Fix tuple

.github/test/Dockerfile-alpine

@@ -1,31 +0,0 @@
-# Taken from https://github.com/linuxserver/docker-changedetection.io/blob/main/Dockerfile
-# 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:3.16
-ENV PYTHONUNBUFFERED=1
-
-COPY requirements.txt /requirements.txt
-
-RUN \
-  apk add --update --no-cache --virtual=build-dependencies \
-    cargo \
-    g++ \
-    gcc \
-    libc-dev \
-    libffi-dev \
-    libxslt-dev \
-    make \
-    openssl-dev \
-    py3-wheel \
-    python3-dev \
-    zlib-dev && \
-  apk add --update --no-cache \
-    libxslt \
-    python3 \
-    py3-pip && \
-  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-3.16/ -r /requirements.txt && \
-  apk del --purge \
-    build-dependencies

.github/workflows/test-container-build.yml

@@ -1,66 +0,0 @@
-name: ChangeDetection.io Container Build Test
-
-# Triggers the workflow on push or pull request events
-
-# This line doesnt work, even tho it is the documented one
-#on: [push, pull_request]
-
-on:
-  push:
-    paths:
-      - requirements.txt
-      - Dockerfile
-
-  pull_request:
-    paths:
-      - requirements.txt
-      - Dockerfile
-
-  # Changes to requirements.txt packages and Dockerfile may or may not always be compatible with arm etc, so worth testing
-  # @todo: some kind of path filter for requirements.txt and Dockerfile
-jobs:
-  test-container-build:
-    runs-on: ubuntu-latest
-    steps:
-        - uses: actions/checkout@v2
-        - name: Set up Python 3.9
-          uses: actions/setup-python@v2
-          with:
-            python-version: 3.9
-
-        # Just test that the build works, some libraries won't compile on ARM/rPi etc
-        - name: Set up QEMU
-          uses: docker/setup-qemu-action@v1
-          with:
-            image: tonistiigi/binfmt:latest
-            platforms: all
-
-        - name: Set up Docker Buildx
-          id: buildx
-          uses: docker/setup-buildx-action@v1
-          with:
-            install: true
-            version: latest
-            driver-opts: image=moby/buildkit:master
-
-        # https://github.com/dgtlmoon/changedetection.io/pull/1067
-        # Check we can still build under alpine/musl
-        - name: Test that the docker containers can build (musl via alpine check)
-          id: docker_build_musl
-          uses: docker/build-push-action@v2
-          with:
-            context: ./
-            file: ./.github/test/Dockerfile-alpine
-            platforms: linux/amd64,linux/arm64
-
-        - name: Test that the docker containers can build
-          id: docker_build
-          uses: docker/build-push-action@v2
-          # https://github.com/docker/build-push-action#customizing
-          with:
-            context: ./
-            file: ./Dockerfile
-            platforms: linux/arm/v7,linux/arm/v6,linux/amd64,linux/arm64,
-            cache-from: type=local,src=/tmp/.buildx-cache
-            cache-to: type=local,dest=/tmp/.buildx-cache
-

.github/workflows/test-only.yml

@@ -1,25 +1,28 @@
-name: ChangeDetection.io App Test
+name: ChangeDetection.io Test
 
 # Triggers the workflow on push or pull request events
 on: [push, pull_request]
 
 jobs:
-  test-application:
+  test-build:
     runs-on: ubuntu-latest
     steps:
+
       - uses: actions/checkout@v2
       - name: Set up Python 3.9
         uses: actions/setup-python@v2
         with:
           python-version: 3.9
 
+      - name: Show env vars
+        run: set
+
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
           pip install flake8 pytest
           if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
           if [ -f requirements-dev.txt ]; then pip install -r requirements-dev.txt; fi
-
       - name: Lint with flake8
         run: |
           # stop the build if there are Python syntax errors or undefined names
@@ -36,4 +39,7 @@ jobs:
           # Each test is totally isolated and performs its own cleanup/reset
           cd changedetectionio; ./run_all_tests.sh
 
+      # https://github.com/docker/build-push-action/blob/master/docs/advanced/test-before-push.md ?
+      # https://github.com/docker/buildx/issues/59 ? Needs to be one platform?
 
+      # https://github.com/docker/buildx/issues/495#issuecomment-918925854

CONTRIBUTING.md

@@ -6,7 +6,7 @@ Otherwise, it's always best to PR into the `dev` branch.
 
 Please be sure that all new functionality has a matching test!
 
