Update MANIFEST.in

"Ignore text" is now "Remove text", it works the same but it removes the text instead of ignoring it, which is the same thing, but makes the code simpler

.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

@@ -1,9 +1,11 @@
 recursive-include changedetectionio/api *
+recursive-include changedetectionio/apprise_plugin *
 recursive-include changedetectionio/blueprint *
 recursive-include changedetectionio/content_fetchers *
 recursive-include changedetectionio/model *
 recursive-include changedetectionio/processors *
 recursive-include changedetectionio/static *
+recursive-include changedetectionio/storage *
 recursive-include changedetectionio/templates *
 recursive-include changedetectionio/tests *
 prune changedetectionio/static/package-lock.json

README.md

@@ -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
 

changedetectionio/__init__.py

@@ -2,7 +2,7 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
-__version__ = '0.46.03'
+__version__ = '0.49.4'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError
@@ -24,6 +24,9 @@ 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
@@ -160,11 +163,10 @@ 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

@@ -58,7 +58,7 @@ class Watch(Resource):
             abort(404, message='No watch exists with the UUID of {}'.format(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()
@@ -76,6 +76,7 @@ class Watch(Resource):
         # 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
+        # attr .last_changed will check for the last written text snapshot on change
         watch['last_changed'] = watch.last_changed
         watch['viewed'] = watch.viewed
         return watch
@@ -246,7 +247,7 @@ 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 +304,7 @@ 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/blueprint/backups/__init__.py

@@ -0,0 +1,164 @@
+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'))
+
+        # Be sure we're written fresh
+        datastore.sync_to_json()
+        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 +88,7 @@ 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')
         )
 
@@ -160,14 +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..
@@ -182,16 +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()
@@ -199,31 +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/env 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/price_data_follower/__init__.py

@@ -19,7 +19,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q: PriorityQueue
         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}))
+        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
         return redirect(url_for("index"))
 
     @login_required

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
@@ -104,9 +105,11 @@ 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 = {

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

@@ -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>

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/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
 
@@ -89,6 +90,7 @@ class fetcher(Fetcher):
         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
 
@@ -179,6 +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)))
@@ -190,6 +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
@@ -199,10 +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/requests.py

@@ -1,8 +1,6 @@
 from loguru import logger
-import chardet
 import hashlib
 import os
-import requests
 from changedetectionio import strtobool
 from changedetectionio.content_fetchers.exceptions import BrowserStepsInUnsupportedFetcher, EmptyReply, Non200ErrorCodeReceived
 from changedetectionio.content_fetchers.base import Fetcher
@@ -28,6 +26,9 @@ class fetcher(Fetcher):
             is_binary=False,
             empty_pages_are_a_change=False):
 
+        import chardet
+        import requests
+
         if self.browser_steps_get_valid_steps():
             raise BrowserStepsInUnsupportedFetcher(url=url)
 
@@ -74,6 +75,7 @@ class fetcher(Fetcher):
         self.headers = r.headers
 
         if not r.content or not len(r.content):
+            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:

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,
     });
 
 });

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/flask_app.py

@@ -1,6 +1,8 @@
 #!/usr/bin/env python3
 
 import datetime
+from zoneinfo import ZoneInfo
+
 import flask_login
 import locale
 import os
@@ -41,6 +43,7 @@ from loguru import logger
 from changedetectionio import html_tools, __version__
 from changedetectionio import queuedWatchMetaData
 from changedetectionio.api import api_v1
+from .time_handler import is_within_schedule
 
 datastore = None
 
@@ -52,6 +55,7 @@ extra_stylesheets = []
 
 update_q = queue.PriorityQueue()
 notification_q = queue.Queue()
+MAX_QUEUE_SIZE = 2000
 
 app = Flask(__name__,
             static_url_path="",
@@ -66,7 +70,6 @@ FlaskCompress(app)
 
 # Stop browser caching of assets
 app.config['SEND_FILE_MAX_AGE_DEFAULT'] = 0
-
 app.config.exit = Event()
 
 app.config['NEW_VERSION_AVAILABLE'] = False
@@ -83,7 +86,7 @@ csrf = CSRFProtect()
 csrf.init_app(app)
 notification_debug_log=[]
 
-# get locale ready
+# Locale for correct presentation of prices etc
 default_locale = locale.getdefaultlocale()
 logger.info(f"System locale default is {default_locale}")
 try:
@@ -469,7 +472,7 @@ def changedetection_app(config=None, datastore_o=None):
                     continue
             if watch.get('last_error'):
                 errored_count += 1
-                
+
             if search_q:
                 if (watch.get('title') and search_q in watch.get('title').lower()) or search_q in watch.get('url', '').lower():
                     sorted_watches.append(watch)
@@ -532,23 +535,32 @@ def changedetection_app(config=None, datastore_o=None):
     @login_optionally_required
     def ajax_callback_send_notification_test(watch_uuid=None):
 
-        # Watch_uuid could be unset in the case its used in tag editor, global setings
+        # Watch_uuid could be unset in the case it`s used in tag editor, global settings
         import apprise
         import random
         from .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):
+        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 = request.form['notification_urls'].strip().splitlines()
+        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")
@@ -566,12 +578,12 @@ def changedetection_app(config=None, datastore_o=None):
 
 
         if not notification_urls:
-            return 'No Notification URLs set/found'
+            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.'
+                    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
@@ -586,15 +598,31 @@ def changedetection_app(config=None, datastore_o=None):
 
             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 .notification import process_notification
+            sent_obj = process_notification(n_object, datastore)
 
-            from . import update_worker
-            new_worker = update_worker.update_worker(update_q, notification_q, app, datastore)
-            new_worker.queue_notification_for_watch(notification_q=notification_q, n_object=n_object, watch=watch)
         except Exception as e:
-            return make_response({'error': str(e)}, 400)
+            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'
 
@@ -704,7 +732,8 @@ def changedetection_app(config=None, datastore_o=None):
 
         form = form_class(formdata=request.form if request.method == 'POST' else None,
                           data=default,
-                          extra_notification_tokens=default.extra_notification_token_values()
+                          extra_notification_tokens=default.extra_notification_token_values(),
+                          default_system_settings=datastore.data['settings']
                           )
 
         # For the form widget tag UUID back to "string name" for the field
@@ -786,21 +815,47 @@ def changedetection_app(config=None, datastore_o=None):
             # Recast it if need be to right data Watch handler
             watch_class = get_custom_watch_obj_for_processor(form.data.get('processor'))
             datastore.data['watching'][uuid] = watch_class(datastore_path=datastore_o.datastore_path, default=datastore.data['watching'][uuid])
-
             flash("Updated watch - unpaused!" if request.args.get('unpause_on_save') else "Updated watch.")
 
             # Re #286 - We wait for syncing new data to disk in another thread every 60 seconds
             # But in the case something is added we should save straight away
             datastore.needs_write_urgent = True
 
-            # Queue the watch for immediate recheck, with a higher priority
-            update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
+            # 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('diff_history_page', uuid=uuid))
 
-            return redirect(url_for('index'))
+            return redirect(url_for('index', tag=request.args.get("tag",'')))
 
         else:
             if request.method == 'POST' and not form.validate():
@@ -820,30 +875,33 @@ def changedetection_app(config=None, datastore_o=None):
 
             system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
 
-            is_html_webdriver = False
+            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_'):
-                is_html_webdriver = True
+                watch_uses_webdriver = True
+
+            from zoneinfo import available_timezones
 
             # Only works reliably with Playwright
-            visualselector_enabled = os.getenv('PLAYWRIGHT_DRIVER_URL', False) and is_html_webdriver
+
             template_args = {
                 'available_processors': processors.available_processors(),
+                'available_timezones': sorted(available_timezones()),
                 'browser_steps_config': browser_step_ui_config,
                 'emailprefix': os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
-                'extra_title': f" - Edit - {watch.label}",
-                'extra_processor_config': form.extra_tab_content(),
                 '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),
-                'is_html_webdriver': is_html_webdriver,
+                '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,
-                'visualselector_enabled': visualselector_enabled,
                 'watch': watch
             }
 
@@ -870,6 +928,8 @@ def changedetection_app(config=None, datastore_o=None):
     @login_optionally_required
     def settings_page():
         from changedetectionio import forms
+        from datetime import datetime
+        from zoneinfo import available_timezones
 
         default = deepcopy(datastore.data['settings'])
         if datastore.proxy_list is not None:
@@ -937,14 +997,20 @@ def changedetection_app(config=None, datastore_o=None):
             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()
+
         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)),
-                                 settings_application=datastore.data['settings']['application']
+                                 settings_application=datastore.data['settings']['application'],
+                                 timezone_default_config=datastore.data['settings']['application'].get('timezone'),
+                                 utc_time=utc_time,
                                  )
 
         return output
@@ -975,7 +1041,7 @@ def changedetection_app(config=None, datastore_o=None):
                 importer = import_url_list()
                 importer.run(data=request.values.get('urls'), flash=flash, datastore=datastore, processor=request.values.get('processor', 'text_json_diff'))
                 for uuid in importer.new_uuids:
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
                 if len(importer.remaining_data) == 0:
                     return redirect(url_for('index'))
@@ -988,7 +1054,7 @@ def changedetection_app(config=None, datastore_o=None):
                 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, 'skip_when_checksum_same': True}))
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
 
             # XLSX importer
             if request.files and request.files.get('xlsx_file'):
@@ -1012,7 +1078,7 @@ def changedetection_app(config=None, datastore_o=None):
                     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, 'skip_when_checksum_same': True}))
+                    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)
@@ -1153,8 +1219,6 @@ def changedetection_app(config=None, datastore_o=None):
     @login_optionally_required
     def preview_page(uuid):
         content = []
-        ignored_line_numbers = []
-        trigger_line_numbers = []
         versions = []
         timestamp = None
 
@@ -1171,11 +1235,10 @@ def changedetection_app(config=None, datastore_o=None):
         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:
@@ -1188,31 +1251,12 @@ def changedetection_app(config=None, datastore_o=None):
 
             try:
                 versions = list(watch.history.keys())
-                tmp = watch.get_history_snapshot(timestamp).splitlines()
+                content = watch.get_history_snapshot(timestamp)
 
-                # Get what needs to be highlighted
-                ignore_rules = watch.get('ignore_text', []) + datastore.data['settings']['application']['global_ignore_text']
-
-                # .readlines will keep the \n, but we will parse it here again, in the future tidy this up
-                ignored_line_numbers = html_tools.strip_ignore_text(content="\n".join(tmp),
-                                                                    wordlist=ignore_rules,
-                                                                    mode='line numbers'
-                                                                    )
-
-                trigger_line_numbers = html_tools.strip_ignore_text(content="\n".join(tmp),
-                                                                    wordlist=watch['trigger_text'],
-                                                                    mode='line numbers'
-                                                                    )
-                # Prepare the classes and lines used in the template
-                i=0
-                for l in tmp:
-                    classes=[]
-                    i+=1
-                    if i in ignored_line_numbers:
-                        classes.append('ignored')
-                    if i in trigger_line_numbers:
-                        classes.append('triggered')
-                    content.append({'line': l, 'classes': ' '.join(classes)})
+                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': ''})
@@ -1223,8 +1267,7 @@ def changedetection_app(config=None, datastore_o=None):
                                  history_n=watch.history_n,
                                  extra_stylesheets=extra_stylesheets,
                                  extra_title=f" - Diff - {watch.label} @ {timestamp}",
-                                 ignored_line_numbers=ignored_line_numbers,
-                                 triggered_line_numbers=trigger_line_numbers,
+                                 triggered_line_numbers=triggered_line_numbers,
                                  current_diff_url=watch['url'],
                                  screenshot=watch.get_screenshot(),
                                  watch=watch,
@@ -1248,78 +1291,6 @@ def changedetection_app(config=None, datastore_o=None):
 
         return output
 
-    # We're good but backups are even better!
-    @app.route("/backup", methods=['GET'])
-    @login_optionally_required
-    def get_backup():
-
-        import zipfile
-        from pathlib import Path
-
-        # Remove any existing backup file, for now we just keep one file
-
-        for previous_backup_filename in Path(datastore_o.datastore_path).rglob('changedetection-backup-*.zip'):
-            os.unlink(previous_backup_filename)
-
-        # create a ZipFile object
-        timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
-        backupname = "changedetection-backup-{}.zip".format(timestamp)
-        backup_filepath = os.path.join(datastore_o.datastore_path, backupname)
-
-        with zipfile.ZipFile(backup_filepath, "w",
-                             compression=zipfile.ZIP_DEFLATED,
-                             compresslevel=8) as zipObj:
-
-            # Be sure we're written fresh
-            datastore.sync_to_json()
-
-            # Add the index
-            zipObj.write(os.path.join(datastore_o.datastore_path, "url-watches.json"), arcname="url-watches.json")
-
-            # Add the flask app secret
-            zipObj.write(os.path.join(datastore_o.datastore_path, "secret.txt"), arcname="secret.txt")
-
-            # Add any data in the watch data directory.
-            for uuid, w in datastore.data['watching'].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_o.datastore_path, list_file), "w") as f:
-                for uuid in datastore.data["watching"]:
-                    url = datastore.data["watching"][uuid]["url"]
-                    f.write("{}\r\n".format(url))
-            list_with_tags_file = "url-list-with-tags.txt"
-            with open(
-                os.path.join(datastore_o.datastore_path, list_with_tags_file), "w"
-            ) as f:
-                for uuid in datastore.data["watching"]:
-                    url = datastore.data["watching"][uuid].get('url')
-                    tag = datastore.data["watching"][uuid].get('tags', {})
-                    f.write("{} {}\r\n".format(url, tag))
-
-            # Add it to the Zip
-            zipObj.write(
-                os.path.join(datastore_o.datastore_path, list_file),
-                arcname=list_file,
-                compress_type=zipfile.ZIP_DEFLATED,
-                compresslevel=8,
-            )
-            zipObj.write(
-                os.path.join(datastore_o.datastore_path, list_with_tags_file),
-                arcname=list_with_tags_file,
-                compress_type=zipfile.ZIP_DEFLATED,
-                compresslevel=8,
-            )
-
-        # Send_from_directory needs to be the full absolute path
-        return send_from_directory(os.path.abspath(datastore_o.datastore_path), backupname, as_attachment=True)
-
     @app.route("/static/<string:group>/<string:filename>", methods=['GET'])
     def static_content(group, filename):
         from flask import make_response
@@ -1352,12 +1323,23 @@ def changedetection_app(config=None, datastore_o=None):
 
             # These files should be in our subdirectory
             try:
-                # set nocache, set content-type
-                response = make_response(send_from_directory(os.path.join(datastore_o.datastore_path, filename), "elements.json"))
-                response.headers['Content-type'] = 'application/json'
-                response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
-                response.headers['Pragma'] = 'no-cache'
-                response.headers['Expires'] = 0
+                # set nocache, set content-type,
+                # `filename` is actually directory UUID of the watch
+                watch_directory = str(os.path.join(datastore_o.datastore_path, filename))
+                response = None
+                if os.path.isfile(os.path.join(watch_directory, "elements.deflate")):
+                    response = make_response(send_from_directory(watch_directory, "elements.deflate"))
+                    response.headers['Content-Type'] = 'application/json'
+                    response.headers['Content-Encoding'] = 'deflate'
+                else:
+                    logger.error(f'Request elements.deflate at "{watch_directory}" but was notfound.')
+                    abort(404)
+
+                if response:
+                    response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
+                    response.headers['Pragma'] = 'no-cache'
+                    response.headers['Expires'] = "0"
+
                 return response
 
             except FileNotFoundError:
@@ -1395,6 +1377,15 @@ def changedetection_app(config=None, datastore_o=None):
         # Return a 500 error
         abort(500)
 
+    # Ajax callback
+    @app.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 .processors.text_json_diff import prepare_filter_prevew
+        return prepare_filter_prevew(watch_uuid=uuid, datastore=datastore)
+
+
     @app.route("/form/add/quickwatch", methods=['POST'])
     @login_optionally_required
     def form_quick_watch_add():
@@ -1409,7 +1400,7 @@ def changedetection_app(config=None, datastore_o=None):
         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})
@@ -1417,13 +1408,13 @@ def changedetection_app(config=None, datastore_o=None):
         if new_uuid:
             if add_paused:
                 flash('Watch added in Paused state, saving will unpause.')
-                return redirect(url_for('edit_page', uuid=new_uuid, unpause_on_save=1))
+                return redirect(url_for('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'))
+        return redirect(url_for('index', tag=request.args.get('tag','')))
 
 
 
@@ -1455,7 +1446,7 @@ def changedetection_app(config=None, datastore_o=None):
         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, 'skip_when_checksum_same': True}))
+                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid}))
             flash('Cloned.')
 
