dont use fetcher when browsersteps are defined

.github/workflows/containers.yml

@@ -98,7 +98,8 @@ jobs:
           platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
           cache-from: type=local,src=/tmp/.buildx-cache
           cache-to: type=local,dest=/tmp/.buildx-cache
-          provenance: false
+# Looks like this was disabled
+#          provenance: false
 
       # A new tagged release is required, which builds :tag and :latest
       - name: Build and push :tag
@@ -117,7 +118,8 @@ jobs:
           platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
           cache-from: type=local,src=/tmp/.buildx-cache
           cache-to: type=local,dest=/tmp/.buildx-cache
-          provenance: false
+# Looks like this was disabled
+#          provenance: false
 
       - name: Image digest
         run: echo step SHA ${{ steps.vars.outputs.sha_short }} tag ${{steps.vars.outputs.tag}} branch ${{steps.vars.outputs.branch}} digest ${{ steps.docker_build.outputs.digest }}

.github/workflows/pypi.yml

@@ -1,38 +0,0 @@
-name: PyPi Test and Push tagged release
-
-# Triggers the workflow on push or pull request events
-on:
-  workflow_run:
-    workflows: ["ChangeDetection.io Test"]
-    tags: '*.*'
-    types: [completed]
-
-
-jobs:
-  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: Test that pip builds without error
-        run: |
-          pip3 --version
-          python3 -m pip install wheel
-          python3 setup.py bdist_wheel
-          python3 -m pip install dist/changedetection.io-*-none-any.whl --force
-          changedetection.io -d /tmp -p 10000 &
-          sleep 3
-          curl http://127.0.0.1:10000/static/styles/pure-min.css >/dev/null
-          killall -9 changedetection.io
-
-      # 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
-#if: ${{ github.event_name == 'release'}}

.github/workflows/test-only.yml

@@ -30,7 +30,7 @@ jobs:
 
           # Selenium+browserless
           docker run --network changedet-network -d --hostname selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome-debug:3.141.59
-          docker run --network changedet-network -d --hostname browserless -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm  -p 3000:3000  --shm-size="2g"  browserless/chrome:1.53-chrome-stable
+          docker run --network changedet-network -d --hostname browserless -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]" -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm  -p 3000:3000  --shm-size="2g"  browserless/chrome:1.53-chrome-stable
 
       - name: Build changedetection.io container for testing
         run: |         
@@ -50,10 +50,18 @@ jobs:
         run: |
           
           # Selenium fetch
-          docker run -e "WEBDRIVER_URL=http://selenium:4444/wd/hub" --network changedet-network  test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py'
+          docker run --rm -e "WEBDRIVER_URL=http://selenium:4444/wd/hub" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py'
           
           # Playwright/Browserless fetch
-          docker run -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network  test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py && pytest tests/visualselector/test_fetch_data.py'
+          docker run --rm -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py && pytest tests/visualselector/test_fetch_data.py'
+          
+          # restock detection via playwright - added name=changedet here so that playwright/browserless can connect to it
+          docker run --rm --name "changedet" -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-port=5004 --live-server-host=0.0.0.0 tests/restock/test_restock.py'
+
+      - name: Test with puppeteer fetcher and disk cache
+        run: |
+          docker run --rm -e "PUPPETEER_DISK_CACHE=/tmp/data/" -e "USE_EXPERIMENTAL_PUPPETEER_FETCH=yes" -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py && pytest tests/visualselector/test_fetch_data.py'
+          # Browserless would have had -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]" added above
 
       - name: Test proxy interaction
         run: |

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

@@ -0,0 +1,36 @@
+name: ChangeDetection.io PIP package 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]
+
+  # 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-pip-build-basics:
+    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: Test that the basic pip built package runs without error
+          run: |
+            set -e
+            mkdir dist
+            pip3 install wheel
+            python3 setup.py bdist_wheel            
+            pip3 install -r requirements.txt
+            rm ./changedetection.py
+            rm -rf changedetectio
+            
+            pip3 install dist/changedetection.io*.whl
+            changedetection.io -d /tmp -p 10000 &
+            sleep 3
+            curl http://127.0.0.1:10000/static/styles/pure-min.css >/dev/null
+            killall -9 changedetection.io

MANIFEST.in

@@ -1,6 +1,7 @@
 recursive-include changedetectionio/api *
 recursive-include changedetectionio/blueprint *
 recursive-include changedetectionio/model *
+recursive-include changedetectionio/processors *
 recursive-include changedetectionio/res *
 recursive-include changedetectionio/static *
 recursive-include changedetectionio/templates *

README.md

@@ -1,4 +1,4 @@
-## Web Site Change Detection, Monitoring and Notification.
+## Web Site Change Detection, Restock monitoring and notifications.
 
 **_Detect website content changes and perform meaningful actions - trigger notifications via Discord, Email, Slack, Telegram, API calls and many more._**
 
@@ -65,6 +65,7 @@ Requires Playwright to be enabled.
 - Get notified when certain keywords appear in Twitter search results
 - Proactively search for jobs, get notified when companies update their careers page, search job portals for keywords.
 - Get alerts when new job positions are open on Bamboo HR and other job platforms
+- Website defacement monitoring
 
 _Need an actual Chrome runner with Javascript support? We support fetching via WebDriver and Playwright!</a>_
 
@@ -102,6 +103,8 @@ $ docker run -d --restart always -p "127.0.0.1:5000:5000" -v datastore-volume:/d
 
 `:latest` tag is our latest stable release, `:dev` tag is our bleeding edge `master` branch.
 