-Use `pytest` to validate/test, you can run the existing tests as `pytest tests/test_notification.py` for example
+Use `pytest` to validate/test, you can run the existing tests as `pytest tests/test_notifications.py` for example
 
 ```
 pip3 install -r requirements-dev

Dockerfile

@@ -5,14 +5,13 @@ FROM python:3.8-slim as builder
 ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    g++ \
+    libssl-dev \
+    libffi-dev \
     gcc \
     libc-dev \
-    libffi-dev \
-    libssl-dev \
     libxslt-dev \
-    make \
+    zlib1g-dev \
-    zlib1g-dev
+    g++
 
 RUN mkdir /install
 WORKDIR /install
@@ -23,7 +22,6 @@ RUN pip install --target=/dependencies -r /requirements.txt
 
 # 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~=1.26 \
     || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
 
@@ -60,7 +58,6 @@ EXPOSE 5000
 
 # The actual flask app
 COPY changedetectionio /app/changedetectionio
-
 # The eventlet server wrapper
 COPY changedetection.py /app/changedetection.py
 

MANIFEST.in

@@ -2,7 +2,6 @@ recursive-include changedetectionio/api *
 recursive-include changedetectionio/templates *
 recursive-include changedetectionio/static *
 recursive-include changedetectionio/model *
-recursive-include changedetectionio/tests *
 include changedetection.py
 global-exclude *.pyc
 global-exclude node_modules

README.md

@@ -1,7 +1,6 @@
 ## Web Site Change Detection, Monitoring and Notification.
 
-_Live your data-life pro-actively, Detect website changes and perform meaningful actions, trigger notifications via Discord, Email, Slack, Telegram, API calls and many more._
+Live your data-life pro-actively, track website content changes and receive notifications via Discord, Email, Slack, Telegram and 70+ more
-
 
 [<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start?src=github)
 
@@ -9,6 +8,8 @@ _Live your data-life pro-actively, Detect website changes and perform meaningful
 
 ![changedetection.io](https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master)
 
+Know when important content changes, we support notifications via Discord, Telegram, Home-Assistant, Slack, Email and 70+ more
+
 [**Don't have time? Let us host it for you! try our $6.99/month subscription - use our proxies and support!**](https://lemonade.changedetection.io/start) , _half the price of other website change monitoring services and comes with unlimited watches & checks!_
 
 - Chrome browser included.
@@ -120,8 +121,8 @@ See the wiki for more information https://github.com/dgtlmoon/changedetection.io
 
 
 ## Filters
+XPath, JSONPath, jq, and CSS support comes baked in! You can be as specific as you need, use XPath exported from various XPath element query creation tools.
 
-XPath, JSONPath, jq, and CSS support comes baked in! You can be as specific as you need, use XPath exported from various XPath element query creation tools. 
 (We support LXML `re:test`, `re:math` and `re:replace`.)
 
 ## Notifications
@@ -160,11 +161,46 @@ This will re-parse the JSON and apply formatting to the text, making it super ea
 
 ### JSONPath or jq?
 
-For more complex parsing, filtering, and modifying of JSON data, jq is recommended due to the built-in operators and functions. Refer to the [documentation](https://stedolan.github.io/jq/manual/) for more specifc information on jq.
+For more complex parsing, filtering, and modifying of JSON data, jq is recommended due to the built-in operators and functions. Refer to the [documentation](https://stedolan.github.io/jq/manual/) for more information on jq.
 
-One big advantage of `jq` is that you can use logic in your JSON filter, such as filters to only show items that have a value greater than/less than etc.
+The example below adds the price in dollars to each item in the JSON data, and then filters to only show items that are greater than 10.
 
-See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/JSON-Selector-Filter-help for more information and examples
+#### Sample input data from API
+```
+{
+    "items": [
+        {
+           "name": "Product A",
+           "priceInCents": 2500
+        },
+        {
+           "name": "Product B",
+           "priceInCents": 500
+        },
+        {
+           "name": "Product C",
+           "priceInCents": 2000
+        }
+    ]
+}
+```
+
+#### Sample jq
+`jq:.items[] | . + { "priceInDollars": (.priceInCents / 100) } | select(.priceInDollars > 10)`
+
+#### Sample output data
+```
+{
+  "name": "Product A",
+  "priceInCents": 2500,
+  "priceInDollars": 25
+}
+{
+  "name": "Product C",
+  "priceInCents": 2000,
+  "priceInDollars": 20
+}
+```
 
 ### Parse JSON embedded in HTML!
 
@@ -180,9 +216,9 @@ When you enable a `json:` or `jq:` filter, you can even automatically extract an
 
 `json:$.price` or `jq:.price` would give `23.50`, or you can extract the whole structure
 
-## Proxy Configuration
+## Proxy configuration
 
-See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration , we also support using [BrightData proxy services where possible]( https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support)
+See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration
 
 ## Raspberry Pi support?
 

changedetectionio/__init__.py

@@ -33,7 +33,7 @@ from flask_wtf import CSRFProtect
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.39.21.1'
+__version__ = '0.39.20'
 
 datastore = None
 
@@ -194,8 +194,7 @@ def changedetection_app(config=None, datastore_o=None):
     watch_api.add_resource(api_v1.Watch, '/api/v1/watch/<string:uuid>',
                            resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
 
-    watch_api.add_resource(api_v1.SystemInfo, '/api/v1/systeminfo',
+
-                           resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
 
 
 
@@ -599,7 +598,7 @@ def changedetection_app(config=None, datastore_o=None):
                     extra_update_obj['previous_md5'] = get_current_checksum_include_ignore_text(uuid=uuid)
 
             # Reset the previous_md5 so we process a new snapshot including stripping ignore text.
-            if form.include_filters.data != datastore.data['watching'][uuid].get('include_filters', []):
+            if form.css_filter.data.strip() != datastore.data['watching'][uuid]['css_filter']:
                 if len(datastore.data['watching'][uuid].history):
                     extra_update_obj['previous_md5'] = get_current_checksum_include_ignore_text(uuid=uuid)
 
@@ -637,27 +636,20 @@ def changedetection_app(config=None, datastore_o=None):
             # Only works reliably with Playwright
             visualselector_enabled = os.getenv('PLAYWRIGHT_DRIVER_URL', False) and default['fetch_backend'] == 'html_webdriver'
 
-            # JQ is difficult to install on windows and must be manually added (outside requirements.txt)
-            jq_support = True
-            try:
-                import jq
-            except ModuleNotFoundError:
-                jq_support = False
 
             output = render_template("edit.html",
+                                     uuid=uuid,
+                                     watch=datastore.data['watching'][uuid],
+                                     form=form,
+                                     has_empty_checktime=using_default_check_time,
+                                     has_default_notification_urls=True if len(datastore.data['settings']['application']['notification_urls']) else False,
+                                     using_global_webdriver_wait=default['webdriver_delay'] is None,
                                      current_base_url=datastore.data['settings']['application']['base_url'],
                                      emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
-                                     form=form,
-                                     has_default_notification_urls=True if len(datastore.data['settings']['application']['notification_urls']) else False,
-                                     has_empty_checktime=using_default_check_time,
-                                     jq_support=jq_support,
-                                     playwright_enabled=os.getenv('PLAYWRIGHT_DRIVER_URL', False),
                                      settings_application=datastore.data['settings']['application'],
-                                     using_global_webdriver_wait=default['webdriver_delay'] is None,
-                                     uuid=uuid,
                                      visualselector_data_is_ready=visualselector_data_is_ready,
                                      visualselector_enabled=visualselector_enabled,
-                                     watch=datastore.data['watching'][uuid],
+                                     playwright_enabled=os.getenv('PLAYWRIGHT_DRIVER_URL', False)
                                      )
 
         return output
@@ -817,10 +809,8 @@ def changedetection_app(config=None, datastore_o=None):
 
         newest_file = history[dates[-1]]
 
-        # Read as binary and force decode as UTF-8
-        # Windows may fail decode in python if we just use 'r' mode (chardet decode exception)
         try:
-            with open(newest_file, 'r', encoding='utf-8', errors='ignore') as f:
+            with open(newest_file, 'r') as f:
                 newest_version_file_contents = f.read()
         except Exception as e:
             newest_version_file_contents = "Unable to read {}.\n".format(newest_file)
@@ -833,7 +823,7 @@ def changedetection_app(config=None, datastore_o=None):
             previous_file = history[dates[-2]]
 
         try:
-            with open(previous_file, 'r', encoding='utf-8', errors='ignore') as f:
+            with open(previous_file, 'r') as f:
                 previous_version_file_contents = f.read()
         except Exception as e:
             previous_version_file_contents = "Unable to read {}.\n".format(previous_file)
@@ -910,7 +900,7 @@ def changedetection_app(config=None, datastore_o=None):
         timestamp = list(watch.history.keys())[-1]
         filename = watch.history[timestamp]
         try:
-            with open(filename, 'r', encoding='utf-8', errors='ignore') as f:
+            with open(filename, 'r') as f:
                 tmp = f.readlines()
 
                 # Get what needs to be highlighted
@@ -985,6 +975,9 @@ def changedetection_app(config=None, datastore_o=None):
 
         # create a ZipFile object
         backupname = "changedetection-backup-{}.zip".format(int(time.time()))
+
+        # We only care about UUIDS from the current index file
+        uuids = list(datastore.data['watching'].keys())
         backup_filepath = os.path.join(datastore_o.datastore_path, backupname)
 
         with zipfile.ZipFile(backup_filepath, "w",
@@ -1000,12 +993,12 @@ def changedetection_app(config=None, datastore_o=None):
             # 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.
+            # Add any snapshot data we find, use the full path to access the file, but make the file 'relative' in the Zip.
-            for uuid, w in datastore.data['watching'].items():
+            for txt_file_path in Path(datastore_o.datastore_path).rglob('*.txt'):
-                for f in Path(w.watch_data_dir).glob('*'):
+                parent_p = txt_file_path.parent
-                    zipObj.write(f,
+                if parent_p.name in uuids:
-                                 # Use the full path to access the file, but make the file 'relative' in the Zip.
+                    zipObj.write(txt_file_path,
-                                 arcname=os.path.join(f.parts[-2], f.parts[-1]),
+                                 arcname=str(txt_file_path).replace(datastore_o.datastore_path, ''),
                                  compress_type=zipfile.ZIP_DEFLATED,
                                  compresslevel=8)
 
@@ -1307,8 +1300,8 @@ def changedetection_app(config=None, datastore_o=None):
 
     threading.Thread(target=notification_runner).start()
 
-    # Check for new release version, but not when running in test/build or pytest
+    # Check for new release version, but not when running in test/build
-    if not os.getenv("GITHUB_REF", False) and not config.get('disable_checkver') == True:
+    if not os.getenv("GITHUB_REF", False):
         threading.Thread(target=check_for_new_version).start()
 
     return app

changedetectionio/api/api_v1.py

@@ -122,37 +122,3 @@ class CreateWatch(Resource):
             return {'status': "OK"}, 200
 
         return list, 200
-
-class SystemInfo(Resource):
-    def __init__(self, **kwargs):
-        # datastore is a black box dependency
-        self.datastore = kwargs['datastore']
-        self.update_q = kwargs['update_q']
-
-    @auth.check_token
-    def get(self):
-        import time
-        overdue_watches = []
-
-        # Check all watches and report which have not been checked but should have been
-
-        for uuid, watch in self.datastore.data.get('watching', {}).items():
-            # see if now - last_checked is greater than the time that should have been
-            # this is not super accurate (maybe they just edited it) but better than nothing