         return redirect(url_for('index'))
@@ -1476,7 +1467,7 @@ def changedetection_app(config=None, datastore_o=None):
 
         if uuid:
             if uuid not in running_uuids:
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
+                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
             i = 1
 
         elif tag:
@@ -1487,7 +1478,7 @@ def changedetection_app(config=None, datastore_o=None):
                         continue
                     if watch_uuid not in running_uuids and not datastore.data['watching'][watch_uuid]['paused']:
                         update_q.put(
-                            queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False})
+                            queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid})
                         )
                         i += 1
 
@@ -1497,9 +1488,8 @@ def changedetection_app(config=None, datastore_o=None):
                 if watch_uuid not in running_uuids and not datastore.data['watching'][watch_uuid]['paused']:
                     if with_errors and not watch.get('last_error'):
                         continue
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False}))
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
                     i += 1
-
         flash(f"{i} watches queued for rechecking.")
         return redirect(url_for('index', tag=tag))
 
@@ -1556,7 +1546,7 @@ def changedetection_app(config=None, datastore_o=None):
                 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, 'skip_when_checksum_same': False}))
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
             flash("{} watches queued for rechecking".format(len(uuids)))
 
         elif (op == 'clear-errors'):
@@ -1691,13 +1681,15 @@ def changedetection_app(config=None, datastore_o=None):
     import changedetectionio.blueprint.check_proxies as check_proxies
     app.register_blueprint(check_proxies.construct_blueprint(datastore=datastore), url_prefix='/check_proxy')
 
+    import changedetectionio.blueprint.backups as backups
+    app.register_blueprint(backups.construct_blueprint(datastore), url_prefix='/backups')
 
     # @todo handle ctrl break
     ticker_thread = threading.Thread(target=ticker_thread_check_time_launch_checks).start()
     threading.Thread(target=notification_runner).start()
 
     # Check for new release version, but not when running in test/build or pytest
-    if not os.getenv("GITHUB_REF", False) and not config.get('disable_checkver') == True:
+    if not os.getenv("GITHUB_REF", False) and not strtobool(os.getenv('DISABLE_VERSION_CHECK', 'no')):
         threading.Thread(target=check_for_new_version).start()
 
     return app
@@ -1781,7 +1773,6 @@ def notification_runner():
 def ticker_thread_check_time_launch_checks():
     import random
     from changedetectionio import update_worker
-
     proxy_last_called_time = {}
 
     recheck_time_minimum_seconds = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 3))
@@ -1815,12 +1806,14 @@ def ticker_thread_check_time_launch_checks():
             except RuntimeError as e:
                 # RuntimeError: dictionary changed size during iteration
                 time.sleep(0.1)
+                watch_uuid_list = []
             else:
                 break
 
         # Re #438 - Don't place more watches in the queue to be checked if the queue is already large
         while update_q.qsize() >= 2000:
-            time.sleep(1)
+            logger.warning(f"Recheck watches queue size limit reached ({MAX_QUEUE_SIZE}), skipping adding more items")
+            time.sleep(3)
 
 
         recheck_time_system_seconds = int(datastore.threshold_seconds)
@@ -1837,6 +1830,28 @@ def ticker_thread_check_time_launch_checks():
             if watch['paused']:
                 continue
 
+            # @todo - Maybe make this a hook?
+            # Time schedule limit - Decide between watch or global settings
+            if watch.get('time_between_check_use_default'):
+                time_schedule_limit = datastore.data['settings']['requests'].get('time_schedule_limit', {})
+                logger.trace(f"{uuid} Time scheduler - Using system/global settings")
+            else:
+                time_schedule_limit = watch.get('time_schedule_limit')
+                logger.trace(f"{uuid} Time scheduler - Using watch settings (not global settings)")
+            tz_name = datastore.data['settings']['application'].get('timezone', 'UTC')
+
+            if time_schedule_limit and time_schedule_limit.get('enabled'):
+                try:
+                    result = is_within_schedule(time_schedule_limit=time_schedule_limit,
+                                                default_tz=tz_name
+                                                )
+                    if not result:
+                        logger.trace(f"{uuid} Time scheduler - not within schedule skipping.")
+                        continue
+                except Exception as e:
+                    logger.error(
+                        f"{uuid} - Recheck scheduler, error handling timezone, check skipped - TZ name '{tz_name}' - {str(e)}")
+                    return False
             # If they supplied an individual entry minutes to threshold.
             threshold = recheck_time_system_seconds if watch.get('time_between_check_use_default') else watch.threshold_seconds()
 
@@ -1880,7 +1895,7 @@ def ticker_thread_check_time_launch_checks():
                         f"{now - watch['last_checked']:0.2f}s since last checked")
 
                     # Into the queue with you
-                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=priority, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+                    update_q.put(queuedWatchMetaData.PrioritizedItem(priority=priority, item={'uuid': uuid}))
 
                     # Reset for next time
                     watch.jitter_seconds = 0

changedetectionio/forms.py

@@ -1,11 +1,14 @@
 import os
 import re
+from loguru import logger
+from wtforms.widgets.core import TimeInput
 
 from changedetectionio.strtobool import strtobool
 
 from wtforms import (
     BooleanField,
     Form,
+    Field,
     IntegerField,
     RadioField,
     SelectField,
@@ -124,6 +127,87 @@ 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")])
@@ -221,10 +305,15 @@ class ValidateAppRiseServers(object):
     def __call__(self, form, field):
         import apprise
         apobj = apprise.Apprise()
-
+        # so that the custom endpoints are registered
+        from changedetectionio.apprise_plugin import apprise_custom_api_call_wrapper
         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 +366,7 @@ 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:
@@ -436,6 +526,7 @@ class commonSettingsForm(Form):
     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")
+    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")])
 
 
@@ -446,7 +537,6 @@ class importForm(Form):
     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')})
 
-
 class SingleBrowserStep(Form):
 
     operation = SelectField('Operation', [validators.Optional()], choices=browser_step_ui_config.keys())
@@ -464,23 +554,28 @@ 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 +587,7 @@ 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(
@@ -511,6 +606,7 @@ 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 +616,65 @@ 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 +695,7 @@ 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;"},
@@ -575,7 +724,7 @@ 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',
@@ -605,7 +754,7 @@ 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/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):'
@@ -36,8 +38,9 @@ class model(watch_base):
     jitter_seconds = 0
 
     def __init__(self, *arg, **kw):
-        self.__datastore_path = kw['datastore_path']
-        del kw['datastore_path']
+        self.__datastore_path = kw.get('datastore_path')
+        if kw.get('datastore_path'):
+            del kw['datastore_path']
         super(model, self).__init__(*arg, **kw)
         if kw.get('default'):
             self.update(kw['default'])
@@ -86,6 +89,10 @@ class model(watch_base):
 
         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 +178,10 @@ 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 +247,32 @@ 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
@@ -293,34 +299,17 @@ class model(watch_base):
     # Save some text file to the appropriate path and bump the history
     # result_obj from fetch_site_status.run()
     def save_history_text(self, contents, timestamp, snapshot_id):
-        import brotli
+        from changedetectionio.store import ChangeDetectionStore
+        from changedetectionio.storage.filesystem_storage import FileSystemStorage
 
         logger.trace(f"{self.get('uuid')} - Updating history.txt with timestamp {timestamp}")
 
-        self.ensure_data_dir_exists()
-
-        threshold = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD', 1024))
-        skip_brotli = strtobool(os.getenv('DISABLE_BROTLI_TEXT_SNAPSHOT', 'False'))
-
-        if not skip_brotli and len(contents) > threshold:
-            snapshot_fname = f"{snapshot_id}.txt.br"
-            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))
-        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)
-
-        # Append to index
-        # @todo check last char was \n
-        index_fname = os.path.join(self.watch_data_dir, "history.txt")
-        with open(index_fname, 'a') as f:
-            f.write("{},{}\n".format(timestamp, snapshot_fname))
-            f.close()
+        # Get storage from singleton store or create a filesystem storage as default
+        store = ChangeDetectionStore.instance if hasattr(ChangeDetectionStore, 'instance') else None
+        storage = store.storage if store and hasattr(store, 'storage') else FileSystemStorage(self.__datastore_path)
+        
+        # Use the storage backend to save the history text
+        snapshot_fname = storage.save_history_text(self.get('uuid'), contents, timestamp, snapshot_id)
 
         self.__newest_history_key = timestamp
         self.__history_n += 1
@@ -328,7 +317,6 @@ 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 +333,32 @@ 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
@@ -396,8 +402,8 @@ class model(watch_base):
     @property
     def watch_data_dir(self):
         # The base dir of the watch data
-        return os.path.join(self.__datastore_path, self['uuid'])
-    
+        return os.path.join(self.__datastore_path, self['uuid']) if self.__datastore_path else None
+
     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 +510,22 @@ 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

@@ -18,6 +18,7 @@ class watch_base(dict):
             '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,
@@ -58,8 +59,69 @@ class watch_base(dict):
             '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': str(uuid.uuid4()),

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.encode('utf-8') if type(body) is str else 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'):
@@ -150,9 +81,16 @@ 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
@@ -223,8 +161,6 @@ 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()

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
+import os
+import pkgutil
+import re
 
 class difference_detection_processor():
 
@@ -18,30 +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
-        from changedetectionio.content_fetchers.exceptions import EmptyReply
 
-        # 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':
@@ -99,6 +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')
@@ -115,9 +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)
 
@@ -154,7 +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()

changedetectionio/processors/restock_diff/processor.py

@@ -2,8 +2,7 @@ from .. import difference_detection_processor
 from ..exceptions import ProcessorException
 from . import Restock
 from loguru import logger
-import hashlib
-import re
+
 import urllib3
 import time
 
@@ -27,6 +26,30 @@ 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 +59,21 @@ 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 +84,17 @@ 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:
@@ -118,7 +144,9 @@ 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.")
 
@@ -132,6 +160,20 @@ 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 +188,7 @@ 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 +224,7 @@ 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 +233,21 @@ 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 +311,4 @@ 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 +1,115 @@
+
+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):
+    '''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, jsonify
+    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=request.form if request.method == 'POST' else None,
+                                                   data=request.form
+                                                   )
+
+        # Only update vars that came in via the AJAX post
+        p = {k: v for k, v in form.data.items() if k in request.form.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 jsonify(
+        {
+            '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

@@ -7,7 +7,7 @@ import re
 import urllib3
 
 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 loguru import logger
@@ -35,7 +35,7 @@ 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 +58,6 @@ 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 +172,13 @@ 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 +194,21 @@ 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 +223,12 @@ 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 +249,6 @@ 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 +257,53 @@ 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 +331,33 @@ 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
 
         # 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 +365,6 @@ 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/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 +1,196 @@
+(function ($) {
+    /**
+     * 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 +26,7 @@ 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/_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 +12,7 @@
 @import "parts/_darkmode";
 @import "parts/_menu";
 @import "parts/_love";
+@import "parts/preview_text_filter";
 
 body {
   color: var(--color-text);
@@ -105,10 +106,34 @@ 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 +147,14 @@ 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 +351,6 @@ a.pure-button-selected {
   background: var(--color-background-button-cancel);
 }
 
-#save_button {
-  margin-right: 1rem;
-}
-
 .messages {
   li {
     list-style: none;
@@ -353,7 +380,15 @@ 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 +655,9 @@ footer {
       list-style: none;
 
       li {
-        >* {
-          display: inline-block;
-        }
+        display: flex;
+        align-items: center;
+        gap: 1em;
       }
     }
   }
@@ -682,6 +717,12 @@ 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 +738,24 @@ 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 +874,11 @@ 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 +945,7 @@ $form-edge-padding: 20px;
 }
 
 .tab-pane-inner {
+
   &:not(:target) {
     display: none;
   }
@@ -930,6 +995,13 @@ 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 +1045,28 @@ 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 +446,83 @@ 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); }
+
 body {
   color: var(--color-text);
   background: var(--color-background-page);
@@ -479,9 +591,26 @@ 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 +620,11 @@ 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 +766,6 @@ 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 +783,14 @@ 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 +971,10 @@ 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 +1010,24 @@ 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 +1119,10 @@ 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 +1183,8 @@ 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 +1193,10 @@ 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 +1225,21 @@ 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 +1368,9 @@ 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/storage/README.md

@@ -0,0 +1,61 @@
+# Storage Backends for changedetection.io
+
+This module provides different storage backends for changedetection.io, allowing you to store data in various systems:
+
+- **FileSystemStorage**: The default storage backend that stores data on the local filesystem.
+- **MongoDBStorage**: Stores data in a MongoDB database.
+- **S3Storage**: Stores data in an Amazon S3 bucket.
+
+## Usage
+
+The storage backend is automatically selected based on the datastore path provided when initializing the application:
+
+- For filesystem storage (default): `/datastore`
+- For MongoDB storage: `mongodb://username:password@host:port/database`
+- For S3 storage: `s3://bucket-name/optional-prefix`
+
+## Configuration
+
+### Filesystem Storage
+
+The default storage backend. Simply specify a directory path:
+
+```
+changedetection.io -d /path/to/datastore
+```
+
+### MongoDB Storage
+
+To use MongoDB storage, specify a MongoDB connection URI:
+
+```
+changedetection.io -d mongodb://username:password@host:port/database
+```
+
+Make sure to install the required dependencies:
+
+```
+pip install -r requirements-storage.txt
+```
+
+### Amazon S3 Storage
+
+To use S3 storage, specify an S3 URI:
+
+```
+changedetection.io -d s3://bucket-name/optional-prefix
+```
+
+Make sure to:
+1. Install the required dependencies: `pip install -r requirements-storage.txt`
+2. Configure AWS credentials using environment variables or IAM roles:
+   - Set `AWS_ACCESS_KEY_ID` and `AWS_SECRET_ACCESS_KEY` environment variables
+   - Or use an IAM role when running on AWS EC2/ECS/EKS
+
+## Custom Storage Backends
+
+You can create custom storage backends by:
+
+1. Subclassing the `StorageBase` abstract class in `storage_base.py`
+2. Implementing all required methods
+3. Adding your backend to the `storage_factory.py` file

