
+        from changedetectionio import processors
+        import importlib
+
+        # More for testing, possible to return the first/only
+        if not datastore.data['watching'].keys():
+            flash("No watches to edit", "error")
+            return redirect(url_for('index'))
+
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
+
+        if not uuid in datastore.data['watching']:
+            flash("No watch with the UUID %s found." % (uuid), "error")
+            return redirect(url_for('index'))
+
+        switch_processor = request.args.get('switch_processor')
+        if switch_processor:
+            for p in processors.available_processors(datastore):
+                if p[0] == switch_processor:
+                    datastore.data['watching'][uuid]['processor'] = switch_processor
+                    flash(f"Switched to mode - {p[1]}.")
+                    datastore.clear_watch_history(uuid)
+                    redirect(url_for('ui_edit.edit_page', uuid=uuid))
+
+
+        default = datastore.data['watching'][uuid]
+
+        # Defaults for proxy choice
+        if datastore.proxy_list is not None:  # When enabled
+            # @todo
+            # Radio needs '' not None, or incase that the chosen one no longer exists
+            if default['proxy'] is None or not any(default['proxy'] in tup for tup in datastore.proxy_list):
+                default['proxy'] = ''
+        # proxy_override set to the json/text list of the items
+
+        # Get the appropriate form class for this processor using the pluggy system
+        processor_name = datastore.data['watching'][uuid].get('processor', 'text_json_diff')
+        form_class = processors.get_form_class_for_processor(processor_name)
+        
+        if not form_class:
+            flash(f"Cannot load the edit form for processor/plugin '{processor_name}', plugin missing?", 'error')
+            return redirect(url_for('index'))
+
+        form = form_class(formdata=request.form if request.method == 'POST' else None,
+                          data=default,
+                          extra_notification_tokens=default.extra_notification_token_values(),
+                          default_system_settings=datastore.data['settings'],
+                          datastore=datastore
+                          )
+
+        # For the form widget tag UUID back to "string name" for the field
+        form.tags.datastore = datastore
+
+        # Used by some forms that need to dig deeper
+        form.datastore = datastore
+        form.watch = default
+
+        for p in datastore.extra_browsers:
+            form.fetch_backend.choices.append(p)
+
+        form.fetch_backend.choices.append(("system", 'System settings default'))
+
+        # form.browser_steps[0] can be assumed that we 'goto url' first
+
+        if datastore.proxy_list is None:
+            # @todo - Couldn't get setattr() etc dynamic addition working, so remove it instead
+            del form.proxy
+        else:
+            form.proxy.choices = [('', 'Default')]
+            for p in datastore.proxy_list:
+                form.proxy.choices.append(tuple((p, datastore.proxy_list[p]['label'])))
+
+
+        if request.method == 'POST' and form.validate():
+
+            # If they changed processor, it makes sense to reset it.
+            if datastore.data['watching'][uuid].get('processor') != form.data.get('processor'):
+                datastore.data['watching'][uuid].clear_watch()
+                flash("Reset watch history due to change of processor")
+
+            extra_update_obj = {
+                'consecutive_filter_failures': 0,
+                'last_error' : False
+            }
+
+            if request.args.get('unpause_on_save'):
+                extra_update_obj['paused'] = False
+
+            extra_update_obj['time_between_check'] = form.time_between_check.data
+            extra_update_obj['ignore_text'] = form.ignore_text.data
+
+            # Be sure proxy value is None
+            if datastore.proxy_list is not None and form.data['proxy'] == '':
+                extra_update_obj['proxy'] = None
+
+            # Unsetting all filter_text methods should make it go back to default
+            # This particularly affects tests running
+            if 'filter_text_added' in form.data and not form.data.get('filter_text_added') \
+                    and 'filter_text_replaced' in form.data and not form.data.get('filter_text_replaced') \
+                    and 'filter_text_removed' in form.data and not form.data.get('filter_text_removed'):
+                extra_update_obj['filter_text_added'] = True
+                extra_update_obj['filter_text_replaced'] = True
+                extra_update_obj['filter_text_removed'] = True
+
+            # Because wtforms doesn't support accessing other data in process_ , but we convert the CSV list of tags back to a list of UUIDs
+            tag_uuids = []
+            if form.data.get('tags'):
+                # Sometimes in testing this can be list, dont know why
+                if type(form.data.get('tags')) == list:
+                    extra_update_obj['tags'] = form.data.get('tags')
+                else:
+                    for t in form.data.get('tags').split(','):
+                        tag_uuids.append(datastore.add_tag(name=t))
+                    extra_update_obj['tags'] = tag_uuids
+
+
+
+
+            if not datastore.data['watching'][uuid].get('tags'):
+                # Force it to be a list, because form.data['tags'] will be string if nothing found
+                # And del(form.data['tags'] ) wont work either for some reason
+                datastore.data['watching'][uuid]['tags'] = []
+
+            datastore.update_watch(uuid=uuid, update_obj=form.data | extra_update_obj)
+
+            # Recast it if need be to right data Watch handler
+            processor_name = datastore.data['watching'][uuid].get('processor')
+            watch_class = processors.get_watch_model_for_processor(processor_name)
+            datastore.data['watching'][uuid] = watch_class(datastore_path=datastore.datastore_path, default=datastore.data['watching'][uuid])
+            datastore.data['watching'][uuid].save_data()
+            flash("Updated watch - unpaused!" if request.args.get('unpause_on_save') else "Updated watch.")
+
+
+            # Do not queue on edit if its not within the time range
+
+            # @todo maybe it should never queue anyway on edit...
+            is_in_schedule = True
+            watch = datastore.data['watching'].get(uuid)
+
+            if watch.get('time_between_check_use_default'):
+                time_schedule_limit = datastore.data['settings']['requests'].get('time_schedule_limit', {})
+            else:
+                time_schedule_limit = watch.get('time_schedule_limit')
+
+            tz_name = time_schedule_limit.get('timezone')
+            if not tz_name:
+                tz_name = datastore.data['settings']['application'].get('timezone', 'UTC')
+
+            if time_schedule_limit and time_schedule_limit.get('enabled'):
+                try:
+                    is_in_schedule = is_within_schedule(time_schedule_limit=time_schedule_limit,
+                                                      default_tz=tz_name
+                                                      )
+                except Exception as e:
+                    logger.error(
+                        f"{uuid} - Recheck scheduler, error handling timezone, check skipped - TZ name '{tz_name}' - {str(e)}")
+                    return False
+
+
+            #############################
+            if not datastore.data['watching'][uuid].get('paused') and is_in_schedule:
+                # Queue the watch for immediate recheck, with a higher priority
+                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
+
+            # Diff page [edit] link should go back to diff page
+            if request.args.get("next") and request.args.get("next") == 'diff':
+                return redirect(url_for('ui.ui_views.diff_history_page', uuid=uuid))
+
+            return redirect(url_for('index', tag=request.args.get("tag",'')))
+
+        else:
+            if request.method == 'POST' and not form.validate():
+                flash("An error occurred, please see below.", "error")
+
+            visualselector_data_is_ready = datastore.visualselector_data_is_ready(uuid)
+
+
+            # JQ is difficult to install on windows and must be manually added (outside requirements.txt)
+            jq_support = True
+            try:
+                import jq
+            except ModuleNotFoundError:
+                jq_support = False
+
+            watch = datastore.data['watching'].get(uuid)
+
+            system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
+
+            watch_uses_webdriver = False
+            if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
+                watch_uses_webdriver = True
+
+            from zoneinfo import available_timezones
+
+            # Only works reliably with Playwright
+
+            template_args = {
+                'available_processors': processors.available_processors(datastore),
+                'available_timezones': sorted(available_timezones()),
+                'browser_steps_config': browser_step_ui_config,
+                'emailprefix': os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
+                'extra_notification_token_placeholder_info': datastore.get_unique_notification_token_placeholders_available(),
+                'extra_processor_config': form.extra_tab_content(),
+                'extra_title': f" - Edit - {watch.label}",
+                'form': form,
+                'has_default_notification_urls': True if len(datastore.data['settings']['application']['notification_urls']) else False,
+                'has_extra_headers_file': len(datastore.get_all_headers_in_textfile_for_watch(uuid=uuid)) > 0,
+                'has_special_tag_options': _watch_has_tag_options_set(watch=watch),
+                'watch_uses_webdriver': watch_uses_webdriver,
+                'jq_support': jq_support,
+                'playwright_enabled': os.getenv('PLAYWRIGHT_DRIVER_URL', False),
+                'settings_application': datastore.data['settings']['application'],
+                'timezone_default_config': datastore.data['settings']['application'].get('timezone'),
+                'using_global_webdriver_wait': not default['webdriver_delay'],
+                'uuid': uuid,
+                'watch': watch
+            }
+
+            included_content = None
+            if form.extra_form_content():
+                # So that the extra panels can access _helpers.html etc, we set the environment to load from templates/
+                # And then render the code from the module
+                templates_dir = str(importlib.resources.files("changedetectionio").joinpath('templates'))
+                env = Environment(loader=FileSystemLoader(templates_dir))
+                template = env.from_string(form.extra_form_content())
+                included_content = template.render(**template_args)
+
+            output = render_template("edit.html",
+                                     extra_tab_content=form.extra_tab_content() if form.extra_tab_content() else None,
+                                     extra_form_content=included_content,
+                                     **template_args
+                                     )
+
+        return output
+
+    @edit_blueprint.route("/edit/<string:uuid>/get-html", methods=['GET'])
+    @login_optionally_required
+    def watch_get_latest_html(uuid):
+        from io import BytesIO
+        from flask import send_file
+        import brotli
+
+        watch = datastore.data['watching'].get(uuid)
+        if watch and watch.history.keys() and os.path.isdir(watch.watch_data_dir):
+            latest_filename = list(watch.history.keys())[-1]
+            html_fname = os.path.join(watch.watch_data_dir, f"{latest_filename}.html.br")
+            with open(html_fname, 'rb') as f:
+                if html_fname.endswith('.br'):
+                    # Read and decompress the Brotli file
+                    decompressed_data = brotli.decompress(f.read())
+                else:
+                    decompressed_data = f.read()
+
+            buffer = BytesIO(decompressed_data)
+
+            return send_file(buffer, as_attachment=True, download_name=f"{latest_filename}.html", mimetype='text/html')
+
+        # Return a 500 error
+        abort(500)
+
+    # Ajax callback
+    @edit_blueprint.route("/edit/<string:uuid>/preview-rendered", methods=['POST'])
+    @login_optionally_required
+    def watch_get_preview_rendered(uuid):
+        '''For when viewing the "preview" of the rendered text from inside of Edit'''
+        from flask import jsonify
+        from changedetectionio.processors.text_json_diff import prepare_filter_prevew
+        result = prepare_filter_prevew(watch_uuid=uuid, form_data=request.form, datastore=datastore)
+        return jsonify(result)
+
+    @edit_blueprint.route("/highlight_submit_ignore_url", methods=['POST'])
+    @login_optionally_required
+    def highlight_submit_ignore_url():
+        import re
+        mode = request.form.get('mode')
+        selection = request.form.get('selection')
+
+        uuid = request.args.get('uuid','')
+        if datastore.data["watching"].get(uuid):
+            if mode == 'exact':
+                for l in selection.splitlines():
+                    datastore.data["watching"][uuid]['ignore_text'].append(l.strip())
+            elif mode == 'digit-regex':
+                for l in selection.splitlines():
+                    # Replace any series of numbers with a regex
+                    s = re.escape(l.strip())
+                    s = re.sub(r'[0-9]+', r'\\d+', s)
+                    datastore.data["watching"][uuid]['ignore_text'].append('/' + s + '/')
+
+        return f"<a href={url_for('ui.ui_views.preview_page', uuid=uuid)}>Click to preview</a>"
+    
+    return edit_blueprint

changedetectionio/blueprint/ui/notification.py

@@ -0,0 +1,107 @@
+from flask import Blueprint, request, make_response
+import random
+from loguru import logger
+
+from changedetectionio.store import ChangeDetectionStore
+from changedetectionio.auth_decorator import login_optionally_required
+
+def construct_blueprint(datastore: ChangeDetectionStore):
+    notification_blueprint = Blueprint('ui_notification', __name__, template_folder="../ui/templates")
+    
+    # AJAX endpoint for sending a test
+    @notification_blueprint.route("/notification/send-test/<string:watch_uuid>", methods=['POST'])
+    @notification_blueprint.route("/notification/send-test", methods=['POST'])
+    @notification_blueprint.route("/notification/send-test/", methods=['POST'])
+    @login_optionally_required
+    def ajax_callback_send_notification_test(watch_uuid=None):
+
+        # Watch_uuid could be unset in the case it`s used in tag editor, global settings
+        import apprise
+        from changedetectionio.apprise_asset import asset
+        apobj = apprise.Apprise(asset=asset)
+
+        # so that the custom endpoints are registered
+        from changedetectionio.apprise_plugin import apprise_custom_api_call_wrapper
+        is_global_settings_form = request.args.get('mode', '') == 'global-settings'
+        is_group_settings_form = request.args.get('mode', '') == 'group-settings'
+
+        # Use an existing random one on the global/main settings form
+        if not watch_uuid and (is_global_settings_form or is_group_settings_form) \
+                and datastore.data.get('watching'):
+            logger.debug(f"Send test notification - Choosing random Watch {watch_uuid}")
+            watch_uuid = random.choice(list(datastore.data['watching'].keys()))
+
+        if not watch_uuid:
+            return make_response("Error: You must have atleast one watch configured for 'test notification' to work", 400)
+
+        watch = datastore.data['watching'].get(watch_uuid)
+
+        notification_urls = None
+
+        if request.form.get('notification_urls'):
+            notification_urls = request.form['notification_urls'].strip().splitlines()
+
+        if not notification_urls:
+            logger.debug("Test notification - Trying by group/tag in the edit form if available")
+            # On an edit page, we should also fire off to the tags if they have notifications
+            if request.form.get('tags') and request.form['tags'].strip():
+                for k in request.form['tags'].split(','):
+                    tag = datastore.tag_exists_by_name(k.strip())
+                    notification_urls = tag.get('notifications_urls') if tag and tag.get('notifications_urls') else None
+
+        if not notification_urls and not is_global_settings_form and not is_group_settings_form:
+            # In the global settings, use only what is typed currently in the text box
+            logger.debug("Test notification - Trying by global system settings notifications")
+            if datastore.data['settings']['application'].get('notification_urls'):
+                notification_urls = datastore.data['settings']['application']['notification_urls']
+
+        if not notification_urls:
+            return 'Error: No Notification URLs set/found'
+
+        for n_url in notification_urls:
+            if len(n_url.strip()):
+                if not apobj.add(n_url):
+                    return f'Error:  {n_url} is not a valid AppRise URL.'
+
+        try:
+            # use the same as when it is triggered, but then override it with the form test values
+            n_object = {
+                'watch_url': request.form.get('window_url', "https://changedetection.io"),
+                'notification_urls': notification_urls
+            }
+
+            # Only use if present, if not set in n_object it should use the default system value
+            if 'notification_format' in request.form and request.form['notification_format'].strip():
+                n_object['notification_format'] = request.form.get('notification_format', '').strip()
+
+            if 'notification_title' in request.form and request.form['notification_title'].strip():
+                n_object['notification_title'] = request.form.get('notification_title', '').strip()
+            elif datastore.data['settings']['application'].get('notification_title'):
+                n_object['notification_title'] = datastore.data['settings']['application'].get('notification_title')
+            else:
+                n_object['notification_title'] = "Test title"
+
+            if 'notification_body' in request.form and request.form['notification_body'].strip():
+                n_object['notification_body'] = request.form.get('notification_body', '').strip()
+            elif datastore.data['settings']['application'].get('notification_body'):
+                n_object['notification_body'] = datastore.data['settings']['application'].get('notification_body')
+            else:
+                n_object['notification_body'] = "Test body"
+
+            n_object['as_async'] = False
+            n_object.update(watch.extra_notification_token_values())
+            from changedetectionio.notification import process_notification
+            sent_obj = process_notification(n_object, datastore)
+
+        except Exception as e:
+            e_str = str(e)
+            # Remove this text which is not important and floods the container
+            e_str = e_str.replace(
+                "DEBUG - <class 'apprise.decorators.base.CustomNotifyPlugin.instantiate_plugin.<locals>.CustomNotifyPluginWrapper'>",
+                '')
+
+            return make_response(e_str, 400)
+
+        return 'OK - Sent test notifications'
+
+    return notification_blueprint

changedetectionio/blueprint/ui/templates/clear_all_history.html

@@ -0,0 +1,49 @@
+{% extends 'base.html' %} {% block content %}
+<div class="edit-form">
+  <div class="box-wrap inner">
+    <form
+      class="pure-form pure-form-stacked"
+      action="{{url_for('ui.clear_all_history')}}"
+      method="POST"
+    >
+      <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
+      <fieldset>
+        <div class="pure-control-group">
+          This will remove version history (snapshots) for ALL watches, but keep
+          your list of URLs! <br />
+          You may like to use the <strong>BACKUP</strong> link first.<br />
+        </div>
+        <br />
+        <div class="pure-control-group">
+          <label for="confirmtext">Confirmation text</label>
+          <input
+            type="text"
+            id="confirmtext"
+            required=""
+            name="confirmtext"
+            value=""
+            size="10"
+          />
+          <span class="pure-form-message-inline"
+            >Type in the word <strong>clear</strong> to confirm that you
+            understand.</span
+          >
+        </div>
+        <br />
+        <div class="pure-control-group">
+          <button type="submit" class="pure-button pure-button-primary">
+            Clear History!
+          </button>
+        </div>
+        <br />
+        <div class="pure-control-group">
+          <a href="{{url_for('index')}}" class="pure-button button-cancel"
+            >Cancel</a
+          >
+        </div>
+      </fieldset>
+    </form>
+  </div>
+</div>
+
+{% endblock %}

changedetectionio/blueprint/ui/views.py

@@ -0,0 +1,220 @@
+from flask import Blueprint, request, redirect, url_for, flash, render_template, make_response, send_from_directory, abort
+from flask_login import current_user
+import os
+import time
+from copy import deepcopy
+
+from changedetectionio.store import ChangeDetectionStore
+from changedetectionio.auth_decorator import login_optionally_required
+from changedetectionio import html_tools
+
+def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMetaData):
+    views_blueprint = Blueprint('ui_views', __name__, template_folder="../ui/templates")
+    
+    @views_blueprint.route("/preview/<string:uuid>", methods=['GET'])
+    @login_optionally_required
+    def preview_page(uuid):
+        content = []
+        versions = []
+        timestamp = None
+
+        # More for testing, possible to return the first/only
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
+
+        try:
+            watch = datastore.data['watching'][uuid]
+        except KeyError:
+            flash("No history found for the specified link, bad link?", "error")
+            return redirect(url_for('index'))
+
+        system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
+        extra_stylesheets = [url_for('static_content', group='styles', filename='diff.css')]
+
+        is_html_webdriver = False
+        if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
+            is_html_webdriver = True
+        triggered_line_numbers = []
+        if datastore.data['watching'][uuid].history_n == 0 and (watch.get_error_text() or watch.get_error_snapshot()):
+            flash("Preview unavailable - No fetch/check completed or triggers not reached", "error")
+        else:
+            # So prepare the latest preview or not
+            preferred_version = request.args.get('version')
+            versions = list(watch.history.keys())
+            timestamp = versions[-1]
+            if preferred_version and preferred_version in versions:
+                timestamp = preferred_version
+
+            try:
+                versions = list(watch.history.keys())
+                content = watch.get_history_snapshot(timestamp)
+
+                triggered_line_numbers = html_tools.strip_ignore_text(content=content,
+                                                                      wordlist=watch['trigger_text'],
+                                                                      mode='line numbers'
+                                                                      )
+
+            except Exception as e:
+                content.append({'line': f"File doesnt exist or unable to read timestamp {timestamp}", 'classes': ''})
+
+        output = render_template("preview.html",
+                                 content=content,
+                                 current_version=timestamp,
+                                 history_n=watch.history_n,
+                                 extra_stylesheets=extra_stylesheets,
+                                 extra_title=f" - Diff - {watch.label} @ {timestamp}",
+                                 triggered_line_numbers=triggered_line_numbers,
+                                 current_diff_url=watch['url'],
+                                 screenshot=watch.get_screenshot(),
+                                 watch=watch,
+                                 uuid=uuid,
+                                 is_html_webdriver=is_html_webdriver,
+                                 last_error=watch['last_error'],
+                                 last_error_text=watch.get_error_text(),
+                                 last_error_screenshot=watch.get_error_snapshot(),
+                                 versions=versions
+                                )
+
+        return output
+
+    @views_blueprint.route("/diff/<string:uuid>", methods=['GET', 'POST'])
+    @login_optionally_required
+    def diff_history_page(uuid):
+        from changedetectionio import forms
+
+        # More for testing, possible to return the first/only
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
+
+        extra_stylesheets = [url_for('static_content', group='styles', filename='diff.css')]
+        try:
+            watch = datastore.data['watching'][uuid]
+        except KeyError:
+            flash("No history found for the specified link, bad link?", "error")
+            return redirect(url_for('index'))
+
+        # For submission of requesting an extract
+        extract_form = forms.extractDataForm(request.form)
+        if request.method == 'POST':
+            if not extract_form.validate():
+                flash("An error occurred, please see below.", "error")
+
+            else:
+                extract_regex = request.form.get('extract_regex').strip()
+                output = watch.extract_regex_from_all_history(extract_regex)
+                if output:
+                    watch_dir = os.path.join(datastore.datastore_path, uuid)
+                    response = make_response(send_from_directory(directory=watch_dir, path=output, as_attachment=True))
+                    response.headers['Content-type'] = 'text/csv'
+                    response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
+                    response.headers['Pragma'] = 'no-cache'
+                    response.headers['Expires'] = 0
+                    return response
+
+                flash('Nothing matches that RegEx', 'error')
+                redirect(url_for('ui_views.diff_history_page', uuid=uuid)+'#extract')
+
+        history = watch.history
+        dates = list(history.keys())
+
+        if len(dates) < 2:
+            flash("Not enough saved change detection snapshots to produce a report.", "error")
+            return redirect(url_for('index'))
+
+        # Save the current newest history as the most recently viewed
+        datastore.set_last_viewed(uuid, time.time())
+
+        # Read as binary and force decode as UTF-8
+        # Windows may fail decode in python if we just use 'r' mode (chardet decode exception)
+        from_version = request.args.get('from_version')
+        from_version_index = -2  # second newest
+        if from_version and from_version in dates:
+            from_version_index = dates.index(from_version)
+        else:
+            from_version = dates[from_version_index]
+
+        try:
+            from_version_file_contents = watch.get_history_snapshot(dates[from_version_index])
+        except Exception as e:
+            from_version_file_contents = f"Unable to read to-version at index {dates[from_version_index]}.\n"
+
+        to_version = request.args.get('to_version')
+        to_version_index = -1
+        if to_version and to_version in dates:
+            to_version_index = dates.index(to_version)
+        else:
+            to_version = dates[to_version_index]
+
+        try:
+            to_version_file_contents = watch.get_history_snapshot(dates[to_version_index])
+        except Exception as e:
+            to_version_file_contents = "Unable to read to-version at index{}.\n".format(dates[to_version_index])
+
+        screenshot_url = watch.get_screenshot()
+
+        system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
+
+        is_html_webdriver = False
+        if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
+            is_html_webdriver = True
+
+        password_enabled_and_share_is_off = False
+        if datastore.data['settings']['application'].get('password') or os.getenv("SALTED_PASS", False):
+            password_enabled_and_share_is_off = not datastore.data['settings']['application'].get('shared_diff_access')
+
+        output = render_template("diff.html",
+                                 current_diff_url=watch['url'],
+                                 from_version=str(from_version),
+                                 to_version=str(to_version),
+                                 extra_stylesheets=extra_stylesheets,
+                                 extra_title=f" - Diff - {watch.label}",
+                                 extract_form=extract_form,
+                                 is_html_webdriver=is_html_webdriver,
+                                 last_error=watch['last_error'],
+                                 last_error_screenshot=watch.get_error_snapshot(),
+                                 last_error_text=watch.get_error_text(),
+                                 left_sticky=True,
+                                 newest=to_version_file_contents,
+                                 newest_version_timestamp=dates[-1],
+                                 password_enabled_and_share_is_off=password_enabled_and_share_is_off,
+                                 from_version_file_contents=from_version_file_contents,
+                                 to_version_file_contents=to_version_file_contents,
+                                 screenshot=screenshot_url,
+                                 uuid=uuid,
+                                 versions=dates, # All except current/last
+                                 watch_a=watch
+                                 )
+
+        return output
+
+    @views_blueprint.route("/form/add/quickwatch", methods=['POST'])
+    @login_optionally_required
+    def form_quick_watch_add():
+        from changedetectionio import forms
+        form = forms.quickWatchForm(request.form, datastore=datastore)
+
+        if not form.validate():
+            for widget, l in form.errors.items():
+                flash(','.join(l), 'error')
+            return redirect(url_for('index'))
+
+        url = request.form.get('url').strip()
+        if datastore.url_exists(url):
+            flash(f'Warning, URL {url} already exists', "notice")
+
+        add_paused = request.form.get('edit_and_watch_submit_button') != None
+        processor = request.form.get('processor', 'text_json_diff')
+        new_uuid = datastore.add_watch(url=url, tag=request.form.get('tags').strip(), extras={'paused': add_paused, 'processor': processor})
+
+        if new_uuid:
+            if add_paused:
+                flash('Watch added in Paused state, saving will unpause.')
+                return redirect(url_for('ui.ui_edit.edit_page', uuid=new_uuid, unpause_on_save=1, tag=request.args.get('tag')))
+            else:
+                # Straight into the queue.
+                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
+                flash("Watch added.")
+
+        return redirect(url_for('index', tag=request.args.get('tag','')))
+
+    return views_blueprint

changedetectionio/conditions/__init__.py

@@ -0,0 +1,135 @@
+from flask import Blueprint
+
+from json_logic.builtins import BUILTINS
+
+from .exceptions import EmptyConditionRuleRowNotUsable
+from .pluggy_interface import plugin_manager  # Import the pluggy plugin manager
+from . import default_plugin
+
+# List of all supported JSON Logic operators
+operator_choices = [
+    (None, "Choose one"),
+    (">", "Greater Than"),
+    ("<", "Less Than"),
+    (">=", "Greater Than or Equal To"),
+    ("<=", "Less Than or Equal To"),
+    ("==", "Equals"),
+    ("!=", "Not Equals"),
+    ("in", "Contains"),
+    ("!in", "Does Not Contain"),
+]
+
+# Fields available in the rules
+field_choices = [
+    (None, "Choose one"),
+]
+
+# The data we will feed the JSON Rules to see if it passes the test/conditions or not
+EXECUTE_DATA = {}
+
+
+# Define the extended operations dictionary
+CUSTOM_OPERATIONS = {
+    **BUILTINS,  # Include all standard operators
+}
+
+def filter_complete_rules(ruleset):
+    rules = [
+        rule for rule in ruleset
+        if all(value not in ("", False, "None", None) for value in [rule["operator"], rule["field"], rule["value"]])
+    ]
+    return rules
+
+def convert_to_jsonlogic(logic_operator: str, rule_dict: list):
+    """
+    Convert a structured rule dict into a JSON Logic rule.
+
+    :param rule_dict: Dictionary containing conditions.
+    :return: JSON Logic rule as a dictionary.
+    """
+
+
+    json_logic_conditions = []
+
+    for condition in rule_dict:
+        operator = condition["operator"]
+        field = condition["field"]
+        value = condition["value"]
+
+        if not operator or operator == 'None' or not value or not field:
+            raise EmptyConditionRuleRowNotUsable()
+
+        # Convert value to int/float if possible
+        try:
+            if isinstance(value, str) and "." in value and str != "None":
+                value = float(value)
+            else:
+                value = int(value)
+        except (ValueError, TypeError):
+            pass  # Keep as a string if conversion fails
+
+        # Handle different JSON Logic operators properly
+        if operator == "in":
+            json_logic_conditions.append({"in": [value, {"var": field}]})  # value first
+        elif operator in ("!", "!!", "-"):
+            json_logic_conditions.append({operator: [{"var": field}]})  # Unary operators
+        elif operator in ("min", "max", "cat"):
+            json_logic_conditions.append({operator: value})  # Multi-argument operators
+        else:
+            json_logic_conditions.append({operator: [{"var": field}, value]})  # Standard binary operators
+
+    return {logic_operator: json_logic_conditions} if len(json_logic_conditions) > 1 else json_logic_conditions[0]
+
+
+def execute_ruleset_against_all_plugins(current_watch_uuid: str, application_datastruct, ephemeral_data={} ):
+    """
+    Build our data and options by calling our plugins then pass it to jsonlogic and see if the conditions pass
+
+    :param ruleset: JSON Logic rule dictionary.
+    :param extracted_data: Dictionary containing the facts.   <-- maybe the app struct+uuid
+    :return: Dictionary of plugin results.
+    """
+    from json_logic import jsonLogic
+
+    EXECUTE_DATA = {}
+    result = True
+    
+    ruleset_settings = application_datastruct['watching'].get(current_watch_uuid)
+
+    if ruleset_settings.get("conditions"):
+        logic_operator = "and" if ruleset_settings.get("conditions_match_logic", "ALL") == "ALL" else "or"
+        complete_rules = filter_complete_rules(ruleset_settings['conditions'])
+        if complete_rules:
+            # Give all plugins a chance to update the data dict again (that we will test the conditions against)
+            for plugin in plugin_manager.get_plugins():
+                new_execute_data = plugin.add_data(current_watch_uuid=current_watch_uuid,
+                                                   application_datastruct=application_datastruct,
+                                                   ephemeral_data=ephemeral_data)
+
+                if new_execute_data and isinstance(new_execute_data, dict):
+                    EXECUTE_DATA.update(new_execute_data)
+
+            # Create the ruleset
+            ruleset = convert_to_jsonlogic(logic_operator=logic_operator, rule_dict=complete_rules)
+            
+            # Pass the custom operations dictionary to jsonLogic
+            if not jsonLogic(logic=ruleset, data=EXECUTE_DATA, operations=CUSTOM_OPERATIONS):
+                result = False
+
+    return result
+
+
+# Load plugins dynamically
+for plugin in plugin_manager.get_plugins():
+    new_ops = plugin.register_operators()
+    if isinstance(new_ops, dict):
+        CUSTOM_OPERATIONS.update(new_ops)
+
+    new_operator_choices = plugin.register_operator_choices()
+    if isinstance(new_operator_choices, list):
+        operator_choices.extend(new_operator_choices)
+
+    new_field_choices = plugin.register_field_choices()
+    if isinstance(new_field_choices, list):
+        field_choices.extend(new_field_choices)
+