-            t = watch.threshold_seconds()
-            if not t:
-                # Use the system wide default
-                t = self.datastore.threshold_seconds
-
-            time_since_check = time.time() - watch.get('last_checked')
-
-            # Allow 5 minutes of grace time before we decide it's overdue
-            if time_since_check - (5 * 60) > t:
-                overdue_watches.append(uuid)
-
-        return {
-                   'queue_size': self.update_q.qsize(),
-                   'overdue_watches': overdue_watches,
-                   'uptime': round(time.time() - self.datastore.start_time, 2),
-                   'watch_count': len(self.datastore.data.get('watching', {}))
-               }, 200

changedetectionio/changedetection.py

@@ -102,14 +102,6 @@ def main():
                     has_password=datastore.data['settings']['application']['password'] != False
                     )
 
-    # 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 os.getenv("HIDE_REFERER", False):
-            response.headers["Referrer-Policy"] = "no-referrer"
-        return response
-
     # Proxy sub-directory support
     # Set environment var USE_X_SETTINGS=1 on this script
     # And then in your proxy_pass settings

changedetectionio/content_fetcher.py

@@ -164,16 +164,16 @@ class Fetcher():
                 }
 
 
-                // inject the current one set in the include_filters, which may be a CSS rule
+                // inject the current one set in the css_filter, which may be a CSS rule
                 // used for displaying the current one in VisualSelector, where its not one we generated.
-                if (include_filters.length) {
+                if (css_filter.length) {
                    q=false;                   
                    try {
                        // is it xpath?
-                       if (include_filters.startsWith('/') || include_filters.startsWith('xpath:')) {
+                       if (css_filter.startsWith('/') || css_filter.startsWith('xpath:')) {
-                         q=document.evaluate(include_filters.replace('xpath:',''), document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
+                         q=document.evaluate(css_filter.replace('xpath:',''), document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
                        } else {
-                         q=document.querySelector(include_filters);
+                         q=document.querySelector(css_filter);
                        }                       
                    } catch (e) {
                     // Maybe catch DOMException and alert? 
@@ -186,7 +186,7 @@ class Fetcher():
                                    
                    if (bbox && bbox['width'] >0 && bbox['height']>0) {                       
                        size_pos.push({
-                           xpath: include_filters,
+                           xpath: css_filter,
                            width: bbox['width'], 
                            height: bbox['height'],
                            left: bbox['left'],
@@ -220,7 +220,7 @@ class Fetcher():
             request_body,
             request_method,
             ignore_status_codes=False,
-            current_include_filters=None):
+            current_css_filter=None):
         # Should set self.error, self.status_code and self.content
         pass
 
@@ -310,7 +310,7 @@ class base_html_playwright(Fetcher):
             request_body,
             request_method,
             ignore_status_codes=False,
-            current_include_filters=None):
+            current_css_filter=None):
 
         from playwright.sync_api import sync_playwright
         import playwright._impl._api_types
@@ -413,10 +413,10 @@ class base_html_playwright(Fetcher):
             self.status_code = response.status
             self.headers = response.all_headers()
 
-            if current_include_filters is not None:
+            if current_css_filter is not None:
-                page.evaluate("var include_filters={}".format(json.dumps(current_include_filters)))
+                page.evaluate("var css_filter={}".format(json.dumps(current_css_filter)))
             else:
-                page.evaluate("var include_filters=''")
+                page.evaluate("var css_filter=''")
 
             self.xpath_data = page.evaluate("async () => {" + self.xpath_element_js + "}")
 
@@ -497,7 +497,7 @@ class base_html_webdriver(Fetcher):
             request_body,
             request_method,
             ignore_status_codes=False,
-            current_include_filters=None):
+            current_css_filter=None):
 
         from selenium import webdriver
         from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
@@ -573,7 +573,7 @@ class html_requests(Fetcher):
             request_body,
             request_method,
             ignore_status_codes=False,
-            current_include_filters=None):
+            current_css_filter=None):
 
         # Make requests use a more modern looking user-agent
         if not 'User-Agent' in request_headers:

changedetectionio/fetch_site_status.py

@@ -10,11 +10,6 @@ from changedetectionio import content_fetcher, html_tools
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
 
-class FilterNotFoundInResponse(ValueError):
-    def __init__(self, msg):
-        ValueError.__init__(self, msg)
-
-
 # Some common stuff here that can be moved to a base class
 # (set_proxy_from_list)
 class perform_site_check():
@@ -38,20 +33,18 @@ class perform_site_check():
 
         return regex
 
+
     def run(self, uuid):
-        from copy import deepcopy
         changed_detected = False
         screenshot = False  # as bytes
         stripped_text_from_html = ""
 
-        # DeepCopy so we can be sure we don't accidently change anything by reference
+        watch = self.datastore.data['watching'].get(uuid)
-        watch = deepcopy(self.datastore.data['watching'].get(uuid))
-
         if not watch:
             return
 
         # Protect against file:// access
-        if re.search(r'^file', watch.get('url', ''), re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
+        if re.search(r'^file', watch['url'], re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
             raise Exception(
                 "file:// type access is denied for security reasons."
             )
@@ -59,10 +52,10 @@ class perform_site_check():
         # Unset any existing notification error
         update_obj = {'last_notification_error': False, 'last_error': False}
 
-        extra_headers = watch.get('headers', [])
+        extra_headers =self.datastore.data['watching'][uuid].get('headers')
 
         # Tweak the base config with the per-watch ones
-        request_headers = deepcopy(self.datastore.data['settings']['headers'])
+        request_headers = self.datastore.data['settings']['headers'].copy()
         request_headers.update(extra_headers)
 
         # https://github.com/psf/requests/issues/4525
@@ -72,9 +65,7 @@ class perform_site_check():
             request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
 
         timeout = self.datastore.data['settings']['requests'].get('timeout')
-
+        url = watch.get('url')
-        url = watch.link
-
         request_body = self.datastore.data['watching'][uuid].get('body')
         request_method = self.datastore.data['watching'][uuid].get('method')
         ignore_status_codes = self.datastore.data['watching'][uuid].get('ignore_status_codes', False)
@@ -86,7 +77,7 @@ class perform_site_check():
             is_source = True
 
         # Pluggable content fetcher
-        prefer_backend = watch.get('fetch_backend')
+        prefer_backend = watch['fetch_backend']
         if hasattr(content_fetcher, prefer_backend):
             klass = getattr(content_fetcher, prefer_backend)
         else:
@@ -97,21 +88,21 @@ class perform_site_check():
         proxy_url = None
         if proxy_id:
             proxy_url = self.datastore.proxy_list.get(proxy_id).get('url')
-            print("UUID {} Using proxy {}".format(uuid, proxy_url))
+            print ("UUID {} Using proxy {}".format(uuid, proxy_url))
 
         fetcher = klass(proxy_override=proxy_url)
 
         # Configurable per-watch or global extra delay before extracting text (for webDriver types)
         system_webdriver_delay = self.datastore.data['settings']['application'].get('webdriver_delay', None)
         if watch['webdriver_delay'] is not None:
-            fetcher.render_extract_delay = watch.get('webdriver_delay')
+            fetcher.render_extract_delay = watch['webdriver_delay']
         elif system_webdriver_delay is not None:
             fetcher.render_extract_delay = system_webdriver_delay
 
-        if watch.get('webdriver_js_execute_code') is not None and watch.get('webdriver_js_execute_code').strip():
+        if watch['webdriver_js_execute_code'] is not None and watch['webdriver_js_execute_code'].strip():
-            fetcher.webdriver_js_execute_code = watch.get('webdriver_js_execute_code')
+            fetcher.webdriver_js_execute_code = watch['webdriver_js_execute_code']
 
-        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch.get('include_filters'))
+        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch['css_filter'])
         fetcher.quit()
 
         self.screenshot = fetcher.screenshot
@@ -135,30 +126,28 @@ class perform_site_check():
             is_html = False
             is_json = False
 
-        include_filters_rule = watch.get('include_filters', [])
+        css_filter_rule = watch['css_filter']
-        # include_filters_rule = watch['include_filters']
         subtractive_selectors = watch.get(
             "subtractive_selectors", []
         ) + self.datastore.data["settings"]["application"].get(
             "global_subtractive_selectors", []
         )
 
-        has_filter_rule = include_filters_rule and len("".join(include_filters_rule).strip())
+        has_filter_rule = css_filter_rule and len(css_filter_rule.strip())
         has_subtractive_selectors = subtractive_selectors and len(subtractive_selectors[0].strip())
 
         if is_json and not has_filter_rule:
-            include_filters_rule.append("json:$")
+            css_filter_rule = "json:$"
             has_filter_rule = True
 
         if has_filter_rule:
             json_filter_prefixes = ['json:', 'jq:']
-            for filter in include_filters_rule:
+            if any(prefix in css_filter_rule for prefix in json_filter_prefixes):
-                if any(prefix in filter for prefix in json_filter_prefixes):
+                stripped_text_from_html = html_tools.extract_json_as_string(content=fetcher.content, json_filter=css_filter_rule)
-                    stripped_text_from_html += html_tools.extract_json_as_string(content=fetcher.content, json_filter=filter)
+                is_html = False
-                    is_html = False
 
         if is_html or is_source:
-
+            
             # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
             fetcher.content = html_tools.workarounds_for_obfuscations(fetcher.content)
             html_content = fetcher.content
@@ -170,36 +159,33 @@ class perform_site_check():
             else:
                 # Then we assume HTML
                 if has_filter_rule:
-                    html_content = ""
+                    # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
-                    for filter_rule in include_filters_rule:
+                    if css_filter_rule[0] == '/' or css_filter_rule.startswith('xpath:'):
-                        # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
+                        html_content = html_tools.xpath_filter(xpath_filter=css_filter_rule.replace('xpath:', ''),
-                        if filter_rule[0] == '/' or filter_rule.startswith('xpath:'):
+                                                               html_content=fetcher.content)
-                            html_content += html_tools.xpath_filter(xpath_filter=filter_rule.replace('xpath:', ''),
+                    else:
-                                                                    html_content=fetcher.content,
+                        # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
-                                                                    append_pretty_line_formatting=not is_source)
+                        html_content = html_tools.css_filter(css_filter=css_filter_rule, html_content=fetcher.content)
-                        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=fetcher.content,
-                                                                       append_pretty_line_formatting=not is_source)
-
-                    if not html_content.strip():
-                        raise FilterNotFoundInResponse(include_filters_rule)
 
                 if has_subtractive_selectors:
                     html_content = html_tools.element_removal(subtractive_selectors, html_content)
 