changedetectionio/storage/__init__.py

@@ -0,0 +1 @@
+# This module contains storage backend implementations

changedetectionio/storage/filesystem_storage.py

@@ -0,0 +1,449 @@
+import os
+import shutil
+import json
+import brotli
+import zlib
+import pathlib
+from loguru import logger
+from os import path
+
+from .storage_base import StorageBase
+
+class FileSystemStorage(StorageBase):
+    """File system storage backend"""
+    
+    def __init__(self, datastore_path, include_default_watches=True, version_tag="0.0.0"):
+        """Initialize the file system storage backend
+        
+        Args:
+            datastore_path (str): Path to the datastore
+            include_default_watches (bool): Whether to include default watches
+            version_tag (str): Version tag
+        """
+        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}'")
+        
+    def load_data(self):
+        """Load data from the file system
+        
+        Returns:
+            dict: The loaded data
+        """
+        if not path.isfile(self.json_store_path):
+            return None
+            
+        with open(self.json_store_path) as json_file:
+            return json.load(json_file)
+
+    def save_data(self, data):
+        """Save data to the file system
+        
+        Args:
+            data (dict): The data to save
+        """
+        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)}")
+            raise e
+    
+    def get_watch_dir(self, watch_uuid):
+        """Get the directory for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            
+        Returns:
+            str: The watch directory
+        """
+        return os.path.join(self.datastore_path, watch_uuid)
+    
+    def ensure_data_dir_exists(self, watch_uuid):
+        """Ensure the data directory exists for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+        """
+        watch_dir = self.get_watch_dir(watch_uuid)
+        if not os.path.isdir(watch_dir):
+            logger.debug(f"> Creating data dir {watch_dir}")
+            os.makedirs(watch_dir, exist_ok=True)
+    
+    def save_history_text(self, watch_uuid, contents, timestamp, snapshot_id):
+        """Save history text to the file system
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            contents (str): Contents to save
+            timestamp (int): Timestamp
+            snapshot_id (str): Snapshot ID
+            
+        Returns:
+            str: Snapshot filename
+        """
+        self.ensure_data_dir_exists(watch_uuid)
+        
+        threshold = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD', 1024))
+        skip_brotli = os.getenv('DISABLE_BROTLI_TEXT_SNAPSHOT', 'False').lower() in ('true', '1', 't')
+        
+        watch_dir = self.get_watch_dir(watch_uuid)
+        
+        if not skip_brotli and len(contents) > threshold:
+            snapshot_fname = f"{snapshot_id}.txt.br"
+            dest = os.path.join(watch_dir, snapshot_fname)
+            if not os.path.exists(dest):
+                with open(dest, 'wb') as f:
+                    f.write(brotli.compress(contents.encode('utf-8'), mode=brotli.MODE_TEXT))
+        else:
+            snapshot_fname = f"{snapshot_id}.txt"
+            dest = os.path.join(watch_dir, snapshot_fname)
+            if not os.path.exists(dest):
+                with open(dest, 'wb') as f:
+                    f.write(contents.encode('utf-8'))
+        
+        # Append to index
+        index_fname = os.path.join(watch_dir, "history.txt")
+        with open(index_fname, 'a') as f:
+            f.write("{},{}\n".format(timestamp, snapshot_fname))
+        
+        return snapshot_fname
+    
+    def get_history(self, watch_uuid):
+        """Get history for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            
+        Returns:
+            dict: The history with timestamp keys and snapshot IDs as values
+        """
+        tmp_history = {}
+        
+        watch_dir = self.get_watch_dir(watch_uuid)
+        if not os.path.isdir(watch_dir):
+            return tmp_history
+        
+        # Read the history file as a dict
+        fname = os.path.join(watch_dir, "history.txt")
+        if os.path.isfile(fname):
+            logger.debug(f"Reading watch history index for {watch_uuid}")
+            with open(fname, "r") as f:
+                for i in f.readlines():
+                    if ',' in i:
+                        k, v = i.strip().split(',', 2)
+                        
+                        # The index history could contain a relative path, so we need to make the fullpath
+                        # so that python can read it
+                        if not '/' in v and not '\'' in v:
+                            v = os.path.join(watch_dir, v)
+                        else:
+                            # It's possible that they moved the datadir on older versions
+                            # So the snapshot exists but is in a different path
+                            snapshot_fname = v.split('/')[-1]
+                            proposed_new_path = os.path.join(watch_dir, snapshot_fname)
+                            if not os.path.exists(v) and os.path.exists(proposed_new_path):
+                                v = proposed_new_path
+                        
+                        tmp_history[k] = v
+        
+        return tmp_history
+    
+    def get_history_snapshot(self, watch_uuid, timestamp):
+        """Get a history snapshot from the file system
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            timestamp (int): Timestamp
+            
+        Returns:
+            str: The snapshot content
+        """
+        history = self.get_history(watch_uuid)
+        if not timestamp in history:
+            return None
+            
+        filepath = history[timestamp]
+        
+        # See if a brotli versions exists and switch to that
+        if not filepath.endswith('.br') and os.path.isfile(f"{filepath}.br"):
+            filepath = f"{filepath}.br"
+        
+        # OR in the backup case that the .br does not exist, but the plain one does
+        if filepath.endswith('.br') and not os.path.isfile(filepath):
+            if os.path.isfile(filepath.replace('.br', '')):
+                filepath = filepath.replace('.br', '')
+        
+        if filepath.endswith('.br'):
+            # Brotli doesnt have a fileheader to detect it, so we rely on filename
+            # https://www.rfc-editor.org/rfc/rfc7932
+            with open(filepath, 'rb') as f:
+                return(brotli.decompress(f.read()).decode('utf-8'))
+        
+        with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
+            return f.read()
+    
+    def save_screenshot(self, watch_uuid, screenshot, as_error=False):
+        """Save a screenshot for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            screenshot (bytes): Screenshot data
+            as_error (bool): Whether this is an error screenshot
+        """
+        self.ensure_data_dir_exists(watch_uuid)
+        watch_dir = self.get_watch_dir(watch_uuid)
+        
+        if as_error:
+            target_path = os.path.join(watch_dir, "last-error-screenshot.png")
+        else:
+            target_path = os.path.join(watch_dir, "last-screenshot.png")
+        
+        with open(target_path, 'wb') as f:
+            f.write(screenshot)
+    
+    def get_screenshot(self, watch_uuid, is_error=False):
+        """Get a screenshot for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            is_error (bool): Whether to get the error screenshot
+            
+        Returns:
+            str or None: The screenshot path or None if not available
+        """
+        watch_dir = self.get_watch_dir(watch_uuid)
+        
+        if is_error:
+            fname = os.path.join(watch_dir, "last-error-screenshot.png")
+        else:
+            fname = os.path.join(watch_dir, "last-screenshot.png")
+            
+        if os.path.isfile(fname):
+            return fname
+        
+        return None
+    
+    def save_error_text(self, watch_uuid, contents):
+        """Save error text for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            contents (str): Error contents
+        """
+        self.ensure_data_dir_exists(watch_uuid)
+        watch_dir = self.get_watch_dir(watch_uuid)
+        
+        target_path = os.path.join(watch_dir, "last-error.txt")
+        with open(target_path, 'w', encoding='utf-8') as f:
+            f.write(contents)
+    
+    def get_error_text(self, watch_uuid):
+        """Get error text for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            
+        Returns:
+            str or False: The error text or False if not available
+        """
+        watch_dir = self.get_watch_dir(watch_uuid)
+        fname = os.path.join(watch_dir, "last-error.txt")
+        
+        if os.path.isfile(fname):
+            with open(fname, 'r') as f:
+                return f.read()
+                
+        return False
+    
+    def save_xpath_data(self, watch_uuid, data, as_error=False):
+        """Save XPath data for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            data (dict): XPath data
+            as_error (bool): Whether this is error data
+        """
+        self.ensure_data_dir_exists(watch_uuid)
+        watch_dir = self.get_watch_dir(watch_uuid)
+        
+        if as_error:
+            target_path = os.path.join(watch_dir, "elements-error.deflate")
+        else:
+            target_path = os.path.join(watch_dir, "elements.deflate")
+        
+        with open(target_path, 'wb') as f:
+            f.write(zlib.compress(json.dumps(data).encode()))
+    
+    def get_xpath_data(self, watch_uuid, is_error=False):
+        """Get XPath data for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            is_error (bool): Whether to get error data
+            
+        Returns:
+            dict or None: The XPath data or None if not available
+        """
+        watch_dir = self.get_watch_dir(watch_uuid)
+        
+        if is_error:
+            path = os.path.join(watch_dir, "elements-error.deflate")
+        else:
+            path = os.path.join(watch_dir, "elements.deflate")
+            
+        if not os.path.isfile(path):
+            return None
+            
+        with open(path, 'rb') as f:
+            return json.loads(zlib.decompress(f.read()).decode('utf-8'))
+    
+    def save_last_fetched_html(self, watch_uuid, timestamp, contents):
+        """Save last fetched HTML for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            timestamp (int): Timestamp
+            contents (str): HTML contents
+        """
+        self.ensure_data_dir_exists(watch_uuid)
+        watch_dir = self.get_watch_dir(watch_uuid)
+        
+        snapshot_fname = f"{timestamp}.html.br"
+        filepath = os.path.join(watch_dir, snapshot_fname)
+        
+        with open(filepath, 'wb') as f:
+            contents = contents.encode('utf-8') if isinstance(contents, str) else contents
+            try:
+                f.write(brotli.compress(contents))
+            except Exception as e:
+                logger.warning(f"{watch_uuid} - Unable to compress snapshot, saving as raw data to {filepath}")
+                logger.warning(e)
+                f.write(contents)
+                
+        # Prune old snapshots - keep only the newest 2
+        self._prune_last_fetched_html_snapshots(watch_uuid)
+    
+    def _prune_last_fetched_html_snapshots(self, watch_uuid):
+        """Prune old HTML snapshots
+        
+        Args:
+            watch_uuid (str): Watch UUID
+        """
+        watch_dir = self.get_watch_dir(watch_uuid)
+        history = self.get_history(watch_uuid)
+        
+        dates = list(history.keys())
+        dates.reverse()
+        
+        for index, timestamp in enumerate(dates):
+            snapshot_fname = f"{timestamp}.html.br"
+            filepath = os.path.join(watch_dir, snapshot_fname)
+            
+            # Keep only the first 2
+            if index > 1 and os.path.isfile(filepath):
+                os.remove(filepath)
+    
+    def get_fetched_html(self, watch_uuid, timestamp):
+        """Get fetched HTML for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            timestamp (int): Timestamp
+            
+        Returns:
+            str or False: The HTML or False if not available
+        """
+        watch_dir = self.get_watch_dir(watch_uuid)
+        
+        snapshot_fname = f"{timestamp}.html.br"
+        filepath = os.path.join(watch_dir, snapshot_fname)
+        
+        if os.path.isfile(filepath):
+            with open(filepath, 'rb') as f:
+                return brotli.decompress(f.read()).decode('utf-8')
+                
+        return False
+    
+    def save_last_text_fetched_before_filters(self, watch_uuid, contents):
+        """Save the last text fetched before filters
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            contents (str): Text contents
+        """
+        self.ensure_data_dir_exists(watch_uuid)
+        watch_dir = self.get_watch_dir(watch_uuid)
+        
+        filepath = os.path.join(watch_dir, 'last-fetched.br')
+        with open(filepath, 'wb') as f:
+            f.write(brotli.compress(contents.encode('utf-8'), mode=brotli.MODE_TEXT))
+    
+    def get_last_fetched_text_before_filters(self, watch_uuid):
+        """Get the last text fetched before filters
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            
+        Returns:
+            str: The text
+        """
+        watch_dir = self.get_watch_dir(watch_uuid)
+        filepath = os.path.join(watch_dir, 'last-fetched.br')
+        
+        if not os.path.isfile(filepath):
+            # If a previous attempt doesnt yet exist, just snarf the previous snapshot instead
+            history = self.get_history(watch_uuid)
+            dates = list(history.keys())
+            
+            if len(dates):
+                return self.get_history_snapshot(watch_uuid, dates[-1])
+            else:
+                return ''
+        
+        with open(filepath, 'rb') as f:
+            return brotli.decompress(f.read()).decode('utf-8')
+    
+    def visualselector_data_is_ready(self, watch_uuid):
+        """Check if visual selector data is ready
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            
+        Returns:
+            bool: Whether visual selector data is ready
+        """
+        watch_dir = self.get_watch_dir(watch_uuid)
+        screenshot_filename = os.path.join(watch_dir, "last-screenshot.png")
+        elements_index_filename = os.path.join(watch_dir, "elements.deflate")
+        
+        return path.isfile(screenshot_filename) and path.isfile(elements_index_filename)
+    
+    def clear_watch_history(self, watch_uuid):
+        """Clear history for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+        """
+        watch_dir = self.get_watch_dir(watch_uuid)
+        if not os.path.exists(watch_dir):
+            return
+            
+        # Delete all files but keep the directory
+        for item in pathlib.Path(watch_dir).glob("*.*"):
+            os.unlink(item)
+    
+    def delete_watch(self, watch_uuid):
+        """Delete a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+        """
+        watch_dir = self.get_watch_dir(watch_uuid)
+        if os.path.exists(watch_dir):
+            shutil.rmtree(watch_dir)