changedetectionio/conditions/blueprint.py

@@ -0,0 +1,80 @@
+# Flask Blueprint Definition
+import json
+
+from flask import Blueprint
+
+from changedetectionio.conditions import execute_ruleset_against_all_plugins
+
+
+def construct_blueprint(datastore):
+    from changedetectionio.flask_app import login_optionally_required
+
+    conditions_blueprint = Blueprint('conditions', __name__, template_folder="templates")
+
+    @conditions_blueprint.route("/<string:watch_uuid>/verify-condition-single-rule", methods=['POST'])
+    @login_optionally_required
+    def verify_condition_single_rule(watch_uuid):
+        """Verify a single condition rule against the current snapshot"""
+        from changedetectionio.processors.text_json_diff import prepare_filter_prevew
+        from flask import request, jsonify
+        from copy import deepcopy
+
+        ephemeral_data = {}
+
+        # Get the watch data
+        watch = datastore.data['watching'].get(watch_uuid)
+        if not watch:
+            return jsonify({'status': 'error', 'message': 'Watch not found'}), 404
+
+        # First use prepare_filter_prevew to process the form data
+        # This will return text_after_filter which is after all current form settings are applied
+        # Create ephemeral data with the text from the current snapshot
+
+        try:
+            # Call prepare_filter_prevew to get a processed version of the content with current form settings
+            # We'll ignore the returned response and just use the datastore which is modified by the function
+
+            # this should apply all filters etc so then we can run the CONDITIONS against the final output text
+            result = prepare_filter_prevew(datastore=datastore,
+                                           form_data=request.form,
+                                           watch_uuid=watch_uuid)
+
+            ephemeral_data['text'] = result.get('after_filter', '')
+            # Create a temporary watch data structure with this single rule
+            tmp_watch_data = deepcopy(datastore.data['watching'].get(watch_uuid))
+
+            # Override the conditions in the temporary watch
+            rule_json = request.args.get("rule")
+            rule = json.loads(rule_json) if rule_json else None
+
+            # Should be key/value of field, operator, value
+            tmp_watch_data['conditions'] = [rule]
+            tmp_watch_data['conditions_match_logic'] = "ALL"  # Single rule, so use ALL
+
+            # Create a temporary application data structure for the rule check
+            temp_app_data = {
+                'watching': {
+                    watch_uuid: tmp_watch_data
+                }
+            }
+
+            # Execute the rule against the current snapshot with form data
+            result = execute_ruleset_against_all_plugins(
+                current_watch_uuid=watch_uuid,
+                application_datastruct=temp_app_data,
+                ephemeral_data=ephemeral_data
+            )
+
+            return jsonify({
+                'status': 'success',
+                'result': result,
+                'message': 'Condition passes' if result else 'Condition does not pass'
+            })
+
+        except Exception as e:
+            return jsonify({
+                'status': 'error',
+                'message': f'Error verifying condition: {str(e)}'
+            }), 500
+
+    return conditions_blueprint

changedetectionio/conditions/default_plugin.py

@@ -0,0 +1,78 @@
+import re
+
+import pluggy
+from price_parser import Price
+from loguru import logger
+
+hookimpl = pluggy.HookimplMarker("changedetectionio_conditions")
+
+
+@hookimpl
+def register_operators():
+    def starts_with(_, text, prefix):
+        return text.lower().strip().startswith(str(prefix).strip().lower())
+
+    def ends_with(_, text, suffix):
+        return text.lower().strip().endswith(str(suffix).strip().lower())
+
+    def length_min(_, text, strlen):
+        return len(text) >= int(strlen)
+
+    def length_max(_, text, strlen):
+        return len(text) <= int(strlen)
+
+    # ✅ Custom function for case-insensitive regex matching
+    def contains_regex(_, text, pattern):
+        """Returns True if `text` contains `pattern` (case-insensitive regex match)."""
+        return bool(re.search(pattern, str(text), re.IGNORECASE))
+
+    # ✅ Custom function for NOT matching case-insensitive regex
+    def not_contains_regex(_, text, pattern):
+        """Returns True if `text` does NOT contain `pattern` (case-insensitive regex match)."""
+        return not bool(re.search(pattern, str(text), re.IGNORECASE))
+
+    return {
+        "!contains_regex": not_contains_regex,
+        "contains_regex": contains_regex,
+        "ends_with": ends_with,
+        "length_max": length_max,
+        "length_min": length_min,
+        "starts_with": starts_with,
+    }
+
+@hookimpl
+def register_operator_choices():
+    return [
+        ("starts_with", "Text Starts With"),
+        ("ends_with", "Text Ends With"),
+        ("length_min", "Length minimum"),
+        ("length_max", "Length maximum"),
+        ("contains_regex", "Text Matches Regex"),
+        ("!contains_regex", "Text Does NOT Match Regex"),
+    ]
+
+@hookimpl
+def register_field_choices():
+    return [
+        ("extracted_number", "Extracted number after 'Filters & Triggers'"),
+#        ("meta_description", "Meta Description"),
+#        ("meta_keywords", "Meta Keywords"),
+        ("page_filtered_text", "Page text after 'Filters & Triggers'"),
+        #("page_title", "Page <title>"), # actual page title <title>
+    ]
+
+@hookimpl
+def add_data(current_watch_uuid, application_datastruct, ephemeral_data):
+
+    res = {}
+    if 'text' in ephemeral_data:
+        res['page_filtered_text'] = ephemeral_data['text']
+
+        # Better to not wrap this in try/except so that the UI can see any errors
+        price = Price.fromstring(ephemeral_data.get('text'))
+        if price and price.amount != None:
+            # This is slightly misleading, it's extracting a PRICE not a Number..
+            res['extracted_number'] = float(price.amount)
+            logger.debug(f"Extracted number result: '{price}' - returning float({res['extracted_number']})")
+
+    return res

changedetectionio/conditions/exceptions.py

@@ -0,0 +1,6 @@
+class EmptyConditionRuleRowNotUsable(Exception):
+    def __init__(self):
+        super().__init__("One of the 'conditions' rulesets is incomplete, cannot run.")
+
+    def __str__(self):
+        return self.args[0]

changedetectionio/conditions/form.py

@@ -0,0 +1,44 @@
+# Condition Rule Form (for each rule row)
+from wtforms import Form, SelectField, StringField, validators
+from wtforms import validators
+
+class ConditionFormRow(Form):
+
+    # ✅ Ensure Plugins Are Loaded BEFORE Importing Choices
+    from changedetectionio.conditions import plugin_manager
+    from changedetectionio.conditions import operator_choices, field_choices
+    field = SelectField(
+        "Field",
+        choices=field_choices,
+        validators=[validators.Optional()]
+    )
+
+    operator = SelectField(
+        "Operator",
+        choices=operator_choices,
+        validators=[validators.Optional()]
+    )
+
+    value = StringField("Value", validators=[validators.Optional()])
+
+    def validate(self, extra_validators=None):
+        # First, run the default validators
+        if not super().validate(extra_validators):
+            return False
+
+        # Custom validation logic
+        # If any of the operator/field/value is set, then they must be all set
+        if any(value not in ("", False, "None", None) for value in [self.operator.data, self.field.data, self.value.data]):
+            if not self.operator.data or self.operator.data == 'None':
+                self.operator.errors.append("Operator is required.")
+                return False
+
+            if not self.field.data or self.field.data == 'None':
+                self.field.errors.append("Field is required.")
+                return False
+
+            if not self.value.data:
+                self.value.errors.append("Value is required.")
+                return False
+
+        return True  # Only return True if all conditions pass

changedetectionio/conditions/pluggy_interface.py

@@ -0,0 +1,44 @@
+import pluggy
+from . import default_plugin  # Import the default plugin
+
+# ✅ Ensure that the namespace in HookspecMarker matches PluginManager
+PLUGIN_NAMESPACE = "changedetectionio_conditions"
+
+hookspec = pluggy.HookspecMarker(PLUGIN_NAMESPACE)
+hookimpl = pluggy.HookimplMarker(PLUGIN_NAMESPACE)
+
+
+class ConditionsSpec:
+    """Hook specifications for extending JSON Logic conditions."""
+
+    @hookspec
+    def register_operators():
+        """Return a dictionary of new JSON Logic operators."""
+        pass
+
+    @hookspec
+    def register_operator_choices():
+        """Return a list of new operator choices."""
+        pass
+
+    @hookspec
+    def register_field_choices():
+        """Return a list of new field choices."""
+        pass
+
+    @hookspec
+    def add_data(current_watch_uuid, application_datastruct, ephemeral_data):
+        """Add to the datadict"""
+        pass
+
+# ✅ Set up Pluggy Plugin Manager
+plugin_manager = pluggy.PluginManager(PLUGIN_NAMESPACE)
+
+# ✅ Register hookspecs (Ensures they are detected)
+plugin_manager.add_hookspecs(ConditionsSpec)
+
+# ✅ Register built-in plugins manually
+plugin_manager.register(default_plugin, "default_plugin")
+
+# ✅ Discover installed plugins from external packages (if any)
+plugin_manager.load_setuptools_entrypoints(PLUGIN_NAMESPACE)

changedetectionio/content_fetchers/__init__.py

@@ -4,7 +4,9 @@ from loguru import logger
 from changedetectionio.content_fetchers.exceptions import BrowserStepsStepException
 import os
 
-visualselector_xpath_selectors = 'div,span,form,table,tbody,tr,td,a,p,ul,li,h1,h2,h3,h4,header,footer,section,article,aside,details,main,nav,section,summary'
+# Visual Selector scraper - 'Button' is there because some sites have <button>OUT OF STOCK</button>.
+visualselector_xpath_selectors = 'div,span,form,table,tbody,tr,td,a,p,ul,li,h1,h2,h3,h4,header,footer,section,article,aside,details,main,nav,section,summary,button'
+
 
 # available_fetchers() will scan this implementation looking for anything starting with html_
 # this information is used in the form selections

changedetectionio/content_fetchers/base.py

@@ -65,8 +65,8 @@ class Fetcher():
 
     def __init__(self):
         import importlib.resources
-        self.xpath_element_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text()
-        self.instock_data_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('stock-not-in-stock.js').read_text()
+        self.xpath_element_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('xpath_element_scraper.js').read_text(encoding='utf-8')
+        self.instock_data_js = importlib.resources.files("changedetectionio.content_fetchers.res").joinpath('stock-not-in-stock.js').read_text(encoding='utf-8')
 
     @abstractmethod
     def get_error(self):
@@ -81,7 +81,8 @@ class Fetcher():
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False):
+            is_binary=False,
+            empty_pages_are_a_change=False):
         # Should set self.error, self.status_code and self.content
         pass
 

changedetectionio/content_fetchers/helpers.py

@@ -0,0 +1,104 @@
+
+# Pages with a vertical height longer than this will use the 'stitch together' method.
+
+# - Many GPUs have a max texture size of 16384x16384px (or lower on older devices).
+# - If a page is taller than ~8000–10000px, it risks exceeding GPU memory limits.
+# - This is especially important on headless Chromium, where Playwright may fail to allocate a massive full-page buffer.
+
+
+# The size at which we will switch to stitching method
+SCREENSHOT_SIZE_STITCH_THRESHOLD=8000
+
+from loguru import logger
+
+def capture_stitched_together_full_page(page):
+    import io
+    import os
+    import time
+    from PIL import Image, ImageDraw, ImageFont
+
+    MAX_TOTAL_HEIGHT = SCREENSHOT_SIZE_STITCH_THRESHOLD*4  # Maximum total height for the final image (When in stitch mode)
+    MAX_CHUNK_HEIGHT = 4000  # Height per screenshot chunk
+    WARNING_TEXT_HEIGHT = 20  # Height of the warning text overlay
+
+    # Save the original viewport size
+    original_viewport = page.viewport_size
+    now = time.time()
+
+    try:
+        viewport = page.viewport_size
+        page_height = page.evaluate("document.documentElement.scrollHeight")
+
+        # Limit the total capture height
+        capture_height = min(page_height, MAX_TOTAL_HEIGHT)
+
+        images = []
+        total_captured_height = 0
+
+        for offset in range(0, capture_height, MAX_CHUNK_HEIGHT):
+            # Ensure we do not exceed the total height limit
+            chunk_height = min(MAX_CHUNK_HEIGHT, MAX_TOTAL_HEIGHT - total_captured_height)
+
+            # Adjust viewport size for this chunk
+            page.set_viewport_size({"width": viewport["width"], "height": chunk_height})
+
+            # Scroll to the correct position
+            page.evaluate(f"window.scrollTo(0, {offset})")
+
+            # Capture screenshot chunk
+            screenshot_bytes = page.screenshot(type='jpeg', quality=int(os.getenv("SCREENSHOT_QUALITY", 30)))
+            images.append(Image.open(io.BytesIO(screenshot_bytes)))
+
+            total_captured_height += chunk_height
+
+            # Stop if we reached the maximum total height
+            if total_captured_height >= MAX_TOTAL_HEIGHT:
+                break
+
+        # Create the final stitched image
+        stitched_image = Image.new('RGB', (viewport["width"], total_captured_height))
+        y_offset = 0
+
+        # Stitch the screenshot chunks together
+        for img in images:
+            stitched_image.paste(img, (0, y_offset))
+            y_offset += img.height
+
+        logger.debug(f"Screenshot stitched together in {time.time()-now:.2f}s")
+
+        # Overlay warning text if the screenshot was trimmed
+        if page_height > MAX_TOTAL_HEIGHT:
+            draw = ImageDraw.Draw(stitched_image)
+            warning_text = f"WARNING: Screenshot was {page_height}px but trimmed to {MAX_TOTAL_HEIGHT}px because it was too long"
+
+            # Load font (default system font if Arial is unavailable)
+            try:
+                font = ImageFont.truetype("arial.ttf", WARNING_TEXT_HEIGHT)  # Arial (Windows/Mac)
+            except IOError:
+                font = ImageFont.load_default()  # Default font if Arial not found
+
+            # Get text bounding box (correct method for newer Pillow versions)
+            text_bbox = draw.textbbox((0, 0), warning_text, font=font)
+            text_width = text_bbox[2] - text_bbox[0]  # Calculate text width
+            text_height = text_bbox[3] - text_bbox[1]  # Calculate text height
+
+            # Define background rectangle (top of the image)
+            draw.rectangle([(0, 0), (viewport["width"], WARNING_TEXT_HEIGHT)], fill="white")
+
+            # Center text horizontally within the warning area
+            text_x = (viewport["width"] - text_width) // 2
+            text_y = (WARNING_TEXT_HEIGHT - text_height) // 2
+
+            # Draw the warning text in red
+            draw.text((text_x, text_y), warning_text, fill="red", font=font)
+
+        # Save or return the final image
+        output = io.BytesIO()
+        stitched_image.save(output, format="JPEG", quality=int(os.getenv("SCREENSHOT_QUALITY", 30)))
+        screenshot = output.getvalue()
+
+    finally:
+        # Restore the original viewport size
+        page.set_viewport_size(original_viewport)
+
+    return screenshot

changedetectionio/content_fetchers/playwright.py

@@ -4,6 +4,7 @@ from urllib.parse import urlparse
 
 from loguru import logger
 
+from changedetectionio.content_fetchers.helpers import capture_stitched_together_full_page, SCREENSHOT_SIZE_STITCH_THRESHOLD
 from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
 from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, ScreenshotUnavailable
 
@@ -83,11 +84,13 @@ class fetcher(Fetcher):
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False):
+            is_binary=False,
+            empty_pages_are_a_change=False):
 
         from playwright.sync_api import sync_playwright
         import playwright._impl._errors
         from changedetectionio.content_fetchers import visualselector_xpath_selectors
+        import time
         self.delete_browser_steps_screenshots()
         response = None
 
@@ -130,7 +133,7 @@ class fetcher(Fetcher):
             if response is None:
                 context.close()
                 browser.close()
-                logger.debug("Content Fetcher > Response object was none")
+                logger.debug("Content Fetcher > Response object from the browser communication was none")
                 raise EmptyReply(url=url, status_code=None)
 
             try:
@@ -166,10 +169,10 @@ class fetcher(Fetcher):
 
                 raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
 
-            if len(self.page.content().strip()) == 0:
+            if not empty_pages_are_a_change and len(self.page.content().strip()) == 0:
+                logger.debug("Content Fetcher > Content was empty, empty_pages_are_a_change = False")
                 context.close()
                 browser.close()
-                logger.debug("Content Fetcher > Content was empty")
                 raise EmptyReply(url=url, status_code=response.status)
 
             # Run Browser Steps here
@@ -178,6 +181,7 @@ class fetcher(Fetcher):
 
             self.page.wait_for_timeout(extra_wait * 1000)
 
+            now = time.time()
             # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
             if current_include_filters is not None:
                 self.page.evaluate("var include_filters={}".format(json.dumps(current_include_filters)))
@@ -189,6 +193,8 @@ class fetcher(Fetcher):
             self.instock_data = self.page.evaluate("async () => {" + self.instock_data_js + "}")
 
             self.content = self.page.content()
+            logger.debug(f"Time to scrape xpath element data in browser {time.time() - now:.2f}s")
+
             # Bug 3 in Playwright screenshot handling
             # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
             # JPEG is better here because the screenshots can be very very large
@@ -198,10 +204,15 @@ class fetcher(Fetcher):
             # acceptable screenshot quality here
             try:
                 # The actual screenshot - this always base64 and needs decoding! horrible! huge CPU usage
-                self.screenshot = self.page.screenshot(type='jpeg',
-                                                       full_page=True,
-                                                       quality=int(os.getenv("SCREENSHOT_QUALITY", 72)),
-                                                       )
+                full_height = self.page.evaluate("document.documentElement.scrollHeight")
+
+                if full_height >= SCREENSHOT_SIZE_STITCH_THRESHOLD:
+                    logger.warning(
+                        f"Page full Height: {full_height}px longer than {SCREENSHOT_SIZE_STITCH_THRESHOLD}px, using 'stitched screenshot method'.")
+                    self.screenshot = capture_stitched_together_full_page(self.page)
+                else:
+                    self.screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("SCREENSHOT_QUALITY", 30)))
+
             except Exception as e:
                 # It's likely the screenshot was too long/big and something crashed
                 raise ScreenshotUnavailable(url=url, status_code=self.status_code)

changedetectionio/content_fetchers/puppeteer.py

@@ -75,7 +75,8 @@ class fetcher(Fetcher):
                          request_method,
                          ignore_status_codes,
                          current_include_filters,
-                         is_binary
+                         is_binary,
+                         empty_pages_are_a_change
                          ):
 
         from changedetectionio.content_fetchers import visualselector_xpath_selectors
@@ -153,7 +154,7 @@ class fetcher(Fetcher):
         if response is None:
             await self.page.close()
             await browser.close()
-            logger.warning("Content Fetcher > Response object was none")
+            logger.warning("Content Fetcher > Response object was none (as in, the response from the browser was empty, not just the content)")
             raise EmptyReply(url=url, status_code=None)
 
         self.headers = response.headers
@@ -186,10 +187,11 @@ class fetcher(Fetcher):
 
             raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
         content = await self.page.content
-        if len(content.strip()) == 0:
+
+        if not empty_pages_are_a_change and len(content.strip()) == 0:
+            logger.error("Content Fetcher > Content was empty (empty_pages_are_a_change is False), closing browsers")
             await self.page.close()
             await browser.close()
-            logger.error("Content Fetcher > Content was empty")
             raise EmptyReply(url=url, status_code=response.status)
 
         # Run Browser Steps here
@@ -247,7 +249,7 @@ class fetcher(Fetcher):
         await self.fetch_page(**kwargs)
 
     def run(self, url, timeout, request_headers, request_body, request_method, ignore_status_codes=False,
-            current_include_filters=None, is_binary=False):
+            current_include_filters=None, is_binary=False, empty_pages_are_a_change=False):
 
         #@todo make update_worker async which could run any of these content_fetchers within memory and time constraints
         max_time = os.getenv('PUPPETEER_MAX_PROCESSING_TIMEOUT_SECONDS', 180)
@@ -262,7 +264,8 @@ class fetcher(Fetcher):
                 request_method=request_method,
                 ignore_status_codes=ignore_status_codes,
                 current_include_filters=current_include_filters,
-                is_binary=is_binary
+                is_binary=is_binary,
+                empty_pages_are_a_change=empty_pages_are_a_change
             ), timeout=max_time))
         except asyncio.TimeoutError:
             raise(BrowserFetchTimedOut(msg=f"Browser connected but was unable to process the page in {max_time} seconds."))

changedetectionio/content_fetchers/requests.py

@@ -1,9 +1,6 @@
+from loguru import logger
 import hashlib
 import os
-
-import chardet
-import requests
-
 from changedetectionio import strtobool
 from changedetectionio.content_fetchers.exceptions import BrowserStepsInUnsupportedFetcher, EmptyReply, Non200ErrorCodeReceived
 from changedetectionio.content_fetchers.base import Fetcher
@@ -26,7 +23,11 @@ class fetcher(Fetcher):
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False):
+            is_binary=False,
+            empty_pages_are_a_change=False):
+
+        import chardet
+        import requests
 
         if self.browser_steps_get_valid_steps():
             raise BrowserStepsInUnsupportedFetcher(url=url)
@@ -53,7 +54,7 @@ class fetcher(Fetcher):
             session.mount('file://', FileAdapter())
 
         r = session.request(method=request_method,
-                            data=request_body,
+                            data=request_body.encode('utf-8') if type(request_body) is str else request_body,
                             url=url,
                             headers=request_headers,
                             timeout=timeout,
@@ -74,7 +75,11 @@ class fetcher(Fetcher):
         self.headers = r.headers
 
         if not r.content or not len(r.content):
-            raise EmptyReply(url=url, status_code=r.status_code)
+            logger.debug(f"Requests returned empty content for '{url}'")
+            if not empty_pages_are_a_change:
+                raise EmptyReply(url=url, status_code=r.status_code)
+            else:
+                logger.debug(f"URL {url} gave zero byte content reply with Status Code {r.status_code}, but empty_pages_are_a_change = True")
 
         # @todo test this
         # @todo maybe you really want to test zero-byte return pages?

changedetectionio/content_fetchers/res/stock-not-in-stock.js

@@ -29,7 +29,12 @@ function isItemInStock() {
         'currently unavailable',
         'dieser artikel ist bald wieder verfügbar',
         'dostępne wkrótce',
+        'en rupture',
         'en rupture de stock',
+        'épuisé',
+        'esgotado',
+        'indisponible',
+        'indisponível',
         'isn\'t in stock right now',
         'isnt in stock right now',
         'isn’t in stock right now',
@@ -37,6 +42,7 @@ function isItemInStock() {
         'let me know when it\'s available',
         'mail me when available',
         'message if back in stock',
+        'mevcut değil',
         'nachricht bei',
         'nicht auf lager',
         'nicht lagernd',
@@ -48,7 +54,9 @@ function isItemInStock() {
         'niet beschikbaar',
         'niet leverbaar',
         'niet op voorraad',
-        'no disponible temporalmente',
+        'no disponible',
+        'non disponibile',
+        'non disponible',
         'no longer in stock',
         'no tickets available',
         'not available',
@@ -57,24 +65,30 @@ function isItemInStock() {
         'notify me when available',
         'notify me',
         'notify when available',
+        'não disponível',
         'não estamos a aceitar encomendas',
         'out of stock',
         'out-of-stock',
+        'plus disponible',
         'prodotto esaurito',
         'produkt niedostępny',
+        'rupture',
         'sold out',
         'sold-out',
+        'stokta yok',
         'temporarily out of stock',
         'temporarily unavailable',
         'there were no search results for',
         'this item is currently unavailable',
         'tickets unavailable',
         'tijdelijk uitverkocht',
+        'tükendi',
         'unavailable nearby',
         'unavailable tickets',
         'vergriffen',
         'vorbestellen',
         'vorbestellung ist bald möglich',
+        'we don\'t currently have any',
         'we couldn\'t find any products that match',
         'we do not currently have an estimate of when this product will be back in stock.',
         'we don\'t know when or if this item will be back in stock.',
@@ -153,10 +167,14 @@ function isItemInStock() {
         }
 
         elementText = "";
-        if (element.tagName.toLowerCase() === "input") {
-            elementText = element.value.toLowerCase().trim();
-        } else {
-            elementText = getElementBaseText(element);
+        try {
+            if (element.tagName.toLowerCase() === "input") {
+                elementText = element.value.toLowerCase().trim();
+            } else {
+                elementText = getElementBaseText(element);
+            }
+        } catch (e) {
+            console.warn('stock-not-in-stock.js scraper - handling element for gettext failed', e);
         }
 
         if (elementText.length) {
@@ -173,7 +191,8 @@ function isItemInStock() {
         const element = elementsToScan[i];
         // outside the 'fold' or some weird text in the heading area
         // .getBoundingClientRect() was causing a crash in chrome 119, can only be run on contentVisibility != hidden
-        if (element.getBoundingClientRect().top + window.scrollY >= vh + 150 || element.getBoundingClientRect().top + window.scrollY <= 100) {
+        // Note: theres also an automated test that places the 'out of stock' text fairly low down
+        if (element.getBoundingClientRect().top + window.scrollY >= vh + 250 || element.getBoundingClientRect().top + window.scrollY <= 100) {
             continue
         }
         elementText = "";
@@ -187,7 +206,7 @@ function isItemInStock() {
             // and these mean its out of stock
             for (const outOfStockText of outOfStockTexts) {
                 if (elementText.includes(outOfStockText)) {
-                    console.log(`Selected 'Out of Stock' - found text "${outOfStockText}" - "${elementText}"`)
+                    console.log(`Selected 'Out of Stock' - found text "${outOfStockText}" - "${elementText}" - offset top ${element.getBoundingClientRect().top}, page height is ${vh}`)
                     return outOfStockText; // item is out of stock
                 }
             }

changedetectionio/content_fetchers/res/xpath_element_scraper.js

@@ -41,7 +41,7 @@ const findUpTag = (el) => {
 
     //  Strategy 1: If it's an input, with name, and there's only one, prefer that
     if (el.name !== undefined && el.name.length) {
-        var proposed = el.tagName + "[name=" + el.name + "]";
+        var proposed = el.tagName + "[name=\"" + CSS.escape(el.name) + "\"]";
         var proposed_element = window.document.querySelectorAll(proposed);
         if (proposed_element.length) {
             if (proposed_element.length === 1) {
@@ -102,13 +102,15 @@ function collectVisibleElements(parent, visibleElements) {
     const children = parent.children;
     for (let i = 0; i < children.length; i++) {
         const child = children[i];
+        const computedStyle = window.getComputedStyle(child);
+
         if (
             child.nodeType === Node.ELEMENT_NODE &&
-            window.getComputedStyle(child).display !== 'none' &&
-            window.getComputedStyle(child).visibility !== 'hidden' &&
+            computedStyle.display !== 'none' &&
+            computedStyle.visibility !== 'hidden' &&
             child.offsetWidth >= 0 &&
             child.offsetHeight >= 0 &&
-            window.getComputedStyle(child).contentVisibility !== 'hidden'
+            computedStyle.contentVisibility !== 'hidden'
         ) {
             // If the child is an element and is visible, recursively collect visible elements
             collectVisibleElements(child, visibleElements);
@@ -164,6 +166,16 @@ visibleElementsArray.forEach(function (element) {
         }
     }
 
+    let label = "not-interesting" // A placeholder, the actual labels for training are done by hand for now
+
+    let text = element.textContent.trim().slice(0, 30).trim();
+    while (/\n{2,}|\t{2,}/.test(text)) {
+        text = text.replace(/\n{2,}/g, '\n').replace(/\t{2,}/g, '\t')
+    }
+
+    // Try to identify any possible currency amounts "Sale: 4000" or "Sale now 3000 Kc", can help with the training.
+    const hasDigitCurrency = (/\d/.test(text.slice(0, 6)) || /\d/.test(text.slice(-6)) ) &&  /([€£$¥₩₹]|USD|AUD|EUR|Kč|kr|SEK|,–)/.test(text) ;
+    const computedStyle = window.getComputedStyle(element);
 
     size_pos.push({
         xpath: xpath_result,
@@ -171,9 +183,16 @@ visibleElementsArray.forEach(function (element) {
         height: Math.round(bbox['height']),
         left: Math.floor(bbox['left']),
         top: Math.floor(bbox['top']) + scroll_y,
+        // tagName used by Browser Steps
         tagName: (element.tagName) ? element.tagName.toLowerCase() : '',
+        // tagtype used by Browser Steps
         tagtype: (element.tagName.toLowerCase() === 'input' && element.type) ? element.type.toLowerCase() : '',
-        isClickable: window.getComputedStyle(element).cursor == "pointer"
+        isClickable: computedStyle.cursor === "pointer",
+        // Used by the keras trainer
+        fontSize: computedStyle.getPropertyValue('font-size'),
+        fontWeight: computedStyle.getPropertyValue('font-weight'),
+        hasDigitCurrency: hasDigitCurrency,
+        label: label,
     });
 
 });
@@ -214,7 +233,7 @@ if (include_filters.length) {
             console.log(e);
         }
 
-        if (results.length) {
+        if (results != null && results.length) {
 
             // Iterate over the results
             results.forEach(node => {

changedetectionio/content_fetchers/webdriver_selenium.py

@@ -56,7 +56,8 @@ class fetcher(Fetcher):
             request_method,
             ignore_status_codes=False,
             current_include_filters=None,
-            is_binary=False):
+            is_binary=False,
+            empty_pages_are_a_change=False):
 
         from selenium import webdriver
         from selenium.webdriver.chrome.options import Options as ChromeOptions

changedetectionio/diff.py

@@ -1,6 +1,9 @@
 import difflib
 from typing import List, Iterator, Union
 
+REMOVED_STYLE = "background-color: #fadad7; color: #b30000;"
+ADDED_STYLE = "background-color: #eaf2c2; color: #406619;"
+
 def same_slicer(lst: List[str], start: int, end: int) -> List[str]:
     """Return a slice of the list, or a single element if start == end."""
     return lst[start:end] if start != end else [lst[start]]
@@ -12,11 +15,12 @@ def customSequenceMatcher(
     include_removed: bool = True,
     include_added: bool = True,
     include_replaced: bool = True,
-    include_change_type_prefix: bool = True
+    include_change_type_prefix: bool = True,
+    html_colour: bool = False
 ) -> Iterator[List[str]]:
     """
     Compare two sequences and yield differences based on specified parameters.
-    
+
     Args:
         before (List[str]): Original sequence
         after (List[str]): Modified sequence
@@ -25,26 +29,35 @@ def customSequenceMatcher(
         include_added (bool): Include added parts
         include_replaced (bool): Include replaced parts
         include_change_type_prefix (bool): Add prefixes to indicate change types
-    
+        html_colour (bool): Use HTML background colors for differences
+
     Yields:
         List[str]: Differences between sequences
     """
     cruncher = difflib.SequenceMatcher(isjunk=lambda x: x in " \t", a=before, b=after)
-    
+
+
+
     for tag, alo, ahi, blo, bhi in cruncher.get_opcodes():
         if include_equal and tag == 'equal':
             yield before[alo:ahi]
         elif include_removed and tag == 'delete':
-            prefix = "(removed) " if include_change_type_prefix else ''
-            yield [f"{prefix}{line}" for line in same_slicer(before, alo, ahi)]
+            if html_colour:
+                yield [f'<span style="{REMOVED_STYLE}">{line}</span>' for line in same_slicer(before, alo, ahi)]
+            else:
+                yield [f"(removed) {line}" for line in same_slicer(before, alo, ahi)] if include_change_type_prefix else same_slicer(before, alo, ahi)
         elif include_replaced and tag == 'replace':
-            prefix_changed = "(changed) " if include_change_type_prefix else ''
-            prefix_into = "(into) " if include_change_type_prefix else ''
-            yield [f"{prefix_changed}{line}" for line in same_slicer(before, alo, ahi)] + \
-                  [f"{prefix_into}{line}" for line in same_slicer(after, blo, bhi)]
+            if html_colour:
+                yield [f'<span style="{REMOVED_STYLE}">{line}</span>' for line in same_slicer(before, alo, ahi)] + \
+                      [f'<span style="{ADDED_STYLE}">{line}</span>' for line in same_slicer(after, blo, bhi)]
+            else:
+                yield [f"(changed) {line}" for line in same_slicer(before, alo, ahi)] + \
+                      [f"(into) {line}" for line in same_slicer(after, blo, bhi)] if include_change_type_prefix else same_slicer(before, alo, ahi) + same_slicer(after, blo, bhi)
         elif include_added and tag == 'insert':
-            prefix = "(added) " if include_change_type_prefix else ''
-            yield [f"{prefix}{line}" for line in same_slicer(after, blo, bhi)]
+            if html_colour:
+                yield [f'<span style="{ADDED_STYLE}">{line}</span>' for line in same_slicer(after, blo, bhi)]
+            else:
+                yield [f"(added) {line}" for line in same_slicer(after, blo, bhi)] if include_change_type_prefix else same_slicer(after, blo, bhi)
 
 def render_diff(
     previous_version_file_contents: str,
@@ -55,11 +68,12 @@ def render_diff(
     include_replaced: bool = True,
     line_feed_sep: str = "\n",
     include_change_type_prefix: bool = True,
-    patch_format: bool = False
+    patch_format: bool = False,
+    html_colour: bool = False
 ) -> str:
     """
     Render the difference between two file contents.
-    
+
     Args:
         previous_version_file_contents (str): Original file contents
         newest_version_file_contents (str): Modified file contents
@@ -70,7 +84,8 @@ def render_diff(
         line_feed_sep (str): Separator for lines in output
         include_change_type_prefix (bool): Add prefixes to indicate change types
         patch_format (bool): Use patch format for output
-    
+        html_colour (bool): Use HTML background colors for differences
+
     Returns:
         str: Rendered difference
     """
@@ -88,10 +103,11 @@ def render_diff(
         include_removed=include_removed,
         include_added=include_added,
         include_replaced=include_replaced,
-        include_change_type_prefix=include_change_type_prefix
+        include_change_type_prefix=include_change_type_prefix,
+        html_colour=html_colour
     )
 
     def flatten(lst: List[Union[str, List[str]]]) -> str:
         return line_feed_sep.join(flatten(x) if isinstance(x, list) else x for x in lst)
 