-                if is_source:
+                if not is_source:
-                    stripped_text_from_html = html_content
-                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,
-                            render_anchor_tag_content=do_anchor
+                            render_anchor_tag_content=self.datastore.data["settings"][
+                                "application"].get(
+                                "render_anchor_tag_content", False)
                         )
 
+                elif is_source:
+                    stripped_text_from_html = html_content
+
+            # Re #340 - return the content before the 'ignore text' was applied
+            text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
+
         # Re #340 - return the content before the 'ignore text' was applied
         text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
 
@@ -232,7 +218,7 @@ class perform_site_check():
 
                 for l in result:
                     if type(l) is tuple:
-                        # @todo - some formatter option default (between groups)
+                        #@todo - some formatter option default (between groups)
                         regex_matched_output += list(l) + [b'\n']
                     else:
                         # @todo - some formatter option default (between each ungrouped result)
@@ -246,6 +232,7 @@ class perform_site_check():
                 stripped_text_from_html = b''.join(regex_matched_output)
                 text_content_before_ignored_filter = stripped_text_from_html
 
+
         # 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()
@@ -255,30 +242,29 @@ class perform_site_check():
         ############ Blocking rules, after checksum #################
         blocked = False
 
-        trigger_text = watch.get('trigger_text', [])
+        if len(watch['trigger_text']):
-        if len(trigger_text):
             # Assume blocked
             blocked = True
             # Filter and trigger works the same, so reuse it
             # It should return the line numbers that match
             result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
-                                                  wordlist=trigger_text,
+                                                  wordlist=watch['trigger_text'],
                                                   mode="line numbers")
             # Unblock if the trigger was found
             if result:
                 blocked = False
 
-        text_should_not_be_present = watch.get('text_should_not_be_present', [])
+
-        if len(text_should_not_be_present):
+        if len(watch['text_should_not_be_present']):
             # If anything matched, then we should block a change from happening
             result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
-                                                  wordlist=text_should_not_be_present,
+                                                  wordlist=watch['text_should_not_be_present'],
                                                   mode="line numbers")
             if result:
                 blocked = True
 
         # The main thing that all this at the moment comes down to :)
-        if watch.get('previous_md5') != fetched_md5:
+        if watch['previous_md5'] != fetched_md5:
             changed_detected = True
 
         # Looks like something changed, but did it match all the rules?
@@ -287,7 +273,7 @@ class perform_site_check():
 
         # Extract title as title
         if is_html:
-            if self.datastore.data['settings']['application'].get('extract_title_as_title') or watch['extract_title_as_title']:
+            if self.datastore.data['settings']['application']['extract_title_as_title'] or watch['extract_title_as_title']:
                 if not watch['title'] or not len(watch['title']):
                     update_obj['title'] = html_tools.extract_element(find='title', html_content=fetcher.content)
 

changedetectionio/forms.py

@@ -303,16 +303,12 @@ class ValidateCSSJSONXPATHInput(object):
 
                 # Re #265 - maybe in the future fetch the page and offer a
                 # warning/notice that its possible the rule doesnt yet match anything?
+
+            if 'jq:' in line:
                 if not self.allow_json:
                     raise ValidationError("jq not permitted in this field!")
 
-            if 'jq:' in line:
+                import jq
-                try:
-                    import jq
-                except ModuleNotFoundError:
-                    # `jq` requires full compilation in windows and so isn't generally available
-                    raise ValidationError("jq not support not found")
-
                 input = line.replace('jq:', '')
 
                 try:
@@ -349,7 +345,7 @@ class watchForm(commonSettingsForm):
 
     time_between_check = FormField(TimeBetweenCheckForm)
 
-    include_filters = StringListField('CSS/JSONPath/JQ/XPath Filters', [ValidateCSSJSONXPATHInput()], default='')
+    css_filter = StringField('CSS/JSON/XPATH Filter', [ValidateCSSJSONXPATHInput()], default='')
 
     subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
 

changedetectionio/html_tools.py

@@ -1,36 +1,33 @@
+import json
+from typing import List
 
 from bs4 import BeautifulSoup
+from jsonpath_ng.ext import parse
+import jq
+import re
 from inscriptis import get_text
 from inscriptis.model.config import ParserConfig
-from jsonpath_ng.ext import parse
-from typing import List
-import json
-import re
 
-# HTML added to be sure each result matching a filter (.example) gets converted to a new line by Inscriptis
+class FilterNotFoundInResponse(ValueError):
-TEXT_FILTER_LIST_LINE_SUFFIX = "<br/>"
+    def __init__(self, msg):
+        ValueError.__init__(self, msg)
 
 class JSONNotFound(ValueError):
     def __init__(self, msg):
         ValueError.__init__(self, msg)
-        
+
+
 # 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):
+def css_filter(css_filter, html_content):
     soup = BeautifulSoup(html_content, "html.parser")
     html_block = ""
-    r = soup.select(include_filters, separator="")
+    r = soup.select(css_filter, separator="")
+    if len(html_content) > 0 and len(r) == 0:
+        raise FilterNotFoundInResponse(css_filter)
+    for item in r:
+        html_block += str(item)
 
-    for element in r:
+    return html_block + "\n"
-        # When there's more than 1 match, then add the suffix to separate each line
-        # And where the matched result doesn't include something that will cause Inscriptis to add a newline
-        # (This way each 'match' reliably has a new-line in the diff)
-        # Divs are converted to 4 whitespaces by inscriptis
-        if append_pretty_line_formatting and len(html_block) and not element.name in (['br', 'hr', 'div', 'p']):
-            html_block += TEXT_FILTER_LIST_LINE_SUFFIX
-
-        html_block += str(element)
-
-    return html_block
 
 def subtractive_css_selector(css_selector, html_content):
     soup = BeautifulSoup(html_content, "html.parser")
@@ -46,29 +43,25 @@ def element_removal(selectors: List[str], html_content):
 
 
 # Return str Utf-8 of matched rules
-def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False):
+def xpath_filter(xpath_filter, html_content):
     from lxml import etree, html
 
     tree = html.fromstring(bytes(html_content, encoding='utf-8'))
     html_block = ""
 
     r = tree.xpath(xpath_filter.strip(), namespaces={'re': 'http://exslt.org/regular-expressions'})
+    if len(html_content) > 0 and len(r) == 0:
+        raise FilterNotFoundInResponse(xpath_filter)
+
     #@note: //title/text() wont work where <title>CDATA..
 
     for element in r:
-        # When there's more than 1 match, then add the suffix to separate each line
-        # And where the matched result doesn't include something that will cause Inscriptis to add a newline
-        # (This way each 'match' reliably has a new-line in the diff)
-        # Divs are converted to 4 whitespaces by inscriptis
-        if append_pretty_line_formatting and len(html_block) and (not hasattr( element, 'tag' ) or not element.tag in (['br', 'hr', 'div', 'p'])):
-            html_block += TEXT_FILTER_LIST_LINE_SUFFIX
-
         if type(element) == etree._ElementStringResult:
-            html_block += str(element)
+            html_block += str(element) + "<br/>"
         elif type(element) == etree._ElementUnicodeResult:
-            html_block += str(element)
+            html_block += str(element) + "<br/>"
         else:
-            html_block += etree.tostring(element, pretty_print=True).decode('utf-8')
+            html_block += etree.tostring(element, pretty_print=True).decode('utf-8') + "<br/>"
 
     return html_block
 
@@ -92,18 +85,9 @@ def _parse_json(json_data, json_filter):
         jsonpath_expression = parse(json_filter.replace('json:', ''))
         match = jsonpath_expression.find(json_data)
         return _get_stripped_text_from_json_match(match)
-
     if 'jq:' in json_filter:
-
-        try:
-            import jq
-        except ModuleNotFoundError:
-            # `jq` requires full compilation in windows and so isn't generally available
-            raise Exception("jq not support not found")
-
         jq_expression = jq.compile(json_filter.replace('jq:', ''))
         match = jq_expression.input(json_data).all()
-
         return _get_stripped_text_from_json_match(match)
 
 def _get_stripped_text_from_json_match(match):

changedetectionio/importer.py

@@ -103,12 +103,12 @@ class import_distill_io_json(Importer):
                     pass
                 except IndexError:
                     pass
-                extras['include_filters'] = []
+
                 try:
+                    extras['css_filter'] = d_config['selections'][0]['frames'][0]['includes'][0]['expr']
                     if d_config['selections'][0]['frames'][0]['includes'][0]['type'] == 'xpath':
-                        extras['include_filters'].append('xpath:' + d_config['selections'][0]['frames'][0]['includes'][0]['expr'])
+                        extras['css_filter'] = 'xpath:' + extras['css_filter']
-                    else:
+
-                        extras['include_filters'].append(d_config['selections'][0]['frames'][0]['includes'][0]['expr'])
                 except KeyError:
                     pass
                 except IndexError:

changedetectionio/model/Watch.py

@@ -1,8 +1,6 @@
-from distutils.util import strtobool
-import logging
 import os
-import time
+import uuid as uuid_builder
-import uuid
+from distutils.util import strtobool
 
 minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 60))
 mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
@@ -16,43 +14,42 @@ class model(dict):
     __newest_history_key = None
     __history_n=0
     __base_config = {
-            #'history': {},  # Dict of timestamp and output stripped filename (removed)
+            'url': None,
-            #'newest_history_key': 0, (removed, taken from history.txt index)
+            'tag': None,
-            'body': None,
-            'check_unique_lines': False, # On change-detected, compare against all history if its something new
-            'check_count': 0,
-            'consecutive_filter_failures': 0, # Every time the CSS/xPath filter cannot be located, reset when all is fine.
-            'extract_text': [],  # Extract text by regex after filters
-            'extract_title_as_title': False,
-            'fetch_backend': None,
-            'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
-            'headers': {},  # Extra headers to send
-            'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
-            'include_filters': [],
             'last_checked': 0,
-            'last_error': False,
+            'paused': False,
             'last_viewed': 0,  # history key value of the last viewed via the [diff] link
+            #'newest_history_key': 0,
+            'title': None,
+            'previous_md5': False,
+            'uuid': str(uuid_builder.uuid4()),
+            'headers': {},  # Extra headers to send
+            'body': None,
             'method': 'GET',
-             # Custom notification content
+            #'history': {},  # Dict of timestamp and output stripped filename
+            'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
+            # Custom notification content
+            'notification_urls': [],  # List of URLs to add to the notification Queue (Usually AppRise)
+            'notification_title': None,
             'notification_body': None,
             'notification_format': default_notification_format_for_watch,
             'notification_muted': False,
-            'notification_title': None,
+            'css_filter': '',
-            'notification_urls': [],  # List of URLs to add to the notification Queue (Usually AppRise)
+            'last_error': False,
-            'paused': False,
+            'extract_text': [],  # Extract text by regex after filters
-            'previous_md5': False,