+Alternative docker repository over at ghcr - [ghcr.io/dgtlmoon/changedetection.io](https://ghcr.io/dgtlmoon/changedetection.io)
+
 ### Windows
 
 See the install instructions at the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Microsoft-Windows

changedetectionio/__init__.py

@@ -33,10 +33,12 @@ from flask import (
     url_for,
 )
 
+from flask_paginate import Pagination, get_page_parameter
+
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.40.3'
+__version__ = '0.41.1'
 
 datastore = None
 
@@ -64,6 +66,9 @@ app.config.exit = Event()
 
 app.config['NEW_VERSION_AVAILABLE'] = False
 
+if os.getenv('FLASK_SERVER_NAME'):
+    app.config['SERVER_NAME'] = os.getenv('FLASK_SERVER_NAME')
+
 #app.config["EXPLAIN_TEMPLATE_LOADING"] = True
 
 # Disables caching of the templates
@@ -337,8 +342,6 @@ def changedetection_app(config=None, datastore_o=None):
             if len(dates) < 2:
                 continue
 
-            prev_fname = watch.history[dates[-2]]
-
             if not watch.viewed:
                 # Re #239 - GUID needs to be individual for each event
                 # @todo In the future make this a configurable link back (see work on BASE_URL https://github.com/dgtlmoon/changedetection.io/pull/228)
@@ -359,9 +362,12 @@ def changedetection_app(config=None, datastore_o=None):
 
                 watch_title = watch.get('title') if watch.get('title') else watch.get('url')
                 fe.title(title=watch_title)
-                latest_fname = watch.history[dates[-1]]
 
-                html_diff = diff.render_diff(prev_fname, latest_fname, include_equal=False, line_feed_sep="<br>")
+                html_diff = diff.render_diff(previous_version_file_contents=watch.get_history_snapshot(dates[-2]),
+                                             newest_version_file_contents=watch.get_history_snapshot(dates[-1]),
+                                             include_equal=False,
+                                             line_feed_sep="<br>")
+
                 fe.content(content="<html><body><h4>{}</h4>{}</body></html>".format(watch_title, html_diff),
                            type='CDATA')
 
@@ -415,6 +421,10 @@ def changedetection_app(config=None, datastore_o=None):
 
         existing_tags = datastore.get_all_tags()
         form = forms.quickWatchForm(request.form)
+        page = request.args.get(get_page_parameter(), type=int, default=1)
+        total_count = len(sorted_watches) if sorted_watches else len(datastore.data['watching'])
+        pagination = Pagination(page=page, total=total_count, per_page=int(os.getenv('pagination_per_page', 50)), css_framework = "semantic")
+
         output = render_template(
             "watch-overview.html",
                                  # Don't link to hosting when we're on the hosting environment
@@ -425,16 +435,28 @@ def changedetection_app(config=None, datastore_o=None):
                                  has_proxies=datastore.proxy_list,
                                  has_unviewed=datastore.has_unviewed,
                                  hosted_sticky=os.getenv("SALTED_PASS", False) == False,
+                                 pagination=pagination,
                                  queued_uuids=[q_uuid.item['uuid'] for q_uuid in update_q.queue],
+                                 sort_attribute=request.args.get('sort') if request.args.get('sort') else request.cookies.get('sort'),
+                                 sort_order=request.args.get('order') if request.args.get('order') else request.cookies.get('order'),
                                  system_default_fetcher=datastore.data['settings']['application'].get('fetch_backend'),
                                  tags=existing_tags,
                                  watches=sorted_watches
                                  )
 
-
         if session.get('share-link'):
             del(session['share-link'])
-        return output
+
+        resp = make_response(output)
+
+        # The template can run on cookie or url query info
+        if request.args.get('sort'):
+            resp.set_cookie('sort', request.args.get('sort'))
+        if request.args.get('order'):
+            resp.set_cookie('order', request.args.get('order'))
+
+        return resp
+
 
 
     # AJAX endpoint for sending a test
@@ -459,11 +481,19 @@ def changedetection_app(config=None, datastore_o=None):
 
         try:
             n_object = {'watch_url': request.form['window_url'],
-                        'notification_urls': request.form['notification_urls'].splitlines(),
-                        'notification_title': request.form['notification_title'].strip(),
-                        'notification_body': request.form['notification_body'].strip(),
-                        'notification_format': request.form['notification_format'].strip()
+                        'notification_urls': request.form['notification_urls'].splitlines()
                         }
+
+            # Only use if present, if not set in n_object it should use the default system value
+            if 'notification_format' in request.form and request.form['notification_format'].strip():
+                n_object['notification_format'] = request.form.get('notification_format', '').strip()
+
+            if 'notification_title' in request.form and request.form['notification_title'].strip():
+                n_object['notification_title'] = request.form.get('notification_title', '').strip()
+
+            if 'notification_body' in request.form and request.form['notification_body'].strip():
+                n_object['notification_body'] = request.form.get('notification_body', '').strip()
+
             notification_q.put(n_object)
         except Exception as e:
             return make_response({'error': str(e)}, 400)
@@ -511,8 +541,9 @@ def changedetection_app(config=None, datastore_o=None):
     # https://wtforms.readthedocs.io/en/3.0.x/forms/#wtforms.form.Form.populate_obj ?
 
     def edit_page(uuid):
-        from changedetectionio import forms
-        from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
+        from . import forms
+        from .blueprint.browser_steps.browser_steps import browser_step_ui_config
+        from . import processors
 
         using_default_check_time = True
         # More for testing, possible to return the first/only
@@ -527,6 +558,15 @@ def changedetection_app(config=None, datastore_o=None):
             flash("No watch with the UUID %s found." % (uuid), "error")
             return redirect(url_for('index'))
 
+        switch_processor = request.args.get('switch_processor')
+        if switch_processor:
+            for p in processors.available_processors():
+                if p[0] == switch_processor:
+                    datastore.data['watching'][uuid]['processor'] = switch_processor
+                    flash(f"Switched to mode - {p[1]}.")
+                    datastore.clear_watch_history(uuid)
+                    redirect(url_for('edit_page', uuid=uuid))
+
         # be sure we update with a copy instead of accidently editing the live object by reference
         default = deepcopy(datastore.data['watching'][uuid])
 