-    return flatten(rendered_diff)
+    return flatten(rendered_diff)

changedetectionio/forms.py

@@ -1,11 +1,15 @@
 import os
 import re
+from loguru import logger
+from wtforms.widgets.core import TimeInput
 
+from changedetectionio.conditions.form import ConditionFormRow
 from changedetectionio.strtobool import strtobool
 
 from wtforms import (
     BooleanField,
     Form,
+    Field,
     IntegerField,
     RadioField,
     SelectField,
@@ -19,7 +23,7 @@ from wtforms import (
 from flask_wtf.file import FileField, FileAllowed
 from wtforms.fields import FieldList
 
-from wtforms.validators import ValidationError
+from wtforms.validators import ValidationError, Optional
 
 from validators.url import url as url_validator
 
@@ -124,6 +128,87 @@ class StringTagUUID(StringField):
 
         return 'error'
 
+class TimeDurationForm(Form):
+    hours = SelectField(choices=[(f"{i}", f"{i}") for i in range(0, 25)], default="24",  validators=[validators.Optional()])
+    minutes = SelectField(choices=[(f"{i}", f"{i}") for i in range(0, 60)], default="00", validators=[validators.Optional()])
+
+class TimeStringField(Field):
+    """
+    A WTForms field for time inputs (HH:MM) that stores the value as a string.
+    """
+    widget = TimeInput()  # Use the built-in time input widget
+
+    def _value(self):
+        """
+        Returns the value for rendering in the form.
+        """
+        return self.data if self.data is not None else ""
+
+    def process_formdata(self, valuelist):
+        """
+        Processes the raw input from the form and stores it as a string.
+        """
+        if valuelist:
+            time_str = valuelist[0]
+            # Simple validation for HH:MM format
+            if not time_str or len(time_str.split(":")) != 2:
+                raise ValidationError("Invalid time format. Use HH:MM.")
+            self.data = time_str
+
+
+class validateTimeZoneName(object):
+    """
+       Flask wtform validators wont work with basic auth
+    """
+
+    def __init__(self, message=None):
+        self.message = message
+
+    def __call__(self, form, field):
+        from zoneinfo import available_timezones
+        python_timezones = available_timezones()
+        if field.data and field.data not in python_timezones:
+            raise ValidationError("Not a valid timezone name")
+
+class ScheduleLimitDaySubForm(Form):
+    enabled = BooleanField("not set", default=True)
+    start_time = TimeStringField("Start At", default="00:00", validators=[validators.Optional()])
+    duration = FormField(TimeDurationForm, label="Run duration")
+
+class ScheduleLimitForm(Form):
+    enabled = BooleanField("Use time scheduler", default=False)
+    # Because the label for=""" doesnt line up/work with the actual checkbox
+    monday = FormField(ScheduleLimitDaySubForm, label="")
+    tuesday = FormField(ScheduleLimitDaySubForm, label="")
+    wednesday = FormField(ScheduleLimitDaySubForm, label="")
+    thursday = FormField(ScheduleLimitDaySubForm, label="")
+    friday = FormField(ScheduleLimitDaySubForm, label="")
+    saturday = FormField(ScheduleLimitDaySubForm, label="")
+    sunday = FormField(ScheduleLimitDaySubForm, label="")
+
+    timezone = StringField("Optional timezone to run in",
+                                  render_kw={"list": "timezones"},
+                                  validators=[validateTimeZoneName()]
+                                  )
+    def __init__(
+        self,
+        formdata=None,
+        obj=None,
+        prefix="",
+        data=None,
+        meta=None,
+        **kwargs,
+    ):
+        super().__init__(formdata, obj, prefix, data, meta, **kwargs)
+        self.monday.form.enabled.label.text="Monday"
+        self.tuesday.form.enabled.label.text = "Tuesday"
+        self.wednesday.form.enabled.label.text = "Wednesday"
+        self.thursday.form.enabled.label.text = "Thursday"
+        self.friday.form.enabled.label.text = "Friday"
+        self.saturday.form.enabled.label.text = "Saturday"
+        self.sunday.form.enabled.label.text = "Sunday"
+
+
 class TimeBetweenCheckForm(Form):
     weeks = IntegerField('Weeks', validators=[validators.Optional(), validators.NumberRange(min=0, message="Should contain zero or more seconds")])
     days = IntegerField('Days', validators=[validators.Optional(), validators.NumberRange(min=0, message="Should contain zero or more seconds")])
@@ -222,9 +307,16 @@ class ValidateAppRiseServers(object):
         import apprise
         apobj = apprise.Apprise()
 
+        # so that the custom endpoints are registered
+        from .apprise_asset import asset
+
         for server_url in field.data:
-            if not apobj.add(server_url):
-                message = field.gettext('\'%s\' is not a valid AppRise URL.' % (server_url))
+            url = server_url.strip()
+            if url.startswith("#"):
+                continue
+
+            if not apobj.add(url):
+                message = field.gettext('\'%s\' is not a valid AppRise URL.' % (url))
                 raise ValidationError(message)
 
 class ValidateJinja2Template(object):
@@ -277,6 +369,7 @@ class validateURL(object):
         # This should raise a ValidationError() or not
         validate_url(field.data)
 
+
 def validate_url(test_url):
     # If hosts that only contain alphanumerics are allowed ("localhost" for example)
     try:
@@ -415,8 +508,15 @@ class quickWatchForm(Form):
     url = fields.URLField('URL', validators=[validateURL()])
     tags = StringTagUUID('Group tag', [validators.Optional()])
     watch_submit_button = SubmitField('Watch', render_kw={"class": "pure-button pure-button-primary"})
-    processor = RadioField(u'Processor', choices=processors.available_processors(), default="text_json_diff")
+    processor = RadioField(u'Processor', default="text_json_diff")
     edit_and_watch_submit_button = SubmitField('Edit > Watch', render_kw={"class": "pure-button pure-button-primary"})
+    
+    def __init__(self, formdata=None, obj=None, prefix="", data=None, meta=None, **kwargs):
+        super().__init__(formdata, obj, prefix, data, meta, **kwargs)
+        # Set processor choices based on datastore if available
+        #datastore = kwargs.get('datastore')
+        self.processor.choices = self.processors.available_processors()
+
 
 
 # Common to a single watch and the global settings
@@ -428,6 +528,13 @@ class commonSettingsForm(Form):
         self.notification_body.extra_notification_tokens = kwargs.get('extra_notification_tokens', {})
         self.notification_title.extra_notification_tokens = kwargs.get('extra_notification_tokens', {})
         self.notification_urls.extra_notification_tokens = kwargs.get('extra_notification_tokens', {})
+        
+        # Set processor choices based on datastore if available
+        datastore = kwargs.get('datastore')
+        if datastore:
+            self.processor.choices = self.processors.available_processors(datastore)
+        else:
+            self.processor.choices = self.processors.available_processors()
 
     extract_title_as_title = BooleanField('Extract <title> from document and use as watch title', default=False)
     fetch_backend = RadioField(u'Fetch Method', choices=content_fetchers.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
@@ -435,17 +542,26 @@ class commonSettingsForm(Form):
     notification_format = SelectField('Notification format', choices=valid_notification_formats.keys())
     notification_title = StringField('Notification Title', default='ChangeDetection.io Notification - {{ watch_url }}', validators=[validators.Optional(), ValidateJinja2Template()])
     notification_urls = StringListField('Notification URL List', validators=[validators.Optional(), ValidateAppRiseServers(), ValidateJinja2Template()])
-    processor = RadioField( label=u"Processor - What do you want to achieve?", choices=processors.available_processors(), default="text_json_diff")
+    processor = RadioField( label=u"Processor - What do you want to achieve?", default="text_json_diff")
+    timezone = StringField("Timezone for watch schedule", render_kw={"list": "timezones"}, validators=[validateTimeZoneName()])
     webdriver_delay = IntegerField('Wait seconds before extracting text', validators=[validators.Optional(), validators.NumberRange(min=1, message="Should contain one or more seconds")])
 
 
 class importForm(Form):
     from . import processors
-    processor = RadioField(u'Processor', choices=processors.available_processors(), default="text_json_diff")
+    processor = RadioField(u'Processor', default="text_json_diff")
     urls = TextAreaField('URLs')
     xlsx_file = FileField('Upload .xlsx file', validators=[FileAllowed(['xlsx'], 'Must be .xlsx file!')])
     file_mapping = SelectField('File mapping', [validators.DataRequired()], choices={('wachete', 'Wachete mapping'), ('custom','Custom mapping')})
-
+    
+    def __init__(self, formdata=None, obj=None, prefix="", data=None, meta=None, **kwargs):
+        super().__init__(formdata, obj, prefix, data, meta, **kwargs)
+        # Set processor choices based on datastore if available
+        datastore = kwargs.get('datastore')
+        if datastore:
+            self.processor.choices = self.processors.available_processors(datastore)
+        else:
+            self.processor.choices = self.processors.available_processors()
 
 class SingleBrowserStep(Form):
 
@@ -464,23 +580,28 @@ class processor_text_json_diff_form(commonSettingsForm):
     tags = StringTagUUID('Group tag', [validators.Optional()], default='')
 
     time_between_check = FormField(TimeBetweenCheckForm)
+
+    time_schedule_limit = FormField(ScheduleLimitForm)
+
     time_between_check_use_default = BooleanField('Use global settings for time between check', default=False)
 
     include_filters = StringListField('CSS/JSONPath/JQ/XPath Filters', [ValidateCSSJSONXPATHInput()], default='')
 
-    subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
+    subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_json=False)])
 
     extract_text = StringListField('Extract text', [ValidateListRegex()])
 
     title = StringField('Title', default='')
 
-    ignore_text = StringListField('Ignore text', [ValidateListRegex()])
+    ignore_text = StringListField('Ignore lines containing', [ValidateListRegex()])
     headers = StringDictKeyValue('Request headers')
     body = TextAreaField('Request body', [validators.Optional()])
     method = SelectField('Request method', choices=valid_method, default=default_method)
     ignore_status_codes = BooleanField('Ignore status codes (process non-2xx status codes as normal)', default=False)
-    check_unique_lines = BooleanField('Only trigger when unique lines appear', default=False)
+    check_unique_lines = BooleanField('Only trigger when unique lines appear in all history', default=False)
+    remove_duplicate_lines = BooleanField('Remove duplicate lines of text', default=False)
     sort_text_alphabetically =  BooleanField('Sort text alphabetically', default=False)
+    trim_text_whitespace = BooleanField('Trim whitespace before and after text', default=False)
 
     filter_text_added = BooleanField('Added lines', default=True)
     filter_text_replaced = BooleanField('Replaced/changed lines', default=True)
@@ -492,7 +613,7 @@ class processor_text_json_diff_form(commonSettingsForm):
     text_should_not_be_present = StringListField('Block change-detection while text matches', [validators.Optional(), ValidateListRegex()])
     webdriver_js_execute_code = TextAreaField('Execute JavaScript before change detection', render_kw={"rows": "5"}, validators=[validators.Optional()])
 
-    save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
+    save_button = SubmitField('Save', render_kw={"class": "pure-button button-small pure-button-primary"})
 
     proxy = RadioField('Proxy')
     filter_failure_notification_send = BooleanField(
@@ -501,6 +622,10 @@ class processor_text_json_diff_form(commonSettingsForm):
     notification_muted = BooleanField('Notifications Muted / Off', default=False)
     notification_screenshot = BooleanField('Attach screenshot to notification (where possible)', default=False)
 
+    conditions_match_logic = RadioField(u'Match', choices=[('ALL', 'Match all of the following'),('ANY', 'Match any of the following')], default='ALL')
+    conditions = FieldList(FormField(ConditionFormRow), min_entries=1)  # Add rule logic here
+
+
     def extra_tab_content(self):
         return None
 
@@ -511,6 +636,7 @@ class processor_text_json_diff_form(commonSettingsForm):
         if not super().validate():
             return False
 
+        from changedetectionio.safe_jinja import render as jinja_render
         result = True
 
         # Fail form validation when a body is set for a GET
@@ -520,13 +646,65 @@ class processor_text_json_diff_form(commonSettingsForm):
 
         # Attempt to validate jinja2 templates in the URL
         try:
-            from changedetectionio.safe_jinja import render as jinja_render
             jinja_render(template_str=self.url.data)
-        except Exception as e:
-            self.url.errors.append('Invalid template syntax')
+        except ModuleNotFoundError as e:
+            # incase jinja2_time or others is missing
+            logger.error(e)
+            self.url.errors.append(f'Invalid template syntax configuration: {e}')
             result = False
+        except Exception as e:
+            logger.error(e)
+            self.url.errors.append(f'Invalid template syntax: {e}')
+            result = False
+
+        # Attempt to validate jinja2 templates in the body
+        if self.body.data and self.body.data.strip():
+            try:
+                jinja_render(template_str=self.body.data)
+            except ModuleNotFoundError as e:
+                # incase jinja2_time or others is missing
+                logger.error(e)
+                self.body.errors.append(f'Invalid template syntax configuration: {e}')
+                result = False
+            except Exception as e:
+                logger.error(e)
+                self.body.errors.append(f'Invalid template syntax: {e}')
+                result = False
+
+        # Attempt to validate jinja2 templates in the headers
+        if len(self.headers.data) > 0:
+            try:
+                for header, value in self.headers.data.items():
+                    jinja_render(template_str=value)
+            except ModuleNotFoundError as e:
+                # incase jinja2_time or others is missing
+                logger.error(e)
+                self.headers.errors.append(f'Invalid template syntax configuration: {e}')
+                result = False
+            except Exception as e:
+                logger.error(e)
+                self.headers.errors.append(f'Invalid template syntax in "{header}" header: {e}')
+                result = False
+
         return result
 
+    def __init__(
+            self,
+            formdata=None,
+            obj=None,
+            prefix="",
+            data=None,
+            meta=None,
+            **kwargs,
+    ):
+        super().__init__(formdata, obj, prefix, data, meta, **kwargs)
+        if kwargs and kwargs.get('default_system_settings'):
+            default_tz = kwargs.get('default_system_settings').get('application', {}).get('timezone')
+            if default_tz:
+                self.time_schedule_limit.form.timezone.render_kw['placeholder'] = default_tz
+
+
+
 class SingleExtraProxy(Form):
 
     # maybe better to set some <script>var..
@@ -547,6 +725,7 @@ class DefaultUAInputForm(Form):
 # datastore.data['settings']['requests']..
 class globalSettingsRequestForm(Form):
     time_between_check = FormField(TimeBetweenCheckForm)
+    time_schedule_limit = FormField(ScheduleLimitForm)
     proxy = RadioField('Proxy')
     jitter_seconds = IntegerField('Random jitter seconds ± check',
                                   render_kw={"style": "width: 5em;"},
@@ -557,11 +736,12 @@ class globalSettingsRequestForm(Form):
     default_ua = FormField(DefaultUAInputForm, label="Default User-Agent overrides")
 
     def validate_extra_proxies(self, extra_validators=None):
-        for e in self.data['extra_proxies']:
-            if e.get('proxy_name') or e.get('proxy_url'):
-                if not e.get('proxy_name','').strip() or not e.get('proxy_url','').strip():
-                    self.extra_proxies.errors.append('Both a name, and a Proxy URL is required.')
-                    return False
+        if self.data.get('extra_proxies'):
+            for e in self.data['extra_proxies']:
+                if e.get('proxy_name') or e.get('proxy_url'):
+                    if not e.get('proxy_name','').strip() or not e.get('proxy_url','').strip():
+                        self.extra_proxies.errors.append('Both a name, and a Proxy URL is required.')
+                        return False
 
 
 # datastore.data['settings']['application']..
@@ -575,7 +755,7 @@ class globalSettingsApplicationForm(commonSettingsForm):
     empty_pages_are_a_change =  BooleanField('Treat empty pages as a change?', default=False)
     fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetchers.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
     global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
-    global_subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
+    global_subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_json=False)])
     ignore_whitespace = BooleanField('Ignore whitespace')
     password = SaltyPasswordField()
     pager_size = IntegerField('Pager size',
@@ -592,7 +772,6 @@ class globalSettingsApplicationForm(commonSettingsForm):
                                                                   validators=[validators.NumberRange(min=0,
                                                                                                      message="Should contain zero or more attempts")])
 
-
 class globalSettingsForm(Form):
     # Define these as FormFields/"sub forms", this way it matches the JSON storage
     # datastore.data['settings']['application']..
@@ -605,7 +784,7 @@ class globalSettingsForm(Form):
 
     requests = FormField(globalSettingsRequestForm)
     application = FormField(globalSettingsApplicationForm)
-    save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
+    save_button = SubmitField('Save', render_kw={"class": "pure-button button-small pure-button-primary"})
 
 
 class extractDataForm(Form):

changedetectionio/html_tools.py

@@ -1,18 +1,14 @@
-
-from bs4 import BeautifulSoup
-from inscriptis import get_text
-from jsonpath_ng.ext import parse
+from loguru import logger
+from lxml import etree
 from typing import List
-from inscriptis.model.config import ParserConfig
-from xml.sax.saxutils import escape as xml_escape
 import json
 import re
 
-
 # HTML added to be sure each result matching a filter (.example) gets converted to a new line by Inscriptis
 TEXT_FILTER_LIST_LINE_SUFFIX = "<br>"
-
+TRANSLATE_WHITESPACE_TABLE = str.maketrans('', '', '\r\n\t ')
 PERL_STYLE_REGEX = r'^/(.*?)/([a-z]*)?$'
+
 # 'price' , 'lowPrice', 'highPrice' are usually under here
 # All of those may or may not appear on different websites - I didnt find a way todo case-insensitive searching here
 LD_JSON_PRODUCT_OFFER_SELECTORS = ["json:$..offers", "json:$..Offers"]
@@ -39,6 +35,7 @@ def perl_style_slash_enclosed_regex_to_options(regex):
 
 # Given a CSS Rule, and a blob of HTML, return the blob of HTML that matches
 def include_filters(include_filters, html_content, append_pretty_line_formatting=False):
+    from bs4 import BeautifulSoup
     soup = BeautifulSoup(html_content, "html.parser")
     html_block = ""
     r = soup.select(include_filters, separator="")
@@ -56,16 +53,67 @@ def include_filters(include_filters, html_content, append_pretty_line_formatting
     return html_block
 
 def subtractive_css_selector(css_selector, html_content):
+    from bs4 import BeautifulSoup
     soup = BeautifulSoup(html_content, "html.parser")
-    for item in soup.select(css_selector):
+
+    # So that the elements dont shift their index, build a list of elements here which will be pointers to their place in the DOM
+    elements_to_remove = soup.select(css_selector)
+
+    # Then, remove them in a separate loop
+    for item in elements_to_remove:
         item.decompose()
+
     return str(soup)
 
+def subtractive_xpath_selector(selectors: List[str], html_content: str) -> str:
+    # Parse the HTML content using lxml
+    html_tree = etree.HTML(html_content)
+
+    # First, collect all elements to remove
+    elements_to_remove = []
+
+    # Iterate over the list of XPath selectors
+    for selector in selectors:
+        # Collect elements for each selector
+        elements_to_remove.extend(html_tree.xpath(selector))
+
+    # Then, remove them in a separate loop
+    for element in elements_to_remove:
+        if element.getparent() is not None:  # Ensure the element has a parent before removing
+            element.getparent().remove(element)
+
+    # Convert the modified HTML tree back to a string
+    modified_html = etree.tostring(html_tree, method="html").decode("utf-8")
+    return modified_html
+
 
 def element_removal(selectors: List[str], html_content):
-    """Joins individual filters into one css filter."""
-    selector = ",".join(selectors)
-    return subtractive_css_selector(selector, html_content)
+    """Removes elements that match a list of CSS or XPath selectors."""
+    modified_html = html_content
+    css_selectors = []
+    xpath_selectors = []
+
+    for selector in selectors:
+        if selector.startswith(('xpath:', 'xpath1:', '//')):
+            # Handle XPath selectors separately
+            xpath_selector = selector.removeprefix('xpath:').removeprefix('xpath1:')
+            xpath_selectors.append(xpath_selector)
+        else:
+            # Collect CSS selectors as one "hit", see comment in subtractive_css_selector
+            css_selectors.append(selector.strip().strip(","))
+
+    if xpath_selectors:
+        modified_html = subtractive_xpath_selector(xpath_selectors, modified_html)
+
+    if css_selectors:
+        # Remove duplicates, then combine all CSS selectors into one string, separated by commas
+        # This stops the elements index shifting
+        unique_selectors = list(set(css_selectors))  # Ensure uniqueness
+        combined_css_selector = " , ".join(unique_selectors)
+        modified_html = subtractive_css_selector(combined_css_selector, modified_html)
+
+
+    return modified_html
 
 def elementpath_tostring(obj):
     """
@@ -181,6 +229,7 @@ def xpath1_filter(xpath_filter, html_content, append_pretty_line_formatting=Fals
 
 # Extract/find element
 def extract_element(find='title', html_content=''):
+    from bs4 import BeautifulSoup
 
     #Re #106, be sure to handle when its not found
     element_text = None
@@ -194,6 +243,8 @@ def extract_element(find='title', html_content=''):
 
 #
 def _parse_json(json_data, json_filter):
+    from jsonpath_ng.ext import parse
+
     if json_filter.startswith("json:"):
         jsonpath_expression = parse(json_filter.replace('json:', ''))
         match = jsonpath_expression.find(json_data)
@@ -242,12 +293,16 @@ def _get_stripped_text_from_json_match(match):
 # json_filter - ie json:$..price
 # ensure_is_ldjson_info_type - str "product", optional, "@type == product" (I dont know how to do that as a json selector)
 def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None):
+    from bs4 import BeautifulSoup
+
     stripped_text_from_html = False
 # https://github.com/dgtlmoon/changedetection.io/pull/2041#issuecomment-1848397161w
     # Try to parse/filter out the JSON, if we get some parser error, then maybe it's embedded within HTML tags
     try:
-        stripped_text_from_html = _parse_json(json.loads(content), json_filter)
-    except json.JSONDecodeError:
+        # .lstrip("\ufeff") strings ByteOrderMark from UTF8 and still lets the UTF work
+        stripped_text_from_html = _parse_json(json.loads(content.lstrip("\ufeff") ), json_filter)
+    except json.JSONDecodeError as e:
+        logger.warning(str(e))
 
         # Foreach <script json></script> blob.. just return the first that matches json_filter
         # As a last resort, try to parse the whole <body>
@@ -309,6 +364,7 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
 #          - "line numbers" return a list of line numbers that match (int list)
 #
 # wordlist - list of regex's (str) or words (str)
+# Preserves all linefeeds and other whitespacing, its not the job of this to remove that
 def strip_ignore_text(content, wordlist, mode="content"):
     i = 0
     output = []
@@ -324,34 +380,33 @@ def strip_ignore_text(content, wordlist, mode="content"):
         else:
             ignore_text.append(k.strip())
 
-    for line in content.splitlines():
+    for line in content.splitlines(keepends=True):
         i += 1
         # Always ignore blank lines in this mode. (when this function gets called)
         got_match = False
-        if len(line.strip()):
-            for l in ignore_text:
-                if l.lower() in line.lower():
+        for l in ignore_text:
+            if l.lower() in line.lower():
+                got_match = True
+
+        if not got_match:
+            for r in ignore_regex:
+                if r.search(line):
                     got_match = True
 
-            if not got_match:
-                for r in ignore_regex:
-                    if r.search(line):
-                        got_match = True
-
-            if not got_match:
-                # Not ignored
-                output.append(line.encode('utf8'))
-            else:
-                ignored_line_numbers.append(i)
-
+        if not got_match:
+            # Not ignored, and should preserve "keepends"
+            output.append(line)
+        else:
+            ignored_line_numbers.append(i)
 
     # Used for finding out what to highlight
     if mode == "line numbers":
         return ignored_line_numbers
 
-    return "\n".encode('utf8').join(output)
+    return ''.join(output)
 
 def cdata_in_document_to_text(html_content: str, render_anchor_tag_content=False) -> str:
+    from xml.sax.saxutils import escape as xml_escape
     pattern = '<!\[CDATA\[(\s*(?:.(?<!\]\]>)\s*)*)\]\]>'
     def repl(m):
         text = m.group(1)
@@ -360,6 +415,9 @@ def cdata_in_document_to_text(html_content: str, render_anchor_tag_content=False
     return re.sub(pattern, repl, html_content)
 
 def html_to_text(html_content: str, render_anchor_tag_content=False, is_rss=False) -> str:
+    from inscriptis import get_text
+    from inscriptis.model.config import ParserConfig
+
     """Converts html string to a string with just the text. If ignoring
     rendering anchor tag content is enable, anchor tag content are also
     included in the text

changedetectionio/model/App.py

@@ -52,7 +52,8 @@ class model(dict):
                     'schema_version' : 0,
                     'shared_diff_access': False,
                     'webdriver_delay': None , # Extra delay in seconds before extracting text
-                    'tags': {} #@todo use Tag.model initialisers
+                    'tags': {}, #@todo use Tag.model initialisers
+                    'timezone': None # Default IANA timezone name
                 }
             }
         }
@@ -68,7 +69,7 @@ def parse_headers_from_text_file(filepath):
         for l in f.readlines():
             l = l.strip()
             if not l.startswith('#') and ':' in l:
-                (k, v) = l.split(':')
+                (k, v) = l.split(':', 1)  # Split only on the first colon
                 headers[k.strip()] = v.strip()
 
     return headers

changedetectionio/model/Tag.py

@@ -1,14 +1,57 @@
 
-from changedetectionio.model import watch_base
+import os
+import json
+import uuid as uuid_builder
+import time
+from copy import deepcopy
+from loguru import logger
+
+from changedetectionio.model import watch_base, schema
 
 
 class model(watch_base):
+    """Tag model that writes to tags/{uuid}/tag.json instead of the main watch directory"""
+    __datastore_path = None
 
     def __init__(self, *arg, **kw):
         super(model, self).__init__(*arg, **kw)
+        self.__datastore_path = kw.get("datastore_path")
 
         self['overrides_watch'] = kw.get('default', {}).get('overrides_watch')
 
         if kw.get('default'):
             self.update(kw['default'])
             del kw['default']
+
+    @property
+    def watch_data_dir(self):
+        # Override to use tags directory instead of the normal watch data directory
+        datastore_path = getattr(self, '_model__datastore_path', None)
+        if datastore_path:
+            tags_path = os.path.join(datastore_path, 'tags')
+            # Make sure the tags directory exists
+            if not os.path.exists(tags_path):
+                os.makedirs(tags_path)
+            return os.path.join(tags_path, self['uuid'])
+        return None
+        
+    def save_data(self):
+        """Override to save tag to tags/{uuid}/tag.json"""
+        logger.debug(f"Saving tag {self['uuid']}")
+
+        if not self.get('uuid'):
+            # Might have been called when creating the tag
+            return
+
+        tags_path = os.path.join(self.__datastore_path, 'tags')
+        if not os.path.isdir(tags_path):
+            os.mkdir(os.path.join(tags_path))
+
+        path = os.path.join(tags_path, self.get('uuid')+".json")
+        try:
+            with open(path + ".tmp", 'w') as json_file:
+                json.dump(self.get_data(), json_file, indent=4)
+            os.replace(path + ".tmp", path)
+        except Exception as e:
+            logger.error(f"Error writing JSON for tag {self.get('uuid')}!! (JSON file save was skipped) : {str(e)}")
+

changedetectionio/model/Watch.py

@@ -6,6 +6,8 @@ import re
 from pathlib import Path
 from loguru import logger
 
+from ..html_tools import TRANSLATE_WHITESPACE_TABLE
+
 # Allowable protocols, protects against javascript: etc
 # file:// is further checked by ALLOW_FILE_URI
 SAFE_PROTOCOL_REGEX='^(http|https|ftp|file):'
@@ -36,16 +38,13 @@ class model(watch_base):
     jitter_seconds = 0
 
     def __init__(self, *arg, **kw):
-        self.__datastore_path = kw['datastore_path']
-        del kw['datastore_path']
+
         super(model, self).__init__(*arg, **kw)
+
         if kw.get('default'):
             self.update(kw['default'])
             del kw['default']
 
-        if self.get('default'):
-            del self['default']
-
         # Be sure the cached timestamp is ready
         bump = self.history
 
@@ -80,12 +79,16 @@ class model(watch_base):
                     flash, Markup, url_for
                 )
                 message = Markup('<a href="{}#general">The URL {} is invalid and cannot be used, click to edit</a>'.format(
-                    url_for('edit_page', uuid=self.get('uuid')), self.get('url', '')))
+                    url_for('ui.ui_edit.edit_page', uuid=self.get('uuid')), self.get('url', '')))
                 flash(message, 'error')
                 return ''
 
         if ready_url.startswith('source:'):
             ready_url=ready_url.replace('source:', '')
+
+        # Also double check it after any Jinja2 formatting just incase
+        if not is_safe_url(ready_url):
+            return 'DISABLED'
         return ready_url
 
     def clear_watch(self):
@@ -171,6 +174,10 @@ class model(watch_base):
         """
         tmp_history = {}
 
+        # In the case we are only using the watch for processing without history
+        if not self.watch_data_dir:
+            return []
+
         # Read the history file as a dict
         fname = os.path.join(self.watch_data_dir, "history.txt")
         if os.path.isfile(fname):
@@ -236,37 +243,32 @@ class model(watch_base):
         bump = self.history
         return self.__newest_history_key
 
-    # Given an arbitrary timestamp, find the closest next key
-    # For example, last_viewed = 1000 so it should return the next 1001 timestamp
-    #
-    # used for the [diff] button so it can preset a smarter from_version
+    # Given an arbitrary timestamp, find the best history key for the [diff] button so it can preset a smarter from_version
     @property
-    def get_next_snapshot_key_to_last_viewed(self):
+    def get_from_version_based_on_last_viewed(self):
 