-            'proxy': None, # Preferred proxy connection
             'subtractive_selectors': [],
-            'tag': None,
+            'trigger_text': [],  # List of text or regex to wait for until a change is detected
             'text_should_not_be_present': [], # Text that should not present
+            'fetch_backend': None,
+            'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
+            'consecutive_filter_failures': 0, # Every time the CSS/xPath filter cannot be located, reset when all is fine.
+            'extract_title_as_title': False,
+            'check_unique_lines': False, # On change-detected, compare against all history if its something new
+            'proxy': None, # Preferred proxy connection
             # Re #110, so then if this is set to None, we know to use the default value instead
             # Requires setting to None on submit if it's the same as the default
             # Should be all None by default, so we use the system default in this case.
             'time_between_check': {'weeks': None, 'days': None, 'hours': None, 'minutes': None, 'seconds': None},
-            'title': None,
-            'trigger_text': [],  # List of text or regex to wait for until a change is detected
-            'url': None,
-            'uuid': str(uuid.uuid4()),
             'webdriver_delay': None,
             'webdriver_js_execute_code': None, # Run before change-detection
         }
@@ -63,7 +60,7 @@ class model(dict):
         self.update(self.__base_config)
         self.__datastore_path = kw['datastore_path']
 
-        self['uuid'] = str(uuid.uuid4())
+        self['uuid'] = str(uuid_builder.uuid4())
 
         del kw['datastore_path']
 
@@ -85,19 +82,10 @@ class model(dict):
         return False
 
     def ensure_data_dir_exists(self):
-        if not os.path.isdir(self.watch_data_dir):
+        target_path = os.path.join(self.__datastore_path, self['uuid'])
-            print ("> Creating data dir {}".format(self.watch_data_dir))
+        if not os.path.isdir(target_path):
-            os.mkdir(self.watch_data_dir)
+            print ("> Creating data dir {}".format(target_path))
-
+            os.mkdir(target_path)
-    @property
-    def link(self):
-        url = self.get('url', '')
-        if '{%' in url or '{{' in url:
-            from jinja2 import Environment
-            # Jinja2 available in URLs along with https://pypi.org/project/jinja2-time/
-            jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
-            return str(jinja2_env.from_string(url).render())
-        return url
 
     @property
     def label(self):
@@ -121,40 +109,16 @@ class model(dict):
 
     @property
     def history(self):
-        """History index is just a text file as a list
-            {watch-uuid}/history.txt
-
-            contains a list like
-
-            {epoch-time},{filename}\n
-
-            We read in this list as the history information
-
-        """
         tmp_history = {}
+        import logging
+        import time
 
         # Read the history file as a dict
-        fname = os.path.join(self.watch_data_dir, "history.txt")
+        fname = os.path.join(self.__datastore_path, self.get('uuid'), "history.txt")
         if os.path.isfile(fname):
             logging.debug("Reading history index " + str(time.time()))
             with open(fname, "r") as f:
-                for i in f.readlines():
+                tmp_history = dict(i.strip().split(',', 2) 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(self.watch_data_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(self.watch_data_dir, snapshot_fname)
-                            if not os.path.exists(v) and os.path.exists(proposed_new_path):
-                                v = proposed_new_path
-
-                        tmp_history[k] = v
 
         if len(tmp_history):
             self.__newest_history_key = list(tmp_history.keys())[-1]
@@ -165,7 +129,7 @@ class model(dict):
 
     @property
     def has_history(self):
-        fname = os.path.join(self.watch_data_dir, "history.txt")
+        fname = os.path.join(self.__datastore_path, self.get('uuid'), "history.txt")
         return os.path.isfile(fname)
 
     # Returns the newest key, but if theres only 1 record, then it's counted as not being new, so return 0.
@@ -184,33 +148,31 @@ class model(dict):
     # 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):
+        import uuid
+        import logging
+
+        output_path = "{}/{}".format(self.__datastore_path, self['uuid'])
 
         self.ensure_data_dir_exists()
 
-        # Small hack so that we sleep just enough to allow 1 second  between history snapshots
+        snapshot_fname = "{}/{}.stripped.txt".format(output_path, uuid.uuid4())
-        # this is because history.txt indexes/keys snapshots by epoch seconds and we dont want dupe keys
+        logging.debug("Saving history text {}".format(snapshot_fname))
-        if self.__newest_history_key and int(timestamp) == int(self.__newest_history_key):
-            time.sleep(timestamp - self.__newest_history_key)
 
-        snapshot_fname = "{}.txt".format(str(uuid.uuid4()))
+        with open(snapshot_fname, 'wb') as f:
-
-        # in /diff/ and /preview/ we are going to assume for now that it's UTF-8 when reading
-        # most sites are utf-8 and some are even broken utf-8
-        with open(os.path.join(self.watch_data_dir, snapshot_fname), 'wb') as f:
             f.write(contents)
             f.close()
 
         # Append to index
         # @todo check last char was \n
-        index_fname = os.path.join(self.watch_data_dir, "history.txt")
+        index_fname = "{}/history.txt".format(output_path)
         with open(index_fname, 'a') as f:
             f.write("{},{}\n".format(timestamp, snapshot_fname))
             f.close()
 
         self.__newest_history_key = timestamp
-        self.__history_n += 1
+        self.__history_n+=1
 
-        # @todo bump static cache of the last timestamp so we dont need to examine the file to set a proper ''viewed'' status
+        #@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
@@ -243,14 +205,14 @@ class model(dict):
         return not local_lines.issubset(existing_history)
 
     def get_screenshot(self):
-        fname = os.path.join(self.watch_data_dir, "last-screenshot.png")
+        fname = os.path.join(self.__datastore_path, self['uuid'], "last-screenshot.png")
         if os.path.isfile(fname):
             return fname
 
         return False
 
     def __get_file_ctime(self, filename):
-        fname = os.path.join(self.watch_data_dir, filename)
+        fname = os.path.join(self.__datastore_path, self['uuid'], filename)
         if os.path.isfile(fname):
             return int(os.path.getmtime(fname))
         return False
@@ -275,14 +237,9 @@ class model(dict):
     def snapshot_error_screenshot_ctime(self):
         return self.__get_file_ctime('last-error-screenshot.png')
 
-    @property
-    def watch_data_dir(self):
-        # The base dir of the watch data
-        return os.path.join(self.__datastore_path, self['uuid'])
-    
     def get_error_text(self):
         """Return the text saved from a previous request that resulted in a non-200 error"""
-        fname = os.path.join(self.watch_data_dir, "last-error.txt")
+        fname = os.path.join(self.__datastore_path, self['uuid'], "last-error.txt")
         if os.path.isfile(fname):
             with open(fname, 'r') as f:
                 return f.read()
@@ -290,7 +247,7 @@ class model(dict):
 
     def get_error_snapshot(self):
         """Return path to the screenshot that resulted in a non-200 error"""
-        fname = os.path.join(self.watch_data_dir, "last-error-screenshot.png")
+        fname = os.path.join(self.__datastore_path, self['uuid'], "last-error-screenshot.png")
         if os.path.isfile(fname):
             return fname
         return False

changedetectionio/run_all_tests.sh

@@ -9,8 +9,6 @@
 # exit when any command fails
 set -e
 
-SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
-
 find tests/test_*py -type f|while read test_name
 do
   echo "TEST RUNNING $test_name"
@@ -24,6 +22,7 @@ echo "RUNNING WITH BASE_URL SET"
 export BASE_URL="https://really-unique-domain.io"
 pytest tests/test_notification.py
 
+
 # Now for the selenium and playwright/browserless fetchers
 # Note - this is not UI functional tests - just checking that each one can fetch the content
 
@@ -39,9 +38,7 @@ docker kill $$-test_selenium
 
 echo "TESTING WEBDRIVER FETCH > PLAYWRIGHT/BROWSERLESS..."
 # Not all platforms support playwright (not ARM/rPI), so it's not packaged in requirements.txt
-PLAYWRIGHT_VERSION=$(grep -i -E "RUN pip install.+" "$SCRIPT_DIR/../Dockerfile" | grep --only-matching -i -E "playwright[=><~+]+[0-9\.]+")
+pip3 install playwright~=1.24
-echo "using $PLAYWRIGHT_VERSION"
-pip3 install "$PLAYWRIGHT_VERSION"
 docker run -d --name $$-test_browserless -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm  -p 3000:3000  --shm-size="2g"  browserless/chrome:1.53-chrome-stable
 # takes a while to spin up
 sleep 5

changedetectionio/static/js/visual-selector.js

@@ -50,7 +50,7 @@ $(document).ready(function() {
         state_clicked=false;
         ctx.clearRect(0, 0, c.width, c.height);
         xctx.clearRect(0, 0, c.width, c.height);
-        $("#include_filters").val('');
+        $("#css_filter").val('');
     });
 
 
@@ -68,7 +68,7 @@ $(document).ready(function() {
                xctx = c.getContext("2d");
                 // redline highlight context
                ctx = c.getContext("2d");
-               current_default_xpath =$("#include_filters").val();
+               current_default_xpath =$("#css_filter").val();
                fetch_data();
                $('#selector-canvas').off("mousemove mousedown");
                // screenshot_url defined in the edit.html template
@@ -205,9 +205,9 @@ $(document).ready(function() {
         var sel = selector_data['size_pos'][current_selected_i];
         if (sel[0] == '/') {
         // @todo - not sure just checking / is right
-            $("#include_filters").val('xpath:'+sel.xpath);
+            $("#css_filter").val('xpath:'+sel.xpath);
         } else {
-            $("#include_filters").val(sel.xpath);
+            $("#css_filter").val(sel.xpath);
         }
         xctx.fillStyle = 'rgba(205,205,205,0.95)';
         xctx.strokeStyle = 'rgba(225,0,0,0.9)';

changedetectionio/static/styles/styles.scss

@@ -156,7 +156,7 @@ body:after, body:before {
 
 .fetch-error {
   padding-top: 1em;
-  font-size: 80%;
+  font-size: 60%;
   max-width: 400px;
   display: block;
 }
@@ -803,4 +803,4 @@ ul {
   padding: 0.5rem;
   border-radius: 5px;
   color: #ff3300;
-}
+}

changedetectionio/store.py

@@ -27,18 +27,17 @@ class ChangeDetectionStore:
     # For when we edit, we should write to disk
     needs_write_urgent = False
 
-    __version_check = True
-
     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.needs_write = False
         self.datastore_path = datastore_path
         self.json_store_path = "{}/url-watches.json".format(self.datastore_path)
-        self.needs_write = False
         self.proxy_list = None
-        self.start_time = time.time()
         self.stop_thread = False
+
+        self.__data = App.model()
+
         # 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={}))
@@ -82,13 +81,8 @@ class ChangeDetectionStore:
         except (FileNotFoundError, json.decoder.JSONDecodeError):
             if include_default_watches:
                 print("Creating JSON store at", self.datastore_path)
-                self.add_watch(url='https://news.ycombinator.com/',
+                self.add_watch(url='https://news.ycombinator.com/', tag='Tech news')
-                               tag='Tech news',
+                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'})
 
         self.__data['version_tag'] = version_tag
 
@@ -272,7 +266,7 @@ class ChangeDetectionStore:
             extras = {}
         # should always be str
         if tag is None or not tag:
-            tag = ''
+            tag=''
 
         # Incase these are copied across, assume it's a reference and deepcopy()
         apply_extras = deepcopy(extras)
@@ -287,31 +281,17 @@ class ChangeDetectionStore:
                 res = r.json()
 
                 # List of permissible attributes we accept from the wild internet
-                for k in [
+                for k in ['url', 'tag',
-                    'body',
+                          'paused', 'title',
-                    'css_filter',
+                          'previous_md5', 'headers',
-                    'extract_text',
+                          'body', 'method',
-                    'extract_title_as_title',
+                          'ignore_text', 'css_filter',
-                    'headers',
+                          'subtractive_selectors', 'trigger_text',
-                    'ignore_text',
+                          'extract_title_as_title', 'extract_text',
-                    'include_filters',