@@ -587,6 +627,16 @@ def changedetection_app(config=None, datastore_o=None):
             if datastore.proxy_list is not None and form.data['proxy'] == '':
                 extra_update_obj['proxy'] = None
 
+            # Unsetting all filter_text methods should make it go back to default
+            # This particularly affects tests running
+            if 'filter_text_added' in form.data and not form.data.get('filter_text_added') \
+                    and 'filter_text_replaced' in form.data and not form.data.get('filter_text_replaced') \
+                    and 'filter_text_removed' in form.data and not form.data.get('filter_text_removed'):
+                extra_update_obj['filter_text_added'] = True
+                extra_update_obj['filter_text_replaced'] = True
+                extra_update_obj['filter_text_removed'] = True
+
+
             datastore.data['watching'][uuid].update(form.data)
             datastore.data['watching'][uuid].update(extra_update_obj)
 
@@ -633,6 +683,7 @@ def changedetection_app(config=None, datastore_o=None):
             visualselector_enabled = os.getenv('PLAYWRIGHT_DRIVER_URL', False) and is_html_webdriver
 
             output = render_template("edit.html",
+                                     available_processors=processors.available_processors(),
                                      browser_steps_config=browser_step_ui_config,
                                      current_base_url=datastore.data['settings']['application']['base_url'],
                                      emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
@@ -735,6 +786,8 @@ def changedetection_app(config=None, datastore_o=None):
     @login_optionally_required
     def import_page():
         remaining_urls = []
+        from . import forms
+
         if request.method == 'POST':
             from .importer import import_url_list, import_distill_io_json
 
@@ -742,7 +795,7 @@ def changedetection_app(config=None, datastore_o=None):
             if request.values.get('urls') and len(request.values.get('urls').strip()):
                 # Import and push into the queue for immediate update check
                 importer = import_url_list()
-                importer.run(data=request.values.get('urls'), flash=flash, datastore=datastore)
+                importer.run(data=request.values.get('urls'), flash=flash, datastore=datastore, processor=request.values.get('processor'))
                 for uuid in importer.new_uuids:
                     update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
 
@@ -760,9 +813,12 @@ def changedetection_app(config=None, datastore_o=None):
                     update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
 
 
-
+        form = forms.importForm(formdata=request.form if request.method == 'POST' else None,
+#                               data=default,
+                               )
         # Could be some remaining, or we could be on GET
         output = render_template("import.html",
+                                 form=form,
                                  import_url_list_remaining="\n".join(remaining_urls),
                                  original_distill_json=''
                                  )
@@ -828,28 +884,22 @@ def changedetection_app(config=None, datastore_o=None):
         # Save the current newest history as the most recently viewed
         datastore.set_last_viewed(uuid, time.time())
 
-        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:
-                newest_version_file_contents = f.read()
+            newest_version_file_contents = watch.get_history_snapshot(dates[-1])
         except Exception as e:
-            newest_version_file_contents = "Unable to read {}.\n".format(newest_file)
+            newest_version_file_contents = "Unable to read {}.\n".format(dates[-1])
 
         previous_version = request.args.get('previous_version')
-        try:
-            previous_file = history[previous_version]
-        except KeyError:
-            # Not present, use a default value, the second one in the sorted list.
-            previous_file = history[dates[-2]]
+        previous_timestamp = dates[-2]
+        if previous_version:
+            previous_timestamp = previous_version
 
         try:
-            with open(previous_file, 'r', encoding='utf-8', errors='ignore') as f:
-                previous_version_file_contents = f.read()
+            previous_version_file_contents = watch.get_history_snapshot(previous_timestamp)
         except Exception as e:
-            previous_version_file_contents = "Unable to read {}.\n".format(previous_file)
+            previous_version_file_contents = "Unable to read {}.\n".format(previous_timestamp)
 
 
         screenshot_url = watch.get_screenshot()
@@ -929,37 +979,35 @@ def changedetection_app(config=None, datastore_o=None):
             return output
 
         timestamp = list(watch.history.keys())[-1]
-        filename = watch.history[timestamp]
         try:
-            with open(filename, 'r', encoding='utf-8', errors='ignore') as f:
-                tmp = f.readlines()
+            tmp = watch.get_history_snapshot(timestamp).splitlines()
 
-                # Get what needs to be highlighted
-                ignore_rules = watch.get('ignore_text', []) + datastore.data['settings']['application']['global_ignore_text']
+            # Get what needs to be highlighted
+            ignore_rules = watch.get('ignore_text', []) + datastore.data['settings']['application']['global_ignore_text']
 
-                # .readlines will keep the \n, but we will parse it here again, in the future tidy this up
-                ignored_line_numbers = html_tools.strip_ignore_text(content="".join(tmp),
-                                                                    wordlist=ignore_rules,
-                                                                    mode='line numbers'
-                                                                    )
+            # .readlines will keep the \n, but we will parse it here again, in the future tidy this up
+            ignored_line_numbers = html_tools.strip_ignore_text(content="\n".join(tmp),
+                                                                wordlist=ignore_rules,
+                                                                mode='line numbers'
+                                                                )
 