         """Unfortunately for now timestamp is stored as string key"""
         keys = list(self.history.keys())
         if not keys:
             return None
+        if len(keys) == 1:
+            return keys[0]
 
         last_viewed = int(self.get('last_viewed'))
-        prev_k = keys[0]
         sorted_keys = sorted(keys, key=lambda x: int(x))
         sorted_keys.reverse()
 
-        # When the 'last viewed' timestamp is greater than the newest snapshot, return second last
-        if last_viewed > int(sorted_keys[0]):
+        # When the 'last viewed' timestamp is greater than or equal the newest snapshot, return second newest
+        if last_viewed >= int(sorted_keys[0]):
             return sorted_keys[1]
+        
+        # When the 'last viewed' timestamp is between snapshots, return the older snapshot
+        for newer, older in list(zip(sorted_keys[0:], sorted_keys[1:])):
+            if last_viewed < int(newer) and last_viewed >= int(older):
+                return older
 
-        for k in sorted_keys:
-            if int(k) < last_viewed:
-                if prev_k == sorted_keys[0]:
-                    # Return the second last one so we dont recommend the same version compares itself
-                    return sorted_keys[1]
-
-                return prev_k
-            prev_k = k
-
-        return keys[0]
+        # When the 'last viewed' timestamp is less than the oldest snapshot, return oldest
+        return sorted_keys[-1]
 
     def get_history_snapshot(self, timestamp):
         import brotli
@@ -294,6 +296,7 @@ class model(watch_base):
     # result_obj from fetch_site_status.run()
     def save_history_text(self, contents, timestamp, snapshot_id):
         import brotli
+        import tempfile
 
         logger.trace(f"{self.get('uuid')} - Updating history.txt with timestamp {timestamp}")
 
@@ -307,13 +310,13 @@ class model(watch_base):
             dest = os.path.join(self.watch_data_dir, snapshot_fname)
             if not os.path.exists(dest):
                 with open(dest, 'wb') as f:
-                    f.write(brotli.compress(contents, mode=brotli.MODE_TEXT))
+                    f.write(brotli.compress(contents.encode('utf-8'), mode=brotli.MODE_TEXT))
         else:
             snapshot_fname = f"{snapshot_id}.txt"
             dest = os.path.join(self.watch_data_dir, snapshot_fname)
             if not os.path.exists(dest):
                 with open(dest, 'wb') as f:
-                    f.write(contents)
+                    f.write(contents.encode('utf-8'))
 
         # Append to index
         # @todo check last char was \n
@@ -328,7 +331,6 @@ class model(watch_base):
         # @todo bump static cache of the last timestamp so we dont need to examine the file to set a proper ''viewed'' status
         return snapshot_fname
 
-    @property
     @property
     def has_empty_checktime(self):
         # using all() + dictionary comprehension
@@ -345,14 +347,32 @@ class model(watch_base):
         return seconds
 
     # Iterate over all history texts and see if something new exists
-    def lines_contain_something_unique_compared_to_history(self, lines: list):
-        local_lines = set([l.decode('utf-8').strip().lower() for l in lines])
+    # Always applying .strip() to start/end but optionally replace any other whitespace
+    def lines_contain_something_unique_compared_to_history(self, lines: list, ignore_whitespace=False):
+        local_lines = set([])
+        if lines:
+            if ignore_whitespace:
+                if isinstance(lines[0], str): # Can be either str or bytes depending on what was on the disk
+                    local_lines = set([l.translate(TRANSLATE_WHITESPACE_TABLE).lower() for l in lines])
+                else:
+                    local_lines = set([l.decode('utf-8').translate(TRANSLATE_WHITESPACE_TABLE).lower() for l in lines])
+            else:
+                if isinstance(lines[0], str): # Can be either str or bytes depending on what was on the disk
+                    local_lines = set([l.strip().lower() for l in lines])
+                else:
+                    local_lines = set([l.decode('utf-8').strip().lower() for l in lines])
+
 
         # Compare each lines (set) against each history text file (set) looking for something new..
         existing_history = set({})
         for k, v in self.history.items():
             content = self.get_history_snapshot(k)
-            alist = set([line.strip().lower() for line in content.splitlines()])
+
+            if ignore_whitespace:
+                alist = set([line.translate(TRANSLATE_WHITESPACE_TABLE).lower() for line in content.splitlines()])
+            else:
+                alist = set([line.strip().lower() for line in content.splitlines()])
+
             existing_history = existing_history.union(alist)
 
         # Check that everything in local_lines(new stuff) already exists in existing_history - it should
@@ -393,11 +413,6 @@ class model(watch_base):
     def snapshot_error_screenshot_ctime(self):
         return self.__get_file_ctime('last-error-screenshot.png')
 
-    @property
-    def watch_data_dir(self):
-        # The base dir of the watch data
-        return os.path.join(self.__datastore_path, self['uuid'])
-    
     def get_error_text(self):
         """Return the text saved from a previous request that resulted in a non-200 error"""
         fname = os.path.join(self.watch_data_dir, "last-error.txt")
@@ -504,21 +519,22 @@ class model(watch_base):
     def save_error_text(self, contents):
         self.ensure_data_dir_exists()
         target_path = os.path.join(self.watch_data_dir, "last-error.txt")
-        with open(target_path, 'w') as f:
+        with open(target_path, 'w', encoding='utf-8') as f:
             f.write(contents)
 
     def save_xpath_data(self, data, as_error=False):
         import json
+        import zlib
 
         if as_error:
-            target_path = os.path.join(self.watch_data_dir, "elements-error.json")
+            target_path = os.path.join(str(self.watch_data_dir), "elements-error.deflate")
         else:
-            target_path = os.path.join(self.watch_data_dir, "elements.json")
+            target_path = os.path.join(str(self.watch_data_dir), "elements.deflate")
 
         self.ensure_data_dir_exists()
 
-        with open(target_path, 'w') as f:
-            f.write(json.dumps(data))
+        with open(target_path, 'wb') as f:
+            f.write(zlib.compress(json.dumps(data).encode()))
             f.close()
 
     # Save as PNG, PNG is larger but better for doing visual diff in the future

changedetectionio/model/__init__.py

@@ -1,73 +1,246 @@
 import os
 import uuid
+from copy import deepcopy
+from loguru import logger
+import time
+import json
 
 from changedetectionio import strtobool
 from changedetectionio.notification import default_notification_format_for_watch
 
+schema = {
+    # Custom notification content
+    # Re #110, so then if this is set to None, we know to use the default value instead
+    # Requires setting to None on submit if it's the same as the default
+    # Should be all None by default, so we use the system default in this case.
+    'body': None,
+    'browser_steps': [],
+    'browser_steps_last_error_step': None,
+    'check_count': 0,
+    'check_unique_lines': False,  # On change-detected, compare against all history if its something new
+    'consecutive_filter_failures': 0,  # Every time the CSS/xPath filter cannot be located, reset when all is fine.
+    'content-type': None,
+    'date_created': None,
+    'extract_text': [],  # Extract text by regex after filters
+    'extract_title_as_title': False,
+    'fetch_backend': 'system',  # plaintext, playwright etc
+    'fetch_time': 0.0,
+    'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
+    'filter_text_added': True,
+    'filter_text_removed': True,
+    'filter_text_replaced': True,
+    'follow_price_changes': True,
+    'has_ldjson_price_data': None,
+    'headers': {},  # Extra headers to send
+    'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
+    'in_stock_only': True,  # Only trigger change on going to instock from out-of-stock
+    'include_filters': [],
+    'last_checked': 0,
+    'last_error': False,
+    'last_modified': None,
+    'last_viewed': 0,  # history key value of the last viewed via the [diff] link
+    'method': 'GET',
+    'notification_alert_count': 0,
+    'notification_body': None,
+    'notification_format': default_notification_format_for_watch,
+    'notification_muted': False,
+    'notification_screenshot': False,  # Include the latest screenshot if available and supported by the apprise URL
+    'notification_title': None,
+    'notification_urls': [],  # List of URLs to add to the notification Queue (Usually AppRise)
+    'paused': False,
+    'previous_md5': False,
+    'previous_md5_before_filters': False,  # Used for skipping changedetection entirely
+    'processor': 'text_json_diff',  # could be restock_diff or others from .processors
+    'processor_state': {}, # Extra configs for custom processors/plugins, keyed by processor name
+    'price_change_threshold_percent': None,
+    'proxy': None,  # Preferred proxy connection
+    'remote_server_reply': None,  # From 'server' reply header
+    'sort_text_alphabetically': False,
+    'subtractive_selectors': [],
+    'tag': '',  # Old system of text name for a tag, to be removed
+    'tags': [],  # list of UUIDs to App.Tags
+    'text_should_not_be_present': [],  # Text that should not present
+    'time_between_check': {'weeks': None, 'days': None, 'hours': None, 'minutes': None, 'seconds': None},
+    'time_between_check_use_default': True,
+    "time_schedule_limit": {
+        "enabled": False,
+        "monday": {
+            "enabled": True,
+            "start_time": "00:00",
+            "duration": {
+                "hours": "24",
+                "minutes": "00"
+            }
+        },
+        "tuesday": {
+            "enabled": True,
+            "start_time": "00:00",
+            "duration": {
+                "hours": "24",
+                "minutes": "00"
+            }
+        },
+        "wednesday": {
+            "enabled": True,
+            "start_time": "00:00",
+            "duration": {
+                "hours": "24",
+                "minutes": "00"
+            }
+        },
+        "thursday": {
+            "enabled": True,
+            "start_time": "00:00",
+            "duration": {
+                "hours": "24",
+                "minutes": "00"
+            }
+        },
+        "friday": {
+            "enabled": True,
+            "start_time": "00:00",
+            "duration": {
+                "hours": "24",
+                "minutes": "00"
+            }
+        },
+        "saturday": {
+            "enabled": True,
+            "start_time": "00:00",
+            "duration": {
+                "hours": "24",
+                "minutes": "00"
+            }
+        },
+        "sunday": {
+            "enabled": True,
+            "start_time": "00:00",
+            "duration": {
+                "hours": "24",
+                "minutes": "00"
+            }
+        },
+    },
+    'title': None,
+    'track_ldjson_price_data': None,
+    'trim_text_whitespace': False,
+    'remove_duplicate_lines': False,
+    'trigger_text': [],  # List of text or regex to wait for until a change is detected
+    'url': '',
+    'uuid': None,
+    'webdriver_delay': None,
+    'webdriver_js_execute_code': None,  # Run before change-detection
+}
+
 class watch_base(dict):
+    __data = {}
+    __datastore_path = None
+    __save_enabled = True
 
     def __init__(self, *arg, **kw):
-        self.update({
-            # Custom notification content
-            # Re #110, so then if this is set to None, we know to use the default value instead
-            # Requires setting to None on submit if it's the same as the default
-            # Should be all None by default, so we use the system default in this case.
-            'body': None,
-            'browser_steps': [],
-            'browser_steps_last_error_step': None,
-            'check_count': 0,
-            'check_unique_lines': False,  # On change-detected, compare against all history if its something new
-            'consecutive_filter_failures': 0,  # Every time the CSS/xPath filter cannot be located, reset when all is fine.
-            'date_created': None,
-            'extract_text': [],  # Extract text by regex after filters
-            'extract_title_as_title': False,
-            'fetch_backend': 'system',  # plaintext, playwright etc
-            'fetch_time': 0.0,
-            'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
-            'filter_text_added': True,
-            'filter_text_removed': True,
-            'filter_text_replaced': True,
-            'follow_price_changes': True,
-            'has_ldjson_price_data': None,
-            'headers': {},  # Extra headers to send
-            'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
-            'in_stock_only': True,  # Only trigger change on going to instock from out-of-stock
-            'include_filters': [],
-            'last_checked': 0,
-            'last_error': False,
-            'last_viewed': 0,  # history key value of the last viewed via the [diff] link
-            'method': 'GET',
-            'notification_alert_count': 0,
-            'notification_body': None,
-            'notification_format': default_notification_format_for_watch,
-            'notification_muted': False,
-            'notification_screenshot': False,  # Include the latest screenshot if available and supported by the apprise URL
-            'notification_title': None,
-            'notification_urls': [],  # List of URLs to add to the notification Queue (Usually AppRise)
-            'paused': False,
-            'previous_md5': False,
-            'previous_md5_before_filters': False,  # Used for skipping changedetection entirely
-            'processor': 'text_json_diff',  # could be restock_diff or others from .processors
-            'price_change_threshold_percent': None,
-            'proxy': None,  # Preferred proxy connection
-            'remote_server_reply': None,  # From 'server' reply header
-            'sort_text_alphabetically': False,
-            'subtractive_selectors': [],
-            'tag': '',  # Old system of text name for a tag, to be removed
-            'tags': [],  # list of UUIDs to App.Tags
-            'text_should_not_be_present': [],  # Text that should not present
-            'time_between_check': {'weeks': None, 'days': None, 'hours': None, 'minutes': None, 'seconds': None},
-            'time_between_check_use_default': True,
-            'title': None,
-            'track_ldjson_price_data': None,
-            'trigger_text': [],  # List of text or regex to wait for until a change is detected
-            'url': '',
-            'uuid': str(uuid.uuid4()),
-            'webdriver_delay': None,
-            'webdriver_js_execute_code': None,  # Run before change-detection
-        })
+        # Initialize internal data storage
 
-        super(watch_base, self).__init__(*arg, **kw)
+        self.__data = deepcopy(schema)
+        self.__datastore_path = kw.pop('datastore_path', None)
+        # Initialize as empty dict but maintain dict interface
+        super(watch_base, self).__init__()
+        
+        # Update with provided data
+        if arg or kw:
+            self.update(*arg, **kw)
 
-        if self.get('default'):
-            del self['default']
+        # Generate UUID if needed
+        if not self.__data.get('uuid'):
+            self.__data['uuid'] = str(uuid.uuid4())
+
+        if self.__data.get('default'):
+            del(self.__data['default'])
+
+    @property
+    def watch_data_dir(self):
+        # The base dir of the watch data
+        return os.path.join(self.__datastore_path, self['uuid']) if self.__datastore_path else None
+
+    def enable_saving(self):
+        self.__save_enabled = True
+
+    # Dictionary interface methods to use self.__data
+    def __getitem__(self, key):
+        return self.__data[key]
+    
+    def __setitem__(self, key, value):
+        self.__data[key] = value
+        self.__data['last_modified'] = time.time()
+
+    def __delitem__(self, key):
+        del self.__data[key]
+    
+    def __contains__(self, key):
+        return key in self.__data
+    
+    def __iter__(self):
+        return iter(self.__data)
+    
+    def __len__(self):
+        return len(self.__data)
+
+    def get(self, key, default=None):
+        return self.__data.get(key, default)
+    
+    def update(self, *args, **kwargs):
+        if args:
+            if len(args) > 1:
+                raise TypeError("update expected at most 1 arguments, got %d" % len(args))
+            other = dict(args[0])
+            for key in other:
+                self.__data[key] = other[key]
+        for key in kwargs:
+            self.__data[key] = kwargs[key]
+
+        self.__data['last_modified'] = time.time()
+
+    def items(self):
+        return self.__data.items()
+    
+    def keys(self):
+        return self.__data.keys()
+        
+    def values(self):
+        return self.__data.values()
+        
+    def pop(self, key, default=None):
+        return self.__data.pop(key, default)
+        
+    def popitem(self):
+        return self.__data.popitem()
+        
+    def clear(self):
+        self.__data.clear()
+        self.__data['last_modified'] = time.time()
+        
+    def get_data(self):
+        """Returns the internal data dictionary"""
+        return self.__data
+
+    def save_data(self):
+        if self.__save_enabled:
+            if not self.__data.get('uuid'):
+                # Might have been called when creating the watch
+                return
+
+            logger.debug(f"Saving watch {self['uuid']}")
+            path = os.path.join(self.__datastore_path, self.get('uuid'))
+            filepath = os.path.join(str(path), "watch.json")
+            if not os.path.exists(path):
+                os.mkdir(path)
+
+            try:
+                import tempfile
+                with tempfile.NamedTemporaryFile(mode='wb+', delete=False) as tmp:
+                    tmp.write(json.dumps(self.get_data(), indent=2).encode('utf-8'))
+                    tmp.flush()
+                    os.replace(tmp.name, filepath)
+
+
+            except Exception as e:
+                logger.error(f"Error writing JSON for {self.get('uuid')}!! (JSON file save was skipped) : {str(e)}")

changedetectionio/notification.py

@@ -1,9 +1,10 @@
-import apprise
+
 import time
 from apprise import NotifyFormat
-import json
+import apprise
 from loguru import logger
 
+
 valid_tokens = {
     'base_url': '',
     'current_snapshot': '',
@@ -22,7 +23,7 @@ valid_tokens = {
 }
 
 default_notification_format_for_watch = 'System default'
-default_notification_format = 'Text'
+default_notification_format = 'HTML Color'
 default_notification_body = '{{watch_url}} had a change.\n---\n{{diff}}\n---\n'
 default_notification_title = 'ChangeDetection.io Notification - {{watch_url}}'
 
@@ -30,90 +31,16 @@ valid_notification_formats = {
     'Text': NotifyFormat.TEXT,
     'Markdown': NotifyFormat.MARKDOWN,
     'HTML': NotifyFormat.HTML,
+    'HTML Color': 'htmlcolor',
     # Used only for editing a watch (not for global)
     default_notification_format_for_watch: default_notification_format_for_watch
 }
 
-# include the decorator
-from apprise.decorators import notify
-
-@notify(on="delete")
-@notify(on="deletes")
-@notify(on="get")
-@notify(on="gets")
-@notify(on="post")
-@notify(on="posts")
-@notify(on="put")
-@notify(on="puts")
-def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
-    import requests
-    from apprise.utils import parse_url as apprise_parse_url
-    from apprise import URLBase
-
-    url = kwargs['meta'].get('url')
-
-    if url.startswith('post'):
-        r = requests.post
-    elif url.startswith('get'):
-        r = requests.get
-    elif url.startswith('put'):
-        r = requests.put
-    elif url.startswith('delete'):
-        r = requests.delete
-
-    url = url.replace('post://', 'http://')
-    url = url.replace('posts://', 'https://')
-    url = url.replace('put://', 'http://')
-    url = url.replace('puts://', 'https://')
-    url = url.replace('get://', 'http://')
-    url = url.replace('gets://', 'https://')
-    url = url.replace('put://', 'http://')
-    url = url.replace('puts://', 'https://')
-    url = url.replace('delete://', 'http://')
-    url = url.replace('deletes://', 'https://')
-
-    headers = {}
-    params = {}
-    auth = None
-
-    # Convert /foobar?+some-header=hello to proper header dictionary
-    results = apprise_parse_url(url)
-    if results:
-        # Add our headers that the user can potentially over-ride if they wish
-        # to to our returned result set and tidy entries by unquoting them
-        headers = {URLBase.unquote(x): URLBase.unquote(y)
-                   for x, y in results['qsd+'].items()}
-
-        # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
-        # In Apprise, it relies on prefixing each request arg with "-", because it uses say &method=update as a flag for apprise
-        # but here we are making straight requests, so we need todo convert this against apprise's logic
-        for k, v in results['qsd'].items():
-            if not k.strip('+-') in results['qsd+'].keys():
-                params[URLBase.unquote(k)] = URLBase.unquote(v)
-
-        # Determine Authentication
-        auth = ''
-        if results.get('user') and results.get('password'):
-            auth = (URLBase.unquote(results.get('user')), URLBase.unquote(results.get('user')))
-        elif results.get('user'):
-            auth = (URLBase.unquote(results.get('user')))
-
-    # Try to auto-guess if it's JSON
-    try:
-        json.loads(body)
-        headers['Content-Type'] = 'application/json; charset=utf-8'
-    except ValueError as e:
-        pass
-
-    r(results.get('url'),
-      auth=auth,
-      data=body,
-      headers=headers,
-      params=params
-      )
 
 
 def process_notification(n_object, datastore):
+    # so that the custom endpoints are registered
+    from changedetectionio.apprise_plugin import apprise_custom_api_call_wrapper
 
     from .safe_jinja import render as jinja_render
     now = time.time()
@@ -140,6 +67,10 @@ def process_notification(n_object, datastore):
 
     sent_objs = []
     from .apprise_asset import asset
+
+    if 'as_async' in n_object:
+        asset.async_mode = n_object.get('as_async')
+
     apobj = apprise.Apprise(debug=True, asset=asset)
 
     if not n_object.get('notification_urls'):
@@ -150,14 +81,21 @@ def process_notification(n_object, datastore):
 
             # Get the notification body from datastore
             n_body = jinja_render(template_str=n_object.get('notification_body', ''), **notification_parameters)
+            if n_object.get('notification_format', '').startswith('HTML'):
+                n_body = n_body.replace("\n", '<br>')
+
             n_title = jinja_render(template_str=n_object.get('notification_title', ''), **notification_parameters)
 
             url = url.strip()
+            if url.startswith('#'):
+                logger.trace(f"Skipping commented out notification URL - {url}")
+                continue
+
             if not url:
                 logger.warning(f"Process Notification: skipping empty notification URL.")
                 continue
 
-            logger.info(">> Process Notification: AppRise notifying {}".format(url))
+            logger.info(f">> Process Notification: AppRise notifying {url}")
             url = jinja_render(template_str=url, **notification_parameters)
 
             # Re 323 - Limit discord length to their 2000 char limit total or it wont send.
@@ -223,13 +161,12 @@ def process_notification(n_object, datastore):
             attach=n_object.get('screenshot', None)
         )
 
-        # Give apprise time to register an error
-        time.sleep(3)
 
         # Returns empty string if nothing found, multi-line string otherwise
         log_value = logs.getvalue()
 
         if log_value and 'WARNING' in log_value or 'ERROR' in log_value:
+            logger.critical(log_value)
             raise Exception(log_value)
 
     # Return what was sent for better logging - after the for loop

changedetectionio/processors/__init__.py

@@ -1,14 +1,14 @@
 from abc import abstractmethod
+from changedetectionio.content_fetchers.base import Fetcher
 from changedetectionio.strtobool import strtobool
-
 from copy import deepcopy
 from loguru import logger
 import hashlib
 import os
 import re
-import importlib
-import pkgutil
-import inspect
+
+
+from .pluggy_interface import plugin_manager, hookimpl
 
 class difference_detection_processor():
 
@@ -18,28 +18,33 @@ class difference_detection_processor():
     screenshot = None
     watch = None
     xpath_data = None
+    preferred_proxy = None
 
     def __init__(self, *args, datastore, watch_uuid, **kwargs):
         super().__init__(*args, **kwargs)
         self.datastore = datastore
         self.watch = deepcopy(self.datastore.data['watching'].get(watch_uuid))
+        # Generic fetcher that should be extended (requests, playwright etc)
+        self.fetcher = Fetcher()
+
+    def call_browser(self, preferred_proxy_id=None):
 
-    def call_browser(self):
         from requests.structures import CaseInsensitiveDict
-        # Protect against file:// access
-        if re.search(r'^file://', self.watch.get('url', '').strip(), re.IGNORECASE):
+
+        url = self.watch.link
+
+        # Protect against file:, file:/, file:// access, check the real "link" without any meta "source:" etc prepended.
+        if re.search(r'^file:', url.strip(), re.IGNORECASE):
             if not strtobool(os.getenv('ALLOW_FILE_URI', 'false')):
                 raise Exception(
                     "file:// type access is denied for security reasons."
                 )
 
-        url = self.watch.link
-
         # Requests, playwright, other browser via wss:// etc, fetch_extra_something
         prefer_fetch_backend = self.watch.get('fetch_backend', 'system')
 
         # Proxy ID "key"
-        preferred_proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=self.watch.get('uuid'))
+        preferred_proxy_id = preferred_proxy_id if preferred_proxy_id else self.datastore.get_preferred_proxy_for_watch(uuid=self.watch.get('uuid'))
 
         # Pluggable content self.fetcher
         if not prefer_fetch_backend or prefer_fetch_backend == 'system':
@@ -97,6 +102,7 @@ class difference_detection_processor():
             self.fetcher.browser_steps_screenshot_path = os.path.join(self.datastore.datastore_path, self.watch.get('uuid'))
 
         # Tweak the base config with the per-watch ones
+        from changedetectionio.safe_jinja import render as jinja_render
         request_headers = CaseInsensitiveDict()
 
         ua = self.datastore.data['settings']['requests'].get('default_ua')
@@ -113,9 +119,15 @@ class difference_detection_processor():
         if 'Accept-Encoding' in request_headers and "br" in request_headers['Accept-Encoding']:
             request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
 
+        for header_name in request_headers:
+            request_headers.update({header_name: jinja_render(template_str=request_headers.get(header_name))})
+
         timeout = self.datastore.data['settings']['requests'].get('timeout')
 
         request_body = self.watch.get('body')
+        if request_body:
+            request_body = jinja_render(template_str=self.watch.get('body'))
+        
         request_method = self.watch.get('method')
         ignore_status_codes = self.watch.get('ignore_status_codes', False)
 
@@ -133,8 +145,18 @@ class difference_detection_processor():
         is_binary = self.watch.is_pdf
 
         # And here we go! call the right browser with browser-specific settings
-        self.fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, self.watch.get('include_filters'),
-                    is_binary=is_binary)
+        empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
+
+        self.fetcher.run(url=url,
+                         timeout=timeout,
+                         request_headers=request_headers,
+                         request_body=request_body,
+                         request_method=request_method,
+                         ignore_status_codes=ignore_status_codes,
+                         current_include_filters=self.watch.get('include_filters'),
+                         is_binary=is_binary,
+                         empty_pages_are_a_change=empty_pages_are_a_change
+                         )
 
         #@todo .quit here could go on close object, so we can run JS if change-detected
         self.fetcher.quit()
@@ -142,7 +164,7 @@ class difference_detection_processor():
         # After init, call run_changedetection() which will do the actual change-detection
 
     @abstractmethod
-    def run_changedetection(self, watch, skip_when_checksum_same=True):
+    def run_changedetection(self, watch):
         update_obj = {'last_notification_error': False, 'last_error': False}
         some_data = 'xxxxx'
         update_obj["previous_md5"] = hashlib.md5(some_data.encode('utf-8')).hexdigest()
@@ -150,83 +172,208 @@ class difference_detection_processor():
         return changed_detected, update_obj, ''.encode('utf-8')
 
 
-def find_sub_packages(package_name):
+def get_all_plugins_info():
     """
-    Find all sub-packages within the given package.
-
-    :param package_name: The name of the base package to scan for sub-packages.
-    :return: A list of sub-package names.
+    Get information about all registered processor plugins
+    :return: A list of dictionaries with plugin info
     """
-    package = importlib.import_module(package_name)
-    return [name for _, name, is_pkg in pkgutil.iter_modules(package.__path__) if is_pkg]
+    plugins_info = []
+    
+    # Collect from all registered plugins
+    for plugin in plugin_manager.get_plugins():
+        if hasattr(plugin, "get_processor_name") and hasattr(plugin, "get_processor_description"):
+            processor_name = plugin.get_processor_name()
+            description = plugin.get_processor_description()
+            
+            # Get version if available
+            version = "N/A"
+            if hasattr(plugin, "get_processor_version"):
+                plugin_version = plugin.get_processor_version()
+                if plugin_version:
+                    version = plugin_version
+            
+            if processor_name and description:
+                plugins_info.append({
+                    "name": processor_name,
+                    "description": description,
+                    "version": version
+                })
+    
+    # Fallback if no plugins registered
+    if not plugins_info:
+        plugins_info = [
+            {"name": "text_json_diff", "description": "Webpage Text/HTML, JSON and PDF changes", "version": "1.0.0"},
+            {"name": "restock_diff", "description": "Re-stock & Price detection for single product pages", "version": "1.0.0"}
+        ]
+    
+    return plugins_info
 
-
-def find_processors():
-    """
-    Find all subclasses of DifferenceDetectionProcessor in the specified package.
-
-    :param package_name: The name of the package to scan for processor modules.
-    :return: A list of (module, class) tuples.
-    """
-    package_name = "changedetectionio.processors"  # Name of the current package/module
-
-    processors = []
-    sub_packages = find_sub_packages(package_name)
-
-    for sub_package in sub_packages:
-        module_name = f"{package_name}.{sub_package}.processor"
-        try:
-            module = importlib.import_module(module_name)
-
-            # Iterate through all classes in the module
-            for name, obj in inspect.getmembers(module, inspect.isclass):
-                if issubclass(obj, difference_detection_processor) and obj is not difference_detection_processor:
-                    processors.append((module, sub_package))
-        except (ModuleNotFoundError, ImportError) as e:
-            logger.warning(f"Failed to import module {module_name}: {e} (find_processors())")
-
-    return processors
-
-
-def get_parent_module(module):
-    module_name = module.__name__
-    if '.' not in module_name:
-        return None  # Top-level module has no parent
-    parent_module_name = module_name.rsplit('.', 1)[0]
-    try:
-        return importlib.import_module(parent_module_name)
-    except Exception as e:
-        pass
-
-    return False
-
-
-
-def get_custom_watch_obj_for_processor(processor_name):
-    from changedetectionio.model import Watch
-    watch_class = Watch.model
-    processor_classes = find_processors()
-    custom_watch_obj = next((tpl for tpl in processor_classes if tpl[1] == processor_name), None)
-    if custom_watch_obj:
-        # Parent of .processor.py COULD have its own Watch implementation
-        parent_module = get_parent_module(custom_watch_obj[0])
-        if hasattr(parent_module, 'Watch'):
-            watch_class = parent_module.Watch
-
-    return watch_class
-
-
-def available_processors():
+def available_processors(datastore=None):
     """
     Get a list of processors by name and description for the UI elements
-    :return: A list :)
+    Filtered by enabled_plugins setting if datastore is provided
+    :return: A list of tuples (processor_name, description)
+    """
+    plugins_info = get_all_plugins_info()
+    processor_list = []
+
+    for plugin in plugins_info:
+        processor_list.append((plugin["name"], plugin["description"]))
+    
+    return processor_list
+
+def get_processor_handler(processor_name, datastore, watch_uuid):
+    """
+    Get the processor handler for the specified processor name
+    :return: The processor handler instance
+    """
+    # Try each plugin in turn
+    for plugin in plugin_manager.get_plugins():
+        if hasattr(plugin, "perform_site_check"):
+            handler = plugin.perform_site_check(datastore=datastore, watch_uuid=watch_uuid)
+            if handler:
+                return handler
+    
+    # If no plugins handled it, use the appropriate built-in processor
+    watch = datastore.data['watching'].get(watch_uuid)
+    if watch and watch.get('processor') == 'restock_diff':
+        from .restock_diff.processor import perform_site_check
+        return perform_site_check(datastore=datastore, watch_uuid=watch_uuid)
+    else:
+        # Default to text_json_diff
+        from .text_json_diff.processor import perform_site_check
+        return perform_site_check(datastore=datastore, watch_uuid=watch_uuid)
+
+def get_form_class_for_processor(processor_name):
+    """
+    Get the form class for the specified processor name
+    :return: The form class
+    """
+    # Try each plugin in turn
+    for plugin in plugin_manager.get_plugins():
+        if hasattr(plugin, "get_form_class"):
+            form_class = plugin.get_form_class(processor_name=processor_name)
+            if form_class:
+                return form_class
+    
+    # If no plugins provided a form class, use the appropriate built-in form
+    if processor_name == 'restock_diff':
+        try:
+            from .restock_diff.forms import processor_settings_form
+            return processor_settings_form
+        except ImportError:
+            pass
+    
+    # Default to text_json_diff form
+    from changedetectionio import forms
+    return forms.processor_text_json_diff_form
+
+def get_watch_model_for_processor(processor_name):
+    """
+    Get the Watch model class for the specified processor name
+    :return: The Watch model class
     """
 