+                          'text_should_not_be_present',
-                    'method',
+                          'webdriver_js_execute_code']:
-                    'paused',
-                    'previous_md5',
-                    'subtractive_selectors',
-                    'tag',
-                    'text_should_not_be_present',
-                    'title',
-                    'trigger_text',
-                    'webdriver_js_execute_code',
-                    'url',
-                ]:
                     if res.get(k):
-                        if k != 'css_filter':
+                        apply_extras[k] = res[k]
-                            apply_extras[k] = res[k]
-                        else:
-                            # We renamed the field and made it a list
-                            apply_extras['include_filters'] = [res['css_filter']]
 
             except Exception as e:
                 logging.error("Error fetching metadata for shared watch link", url, str(e))
@@ -334,13 +314,12 @@ class ChangeDetectionStore:
                     del apply_extras[k]
 
             new_watch.update(apply_extras)
-            self.__data['watching'][new_uuid] = new_watch
+            self.__data['watching'][new_uuid]=new_watch
 
         self.__data['watching'][new_uuid].ensure_data_dir_exists()
 
         if write_to_disk_now:
             self.sync_to_json()
-
         return new_uuid
 
     def visualselector_data_is_ready(self, watch_uuid):
@@ -604,14 +583,3 @@ class ChangeDetectionStore:
         for v in ['User-Agent', 'Accept', 'Accept-Encoding', 'Accept-Language']:
             if self.data['settings']['headers'].get(v):
                 del self.data['settings']['headers'][v]
-
-    # Convert filters to a list of filters css_filter -> include_filters
-    def update_8(self):
-        for uuid, watch in self.data['watching'].items():
-            try:
-                existing_filter = watch.get('css_filter', '')
-                if existing_filter:
-                    watch['include_filters'] = [existing_filter]
-            except:
-                continue
-        return

changedetectionio/templates/edit.html

@@ -40,8 +40,7 @@
                 <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">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>
-                        <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>
                     <div class="pure-control-group">
                         {{ render_field(form.title, class="m-d") }}
@@ -174,27 +173,21 @@ User-Agent: wonderbra 1.0") }}
                         </div>
                     </fieldset>
                     <div class="pure-control-group">
-                        {% set field = render_field(form.include_filters,
+                        {% set field = render_field(form.css_filter,
-                            rows=5,
+                            placeholder=".class-name or #some-id, or other CSS selector rule.",
-                            placeholder="#example
-xpath://body/div/span[contains(@class, 'example-class')]",
                             class="m-d")
                         %}
                         {{ field }}
                         {% 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/>
+                        <span class="pure-form-message-inline">
                     <ul>
                         <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).
+                        <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>.
                             <ul>
                                 <li>JSONPath: Prefix with <code>json:</code>, use <code>json:$</code> to force re-formatting if required,  <a href="https://jsonpath.com/" target="new">test your JSONPath here</a>.</li>
-                                {% if jq_support %}
                                 <li>jq: Prefix with <code>jq:</code> and <a href="https://jqplay.org/" target="new">test your jq here</a>. Using <a href="https://stedolan.github.io/jq/" target="new">jq</a> allows for complex filtering and processing of JSON data with built-in functions, regex, filtering, and more. See examples and documentation <a href="https://stedolan.github.io/jq/manual/" target="new">here</a>.</li>
-                                {% else %}
-                                <li>jq support not installed</li>
-                                {% endif %}
                             </ul>
                         </li>
                         <li>XPath - Limit text to this XPath rule, simply start with a forward-slash,
@@ -205,7 +198,7 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                             </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
+                    Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath, or jq selector 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/>
                 </span>
                     </div>

changedetectionio/templates/watch-overview.html

@@ -87,7 +87,7 @@
                     <a class="state-{{'on' if watch.notification_muted}}" href="{{url_for('index', op='mute', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications"/></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>
+                    <a class="external" target="_blank" rel="noopener" href="{{ watch.url.replace('source:','') }}"></a>
                     <a href="{{url_for('form_share_put_watch', uuid=watch.uuid)}}"><img style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread.svg')}}" /></a>
 
                     {%if watch.fetch_backend == "html_webdriver" %}<img style="height: 1em; display:inline-block;" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" />{% endif %}

changedetectionio/tests/conftest.py

@@ -41,7 +41,7 @@ def app(request):
 
     cleanup(datastore_path)
 
-    app_config = {'datastore_path': datastore_path, 'disable_checkver' : True}
+    app_config = {'datastore_path': datastore_path}
     cleanup(app_config['datastore_path'])
     datastore = store.ChangeDetectionStore(datastore_path=app_config['datastore_path'], include_default_watches=False)
     app = changedetection_app(app_config, datastore)

changedetectionio/tests/proxy_list/test_multiple_proxy.py

@@ -24,7 +24,7 @@ def test_preferred_proxy(client, live_server):
     res = client.post(
         url_for("edit_page", uuid="first"),
         data={
-                "include_filters": "",
+                "css_filter": "",
                 "fetch_backend": "html_requests",
                 "headers": "",
                 "proxy": "proxy-two",

changedetectionio/tests/test_api.py

@@ -147,16 +147,6 @@ def test_api_simple(client, live_server):
     # @todo how to handle None/default global values?
     assert watch['history_n'] == 2, "Found replacement history section, which is in its own API"
 
-    # basic systeminfo check
-    res = client.get(
-        url_for("systeminfo"),
-        headers={'x-api-key': api_key},
-    )
-    info = json.loads(res.data)
-    assert info.get('watch_count') == 1
-    assert info.get('uptime') > 0.5
-
-
     # Finally delete the watch
     res = client.delete(
         url_for("watch", uuid=watch_uuid),

changedetectionio/tests/test_auth.py

@@ -23,7 +23,7 @@ def test_basic_auth(client, live_server):
     # Check form validation
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": "", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"css_filter": "", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data

changedetectionio/tests/test_backend.py

@@ -3,7 +3,7 @@
 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
+from .util import set_original_response, set_modified_response, live_server_setup
 
 sleep_time_for_fetch_thread = 3
 
@@ -36,7 +36,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
         client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
         # Give the thread time to pick it up
-        wait_for_all_checks(client)
+        time.sleep(sleep_time_for_fetch_thread)
 
         # It should report nothing found (no new 'unviewed' class)
         res = client.get(url_for("index"))
@@ -69,7 +69,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
     res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
     assert b'1 watches are queued for rechecking.' in res.data
 
-    wait_for_all_checks(client)
+    time.sleep(sleep_time_for_fetch_thread)
 
     # Now something should be ready, indicated by having a 'unviewed' class
     res = client.get(url_for("index"))
@@ -98,14 +98,14 @@ def test_check_basic_change_detection_functionality(client, live_server):
     assert b'which has this one new line' in res.data
     assert b'Which is across multiple lines' not in res.data
 
-    wait_for_all_checks(client)
+    time.sleep(2)
 
     # Do this a few times.. ensures we dont accidently set the status
     for n in range(2):
         client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
         # Give the thread time to pick it up
-        wait_for_all_checks(client)
+        time.sleep(sleep_time_for_fetch_thread)
 
         # It should report nothing found (no new 'unviewed' class)
         res = client.get(url_for("index"))
@@ -125,7 +125,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
     )
 
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    wait_for_all_checks(client)
+    time.sleep(sleep_time_for_fetch_thread)
 
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data

changedetectionio/tests/test_backup.py

@@ -1,31 +1,18 @@
 #!/usr/bin/python3
 
-from .util import set_original_response, set_modified_response, live_server_setup
+import time
 from flask import url_for
 from urllib.request import urlopen
-from zipfile import ZipFile
+from . util import set_original_response, set_modified_response, live_server_setup
-import re
-import time
 
 
 def test_backup(client, live_server):
-    live_server_setup(live_server)
 
-    set_original_response()
+    live_server_setup(live_server)
 
     # Give the endpoint time to spin up
     time.sleep(1)
 
-    # Add our URL to the import page
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": url_for('test_endpoint', _external=True)},
-        follow_redirects=True
-    )
-
-    assert b"1 Imported" in res.data
-    time.sleep(3)
-
     res = client.get(
         url_for("get_backup"),
         follow_redirects=True
@@ -33,19 +20,6 @@ def test_backup(client, live_server):
 
     # Should get the right zip content type
     assert res.content_type == "application/zip"
-
     # Should be PK/ZIP stream
     assert res.data.count(b'PK') >= 2
 
-    # ZipFile from buffer seems non-obvious, just save it instead
-    with open("download.zip", 'wb') as f:
-        f.write(res.data)
-
-    zip = ZipFile('download.zip')
-    l = zip.namelist()
-    uuid4hex = re.compile('^[a-f0-9]{8}-?[a-f0-9]{4}-?4[a-f0-9]{3}-?[89ab][a-f0-9]{3}-?[a-f0-9]{12}.*txt', re.I)
-    newlist = list(filter(uuid4hex.match, l))  # Read Note below
-
-    # Should be two txt files in the archive (history and the snapshot)
-    assert len(newlist) == 2
-

changedetectionio/tests/test_css_selector.py

@@ -46,23 +46,22 @@ def set_modified_response():
 
 
 # Test that the CSS extraction works how we expect, important here is the right placing of new lines \n's
-def test_include_filters_output():
+def test_css_filter_output():
+    from changedetectionio import fetch_site_status
     from inscriptis import get_text
 
     # Check text with sub-parts renders correctly
     content = """<html> <body><div id="thingthing" >  Some really <b>bold</b> text  </div> </body> </html>"""
-    html_blob = include_filters(include_filters="#thingthing", html_content=content)
+    html_blob = css_filter(css_filter="#thingthing", html_content=content)
     text = get_text(html_blob)
     assert text == "  Some really bold text"
 
     content = """<html> <body>
     <p>foo bar blah</p>
-    <DIV class="parts">Block A</DiV> <div class="parts">Block B</DIV></body> 
+    <div class="parts">Block A</div> <div class="parts">Block B</div></body> 
     </html>
 """
-
+    html_blob = css_filter(css_filter=".parts", html_content=content)
-    # in xPath this would be //*[@class='parts']
-    html_blob = include_filters(include_filters=".parts", html_content=content)
     text = get_text(html_blob)
 
     # Divs are converted to 4 whitespaces by inscriptis
@@ -70,10 +69,10 @@ def test_include_filters_output():
 
 
 # Tests the whole stack works with the CSS Filter
-def test_check_markup_include_filters_restriction(client, live_server):
+def test_check_markup_css_filter_restriction(client, live_server):
     sleep_time_for_fetch_thread = 3
 
-    include_filters = "#sametext"
+    css_filter = "#sametext"
 
     set_original_response()
 
@@ -99,7 +98,7 @@ def test_check_markup_include_filters_restriction(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": include_filters, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"css_filter": css_filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -108,7 +107,7 @@ def test_check_markup_include_filters_restriction(client, live_server):