-                trigger_line_numbers = html_tools.strip_ignore_text(content="".join(tmp),
-                                                                    wordlist=watch['trigger_text'],
-                                                                    mode='line numbers'
-                                                                    )
-                # Prepare the classes and lines used in the template
-                i=0
-                for l in tmp:
-                    classes=[]
-                    i+=1
-                    if i in ignored_line_numbers:
-                        classes.append('ignored')
-                    if i in trigger_line_numbers:
-                        classes.append('triggered')
-                    content.append({'line': l, 'classes': ' '.join(classes)})
+            trigger_line_numbers = html_tools.strip_ignore_text(content="\n".join(tmp),
+                                                                wordlist=watch['trigger_text'],
+                                                                mode='line numbers'
+                                                                )
+            # Prepare the classes and lines used in the template
+            i=0
+            for l in tmp:
+                classes=[]
+                i+=1
+                if i in ignored_line_numbers:
+                    classes.append('ignored')
+                if i in trigger_line_numbers:
+                    classes.append('triggered')
+                content.append({'line': l, 'classes': ' '.join(classes)})
 
         except Exception as e:
-            content.append({'line': "File doesnt exist or unable to read file {}".format(filename), 'classes': ''})
+            content.append({'line': f"File doesnt exist or unable to read timestamp {timestamp}", 'classes': ''})
 
         output = render_template("preview.html",
                                  content=content,
@@ -1126,7 +1174,8 @@ def changedetection_app(config=None, datastore_o=None):
             return redirect(url_for('index'))
 
         add_paused = request.form.get('edit_and_watch_submit_button') != None
-        new_uuid = datastore.add_watch(url=url, tag=request.form.get('tag').strip(), extras={'paused': add_paused})
+        processor = request.form.get('processor', 'text_json_diff')
+        new_uuid = datastore.add_watch(url=url, tag=request.form.get('tag').strip(), extras={'paused': add_paused, 'processor': processor})
 
         if new_uuid:
             if add_paused:
@@ -1168,7 +1217,8 @@ def changedetection_app(config=None, datastore_o=None):
 
         new_uuid = datastore.clone(uuid)
         if new_uuid:
-            update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
+            if not datastore.data['watching'].get(uuid).get('paused'):
+                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
             flash('Cloned.')
 
         return redirect(url_for('index'))
@@ -1234,6 +1284,13 @@ def changedetection_app(config=None, datastore_o=None):
                     datastore.data['watching'][uuid.strip()]['paused'] = False
             flash("{} watches unpaused".format(len(uuids)))
 
+        elif (op == 'mark-viewed'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.set_last_viewed(uuid, int(time.time()))
+            flash("{} watches updated".format(len(uuids)))
+
         elif (op == 'mute'):
             for uuid in uuids:
                 uuid = uuid.strip()
@@ -1256,6 +1313,13 @@ def changedetection_app(config=None, datastore_o=None):
                     update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
             flash("{} watches queued for rechecking".format(len(uuids)))
 
+        elif (op == 'clear-history'):
+            for uuid in uuids:
+                uuid = uuid.strip()
+                if datastore.data['watching'].get(uuid):
+                    datastore.clear_watch_history(uuid)
+            flash("{} watches cleared/reset.".format(len(uuids)))
+
         elif (op == 'notification-default'):
             from changedetectionio.notification import (
                 default_notification_format_for_watch

changedetectionio/api/api_v1.py

@@ -179,9 +179,7 @@ class WatchSingleHistory(Resource):
         if timestamp == 'latest':
             timestamp = list(watch.history.keys())[-1]
 
-        # @todo - Check for UTF-8 compatability
-        with open(watch.history[timestamp], 'r') as f:
-            content = f.read()
+        content = watch.get_history_snapshot(timestamp)
 
         response = make_response(content, 200)
         response.mimetype = "text/plain"

changedetectionio/blueprint/browser_steps/__init__.py

@@ -146,8 +146,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                 from . import nonContext
                 browsersteps_playwright_browser_interface_context = nonContext.c_sync_playwright()
                 browsersteps_playwright_browser_interface = browsersteps_playwright_browser_interface_context.start()
-
-                time.sleep(1)
                 # At 20 minutes, some other variable is closing it
                 # @todo find out what it is and set it
                 seconds_keepalive = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
@@ -171,7 +169,18 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                 if proxy_id:
                     proxy_url = datastore.proxy_list.get(proxy_id).get('url')
                     if proxy_url:
+
+                        # Playwright needs separate username and password values
+                        from urllib.parse import urlparse
+                        parsed = urlparse(proxy_url)
                         proxy = {'server': proxy_url}
+
+                        if parsed.username:
+                            proxy['username'] = parsed.username
+
+                        if parsed.password:
+                            proxy['password'] = parsed.password
+
                         print("Browser Steps: UUID {} Using proxy {}".format(uuid, proxy_url))
 
                 # Begin the new "Playwright Context" that re-uses the playwright interface

changedetectionio/content_fetcher.py

@@ -10,6 +10,7 @@ import time
 
 visualselector_xpath_selectors = 'div,span,form,table,tbody,tr,td,a,p,ul,li,h1,h2,h3,h4, header, footer, section, article, aside, details, main, nav, section, summary'
 
+
 class Non200ErrorCodeReceived(Exception):
     def __init__(self, status_code, url, screenshot=None, xpath_data=None, page_html=None):
         # Set this so we can use it in other parts of the app
@@ -24,10 +25,12 @@ class Non200ErrorCodeReceived(Exception):
             self.page_text = html_tools.html_to_text(page_html)
         return
 
+
 class checksumFromPreviousCheckWasTheSame(Exception):
     def __init__(self):
         return
 
+
 class JSActionExceptions(Exception):
     def __init__(self, status_code, url, screenshot, message=''):
         self.status_code = status_code
@@ -36,6 +39,7 @@ class JSActionExceptions(Exception):
         self.message = message
         return
 
+
 class BrowserStepsStepTimout(Exception):
     def __init__(self, step_n):
         self.step_n = step_n
@@ -51,6 +55,7 @@ class PageUnloadable(Exception):
         self.message = message
         return
 
+
 class EmptyReply(Exception):
     def __init__(self, status_code, url, screenshot=None):
         # Set this so we can use it in other parts of the app
@@ -59,6 +64,7 @@ class EmptyReply(Exception):
         self.screenshot = screenshot
         return
 
+
 class ScreenshotUnavailable(Exception):
     def __init__(self, status_code, url, page_html=None):
         # Set this so we can use it in other parts of the app
@@ -69,6 +75,7 @@ class ScreenshotUnavailable(Exception):
             self.page_text = html_to_text(page_html)
         return
 