changedetectionio/storage/mongodb_storage.py

@@ -0,0 +1,466 @@
+import os
+from copy import deepcopy
+
+import brotli
+import zlib
+import json
+import time
+from loguru import logger
+from pymongo import MongoClient
+from urllib.parse import urlparse
+import base64
+
+from .storage_base import StorageBase
+
+class MongoDBStorage(StorageBase):
+    """MongoDB storage backend"""
+    
+    def __init__(self, datastore_path, include_default_watches=True, version_tag="0.0.0"):
+        """Initialize the MongoDB storage backend
+        
+        Args:
+            datastore_path (str): MongoDB connection URI
+            include_default_watches (bool): Whether to include default watches
+            version_tag (str): Version tag
+        """
+        # Parse MongoDB URI from datastore_path
+        parsed_uri = urlparse(datastore_path)
+        self.db_name = parsed_uri.path.lstrip('/')
+        if not self.db_name:
+            self.db_name = 'changedetection'
+            
+        # Connect to MongoDB
+        self.client = MongoClient(datastore_path)
+        self.db = self.client[self.db_name]
+        
+        # Collections
+        self.app_collection = self.db['app']
+        self.watches_collection = self.db['watches']
+        self.snapshots_collection = self.db['snapshots']
+        self.history_collection = self.db['history']
+        self.error_collection = self.db['errors']
+        self.xpath_collection = self.db['xpath']
+        self.html_collection = self.db['html']
+        
+        logger.info(f"MongoDB storage initialized, connected to {datastore_path}")
+    
+    def load_data(self):
+        """Load data from MongoDB
+        
+        Returns:
+            dict: The loaded data
+        """
+        app_data = self.app_collection.find_one({'_id': 'app_data'})
+        if not app_data:
+            return None
+            
+        # Remove MongoDB _id field
+        if '_id' in app_data:
+            del app_data['_id']
+            
+        return app_data
+    
+    def save_data(self, data):
+        """Save data to MongoDB
+        
+        Args:
+            data (dict): The data to save
+        """
+        try:
+            # Create a copy to modify
+            data_copy = deepcopy(data)
+            
+            # Set _id for app data
+            data_copy['_id'] = 'app_data'
+            
+            # Insert or update app data
+            self.app_collection.replace_one({'_id': 'app_data'}, data_copy, upsert=True)
+            
+            # Also store watches separately for more granular access
+            # This provides a safety net in case of corrupted app_data
+            watches = data.get('watching', {})
+            for uuid, watch in watches.items():
+                if isinstance(watch, dict):  # Handle case where watch is a Watch object
+                    watch_copy = deepcopy(dict(watch))
+                else:
+                    watch_copy = deepcopy(watch)
+                watch_copy['_id'] = uuid
+                self.watches_collection.replace_one({'_id': uuid}, watch_copy, upsert=True)
+                
+            # Also store tags separately
+            if 'settings' in data and 'application' in data['settings'] and 'tags' in data['settings']['application']:
+                tags = data['settings']['application']['tags']
+                for uuid, tag in tags.items():
+                    if isinstance(tag, dict):  # Handle case where tag is a Tag object
+                        tag_copy = deepcopy(dict(tag))
+                    else:
+                        tag_copy = deepcopy(tag)
+                    tag_copy['_id'] = uuid
+                    self.db['tags'].replace_one({'_id': uuid}, tag_copy, upsert=True)
+                    
+        except Exception as e:
+            logger.error(f"Error writing to MongoDB: {str(e)}")
+            raise e
+    
+    def ensure_data_dir_exists(self, watch_uuid):
+        """Ensure the data directory exists for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+        """
+        # MongoDB doesn't need directories, this is a no-op
+        pass
+    
+    def save_history_text(self, watch_uuid, contents, timestamp, snapshot_id):
+        """Save history text to MongoDB
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            contents (str): Contents to save
+            timestamp (int): Timestamp
+            snapshot_id (str): Snapshot ID
+            
+        Returns:
+            str: Snapshot ID
+        """
+        # Compress the contents
+        compressed_contents = brotli.compress(contents.encode('utf-8'), mode=brotli.MODE_TEXT)
+        
+        # Store the snapshot
+        snapshot_data = {
+            '_id': f"{watch_uuid}:{timestamp}",
+            'watch_uuid': watch_uuid,
+            'timestamp': timestamp,
+            'snapshot_id': snapshot_id,
+            'contents': base64.b64encode(compressed_contents).decode('ascii'),
+            'compressed': True
+        }
+        
+        self.snapshots_collection.replace_one({'_id': snapshot_data['_id']}, snapshot_data, upsert=True)
+        
+        # Update history index
+        history_entry = {
+            'watch_uuid': watch_uuid,
+            'timestamp': timestamp,
+            'snapshot_id': snapshot_id
+        }
+        
+        self.history_collection.replace_one(
+            {'watch_uuid': watch_uuid, 'timestamp': timestamp},
+            history_entry, 
+            upsert=True
+        )
+        
+        return snapshot_id
+    
+    def get_history(self, watch_uuid):
+        """Get history for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            
+        Returns:
+            dict: The history with timestamp keys and snapshot IDs as values
+        """
+        history = {}
+        
+        # Query history entries for this watch
+        entries = self.history_collection.find({'watch_uuid': watch_uuid}).sort('timestamp', 1)
+        
+        for entry in entries:
+            history[str(entry['timestamp'])] = entry['snapshot_id']
+            
+        return history
+    
+    def get_history_snapshot(self, watch_uuid, timestamp):
+        """Get a history snapshot from MongoDB
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            timestamp (int): Timestamp
+            
+        Returns:
+            str: The snapshot content
+        """
+        # Query for the snapshot
+        snapshot = self.snapshots_collection.find_one({'_id': f"{watch_uuid}:{timestamp}"})
+        
+        if not snapshot:
+            return None
+            
+        if snapshot.get('compressed', False):
+            # Decompress the contents
+            compressed_data = base64.b64decode(snapshot['contents'])
+            return brotli.decompress(compressed_data).decode('utf-8')
+        else:
+            return snapshot['contents']
+    
+    def save_screenshot(self, watch_uuid, screenshot, as_error=False):
+        """Save a screenshot for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            screenshot (bytes): Screenshot data
+            as_error (bool): Whether this is an error screenshot
+        """
+        collection_name = 'error_screenshots' if as_error else 'screenshots'
+        collection = self.db[collection_name]
+        
+        # Encode the screenshot as base64
+        encoded_screenshot = base64.b64encode(screenshot).decode('ascii')
+        
+        screenshot_data = {
+            '_id': watch_uuid,
+            'watch_uuid': watch_uuid,
+            'screenshot': encoded_screenshot,
+            'timestamp': int(time.time())
+        }
+        
+        collection.replace_one({'_id': watch_uuid}, screenshot_data, upsert=True)
+    
+    def get_screenshot(self, watch_uuid, is_error=False):
+        """Get a screenshot for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            is_error (bool): Whether to get the error screenshot
+            
+        Returns:
+            bytes or None: The screenshot data or None if not available
+        """
+        collection_name = 'error_screenshots' if is_error else 'screenshots'
+        collection = self.db[collection_name]
+        
+        screenshot_data = collection.find_one({'_id': watch_uuid})
+        if not screenshot_data:
+            return None
+            
+        # Decode the screenshot from base64
+        return base64.b64decode(screenshot_data['screenshot'])
+    
+    def save_error_text(self, watch_uuid, contents):
+        """Save error text for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            contents (str): Error contents
+        """
+        error_data = {
+            '_id': watch_uuid,
+            'watch_uuid': watch_uuid,
+            'error_text': contents,
+            'timestamp': int(time.time())
+        }
+        
+        self.error_collection.replace_one({'_id': watch_uuid}, error_data, upsert=True)
+    
+    def get_error_text(self, watch_uuid):
+        """Get error text for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            
+        Returns:
+            str or False: The error text or False if not available
+        """
+        error_data = self.error_collection.find_one({'_id': watch_uuid})
+        if not error_data:
+            return False
+            
+        return error_data['error_text']
+    
+    def save_xpath_data(self, watch_uuid, data, as_error=False):
+        """Save XPath data for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            data (dict): XPath data
+            as_error (bool): Whether this is error data
+        """
+        # Compress the data
+        compressed_data = zlib.compress(json.dumps(data).encode())
+        
+        _id = f"{watch_uuid}:error" if as_error else watch_uuid
+        
+        xpath_data = {
+            '_id': _id,
+            'watch_uuid': watch_uuid,
+            'is_error': as_error,
+            'data': base64.b64encode(compressed_data).decode('ascii'),
+            'timestamp': int(time.time())
+        }
+        
+        self.xpath_collection.replace_one({'_id': _id}, xpath_data, upsert=True)
+    
+    def get_xpath_data(self, watch_uuid, is_error=False):
+        """Get XPath data for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            is_error (bool): Whether to get error data
+            
+        Returns:
+            dict or None: The XPath data or None if not available
+        """
+        _id = f"{watch_uuid}:error" if is_error else watch_uuid
+        
+        xpath_data = self.xpath_collection.find_one({'_id': _id})
+        if not xpath_data:
+            return None
+            
+        # Decompress the data
+        compressed_data = base64.b64decode(xpath_data['data'])
+        return json.loads(zlib.decompress(compressed_data).decode('utf-8'))
+    
+    def save_last_fetched_html(self, watch_uuid, timestamp, contents):
+        """Save last fetched HTML for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            timestamp (int): Timestamp
+            contents (str): HTML contents
+        """
+        # Compress the contents
+        contents_bytes = contents.encode('utf-8') if isinstance(contents, str) else contents
+        try:
+            compressed_contents = brotli.compress(contents_bytes)
+        except Exception as e:
+            logger.warning(f"{watch_uuid} - Unable to compress HTML snapshot: {str(e)}")
+            compressed_contents = contents_bytes
+        
+        html_data = {
+            '_id': f"{watch_uuid}:{timestamp}",
+            'watch_uuid': watch_uuid,
+            'timestamp': timestamp,
+            'html': base64.b64encode(compressed_contents).decode('ascii'),
+            'compressed': True
+        }
+        
+        self.html_collection.replace_one({'_id': html_data['_id']}, html_data, upsert=True)
+        
+        # Prune old snapshots - keep only the newest 2
+        self._prune_last_fetched_html_snapshots(watch_uuid)
+    
+    def _prune_last_fetched_html_snapshots(self, watch_uuid):
+        """Prune old HTML snapshots
+        
+        Args:
+            watch_uuid (str): Watch UUID
+        """
+        # Get all HTML snapshots for this watch, sorted by timestamp descending
+        html_snapshots = list(
+            self.html_collection.find({'watch_uuid': watch_uuid}).sort('timestamp', -1)
+        )
+        
+        # Keep only the first 2
+        if len(html_snapshots) > 2:
+            for snapshot in html_snapshots[2:]:
+                self.html_collection.delete_one({'_id': snapshot['_id']})
+    
+    def get_fetched_html(self, watch_uuid, timestamp):
+        """Get fetched HTML for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            timestamp (int): Timestamp
+            
+        Returns:
+            str or False: The HTML or False if not available
+        """
+        html_data = self.html_collection.find_one({'_id': f"{watch_uuid}:{timestamp}"})
+        
+        if not html_data:
+            return False
+            
+        if html_data.get('compressed', False):
+            # Decompress the contents
+            compressed_data = base64.b64decode(html_data['html'])
+            return brotli.decompress(compressed_data).decode('utf-8')
+        else:
+            return html_data['html']
+    
+    def save_last_text_fetched_before_filters(self, watch_uuid, contents):
+        """Save the last text fetched before filters
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            contents (str): Text contents
+        """
+        # Compress the contents
+        compressed_contents = brotli.compress(contents.encode('utf-8'), mode=brotli.MODE_TEXT)
+        
+        last_fetched_data = {
+            '_id': watch_uuid,
+            'watch_uuid': watch_uuid,
+            'contents': base64.b64encode(compressed_contents).decode('ascii'),
+            'timestamp': int(time.time())
+        }
+        
+        self.db['last_fetched'].replace_one({'_id': watch_uuid}, last_fetched_data, upsert=True)
+    
+    def get_last_fetched_text_before_filters(self, watch_uuid):
+        """Get the last text fetched before filters
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            
+        Returns:
+            str: The text
+        """
+        last_fetched_data = self.db['last_fetched'].find_one({'_id': watch_uuid})
+        
+        if not last_fetched_data:
+            # If a previous attempt doesnt yet exist, just snarf the previous snapshot instead
+            history = self.get_history(watch_uuid)
+            dates = list(history.keys())
+            
+            if len(dates):
+                return self.get_history_snapshot(watch_uuid, dates[-1])
+            else:
+                return ''
+                
+        # Decompress the contents
+        compressed_data = base64.b64decode(last_fetched_data['contents'])
+        return brotli.decompress(compressed_data).decode('utf-8')
+    
+    def visualselector_data_is_ready(self, watch_uuid):
+        """Check if visual selector data is ready
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            
+        Returns:
+            bool: Whether visual selector data is ready
+        """
+        # Check if screenshot and xpath data exist
+        screenshot = self.db['screenshots'].find_one({'_id': watch_uuid})
+        xpath_data = self.xpath_collection.find_one({'_id': watch_uuid})
+        
+        return screenshot is not None and xpath_data is not None
+    
+    def clear_watch_history(self, watch_uuid):
+        """Clear history for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+        """
+        # Delete all snapshots and history for this watch
+        self.snapshots_collection.delete_many({'watch_uuid': watch_uuid})
+        self.history_collection.delete_many({'watch_uuid': watch_uuid})
+        self.html_collection.delete_many({'watch_uuid': watch_uuid})
+        self.db['last_fetched'].delete_many({'watch_uuid': watch_uuid})
+        self.xpath_collection.delete_many({'watch_uuid': watch_uuid})
+        self.db['screenshots'].delete_many({'watch_uuid': watch_uuid})
+        self.error_collection.delete_many({'watch_uuid': watch_uuid})
+    
+    def delete_watch(self, watch_uuid):
+        """Delete a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+        """
+        # Clear all history data
+        self.clear_watch_history(watch_uuid)
+        
+        # Also delete error screenshots
+        self.db['error_screenshots'].delete_many({'watch_uuid': watch_uuid})

changedetectionio/storage/s3_storage.py

@@ -0,0 +1,525 @@
+import os
+import io
+import json
+import brotli
+import zlib
+import time
+from loguru import logger
+import boto3
+from urllib.parse import urlparse
+import base64
+
+from .storage_base import StorageBase
+
+class S3Storage(StorageBase):
+    """Amazon S3 storage backend"""
+    
+    def __init__(self, datastore_path, include_default_watches=True, version_tag="0.0.0"):
+        """Initialize the S3 storage backend
+        
+        Args:
+            datastore_path (str): S3 URI (s3://bucket-name/optional-prefix)
+            include_default_watches (bool): Whether to include default watches
+            version_tag (str): Version tag
+        """
+        # Parse S3 URI
+        parsed_uri = urlparse(datastore_path)
+        self.bucket_name = parsed_uri.netloc
+        self.prefix = parsed_uri.path.lstrip('/')
+        
+        if self.prefix and not self.prefix.endswith('/'):
+            self.prefix += '/'
+            
+        # Initialize S3 client
+        # Uses AWS credentials from environment variables or IAM role
+        self.s3 = boto3.client('s3')
+        
+        logger.info(f"S3 storage initialized, using bucket '{self.bucket_name}' with prefix '{self.prefix}'")
+    
+    def _get_key(self, path):
+        """Get the S3 key for a path
+        
+        Args:
+            path (str): Path relative to the prefix
+            
+        Returns:
+            str: The full S3 key
+        """
+        return f"{self.prefix}{path}"
+    
+    def load_data(self):
+        """Load data from S3
+        
+        Returns:
+            dict: The loaded data
+        """
+        key = self._get_key("app-data.json")
+        
+        try:
+            response = self.s3.get_object(Bucket=self.bucket_name, Key=key)
+            return json.loads(response['Body'].read().decode('utf-8'))
+        except self.s3.exceptions.NoSuchKey:
+            return None
+        except Exception as e:
+            logger.error(f"Error loading data from S3: {str(e)}")
+            raise e
+    
+    def save_data(self, data):
+        """Save data to S3
+        
+        Args:
+            data (dict): The data to save
+        """
+        try:
+            key = self._get_key("app-data.json")
+            self.s3.put_object(
+                Bucket=self.bucket_name,
+                Key=key,
+                Body=json.dumps(data, indent=4),
+                ContentType='application/json'
+            )
+        except Exception as e:
+            logger.error(f"Error saving data to S3: {str(e)}")
+            raise e
+    
+    def ensure_data_dir_exists(self, watch_uuid):
+        """Ensure the data directory exists for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+        """
+        # S3 doesn't need directories, this is a no-op
+        pass
+    
+    def _get_watch_prefix(self, watch_uuid):
+        """Get the S3 prefix for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            
+        Returns:
+            str: The watch prefix
+        """
+        return self._get_key(f"watches/{watch_uuid}/")
+    
+    def save_history_text(self, watch_uuid, contents, timestamp, snapshot_id):
+        """Save history text to S3
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            contents (str): Contents to save
+            timestamp (int): Timestamp
+            snapshot_id (str): Snapshot ID
+            
+        Returns:
+            str: Snapshot ID
+        """
+        # Determine if we should compress
+        threshold = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD', 1024))
+        skip_brotli = os.getenv('DISABLE_BROTLI_TEXT_SNAPSHOT', 'False').lower() in ('true', '1', 't')
+        
+        watch_prefix = self._get_watch_prefix(watch_uuid)
+        
+        # Save the snapshot
+        if not skip_brotli and len(contents) > threshold:
+            snapshot_key = f"{watch_prefix}snapshots/{snapshot_id}.txt.br"
+            snapshot_fname = f"{snapshot_id}.txt.br"
+            compressed_contents = brotli.compress(contents.encode('utf-8'), mode=brotli.MODE_TEXT)
+            
+            self.s3.put_object(
+                Bucket=self.bucket_name,
+                Key=snapshot_key,
+                Body=compressed_contents
+            )
+        else:
+            snapshot_key = f"{watch_prefix}snapshots/{snapshot_id}.txt"
+            snapshot_fname = f"{snapshot_id}.txt"
+            
+            self.s3.put_object(
+                Bucket=self.bucket_name,
+                Key=snapshot_key,
+                Body=contents.encode('utf-8')
+            )
+        
+        # Update history index
+        history_key = f"{watch_prefix}history.txt"
+        
+        # Try to get existing history first
+        try:
+            response = self.s3.get_object(Bucket=self.bucket_name, Key=history_key)
+            history_content = response['Body'].read().decode('utf-8')
+        except self.s3.exceptions.NoSuchKey:
+            history_content = ""
+        
+        # Append new entry
+        history_content += f"{timestamp},{snapshot_fname}\n"
+        
+        # Save updated history
+        self.s3.put_object(
+            Bucket=self.bucket_name,
+            Key=history_key,
+            Body=history_content
+        )
+        
+        return snapshot_fname
+    
+    def get_history(self, watch_uuid):
+        """Get history for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            
+        Returns:
+            dict: The history with timestamp keys and snapshot IDs as values
+        """
+        tmp_history = {}
+        watch_prefix = self._get_watch_prefix(watch_uuid)
+        history_key = f"{watch_prefix}history.txt"
+        
+        try:
+            response = self.s3.get_object(Bucket=self.bucket_name, Key=history_key)
+            history_content = response['Body'].read().decode('utf-8')
+            
+            for line in history_content.splitlines():
+                if ',' in line:
+                    k, v = line.strip().split(',', 2)
+                    tmp_history[k] = f"{watch_prefix}snapshots/{v}"
+            
+            return tmp_history
+        except self.s3.exceptions.NoSuchKey:
+            return {}
+    
+    def get_history_snapshot(self, watch_uuid, timestamp):
+        """Get a history snapshot from S3
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            timestamp (int): Timestamp
+            
+        Returns:
+            str: The snapshot content
+        """
+        history = self.get_history(watch_uuid)
+        if not timestamp in history:
+            return None
+            
+        key = history[timestamp]
+        
+        try:
+            response = self.s3.get_object(Bucket=self.bucket_name, Key=key)
+            content = response['Body'].read()
+            
+            if key.endswith('.br'):
+                # Decompress brotli
+                return brotli.decompress(content).decode('utf-8')
+            else:
+                return content.decode('utf-8')
+        except Exception as e:
+            logger.error(f"Error reading snapshot from S3: {str(e)}")
+            return None
+    
+    def save_screenshot(self, watch_uuid, screenshot, as_error=False):
+        """Save a screenshot for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            screenshot (bytes): Screenshot data
+            as_error (bool): Whether this is an error screenshot
+        """
+        watch_prefix = self._get_watch_prefix(watch_uuid)
+        
+        if as_error:
+            key = f"{watch_prefix}last-error-screenshot.png"
+        else:
+            key = f"{watch_prefix}last-screenshot.png"
+        
+        self.s3.put_object(
+            Bucket=self.bucket_name,
+            Key=key,
+            Body=screenshot,
+            ContentType='image/png'
+        )
+    
+    def get_screenshot(self, watch_uuid, is_error=False):
+        """Get a screenshot for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            is_error (bool): Whether to get the error screenshot
+            
+        Returns:
+            bytes or None: The screenshot data or None if not available
+        """
+        watch_prefix = self._get_watch_prefix(watch_uuid)
+        
+        if is_error:
+            key = f"{watch_prefix}last-error-screenshot.png"
+        else:
+            key = f"{watch_prefix}last-screenshot.png"
+        
+        try:
+            response = self.s3.get_object(Bucket=self.bucket_name, Key=key)
+            return response['Body'].read()
+        except self.s3.exceptions.NoSuchKey:
+            return None
+    
+    def save_error_text(self, watch_uuid, contents):
+        """Save error text for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            contents (str): Error contents
+        """
+        watch_prefix = self._get_watch_prefix(watch_uuid)
+        key = f"{watch_prefix}last-error.txt"
+        
+        self.s3.put_object(
+            Bucket=self.bucket_name,
+            Key=key,
+            Body=contents.encode('utf-8')
+        )
+    
+    def get_error_text(self, watch_uuid):
+        """Get error text for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            
+        Returns:
+            str or False: The error text or False if not available
+        """
+        watch_prefix = self._get_watch_prefix(watch_uuid)
+        key = f"{watch_prefix}last-error.txt"
+        
+        try:
+            response = self.s3.get_object(Bucket=self.bucket_name, Key=key)
+            return response['Body'].read().decode('utf-8')
+        except self.s3.exceptions.NoSuchKey:
+            return False
+    
+    def save_xpath_data(self, watch_uuid, data, as_error=False):
+        """Save XPath data for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            data (dict): XPath data
+            as_error (bool): Whether this is error data
+        """
+        watch_prefix = self._get_watch_prefix(watch_uuid)
+        
+        if as_error:
+            key = f"{watch_prefix}elements-error.deflate"
+        else:
+            key = f"{watch_prefix}elements.deflate"
+        
+        compressed_data = zlib.compress(json.dumps(data).encode())
+        
+        self.s3.put_object(
+            Bucket=self.bucket_name,
+            Key=key,
+            Body=compressed_data
+        )
+    
+    def get_xpath_data(self, watch_uuid, is_error=False):
+        """Get XPath data for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            is_error (bool): Whether to get error data
+            
+        Returns:
+            dict or None: The XPath data or None if not available
+        """
+        watch_prefix = self._get_watch_prefix(watch_uuid)
+        
+        if is_error:
+            key = f"{watch_prefix}elements-error.deflate"
+        else:
+            key = f"{watch_prefix}elements.deflate"
+        
+        try:
+            response = self.s3.get_object(Bucket=self.bucket_name, Key=key)
+            compressed_data = response['Body'].read()
+            return json.loads(zlib.decompress(compressed_data).decode('utf-8'))
+        except self.s3.exceptions.NoSuchKey:
+            return None
+    
+    def save_last_fetched_html(self, watch_uuid, timestamp, contents):
+        """Save last fetched HTML for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            timestamp (int): Timestamp
+            contents (str): HTML contents
+        """
+        watch_prefix = self._get_watch_prefix(watch_uuid)
+        key = f"{watch_prefix}html/{timestamp}.html.br"
+        
+        contents_bytes = contents.encode('utf-8') if isinstance(contents, str) else contents
+        try:
+            compressed_contents = brotli.compress(contents_bytes)
+        except Exception as e:
+            logger.warning(f"{watch_uuid} - Unable to compress HTML snapshot: {str(e)}")
+            compressed_contents = contents_bytes
+        
+        self.s3.put_object(
+            Bucket=self.bucket_name,
+            Key=key,
+            Body=compressed_contents
+        )
+        
+        # Prune old snapshots - keep only the newest 2
+        self._prune_last_fetched_html_snapshots(watch_uuid)
+    
+    def _prune_last_fetched_html_snapshots(self, watch_uuid):
+        """Prune old HTML snapshots
+        
+        Args:
+            watch_uuid (str): Watch UUID
+        """
+        watch_prefix = self._get_watch_prefix(watch_uuid)
+        html_prefix = f"{watch_prefix}html/"
+        
+        # List all HTML snapshots
+        response = self.s3.list_objects_v2(
+            Bucket=self.bucket_name,
+            Prefix=html_prefix
+        )
+        
+        if 'Contents' not in response:
+            return
+            
+        # Sort by timestamp (extract from key)
+        html_files = sorted(
+            response['Contents'],
+            key=lambda x: int(x['Key'].split('/')[-1].split('.')[0]),
+            reverse=True
+        )
+        
+        # Delete all but the newest 2
+        if len(html_files) > 2:
+            for file in html_files[2:]:
+                self.s3.delete_object(
+                    Bucket=self.bucket_name,
+                    Key=file['Key']
+                )
+    
+    def get_fetched_html(self, watch_uuid, timestamp):
+        """Get fetched HTML for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            timestamp (int): Timestamp
+            
+        Returns:
+            str or False: The HTML or False if not available
+        """
+        watch_prefix = self._get_watch_prefix(watch_uuid)
+        key = f"{watch_prefix}html/{timestamp}.html.br"
+        
+        try:
+            response = self.s3.get_object(Bucket=self.bucket_name, Key=key)
+            compressed_data = response['Body'].read()
+            return brotli.decompress(compressed_data).decode('utf-8')
+        except self.s3.exceptions.NoSuchKey:
+            return False
+    
+    def save_last_text_fetched_before_filters(self, watch_uuid, contents):
+        """Save the last text fetched before filters
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            contents (str): Text contents
+        """
+        watch_prefix = self._get_watch_prefix(watch_uuid)
+        key = f"{watch_prefix}last-fetched.br"
+        
+        compressed_contents = brotli.compress(contents.encode('utf-8'), mode=brotli.MODE_TEXT)
+        
+        self.s3.put_object(
+            Bucket=self.bucket_name,
+            Key=key,
+            Body=compressed_contents
+        )
+    
+    def get_last_fetched_text_before_filters(self, watch_uuid):
+        """Get the last text fetched before filters
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            
+        Returns:
+            str: The text
+        """
+        watch_prefix = self._get_watch_prefix(watch_uuid)
+        key = f"{watch_prefix}last-fetched.br"
+        
+        try:
+            response = self.s3.get_object(Bucket=self.bucket_name, Key=key)
+            compressed_data = response['Body'].read()
+            return brotli.decompress(compressed_data).decode('utf-8')
+        except self.s3.exceptions.NoSuchKey:
+            # If a previous attempt doesnt yet exist, just snarf the previous snapshot instead
+            history = self.get_history(watch_uuid)
+            dates = list(history.keys())
+            
+            if len(dates):
+                return self.get_history_snapshot(watch_uuid, dates[-1])
+            else:
+                return ''
+    
+    def visualselector_data_is_ready(self, watch_uuid):
+        """Check if visual selector data is ready
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            
+        Returns:
+            bool: Whether visual selector data is ready
+        """
+        watch_prefix = self._get_watch_prefix(watch_uuid)
+        screenshot_key = f"{watch_prefix}last-screenshot.png"
+        elements_key = f"{watch_prefix}elements.deflate"
+        
+        try:
+            # Just check if both files exist
+            self.s3.head_object(Bucket=self.bucket_name, Key=screenshot_key)
+            self.s3.head_object(Bucket=self.bucket_name, Key=elements_key)
+            return True
+        except self.s3.exceptions.ClientError:
+            return False
+    
+    def clear_watch_history(self, watch_uuid):
+        """Clear history for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+        """
+        watch_prefix = self._get_watch_prefix(watch_uuid)
+        
+        # List all objects with this watch's prefix
+        paginator = self.s3.get_paginator('list_objects_v2')
+        pages = paginator.paginate(
+            Bucket=self.bucket_name,
+            Prefix=watch_prefix
+        )
+        
+        # Delete all objects in batches
+        for page in pages:
+            if 'Contents' not in page:
+                continue
+                
+            delete_keys = {'Objects': [{'Key': obj['Key']} for obj in page['Contents']]}
+            self.s3.delete_objects(
+                Bucket=self.bucket_name,
+                Delete=delete_keys
+            )
+    
+    def delete_watch(self, watch_uuid):
+        """Delete a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+        """
+        # Same implementation as clear_watch_history for S3
+        self.clear_watch_history(watch_uuid)