     res = client.get(
         url_for("edit_page", uuid="first"),
     )
-    assert bytes(include_filters.encode('utf-8')) in res.data
+    assert bytes(css_filter.encode('utf-8')) in res.data
 
     # Trigger a check
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
@@ -127,58 +126,3 @@ def test_check_markup_include_filters_restriction(client, live_server):
     # Because it should be looking at only that 'sametext' id
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
-
-
-# Tests the whole stack works with the CSS Filter
-def test_check_multiple_filters(client, live_server):
-    sleep_time_for_fetch_thread = 3
-
-    include_filters = "#blob-a\r\nxpath://*[contains(@id,'blob-b')]"
-
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write("""<html><body>
-     <div id="blob-a">Blob A</div>
-     <div id="blob-b">Blob B</div>
-     <div id="blob-c">Blob C</div>
-     </body>
-     </html>
-    """)
-
-    # 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)
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-    assert b"1 Imported" in res.data
-    time.sleep(1)
-
-    # Goto the edit page, add our ignore text
-    # Add our URL to the import page
-    res = client.post(
-        url_for("edit_page", uuid="first"),
-        data={"include_filters": include_filters,
-              "url": test_url,
-              "tag": "",
-              "headers": "",
-              'fetch_backend': "html_requests"},
-        follow_redirects=True
-    )
-    assert b"Updated watch." in res.data
-
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
-
-    res = client.get(
-        url_for("preview_page", uuid="first"),
-        follow_redirects=True
-    )
-
-    # Only the two blobs should be here
-    assert b"Blob A" in res.data # CSS was ok
-    assert b"Blob B" in res.data # xPath was ok
-    assert b"Blob C" not in res.data # Should not be included

changedetectionio/tests/test_extract_regex.py

@@ -88,7 +88,7 @@ def test_check_filter_multiline(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": '',
+        data={"css_filter": '',
               'extract_text': '/something.+?6 billion.+?lines/si',
               "url": test_url,
               "tag": "",
@@ -116,7 +116,7 @@ def test_check_filter_multiline(client, live_server):
 
 def test_check_filter_and_regex_extract(client, live_server):
     sleep_time_for_fetch_thread = 3
-    include_filters = ".changetext"
+    css_filter = ".changetext"
 
     set_original_response()
 
@@ -143,7 +143,7 @@ def test_check_filter_and_regex_extract(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": include_filters,
+        data={"css_filter": css_filter,
               'extract_text': '\d+ online\r\n\d+ guests\r\n/somecase insensitive \d+/i\r\n/somecase insensitive (345\d)/i',
               "url": test_url,
               "tag": "",

changedetectionio/tests/test_filter_exist_changes.py

@@ -92,7 +92,7 @@ def test_filter_doesnt_exist_then_exists_should_get_notification(client, live_se
         "tag": "my tag",
         "title": "my title",
         "headers": "",
-        "include_filters": '.ticket-available',
+        "css_filter": '.ticket-available',
         "fetch_backend": "html_requests"})
 
     res = client.post(

changedetectionio/tests/test_filter_failure_notification.py

@@ -76,7 +76,7 @@ def run_filter_test(client, content_filter):
         "title": "my title",
         "headers": "",
         "filter_failure_notification_send": 'y',
-        "include_filters": content_filter,
+        "css_filter": content_filter,
         "fetch_backend": "html_requests"})
 
     res = client.post(
@@ -95,7 +95,7 @@ def run_filter_test(client, content_filter):
         time.sleep(3)
 
     # We should see something in the frontend
-    assert b'Warning, no filters were found' in res.data
+    assert b'Warning, filter' in res.data
 
     # Now it should exist and contain our "filter not found" alert
     assert os.path.isfile("test-datastore/notification.txt")
@@ -131,7 +131,7 @@ def run_filter_test(client, content_filter):
 def test_setup(live_server):
     live_server_setup(live_server)
 
-def test_check_include_filters_failure_notification(client, live_server):
+def test_check_css_filter_failure_notification(client, live_server):
     set_original_response()
     time.sleep(1)
     run_filter_test(client, '#nope-doesnt-exist')

changedetectionio/tests/test_jinja2.py

@@ -1,33 +0,0 @@
-#!/usr/bin/python3
-
-import time
-from flask import url_for
-from .util import live_server_setup
-
-
-# If there was only a change in the whitespacing, then we shouldnt have a change detected
-def test_jinja2_in_url_query(client, live_server):
-    live_server_setup(live_server)
-
-    # Give the endpoint time to spin up
-    time.sleep(1)
-
-    # Add our URL to the import page
-    test_url = url_for('test_return_query', _external=True)
-
-    # because url_for() will URL-encode the var, but we dont here
-    full_url = "{}?{}".format(test_url,
-                              "date={% now 'Europe/Berlin', '%Y' %}.{% now 'Europe/Berlin', '%m' %}.{% now 'Europe/Berlin', '%d' %}", )
-    res = client.post(
-        url_for("form_quick_watch_add"),
-        data={"url": full_url, "tag": "test"},
-        follow_redirects=True
-    )
-    assert b"Watch added" in res.data
-    time.sleep(3)
-    # It should report nothing found (no new 'unviewed' class)
-    res = client.get(
-        url_for("preview_page", uuid="first"),
-        follow_redirects=True
-    )
-    assert b'date=2' in res.data

changedetectionio/tests/test_jsonpath_jq_selector.py

@@ -5,12 +5,7 @@ import time
 from flask import url_for, escape
 from . util import live_server_setup
 import pytest
-jq_support = True
 
-try:
-    import jq
-except ModuleNotFoundError:
-    jq_support = False
 
 def test_setup(live_server):
     live_server_setup(live_server)
@@ -45,24 +40,22 @@ and it can also be repeated
     assert text == "23.5"
 
     # also check for jq
-    if jq_support:
+    text = html_tools.extract_json_as_string(content, "jq:.offers.price")
-        text = html_tools.extract_json_as_string(content, "jq:.offers.price")
+    assert text == "23.5"
-        assert text == "23.5"
-
-        text = html_tools.extract_json_as_string('{"id":5}', "jq:.id")
-        assert text == "5"
 
     text = html_tools.extract_json_as_string('{"id":5}', "json:$.id")
     assert text == "5"
 
+    text = html_tools.extract_json_as_string('{"id":5}', "jq:.id")
+    assert text == "5"
+
     # When nothing at all is found, it should throw JSONNOTFound
     # Which is caught and shown to the user in the watch-overview table
     with pytest.raises(html_tools.JSONNotFound) as e_info:
         html_tools.extract_json_as_string('COMPLETE GIBBERISH, NO JSON!', "json:$.id")
 
-    if jq_support:
+    with pytest.raises(html_tools.JSONNotFound) as e_info:
-        with pytest.raises(html_tools.JSONNotFound) as e_info:
+        html_tools.extract_json_as_string('COMPLETE GIBBERISH, NO JSON!', "jq:.id")
-            html_tools.extract_json_as_string('COMPLETE GIBBERISH, NO JSON!', "jq:.id")
 
 def set_original_ext_response():
     data = """
@@ -132,7 +125,7 @@ def set_original_response():
     return None
 
 
-def set_json_response_with_html():
+def set_response_with_html():
     test_return_data = """
     {
       "test": [
@@ -176,7 +169,7 @@ def set_modified_response():
 def test_check_json_without_filter(client, live_server):
     # Request a JSON document from a application/json source containing HTML
     # and be sure it doesn't get chewed up by instriptis
-    set_json_response_with_html()
+    set_response_with_html()
 
     # Give the endpoint time to spin up
     time.sleep(1)
@@ -189,6 +182,9 @@ def test_check_json_without_filter(client, live_server):
         follow_redirects=True
     )
 
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
     # Give the thread time to pick it up
     time.sleep(3)
 
@@ -197,7 +193,6 @@ def test_check_json_without_filter(client, live_server):
         follow_redirects=True
     )
 
-    # Should still see '"html": "<b>"'
     assert b'&#34;&lt;b&gt;' in res.data
     assert res.data.count(b'{\n') >= 2
 
@@ -219,6 +214,9 @@ def check_json_filter(json_filter, client, live_server):
     )
     assert b"1 Imported" in res.data
 
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
     # Give the thread time to pick it up
     time.sleep(3)
 
@@ -226,7 +224,7 @@ def check_json_filter(json_filter, client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": json_filter,
+        data={"css_filter": json_filter,
               "url": test_url,
               "tag": "",
               "headers": "",
@@ -242,6 +240,9 @@ def check_json_filter(json_filter, client, live_server):
     )
     assert bytes(escape(json_filter).encode('utf-8')) in res.data
 
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
     # Give the thread time to pick it up
     time.sleep(3)
     #  Make a change
@@ -270,8 +271,7 @@ def test_check_jsonpath_filter(client, live_server):
     check_json_filter('json:boss.name', client, live_server)
 
 def test_check_jq_filter(client, live_server):
-    if jq_support:
+    check_json_filter('jq:.boss.name', client, live_server)
-        check_json_filter('jq:.boss.name', client, live_server)
 
 def check_json_filter_bool_val(json_filter, client, live_server):
     set_original_response()
@@ -293,7 +293,7 @@ def check_json_filter_bool_val(json_filter, client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": json_filter,
+        data={"css_filter": json_filter,
               "url": test_url,
               "tag": "",
               "headers": "",
@@ -303,6 +303,11 @@ def check_json_filter_bool_val(json_filter, client, live_server):
     )
     assert b"Updated watch." in res.data
 
+    time.sleep(3)
+
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
     # Give the thread time to pick it up
     time.sleep(3)
     #  Make a change
@@ -324,8 +329,7 @@ def test_check_jsonpath_filter_bool_val(client, live_server):
     check_json_filter_bool_val("json:$['available']", client, live_server)
 
 def test_check_jq_filter_bool_val(client, live_server):
-    if jq_support:
+    check_json_filter_bool_val("jq:.available", client, live_server)
-        check_json_filter_bool_val("jq:.available", client, live_server)
 
 # Re #265 - Extended JSON selector test
 # Stuff to consider here
@@ -347,6 +351,9 @@ def check_json_ext_filter(json_filter, client, live_server):
     )
     assert b"1 Imported" in res.data
 
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
     # Give the thread time to pick it up
     time.sleep(3)
 
@@ -354,7 +361,7 @@ def check_json_ext_filter(json_filter, client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": json_filter,
+        data={"css_filter": json_filter,
               "url": test_url,
               "tag": "",
               "headers": "",
@@ -370,6 +377,9 @@ def check_json_ext_filter(json_filter, client, live_server):
     )
     assert bytes(escape(json_filter).encode('utf-8')) in res.data
 
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
     # Give the thread time to pick it up
     time.sleep(3)
     #  Make a change
@@ -398,5 +408,4 @@ def test_check_jsonpath_ext_filter(client, live_server):
     check_json_ext_filter('json:$[?(@.status==Sold)]', client, live_server)
 
 def test_check_jq_ext_filter(client, live_server):
-    if jq_support:
+    check_json_ext_filter('jq:.[] | select(.status | contains("Sold"))', client, live_server)
-        check_json_ext_filter('jq:.[] | select(.status | contains("Sold"))', client, live_server)

changedetectionio/tests/test_share_watch.py

@@ -14,7 +14,7 @@ def test_share_watch(client, live_server):
     live_server_setup(live_server)
 
     test_url = url_for('test_endpoint', _external=True)
-    include_filters = ".nice-filter"
+    css_filter = ".nice-filter"
 
     # Add our URL to the import page
     res = client.post(
@@ -29,7 +29,7 @@ def test_share_watch(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": include_filters, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"css_filter": css_filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -37,7 +37,7 @@ def test_share_watch(client, live_server):
     res = client.get(
         url_for("edit_page", uuid="first"),
     )
-    assert bytes(include_filters.encode('utf-8')) in res.data
+    assert bytes(css_filter.encode('utf-8')) in res.data
 
     # click share the link
     res = client.get(
@@ -73,8 +73,4 @@ def test_share_watch(client, live_server):
     res = client.get(
         url_for("edit_page", uuid="first"),
     )
-    assert bytes(include_filters.encode('utf-8')) in res.data
+    assert bytes(css_filter.encode('utf-8')) in res.data
-
-    # Check it saved the URL
-    res = client.get(url_for("index"))
-    assert bytes(test_url.encode('utf-8')) in res.data

changedetectionio/tests/test_source.py

@@ -57,9 +57,10 @@ def test_check_basic_change_detection_functionality_source(client, live_server):
 
 
 
-# `subtractive_selectors` should still work in `source:` type requests