+
 class ReplyWithContentButNoText(Exception):
     def __init__(self, status_code, url, screenshot=None):
         # Set this so we can use it in other parts of the app
@@ -77,19 +84,20 @@ class ReplyWithContentButNoText(Exception):
         self.screenshot = screenshot
         return
 
+
 class Fetcher():
-    error = None
-    status_code = None
-    content = None
-    headers = None
     browser_steps = None
     browser_steps_screenshot_path = None
-
+    content = None
+    error = None
     fetcher_description = "No description"
+    headers = {}
+    status_code = None
     webdriver_js_execute_code = None
-    xpath_element_js = ""
-
     xpath_data = None
+    xpath_element_js = ""
+    instock_data = None
+    instock_data_js = ""
 
     # Will be needed in the future by the VisualSelector, always get this where possible.
     screenshot = False
@@ -103,7 +111,7 @@ class Fetcher():
         from pkg_resources import resource_string
         # The code that scrapes elements and makes a list of elements/size/position to click on in the VisualSelector
         self.xpath_element_js = resource_string(__name__, "res/xpath_element_scraper.js").decode('utf-8')
-
+        self.instock_data_js = resource_string(__name__, "res/stock-not-in-stock.js").decode('utf-8')
 
     @abstractmethod
     def get_error(self):
@@ -151,13 +159,15 @@ class Fetcher():
             interface = steppable_browser_interface()
             interface.page = self.page
 
-            valid_steps = filter(lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'), self.browser_steps)
+            valid_steps = filter(
+                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
+                self.browser_steps)
 
             for step in valid_steps:
                 step_n += 1
                 print(">> Iterating check - browser Step n {} - {}...".format(step_n, step['operation']))
-                self.screenshot_step("before-"+str(step_n))
-                self.save_step_html("before-"+str(step_n))
+                self.screenshot_step("before-" + str(step_n))
+                self.save_step_html("before-" + str(step_n))
                 try:
                     optional_value = step['optional_value']
                     selector = step['selector']
@@ -176,8 +186,6 @@ class Fetcher():
                     # Stop processing here
                     raise BrowserStepsStepTimout(step_n=step_n)
 
-
-
     # It's always good to reset these
     def delete_browser_steps_screenshots(self):
         import glob
@@ -187,6 +195,7 @@ class Fetcher():
             for f in files:
                 os.unlink(f)
 
+
 #   Maybe for the future, each fetcher provides its own diff output, could be used for text, image
 #   the current one would return javascript output (as we use JS to generate the diff)
 #
@@ -204,6 +213,7 @@ def available_fetchers():
 
     return p
 
+
 class base_html_playwright(Fetcher):
     fetcher_description = "Playwright {}/Javascript".format(
         os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
@@ -267,6 +277,118 @@ class base_html_playwright(Fetcher):
         with open(destination, 'w') as f:
             f.write(content)
 
+    def run_fetch_browserless_puppeteer(self,
+            url,
+            timeout,
+            request_headers,
+            request_body,
+            request_method,
+            ignore_status_codes=False,
+            current_include_filters=None,
+            is_binary=False):
+
+        from pkg_resources import resource_string
+
+        extra_wait_ms = (int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay) * 1000
+
+        self.xpath_element_js = self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors)
+        code = resource_string(__name__, "res/puppeteer_fetch.js").decode('utf-8')
+        # In the future inject this is a proper JS package
+        code = code.replace('%xpath_scrape_code%', self.xpath_element_js)
+        code = code.replace('%instock_scrape_code%', self.instock_data_js)
+
+        from requests.exceptions import ConnectTimeout, ReadTimeout
+        wait_browserless_seconds = 240
+
+        browserless_function_url = os.getenv('BROWSERLESS_FUNCTION_URL')
+        from urllib.parse import urlparse
+        if not browserless_function_url:
+            # Convert/try to guess from PLAYWRIGHT_DRIVER_URL
+            o = urlparse(os.getenv('PLAYWRIGHT_DRIVER_URL'))
+            browserless_function_url = o._replace(scheme="http")._replace(path="function").geturl()
+
+
+        # Append proxy connect string
+        if self.proxy:
+            import urllib.parse
+            # Remove username/password if it exists in the URL or you will receive "ERR_NO_SUPPORTED_PROXIES" error
+            # Actual authentication handled by Puppeteer/node
+            o = urlparse(self.proxy.get('server'))
+            proxy_url = urllib.parse.quote(o._replace(netloc="{}:{}".format(o.hostname, o.port)).geturl())
+            browserless_function_url = f"{browserless_function_url}&--proxy-server={proxy_url}&dumpio=true"
+
+
+        try:
+            amp = '&' if '?' in browserless_function_url else '?'
+            response = requests.request(
+                method="POST",
+                json={
+                    "code": code,
+                    "context": {
+                        # Very primitive disk cache - USE WITH EXTREME CAUTION
+                        # Run browserless container  with -e "FUNCTION_BUILT_INS=[\"fs\",\"crypto\"]"
+                        'disk_cache_dir': os.getenv("PUPPETEER_DISK_CACHE", False), # or path to disk cache ending in /, ie /tmp/cache/
+                        'execute_js': self.webdriver_js_execute_code,
+                        'extra_wait_ms': extra_wait_ms,
+                        'include_filters': current_include_filters,
+                        'req_headers': request_headers,
+                        'screenshot_quality': int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)),
+                        'url': url,
+                        'user_agent': request_headers.get('User-Agent', 'Mozilla/5.0'),
+                        'proxy_username': self.proxy.get('username','') if self.proxy else False,
+                        'proxy_password': self.proxy.get('password', '') if self.proxy else False,
+                        'no_cache_list': [
+                            'twitter',
+                            '.pdf'
+                        ],
+                        # Could use https://github.com/easylist/easylist here, or install a plugin
+                        'block_url_list': [
+                            'adnxs.com',
+                            'analytics.twitter.com',
+                            'doubleclick.net',
+                            'google-analytics.com',
+                            'googletagmanager',
+                            'trustpilot.com'
+                        ]
+                    }
+                },
+                # @todo /function needs adding ws:// to http:// rebuild this
+                url=browserless_function_url+f"{amp}--disable-features=AudioServiceOutOfProcess&dumpio=true&--disable-remote-fonts",
+                timeout=wait_browserless_seconds)
+
+        except ReadTimeout:
+            raise PageUnloadable(url=url, status_code=None, message=f"No response from browserless in {wait_browserless_seconds}s")
+        except ConnectTimeout:
+            raise PageUnloadable(url=url, status_code=None, message=f"Timed out connecting to browserless, retrying..")
+        else:
+            # 200 Here means that the communication to browserless worked only, not the page state
+            if response.status_code == 200:
+                import base64
+
+                x = response.json()
+                if not x.get('screenshot'):
+                    # https://github.com/puppeteer/puppeteer/blob/v1.0.0/docs/troubleshooting.md#tips
+                    # https://github.com/puppeteer/puppeteer/issues/1834
+                    # https://github.com/puppeteer/puppeteer/issues/1834#issuecomment-381047051
+                    # Check your memory is shared and big enough
+                    raise ScreenshotUnavailable(url=url, status_code=None)
+
+                if not x.get('content', '').strip():
+                    raise EmptyReply(url=url, status_code=None)
+
+                if x.get('status_code', 200) != 200 and not ignore_status_codes:
+                    raise Non200ErrorCodeReceived(url=url, status_code=x.get('status_code', 200), page_html=x['content'])
+
+                self.content = x.get('content')
+                self.headers = x.get('headers')
+                self.instock_data = x.get('instock_data')
+                self.screenshot = base64.b64decode(x.get('screenshot'))
+                self.xpath_data = x.get('xpath_data')
+
+            else:
+                # Some other error from browserless
+                raise PageUnloadable(url=url, status_code=None, message=response.content.decode('utf-8'))
+
     def run(self,
             url,
             timeout,
@@ -277,6 +399,24 @@ class base_html_playwright(Fetcher):
             current_include_filters=None,
             is_binary=False):
 