-    processor_classes = find_processors()
+    # Try each plugin in turn
+    for plugin in plugin_manager.get_plugins():
+        if hasattr(plugin, "get_watch_model_class"):
+            model_class = plugin.get_watch_model_class(processor_name=processor_name)
+            if model_class:
+                return model_class
 
-    available = []
-    for package, processor_class in processor_classes:
-        available.append((processor_class, package.name))
+    # Default to standard Watch model
+    from changedetectionio.model import Watch
+    return Watch.model
 
-    return available
+# Define plugin implementations for the built-in processors
+class TextJsonDiffPlugin:
+    @hookimpl
+    def get_processor_name(self):
+        return "text_json_diff"
 
+    @hookimpl
+    def get_processor_description(self):
+        from .text_json_diff.processor import name
+        return name
+        
+    @hookimpl
+    def get_processor_version(self):
+        from changedetectionio import __version__
+        return __version__
+        
+    @hookimpl
+    def get_processor_ui_tag(self):
+        from .text_json_diff.processor import UI_tag
+        return UI_tag
+
+    @hookimpl
+    def perform_site_check(self, datastore, watch_uuid):
+        watch = datastore.data['watching'].get(watch_uuid)
+        if watch and watch.get('processor', 'text_json_diff') == 'text_json_diff':
+            from .text_json_diff.processor import perform_site_check
+            return perform_site_check(datastore=datastore, watch_uuid=watch_uuid)
+        return None
+
+    @hookimpl
+    def get_form_class(self, processor_name):
+        if processor_name == 'text_json_diff':
+            from changedetectionio import forms
+            return forms.processor_text_json_diff_form
+        return None
+
+    @hookimpl
+    def get_watch_model_class(self, processor_name):
+        if processor_name == 'text_json_diff':
+            from changedetectionio.model import Watch
+            return Watch.model
+        return None
+
+class RestockDiffPlugin:
+    @hookimpl
+    def get_processor_name(self):
+        return "restock_diff"
+
+    @hookimpl
+    def get_processor_description(self):
+        from .restock_diff.processor import name
+        return name
+        
+    @hookimpl
+    def get_processor_version(self):
+        from changedetectionio import __version__
+        return __version__
+        
+    @hookimpl
+    def get_processor_ui_tag(self):
+        from .restock_diff.processor import UI_tag
+        return UI_tag
+
+    @hookimpl
+    def perform_site_check(self, datastore, watch_uuid):
+        watch = datastore.data['watching'].get(watch_uuid)
+        if watch and watch.get('processor') == 'restock_diff':
+            from .restock_diff.processor import perform_site_check
+            return perform_site_check(datastore=datastore, watch_uuid=watch_uuid)
+        return None
+
+    @hookimpl
+    def get_form_class(self, processor_name):
+        if processor_name == 'restock_diff':
+            try:
+                from .restock_diff.forms import processor_settings_form
+                return processor_settings_form
+            except ImportError:
+                pass
+        return None
+
+    @hookimpl
+    def get_watch_model_class(self, processor_name):
+        if processor_name == 'restock_diff':
+            from . import restock_diff
+            return restock_diff.Watch
+        return None
+
+
+# Register the built-in processor plugins
+plugin_manager.register(TextJsonDiffPlugin())
+plugin_manager.register(RestockDiffPlugin())

changedetectionio/processors/constants.py

@@ -0,0 +1,5 @@
+# Common constants used across processors
+
+# Price data tracking constants
+PRICE_DATA_TRACK_ACCEPT = 'accepted'
+PRICE_DATA_TRACK_REJECT = 'rejected'

changedetectionio/processors/pluggy_interface.py

@@ -0,0 +1,85 @@
+import pluggy
+from loguru import logger
+
+# Ensure that the namespace in HookspecMarker matches PluginManager
+PLUGIN_NAMESPACE = "changedetectionio_processors"
+
+hookspec = pluggy.HookspecMarker(PLUGIN_NAMESPACE)
+hookimpl = pluggy.HookimplMarker(PLUGIN_NAMESPACE)
+
+UI_tags = {}
+
+class ProcessorSpec:
+    """Hook specifications for difference detection processors."""
+
+    @hookspec
+    def get_processor_name():
+        """Return the processor name for selection in the UI."""
+        pass
+
+    @hookspec
+    def get_processor_description():
+        """Return a human-readable description of the processor."""
+        pass
+        
+    @hookspec
+    def get_processor_version():
+        """Return the processor plugin version."""
+        pass
+    
+    @hookspec
+    def get_processor_ui_tag():
+        """Return the UI tag for the processor (used for categorization in UI)."""
+        pass
+    
+    @hookspec
+    def perform_site_check(datastore, watch_uuid):
+        """Return the processor handler class or None if not applicable.
+        
+        Each plugin should check if it's the right processor for this watch
+        and return None if it's not.
+        
+        Should return an instance of a class that implements:
+        - call_browser(preferred_proxy_id=None): Fetch the content
+        - run_changedetection(watch): Analyze for changes and return tuple of (changed_detected, update_obj, contents)
+        """
+        pass
+    
+    @hookspec
+    def get_form_class(processor_name):
+        """Return the WTForms form class for the processor settings or None if not applicable.
+        
+        Each plugin should check if it's the right processor and return None if not.
+        """
+        pass
+
+    @hookspec
+    def get_watch_model_class(processor_name):
+        """Return a custom Watch model class if needed or None if not applicable.
+        
+        Each plugin should check if it's the right processor and return None if not.
+        """
+        pass
+
+# Set up Pluggy Plugin Manager
+plugin_manager = pluggy.PluginManager(PLUGIN_NAMESPACE)
+
+# Register hookspecs
+plugin_manager.add_hookspecs(ProcessorSpec)
+
+# Initialize by loading plugins and building UI_tags dictionary
+try:
+    # Discover installed plugins from external packages (if any)
+    plugin_manager.load_setuptools_entrypoints(PLUGIN_NAMESPACE)
+    logger.info(f"Loaded plugins: {plugin_manager.get_plugins()}")
+    
+    # Build UI_tags dictionary from all plugins
+    for plugin in plugin_manager.get_plugins():
+        if hasattr(plugin, "get_processor_name") and hasattr(plugin, "get_processor_ui_tag"):
+            plugin_name = plugin.get_processor_name()
+            ui_tag = plugin.get_processor_ui_tag()
+            if plugin_name and ui_tag:
+                UI_tags[plugin_name] = ui_tag
+                logger.info(f"Found UI tag for plugin {plugin_name}: {ui_tag}")
+except Exception as e:
+    logger.critical(f"Error loading plugins: {str(e)}")

changedetectionio/processors/restock_diff/__init__.py

@@ -1,11 +1,12 @@
 
 from changedetectionio.model.Watch import model as BaseWatch
+from typing import Union
 import re
-from babel.numbers import parse_decimal
 
 class Restock(dict):
 
-    def parse_currency(self, raw_value: str) -> float:
+    def parse_currency(self, raw_value: str) -> Union[float, None]:
+        from babel.numbers import parse_decimal
         # Clean and standardize the value (ie 1,400.00 should be 1400.00), even better would be store the whole thing as an integer.
         standardized_value = raw_value
 
@@ -21,8 +22,11 @@ class Restock(dict):
         # Remove any non-numeric characters except for the decimal point
         standardized_value = re.sub(r'[^\d.-]', '', standardized_value)
 
-        # Convert to float
-        return float(parse_decimal(standardized_value, locale='en'))
+        if standardized_value:
+            # Convert to float
+            return float(parse_decimal(standardized_value, locale='en'))
+
+        return None
 
     def __init__(self, *args, **kwargs):
         # Define default values
@@ -52,14 +56,19 @@ class Restock(dict):
         super().__setitem__(key, value)
 
 class Watch(BaseWatch):
+
+    def load_extra_vars(self):
+        # something from disk?
+
     def __init__(self, *arg, **kw):
         super().__init__(*arg, **kw)
+        # Restock Obj helps with the state of the situation
         self['restock'] = Restock(kw['default']['restock']) if kw.get('default') and kw['default'].get('restock') else Restock()
 
         self['restock_settings'] = kw['default']['restock_settings'] if kw.get('default',{}).get('restock_settings') else {
             'follow_price_changes': True,
             'in_stock_processing' : 'in_stock_only'
-        } #@todo update
+        }
 
     def clear_watch(self):
         super().clear_watch()

changedetectionio/processors/restock_diff/processor.py

@@ -2,14 +2,14 @@ from .. import difference_detection_processor
 from ..exceptions import ProcessorException
 from . import Restock
 from loguru import logger
-import hashlib
-import re
+
 import urllib3
 import time
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 name = 'Re-stock & Price detection for single product pages'
 description = 'Detects if the product goes back to in-stock'
+UI_tag = "Restock"
 
 class UnableToExtractRestockData(Exception):
     def __init__(self, status_code):
@@ -27,6 +27,30 @@ def _search_prop_by_value(matches, value):
             if value in prop[0]:
                 return prop[1]  # Yield the desired value and exit the function
 
+def _deduplicate_prices(data):
+    import re
+
+    '''
+    Some price data has multiple entries, OR it has a single entry with ['$159', '159', 159, "$ 159"] or just "159"
+    Get all the values, clean it and add it to a set then return the unique values
+    '''
+    unique_data = set()
+
+    # Return the complete 'datum' where its price was not seen before
+    for datum in data:
+
+        if isinstance(datum.value, list):
+            # Process each item in the list
+            normalized_value = set([float(re.sub(r'[^\d.]', '', str(item))) for item in datum.value if str(item).strip()])
+            unique_data.update(normalized_value)
+        else:
+            # Process single value
+            v = float(re.sub(r'[^\d.]', '', str(datum.value)))
+            unique_data.add(v)
+
+    return list(unique_data)
+
+
 # should return Restock()
 # add casting?
 def get_itemprop_availability(html_content) -> Restock:
@@ -36,17 +60,21 @@ def get_itemprop_availability(html_content) -> Restock:
     """
     from jsonpath_ng import parse
 
+    import re
     now = time.time()
     import extruct
     logger.trace(f"Imported extruct module in {time.time() - now:.3f}s")
 
-    value = {}
     now = time.time()
+
     # Extruct is very slow, I'm wondering if some ML is going to be faster (800ms on my i7), 'rdfa' seems to be the heaviest.
-
     syntaxes = ['dublincore', 'json-ld', 'microdata', 'microformat', 'opengraph']
+    try:
+        data = extruct.extract(html_content, syntaxes=syntaxes)
+    except Exception as e:
+        logger.warning(f"Unable to extract data, document parsing with extruct failed with {type(e).__name__} - {str(e)}")
+        return Restock()
 
-    data = extruct.extract(html_content, syntaxes=syntaxes)
     logger.trace(f"Extruct basic extract of all metadata done in {time.time() - now:.3f}s")
 
     # First phase, dead simple scanning of anything that looks useful
@@ -57,18 +85,17 @@ def get_itemprop_availability(html_content) -> Restock:
         pricecurrency_parse = parse('$..(pricecurrency|currency|priceCurrency )')
         availability_parse = parse('$..(availability|Availability)')
 
-        price_result = price_parse.find(data)
+        price_result = _deduplicate_prices(price_parse.find(data))
         if price_result:
             # Right now, we just support single product items, maybe we will store the whole actual metadata seperately in teh future and
             # parse that for the UI?
-            prices_found = set(str(item.value).replace('$', '') for item in price_result)
-            if len(price_result) > 1 and len(prices_found) > 1:
+            if len(price_result) > 1 and len(price_result) > 1:
                 # See of all prices are different, in the case that one product has many embedded data types with the same price
                 # One might have $121.95 and another 121.95 etc
-                logger.warning(f"More than one price found {prices_found}, throwing exception, cant use this plugin.")
+                logger.warning(f"More than one price found {price_result}, throwing exception, cant use this plugin.")
                 raise MoreThanOnePriceFound()
 
-            value['price'] = price_result[0].value
+            value['price'] = price_result[0]
 
         pricecurrency_result = pricecurrency_parse.find(data)
         if pricecurrency_result:
@@ -118,13 +145,16 @@ class perform_site_check(difference_detection_processor):
     screenshot = None
     xpath_data = None
 
-    def run_changedetection(self, watch, skip_when_checksum_same=True):
+    def run_changedetection(self, watch):
+        import hashlib
+
         if not watch:
             raise Exception("Watch no longer exists.")
 
         # Unset any existing notification error
         update_obj = {'last_notification_error': False, 'last_error': False, 'restock':  Restock()}
-
+        if not 'restock_settings' in watch.keys():
+            raise Exception("Restock settings not found in watch.")
         self.screenshot = self.fetcher.screenshot
         self.xpath_data = self.fetcher.xpath_data
 
@@ -132,6 +162,20 @@ class perform_site_check(difference_detection_processor):
         update_obj['content_type'] = self.fetcher.headers.get('Content-Type', '')
         update_obj["last_check_status"] = self.fetcher.get_last_status_code()
 
+        # Only try to process restock information (like scraping for keywords) if the page was actually rendered correctly.
+        # Otherwise it will assume "in stock" because nothing suggesting the opposite was found
+        from ...html_tools import html_to_text
+        text = html_to_text(self.fetcher.content)
+        logger.debug(f"Length of text after conversion: {len(text)}")
+        if not len(text):
+            from ...content_fetchers.exceptions import ReplyWithContentButNoText
+            raise ReplyWithContentButNoText(url=watch.link,
+                                            status_code=self.fetcher.get_last_status_code(),
+                                            screenshot=self.fetcher.screenshot,
+                                            html_content=self.fetcher.content,
+                                            xpath_data=self.fetcher.xpath_data
+                                            )
+
         # Which restock settings to compare against?
         restock_settings = watch.get('restock_settings', {})
 
@@ -146,7 +190,7 @@ class perform_site_check(difference_detection_processor):
 
         itemprop_availability = {}
         try:
-            itemprop_availability = get_itemprop_availability(html_content=self.fetcher.content)
+            itemprop_availability = get_itemprop_availability(self.fetcher.content)
         except MoreThanOnePriceFound as e:
             # Add the real data
             raise ProcessorException(message="Cannot run, more than one price detected, this plugin is only for product pages with ONE product, try the content-change detection mode.",
@@ -182,7 +226,7 @@ class perform_site_check(difference_detection_processor):
             itemprop_availability['original_price'] = itemprop_availability.get('price')
             update_obj['restock']["original_price"] = itemprop_availability.get('price')
 
-        if not self.fetcher.instock_data and not itemprop_availability.get('availability'):
+        if not self.fetcher.instock_data and not itemprop_availability.get('availability') and not itemprop_availability.get('price'):
             raise ProcessorException(
                 message=f"Unable to extract restock data for this page unfortunately. (Got code {self.fetcher.get_last_status_code()} from server), no embedded stock information was found and nothing interesting in the text, try using this watch with Chrome.",
                 url=watch.get('url'),
@@ -191,12 +235,21 @@ class perform_site_check(difference_detection_processor):
                 xpath_data=self.fetcher.xpath_data
                 )
 
+        logger.debug(f"self.fetcher.instock_data is - '{self.fetcher.instock_data}' and itemprop_availability.get('availability') is {itemprop_availability.get('availability')}")
         # Nothing automatic in microdata found, revert to scraping the page
         if self.fetcher.instock_data and itemprop_availability.get('availability') is None:
             # 'Possibly in stock' comes from stock-not-in-stock.js when no string found above the fold.
             # Careful! this does not really come from chrome/js when the watch is set to plaintext
             update_obj['restock']["in_stock"] = True if self.fetcher.instock_data == 'Possibly in stock' else False
-            logger.debug(f"Watch UUID {watch.get('uuid')} restock check returned '{self.fetcher.instock_data}' from JS scraper.")
+            logger.debug(f"Watch UUID {watch.get('uuid')} restock check returned instock_data - '{self.fetcher.instock_data}' from JS scraper.")
+
+        # Very often websites will lie about the 'availability' in the metadata, so if the scraped version says its NOT in stock, use that.
+        if self.fetcher.instock_data and self.fetcher.instock_data != 'Possibly in stock':
+            if update_obj['restock'].get('in_stock'):
+                logger.warning(
+                    f"Lie detected in the availability machine data!! when scraping said its not in stock!! itemprop was '{itemprop_availability}' and scraped from browser was '{self.fetcher.instock_data}' update obj was {update_obj['restock']} ")
+                logger.warning(f"Setting instock to FALSE, scraper found '{self.fetcher.instock_data}' in the body but metadata reported not-in-stock")
+                update_obj['restock']["in_stock"] = False
 
         # What we store in the snapshot
         price = update_obj.get('restock').get('price') if update_obj.get('restock').get('price') else ""
@@ -260,4 +313,4 @@ class perform_site_check(difference_detection_processor):
         # Always record the new checksum
         update_obj["previous_md5"] = fetched_md5
 
-        return changed_detected, update_obj, snapshot_content.encode('utf-8').strip()
+        return changed_detected, update_obj, snapshot_content.strip()

changedetectionio/processors/text_json_diff/__init__.py

@@ -0,0 +1,114 @@
+
+from loguru import logger
+
+
+
+def _task(watch, update_handler):
+    from changedetectionio.content_fetchers.exceptions import ReplyWithContentButNoText
+    from changedetectionio.processors.text_json_diff.processor import FilterNotFoundInResponse
+
+    text_after_filter = ''
+
+    try:
+        # The slow process (we run 2 of these in parallel)
+        changed_detected, update_obj, text_after_filter = update_handler.run_changedetection(watch=watch)
+    except FilterNotFoundInResponse as e:
+        text_after_filter = f"Filter not found in HTML: {str(e)}"
+    except ReplyWithContentButNoText as e:
+        text_after_filter = f"Filter found but no text (empty result)"
+    except Exception as e:
+        text_after_filter = f"Error: {str(e)}"
+
+    if not text_after_filter.strip():
+        text_after_filter = 'Empty content'
+
+    # because run_changedetection always returns bytes due to saving the snapshots etc
+    text_after_filter = text_after_filter.decode('utf-8') if isinstance(text_after_filter, bytes) else text_after_filter
+
+    return text_after_filter
+
+
+def prepare_filter_prevew(datastore, watch_uuid, form_data):
+    '''Used by @app.route("/edit/<string:uuid>/preview-rendered", methods=['POST'])'''
+    from changedetectionio import forms, html_tools
+    from changedetectionio.model.Watch import model as watch_model
+    from concurrent.futures import ProcessPoolExecutor
+    from copy import deepcopy
+    from flask import request
+    import brotli
+    import importlib
+    import os
+    import time
+    now = time.time()
+
+    text_after_filter = ''
+    text_before_filter = ''
+    trigger_line_numbers = []
+    ignore_line_numbers = []
+
+    tmp_watch = deepcopy(datastore.data['watching'].get(watch_uuid))
+
+    if tmp_watch and tmp_watch.history and os.path.isdir(tmp_watch.watch_data_dir):
+        # Splice in the temporary stuff from the form
+        form = forms.processor_text_json_diff_form(formdata=form_data if request.method == 'POST' else None,
+                                                   data=form_data
+                                                   )
+
+        # Only update vars that came in via the AJAX post
+        p = {k: v for k, v in form.data.items() if k in form_data.keys()}
+        tmp_watch.update(p)
+        blank_watch_no_filters = watch_model()
+        blank_watch_no_filters['url'] = tmp_watch.get('url')
+
+        latest_filename = next(reversed(tmp_watch.history))
+        html_fname = os.path.join(tmp_watch.watch_data_dir, f"{latest_filename}.html.br")
+        with open(html_fname, 'rb') as f:
+            decompressed_data = brotli.decompress(f.read()).decode('utf-8') if html_fname.endswith('.br') else f.read().decode('utf-8')
+
+            # Just like a normal change detection except provide a fake "watch" object and dont call .call_browser()
+            processor_module = importlib.import_module("changedetectionio.processors.text_json_diff.processor")
+            update_handler = processor_module.perform_site_check(datastore=datastore,
+                                                                 watch_uuid=tmp_watch.get('uuid')  # probably not needed anymore anyway?
+                                                                 )
+            # Use the last loaded HTML as the input
+            update_handler.datastore = datastore
+            update_handler.fetcher.content = str(decompressed_data) # str() because playwright/puppeteer/requests return string
+            update_handler.fetcher.headers['content-type'] = tmp_watch.get('content-type')
+
+            # Process our watch with filters and the HTML from disk, and also a blank watch with no filters but also with the same HTML from disk
+            # Do this as a parallel process because it could take some time
+            with ProcessPoolExecutor(max_workers=2) as executor:
+                future1 = executor.submit(_task, tmp_watch, update_handler)
+                future2 = executor.submit(_task, blank_watch_no_filters, update_handler)
+
+                text_after_filter = future1.result()
+                text_before_filter = future2.result()
+
+    try:
+        trigger_line_numbers = html_tools.strip_ignore_text(content=text_after_filter,
+                                                            wordlist=tmp_watch['trigger_text'],
+                                                            mode='line numbers'
+                                                            )
+    except Exception as e:
+        text_before_filter = f"Error: {str(e)}"
+
+    try:
+        text_to_ignore = tmp_watch.get('ignore_text', []) + datastore.data['settings']['application'].get('global_ignore_text', [])
+        ignore_line_numbers = html_tools.strip_ignore_text(content=text_after_filter,
+                                                           wordlist=text_to_ignore,
+                                                           mode='line numbers'
+                                                           )
+    except Exception as e:
+        text_before_filter = f"Error: {str(e)}"
+
+    logger.trace(f"Parsed in {time.time() - now:.3f}s")
+
+    return ({
+            'after_filter': text_after_filter,
+            'before_filter': text_before_filter.decode('utf-8') if isinstance(text_before_filter, bytes) else text_before_filter,
+            'duration': time.time() - now,
+            'trigger_line_numbers': trigger_line_numbers,
+            'ignore_line_numbers': ignore_line_numbers,
+        })
+
+

changedetectionio/processors/text_json_diff/processor.py

@@ -6,16 +6,18 @@ import os
 import re
 import urllib3
 
+from changedetectionio.conditions import execute_ruleset_against_all_plugins
 from changedetectionio.processors import difference_detection_processor
-from changedetectionio.html_tools import PERL_STYLE_REGEX, cdata_in_document_to_text
+from changedetectionio.html_tools import PERL_STYLE_REGEX, cdata_in_document_to_text, TRANSLATE_WHITESPACE_TABLE
 from changedetectionio import html_tools, content_fetchers
-from changedetectionio.blueprint.price_data_follower import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
+from changedetectionio.processors.constants import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
 from loguru import logger
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
 name = 'Webpage Text/HTML, JSON and PDF changes'
 description = 'Detects all text changes where possible'
+UI_tag = "Text Diff"
 
 json_filter_prefixes = ['json:', 'jq:', 'jqraw:']
 
@@ -35,7 +37,7 @@ class PDFToHTMLToolNotFound(ValueError):
 # (set_proxy_from_list)
 class perform_site_check(difference_detection_processor):
 
-    def run_changedetection(self, watch, skip_when_checksum_same=True):
+    def run_changedetection(self, watch):
         changed_detected = False
         html_content = ""
         screenshot = False  # as bytes
@@ -58,9 +60,6 @@ class perform_site_check(difference_detection_processor):
         # Watches added automatically in the queue manager will skip if its the same checksum as the previous run
         # Saves a lot of CPU
         update_obj['previous_md5_before_filters'] = hashlib.md5(self.fetcher.content.encode('utf-8')).hexdigest()
-        if skip_when_checksum_same:
-            if update_obj['previous_md5_before_filters'] == watch.get('previous_md5_before_filters'):
-                raise content_fetchers.exceptions.checksumFromPreviousCheckWasTheSame()
 
         # Fetching complete, now filters
 
@@ -175,13 +174,13 @@ class perform_site_check(difference_detection_processor):
                                                                     html_content=self.fetcher.content,
                                                                     append_pretty_line_formatting=not watch.is_source_type_url,
                                                                     is_rss=is_rss)
+
                         elif filter_rule.startswith('xpath1:'):
                             html_content += html_tools.xpath1_filter(xpath_filter=filter_rule.replace('xpath1:', ''),
-                                                                    html_content=self.fetcher.content,
-                                                                    append_pretty_line_formatting=not watch.is_source_type_url,
-                                                                    is_rss=is_rss)
+                                                                     html_content=self.fetcher.content,
+                                                                     append_pretty_line_formatting=not watch.is_source_type_url,
+                                                                     is_rss=is_rss)
                         else:
-                            # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
                             html_content += html_tools.include_filters(include_filters=filter_rule,
                                                                        html_content=self.fetcher.content,
                                                                        append_pretty_line_formatting=not watch.is_source_type_url)
@@ -197,25 +196,21 @@ class perform_site_check(difference_detection_processor):
                 else:
                     # extract text
                     do_anchor = self.datastore.data["settings"]["application"].get("render_anchor_tag_content", False)
-                    stripped_text_from_html = \
-                        html_tools.html_to_text(
-                            html_content=html_content,
-                            render_anchor_tag_content=do_anchor,
-                            is_rss=is_rss # #1874 activate the <title workaround hack
-                        )
+                    stripped_text_from_html = html_tools.html_to_text(html_content=html_content,
+                                                                      render_anchor_tag_content=do_anchor,
+                                                                      is_rss=is_rss)  # 1874 activate the <title workaround hack
 
-        if watch.get('sort_text_alphabetically') and stripped_text_from_html:
-            # Note: Because a <p>something</p> will add an extra line feed to signify the paragraph gap
-            # we end up with 'Some text\n\n', sorting will add all those extra \n at the start, so we remove them here.
-            stripped_text_from_html = stripped_text_from_html.replace('\n\n', '\n')
-            stripped_text_from_html = '\n'.join( sorted(stripped_text_from_html.splitlines(), key=lambda x: x.lower() ))
+        if watch.get('trim_text_whitespace'):
+            stripped_text_from_html = '\n'.join(line.strip() for line in stripped_text_from_html.replace("\n\n", "\n").splitlines())
 
         # Re #340 - return the content before the 'ignore text' was applied
-        text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
+        # Also used to calculate/show what was removed
+        text_content_before_ignored_filter = stripped_text_from_html
 
         # @todo whitespace coming from missing rtrim()?
         # stripped_text_from_html could be based on their preferences, replace the processed text with only that which they want to know about.
         # Rewrite's the processing text based on only what diff result they want to see
+
         if watch.has_special_diff_filter_options_set() and len(watch.history.keys()):
             # Now the content comes from the diff-parser and not the returned HTTP traffic, so could be some differences
             from changedetectionio import diff
@@ -230,12 +225,12 @@ class perform_site_check(difference_detection_processor):
                                              line_feed_sep="\n",
                                              include_change_type_prefix=False)
 
-            watch.save_last_text_fetched_before_filters(text_content_before_ignored_filter)
+            watch.save_last_text_fetched_before_filters(text_content_before_ignored_filter.encode('utf-8'))
 
             if not rendered_diff and stripped_text_from_html:
                 # We had some content, but no differences were found
                 # Store our new file as the MD5 so it will trigger in the future
-                c = hashlib.md5(text_content_before_ignored_filter.translate(None, b'\r\n\t ')).hexdigest()
+                c = hashlib.md5(stripped_text_from_html.translate(TRANSLATE_WHITESPACE_TABLE).encode('utf-8')).hexdigest()
                 return False, {'previous_md5': c}, stripped_text_from_html.encode('utf-8')
             else:
                 stripped_text_from_html = rendered_diff
@@ -256,14 +251,6 @@ class perform_site_check(difference_detection_processor):
 
         update_obj["last_check_status"] = self.fetcher.get_last_status_code()
 
-        # If there's text to skip
-        # @todo we could abstract out the get_text() to handle this cleaner
-        text_to_ignore = watch.get('ignore_text', []) + self.datastore.data['settings']['application'].get('global_ignore_text', [])
-        if len(text_to_ignore):
-            stripped_text_from_html = html_tools.strip_ignore_text(stripped_text_from_html, text_to_ignore)
-        else:
-            stripped_text_from_html = stripped_text_from_html.encode('utf8')
-
         # 615 Extract text by regex
         extract_text = watch.get('extract_text', [])
         if len(extract_text) > 0:
@@ -272,37 +259,53 @@ class perform_site_check(difference_detection_processor):
                 # incase they specified something in '/.../x'
                 if re.search(PERL_STYLE_REGEX, s_re, re.IGNORECASE):
                     regex = html_tools.perl_style_slash_enclosed_regex_to_options(s_re)
-                    result = re.findall(regex.encode('utf-8'), stripped_text_from_html)
+                    result = re.findall(regex, stripped_text_from_html)
 
                     for l in result:
                         if type(l) is tuple:
                             # @todo - some formatter option default (between groups)
-                            regex_matched_output += list(l) + [b'\n']
+                            regex_matched_output += list(l) + ['\n']
                         else:
                             # @todo - some formatter option default (between each ungrouped result)
-                            regex_matched_output += [l] + [b'\n']
+                            regex_matched_output += [l] + ['\n']
                 else:
                     # Doesnt look like regex, just hunt for plaintext and return that which matches
                     # `stripped_text_from_html` will be bytes, so we must encode s_re also to bytes
-                    r = re.compile(re.escape(s_re.encode('utf-8')), re.IGNORECASE)
+                    r = re.compile(re.escape(s_re), re.IGNORECASE)
                     res = r.findall(stripped_text_from_html)
                     if res:
                         for match in res:
-                            regex_matched_output += [match] + [b'\n']
+                            regex_matched_output += [match] + ['\n']
+
+            ##########################################################
+            stripped_text_from_html = ''
 
-            # Now we will only show what the regex matched
-            stripped_text_from_html = b''
-            text_content_before_ignored_filter = b''
             if regex_matched_output:
                 # @todo some formatter for presentation?
-                stripped_text_from_html = b''.join(regex_matched_output)
-                text_content_before_ignored_filter = stripped_text_from_html
+                stripped_text_from_html = ''.join(regex_matched_output)
+
+        if watch.get('remove_duplicate_lines'):
+            stripped_text_from_html = '\n'.join(dict.fromkeys(line for line in stripped_text_from_html.replace("\n\n", "\n").splitlines()))
+
+
+        if watch.get('sort_text_alphabetically'):
+            # Note: Because a <p>something</p> will add an extra line feed to signify the paragraph gap
+            # we end up with 'Some text\n\n', sorting will add all those extra \n at the start, so we remove them here.
+            stripped_text_from_html = stripped_text_from_html.replace("\n\n", "\n")
+            stripped_text_from_html = '\n'.join(sorted(stripped_text_from_html.splitlines(), key=lambda x: x.lower()))
+
+### CALCULATE MD5
+        # If there's text to ignore
+        text_to_ignore = watch.get('ignore_text', []) + self.datastore.data['settings']['application'].get('global_ignore_text', [])
+        text_for_checksuming = stripped_text_from_html
+        if text_to_ignore:
+            text_for_checksuming = html_tools.strip_ignore_text(stripped_text_from_html, text_to_ignore)
 
         # Re #133 - if we should strip whitespaces from triggering the change detected comparison
-        if self.datastore.data['settings']['application'].get('ignore_whitespace', False):
-            fetched_md5 = hashlib.md5(stripped_text_from_html.translate(None, b'\r\n\t ')).hexdigest()
+        if text_for_checksuming and self.datastore.data['settings']['application'].get('ignore_whitespace', False):
+            fetched_md5 = hashlib.md5(text_for_checksuming.translate(TRANSLATE_WHITESPACE_TABLE).encode('utf-8')).hexdigest()
         else:
-            fetched_md5 = hashlib.md5(stripped_text_from_html).hexdigest()
+            fetched_md5 = hashlib.md5(text_for_checksuming.encode('utf-8')).hexdigest()
 