changedetectionio/storage/storage_base.py

@@ -0,0 +1,230 @@
+from abc import ABC, abstractmethod
+import json
+from loguru import logger
+
+class StorageBase(ABC):
+    """Abstract base class for storage backends"""
+    
+    @abstractmethod
+    def __init__(self, datastore_path, include_default_watches=True, version_tag="0.0.0"):
+        """Initialize the storage backend
+        
+        Args:
+            datastore_path (str): Path to the datastore
+            include_default_watches (bool): Whether to include default watches
+            version_tag (str): Version tag
+        """
+        pass
+    
+    @abstractmethod
+    def load_data(self):
+        """Load data from the storage backend
+        
+        Returns:
+            dict: The loaded data
+        """
+        pass
+    
+    @abstractmethod
+    def save_data(self, data):
+        """Save data to the storage backend
+        
+        Args:
+            data (dict): The data to save
+        """
+        pass
+    
+    @abstractmethod
+    def save_history_text(self, watch_uuid, contents, timestamp, snapshot_id):
+        """Save history text to the storage backend
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            contents (str): Contents to save
+            timestamp (int): Timestamp
+            snapshot_id (str): Snapshot ID
+            
+        Returns:
+            str: Snapshot filename or ID
+        """
+        pass
+    
+    @abstractmethod
+    def get_history_snapshot(self, watch_uuid, timestamp):
+        """Get a history snapshot from the storage backend
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            timestamp (int): Timestamp
+            
+        Returns:
+            str: The snapshot content
+        """
+        pass
+    
+    @abstractmethod
+    def get_history(self, watch_uuid):
+        """Get history for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            
+        Returns:
+            dict: The history with timestamp keys and snapshot IDs as values
+        """
+        pass
+    
+    @abstractmethod
+    def save_screenshot(self, watch_uuid, screenshot, as_error=False):
+        """Save a screenshot for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            screenshot (bytes): Screenshot data
+            as_error (bool): Whether this is an error screenshot
+        """
+        pass
+    
+    @abstractmethod
+    def get_screenshot(self, watch_uuid, is_error=False):
+        """Get a screenshot for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            is_error (bool): Whether to get the error screenshot
+            
+        Returns:
+            str or None: The screenshot path or None if not available
+        """
+        pass
+    
+    @abstractmethod
+    def save_error_text(self, watch_uuid, contents):
+        """Save error text for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            contents (str): Error contents
+        """
+        pass
+    
+    @abstractmethod
+    def get_error_text(self, watch_uuid):
+        """Get error text for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            
+        Returns:
+            str or False: The error text or False if not available
+        """
+        pass
+    
+    @abstractmethod
+    def save_xpath_data(self, watch_uuid, data, as_error=False):
+        """Save XPath data for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            data (dict): XPath data
+            as_error (bool): Whether this is error data
+        """
+        pass
+    
+    @abstractmethod
+    def get_xpath_data(self, watch_uuid, is_error=False):
+        """Get XPath data for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            is_error (bool): Whether to get error data
+            
+        Returns:
+            dict or None: The XPath data or None if not available
+        """
+        pass
+    
+    @abstractmethod
+    def save_last_fetched_html(self, watch_uuid, timestamp, contents):
+        """Save last fetched HTML for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            timestamp (int): Timestamp
+            contents (str): HTML contents
+        """
+        pass
+    
+    @abstractmethod
+    def get_fetched_html(self, watch_uuid, timestamp):
+        """Get fetched HTML for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            timestamp (int): Timestamp
+            
+        Returns:
+            str or False: The HTML or False if not available
+        """
+        pass
+    
+    @abstractmethod
+    def save_last_text_fetched_before_filters(self, watch_uuid, contents):
+        """Save the last text fetched before filters
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            contents (str): Text contents
+        """
+        pass
+    
+    @abstractmethod
+    def get_last_fetched_text_before_filters(self, watch_uuid):
+        """Get the last text fetched before filters
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            
+        Returns:
+            str: The text
+        """
+        pass
+    
+    @abstractmethod
+    def ensure_data_dir_exists(self, watch_uuid):
+        """Ensure the data directory exists for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+        """
+        pass
+    
+    @abstractmethod
+    def visualselector_data_is_ready(self, watch_uuid):
+        """Check if visual selector data is ready
+        
+        Args:
+            watch_uuid (str): Watch UUID
+            
+        Returns:
+            bool: Whether visual selector data is ready
+        """
+        pass
+    
+    @abstractmethod
+    def clear_watch_history(self, watch_uuid):
+        """Clear history for a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+        """
+        pass
+    
+    @abstractmethod
+    def delete_watch(self, watch_uuid):
+        """Delete a watch
+        
+        Args:
+            watch_uuid (str): Watch UUID
+        """
+        pass

changedetectionio/storage/storage_factory.py

@@ -0,0 +1,33 @@
+import re
+from loguru import logger
+from urllib.parse import urlparse
+
+from .storage_base import StorageBase
+from .filesystem_storage import FileSystemStorage
+from .mongodb_storage import MongoDBStorage
+from .s3_storage import S3Storage
+
+def create_storage(datastore_path, include_default_watches=True, version_tag="0.0.0"):
+    """Create a storage backend based on the datastore path
+    
+    Args:
+        datastore_path (str): Path to the datastore
+        include_default_watches (bool): Whether to include default watches
+        version_tag (str): Version tag
+        
+    Returns:
+        StorageBase: The storage backend
+    """
+    # Check if it's a MongoDB URI
+    if datastore_path.startswith('mongodb://') or datastore_path.startswith('mongodb+srv://'):
+        logger.info(f"Using MongoDB storage backend with URI {datastore_path}")
+        return MongoDBStorage(datastore_path, include_default_watches, version_tag)
+    
+    # Check if it's an S3 URI
+    if datastore_path.startswith('s3://'):
+        logger.info(f"Using S3 storage backend with URI {datastore_path}")
+        return S3Storage(datastore_path, include_default_watches, version_tag)
+    
+    # Default to filesystem
+    logger.info(f"Using filesystem storage backend with path {datastore_path}")
+    return FileSystemStorage(datastore_path, include_default_watches, version_tag)

changedetectionio/store.py

@@ -4,6 +4,7 @@ from flask import (
     flash
 )
 
+from .html_tools import TRANSLATE_WHITESPACE_TABLE
 from . model import App, Watch
 from copy import deepcopy, copy
 from os import path, unlink
@@ -11,7 +12,6 @@ from threading import Lock
 import json
 import os
 import re
-import requests
 import secrets
 import threading
 import time
@@ -20,6 +20,7 @@ from loguru import logger
 
 from .processors import get_custom_watch_obj_for_processor
 from .processors.restock_diff import Restock
+from .storage.storage_factory import create_storage
 
 # 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)'
@@ -38,20 +39,28 @@ class ChangeDetectionStore:
     needs_write_urgent = False
 
     __version_check = True
+    
+    # Singleton instance for access from Watch class methods
+    instance = None
 
     def __init__(self, datastore_path="/datastore", include_default_watches=True, version_tag="0.0.0"):
         # Should only be active for docker
         # logging.basicConfig(filename='/dev/stdout', level=logging.INFO)
         self.__data = App.model()
         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}'")
+        
+        # Create the appropriate storage backend based on the datastore path
+        self.storage = create_storage(datastore_path, include_default_watches, version_tag)
+        
         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={}))
+        self.generic_definition = deepcopy(Watch.model(datastore_path=datastore_path, default={}))
+        
+        # Set singleton instance
+        ChangeDetectionStore.instance = self
 
         if path.isfile('changedetectionio/source.txt'):
             with open('changedetectionio/source.txt') as f:
@@ -60,10 +69,9 @@ class ChangeDetectionStore:
                 self.__data['build_sha'] = f.read()
 
         try:
-            # @todo retest with ", encoding='utf-8'"
-            with open(self.json_store_path) as json_file:
-                from_disk = json.load(json_file)
-
+            # Load data from storage
+            from_disk = self.storage.load_data()
+            if from_disk:
                 # @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:
@@ -91,22 +99,24 @@ class ChangeDetectionStore:
                 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']}")
+            else:
+                # First time ran, Create the datastore.
+                if include_default_watches:
+                    logger.critical(f"No data store found, creating new store")
+                    self.add_watch(url='https://news.ycombinator.com/',
+                                  tag='Tech news',
+                                  extras={'fetch_backend': 'html_requests'})
 
-        # First time ran, Create the datastore.
-        except (FileNotFoundError):
-            if include_default_watches:
-                logger.critical(f"No JSON DB found at {self.json_store_path}, creating JSON store at {self.datastore_path}")
-                self.add_watch(url='https://news.ycombinator.com/',
-                               tag='Tech news',
-                               extras={'fetch_backend': 'html_requests'})
+                    self.add_watch(url='https://changedetection.io/CHANGELOG.txt',
+                                  tag='changedetection.io',
+                                  extras={'fetch_backend': 'html_requests'})
 
-                self.add_watch(url='https://changedetection.io/CHANGELOG.txt',
-                               tag='changedetection.io',
-                               extras={'fetch_backend': 'html_requests'})
-
-            updates_available = self.get_updates_available()
-            self.__data['settings']['application']['schema_version'] = updates_available.pop()
+                updates_available = self.get_updates_available()
+                self.__data['settings']['application']['schema_version'] = updates_available.pop()
 
+        except Exception as e:
+            logger.error(f"Error loading data from storage: {str(e)}")
+            raise e
         else:
             # Bump the update version by running updates
             self.run_updates()
@@ -227,23 +237,15 @@ class ChangeDetectionStore:
 
     # Delete a single watch by UUID
     def delete(self, uuid):
-        import pathlib
-        import shutil
-
         with self.lock:
             if uuid == 'all':
+                # Delete all watches
+                for watch_uuid in list(self.data['watching'].keys()):
+                    self.storage.delete_watch(watch_uuid)
                 self.__data['watching'] = {}
-
-                # GitHub #30 also delete history records
-                for uuid in self.data['watching']:
-                    path = pathlib.Path(os.path.join(self.datastore_path, uuid))
-                    if os.path.exists(path):
-                        shutil.rmtree(path)
-
             else:
-                path = pathlib.Path(os.path.join(self.datastore_path, uuid))
-                if os.path.exists(path):
-                    shutil.rmtree(path)
+                # Delete a single watch
+                self.storage.delete_watch(uuid)
                 del self.data['watching'][uuid]
 
         self.needs_write_urgent = True
@@ -266,10 +268,12 @@ class ChangeDetectionStore:
 