+        # For now, USE_EXPERIMENTAL_PUPPETEER_FETCH is not supported by watches with BrowserSteps (for now!)
+        has_browser_steps = self.browser_steps and list(filter(
+                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
+                self.browser_steps))
+
+        if not has_browser_steps:
+            if os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH'):
+                # Temporary backup solution until we rewrite the playwright code
+                return self.run_fetch_browserless_puppeteer(
+                    url,
+                    timeout,
+                    request_headers,
+                    request_body,
+                    request_method,
+                    ignore_status_codes,
+                    current_include_filters,
+                    is_binary)
+
         from playwright.sync_api import sync_playwright
         import playwright._impl._api_types
 
@@ -293,7 +433,7 @@ class base_html_playwright(Fetcher):
             # Set user agent to prevent Cloudflare from blocking the browser
             # Use the default one configured in the App.py model that's passed from fetch_site_status.py
             context = browser.new_context(
-                user_agent=request_headers['User-Agent'] if request_headers.get('User-Agent') else 'Mozilla/5.0',
+                user_agent=request_headers.get('User-Agent', 'Mozilla/5.0'),
                 proxy=self.proxy,
                 # This is needed to enable JavaScript execution on GitHub and others
                 bypass_csp=True,
@@ -323,12 +463,12 @@ class base_html_playwright(Fetcher):
             except playwright._impl._api_types.Error as e:
                 # Retry once - https://github.com/browserless/chrome/issues/2485
                 # Sometimes errors related to invalid cert's and other can be random
-                print ("Content Fetcher > retrying request got error - ", str(e))
+                print("Content Fetcher > retrying request got error - ", str(e))
                 time.sleep(1)
                 response = self.page.goto(url, wait_until='commit')
 
             except Exception as e:
-                print ("Content Fetcher > Other exception when page.goto", str(e))
+                print("Content Fetcher > Other exception when page.goto", str(e))
                 context.close()
                 browser.close()
                 raise PageUnloadable(url=url, status_code=None, message=str(e))
@@ -347,7 +487,7 @@ class base_html_playwright(Fetcher):
                 # This can be ok, we will try to grab what we could retrieve
                 pass
             except Exception as e:
-                print ("Content Fetcher > Other exception when executing custom JS code", str(e))
+                print("Content Fetcher > Other exception when executing custom JS code", str(e))
                 context.close()
                 browser.close()
                 raise PageUnloadable(url=url, status_code=None, message=str(e))
@@ -355,7 +495,7 @@ class base_html_playwright(Fetcher):
             if response is None:
                 context.close()
                 browser.close()
-                print ("Content Fetcher > Response object was none")
+                print("Content Fetcher > Response object was none")
                 raise EmptyReply(url=url, status_code=None)
 
             # Run Browser Steps here
@@ -369,11 +509,10 @@ class base_html_playwright(Fetcher):
             if len(self.page.content().strip()) == 0:
                 context.close()
                 browser.close()
-                print ("Content Fetcher > Content was empty")
+                print("Content Fetcher > Content was empty")
                 raise EmptyReply(url=url, status_code=response.status)
 
             self.status_code = response.status
-            self.content = self.page.content()
             self.headers = response.all_headers()
 
             # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
@@ -382,7 +521,9 @@ class base_html_playwright(Fetcher):
             else:
                 self.page.evaluate("var include_filters=''")
 
-            self.xpath_data = self.page.evaluate("async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
+            self.xpath_data = self.page.evaluate(
+                "async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
+            self.instock_data = self.page.evaluate("async () => {" + self.instock_data_js + "}")
 
             # Bug 3 in Playwright screenshot handling
             # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
@@ -393,7 +534,8 @@ class base_html_playwright(Fetcher):
             # acceptable screenshot quality here
             try:
                 # The actual screenshot
-                self.screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
+                self.screenshot = self.page.screenshot(type='jpeg', full_page=True,
+                                                       quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
             except Exception as e:
                 context.close()
                 browser.close()
@@ -402,6 +544,7 @@ class base_html_playwright(Fetcher):
             context.close()
             browser.close()
 