         ############ Blocking rules, after checksum #################
         blocked = False
@@ -330,19 +333,43 @@ class perform_site_check(difference_detection_processor):
             if result:
                 blocked = True
 
-        # The main thing that all this at the moment comes down to :)
-        if watch.get('previous_md5') != fetched_md5:
-            changed_detected = True
+        # And check if 'conditions' will let this pass through
+        if watch.get('conditions') and watch.get('conditions_match_logic'):
+            if not execute_ruleset_against_all_plugins(current_watch_uuid=watch.get('uuid'),
+                                                application_datastruct=self.datastore.data,
+                                                ephemeral_data={
+                                                    'text': stripped_text_from_html
+                                                }
+                                                ):
+                # Conditions say "Condition not met" so we block it.
+                blocked = True
 
         # Looks like something changed, but did it match all the rules?
         if blocked:
             changed_detected = False
+        else:
+            # The main thing that all this at the moment comes down to :)
+            if watch.get('previous_md5') != fetched_md5:
+                changed_detected = True
+
+            # Always record the new checksum
+            update_obj["previous_md5"] = fetched_md5
+
+            # On the first run of a site, watch['previous_md5'] will be None, set it the current one.
+            if not watch.get('previous_md5'):
+                watch['previous_md5'] = fetched_md5
 
         logger.debug(f"Watch UUID {watch.get('uuid')} content check - Previous MD5: {watch.get('previous_md5')}, Fetched MD5 {fetched_md5}")
 
         if changed_detected:
             if watch.get('check_unique_lines', False):
-                has_unique_lines = watch.lines_contain_something_unique_compared_to_history(lines=stripped_text_from_html.splitlines())
+                ignore_whitespace = self.datastore.data['settings']['application'].get('ignore_whitespace')
+
+                has_unique_lines = watch.lines_contain_something_unique_compared_to_history(
+                    lines=stripped_text_from_html.splitlines(),
+                    ignore_whitespace=ignore_whitespace
+                )
+
                 # One or more lines? unsure?
                 if not has_unique_lines:
                     logger.debug(f"check_unique_lines: UUID {watch.get('uuid')} didnt have anything new setting change_detected=False")
@@ -350,11 +377,6 @@ class perform_site_check(difference_detection_processor):
                 else:
                     logger.debug(f"check_unique_lines: UUID {watch.get('uuid')} had unique content")
 
-        # Always record the new checksum
-        update_obj["previous_md5"] = fetched_md5
 
-        # On the first run of a site, watch['previous_md5'] will be None, set it the current one.
-        if not watch.get('previous_md5'):
-            watch['previous_md5'] = fetched_md5
-
-        return changed_detected, update_obj, text_content_before_ignored_filter
+        # stripped_text_from_html - Everything after filters and NO 'ignored' content
+        return changed_detected, update_obj, stripped_text_from_html

changedetectionio/run_socks_proxy_tests.sh

@@ -16,25 +16,31 @@ echo "---------------------------------- SOCKS5 -------------------"
 docker run --network changedet-network \
   -v `pwd`/tests/proxy_socks5/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json \
   --rm \
+  -e "FLASK_SERVER_NAME=cdio" \
+  --hostname cdio \
   -e "SOCKSTEST=proxiesjson" \
   test-changedetectionio \
-  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'
+  bash -c 'cd changedetectionio && pytest --live-server-host=0.0.0.0 --live-server-port=5004  -s tests/proxy_socks5/test_socks5_proxy_sources.py'
 
 # SOCKS5 related - by manually entering in UI
 docker run --network changedet-network \
   --rm \
+  -e "FLASK_SERVER_NAME=cdio" \
+  --hostname cdio \
   -e "SOCKSTEST=manual" \
   test-changedetectionio \
-  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy.py'
+  bash -c 'cd changedetectionio && pytest --live-server-host=0.0.0.0 --live-server-port=5004  -s tests/proxy_socks5/test_socks5_proxy.py'
 
 # SOCKS5 related - test from proxies.json via playwright - NOTE- PLAYWRIGHT DOESNT SUPPORT AUTHENTICATING PROXY
 docker run --network changedet-network \
   -e "SOCKSTEST=manual-playwright" \
+  --hostname cdio \
+  -e "FLASK_SERVER_NAME=cdio" \
   -v `pwd`/tests/proxy_socks5/proxies.json-example-noauth:/app/changedetectionio/test-datastore/proxies.json \
   -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" \
   --rm \
   test-changedetectionio \
-  bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'
+  bash -c 'cd changedetectionio && pytest --live-server-host=0.0.0.0 --live-server-port=5004  -s tests/proxy_socks5/test_socks5_proxy_sources.py'
 
 echo "socks5 server logs"
 docker logs socks5proxy

changedetectionio/static/images/copy.svg

@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="UTF-8" standalone="no"?>
 <svg
    version="1.1"
-   id="Layer_1"
+   id="copy"
    x="0px"
    y="0px"
    viewBox="0 0 115.77 122.88"

changedetectionio/static/images/email.svg

@@ -6,7 +6,7 @@
    height="7.5005589"
    width="11.248507"
    version="1.1"
-   id="Layer_1"
+   id="email"
    viewBox="0 0 7.1975545 4.7993639"
    xml:space="preserve"
    xmlns="http://www.w3.org/2000/svg"

changedetectionio/static/images/schedule.svg

@@ -0,0 +1,225 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   version="1.1"
+   id="schedule"
+   x="0px"
+   y="0px"
+   viewBox="0 0 661.20001 665.40002"
+   xml:space="preserve"
+   width="661.20001"
+   height="665.40002"
+   inkscape:version="1.1.2 (0a00cf5339, 2022-02-04)"
+   sodipodi:docname="schedule.svg"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg"><defs
+   id="defs77" /><sodipodi:namedview
+   id="namedview75"
+   pagecolor="#ffffff"
+   bordercolor="#666666"
+   borderopacity="1.0"
+   inkscape:pageshadow="2"
+   inkscape:pageopacity="0.0"
+   inkscape:pagecheckerboard="0"
+   showgrid="false"
+   fit-margin-top="0"
+   fit-margin-left="0"
+   fit-margin-right="0"
+   fit-margin-bottom="0"
+   inkscape:zoom="1.2458671"
+   inkscape:cx="300.59386"
+   inkscape:cy="332.29869"
+   inkscape:window-width="1920"
+   inkscape:window-height="1051"
+   inkscape:window-x="1920"
+   inkscape:window-y="0"
+   inkscape:window-maximized="1"
+   inkscape:current-layer="g72" /> <style
+   type="text/css"
+   id="style2"> .st0{fill:#FFFFFF;} .st1{fill:#C1272D;} .st2{fill:#991D26;} .st3{fill:#CCCCCC;} .st4{fill:#E6E6E6;} .st5{fill:#F7931E;} .st6{fill:#F2F2F2;} .st7{fill:none;stroke:#999999;stroke-width:17.9763;stroke-linecap:round;stroke-miterlimit:10;} .st8{fill:none;stroke:#333333;stroke-width:8.9882;stroke-linecap:round;stroke-miterlimit:10;} .st9{fill:none;stroke:#C1272D;stroke-width:5.9921;stroke-linecap:round;stroke-miterlimit:10;} .st10{fill:#245F7F;} </style> <g
+   id="g72"
+   transform="translate(-149.4,-147.3)"> <path
+   class="st0"
+   d="M 601.2,699.8 H 205 c -30.7,0 -55.6,-24.9 -55.6,-55.6 V 248 c 0,-30.7 24.9,-55.6 55.6,-55.6 h 396.2 c 30.7,0 55.6,24.9 55.6,55.6 v 396.2 c 0,30.7 -24.9,55.6 -55.6,55.6 z"
+   id="path4"
+   style="fill:#dfdfdf;fill-opacity:1" /> <path
+   class="st1"
+   d="M 601.2,192.4 H 205 c -30.7,0 -55.6,24.9 -55.6,55.6 v 88.5 H 656.8 V 248 c 0,-30.7 -24.9,-55.6 -55.6,-55.6 z"
+   id="path6"
+   style="fill:#d62128;fill-opacity:1" /> <circle
+   class="st2"
+   cx="253.3"
+   cy="264.5"
+   r="36.700001"
+   id="circle8" /> <circle
+   class="st2"
+   cx="551.59998"
+   cy="264.5"
+   r="36.700001"
+   id="circle10" /> <path
+   class="st3"
+   d="m 253.3,275.7 v 0 c -11.8,0 -21.3,-9.6 -21.3,-21.3 v -85.8 c 0,-11.8 9.6,-21.3 21.3,-21.3 v 0 c 11.8,0 21.3,9.6 21.3,21.3 v 85.8 c 0,11.8 -9.5,21.3 -21.3,21.3 z"
+   id="path12" /> <path
+   class="st3"
+   d="m 551.6,275.7 v 0 c -11.8,0 -21.3,-9.6 -21.3,-21.3 v -85.8 c 0,-11.8 9.6,-21.3 21.3,-21.3 v 0 c 11.8,0 21.3,9.6 21.3,21.3 v 85.8 c 0.1,11.8 -9.5,21.3 -21.3,21.3 z"
+   id="path14" /> <rect
+   x="215.7"
+   y="370.89999"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect16"
+   style="fill:#ffffff;fill-opacity:1" /> <rect
+   x="313"
+   y="370.89999"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect18"
+   style="fill:#ffffff;fill-opacity:1" /> <rect
+   x="410.20001"
+   y="370.89999"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect20"
+   style="fill:#ffffff;fill-opacity:1" /> <rect
+   x="507.5"
+   y="370.89999"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect22"
+   style="fill:#ffffff;fill-opacity:1" /> <rect
+   x="215.7"
+   y="465"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect24"
+   style="fill:#ffffff;fill-opacity:1" /> <rect
+   x="313"
+   y="465"
+   class="st1"
+   width="75.199997"
+   height="75.199997"
+   id="rect26"
+   style="fill:#27c12b;fill-opacity:1" /> <rect
+   x="410.20001"
+   y="465"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect28"
+   style="fill:#ffffff;fill-opacity:1" /> <rect
+   x="507.5"
+   y="465"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect30" /> <rect
+   x="215.7"
+   y="559.09998"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect32"
+   style="fill:#ffffff;fill-opacity:1" /> <rect
+   x="313"
+   y="559.09998"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect34"
+   style="fill:#ffffff;fill-opacity:1" /> <rect
+   x="410.20001"
+   y="559.09998"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect36"
+   style="fill:#ffffff;fill-opacity:1" /> <rect
+   x="507.5"
+   y="559.09998"
+   class="st4"
+   width="75.199997"
+   height="75.199997"
+   id="rect38" /> <g
+   id="g70"> <circle
+   class="st5"
+   cx="621.90002"
+   cy="624"
+   r="188.7"
+   id="circle40" /> <circle
+   class="st0"
+   cx="621.90002"
+   cy="624"
+   r="148"
+   id="circle42" /> <path
+   class="st6"
+   d="m 486.6,636.8 c 0,-81.7 66.3,-148 148,-148 37.6,0 72,14.1 98.1,37.2 -27.1,-30.6 -66.7,-49.9 -110.8,-49.9 -81.7,0 -148,66.3 -148,148 0,44.1 19.3,83.7 49.9,110.8 -23.1,-26.2 -37.2,-60.5 -37.2,-98.1 z"
+   id="path44" /> <polyline
+   class="st7"
+   points="621.9,530.4 621.9,624 559,624  "
+   id="polyline46" /> <g
+   id="g64"> <line
+   class="st8"
+   x1="621.90002"
+   y1="508.29999"
+   x2="621.90002"
+   y2="497.10001"
+   id="line48" /> <line
+   class="st8"
+   x1="621.90002"
+   y1="756.29999"
+   x2="621.90002"
+   y2="745.09998"
+   id="line50" /> <line
+   class="st8"
+   x1="740.29999"
+   y1="626.70001"
+   x2="751.5"
+   y2="626.70001"
+   id="line52" /> <line
+   class="st8"
+   x1="492.29999"
+   y1="626.70001"
+   x2="503.5"
+   y2="626.70001"
+   id="line54" /> <line
+   class="st8"
+   x1="705.59998"
+   y1="710.40002"
+   x2="713.5"
+   y2="718.29999"
+   id="line56" /> <line
+   class="st8"
+   x1="530.29999"
+   y1="535.09998"
+   x2="538.20001"
+   y2="543"
+   id="line58" /> <line
+   class="st8"
+   x1="538.20001"
+   y1="710.40002"
+   x2="530.29999"
+   y2="718.29999"
+   id="line60" /> <line
+   class="st8"
+   x1="713.5"
+   y1="535.09998"
+   x2="705.59998"
+   y2="543"
+   id="line62" /> </g> <line
+   class="st9"
+   x1="604.40002"
+   y1="606.29999"
+   x2="684.5"
+   y2="687.40002"
+   id="line66" /> <circle
+   class="st10"
+   cx="621.90002"
+   cy="624"
+   r="16.1"
+   id="circle68" /> </g> </g> </svg>

changedetectionio/static/js/browser-steps.js

@@ -221,7 +221,7 @@ $(document).ready(function () {
                     // If you switch to "Click X,y" after an element here is setup, it will give the last co-ords anyway
                     //if (x['isClickable'] || x['tagName'].startsWith('h') || x['tagName'] === 'a' || x['tagName'] === 'button' || x['tagtype'] === 'submit' || x['tagtype'] === 'checkbox' || x['tagtype'] === 'radio' || x['tagtype'] === 'li') {
                         $('select', first_available).val('Click element').change();
-                        $('input[type=text]', first_available).first().val(x['xpath']);
+                        $('input[type=text]', first_available).first().val(x['xpath']).focus();
                         found_something = true;
                     //}
                 }
@@ -305,7 +305,7 @@ $(document).ready(function () {
 
         if ($(this).val() === 'Click X,Y' && last_click_xy['x'] > 0 && $(elem_value).val().length === 0) {
             // @todo handle scale
-            $(elem_value).val(last_click_xy['x'] + ',' + last_click_xy['y']);
+            $(elem_value).val(last_click_xy['x'] + ',' + last_click_xy['y']).focus();
         }
     }).change();
 

changedetectionio/static/js/conditions.js

@@ -0,0 +1,150 @@
+$(document).ready(function () {
+    // Function to set up button event handlers
+    function setupButtonHandlers() {
+        // Unbind existing handlers first to prevent duplicates
+        $(".addRuleRow, .removeRuleRow, .verifyRuleRow").off("click");
+        
+        // Add row button handler
+        $(".addRuleRow").on("click", function(e) {
+            e.preventDefault();
+            
+            let currentRow = $(this).closest("tr");
+            
+            // Clone without events
+            let newRow = currentRow.clone(false);
+            
+            // Reset input values in the cloned row
+            newRow.find("input").val("");
+            newRow.find("select").prop("selectedIndex", 0);
+            
+            // Insert the new row after the current one
+            currentRow.after(newRow);
+            
+            // Reindex all rows
+            reindexRules();
+        });
+        
+        // Remove row button handler
+        $(".removeRuleRow").on("click", function(e) {
+            e.preventDefault();
+            
+            // Only remove if there's more than one row
+            if ($("#rulesTable tbody tr").length > 1) {
+                $(this).closest("tr").remove();
+                reindexRules();
+            }
+        });
+        
+        // Verify rule button handler
+        $(".verifyRuleRow").on("click", function(e) {
+            e.preventDefault();
+            
+            let row = $(this).closest("tr");
+            let field = row.find("select[name$='field']").val();
+            let operator = row.find("select[name$='operator']").val();
+            let value = row.find("input[name$='value']").val();
+            
+            // Validate that all fields are filled
+            if (!field || field === "None" || !operator || operator === "None" || !value) {
+                alert("Please fill in all fields (Field, Operator, and Value) before verifying.");
+                return;
+            }
+
+            
+            // Create a rule object
+            const rule = {
+                field: field,
+                operator: operator,
+                value: value
+            };
+            
+            // Show a spinner or some indication that verification is in progress
+            const $button = $(this);
+            const originalHTML = $button.html();
+            $button.html("⌛").prop("disabled", true);
+            
+            // Collect form data - similar to request_textpreview_update() in watch-settings.js
+            let formData = new FormData();
+            $('#edit-text-filter textarea, #edit-text-filter input').each(function() {
+                const $element = $(this);
+                const name = $element.attr('name');
+                if (name) {
+                    if ($element.is(':checkbox')) {
+                        formData.append(name, $element.is(':checked') ? $element.val() : false);
+                    } else {
+                        formData.append(name, $element.val());
+                    }
+                }
+            });
+            
+            // Also collect select values
+            $('#edit-text-filter select').each(function() {
+                const $element = $(this);
+                const name = $element.attr('name');
+                if (name) {
+                    formData.append(name, $element.val());
+                }
+            });
+
+
+            // Send the request to verify the rule
+            $.ajax({
+                url: verify_condition_rule_url+"?"+ new URLSearchParams({ rule: JSON.stringify(rule) }).toString(),
+                type: "POST",
+                data: formData,
+                processData: false, // Prevent jQuery from converting FormData to a string
+                contentType: false, // Let the browser set the correct content type
+                success: function (response) {
+                    if (response.status === "success") {
+                        if (response.result) {
+                            alert("✅ Condition PASSES verification against current snapshot!");
+                        } else {
+                            alert("❌ Condition FAILS verification against current snapshot.");
+                        }
+                    } else {
+                        alert("Error: " + response.message);
+                    }
+                    $button.html(originalHTML).prop("disabled", false);
+                },
+                error: function (xhr) {
+                    let errorMsg = "Error verifying condition.";
+                    if (xhr.responseJSON && xhr.responseJSON.message) {
+                        errorMsg = xhr.responseJSON.message;
+                    }
+                    alert(errorMsg);
+                    $button.html(originalHTML).prop("disabled", false);
+                }
+            });
+        });
+    }
+
+    // Function to reindex form elements and re-setup event handlers
+    function reindexRules() {
+        // Unbind all button handlers first
+        $(".addRuleRow, .removeRuleRow, .verifyRuleRow").off("click");
+        
+        // Reindex all form elements
+        $("#rulesTable tbody tr").each(function(index) {
+            $(this).find("select, input").each(function() {
+                let oldName = $(this).attr("name");
+                let oldId = $(this).attr("id");
+
+                if (oldName) {
+                    let newName = oldName.replace(/\d+/, index);
+                    $(this).attr("name", newName);
+                }
+
+                if (oldId) {
+                    let newId = oldId.replace(/\d+/, index);
+                    $(this).attr("id", newId);
+                }
+            });
+        });
+        
+        // Reattach event handlers after reindexing
+        setupButtonHandlers();
+    }
+
+    // Initial setup of button handlers
+    setupButtonHandlers();
+});

changedetectionio/static/js/global-settings.js

@@ -18,9 +18,25 @@ $(document).ready(function () {
 
     });
 
-    $("#notification-token-toggle").click(function (e) {
+    $(".toggle-show").click(function (e) {
         e.preventDefault();
-        $('#notification-tokens-info').toggle();
+        let target = $(this).data('target');
+        $(target).toggle();
     });
+
+    // Time zone config related
+    $(".local-time").each(function (e) {
+        $(this).text(new Date($(this).data("utc")).toLocaleString());
+    })
+
+    const timezoneInput = $('#application-timezone');
+    if(timezoneInput.length) {
+        const timezone = Intl.DateTimeFormat().resolvedOptions().timeZone;
+        if (!timezoneInput.val().trim()) {
+            timezoneInput.val(timezone);
+            timezoneInput.after('<div class="timezone-message">The timezone was set from your browser, <strong>be sure to press save!</strong></div>');
+        }
+    }
+
 });
 

changedetectionio/static/js/limit.js

@@ -1,56 +0,0 @@
-/**
- * debounce
- * @param {integer} milliseconds This param indicates the number of milliseconds
- *     to wait after the last call before calling the original function.
- * @param {object} What "this" refers to in the returned function.
- * @return {function} This returns a function that when called will wait the
- *     indicated number of milliseconds after the last call before
- *     calling the original function.
- */
-Function.prototype.debounce = function (milliseconds, context) {
-    var baseFunction = this,
-        timer = null,
-        wait = milliseconds;
-
-    return function () {
-        var self = context || this,
-            args = arguments;
-
-        function complete() {
-            baseFunction.apply(self, args);
-            timer = null;
-        }
-
-        if (timer) {
-            clearTimeout(timer);
-        }
-
-        timer = setTimeout(complete, wait);
-    };
-};
-
-/**
-* throttle
-* @param {integer} milliseconds This param indicates the number of milliseconds
-*     to wait between calls before calling the original function.
-* @param {object} What "this" refers to in the returned function.
-* @return {function} This returns a function that when called will wait the
-*     indicated number of milliseconds between calls before
-*     calling the original function.
-*/
-Function.prototype.throttle = function (milliseconds, context) {
-    var baseFunction = this,
-        lastEventTimestamp = null,
-        limit = milliseconds;
-
-    return function () {
-        var self = context || this,
-            args = arguments,
-            now = Date.now();
-
-        if (!lastEventTimestamp || now - lastEventTimestamp >= limit) {
-            lastEventTimestamp = now;
-            baseFunction.apply(self, args);
-        }
-    };
-};

changedetectionio/static/js/notifications.js

@@ -1,45 +1,52 @@
-$(document).ready(function() {
+$(document).ready(function () {
 
-  $('#add-email-helper').click(function (e) {
-    e.preventDefault();
-    email = prompt("Destination email");
-    if(email) {
-      var n = $(".notification-urls");
-      var p=email_notification_prefix;
-      $(n).val( $.trim( $(n).val() )+"\n"+email_notification_prefix+email );
-    }
-  });
-
-  $('#send-test-notification').click(function (e) {
-    e.preventDefault();
-
-    data = {
-      notification_body: $('#notification_body').val(),
-      notification_format: $('#notification_format').val(),
-      notification_title: $('#notification_title').val(),
-      notification_urls: $('.notification-urls').val(),
-      tags: $('#tags').val(),
-      window_url: window.location.href,
-    }
-
-
-    $.ajax({
-      type: "POST",
-      url: notification_base_url,
-      data : data,
-        statusCode: {
-        400: function() {
-            // More than likely the CSRF token was lost when the server restarted
-          alert("There was a problem processing the request, please reload the page.");
+    $('#add-email-helper').click(function (e) {
+        e.preventDefault();
+        email = prompt("Destination email");
+        if (email) {
+            var n = $(".notification-urls");
+            var p = email_notification_prefix;
+            $(n).val($.trim($(n).val()) + "\n" + email_notification_prefix + email);
         }
-      }
-    }).done(function(data){
-      console.log(data);
-      alert(data);
-    }).fail(function(data){
-      console.log(data);
-      alert('There was an error communicating with the server.');
-    })
-  });
+    });
+
+    $('#send-test-notification').click(function (e) {
+        e.preventDefault();
+
+        data = {
+            notification_body: $('#notification_body').val(),
+            notification_format: $('#notification_format').val(),
+            notification_title: $('#notification_title').val(),
+            notification_urls: $('.notification-urls').val(),
+            tags: $('#tags').val(),
+            window_url: window.location.href,
+        }
+
+        $('.notifications-wrapper .spinner').fadeIn();
+        $('#notification-test-log').show();
+        $.ajax({
+            type: "POST",
+            url: notification_base_url,
+            data: data,
+            statusCode: {
+                400: function (data) {
+                    $("#notification-test-log>span").text(data.responseText);
+                },
+            }
+        }).done(function (data) {
+            $("#notification-test-log>span").text(data);
+        }).fail(function (jqXHR, textStatus, errorThrown) {
+            // Handle connection refused or other errors
+            if (textStatus === "error" && errorThrown === "") {
+                console.error("Connection refused or server unreachable");
+                $("#notification-test-log>span").text("Error: Connection refused or server is unreachable.");
+            } else {
+                console.error("Error:", textStatus, errorThrown);
+                $("#notification-test-log>span").text("An error occurred: " + textStatus);
+            }
+        }).always(function () {
+            $('.notifications-wrapper .spinner').hide();
+        })
+    });
 });
 

changedetectionio/static/js/plugins.js

@@ -0,0 +1,214 @@
+(function ($) {
+    // Initialize plugin management UI when the DOM is ready
+    $(document).ready(function() {
+        // Add event handlers for plugin checkboxes
+        $("#plugins-table input[type='checkbox']").on('change', function() {
+            const isEnabled = $(this).is(':checked');
+            
+            // For visual feedback, fade the row when disabled
+            if (isEnabled) {
+                $(this).closest('tr').removeClass('disabled-plugin');
+            } else {
+                $(this).closest('tr').addClass('disabled-plugin');
+            }
+            
+            const pluginName = $(this).closest('tr').find('td:nth-child(2)').text().trim();
+            console.log(`Plugin ${pluginName} ${isEnabled ? 'enabled' : 'disabled'}`);
+        });
+    });
+    
+    /**
+     * debounce
+     * @param {integer} milliseconds This param indicates the number of milliseconds
+     *     to wait after the last call before calling the original function.
+     * @param {object} What "this" refers to in the returned function.
+     * @return {function} This returns a function that when called will wait the
+     *     indicated number of milliseconds after the last call before
+     *     calling the original function.
+     */
+    Function.prototype.debounce = function (milliseconds, context) {
+        var baseFunction = this,
+            timer = null,
+            wait = milliseconds;
+
+        return function () {
+            var self = context || this,
+                args = arguments;
+
+            function complete() {
+                baseFunction.apply(self, args);
+                timer = null;
+            }
+
+            if (timer) {
+                clearTimeout(timer);
+            }
+
+            timer = setTimeout(complete, wait);
+        };
+    };
+
+    /**
+     * throttle
+     * @param {integer} milliseconds This param indicates the number of milliseconds
+     *     to wait between calls before calling the original function.
+     * @param {object} What "this" refers to in the returned function.
+     * @return {function} This returns a function that when called will wait the
+     *     indicated number of milliseconds between calls before
+     *     calling the original function.
+     */
+    Function.prototype.throttle = function (milliseconds, context) {
+        var baseFunction = this,
+            lastEventTimestamp = null,
+            limit = milliseconds;
+
+        return function () {
+            var self = context || this,
+                args = arguments,
+                now = Date.now();
+
+            if (!lastEventTimestamp || now - lastEventTimestamp >= limit) {
+                lastEventTimestamp = now;
+                baseFunction.apply(self, args);
+            }
+        };
+    };
+
+    $.fn.highlightLines = function (configurations) {
+        return this.each(function () {
+            const $pre = $(this);
+            const textContent = $pre.text();
+            const lines = textContent.split(/\r?\n/); // Handles both \n and \r\n line endings
+
+            // Build a map of line numbers to styles
+            const lineStyles = {};
+
+            configurations.forEach(config => {
+                const {color, lines: lineNumbers} = config;
+                lineNumbers.forEach(lineNumber => {
+                    lineStyles[lineNumber] = color;
+                });
+            });
+
+            // Function to escape HTML characters
+            function escapeHtml(text) {
+                return text.replace(/[&<>"'`=\/]/g, function (s) {
+                    return "&#" + s.charCodeAt(0) + ";";
+                });
+            }
+
+            // Process each line
+            const processedLines = lines.map((line, index) => {
+                const lineNumber = index + 1; // Line numbers start at 1
+                const escapedLine = escapeHtml(line);
+                const color = lineStyles[lineNumber];
+
+                if (color) {
+                    // Wrap the line in a span with inline style
+                    return `<span style="background-color: ${color}">${escapedLine}</span>`;
+                } else {
+                    return escapedLine;
+                }
+            });
+
+            // Join the lines back together
+            const newContent = processedLines.join('\n');
+
+            // Set the new content as HTML
+            $pre.html(newContent);
+        });
+    };
+    $.fn.miniTabs = function (tabsConfig, options) {
+        const settings = {
+            tabClass: 'minitab',
+            tabsContainerClass: 'minitabs',
+            activeClass: 'active',
+            ...(options || {})
+        };
+
+        return this.each(function () {
+            const $wrapper = $(this);
+            const $contents = $wrapper.find('div[id]').hide();
+            const $tabsContainer = $('<div>', {class: settings.tabsContainerClass}).prependTo($wrapper);
+
+            // Generate tabs
+            Object.entries(tabsConfig).forEach(([tabTitle, contentSelector], index) => {
+                const $content = $wrapper.find(contentSelector);
+                if (index === 0) $content.show(); // Show first content by default
+
+                $('<a>', {
+                    class: `${settings.tabClass}${index === 0 ? ` ${settings.activeClass}` : ''}`,
+                    text: tabTitle,
+                    'data-target': contentSelector
+                }).appendTo($tabsContainer);
+            });
+
+            // Tab click event
+            $tabsContainer.on('click', `.${settings.tabClass}`, function (e) {
+                e.preventDefault();
+                const $tab = $(this);
+                const target = $tab.data('target');
+
+                // Update active tab
+                $tabsContainer.find(`.${settings.tabClass}`).removeClass(settings.activeClass);
+                $tab.addClass(settings.activeClass);
+
+                // Show/hide content
+                $contents.hide();
+                $wrapper.find(target).show();
+            });
+        });
+    };
+
+    // Object to store ongoing requests by namespace
+    const requests = {};
+
+    $.abortiveSingularAjax = function (options) {
+        const namespace = options.namespace || 'default';
+
+        // Abort the current request in this namespace if it's still ongoing
+        if (requests[namespace]) {
+            requests[namespace].abort();
+        }
+
+        // Start a new AJAX request and store its reference in the correct namespace
+        requests[namespace] = $.ajax(options);
+
+        // Return the current request in case it's needed
+        return requests[namespace];
+    };
+})(jQuery);
+
+
+
+function toggleOpacity(checkboxSelector, fieldSelector, inverted) {
+    const checkbox = document.querySelector(checkboxSelector);
+    const fields = document.querySelectorAll(fieldSelector);
+
+    function updateOpacity() {
+        const opacityValue = !checkbox.checked ? (inverted ? 0.6 : 1) : (inverted ? 1 : 0.6);
+        fields.forEach(field => {
+            field.style.opacity = opacityValue;
+        });
+    }
+
+    // Initial setup
+    updateOpacity();
+    checkbox.addEventListener('change', updateOpacity);
+}
+
+function toggleVisibility(checkboxSelector, fieldSelector, inverted) {
+    const checkbox = document.querySelector(checkboxSelector);
+    const fields = document.querySelectorAll(fieldSelector);
+
+    function updateOpacity() {
+        const opacityValue = !checkbox.checked ? (inverted ? 'none' : 'block') : (inverted ? 'block' : 'none');
+        fields.forEach(field => {
+            field.style.display = opacityValue;
+        });
+    }
+
+    // Initial setup
+    updateOpacity();
+    checkbox.addEventListener('change', updateOpacity);
+}

changedetectionio/static/js/preview.js

@@ -1,53 +1,63 @@
-function redirect_to_version(version) {
-    var currentUrl = window.location.href;
-    var baseUrl = currentUrl.split('?')[0]; // Base URL without query parameters
+function redirectToVersion(version) {
+    var currentUrl = window.location.href.split('?')[0]; // Base URL without query parameters
     var anchor = '';
 