     # Remove a watchs data but keep the entry (URL etc)
     def clear_watch_history(self, uuid):
+        self.storage.clear_watch_history(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 = {}
@@ -371,43 +375,30 @@ class ChangeDetectionStore:
         return new_uuid
 
     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)
-        if path.isfile(screenshot_filename) and  path.isfile(elements_index_filename) :
-            return True
-
-        return False
+        return self.storage.visualselector_data_is_ready(watch_uuid)
 
     def sync_to_json(self):
-        logger.info("Saving JSON..")
+        logger.info("Saving data to storage backend...")
         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)}")
+            logger.error(f"! Data changed when writing to storage, 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)
+                self.storage.save_data(data)
             except Exception as e:
-                logger.error(f"Error writing JSON!! (Main JSON file save was skipped) : {str(e)}")
+                logger.error(f"Error writing to storage backend: {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
+    # Thread runner, this helps with thread/write issues when there are many operations that want to update the data
     # 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.
@@ -750,17 +741,17 @@ 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:
@@ -908,3 +899,18 @@ 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>
+                              <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>

changedetectionio/templates/_helpers.html

@@ -59,4 +59,112 @@
 
 {% macro render_button(field) %}
   {{ field(**kwargs)|safe }}
+{% endmacro %}
+
+{% macro playwright_warning() %}
+    <p><strong>Error - Playwright support for Chrome based fetching is not enabled.</strong> Alternatively try our <a href="https://changedetection.io">very affordable subscription based service which has all this setup for you</a>.</p>
+    <p>You may need to <a href="https://github.com/dgtlmoon/changedetection.io/blob/09ebc6ec6338545bdd694dc6eee57f2e9d2b8075/docker-compose.yml#L31">Enable playwright environment variable</a> and uncomment the <strong>sockpuppetbrowser</strong> in the <a href="https://github.com/dgtlmoon/changedetection.io/blob/master/docker-compose.yml">docker-compose.yml</a> file.</p>
+    <br>
+    <p>(Also Selenium/WebDriver can not extract full page screenshots reliably so Playwright is recommended here)</p>
+
+{% endmacro %}
+
+{% macro only_webdriver_type_watches_warning() %}
+    <p><strong>Sorry, this functionality only works with Playwright/Chrome enabled watches.<br>You need to <a href="#request">Set the fetch method to Playwright/Chrome mode and resave</a> and have the Playwright connection enabled.</strong></p><br>
+{% endmacro %}
+
+{% macro render_time_schedule_form(form, available_timezones, timezone_default_config) %}
+    <style>
+    .day-schedule *, .day-schedule select {
+        display: inline-block;
+    }
+
+    .day-schedule label[for*="time_schedule_limit-"][for$="-enabled"] {
+        min-width: 6rem;
+        font-weight: bold;
+    }
+    .day-schedule label {
+        font-weight: normal;
+    }
+
+    .day-schedule table label {
+        padding-left: 0.5rem;
+        padding-right: 0.5rem;
+    }
+    #timespan-warning, input[id*='time_schedule_limit-timezone'].error {
+        color: #ff0000;
+    }
+    .day-schedule.warning table {
+        background-color: #ffbbc2;
+    }
+    ul#day-wrapper {
+        list-style: none;
+    }
+    #timezone-info > * {
+        display: inline-block;
+    }
+
+    #scheduler-icon-label {
+        background-position: left center;
+        background-repeat: no-repeat;
+        background-size: contain;
+        display: inline-block;
+        vertical-align: middle;
+        padding-left: 50px;
+        background-image: url({{ url_for('static_content', group='images', filename='schedule.svg') }});
+    }
+    #timespan-warning {
+        display: none;
+    }
+    </style>
+    <br>
+
+    {% if timezone_default_config %}
+    <div>
+        <span id="scheduler-icon-label" style="">
+            {{ render_checkbox_field(form.time_schedule_limit.enabled) }}
+            <div class="pure-form-message-inline">
+                Set a hourly/week day schedule
+            </div>
+        </span>
+
+    </div>
+    <br>
+    <div id="schedule-day-limits-wrapper">
+        <label>Schedule time limits</label><a data-template="business-hours"
+                                              class="set-schedule pure-button button-secondary button-xsmall">Business
+        hours</a>
+        <a data-template="weekend" class="set-schedule pure-button button-secondary button-xsmall">Weekends</a>
+        <a data-template="reset" class="set-schedule pure-button button-xsmall">Reset</a><br>
+        <br>
+
+        <ul id="day-wrapper">
+            {% for day in ['monday', 'tuesday', 'wednesday', 'thursday', 'friday', 'saturday', 'sunday'] %}
+                <li class="day-schedule" id="schedule-{{ day }}">
+                    {{ render_nolabel_field(form.time_schedule_limit[day]) }}
+                </li>
+            {% endfor %}
+            <li id="timespan-warning">Warning, one or more of your 'days' has a duration that would extend into the next day.<br>
+            This could have unintended consequences.</li>
+            <li id="timezone-info">
+                {{ render_field(form.time_schedule_limit.timezone, placeholder=timezone_default_config) }} <span id="local-time-in-tz"></span>
+                <datalist id="timezones" style="display: none;">
+                    {% for timezone in available_timezones %}
+                        <option value="{{ timezone }}">{{ timezone }}</option>
+                    {% endfor %}
+                </datalist>
+            </li>
+        </ul>
+    <br>
+        <span class="pure-form-message-inline">
+         <a href="https://changedetection.io/tutorials">More help and examples about using the scheduler</a>
+        </span>
+    </div>
+    {% else %}
+        <span class="pure-form-message-inline">
+            Want to use a time schedule? <a href="{{url_for('settings_page')}}#timedate">First confirm/save your Time Zone Settings</a>
+        </span>
+        <br>
+    {% endif %}
+
 {% endmacro %}

changedetectionio/templates/base.html

@@ -33,9 +33,11 @@
     <script src="{{url_for('static_content', group='js', filename='csrf.js')}}" defer></script>
   </head>
 
-  <body>
+  <body class="">
     <div class="header">
-      <div class="home-menu pure-menu pure-menu-horizontal pure-menu-fixed" id="nav-menu">
+    <div class="pure-menu-fixed" style="width: 100%;">
+      <div class="home-menu pure-menu pure-menu-horizontal" id="nav-menu">
+
         {% if has_password and not current_user.is_authenticated %}
           <a class="pure-menu-heading" href="https://changedetection.io" rel="noopener">
             <strong>Change</strong>Detection.io</a>
@@ -68,7 +70,7 @@
                 <a href="{{ url_for('import_page')}}" class="pure-menu-link">IMPORT</a>
               </li>
               <li class="pure-menu-item">
-                <a href="{{ url_for('get_backup')}}" class="pure-menu-link">BACKUP</a>
+                <a href="{{ url_for('backups.index')}}" class="pure-menu-link">BACKUPS</a>
               </li>
             {% else %}
               <li class="pure-menu-item">
@@ -129,7 +131,12 @@
           </li>
         </ul>
       </div>
+      <div id="pure-menu-horizontal-spinner"></div>
+      </div>
+
     </div>
+
+
     {% if hosted_sticky %}
       <div class="sticky-tab" id="hosted-sticky">
         <a href="https://changedetection.io/?ref={{guid}}">Let us host your instance!</a>
@@ -152,7 +159,7 @@
                     <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')}}">
+                        <img alt="Chrome store icon" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}">
                         Chrome Webstore
                     </a>
                 </p>

changedetectionio/templates/diff.html

@@ -14,7 +14,7 @@
 
 <div id="settings">
     <form class="pure-form " action="" method="GET" id="diff-form">
-        <fieldset>
+        <fieldset class="diff-fieldset">
             {% if versions|length >= 1 %}
                 <strong>Compare</strong>
                 <del class="change"><span>from</span></del>
@@ -33,7 +33,7 @@
                         </option>
                     {% endfor %}
                 </select>
-                <button type="submit" class="pure-button pure-button-primary">Go</button>
+                <button type="submit" class="pure-button pure-button-primary reset-margin">Go</button>
             {% endif %}
         </fieldset>
         <fieldset>

changedetectionio/templates/edit.html

@@ -1,9 +1,11 @@
 {% 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, playwright_warning, only_webdriver_type_watches_warning %}
 {% from '_common_fields.html' import render_common_settings_form %}
 <script src="{{url_for('static_content', group='js', filename='tabs.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>
 <script>
     const browser_steps_available_screenshots=JSON.parse('{{ watch.get_browsersteps_available_screenshots|tojson }}');
     const browser_steps_config=JSON.parse('{{ browser_steps_config|tojson }}');
@@ -23,9 +25,8 @@
     const watch_visual_selector_data_url="{{url_for('static_content', group='visual_selector_data', filename=uuid)}}";
     const default_system_fetch_backend="{{ settings_application['fetch_backend'] }}";
 </script>
-
+<script src="{{url_for('static_content', group='js', filename='plugins.js')}}" defer></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>
 <script src="{{url_for('static_content', group='js', filename='visual-selector.js')}}" defer></script>
 {% if playwright_enabled %}
@@ -39,17 +40,16 @@
 
     <div class="tabs collapsable">
         <ul>
-            <li class="tab" id=""><a href="#general">General</a></li>
+            <li class="tab"><a href="#general">General</a></li>
             <li class="tab"><a href="#request">Request</a></li>
             {% if extra_tab_content %}
             <li class="tab"><a href="#extras_tab">{{ extra_tab_content }}</a></li>
             {% endif %}
-            {% if playwright_enabled %}
             <li class="tab"><a id="browsersteps-tab" href="#browser-steps">Browser Steps</a></li>
-            {% endif %}
+        <!-- should goto extra forms? -->
             {% if watch['processor'] == 'text_json_diff' %}
             <li class="tab"><a id="visualselector-tab" href="#visualselector">Visual Filter Selector</a></li>
-            <li class="tab"><a href="#filters-and-triggers">Filters &amp; Triggers</a></li>
+            <li class="tab" id="filters-and-triggers-tab"><a href="#filters-and-triggers">Filters &amp; Triggers</a></li>
             {% endif %}
             <li class="tab"><a href="#notifications">Notifications</a></li>
             <li class="tab"><a href="#stats">Stats</a></li>
@@ -58,15 +58,15 @@
 
     <div class="box-wrap inner">
         <form class="pure-form pure-form-stacked"
-              action="{{ url_for('edit_page', uuid=uuid, next = request.args.get('next'), unpause_on_save = request.args.get('unpause_on_save')) }}" method="POST">
+              action="{{ url_for('edit_page', uuid=uuid, next = request.args.get('next'), unpause_on_save = request.args.get('unpause_on_save'), tag = request.args.get('tag')) }}" 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.url, placeholder="https://...", required=true, class="m-d") }}
-                        <span class="pure-form-message-inline">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></span><br>
-                        <span class="pure-form-message-inline">You can use variables in the URL, perfect for inserting the current date and other logic, <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a></span><br>
+                        <div class="pure-form-message">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></div>
+                        <div class="pure-form-message">Variables are supported in the URL (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a>).</div>
                     </div>
                     <div class="pure-control-group inline-radio">
                         {{ render_field(form.processor) }}
@@ -79,9 +79,24 @@
                         <span class="pure-form-message-inline">Organisational tag/group name used in the main listing page</span>
                     </div>
                     <div class="pure-control-group time-between-check border-fieldset">
-                        {{ render_field(form.time_between_check, class="time-check-widget") }}
+
                         {{ render_checkbox_field(form.time_between_check_use_default, class="use-default-timecheck") }}
-                    </div>
+                        <br>
+                        <div id="time-check-widget-wrapper">
+                            {{ render_field(form.time_between_check, class="time-check-widget") }}
+
+                            <span class="pure-form-message-inline">
+                             The interval/amount of time between each check.
+                            </span>
+                        </div>
+                        <div id="time-between-check-schedule">
+                            <!-- Start Time and End Time -->
+                            <div id="limit-between-time">
+                                {{ render_time_schedule_form(form, available_timezones, timezone_default_config) }}
+                            </div>
+                        </div>
+<br>
+              </div>
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.extract_title_as_title) }}
                     </div>
@@ -149,21 +164,24 @@
                             {{ render_field(form.method) }}
                         </div>
                         <div id="request-body">
-                                            {{ render_field(form.body, rows=5, placeholder="Example
+                                            {{ render_field(form.body, rows=7, placeholder="Example
 {
    \"name\":\"John\",
    \"age\":30,
-   \"car\":null
+   \"car\":null,
+   \"year\":{% now 'Europe/Berlin', '%Y' %}
 }") }}
                         </div>
+                        <div class="pure-form-message">Variables are supported in the request body (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a>).</div>
                     </div>
                 </fieldset>
             <!-- hmm -->
                 <div class="pure-control-group advanced-options"  style="display: none;">
-                    {{ render_field(form.headers, rows=5, placeholder="Example
+                    {{ render_field(form.headers, rows=7, placeholder="Example
 Cookie: foobar
-User-Agent: wonderbra 1.0") }}
-
+User-Agent: wonderbra 1.0
+Math: {{ 1 + 1 }}") }}
+                        <div class="pure-form-message">Variables are supported in the request header values (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a>).</div>
                         <div class="pure-form-message-inline">
                             {% if has_extra_headers_file %}
                                 <strong>Alert! Extra headers file found and will be added to this watch!</strong>
@@ -180,8 +198,9 @@ User-Agent: wonderbra 1.0") }}
                     </div>
             </fieldset>
             </div>
-            {% if playwright_enabled %}
+
             <div class="tab-pane-inner" id="browser-steps">
+            {% if playwright_enabled and watch_uses_webdriver %}
                 <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}" alt="New beta functionality">
                 <fieldset>
                     <div class="pure-control-group">
@@ -199,13 +218,13 @@ User-Agent: wonderbra 1.0") }}
                         <div id="loading-status-text" style="display: none;">Please wait, first browser step can take a little time to load..<div class="spinner"></div></div>
                         <div class="flex-wrapper" >
 
-                            <div id="browser-steps-ui" class="noselect"  style="width: 100%; background-color: #eee; border-radius: 5px;">
+                            <div id="browser-steps-ui" class="noselect">
 
                                 <div class="noselect"  id="browsersteps-selector-wrapper" style="width: 100%">
                                     <span class="loader" >
                                         <span id="browsersteps-click-start">
                                             <h2 >Click here to Start</h2>
-                                            <svg style="height: 3.5rem;" version="1.1" viewBox="0 0 32 32"  xml:space="preserve" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g id="Layer_1"/><g id="play_x5F_alt"><path d="M16,0C7.164,0,0,7.164,0,16s7.164,16,16,16s16-7.164,16-16S24.836,0,16,0z M10,24V8l16.008,8L10,24z" style="fill: var(--color-grey-400);"/></g></svg><br>
+                                            <svg style="height: 3.5rem;" version="1.1" viewBox="0 0 32 32"  xml:space="preserve" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g id="start"/><g id="play_x5F_alt"><path d="M16,0C7.164,0,0,7.164,0,16s7.164,16,16,16s16-7.164,16-16S24.836,0,16,0z M10,24V8l16.008,8L10,24z" style="fill: var(--color-grey-400);"/></g></svg><br>
                                             Please allow 10-15 seconds for the browser to connect.<br>
                                         </span>
                                         <div class="spinner"  style="display: none;"></div>
@@ -214,22 +233,32 @@ User-Agent: wonderbra 1.0") }}
                                     <canvas  class="noselect" id="browsersteps-selector-canvas" style="max-width: 100%; width: 100%;"></canvas>
                                 </div>
                             </div>
-                            <div id="browser-steps-fieldlist" style="padding-left: 1em;  width: 350px; font-size: 80%;" >
-                                <span id="browser-seconds-remaining">Loading</span> <span style="font-size: 80%;"> (<a target=_new href="https://github.com/dgtlmoon/changedetection.io/pull/478/files#diff-1a79d924d1840c485238e66772391268a89c95b781d69091384cf1ea1ac146c9R4">?</a>) </span>
+                            <div id="browser-steps-fieldlist" >
+                                <span id="browser-seconds-remaining">Loading</span> <span style="font-size: 80%;"> (<a target="newwindow" href="https://github.com/dgtlmoon/changedetection.io/pull/478/files#diff-1a79d924d1840c485238e66772391268a89c95b781d69091384cf1ea1ac146c9R4">?</a>) </span>
                                 {{ render_field(form.browser_steps) }}
                             </div>
                         </div>
                     </div>
                 </fieldset>
+                {% else %}
+                    <span class="pure-form-message-inline">
+                        {% if not watch_uses_webdriver %}
+                            {{ only_webdriver_type_watches_warning() }}
+                        {% endif %}
+                        {%  if not playwright_enabled %}
+                            {{ playwright_warning() }}
+                        {% endif %}
+                    </span>
+                {% endif %}
             </div>
-            {% endif %}
+
 