+
 class base_html_webdriver(Fetcher):
     if os.getenv("WEBDRIVER_URL"):
         fetcher_description = "WebDriver Chrome/Javascript via '{}'".format(os.getenv("WEBDRIVER_URL"))

changedetectionio/diff.py

@@ -10,7 +10,7 @@ def same_slicer(l, a, b):
         return l[a:b]
 
 # like .compare but a little different output
-def customSequenceMatcher(before, after, include_equal=False, include_removed=True, include_added=True):
+def customSequenceMatcher(before, after, include_equal=False, include_removed=True, include_added=True, include_replaced=True, include_change_type_prefix=True):
     cruncher = difflib.SequenceMatcher(isjunk=lambda x: x in " \\t", a=before, b=after)
 
     # @todo Line-by-line mode instead of buncghed, including `after` that is not in `before` (maybe unset?)
@@ -19,33 +19,38 @@ def customSequenceMatcher(before, after, include_equal=False, include_removed=Tr
             g = before[alo:ahi]
             yield g
         elif include_removed and tag == 'delete':
-            g = ["(removed) " + i for i in same_slicer(before, alo, ahi)]
+            row_prefix = "(removed) " if include_change_type_prefix else ''
+            g = [ row_prefix + i for i in same_slicer(before, alo, ahi)]
             yield g
-        elif tag == 'replace':
-            g = ["(changed) " + i for i in same_slicer(before, alo, ahi)]
-            g += ["(into) " + i for i in same_slicer(after, blo, bhi)]
+        elif include_replaced and tag == 'replace':
+            row_prefix = "(changed) " if include_change_type_prefix else ''
+            g = [row_prefix + i for i in same_slicer(before, alo, ahi)]
+            row_prefix = "(into) " if include_change_type_prefix else ''
+            g += [row_prefix + i for i in same_slicer(after, blo, bhi)]
             yield g
         elif include_added and tag == 'insert':
-            g = ["(added) " + i for i in same_slicer(after, blo, bhi)]
+            row_prefix = "(added) " if include_change_type_prefix else ''
+            g = [row_prefix + i for i in same_slicer(after, blo, bhi)]
             yield g
 
 # only_differences - only return info about the differences, no context
 # line_feed_sep could be "<br>" or "<li>" or "\n" etc
-def render_diff(previous_file, newest_file, include_equal=False, include_removed=True, include_added=True, line_feed_sep="\n"):
-    with open(newest_file, 'r') as f:
-        newest_version_file_contents = f.read()
-        newest_version_file_contents = [line.rstrip() for line in newest_version_file_contents.splitlines()]
+def render_diff(previous_version_file_contents, newest_version_file_contents, include_equal=False, include_removed=True, include_added=True, include_replaced=True, line_feed_sep="\n", include_change_type_prefix=True):
 
-    if previous_file:
-        with open(previous_file, 'r') as f:
-            previous_version_file_contents = f.read()
+    newest_version_file_contents = [line.rstrip() for line in newest_version_file_contents.splitlines()]
+
+    if previous_version_file_contents:
             previous_version_file_contents = [line.rstrip() for line in previous_version_file_contents.splitlines()]
     else:
         previous_version_file_contents = ""
 
-    rendered_diff = customSequenceMatcher(previous_version_file_contents,
-                                          newest_version_file_contents,
-                                          include_equal, include_removed, include_added)
+    rendered_diff = customSequenceMatcher(before=previous_version_file_contents,
+                                          after=newest_version_file_contents,
+                                          include_equal=include_equal,
+                                          include_removed=include_removed,
+                                          include_added=include_added,
+                                          include_replaced=include_replaced,
+                                          include_change_type_prefix=include_change_type_prefix)
 
     # Recursively join lists
     f = lambda L: line_feed_sep.join([f(x) if type(x) is list else x for x in L])

changedetectionio/forms.py

@@ -344,13 +344,15 @@ class ValidateCSSJSONXPATHInput(object):
                     raise ValidationError("A system-error occurred when validating your jq expression")
 
 class quickWatchForm(Form):
+    from . import processors
+
     url = fields.URLField('URL', validators=[validateURL()])
     tag = StringField('Group tag', [validators.Optional()])
     watch_submit_button = SubmitField('Watch', render_kw={"class": "pure-button pure-button-primary"})
+    processor = RadioField(u'Processor', choices=processors.available_processors(), default="text_json_diff")
     edit_and_watch_submit_button = SubmitField('Edit > Watch', render_kw={"class": "pure-button pure-button-primary"})
 
 
-
 # Common to a single watch and the global settings
 class commonSettingsForm(Form):
     notification_urls = StringListField('Notification URL List', validators=[validators.Optional(), ValidateAppRiseServers()])
@@ -361,6 +363,10 @@ class commonSettingsForm(Form):
     extract_title_as_title = BooleanField('Extract <title> from document and use as watch title', default=False)
     webdriver_delay = IntegerField('Wait seconds before extracting text', validators=[validators.Optional(), validators.NumberRange(min=1,
                                                                                                                                     message="Should contain one or more seconds")])
+class importForm(Form):
+    from . import processors
+    processor = RadioField(u'Processor', choices=processors.available_processors(), default="text_json_diff")
+    urls = TextAreaField('URLs')
 
 class SingleBrowserStep(Form):
 