     // Check if there is an anchor
-    if (baseUrl.indexOf('#') !== -1) {
-        anchor = baseUrl.substring(baseUrl.indexOf('#'));
-        baseUrl = baseUrl.substring(0, baseUrl.indexOf('#'));
+    if (currentUrl.indexOf('#') !== -1) {
+        anchor = currentUrl.substring(currentUrl.indexOf('#'));
+        currentUrl = currentUrl.substring(0, currentUrl.indexOf('#'));
     }
-    window.location.href = baseUrl + '?version=' + version + anchor;
+
+    window.location.href = currentUrl + '?version=' + version + anchor;
 }
 
-document.addEventListener('keydown', function (event) {
-    var selectElement = document.getElementById('preview-version');
-    if (selectElement) {
-        var selectedOption = selectElement.querySelector('option:checked');
-        if (selectedOption) {
-            if (event.key === 'ArrowLeft') {
-                if (selectedOption.previousElementSibling) {
-                    redirect_to_version(selectedOption.previousElementSibling.value);
-                }
-            } else if (event.key === 'ArrowRight') {
-                if (selectedOption.nextElementSibling) {
-                    redirect_to_version(selectedOption.nextElementSibling.value);
-                }
+function setupDateWidget() {
+    $(document).on('keydown', function (event) {
+        var $selectElement = $('#preview-version');
+        var $selectedOption = $selectElement.find('option:selected');
+
+        if ($selectedOption.length) {
+            if (event.key === 'ArrowLeft' && $selectedOption.prev().length) {
+                redirectToVersion($selectedOption.prev().val());
+            } else if (event.key === 'ArrowRight' && $selectedOption.next().length) {
+                redirectToVersion($selectedOption.next().val());
             }
         }
-    }
-});
+    });
 
+    $('#preview-version').on('change', function () {
+        redirectToVersion($(this).val());
+    });
 
-document.getElementById('preview-version').addEventListener('change', function () {
-    redirect_to_version(this.value);
-});
+    var $selectedOption = $('#preview-version option:selected');
 
-var selectElement = document.getElementById('preview-version');
-if (selectElement) {
-    var selectedOption = selectElement.querySelector('option:checked');
-    if (selectedOption) {
-        if (selectedOption.previousElementSibling) {
-            document.getElementById('btn-previous').href = "?version=" + selectedOption.previousElementSibling.value;
+    if ($selectedOption.length) {
+        var $prevOption = $selectedOption.prev();
+        var $nextOption = $selectedOption.next();
+
+        if ($prevOption.length) {
+            $('#btn-previous').attr('href', '?version=' + $prevOption.val());
         } else {
-            document.getElementById('btn-previous').remove()
-        }
-        if (selectedOption.nextElementSibling) {
-            document.getElementById('btn-next').href = "?version=" + selectedOption.nextElementSibling.value;
-        } else {
-            document.getElementById('btn-next').remove()
+            $('#btn-previous').remove();
         }
 
+        if ($nextOption.length) {
+            $('#btn-next').attr('href', '?version=' + $nextOption.val());
+        } else {
+            $('#btn-next').remove();
+        }
     }
 }
+
+$(document).ready(function () {
+    if ($('#preview-version').length) {
+        setupDateWidget();
+    }
+
+    $('#diff-col > pre').highlightLines([
+        {
+            'color': '#ee0000',
+            'lines': triggered_line_numbers
+        }
+    ]);
+});

changedetectionio/static/js/recheck-proxy.js

@@ -1,14 +1,14 @@
 $(function () {
     /* add container before each proxy location to show status */
-
-    var option_li = $('.fetch-backend-proxy li').filter(function() {
-        return $("input",this)[0].value.length >0;
-    });
-
-    //var option_li = $('.fetch-backend-proxy li');
     var isActive = false;
-    $(option_li).prepend('<div class="proxy-status"></div>');
-    $(option_li).append('<div class="proxy-timing"></div><div class="proxy-check-details"></div>');
+
+    function setup_html_widget() {
+        var option_li = $('.fetch-backend-proxy li').filter(function () {
+            return $("input", this)[0].value.length > 0;
+        });
+        $(option_li).prepend('<div class="proxy-status"></div>');
+        $(option_li).append('<div class="proxy-timing"></div><div class="proxy-check-details"></div>');
+    }
 
     function set_proxy_check_status(proxy_key, state) {
         // select input by value name
@@ -59,8 +59,14 @@ $(function () {
     }
 
     $('#check-all-proxies').click(function (e) {
+
         e.preventDefault()
-        $('body').addClass('proxy-check-active');
+
+        if (!$('body').hasClass('proxy-check-active')) {
+            setup_html_widget();
+            $('body').addClass('proxy-check-active');
+        }
+
         $('.proxy-check-details').html('');
         $('.proxy-status').html('<span class="spinner"></span>').fadeIn();
         $('.proxy-timing').html('');

changedetectionio/static/js/scheduler.js

@@ -0,0 +1,109 @@
+function getTimeInTimezone(timezone) {
+    const now = new Date();
+    const options = {
+        timeZone: timezone,
+        weekday: 'long',
+        year: 'numeric',
+        hour12: false,
+        month: '2-digit',
+        day: '2-digit',
+        hour: '2-digit',
+        minute: '2-digit',
+        second: '2-digit',
+    };
+
+    const formatter = new Intl.DateTimeFormat('en-US', options);
+    return formatter.format(now);
+}
+
+$(document).ready(function () {
+
+    let exceedsLimit = false;
+    const warning_text = $("#timespan-warning")
+    const timezone_text_widget = $("input[id*='time_schedule_limit-timezone']")
+
+    toggleVisibility('#time_schedule_limit-enabled, #requests-time_schedule_limit-enabled', '#schedule-day-limits-wrapper', true)
+
+    setInterval(() => {
+        let success = true;
+        try {
+            // Show the current local time according to either placeholder or entered TZ name
+            if (timezone_text_widget.val().length) {
+                $('#local-time-in-tz').text(getTimeInTimezone(timezone_text_widget.val()));
+            } else {
+                // So maybe use what is in the placeholder (which will be the default settings)
+                $('#local-time-in-tz').text(getTimeInTimezone(timezone_text_widget.attr('placeholder')));
+            }
+        } catch (error) {
+            success = false;
+            $('#local-time-in-tz').text("");
+            console.error(timezone_text_widget.val())
+        }
+
+        $(timezone_text_widget).toggleClass('error', !success);
+
+    }, 500);
+
+    $('#schedule-day-limits-wrapper').on('change click blur', 'input, checkbox, select', function() {
+
+        let allOk = true;
+
+        // Controls setting the warning that the time could overlap into the next day
+        $("li.day-schedule").each(function () {
+            const $schedule = $(this);
+            const $checkbox = $schedule.find("input[type='checkbox']");
+
+            if ($checkbox.is(":checked")) {
+                const timeValue = $schedule.find("input[type='time']").val();
+                const durationHours = parseInt($schedule.find("select[name*='-duration-hours']").val(), 10) || 0;
+                const durationMinutes = parseInt($schedule.find("select[name*='-duration-minutes']").val(), 10) || 0;
+
+                if (timeValue) {
+                    const [startHours, startMinutes] = timeValue.split(":").map(Number);
+                    const totalMinutes = (startHours * 60 + startMinutes) + (durationHours * 60 + durationMinutes);
+
+                    exceedsLimit = totalMinutes > 1440
+                    if (exceedsLimit) {
+                        allOk = false
+                    }
+                    // Set the row/day-of-week highlight
+                    $schedule.toggleClass("warning", exceedsLimit);
+                }
+            } else {
+                $schedule.toggleClass("warning", false);
+            }
+        });
+
+        warning_text.toggle(!allOk)
+    });
+
+    $('table[id*="time_schedule_limit-saturday"], table[id*="time_schedule_limit-sunday"]').addClass("weekend-day")
+
+    // Presets [weekend] [business hours] etc
+    $(document).on('click', '[data-template].set-schedule', function () {
+        // Get the value of the 'data-template' attribute
+        switch ($(this).attr('data-template')) {
+            case 'business-hours':
+                $('.day-schedule table:not(.weekend-day) input[type="time"]').val('09:00')
+                $('.day-schedule table:not(.weekend-day) select[id*="-duration-hours"]').val('8');
+                $('.day-schedule table:not(.weekend-day) select[id*="-duration-minutes"]').val('0');
+                $('.day-schedule input[id*="-enabled"]').prop('checked', true);
+                $('.day-schedule .weekend-day input[id*="-enabled"]').prop('checked', false);
+                break;
+            case 'weekend':
+                $('.day-schedule .weekend-day input[type="time"][id$="start-time"]').val('00:00')
+                $('.day-schedule .weekend-day select[id*="-duration-hours"]').val('24');
+                $('.day-schedule .weekend-day select[id*="-duration-minutes"]').val('0');
+                $('.day-schedule input[id*="-enabled"]').prop('checked', false);
+                $('.day-schedule .weekend-day input[id*="-enabled"]').prop('checked', true);
+                break;
+            case 'reset':
+
+                $('.day-schedule input[type="time"]').val('00:00')
+                $('.day-schedule select[id*="-duration-hours"]').val('24');
+                $('.day-schedule select[id*="-duration-minutes"]').val('0');
+                $('.day-schedule input[id*="-enabled"]').prop('checked', true);
+                break;
+        }
+    });
+});

changedetectionio/static/js/tabs.js

@@ -26,8 +26,6 @@ function set_active_tab() {
     if (tab.length) {
         tab[0].parentElement.className = "active";
     }
-    // hash could move the page down
-    window.scrollTo(0, 0);
 }
 
 function focus_error_tab() {

changedetectionio/static/js/toggle-theme.js

@@ -49,4 +49,9 @@ $(document).ready(function () {
         $("#overlay").toggleClass('visible');
         heartpath.style.fill = document.getElementById("overlay").classList.contains("visible") ? '#ff0000' : 'var(--color-background)';
     });
+
+    setInterval(function () {
+        $('body').toggleClass('spinner-active', $.active > 0);
+    }, 2000);
+
 });

changedetectionio/static/js/visual-selector.js

@@ -132,6 +132,7 @@ $(document).ready(() => {
         }).done((data) => {
             $fetchingUpdateNoticeElem.html("Rendering..");
             selectorData = data;
+
             sortScrapedElementsBySize();
             console.log(`Reported browser width from backend: ${data['browser_width']}`);
 

changedetectionio/static/js/watch-settings.js

@@ -1,18 +1,51 @@
-function toggleOpacity(checkboxSelector, fieldSelector, inverted) {
-    const checkbox = document.querySelector(checkboxSelector);
-    const fields = document.querySelectorAll(fieldSelector);
-    function updateOpacity() {
-        const opacityValue = !checkbox.checked ? (inverted ? 0.6 : 1) : (inverted ? 1 : 0.6);
-        fields.forEach(field => {
-            field.style.opacity = opacityValue;
-        });
+
+function request_textpreview_update() {
+    if (!$('body').hasClass('preview-text-enabled')) {
+        console.error("Preview text was requested but body tag was not setup")
+        return
     }
-    // Initial setup
-    updateOpacity();
-    checkbox.addEventListener('change', updateOpacity);
+
+    const data = {};
+    $('textarea:visible, input:visible').each(function () {
+        const $element = $(this); // Cache the jQuery object for the current element
+        const name = $element.attr('name'); // Get the name attribute of the element
+        data[name] = $element.is(':checkbox') ? ($element.is(':checked') ? $element.val() : false) : $element.val();
+    });
+
+    $('body').toggleClass('spinner-active', 1);
+
+    $.abortiveSingularAjax({
+        type: "POST",
+        url: preview_text_edit_filters_url,
+        data: data,
+        namespace: 'watchEdit'
+    }).done(function (data) {
+        console.debug(data['duration'])
+        $('#filters-and-triggers #text-preview-before-inner').text(data['before_filter']);
+        $('#filters-and-triggers #text-preview-inner')
+            .text(data['after_filter'])
+            .highlightLines([
+                {
+                    'color': '#ee0000',
+                    'lines': data['trigger_line_numbers']
+                },
+                {
+                    'color': '#757575',
+                    'lines': data['ignore_line_numbers']
+                }
+            ])
+    }).fail(function (error) {
+        if (error.statusText === 'abort') {
+            console.log('Request was aborted due to a new request being fired.');
+        } else {
+            $('#filters-and-triggers #text-preview-inner').text('There was an error communicating with the server.');
+        }
+    })
 }
 
+
 $(document).ready(function () {
+
     $('#notification-setting-reset-to-default').click(function (e) {
         $('#notification_title').val('');
         $('#notification_body').val('');
@@ -25,7 +58,24 @@ $(document).ready(function () {
         $('#notification-tokens-info').toggle();
     });
 
-    toggleOpacity('#time_between_check_use_default', '#time_between_check', false);
+    toggleOpacity('#time_between_check_use_default', '#time-check-widget-wrapper, #time-between-check-schedule', false);
 
+
+    const vh = Math.max(document.documentElement.clientHeight || 0, window.innerHeight || 0);
+    $("#text-preview-inner").css('max-height', (vh - 300) + "px");
+    $("#text-preview-before-inner").css('max-height', (vh - 300) + "px");
+
+    $("#activate-text-preview").click(function (e) {
+        $('body').toggleClass('preview-text-enabled')
+        request_textpreview_update();
+        const method = $('body').hasClass('preview-text-enabled') ? 'on' : 'off';
+        $('#filters-and-triggers textarea')[method]('blur', request_textpreview_update.throttle(1000));
+        $('#filters-and-triggers input')[method]('change', request_textpreview_update.throttle(1000));
+        $("#filters-and-triggers-tab")[method]('click', request_textpreview_update.throttle(1000));
+    });
+    $('.minitabs-wrapper').miniTabs({
+        "Content after filters": "#text-preview-inner",
+        "Content raw/before filters": "#text-preview-before-inner"
+    });
 });
 

changedetectionio/static/styles/diff.css

@@ -153,7 +153,8 @@ html[data-darkmode="true"] {
     border: 1px solid transparent;
     vertical-align: top;
     font: 1em monospace;
-    text-align: left; }
+    text-align: left;
+    overflow: clip; }
   #diff-ui pre {
     white-space: pre-wrap; }
 
@@ -172,7 +173,9 @@ ins {
   text-decoration: none; }
 
 #result {
-  white-space: pre-wrap; }
+  white-space: pre-wrap;
+  word-break: break-word;
+  overflow-wrap: break-word; }
 
 #settings {
   background: rgba(0, 0, 0, 0.05);
@@ -231,3 +234,12 @@ td#diff-col div {
   border-radius: 5px;
   background: var(--color-background);
   box-shadow: 1px 1px 4px var(--color-shadow-jump); }
+
+.pure-form button.reset-margin {
+  margin: 0px; }
+
+.diff-fieldset {
+  display: flex;
+  align-items: center;
+  gap: 4px;
+  flex-wrap: wrap; }

changedetectionio/static/styles/scss/diff.scss

@@ -24,6 +24,7 @@
     vertical-align: top;
     font: 1em monospace;
     text-align: left;
+    overflow: clip; // clip overflowing contents to cell boundariess
   }
 
   pre {
@@ -50,6 +51,8 @@ ins {
 
 #result {
   white-space: pre-wrap;
+  word-break: break-word;
+  overflow-wrap: break-word;
 
   .change {
     span {}
@@ -134,3 +137,15 @@ td#diff-col div {
   background: var(--color-background);
   box-shadow: 1px 1px 4px var(--color-shadow-jump);
 }
+
+// resets button margin to 0px
+.pure-form button.reset-margin {
+  margin: 0px;
+}
+
+.diff-fieldset {
+  display: flex;
+  align-items: center;
+  gap: 4px;
+  flex-wrap: wrap;
+}

changedetectionio/static/styles/scss/parts/_browser-steps.scss

@@ -40,24 +40,47 @@
   }
 }
 
-#browser-steps-fieldlist {
-  height: 100%;
-  overflow-y: scroll;
-}
+@media only screen and (min-width: 760px) {
 
-#browser-steps .flex-wrapper {
-  display: flex;
-  flex-flow: row;
-  height: 70vh;
+  #browser-steps .flex-wrapper {
+    display: flex;
+    flex-flow: row;
+    height: 70vh;
+    font-size: 80%;
+
+    #browser-steps-ui {
+      flex-grow: 1; /* Allow it to grow and fill the available space */
+      flex-shrink: 1; /* Allow it to shrink if needed */
+      flex-basis: 0; /* Start with 0 base width so it stretches as much as possible */
+      background-color: #eee;
+      border-radius: 5px;
+
+    }
+  }
+
+  #browser-steps-fieldlist {
+    flex-grow: 0;      /* Don't allow it to grow */
+    flex-shrink: 0;    /* Don't allow it to shrink */
+    flex-basis: auto;  /* Base width is determined by the content */
+    max-width: 400px;  /* Set a max width to prevent overflow */
+    padding-left: 1rem;
+    overflow-y: scroll;
+  }
+
+  /*  this is duplicate :( */
+  #browsersteps-selector-wrapper {
+    height: 100% !important;
+  }
 }
 
 /*  this is duplicate :( */
 #browsersteps-selector-wrapper {
-  height: 100%;
+
   width: 100%;
   overflow-y: scroll;
   position: relative;
-  //width: 100%;
+  height: 80vh;
+
   > img {
     position: absolute;
     max-width: 100%;
@@ -77,7 +100,6 @@
     left: 50%;
     top: 50%;
     transform: translate(-50%, -50%);
-    margin-left: -40px;
     z-index: 100;
     max-width: 350px;
     text-align: center;

changedetectionio/static/styles/scss/parts/_edit.scss

@@ -0,0 +1,9 @@
+ul#conditions_match_logic {
+    list-style: none;
+  input, label, li {
+    display: inline-block;
+  }
+  li {
+    padding-right: 1em;
+  }
+}

changedetectionio/static/styles/scss/parts/_extra_browsers.scss

@@ -11,7 +11,22 @@ ul#requests-extra_browsers {
   /* each proxy entry is a `table` */
   table {
     tr {
-      display: inline;
+      display: table-row; // default display for small screens
+      input[type=text] {
+        width: 100%;
+      }
+    }
+  }
+  
+  // apply inline display for larger screens
+  @media only screen and (min-width: 1280px) {
+    table {
+      tr {
+        display: inline;
+        input[type=text] {
+          width: 100%;
+        }
+      }
     }
   }
 }

changedetectionio/static/styles/scss/parts/_extra_proxies.scss

@@ -11,7 +11,19 @@ ul#requests-extra_proxies {
   /* each proxy entry is a `table` */
   table {
     tr {
-      display: inline;
+      display: table-row; // default display for small screens
+      input[type=text] {
+        width: 100%;
+      }
+    }
+  }
+  
+  // apply inline display for large screens
+  @media only screen and (min-width: 1024px) {
+    table {
+      tr {
+        display: inline;
+      }
     }
   }
 }
@@ -25,15 +37,19 @@ ul#requests-extra_proxies {
 
 body.proxy-check-active {
   #request {
+    // Padding set by flex layout
+    /*
     .proxy-status {
       width: 2em;
     }
+    */
 
     .proxy-check-details {
       font-size: 80%;
       color: #555;
       display: block;
-      padding-left: 4em;
+      padding-left: 2em;
+      max-width: 500px;
     }
 
     .proxy-timing {

changedetectionio/static/styles/scss/parts/_minitabs.scss

@@ -0,0 +1,47 @@
+.minitabs-wrapper {
+  width: 100%;
+
+  > div[id] {
+    padding: 20px;
+    border: 1px solid #ccc;
+    border-top: none;
+  }
+
+  .minitabs-content {
+    width: 100%;
+    display: flex;
+    > div {
+      flex: 1 1 auto;
+      min-width: 0;
+      overflow: scroll;
+    }
+  }
+
+  .minitabs {
+    display: flex;
+    border-bottom: 1px solid #ccc;
+  }
+
+  .minitab {
+    flex: 1;
+    text-align: center;
+    padding: 12px 0;
+    text-decoration: none;
+    color: #333;
+    background-color: #f1f1f1;
+    border: 1px solid #ccc;
+    border-bottom: none;
+    cursor: pointer;
+    transition: background-color 0.3s;
+  }
+
+  .minitab:hover {
+    background-color: #ddd;
+  }
+
+  .minitab.active {
+    background-color: #fff;
+    font-weight: bold;
+  }
+
+}

changedetectionio/static/styles/scss/parts/_preview_text_filter.scss

@@ -0,0 +1,55 @@
+@import "minitabs";
+
+body.preview-text-enabled {
+
+  @media (min-width: 800px) {
+    #filters-and-triggers > div {
+      display: flex; /* Establishes Flexbox layout */
+      gap: 20px; /* Adds space between the columns */
+      position: relative; /* Ensures the sticky positioning is relative to this parent */
+    }
+  }
+
+  /* layout of the page */
+  #edit-text-filter, #text-preview {
+    flex: 1; /* Each column takes an equal amount of available space */
+    align-self: flex-start; /* Aligns the right column to the start, allowing it to maintain its content height */
+  }
+
+  #edit-text-filter {
+    #pro-tips {
+      display: none;
+    }
+  }
+
+  #text-preview {
+    position: sticky;
+    top: 20px;
+    padding-top: 1rem;
+    padding-bottom: 1rem;
+    display: block !important;
+  }
+
+  #activate-text-preview {
+      background-color: var(--color-grey-500);
+  }
+
+  /* actual preview area */
+  .monospace-preview {
+    background: var(--color-background-input);
+    border: 1px solid var(--color-grey-600);
+    padding: 1rem;
+    color: var(--color-text-input);
+    font-family: "Courier New", Courier, monospace; /* Sets the font to a monospace type */
+    font-size: 70%;
+    word-break: break-word;
+    white-space: pre-wrap; /* Preserves whitespace and line breaks like <pre> */
+  }
+}
+
+#activate-text-preview {
+  right: 0;
+  position: absolute;
+  z-index: 3;
+  box-shadow: 1px 1px 4px var(--color-shadow-jump);
+}

changedetectionio/static/styles/scss/styles.scss

@@ -12,6 +12,8 @@
 @import "parts/_darkmode";
 @import "parts/_menu";
 @import "parts/_love";
+@import "parts/preview_text_filter";
+@import "parts/_edit";
 
 body {
   color: var(--color-text);
@@ -105,10 +107,34 @@ button.toggle-button {
   padding: 5px;
   display: flex;
   justify-content: space-between;
-  border-bottom: 2px solid var(--color-menu-accent);
   align-items: center;
 }
 
+#pure-menu-horizontal-spinner {
+  height: 3px;
+  background: linear-gradient(-75deg, #ff6000, #ff8f00, #ffdd00, #ed0000);
+  background-size: 400% 400%;
+  width: 100%;
+  animation: gradient 200s ease infinite;
+}
+
+body.spinner-active {
+  #pure-menu-horizontal-spinner {
+    animation: gradient 1s ease infinite;
+  }
+}
+
+@keyframes gradient {
+	0% {
+		background-position: 0% 50%;
+	}
+	50% {
+		background-position: 100% 50%;
+	}
+	100% {
+		background-position: 0% 50%;
+	}
+}
 .pure-menu-heading {
   color: var(--color-text-menu-heading);
 }
@@ -122,8 +148,14 @@ button.toggle-button {
   }
 }
 
+
+.tab-pane-inner {
+  // .tab-pane-inner will have the #id that the tab button jumps/anchors to
+  scroll-margin-top: 200px;
+}
+
 section.content {
-  padding-top: 5em;
+  padding-top: 100px;
   padding-bottom: 1em;
   flex-direction: column;
   display: flex;
@@ -320,10 +352,6 @@ a.pure-button-selected {
   background: var(--color-background-button-cancel);
 }
 
-#save_button {
-  margin-right: 1rem;
-}
-
 .messages {
   li {
     list-style: none;
@@ -353,7 +381,15 @@ a.pure-button-selected {
 }
 
 .notifications-wrapper {
-  padding: 0.5rem 0 1rem 0;
+  padding-top: 0.5rem;
+  #notification-test-log {
+    padding-top: 1rem;
+    white-space: pre-wrap;
+    word-break: break-word;
+    overflow-wrap: break-word;
+    max-width: 100%;
+    box-sizing: border-box;
+  }
 }
 
 label {
@@ -620,9 +656,9 @@ footer {
       list-style: none;
 
       li {
-        >* {
-          display: inline-block;
-        }
+        display: flex;
+        align-items: center;
+        gap: 1em;
       }
     }
   }
@@ -682,6 +718,12 @@ footer {
       tr {
         th {
           display: inline-block;
+          // Hide the "Last" text for smaller screens
+          @media (max-width: 768px) {
+            .hide-on-mobile {
+              display: none; 
+            }
+          }
         }
       }
       .empty-cell {
@@ -697,6 +739,24 @@ footer {
       }
     }
 
+    tbody {
+      tr {
+        display: flex;
+        flex-wrap: wrap;
+
+        // The third child of each row will take up the remaining space
+        // This is useful for the URL column, which should expand to fill the remaining space
+        :nth-child(3) {
+          flex-grow: 1;
+        }
+        // The last three children (from the end) of each row will take up the full width
+        // This is useful for the "Last Checked", "Last Changed", and the action buttons columns, which should each take up the full width
+        :nth-last-child(-n+3) {
+          flex-basis: 100%;
+        }
+      }
+    }
+
     .last-checked {
       >span {
         vertical-align: middle;
@@ -815,6 +875,11 @@ textarea::placeholder {
 - We dont use 'size' with <input> because `size` is too unreliable to override, and will often push-out
 - Rely always on width in CSS
 */
+/** Set max width for input field */
+.m-d {
+  min-width: 100%;
+}
+
 @media only screen and (min-width: 761px) {
 
   /* m-d is medium-desktop */
@@ -881,6 +946,7 @@ $form-edge-padding: 20px;
 }
 
 .tab-pane-inner {
+
   &:not(:target) {
     display: none;
   }
@@ -930,6 +996,13 @@ body.full-width {
     background: var(--color-background);
   }
 
+  /* Make action buttons have consistent size and spacing */
+  #actions .pure-control-group {
+    display: flex;
+    gap: 0.625em;
+    flex-wrap: wrap;
+  }
+
   .pure-form-message-inline {
     padding-left: 0;
     color: var(--color-text-input-description);
@@ -973,6 +1046,28 @@ ul {
   }
 }
 
+@media only screen and (max-width: 760px) {
+  .time-check-widget {
+    tbody {
+      display: grid;
+      grid-template-columns: auto 1fr auto 1fr;
+      gap: 0.625em 0.3125em;
+      align-items: center;
+    }    
+    tr {
+      display: contents; 
+      th {
+        text-align: right;
+        padding-right: 5px;
+      }
+      input[type="number"] {
+        width: 100%;
+        max-width: 5em;
+      }
+    }
+  }
+}
+
 @import "parts/_visualselector";
 
 #webdriver_delay {

changedetectionio/static/styles/styles.css

@@ -46,21 +46,42 @@
     #browser_steps li > label {
       display: none; }
 
-#browser-steps-fieldlist {
-  height: 100%;
-  overflow-y: scroll; }
-
-#browser-steps .flex-wrapper {
-  display: flex;
-  flex-flow: row;
-  height: 70vh; }
+@media only screen and (min-width: 760px) {
+  #browser-steps .flex-wrapper {
+    display: flex;
+    flex-flow: row;
+    height: 70vh;
+    font-size: 80%; }
+    #browser-steps .flex-wrapper #browser-steps-ui {
+      flex-grow: 1;
+      /* Allow it to grow and fill the available space */
+      flex-shrink: 1;
+      /* Allow it to shrink if needed */
+      flex-basis: 0;
+      /* Start with 0 base width so it stretches as much as possible */
+      background-color: #eee;
+      border-radius: 5px; }
+  #browser-steps-fieldlist {
+    flex-grow: 0;
+    /* Don't allow it to grow */
+    flex-shrink: 0;
+    /* Don't allow it to shrink */
+    flex-basis: auto;
+    /* Base width is determined by the content */
+    max-width: 400px;
+    /* Set a max width to prevent overflow */
+    padding-left: 1rem;
+    overflow-y: scroll; }
+  /*  this is duplicate :( */
+  #browsersteps-selector-wrapper {
+    height: 100% !important; } }
 
 /*  this is duplicate :( */
 #browsersteps-selector-wrapper {
-  height: 100%;
   width: 100%;
   overflow-y: scroll;
   position: relative;
+  height: 80vh;
   /* nice tall skinny one */ }
   #browsersteps-selector-wrapper > img {
     position: absolute;
@@ -75,7 +96,6 @@
     left: 50%;
     top: 50%;
     transform: translate(-50%, -50%);
-    margin-left: -40px;
     z-index: 100;
     max-width: 350px;
     text-align: center; }
@@ -95,26 +115,34 @@ ul#requests-extra_proxies {
   ul#requests-extra_proxies li > label {
     display: none; }
   ul#requests-extra_proxies table tr {
-    display: inline; }
+    display: table-row; }
+    ul#requests-extra_proxies table tr input[type=text] {
+      width: 100%; }
+  @media only screen and (min-width: 1024px) {
+    ul#requests-extra_proxies table tr {
+      display: inline; } }
 
 #request {
   /* Auto proxy scan/checker */ }
   #request label[for=proxy] {
     display: inline-block; }
 
-body.proxy-check-active #request .proxy-status {
-  width: 2em; }
-
-body.proxy-check-active #request .proxy-check-details {
-  font-size: 80%;
-  color: #555;
-  display: block;
-  padding-left: 4em; }
-
-body.proxy-check-active #request .proxy-timing {
-  font-size: 80%;
-  padding-left: 1rem;
-  color: var(--color-link); }
+body.proxy-check-active #request {
+  /*
+    .proxy-status {
+      width: 2em;
+    }
+    */ }
+  body.proxy-check-active #request .proxy-check-details {
+    font-size: 80%;
+    color: #555;
+    display: block;
+    padding-left: 2em;
+    max-width: 500px; }
+  body.proxy-check-active #request .proxy-timing {
+    font-size: 80%;
+    padding-left: 1rem;
+    color: var(--color-link); }
 
 #recommended-proxy {
   display: grid;
@@ -141,7 +169,14 @@ ul#requests-extra_browsers {
   ul#requests-extra_browsers li > label {
     display: none; }
   ul#requests-extra_browsers table tr {
-    display: inline; }
+    display: table-row; }
+    ul#requests-extra_browsers table tr input[type=text] {
+      width: 100%; }
+  @media only screen and (min-width: 1280px) {
+    ul#requests-extra_browsers table tr {
+      display: inline; }
+      ul#requests-extra_browsers table tr input[type=text] {
+        width: 100%; } }
 
 #extra-browsers-setting {
   border: 1px solid var(--color-grey-800);
@@ -411,6 +446,90 @@ html[data-darkmode="true"] #toggle-light-mode .icon-dark {
     fill: #ff0000 !important;
     transition: all ease 0.3s !important; }
 