+
 def test_check_ignore_elements(client, live_server):
     set_original_response()
+
     time.sleep(2)
     test_url = 'source:'+url_for('test_endpoint', _external=True)
     # Add our URL to the import page
@@ -76,9 +77,9 @@ def test_check_ignore_elements(client, live_server):
     #####################
     # We want <span> and <p> ONLY, but ignore span with .foobar-detection
 
-    client.post(
+    res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": 'span,p', "url": test_url, "tag": "", "subtractive_selectors": ".foobar-detection", 'fetch_backend': "html_requests"},
+        data={"css_filter": 'span,p', "url": test_url, "tag": "", "subtractive_selectors": ".foobar-detection", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
 
@@ -88,6 +89,7 @@ def test_check_ignore_elements(client, live_server):
         url_for("preview_page", uuid="first"),
         follow_redirects=True
     )
+
     assert b'foobar-detection' not in res.data
     assert b'&lt;br' not in res.data
     assert b'&lt;p' in res.data

changedetectionio/tests/test_trigger_regex_with_filter.py

@@ -49,7 +49,7 @@ def test_trigger_regex_functionality_with_filter(client, live_server):
         url_for("edit_page", uuid="first"),
         data={"trigger_text": "/cool.stuff/",
               "url": test_url,
-              "include_filters": '#in-here',
+              "css_filter": '#in-here',
               "fetch_backend": "html_requests"},
         follow_redirects=True
     )

changedetectionio/tests/test_watch_fields_storage.py

@@ -22,7 +22,7 @@ def test_check_watch_field_storage(client, live_server):
         url_for("edit_page", uuid="first"),
         data={ "notification_urls": "json://127.0.0.1:30000\r\njson://128.0.0.1\r\n",
                "time_between_check-minutes": 126,
-               "include_filters" : ".fooclass",
+               "css_filter" : ".fooclass",
                "title" : "My title",
                "ignore_text" : "ignore this",
                "url": test_url,

changedetectionio/tests/test_xpath_selector.py

@@ -89,7 +89,7 @@ def test_check_xpath_filter_utf8(client, live_server):
     time.sleep(1)
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"css_filter": filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -143,7 +143,7 @@ def test_check_xpath_text_function_utf8(client, live_server):
     time.sleep(1)
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"css_filter": filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -182,6 +182,9 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
     )
     assert b"1 Imported" in res.data
 
+    # Trigger a check
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+
     # Give the thread time to pick it up
     time.sleep(sleep_time_for_fetch_thread)
 
@@ -189,7 +192,7 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": xpath_filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"css_filter": xpath_filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -227,11 +230,10 @@ def test_xpath_validation(client, live_server):
         follow_redirects=True
     )
     assert b"1 Imported" in res.data
-    time.sleep(2)
 
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters": "/something horrible", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"css_filter": "/something horrible", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"is not a valid XPath expression" in res.data
@@ -240,7 +242,7 @@ def test_xpath_validation(client, live_server):
 
 
 # actually only really used by the distll.io importer, but could be handy too
-def test_check_with_prefix_include_filters(client, live_server):
+def test_check_with_prefix_css_filter(client, live_server):
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data
 
@@ -261,7 +263,7 @@ def test_check_with_prefix_include_filters(client, live_server):
 
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"include_filters":  "xpath://*[contains(@class, 'sametext')]", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        data={"css_filter":  "xpath://*[contains(@class, 'sametext')]", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
 

changedetectionio/tests/util.py

@@ -86,7 +86,6 @@ def extract_UUID_from_client(client):
 def wait_for_all_checks(client):
     # Loop waiting until done..
     attempt=0
-    time.sleep(0.1)
     while attempt < 60:
         time.sleep(1)
         res = client.get(url_for("index"))
@@ -160,10 +159,5 @@ def live_server_setup(live_server):
         ret = " ".join([auth.username, auth.password, auth.type])
         return ret
 
-    # Just return some GET var
-    @live_server.app.route('/test-return-query', methods=['GET'])
-    def test_return_query():
-        return request.query_string
-
     live_server.start()
 

changedetectionio/tests/visualselector/test_fetch_data.py

@@ -13,9 +13,9 @@ def test_visual_selector_content_ready(client, live_server):
     live_server_setup(live_server)
     time.sleep(1)
 
-    # Add our URL to the import page, because the docker container (playwright/selenium) wont be able to connect to our usual test url
+    # Add our URL to the import page, maybe better to use something we control?
-    test_url = "https://changedetection.io/ci-test/test-runjs.html"
+    # We use an external URL because the docker container is too difficult to setup to connect back to the pytest socket
-
+    test_url = 'https://news.ycombinator.com'
     res = client.post(
         url_for("form_quick_watch_add"),
         data={"url": test_url, "tag": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
@@ -25,27 +25,13 @@ def test_visual_selector_content_ready(client, live_server):
 
     res = client.post(
         url_for("edit_page", uuid="first", unpause_on_save=1),
-        data={
+        data={"css_filter": ".does-not-exist", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_webdriver"},
-              "url": test_url,
-              "tag": "",
-              "headers": "",
-              'fetch_backend': "html_webdriver",
-              'webdriver_js_execute_code': 'document.querySelector("button[name=test-button]").click();'
-        },
         follow_redirects=True
     )
     assert b"unpaused" in res.data
     time.sleep(1)
     wait_for_all_checks(client)
     uuid = extract_UUID_from_client(client)
-
-    # Check the JS execute code before extract worked
-    res = client.get(
-        url_for("preview_page", uuid="first"),
-        follow_redirects=True
-    )
-    assert b'I smell JavaScript' in res.data
-
     assert os.path.isfile(os.path.join('test-datastore', uuid, 'last-screenshot.png')), "last-screenshot.png should exist"
     assert os.path.isfile(os.path.join('test-datastore', uuid, 'elements.json')), "xpath elements.json data should exist"
 

changedetectionio/update_worker.py

@@ -4,7 +4,7 @@ import queue
 import time
 
 from changedetectionio import content_fetcher
-from changedetectionio.fetch_site_status import FilterNotFoundInResponse
+from changedetectionio.html_tools import FilterNotFoundInResponse
 
 # A single update worker
 #
@@ -91,8 +91,8 @@ class update_worker(threading.Thread):
             return
 
         n_object = {'notification_title': 'Changedetection.io - Alert - CSS/xPath filter was not present in the page',
-                    'notification_body': "Your configured CSS/xPath filters of '{}' for {{watch_url}} did not appear on the page after {} attempts, did the page change layout?\n\nLink: {{base_url}}/edit/{{watch_uuid}}\n\nThanks - Your omniscient changedetection.io installation :)\n".format(
+                    'notification_body': "Your configured CSS/xPath filter of '{}' for {{watch_url}} did not appear on the page after {} attempts, did the page change layout?\n\nLink: {{base_url}}/edit/{{watch_uuid}}\n\nThanks - Your omniscient changedetection.io installation :)\n".format(
-                        ", ".join(watch['include_filters']),
+                        watch['css_filter'],
                         threshold),
                     'notification_format': 'text'}
 
@@ -189,7 +189,7 @@ class update_worker(threading.Thread):
                         if not self.datastore.data['watching'].get(uuid):
                             continue
 
-                        err_text = "Warning, no filters were found, no change detection ran."
+                        err_text = "Warning, filter '{}' not found".format(str(e))
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            # So that we get a trigger when the content is added again
                                                                            'previous_md5': ''})
@@ -282,19 +282,16 @@ class update_worker(threading.Thread):
                             self.app.logger.error("Exception reached processing watch UUID: %s - %s", uuid, str(e))
                             self.datastore.update_watch(uuid=uuid, update_obj={'last_error': str(e)})
 
-                    if self.datastore.data['watching'].get(uuid):
-                        # Always record that we atleast tried
-                        count = self.datastore.data['watching'][uuid].get('check_count', 0) + 1
-                        self.datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - now, 3),
-                                                                           'last_checked': round(time.time()),
-                                                                           'check_count': count
-                                                                           })
 
-                        # Always save the screenshot if it's available
+                    # Always record that we atleast tried
-                        if update_handler.screenshot:
+                    self.datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - now, 3),
-                            self.datastore.save_screenshot(watch_uuid=uuid, screenshot=update_handler.screenshot)
+                                                                       'last_checked': round(time.time())})
-                        if update_handler.xpath_data:
+
-                            self.datastore.save_xpath_data(watch_uuid=uuid, data=update_handler.xpath_data)
+                    # Always save the screenshot if it's available
+                    if update_handler.screenshot:
+                        self.datastore.save_screenshot(watch_uuid=uuid, screenshot=update_handler.screenshot)
+                    if update_handler.xpath_data:
+                        self.datastore.save_xpath_data(watch_uuid=uuid, data=update_handler.xpath_data)
 
 
                 self.current_uuid = None  # Done

docker-compose.yml

@@ -45,9 +45,6 @@ services:
   #        Respect proxy_pass type settings, `proxy_set_header Host "localhost";` and `proxy_set_header X-Forwarded-Prefix /app;`
   #        More here https://github.com/dgtlmoon/changedetection.io/wiki/Running-changedetection.io-behind-a-reverse-proxy-sub-directory
   #      - USE_X_SETTINGS=1
-  #
-  #        Hides the `Referer` header so that monitored websites can't see the changedetection.io hostname.
-  #      - HIDE_REFERER=true
 
       # Comment out ports: when using behind a reverse proxy , enable networks: etc.
       ports:

requirements.txt

@@ -1,36 +1,35 @@
-flask~=2.0
+flask~= 2.0
 flask_wtf
 eventlet>=0.31.0
 validators
-timeago~=1.0
+timeago ~=1.0
-inscriptis~=2.2
+inscriptis ~= 2.2
-feedgen~=0.9
+feedgen ~= 0.9
-flask-login~=0.5
+flask-login ~= 0.5
 flask_restful
 pytz
 
 # Set these versions together to avoid a RequestsDependencyWarning
 # >= 2.26 also adds Brotli support if brotli is installed
-brotli~=1.0
+brotli ~= 1.0
-requests[socks] ~=2.28
+requests[socks] ~= 2.28
 
-urllib3>1.26
+urllib3 > 1.26
-chardet>2.3.0
+chardet > 2.3.0
 
-wtforms~=3.0
+wtforms ~= 3.0
-jsonpath-ng~=1.5.3
+jsonpath-ng ~= 1.5.3
-
+jq ~= 1.3.0
-# jq not available on Windows so must be installed manually
 
 # Notification library
-apprise~=1.1.0
+apprise ~= 1.1.0
 
 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
 paho-mqtt
 
 # Pinned version of cryptography otherwise
 # ERROR: Could not build wheels for cryptography which use PEP 517 and cannot be installed directly
-cryptography~=3.4
+cryptography ~= 3.4
 
 # Used for CSS filtering
 bs4
@@ -39,20 +38,11 @@ bs4
 lxml
 
 # 3.141 was missing socksVersion, 3.150 was not in pypi, so we try 4.1.0
-selenium~=4.1.0
+selenium ~= 4.1.0
 
 # https://stackoverflow.com/questions/71652965/importerror-cannot-import-name-safe-str-cmp-from-werkzeug-security/71653849#71653849
 # ImportError: cannot import name 'safe_str_cmp' from 'werkzeug.security'
 # need to revisit flask login versions
-werkzeug~=2.0.0
+werkzeug ~= 2.0.0
-
-# Templating, so far just in the URLs but in the future can be for the notifications also
-jinja2~=3.1
-jinja2-time
-
-# https://peps.python.org/pep-0508/#environment-markers
-# https://github.com/dgtlmoon/changedetection.io/pull/1009
-jq~=1.3 ;python_version >= "3.8" and sys_platform == "linux"
 
 # playwright is installed at Dockerfile build time because it's not available on all platforms
-