             <div class="tab-pane-inner" id="notifications">
                 <fieldset>
                     <div  class="pure-control-group inline-radio">
                       {{ render_checkbox_field(form.notification_muted) }}
                     </div>
-                    {% if is_html_webdriver %}
+                    {% if watch_uses_webdriver %}
                     <div class="pure-control-group inline-radio">
                       {{ render_checkbox_field(form.notification_screenshot) }}
                         <span class="pure-form-message-inline">
@@ -253,7 +282,10 @@ User-Agent: wonderbra 1.0") }}
 
             {% if watch['processor'] == 'text_json_diff' %}
             <div class="tab-pane-inner" id="filters-and-triggers">
-                    <div class="pure-control-group">
+                <span id="activate-text-preview" class="pure-button pure-button-primary button-xsmall">Activate preview</span>
+              <div>
+              <div id="edit-text-filter">
+                    <div class="pure-control-group" id="pro-tips">
                             <strong>Pro-tips:</strong><br>
                             <ul>
                                 <li>
@@ -275,9 +307,9 @@ 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>
+                        <span data-target="#advanced-help-selectors" class="toggle-show pure-button button-tag button-xsmall">Show advanced help and tips</span><br>
+                    <ul id="advanced-help-selectors" style="display: none;">
                         <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>
@@ -297,21 +329,25 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                                 <li>To use XPath1.0: Prefix with <code>xpath1:</code></li>
                             </ul>
                             </li>
-                    </ul>
-                    Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath{% if jq_support %}, or jq selector{%endif%} rules before filing an issue on GitHub! <a
+                    <li>
+                        Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath{% if jq_support %}, or jq selector{%endif%} rules before filing an issue on GitHub! <a
                                 href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br>
+                    </li>
+                    </ul>
+
                 </span>
                     </div>
                 <fieldset class="pure-control-group">
                     {{ render_field(form.subtractive_selectors, rows=5, placeholder=has_tag_filters_extra+"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> Don't paste HTML here, use only CSS selectors </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>
@@ -322,18 +358,25 @@ nav
                         {{ render_checkbox_field(form.filter_text_added) }}
                         {{ render_checkbox_field(form.filter_text_replaced) }}
                         {{ render_checkbox_field(form.filter_text_removed) }}
-                    <span class="pure-form-message-inline">Note: Depending on the length and similarity of the text on each line, the algorithm may consider an <strong>addition</strong> instead of <strong>replacement</strong> for example.</span>
-                    <span class="pure-form-message-inline">So it's always better to select <strong>Added</strong>+<strong>Replaced</strong> when you're interested in new content.</span><br>
-                    <span class="pure-form-message-inline">When content is merely moved in a list, it will also trigger an <strong>addition</strong>, consider enabling <code><strong>Only trigger when unique lines appear</strong></code></span>
+                    <span class="pure-form-message-inline">Note: Depending on the length and similarity of the text on each line, the algorithm may consider an <strong>addition</strong> instead of <strong>replacement</strong> for example.</span><br>
+                    <span class="pure-form-message-inline">&nbsp;So it's always better to select <strong>Added</strong>+<strong>Replaced</strong> when you're interested in new content.</span><br>
+                    <span class="pure-form-message-inline">&nbsp;When content is merely moved in a list, it will also trigger an <strong>addition</strong>, consider enabling <code><strong>Only trigger when unique lines appear</strong></code></span>
+                </fieldset>
+                <fieldset class="pure-control-group">
+                    {{ render_checkbox_field(form.check_unique_lines) }}
+                    <span class="pure-form-message-inline">Good for websites that just move the content around, and you want to know when NEW content is added, compares new lines against all history for this watch.</span>
+                </fieldset>
+                <fieldset class="pure-control-group">
+                    {{ render_checkbox_field(form.remove_duplicate_lines) }}
+                    <span class="pure-form-message-inline">Remove duplicate lines of text</span>
                 </fieldset>
-
                 <fieldset class="pure-control-group">
                     {{ render_checkbox_field(form.sort_text_alphabetically) }}
                     <span class="pure-form-message-inline">Helps reduce changes detected caused by sites shuffling lines around, combine with <i>check unique lines</i> below.</span>
                 </fieldset>
                 <fieldset class="pure-control-group">
-                    {{ render_checkbox_field(form.check_unique_lines) }}
-                    <span class="pure-form-message-inline">Good for websites that just move the content around, and you want to know when NEW content is added, compares new lines against all history for this watch.</span>
+                    {{ render_checkbox_field(form.trim_text_whitespace) }}
+                    <span class="pure-form-message-inline">Remove any whitespace before and after each line of text</span>
                 </fieldset>
                 <fieldset>
                     <div class="pure-control-group">
@@ -356,10 +399,10 @@ nav
 ") }}
                     <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>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>
 
@@ -383,7 +426,9 @@ Unavailable") }}
                 </fieldset>
                 <fieldset>
                     <div class="pure-control-group">
-                        {{ render_field(form.extract_text, rows=5, placeholder="\d+ online") }}
+                        {{ render_field(form.extract_text, rows=5, placeholder="/.+?\d+ comments.+?/
+ or
+keyword") }}
                         <span class="pure-form-message-inline">
                     <ul>
                         <li>Extracts text in the final output (line by line) after other filters using regular expressions or string match;
@@ -403,7 +448,27 @@ Unavailable") }}
                 </fieldset>
                 </div>
             </div>
-            {% endif %}
+              <div id="text-preview" style="display: none;" >
+                    <script>
+                        const preview_text_edit_filters_url="{{url_for('watch_get_preview_rendered', uuid=uuid)}}";
+                    </script>
+                    <br>
+                    {#<div id="text-preview-controls"><span id="text-preview-refresh" class="pure-button button-xsmall">Refresh</span></div>#}
+                    <div class="minitabs-wrapper">
+                      <div class="minitabs-content">
+                          <div id="text-preview-inner" class="monospace-preview">
+                              <p>Loading...</p>
+                          </div>
+                          <div id="text-preview-before-inner" style="display: none;" class="monospace-preview">
+                              <p>Loading...</p>
+                          </div>
+                      </div>
+                    </div>
+            </div>
+          </div>
+        </div>
+
+        {% endif %}
         {# rendered sub Template #}
         {% if extra_form_content %}
             <div class="tab-pane-inner" id="extras_tab">
@@ -416,7 +481,7 @@ Unavailable") }}
 
                 <fieldset>
                     <div class="pure-control-group">
-                        {% if visualselector_enabled %}
+                        {% if playwright_enabled and watch_uses_webdriver %}
                             <span class="pure-form-message-inline" id="visual-selector-heading">
                                 The Visual Selector tool lets you select the <i>text</i> elements that will be used for the change detection. It automatically fills-in the filters in the "CSS/JSONPath/JQ/XPath Filters" box of the <a href="#filters-and-triggers">Filters & Triggers</a> tab. Use <strong>Shift+Click</strong> to select multiple items.
                             </span>
@@ -434,11 +499,12 @@ Unavailable") }}
                             </div>
                             <div id="selector-current-xpath" style="overflow-x: hidden"><strong>Currently:</strong>&nbsp;<span class="text">Loading...</span></div>
                         {% else %}
-                            <span class="pure-form-message-inline">
-                                <p>Sorry, this functionality only works with Playwright/Chrome enabled watches.</p>
-                                <p>Enable the Playwright Chrome fetcher, or alternatively try our <a href="https://lemonade.changedetection.io/start">very affordable subscription based service</a>.</p>
-                                <p>This is because Selenium/WebDriver can not extract full page screenshots reliably.</p>
-                            </span>
+                            {% if not watch_uses_webdriver %}
+                                {{ only_webdriver_type_watches_warning() }}
+                            {% endif %}
+                            {% if not playwright_enabled %}
+                                {{ playwright_warning() }}
+                            {% endif %}
                         {% endif %}
                     </div>
                 </fieldset>

changedetectionio/templates/preview.html

@@ -3,11 +3,13 @@
 {% block content %}
     <script>
         const screenshot_url = "{{url_for('static_content', group='screenshot', filename=uuid)}}";
+        const triggered_line_numbers = {{ triggered_line_numbers|tojson }};
         {% if last_error_screenshot %}
             const error_screenshot_url = "{{url_for('static_content', group='screenshot', filename=uuid, error_screenshot=1) }}";
         {% endif %}
         const highlight_submit_ignore_url = "{{url_for('highlight_submit_ignore_url', uuid=uuid)}}";
     </script>
+    <script src="{{url_for('static_content', group='js', filename='plugins.js')}}"></script>
     <script src="{{ url_for('static_content', group='js', filename='diff-overview.js') }}" defer></script>
     <script src="{{ url_for('static_content', group='js', filename='preview.js') }}" defer></script>
     <script src="{{ url_for('static_content', group='js', filename='tabs.js') }}" defer></script>
@@ -67,16 +69,15 @@
 
         <div class="tab-pane-inner" id="text">
             <div class="snapshot-age">{{ current_version|format_timestamp_timeago }}</div>
-            <span class="ignored">Grey lines are ignored</span> <span class="triggered">Blue lines are triggers</span>
             <span class="tip"><strong>Pro-tip</strong>: Highlight text to add to ignore filters</span>
 
             <table>
                 <tbody>
                 <tr>
                     <td id="diff-col" class="highlightable-filter">
-                        {% for row in content %}
-                            <div class="{{ row.classes }}">{{ row.line }}</div>
-                        {% endfor %}
+                        <pre style="border-left: 2px solid #ddd;">
+{{ content }}
+                        </pre>
                     </td>
                 </tr>
                 </tbody>

changedetectionio/templates/settings.html

@@ -1,7 +1,7 @@
 {% 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")}}";
@@ -10,9 +10,11 @@
 {% 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>
@@ -21,6 +23,7 @@
             <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>
         </ul>
     </div>
@@ -32,6 +35,12 @@
                     <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") }}
@@ -155,11 +164,13 @@
                       {{ 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 +181,11 @@ 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>
@@ -203,12 +214,29 @@ 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 +280,7 @@ 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">
@@ -274,7 +300,7 @@ nav
                 <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('clear_all_history')}}" class="pure-button button-small button-error">Clear Snapshot History</a>
                 </div>
             </div>
         </form>

changedetectionio/templates/svgs/search-icon.svg

@@ -1 +1 @@
-<svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" viewBox="0 0 122.879 119.799" enable-background="new 0 0 122.879 119.799" xml:space="preserve"><g><path d="M49.988,0h0.016v0.007C63.803,0.011,76.298,5.608,85.34,14.652c9.027,9.031,14.619,21.515,14.628,35.303h0.007v0.033v0.04 h-0.007c-0.005,5.557-0.917,10.905-2.594,15.892c-0.281,0.837-0.575,1.641-0.877,2.409v0.007c-1.446,3.66-3.315,7.12-5.547,10.307 l29.082,26.139l0.018,0.016l0.157,0.146l0.011,0.011c1.642,1.563,2.536,3.656,2.649,5.78c0.11,2.1-0.543,4.248-1.979,5.971 l-0.011,0.016l-0.175,0.203l-0.035,0.035l-0.146,0.16l-0.016,0.021c-1.565,1.642-3.654,2.534-5.78,2.646 c-2.097,0.111-4.247-0.54-5.971-1.978l-0.015-0.011l-0.204-0.175l-0.029-0.024L78.761,90.865c-0.88,0.62-1.778,1.209-2.687,1.765 c-1.233,0.755-2.51,1.466-3.813,2.115c-6.699,3.342-14.269,5.222-22.272,5.222v0.007h-0.016v-0.007 c-13.799-0.004-26.296-5.601-35.338-14.645C5.605,76.291,0.016,63.805,0.007,50.021H0v-0.033v-0.016h0.007 c0.004-13.799,5.601-26.296,14.645-35.338C23.683,5.608,36.167,0.016,49.955,0.007V0H49.988L49.988,0z M50.004,11.21v0.007h-0.016 h-0.033V11.21c-10.686,0.007-20.372,4.35-27.384,11.359C15.56,29.578,11.213,39.274,11.21,49.973h0.007v0.016v0.033H11.21 c0.007,10.686,4.347,20.367,11.359,27.381c7.009,7.012,16.705,11.359,27.403,11.361v-0.007h0.016h0.033v0.007 c10.686-0.007,20.368-4.348,27.382-11.359c7.011-7.009,11.358-16.702,11.36-27.4h-0.006v-0.016v-0.033h0.006 c-0.006-10.686-4.35-20.372-11.358-27.384C70.396,15.56,60.703,11.213,50.004,11.21L50.004,11.21z"/></g></svg>
+<svg version="1.1" id="search" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" viewBox="0 0 122.879 119.799" enable-background="new 0 0 122.879 119.799" xml:space="preserve"><g><path d="M49.988,0h0.016v0.007C63.803,0.011,76.298,5.608,85.34,14.652c9.027,9.031,14.619,21.515,14.628,35.303h0.007v0.033v0.04 h-0.007c-0.005,5.557-0.917,10.905-2.594,15.892c-0.281,0.837-0.575,1.641-0.877,2.409v0.007c-1.446,3.66-3.315,7.12-5.547,10.307 l29.082,26.139l0.018,0.016l0.157,0.146l0.011,0.011c1.642,1.563,2.536,3.656,2.649,5.78c0.11,2.1-0.543,4.248-1.979,5.971 l-0.011,0.016l-0.175,0.203l-0.035,0.035l-0.146,0.16l-0.016,0.021c-1.565,1.642-3.654,2.534-5.78,2.646 c-2.097,0.111-4.247-0.54-5.971-1.978l-0.015-0.011l-0.204-0.175l-0.029-0.024L78.761,90.865c-0.88,0.62-1.778,1.209-2.687,1.765 c-1.233,0.755-2.51,1.466-3.813,2.115c-6.699,3.342-14.269,5.222-22.272,5.222v0.007h-0.016v-0.007 c-13.799-0.004-26.296-5.601-35.338-14.645C5.605,76.291,0.016,63.805,0.007,50.021H0v-0.033v-0.016h0.007 c0.004-13.799,5.601-26.296,14.645-35.338C23.683,5.608,36.167,0.016,49.955,0.007V0H49.988L49.988,0z M50.004,11.21v0.007h-0.016 h-0.033V11.21c-10.686,0.007-20.372,4.35-27.384,11.359C15.56,29.578,11.213,39.274,11.21,49.973h0.007v0.016v0.033H11.21 c0.007,10.686,4.347,20.367,11.359,27.381c7.009,7.012,16.705,11.359,27.403,11.361v-0.007h0.016h0.033v0.007 c10.686-0.007,20.368-4.348,27.382-11.359c7.011-7.009,11.358-16.702,11.36-27.4h-0.006v-0.016v-0.033h0.006 c-0.006-10.686-4.35-20.372-11.358-27.384C70.396,15.56,60.703,11.213,50.004,11.21L50.004,11.21z"/></g></svg>

changedetectionio/templates/watch-overview.html

@@ -6,7 +6,7 @@
 
 <div class="box">
 
-    <form class="pure-form" action="{{ url_for('form_quick_watch_add') }}" method="POST" id="new-watch-form">
+    <form class="pure-form" action="{{ url_for('form_quick_watch_add', tag=active_tag_uuid) }}" method="POST" id="new-watch-form">
         <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
         <fieldset>
             <legend>Add a new change detection watch</legend>
@@ -78,8 +78,8 @@
              {% if any_has_restock_price_processor %}
                 <th>Restock &amp; Price</th>
              {% endif %}
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_checked' else 'inactive' }}" href="{{url_for('index', sort='last_checked', order=link_order, tag=active_tag_uuid)}}">Last Checked <span class='arrow {{link_order}}'></span></a></th>
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_changed' else 'inactive' }}" href="{{url_for('index', sort='last_changed', order=link_order, tag=active_tag_uuid)}}">Last Changed <span class='arrow {{link_order}}'></span></a></th>
+                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_checked' else 'inactive' }}" href="{{url_for('index', sort='last_checked', order=link_order, tag=active_tag_uuid)}}"><span class="hide-on-mobile">Last</span> Checked <span class='arrow {{link_order}}'></span></a></th>
+                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_changed' else 'inactive' }}" href="{{url_for('index', sort='last_changed', order=link_order, tag=active_tag_uuid)}}"><span class="hide-on-mobile">Last</span> Changed <span class='arrow {{link_order}}'></span></a></th>
                 <th class="empty-cell"></th>
             </tr>
             </thead>
@@ -108,7 +108,8 @@
                     {% else %}
                     <a class="state-on" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='play.svg')}}" alt="UnPause checks" title="UnPause checks" class="icon icon-unpause" ></a>
                     {% endif %}
-                    <a class="link-mute state-{{'on' if watch.notification_muted else 'off'}}" href="{{url_for('index', op='mute', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications" class="icon icon-mute" ></a>
+                    {% set mute_label = 'UnMute notification' if watch.notification_muted else 'Mute notification' %}
+                    <a class="link-mute state-{{'on' if watch.notification_muted else 'off'}}" href="{{url_for('index', op='mute', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="{{ mute_label }}" title="{{ mute_label }}" class="icon icon-mute" ></a>
                 </td>
                 <td class="title-col inline">{{watch.title if watch.title is not none and watch.title|length > 0 else watch.url}}
                     <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}"></a>
@@ -118,7 +119,7 @@
                          or (  watch.get_fetch_backend == "system" and system_default_fetcher == 'html_webdriver'  )
                          or "extra_browser_" in watch.get_fetch_backend
                     %}
-                    <img class="status-icon" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" title="Using a Chrome browser" >
+                    <img class="status-icon" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" alt="Using a Chrome browser" title="Using a Chrome browser" >
                     {% endif %}
 