+.minitabs-wrapper {
+  width: 100%; }
+  .minitabs-wrapper > div[id] {
+    padding: 20px;
+    border: 1px solid #ccc;
+    border-top: none; }
+  .minitabs-wrapper .minitabs-content {
+    width: 100%;
+    display: flex; }
+    .minitabs-wrapper .minitabs-content > div {
+      flex: 1 1 auto;
+      min-width: 0;
+      overflow: scroll; }
+  .minitabs-wrapper .minitabs {
+    display: flex;
+    border-bottom: 1px solid #ccc; }
+  .minitabs-wrapper .minitab {
+    flex: 1;
+    text-align: center;
+    padding: 12px 0;
+    text-decoration: none;
+    color: #333;
+    background-color: #f1f1f1;
+    border: 1px solid #ccc;
+    border-bottom: none;
+    cursor: pointer;
+    transition: background-color 0.3s; }
+  .minitabs-wrapper .minitab:hover {
+    background-color: #ddd; }
+  .minitabs-wrapper .minitab.active {
+    background-color: #fff;
+    font-weight: bold; }
+
+body.preview-text-enabled {
+  /* layout of the page */
+  /* actual preview area */ }
+  @media (min-width: 800px) {
+    body.preview-text-enabled #filters-and-triggers > div {
+      display: flex;
+      /* Establishes Flexbox layout */
+      gap: 20px;
+      /* Adds space between the columns */
+      position: relative;
+      /* Ensures the sticky positioning is relative to this parent */ } }
+  body.preview-text-enabled #edit-text-filter, body.preview-text-enabled #text-preview {
+    flex: 1;
+    /* Each column takes an equal amount of available space */
+    align-self: flex-start;
+    /* Aligns the right column to the start, allowing it to maintain its content height */ }
+  body.preview-text-enabled #edit-text-filter #pro-tips {
+    display: none; }
+  body.preview-text-enabled #text-preview {
+    position: sticky;
+    top: 20px;
+    padding-top: 1rem;
+    padding-bottom: 1rem;
+    display: block !important; }
+  body.preview-text-enabled #activate-text-preview {
+    background-color: var(--color-grey-500); }
+  body.preview-text-enabled .monospace-preview {
+    background: var(--color-background-input);
+    border: 1px solid var(--color-grey-600);
+    padding: 1rem;
+    color: var(--color-text-input);
+    font-family: "Courier New", Courier, monospace;
+    /* Sets the font to a monospace type */
+    font-size: 70%;
+    word-break: break-word;
+    white-space: pre-wrap;
+    /* Preserves whitespace and line breaks like <pre> */ }
+
+#activate-text-preview {
+  right: 0;
+  position: absolute;
+  z-index: 3;
+  box-shadow: 1px 1px 4px var(--color-shadow-jump); }
+
+ul#conditions_match_logic {
+  list-style: none; }
+  ul#conditions_match_logic input, ul#conditions_match_logic label, ul#conditions_match_logic li {
+    display: inline-block; }
+  ul#conditions_match_logic li {
+    padding-right: 1em; }
+
 body {
   color: var(--color-text);
   background: var(--color-background-page);
@@ -479,9 +598,26 @@ button.toggle-button {
   padding: 5px;
   display: flex;
   justify-content: space-between;
-  border-bottom: 2px solid var(--color-menu-accent);
   align-items: center; }
 
+#pure-menu-horizontal-spinner {
+  height: 3px;
+  background: linear-gradient(-75deg, #ff6000, #ff8f00, #ffdd00, #ed0000);
+  background-size: 400% 400%;
+  width: 100%;
+  animation: gradient 200s ease infinite; }
+
+body.spinner-active #pure-menu-horizontal-spinner {
+  animation: gradient 1s ease infinite; }
+
+@keyframes gradient {
+  0% {
+    background-position: 0% 50%; }
+  50% {
+    background-position: 100% 50%; }
+  100% {
+    background-position: 0% 50%; } }
+
 .pure-menu-heading {
   color: var(--color-text-menu-heading); }
 
@@ -491,8 +627,11 @@ button.toggle-button {
     background-color: var(--color-background-menu-link-hover);
     color: var(--color-text-menu-link-hover); }
 
+.tab-pane-inner {
+  scroll-margin-top: 200px; }
+
 section.content {
-  padding-top: 5em;
+  padding-top: 100px;
   padding-bottom: 1em;
   flex-direction: column;
   display: flex;
@@ -634,9 +773,6 @@ a.pure-button-selected {
 .button-cancel {
   background: var(--color-background-button-cancel); }
 
-#save_button {
-  margin-right: 1rem; }
-
 .messages li {
   list-style: none;
   padding: 1em;
@@ -654,7 +790,14 @@ a.pure-button-selected {
   cursor: pointer; }
 
 .notifications-wrapper {
-  padding: 0.5rem 0 1rem 0; }
+  padding-top: 0.5rem; }
+  .notifications-wrapper #notification-test-log {
+    padding-top: 1rem;
+    white-space: pre-wrap;
+    word-break: break-word;
+    overflow-wrap: break-word;
+    max-width: 100%;
+    box-sizing: border-box; }
 
 label:hover {
   cursor: pointer; }
@@ -835,8 +978,10 @@ footer {
   .pure-form .inline-radio ul {
     margin: 0px;
     list-style: none; }
-    .pure-form .inline-radio ul li > * {
-      display: inline-block; }
+    .pure-form .inline-radio ul li {
+      display: flex;
+      align-items: center;
+      gap: 1em; }
 
 @media only screen and (max-width: 760px), (min-device-width: 768px) and (max-device-width: 1024px) {
   .box {
@@ -872,12 +1017,24 @@ footer {
     .watch-table thead {
       display: block; }
       .watch-table thead tr th {
-        display: inline-block; }
+        display: inline-block; } }
+      @media only screen and (max-width: 760px) and (max-width: 768px), (min-device-width: 768px) and (max-device-width: 800px) and (max-width: 768px) {
+        .watch-table thead tr th .hide-on-mobile {
+          display: none; } }
+
+@media only screen and (max-width: 760px), (min-device-width: 768px) and (max-device-width: 800px) {
       .watch-table thead .empty-cell {
         display: none; }
     .watch-table tbody td,
     .watch-table tbody tr {
       display: block; }
+    .watch-table tbody tr {
+      display: flex;
+      flex-wrap: wrap; }
+      .watch-table tbody tr :nth-child(3) {
+        flex-grow: 1; }
+      .watch-table tbody tr :nth-last-child(-n+3) {
+        flex-basis: 100%; }
     .watch-table .last-checked > span {
       vertical-align: middle; }
     .watch-table .last-checked::before {
@@ -969,6 +1126,10 @@ textarea::placeholder {
 - We dont use 'size' with <input> because `size` is too unreliable to override, and will often push-out
 - Rely always on width in CSS
 */
+/** Set max width for input field */
+.m-d {
+  min-width: 100%; }
+
 @media only screen and (min-width: 761px) {
   /* m-d is medium-desktop */
   .m-d {
@@ -1029,7 +1190,8 @@ body.full-width .edit-form {
 .edit-form {
   min-width: 70%;
   /* so it cant overflow */
-  max-width: 95%; }
+  max-width: 95%;
+  /* Make action buttons have consistent size and spacing */ }
   .edit-form .box-wrap {
     position: relative; }
   .edit-form .inner {
@@ -1038,6 +1200,10 @@ body.full-width .edit-form {
   .edit-form #actions {
     display: block;
     background: var(--color-background); }
+  .edit-form #actions .pure-control-group {
+    display: flex;
+    gap: 0.625em;
+    flex-wrap: wrap; }
   .edit-form .pure-form-message-inline {
     padding-left: 0;
     color: var(--color-text-input-description); }
@@ -1066,6 +1232,21 @@ ul {
   .time-check-widget tr input[type="number"] {
     width: 5em; }
 
+@media only screen and (max-width: 760px) {
+  .time-check-widget tbody {
+    display: grid;
+    grid-template-columns: auto 1fr auto 1fr;
+    gap: 0.625em 0.3125em;
+    align-items: center; }
+  .time-check-widget tr {
+    display: contents; }
+    .time-check-widget tr th {
+      text-align: right;
+      padding-right: 5px; }
+    .time-check-widget tr input[type="number"] {
+      width: 100%;
+      max-width: 5em; } }
+
 #selector-wrapper {
   height: 100%;
   text-align: center;
@@ -1194,11 +1375,9 @@ ul {
   color: #fff;
   opacity: 0.7; }
 
-
 .restock-label svg {
   vertical-align: middle; }
 
-
 #chrome-extension-link {
   padding: 9px;
   border: 1px solid var(--color-grey-800);

changedetectionio/store.py

@@ -4,22 +4,22 @@ from flask import (
     flash
 )
 
+from .html_tools import TRANSLATE_WHITESPACE_TABLE
 from . model import App, Watch
-from copy import deepcopy, copy
+from copy import deepcopy
 from os import path, unlink
 from threading import Lock
 import json
 import os
 import re
-import requests
 import secrets
 import threading
 import time
 import uuid as uuid_builder
 from loguru import logger
+from deepmerge import always_merger
 
-from .processors import get_custom_watch_obj_for_processor
-from .processors.restock_diff import Restock
+from .processors import get_watch_model_for_processor
 
 # Because the server will run as a daemon and wont know the URL for notification links when firing off a notification
 BASE_URL_NOT_SET_TEXT = '("Base URL" not set - see settings - notifications)'
@@ -31,11 +31,6 @@ dictfilt = lambda x, y: dict([ (i,x[i]) for i in x if i in set(y) ])
 # https://stackoverflow.com/questions/6190468/how-to-trigger-function-on-value-change
 class ChangeDetectionStore:
     lock = Lock()
-    # For general updates/writes that can wait a few seconds
-    needs_write = False
-
-    # For when we edit, we should write to disk
-    needs_write_urgent = False
 
     __version_check = True
 
@@ -46,12 +41,9 @@ class ChangeDetectionStore:
         self.datastore_path = datastore_path
         self.json_store_path = "{}/url-watches.json".format(self.datastore_path)
         logger.info(f"Datastore path is '{self.json_store_path}'")
-        self.needs_write = False
+
         self.start_time = time.time()
         self.stop_thread = False
-        # Base definition for all watchers
-        # deepcopy part of #569 - not sure why its needed exactly
-        self.generic_definition = deepcopy(Watch.model(datastore_path = datastore_path, default={}))
 
         if path.isfile('changedetectionio/source.txt'):
             with open('changedetectionio/source.txt') as f:
@@ -59,38 +51,30 @@ class ChangeDetectionStore:
                 # So when someone gives us a backup file to examine, we know exactly what code they were running.
                 self.__data['build_sha'] = f.read()
 
+        self.generic_definition = deepcopy(Watch.model(datastore_path = datastore_path, default={}))
+
         try:
-            # @todo retest with ", encoding='utf-8'"
-            with open(self.json_store_path) as json_file:
-                from_disk = json.load(json_file)
+            import os
+            # First load global settings from the main JSON file if it exists
+            if os.path.isfile(self.json_store_path):
+                with open(self.json_store_path) as json_file:
+                    from_disk = json.load(json_file)
+                    
+                    # Load app_guid and settings from the main JSON file
+                    if 'app_guid' in from_disk:
+                        self.__data['app_guid'] = from_disk['app_guid']
+    
+                    if 'settings' in from_disk:
+                        if 'headers' in from_disk['settings']:
+                            self.__data['settings']['headers'].update(from_disk['settings']['headers'])
+    
+                        if 'requests' in from_disk['settings']:
+                            self.__data['settings']['requests'].update(from_disk['settings']['requests'])
+    
+                        if 'application' in from_disk['settings']:
+                            self.__data['settings']['application'].update(from_disk['settings']['application'])
 
-                # @todo isnt there a way todo this dict.update recursively?
-                # Problem here is if the one on the disk is missing a sub-struct, it wont be present anymore.
-                if 'watching' in from_disk:
-                    self.__data['watching'].update(from_disk['watching'])
 
-                if 'app_guid' in from_disk:
-                    self.__data['app_guid'] = from_disk['app_guid']
-
-                if 'settings' in from_disk:
-                    if 'headers' in from_disk['settings']:
-                        self.__data['settings']['headers'].update(from_disk['settings']['headers'])
-
-                    if 'requests' in from_disk['settings']:
-                        self.__data['settings']['requests'].update(from_disk['settings']['requests'])
-
-                    if 'application' in from_disk['settings']:
-                        self.__data['settings']['application'].update(from_disk['settings']['application'])
-
-                # Convert each existing watch back to the Watch.model object
-                for uuid, watch in self.__data['watching'].items():
-                    self.__data['watching'][uuid] = self.rehydrate_entity(uuid, watch)
-                    logger.info(f"Watching: {uuid} {watch['url']}")
-
-                # And for Tags also, should be Restock type because it has extra settings
-                for uuid, tag in self.__data['settings']['application']['tags'].items():
-                    self.__data['settings']['application']['tags'][uuid] = self.rehydrate_entity(uuid, tag, processor_override='restock_diff')
-                    logger.info(f"Tag: {uuid} {tag['title']}")
 
         # First time ran, Create the datastore.
         except (FileNotFoundError):
@@ -109,6 +93,8 @@ class ChangeDetectionStore:
 
         else:
             # Bump the update version by running updates
+            self.scan_load_watches()
+            self.scan_load_tags()
             self.run_updates()
 
         self.__data['version_tag'] = version_tag
@@ -140,53 +126,93 @@ class ChangeDetectionStore:
             secret = secrets.token_hex(16)
             self.__data['settings']['application']['api_access_token'] = secret
 
-        self.needs_write = True
+    def scan_load_watches(self):
 
-        # Finally start the thread that will manage periodic data saves to JSON
-        save_data_thread = threading.Thread(target=self.save_datastore).start()
+        # Now scan for individual watch.json files in the datastore directory
+        import pathlib
+        watch_jsons = list(pathlib.Path(self.datastore_path).rglob("*/watch.json"))
 
-    def rehydrate_entity(self, uuid, entity, processor_override=None):
-        """Set the dict back to the dict Watch object"""
-        entity['uuid'] = uuid
+        for watch_file in watch_jsons:
+            # Extract UUID from the directory name (parent directory of watch.json)
+            uuid = watch_file.parent.name
 
-        if processor_override:
-            watch_class = get_custom_watch_obj_for_processor(processor_override)
-            entity['processor']=processor_override
-        else:
-            watch_class = get_custom_watch_obj_for_processor(entity.get('processor'))
+            try:
+                with open(watch_file, 'r') as f:
+                    watch_data = json.load(f)
+                    # Create a Watch object and add it to the datastore
+                    self.__data['watching'][uuid] = self.rehydrate_entity(default_dict=watch_data)
+                    logger.info(f"Watching: {uuid} {watch_data.get('url')}")
 
-        if entity.get('uuid') != 'text_json_diff':
-            logger.trace(f"Loading Watch object '{watch_class.__module__}.{watch_class.__name__}' for UUID {uuid}")
+            except Exception as e:
+                logger.error(f"Error loading watch from {watch_file}: {str(e)}")
+                continue
+        logger.debug(f"{len(self.__data['watching'])} watches loaded.")
 
-        entity = watch_class(datastore_path=self.datastore_path, default=entity)
+    def scan_load_tags(self):
+        import pathlib
+        # Now scan for individual tag.json files in the tags directory
+        tags_path = os.path.join(self.datastore_path, 'tags')
+        if os.path.exists(tags_path):
+            tag_jsons = list(pathlib.Path(tags_path).rglob("*.json"))
+
+            for tag_file in tag_jsons:
+                # Extract UUID from the directory name (parent directory of tag.json)
+
+                try:
+                    with open(tag_file, 'r') as f:
+                        tag_data = json.load(f)
+                        uuid = str(tag_file).replace('.json', '')
+                        tag_data['uuid'] = uuid
+                        # Create a Tag object and add it to the datastore
+                        self.__data['settings']['application']['tags'][uuid] = self.rehydrate_entity(
+                            default_dict=tag_data,
+                            processor_override='restock_diff'
+                        )
+                        logger.info(f"Tag: {uuid} {tag_data.get('title', 'No title found')}")
+                except Exception as e:
+                    logger.error(f"Error loading tag from {tag_file}: {str(e)}")
+                    continue
+        logger.debug(f"{len(self.__data['settings']['application']['tags'])} tags loaded.")
+
+    def rehydrate_entity(self, default_dict: dict, processor_override=None):
+
+        if not processor_override and default_dict.get('processor'):
+            processor_override = default_dict.get('processor')
+        if not processor_override:
+            processor_override = 'text_json_diff'
+        watch_class = get_watch_model_for_processor(processor_override)
+        default_dict['processor'] = processor_override
+        entity = watch_class(datastore_path=self.datastore_path, default=default_dict)
+        entity.enable_saving()
         return entity
 
     def set_last_viewed(self, uuid, timestamp):
         logger.debug(f"Setting watch UUID: {uuid} last viewed to {int(timestamp)}")
         self.data['watching'][uuid].update({'last_viewed': int(timestamp)})
-        self.needs_write = True
+        self.data['watching'][uuid].save_data()
 
     def remove_password(self):
         self.__data['settings']['application']['password'] = False
-        self.needs_write = True
+        self.save_settings()
 
     def update_watch(self, uuid, update_obj):
-
+        """
+        Update a watch with new values using the deepmerge library.
+        """
         # It's possible that the watch could be deleted before update
-        if not self.__data['watching'].get(uuid):
+        if not uuid in self.data['watching'].keys() or update_obj is None:
             return
 
-        with self.lock:
+        # In python 3.9 we have the |= dict operator, but that still will lose data on nested structures...
+        for dict_key, d in self.generic_definition.items():
+            if isinstance(d, dict):
+                if update_obj is not None and dict_key in update_obj:
+                    self.__data['watching'][uuid][dict_key].update(update_obj[dict_key])
+                    del (update_obj[dict_key])
 
-            # In python 3.9 we have the |= dict operator, but that still will lose data on nested structures...
-            for dict_key, d in self.generic_definition.items():
-                if isinstance(d, dict):
-                    if update_obj is not None and dict_key in update_obj:
-                        self.__data['watching'][uuid][dict_key].update(update_obj[dict_key])
-                        del (update_obj[dict_key])
+        self.__data['watching'][uuid].update(update_obj)
+        self.__data['watching'][uuid].save_data()
 
-            self.__data['watching'][uuid].update(update_obj)
-        self.needs_write = True
 
     @property
     def threshold_seconds(self):
@@ -246,8 +272,6 @@ class ChangeDetectionStore:
                     shutil.rmtree(path)
                 del self.data['watching'][uuid]
 
-        self.needs_write_urgent = True
-
     # Clone a watch by UUID
     def clone(self, uuid):
         url = self.data['watching'][uuid].get('url')
@@ -267,9 +291,9 @@ class ChangeDetectionStore:
     # Remove a watchs data but keep the entry (URL etc)
     def clear_watch_history(self, uuid):
         self.__data['watching'][uuid].clear_watch()
-        self.needs_write_urgent = True
 
     def add_watch(self, url, tag='', extras=None, tag_uuids=None, write_to_disk_now=True):
+        import requests
 
         if extras is None:
             extras = {}
@@ -344,7 +368,7 @@ class ChangeDetectionStore:
             apply_extras['tags'] = list(set(apply_extras.get('tags')))
 
         # If the processor also has its own Watch implementation
-        watch_class = get_custom_watch_obj_for_processor(apply_extras.get('processor'))
+        watch_class = get_watch_model_for_processor(apply_extras.get('processor'))
         new_watch = watch_class(datastore_path=self.datastore_path, url=url)
 
         new_uuid = new_watch.get('uuid')
@@ -357,15 +381,11 @@ class ChangeDetectionStore:
 
         if not apply_extras.get('date_created'):
             apply_extras['date_created'] = int(time.time())
-
-        new_watch.update(apply_extras)
         new_watch.ensure_data_dir_exists()
+        new_watch.update(apply_extras)
+
         self.__data['watching'][new_uuid] = new_watch
-
-
-        if write_to_disk_now:
-            self.sync_to_json()
-
+        self.__data['watching'][new_uuid].save_data()
         logger.debug(f"Added '{url}'")
 
         return new_uuid
@@ -373,64 +393,28 @@ class ChangeDetectionStore:
     def visualselector_data_is_ready(self, watch_uuid):
         output_path = "{}/{}".format(self.datastore_path, watch_uuid)
         screenshot_filename = "{}/last-screenshot.png".format(output_path)
-        elements_index_filename = "{}/elements.json".format(output_path)
+        elements_index_filename = "{}/elements.deflate".format(output_path)
         if path.isfile(screenshot_filename) and  path.isfile(elements_index_filename) :
             return True
 
         return False
 
-    def sync_to_json(self):
-        logger.info("Saving JSON..")
+    def save_settings(self):
+        logger.info("Saving application settings...")
         try:
-            data = deepcopy(self.__data)
-        except RuntimeError as e:
-            # Try again in 15 seconds
-            time.sleep(15)
-            logger.error(f"! Data changed when writing to JSON, trying again.. {str(e)}")
-            self.sync_to_json()
-            return
-        else:
-
-            try:
-                # Re #286  - First write to a temp file, then confirm it looks OK and rename it
-                # This is a fairly basic strategy to deal with the case that the file is corrupted,
-                # system was out of memory, out of RAM etc
-                with open(self.json_store_path+".tmp", 'w') as json_file:
-                    json.dump(data, json_file, indent=4)
-                os.replace(self.json_store_path+".tmp", self.json_store_path)
-            except Exception as e:
-                logger.error(f"Error writing JSON!! (Main JSON file save was skipped) : {str(e)}")
-
-            self.needs_write = False
-            self.needs_write_urgent = False
-
-    # Thread runner, this helps with thread/write issues when there are many operations that want to update the JSON
-    # by just running periodically in one thread, according to python, dict updates are threadsafe.
-    def save_datastore(self):
-
-        while True:
-            if self.stop_thread:
-                # Suppressing "Logging error in Loguru Handler #0" during CICD.
-                # Not a meaningful difference for a real use-case just for CICD.
-                # the side effect is a "Shutting down datastore thread" message
-                # at the end of each test.
-                # But still more looking better.
-                import sys
-                logger.remove()
-                logger.add(sys.stderr)
-
-                logger.critical("Shutting down datastore thread")
-                return
-
-            if self.needs_write or self.needs_write_urgent:
-                self.sync_to_json()
-
-            # Once per minute is enough, more and it can cause high CPU usage
-            # better here is to use something like self.app.config.exit.wait(1), but we cant get to 'app' from here
-            for i in range(120):
-                time.sleep(0.5)
-                if self.stop_thread or self.needs_write_urgent:
-                    break
+            # Only save app settings, not the watches or tags (they're saved individually)
+            data = {'settings': self.__data.get('settings')}
+            #data = deepcopy(self.__data)
+            
+            # Remove the watches from the main JSON file
+            if 'watching' in data:
+                del data['watching']
+                
+            # Remove the tags from the main JSON file since they're saved individually now
+#            if 'settings' in data and 'application' in data['settings'] and 'tags' in data['settings']['application']:
+#                del data['settings']['application']['tags']
+        except Exception as e:
+            x=1
 
     # Go through the datastore path and remove any snapshots that are not mentioned in the index
     # This usually is not used, but can be handy.
@@ -584,16 +568,17 @@ class ChangeDetectionStore:
 
         # Eventually almost everything todo with a watch will apply as a Tag
         # So we use the same model as a Watch
-        with self.lock:
-            from .model import Tag
-            new_tag = Tag.model(datastore_path=self.datastore_path, default={
-                'title': name.strip(),
-                'date_created': int(time.time())
-            })
+        from .model import Tag
+        new_tag = Tag.model(datastore_path=self.datastore_path, default={
+            'title': name.strip(),
+            'date_created': int(time.time())
+        })
 
-            new_uuid = new_tag.get('uuid')
+        new_uuid = new_tag.get('uuid')
+
+        self.__data['settings']['application']['tags'][new_uuid] = new_tag
+        self.__data['settings']['application']['tags'][new_uuid].save_data()
 
-            self.__data['settings']['application']['tags'][new_uuid] = new_tag
 
         return new_uuid
 
@@ -750,17 +735,17 @@ class ChangeDetectionStore:
     def update_5(self):
         # If the watch notification body, title look the same as the global one, unset it, so the watch defaults back to using the main settings
         # In other words - the watch notification_title and notification_body are not needed if they are the same as the default one
-        current_system_body = self.data['settings']['application']['notification_body'].translate(str.maketrans('', '', "\r\n "))
-        current_system_title = self.data['settings']['application']['notification_body'].translate(str.maketrans('', '', "\r\n "))
+        current_system_body = self.data['settings']['application']['notification_body'].translate(TRANSLATE_WHITESPACE_TABLE)
+        current_system_title = self.data['settings']['application']['notification_body'].translate(TRANSLATE_WHITESPACE_TABLE)
         for uuid, watch in self.data['watching'].items():
             try:
                 watch_body = watch.get('notification_body', '')
-                if watch_body and watch_body.translate(str.maketrans('', '', "\r\n ")) == current_system_body:
+                if watch_body and watch_body.translate(TRANSLATE_WHITESPACE_TABLE) == current_system_body:
                     # Looks the same as the default one, so unset it
                     watch['notification_body'] = None
 
                 watch_title = watch.get('notification_title', '')
-                if watch_title and watch_title.translate(str.maketrans('', '', "\r\n ")) == current_system_title:
+                if watch_title and watch_title.translate(TRANSLATE_WHITESPACE_TABLE) == current_system_title:
                     # Looks the same as the default one, so unset it
                     watch['notification_title'] = None
             except Exception as e:
@@ -889,6 +874,7 @@ class ChangeDetectionStore:
 
     # Migrate old 'in_stock' values to the new Restock
     def update_17(self):
+        from .processors.restock_diff import Restock
         for uuid, watch in self.data['watching'].items():
             if 'in_stock' in watch:
                 watch['restock'] = Restock({'in_stock': watch.get('in_stock')})
@@ -908,3 +894,18 @@ class ChangeDetectionStore:
             if self.data['watching'][uuid].get('in_stock_only'):
                 del (self.data['watching'][uuid]['in_stock_only'])
 
+    # Compress old elements.json to elements.deflate, saving disk, this compression is pretty fast.
+    def update_19(self):
+        import zlib
+
+        for uuid, watch in self.data['watching'].items():
+            json_path = os.path.join(self.datastore_path, uuid, "elements.json")
+            deflate_path = os.path.join(self.datastore_path, uuid, "elements.deflate")
+
+            if os.path.exists(json_path):
+                with open(json_path, "rb") as f_j:
+                    with open(deflate_path, "wb") as f_d:
+                        logger.debug(f"Compressing {str(json_path)} to {str(deflate_path)}..")
+                        f_d.write(zlib.compress(f_j.read()))
+                        os.unlink(json_path)
+

changedetectionio/templates/_common_fields.html

@@ -11,21 +11,26 @@
     class="notification-urls" )
                             }}
                             <div class="pure-form-message-inline">
-                              <ul>
-                                <li>Use <a target=_new href="https://github.com/caronc/apprise">AppRise URLs</a> for notification to just about any service! <i><a target=_new href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes">Please read the notification services wiki here for important configuration notes</a></i>.</li>
-                                <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_discord">discord://</a></code> (or <code>https://discord.com/api/webhooks...</code>)) only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
-                                <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> bots can't send messages to other bots, so you should specify chat ID of non-bot user.</li>
-                                <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> only supports very limited HTML and can fail when extra tags are sent, <a href="https://core.telegram.org/bots/api#html-style">read more here</a> (or use plaintext/markdown format)</li>
+                                <p>
+                                <strong>Tip:</strong> Use <a target="newwindow" href="https://github.com/caronc/apprise">AppRise Notification URLs</a> for notification to just about any service! <i><a target="newwindow" href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes">Please read the notification services wiki here for important configuration notes</a></i>.<br>
+</p>
+                                <div data-target="#advanced-help-notifications" class="toggle-show pure-button button-tag button-xsmall">Show advanced help and tips</div>
+                                <ul style="display: none" id="advanced-help-notifications">
+                                <li><code><a target="newwindow" href="https://github.com/caronc/apprise/wiki/Notify_discord">discord://</a></code> (or <code>https://discord.com/api/webhooks...</code>)) only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
+                                <li><code><a target="newwindow" href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> bots can't send messages to other bots, so you should specify chat ID of non-bot user.</li>
+                                <li><code><a target="newwindow" href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> only supports very limited HTML and can fail when extra tags are sent, <a href="https://core.telegram.org/bots/api#html-style">read more here</a> (or use plaintext/markdown format)</li>
                                 <li><code>gets://</code>, <code>posts://</code>, <code>puts://</code>, <code>deletes://</code> for direct API calls (or omit the "<code>s</code>" for non-SSL ie <code>get://</code>) <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes#postposts">more help here</a></li>
                                   <li>Accepts the <code>{{ '{{token}}' }}</code> placeholders listed below</li>
                               </ul>
                             </div>
                             <div class="notifications-wrapper">
-                              <a id="send-test-notification" class="pure-button button-secondary button-xsmall" >Send test notification</a>
+                              <a id="send-test-notification" class="pure-button button-secondary button-xsmall" >Send test notification</a> <div class="spinner"  style="display: none;"></div>
                             {% if emailprefix %}
                               <a id="add-email-helper" class="pure-button button-secondary button-xsmall" >Add email <img style="height: 1em; display: inline-block" src="{{url_for('static_content', group='images', filename='email.svg')}}" alt="Add an email address"> </a>
                             {% endif %}
-                              <a href="{{url_for('notification_logs')}}" class="pure-button button-secondary button-xsmall" >Notification debug logs</a>
+                              <a href="{{url_for('settings.notification_logs')}}" class="pure-button button-secondary button-xsmall" >Notification debug logs</a>
+                              <br>
+                                <div id="notification-test-log" style="display: none;"><span class="pure-form-message-inline">Processing..</span></div>
                             </div>
                         </div>
                         <div id="notification-customisation" class="pure-control-group">
@@ -35,12 +40,12 @@
                             </div>
                             <div class="pure-control-group">
                                 {{ render_field(form.notification_body , rows=5, class="notification-body", placeholder=settings_application['notification_body']) }}
-                                <span class="pure-form-message-inline">Body for all notifications &dash; You can use <a target="_new" href="https://jinja.palletsprojects.com/en/3.0.x/templates/">Jinja2</a> templating in the notification title, body and URL, and tokens from below.
+                                <span class="pure-form-message-inline">Body for all notifications &dash; You can use <a target="newwindow" href="https://jinja.palletsprojects.com/en/3.0.x/templates/">Jinja2</a> templating in the notification title, body and URL, and tokens from below.
                                 </span>
 
                             </div>
                             <div class="pure-controls">
-                                <div id="notification-token-toggle" class="pure-button button-tag button-xsmall">Show token/placeholders</div>
+                                <div data-target="#notification-tokens-info" class="toggle-show pure-button button-tag button-xsmall">Show token/placeholders</div>
                             </div>
                             <div class="pure-controls" style="display: none;" id="notification-tokens-info">
                                 <table class="pure-table" id="token-table">
@@ -121,7 +126,7 @@
                                 <div class="pure-form-message-inline">
                                     <p>
 									Warning: Contents of <code>{{ '{{diff}}' }}</code>, <code>{{ '{{diff_removed}}' }}</code>, and <code>{{ '{{diff_added}}' }}</code> depend on how the difference algorithm perceives the change. <br>
-                                    For example, an addition or removal could be perceived as a change in some cases. <a target="_new" href="https://github.com/dgtlmoon/changedetection.io/wiki/Using-the-%7B%7Bdiff%7D%7D,-%7B%7Bdiff_added%7D%7D,-and-%7B%7Bdiff_removed%7D%7D-notification-tokens">More Here</a> <br>
+                                    For example, an addition or removal could be perceived as a change in some cases. <a target="newwindow" href="https://github.com/dgtlmoon/changedetection.io/wiki/Using-the-%7B%7Bdiff%7D%7D,-%7B%7Bdiff_added%7D%7D,-and-%7B%7Bdiff_removed%7D%7D-notification-tokens">More Here</a> <br>
                                     </p>
                                     <p>
                                         For JSON payloads, use <strong>|tojson</strong> without quotes for automatic escaping, for example - <code>{ "name": {{ '{{ watch_title|tojson }}' }} }</code>