                     {%if watch.is_pdf  %}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" title="Converting PDF to text" >{% endif %}
@@ -187,13 +188,13 @@
                 <td>
                     <a {% if watch.uuid in queued_uuids %}disabled="true"{% endif %} href="{{ url_for('form_watch_checknow', uuid=watch.uuid, tag=request.args.get('tag')) }}"
                        class="recheck pure-button pure-button-primary">{% if watch.uuid in queued_uuids %}Queued{% else %}Recheck{% endif %}</a>
-                    <a href="{{ url_for('edit_page', uuid=watch.uuid)}}#general" class="pure-button pure-button-primary">Edit</a>
+                    <a href="{{ url_for('edit_page', uuid=watch.uuid, tag=active_tag_uuid)}}#general" class="pure-button pure-button-primary">Edit</a>
                     {% if watch.history_n >= 2 %}
 
                         {%  if is_unviewed %}
-                           <a href="{{ url_for('diff_history_page', uuid=watch.uuid, from_version=watch.get_next_snapshot_key_to_last_viewed) }}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">Diff</a>
+                           <a href="{{ url_for('diff_history_page', uuid=watch.uuid, from_version=watch.get_from_version_based_on_last_viewed) }}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">History</a>
                         {% else %}
-                           <a href="{{ url_for('diff_history_page', uuid=watch.uuid)}}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">Diff</a>
+                           <a href="{{ url_for('diff_history_page', uuid=watch.uuid)}}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">History</a>
                         {% endif %}
 
                     {% else %}

changedetectionio/tests/fetchers/test_custom_js_before_content.py

@@ -34,7 +34,7 @@ def test_execute_custom_js(client, live_server, measure_memory_usage):
     assert b"unpaused" in res.data
     wait_for_all_checks(client)
 
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
     assert live_server.app.config['DATASTORE'].data['watching'][uuid].history_n >= 1, "Watch history had atleast 1 (everything fetched OK)"
 
     assert b"This text should be removed" not in res.data

changedetectionio/tests/itemprop_test_examples/README.md

@@ -0,0 +1,6 @@
+# A list of real world examples!
+
+Always the price should be 666.66 for our tests
+
+see test_restock_itemprop.py::test_special_prop_examples
+

changedetectionio/tests/itemprop_test_examples/a.txt

@@ -0,0 +1,25 @@
+<div class="PriceSection PriceSection_PriceSection__Vx1_Q PriceSection_variantHuge__P9qxg PdpPriceSection"
+     data-testid="price-section"
+     data-optly-product-tile-price-section="true"><span
+        class="PriceRange ProductPrice variant-huge" itemprop="offers"
+        itemscope="" itemtype="http://schema.org/Offer"><div
+        class="VisuallyHidden_VisuallyHidden__VBD83">$155.55</div><span
+        aria-hidden="true" class="Price variant-huge" data-testid="price"
+        itemprop="price"><sup class="sup" data-testid="price-symbol"
+                              itemprop="priceCurrency" content="AUD">$</sup><span
+        class="dollars" data-testid="price-value" itemprop="price"
+        content="155.55">155.55</span><span class="extras"><span class="sup"
+                                                              data-testid="price-sup"></span></span></span></span>
+</div>
+
+<script type="application/ld+json">{
+                                "@type": "Product",
+                                "@context": "https://schema.org",
+                                "name": "test",
+                                "description": "test",
+                                "offers": {
+                                    "@type": "Offer",
+                                    "priceCurrency": "AUD",
+                                    "price": 155.55
+                                },
+                            }</script>

changedetectionio/tests/proxy_list/test_noproxy.py

@@ -48,7 +48,7 @@ def test_noproxy_option(client, live_server, measure_memory_usage):
         follow_redirects=True
     )
     assert b"Watch added in Paused state, saving will unpause" in res.data
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
     res = client.get(
         url_for("edit_page", uuid=uuid, unpause_on_save=1))
     assert b'No proxy' in res.data

changedetectionio/tests/proxy_list/test_proxy.py

@@ -16,4 +16,4 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     )
 
     assert b"1 Imported" in res.data
-    time.sleep(3)
+    wait_for_all_checks(client)

changedetectionio/tests/proxy_list/test_select_custom_proxy.py

@@ -44,7 +44,7 @@ def test_select_custom(client, live_server, measure_memory_usage):
         follow_redirects=True
     )
     # We should see something via proxy
-    assert b'<div class=""> - 0.' in res.data
+    assert b' - 0.' in res.data
 
     #
     # Now we should see the request in the container logs for "squid-squid-custom" because it will be the only default

changedetectionio/tests/proxy_socks5/test_socks5_proxy.py

@@ -1,12 +1,27 @@
 #!/usr/bin/env python3
+import json
 import os
-import time
 from flask import url_for
-from changedetectionio.tests.util import live_server_setup, wait_for_all_checks
+from changedetectionio.tests.util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
 
 
+def set_response():
+    import time
+    data = f"""<html>
+       <body>
+     <h1>Awesome, you made it</h1>
+     yeah the socks request worked
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(data)
+    time.sleep(1)
+
 def test_socks5(client, live_server, measure_memory_usage):
     live_server_setup(live_server)
+    set_response()
 
     # Setup a proxy
     res = client.post(
@@ -24,7 +39,10 @@ def test_socks5(client, live_server, measure_memory_usage):
 
     assert b"Settings updated." in res.data
 
-    test_url = "https://changedetection.io/CHANGELOG.txt?socks-test-tag=" + os.getenv('SOCKSTEST', '')
+    # Because the socks server should connect back to us
+    test_url = url_for('test_endpoint', _external=True) + f"?socks-test-tag={os.getenv('SOCKSTEST', '')}"
+    test_url = test_url.replace('localhost.localdomain', 'cdio')
+    test_url = test_url.replace('localhost', 'cdio')
 
     res = client.post(
         url_for("form_quick_watch_add"),
@@ -60,4 +78,25 @@ def test_socks5(client, live_server, measure_memory_usage):
     )
 
     # Should see the proper string
-    assert "+0200:".encode('utf-8') in res.data
+    assert "Awesome, you made it".encode('utf-8') in res.data
+
+    # PROXY CHECKER WIDGET CHECK - this needs more checking
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
+
+    res = client.get(
+        url_for("check_proxies.start_check", uuid=uuid),
+        follow_redirects=True
+    )
+    # It's probably already finished super fast :(
+    #assert b"RUNNING" in res.data
+    
+    wait_for_all_checks(client)
+    res = client.get(
+        url_for("check_proxies.get_recheck_status", uuid=uuid),
+        follow_redirects=True
+    )
+    assert b"OK" in res.data
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+

changedetectionio/tests/proxy_socks5/test_socks5_proxy_sources.py

@@ -1,16 +1,32 @@
 #!/usr/bin/env python3
 import os
-import time
 from flask import url_for
 from changedetectionio.tests.util import live_server_setup, wait_for_all_checks
 
 
+def set_response():
+    import time
+    data = f"""<html>
+       <body>
+     <h1>Awesome, you made it</h1>
+     yeah the socks request worked
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(data)
+    time.sleep(1)
+
 # should be proxies.json mounted from run_proxy_tests.sh already
 # -v `pwd`/tests/proxy_socks5/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json
 def test_socks5_from_proxiesjson_file(client, live_server, measure_memory_usage):
     live_server_setup(live_server)
-
-    test_url = "https://changedetection.io/CHANGELOG.txt?socks-test-tag=" + os.getenv('SOCKSTEST', '')
+    set_response()
+    # Because the socks server should connect back to us
+    test_url = url_for('test_endpoint', _external=True) + f"?socks-test-tag={os.getenv('SOCKSTEST', '')}"
+    test_url = test_url.replace('localhost.localdomain', 'cdio')
+    test_url = test_url.replace('localhost', 'cdio')
 
     res = client.get(url_for("settings_page"))
     assert b'name="requests-proxy" type="radio" value="socks5proxy"' in res.data
@@ -49,4 +65,4 @@ def test_socks5_from_proxiesjson_file(client, live_server, measure_memory_usage)
     )
 
     # Should see the proper string
-    assert "+0200:".encode('utf-8') in res.data
+    assert "Awesome, you made it".encode('utf-8') in res.data

changedetectionio/tests/restock/test_restock.py

@@ -2,7 +2,7 @@
 import os
 import time
 from flask import url_for
-from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client, wait_for_notification_endpoint_output
 from changedetectionio.notification import (
     default_notification_body,
     default_notification_format,
@@ -94,7 +94,7 @@ def test_restock_detection(client, live_server, measure_memory_usage):
     assert b'not-in-stock' not in res.data
 
     # We should have a notification
-    time.sleep(2)
+    wait_for_notification_endpoint_output()
     assert os.path.isfile("test-datastore/notification.txt"), "Notification received"
     os.unlink("test-datastore/notification.txt")
 
@@ -103,6 +103,7 @@ def test_restock_detection(client, live_server, measure_memory_usage):
     set_original_response()
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
+    time.sleep(5)
     assert not os.path.isfile("test-datastore/notification.txt"), "No notification should have fired when it went OUT OF STOCK by default"
 
     # BUT we should see that it correctly shows "not in stock"

changedetectionio/tests/test_add_replace_remove_filter.py

@@ -1,9 +1,9 @@
 #!/usr/bin/env python3
+
 import os.path
-import time
+
 from flask import url_for
-from .util import live_server_setup, wait_for_all_checks
-from changedetectionio import html_tools
+from .util import live_server_setup, wait_for_all_checks, wait_for_notification_endpoint_output
 
 
 def set_original(excluding=None, add_line=None):
@@ -39,9 +39,8 @@ def test_setup(client, live_server, measure_memory_usage):
     live_server_setup(live_server)
 
 def test_check_removed_line_contains_trigger(client, live_server, measure_memory_usage):
-
+    #live_server_setup(live_server)
     # Give the endpoint time to spin up
-    time.sleep(1)
     set_original()
     # Add our URL to the import page
     test_url = url_for('test_endpoint', _external=True)
@@ -78,6 +77,8 @@ def test_check_removed_line_contains_trigger(client, live_server, measure_memory
 
     # The trigger line is REMOVED,  this should trigger
     set_original(excluding='The golden line')
+
+    # Check in the processor here what's going on, its triggering empty-reply and no change.
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
@@ -112,7 +113,8 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
     res = client.post(
         url_for("settings_page"),
         data={"application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
-              "application-notification_body": 'triggered text was -{{triggered_text}}- 网站监测 内容更新了',
+              # triggered_text will contain multiple lines
+              "application-notification_body": 'triggered text was -{{triggered_text}}- ### 网站监测 内容更新了 ####',
               # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
               "application-notification_urls": test_notification_url,
               "application-minutes_between_check": 180,
@@ -153,6 +155,7 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
     # A line thats not the trigger should not trigger anything
     res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
     assert b'1 watches queued for rechecking.' in res.data
+
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'unviewed' not in res.data
@@ -165,13 +168,12 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
     assert b'unviewed' in res.data
 
     # Takes a moment for apprise to fire
-    time.sleep(3)
+    wait_for_notification_endpoint_output()
     assert os.path.isfile("test-datastore/notification.txt"), "Notification fired because I can see the output file"
     with open("test-datastore/notification.txt", 'rb') as f:
         response = f.read()
-        assert b'-Oh yes please-' in response
+        assert b'-Oh yes please' in response
         assert '网站监测 内容更新了'.encode('utf-8') in response
 
-
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data

changedetectionio/tests/test_api.py

@@ -44,7 +44,6 @@ def set_modified_response():
 
     return None
 
-
 def is_valid_uuid(val):
     try:
         uuid.UUID(str(val))
@@ -56,8 +55,9 @@ def is_valid_uuid(val):
 def test_setup(client, live_server, measure_memory_usage):
     live_server_setup(live_server)
 
+
 def test_api_simple(client, live_server, measure_memory_usage):
-    #live_server_setup(live_server)
+#    live_server_setup(live_server)
 
     api_key = extract_api_key_from_UI(client)
 
@@ -129,6 +129,9 @@ def test_api_simple(client, live_server, measure_memory_usage):
     assert after_recheck_info['last_checked'] != before_recheck_info['last_checked']
     assert after_recheck_info['last_changed'] != 0
 
+    # #2877 When run in a slow fetcher like playwright etc
+    assert after_recheck_info['last_changed'] ==  after_recheck_info['last_checked']
+
     # Check history index list
     res = client.get(
         url_for("watchhistory", uuid=watch_uuid),

changedetectionio/tests/test_automatic_follow_ldjson_price.py

@@ -99,7 +99,7 @@ def test_check_ldjson_price_autodetect(client, live_server, measure_memory_usage
     assert b'ldjson-price-track-offer' in res.data
 
     # Accept it
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
     #time.sleep(1)
     client.get(url_for('price_data_follower.accept', uuid=uuid, follow_redirects=True))
     client.get(url_for("form_watch_checknow"), follow_redirects=True)

changedetectionio/tests/test_backend.py

@@ -2,7 +2,6 @@
 
 import time
 from flask import url_for
-from urllib.request import urlopen
 from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, extract_rss_token_from_UI, \
     extract_UUID_from_client
 
@@ -69,7 +68,7 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
 
     wait_for_all_checks(client)
 
-    uuid = extract_UUID_from_client(client)
+    uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
 
     # Check the 'get latest snapshot works'
     res = client.get(url_for("watch_get_latest_html", uuid=uuid))

changedetectionio/tests/test_backup.py

@@ -26,8 +26,24 @@ def test_backup(client, live_server, measure_memory_usage):
     assert b"1 Imported" in res.data
     wait_for_all_checks(client)
 
+    # Launch the thread in the background to create the backup
     res = client.get(
-        url_for("get_backup"),
+        url_for("backups.request_backup"),
+        follow_redirects=True
+    )
+    time.sleep(2)
+
+    res = client.get(
+        url_for("backups.index"),
+        follow_redirects=True
+    )
+    # Can see the download link to the backup
+    assert b'<a href="/backups/download/changedetection-backup-20' in res.data
+    assert b'Remove backups' in res.data
+
+    # Get the latest one
+    res = client.get(
+        url_for("backups.download_backup", filename="latest"),
         follow_redirects=True
     )
 
@@ -44,3 +60,11 @@ def test_backup(client, live_server, measure_memory_usage):
 
     # Should be two txt files in the archive (history and the snapshot)
     assert len(newlist) == 2
+
+    # Get the latest one
+    res = client.get(
+        url_for("backups.remove_backups"),
+        follow_redirects=True
+    )
+
+    assert b'No backups found.' in res.data

changedetectionio/tests/test_block_while_text_present.py

@@ -65,11 +65,8 @@ def test_check_block_changedetection_text_NOT_present(client, live_server, measu
     live_server_setup(live_server)
     # Use a mix of case in ZzZ to prove it works case-insensitive.
     ignore_text = "out of stoCk\r\nfoobar"
-
     set_original_ignore_response()
 
-    # Give the endpoint time to spin up
-    time.sleep(1)
 
     # Add our URL to the import page
     test_url = url_for('test_endpoint', _external=True)
@@ -127,13 +124,24 @@ def test_check_block_changedetection_text_NOT_present(client, live_server, measu
     assert b'unviewed' not in res.data
     assert b'/test-endpoint' in res.data
 
+    # 2548
+    # Going back to the ORIGINAL should NOT trigger a change
+    set_original_ignore_response()
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
 
-    # Now we set a change where the text is gone, it should now trigger
+
+    # Now we set a change where the text is gone AND its different content, it should now trigger
     set_modified_response_minus_block_text()
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
 
+
+
+
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data