@@ -393,11 +399,19 @@ class watchForm(commonSettingsForm):
     body = TextAreaField('Request body', [validators.Optional()])
     method = SelectField('Request method', choices=valid_method, default=default_method)
     ignore_status_codes = BooleanField('Ignore status codes (process non-2xx status codes as normal)', default=False)
-    check_unique_lines = BooleanField('Only trigger when new lines appear', default=False)
+    check_unique_lines = BooleanField('Only trigger when unique lines appear', default=False)
+
+    filter_text_added = BooleanField('Added lines', default=True)
+    filter_text_replaced = BooleanField('Replaced/changed lines', default=True)
+    filter_text_removed = BooleanField('Removed lines', default=True)
+
+    # @todo this class could be moved to its own text_json_diff_watchForm and this goes to restock_diff_Watchform perhaps
+    in_stock_only = BooleanField('Only trigger when product goes BACK to in-stock', default=True)
+
     trigger_text = StringListField('Trigger/wait for text', [validators.Optional(), ValidateListRegex()])
     if os.getenv("PLAYWRIGHT_DRIVER_URL"):
         browser_steps = FieldList(FormField(SingleBrowserStep), min_entries=10)
-    text_should_not_be_present = StringListField('Block change-detection if text matches', [validators.Optional(), ValidateListRegex()])
+    text_should_not_be_present = StringListField('Block change-detection while text matches', [validators.Optional(), ValidateListRegex()])
     webdriver_js_execute_code = TextAreaField('Execute JavaScript before change detection', render_kw={"rows": "5"}, validators=[validators.Optional()])
 
     save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})

changedetectionio/html_tools.py

@@ -287,3 +287,18 @@ def workarounds_for_obfuscations(content):
     content = re.sub('<!--\s+-->', '', content)
 
     return content
+
+
+def get_triggered_text(content, trigger_text):
+    triggered_text = []
+    result = strip_ignore_text(content=content,
+                               wordlist=trigger_text,
+                               mode="line numbers")
+
+    i = 1
+    for p in content.splitlines():
+        if i in result:
+            triggered_text.append(p)
+        i += 1
+
+    return triggered_text

changedetectionio/importer.py

@@ -29,6 +29,7 @@ class import_url_list(Importer):
             data,
             flash,
             datastore,
+            processor=None
             ):
 
         urls = data.split("\n")
@@ -52,7 +53,11 @@ class import_url_list(Importer):
             # Flask wtform validators wont work with basic auth, use validators package
             # Up to 5000 per batch so we dont flood the server
             if len(url) and validators.url(url.replace('source:', '')) and good < 5000:
-                new_uuid = datastore.add_watch(url=url.strip(), tag=tags, write_to_disk_now=False)
+                extras = None
+                if processor:
+                    extras = {'processor': processor}
+                new_uuid = datastore.add_watch(url=url.strip(), tag=tags, write_to_disk_now=False, extras=extras)
+
                 if new_uuid:
                     # Straight into the queue.
                     self.new_uuids.append(new_uuid)

changedetectionio/model/Watch.py

@@ -20,15 +20,21 @@ base_config = {
     'body': None,
     'check_unique_lines': False,  # On change-detected, compare against all history if its something new
     'check_count': 0,
+    'date_created': None,
     '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': 'system',
+    'fetch_backend': 'system', # plaintext, playwright etc
+    'processor': 'text_json_diff', # could be restock_diff or others from .processors
     'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
+    'filter_text_added': True,
+    'filter_text_replaced': True,
+    'filter_text_removed': True,
     'has_ldjson_price_data': None,
     'track_ldjson_price_data': None,
     'headers': {},  # Extra headers to send
     'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
+    'in_stock_only' : True, # Only trigger change on going to instock from out-of-stock
     'include_filters': [],
     'last_checked': 0,
     'last_error': False,
@@ -239,9 +245,32 @@ class model(dict):
         bump = self.history
         return self.__newest_history_key
 
+    def get_history_snapshot(self, timestamp):
+        import brotli
+        filepath = self.history[timestamp]
+
+        # See if a brotli versions exists and switch to that
+        if not filepath.endswith('.br') and os.path.isfile(f"{filepath}.br"):
+            filepath = f"{filepath}.br"
+
+        # OR in the backup case that the .br does not exist, but the plain one does
+        if filepath.endswith('.br') and not os.path.isfile(filepath):
+            if os.path.isfile(filepath.replace('.br', '')):
+                filepath = filepath.replace('.br', '')
+
+        if filepath.endswith('.br'):
+            # Brotli doesnt have a fileheader to detect it, so we rely on filename
+            # https://www.rfc-editor.org/rfc/rfc7932
+            with open(filepath, 'rb') as f:
+                return(brotli.decompress(f.read()).decode('utf-8'))
+
+        with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
+            return f.read()
+
     # Save some text file to the appropriate path and bump the history
     # result_obj from fetch_site_status.run()
     def save_history_text(self, contents, timestamp, snapshot_id):
+        import brotli
 
         self.ensure_data_dir_exists()
 
@@ -250,16 +279,21 @@ class model(dict):
         if self.__newest_history_key and int(timestamp) == int(self.__newest_history_key):
             time.sleep(timestamp - self.__newest_history_key)
 
-        snapshot_fname = f"{snapshot_id}.txt"
+        threshold = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD', 1024))
+        skip_brotli = strtobool(os.getenv('DISABLE_BROTLI_TEXT_SNAPSHOT', 'False'))
 
-        # Only write if it does not exist, this is so that we dont bother re-saving the same data by checksum under different filenames.
-        dest = os.path.join(self.watch_data_dir, snapshot_fname)
-        if not os.path.exists(dest):
-            # 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(dest, 'wb') as f:
-                f.write(contents)
-                f.close()
+        if not skip_brotli and len(contents) > threshold:
+            snapshot_fname = f"{snapshot_id}.txt.br"
+            dest = os.path.join(self.watch_data_dir, snapshot_fname)
+            if not os.path.exists(dest):
+                with open(dest, 'wb') as f:
+                    f.write(brotli.compress(contents, mode=brotli.MODE_TEXT))
+        else:
+            snapshot_fname = f"{snapshot_id}.txt"
+            dest = os.path.join(self.watch_data_dir, snapshot_fname)
+            if not os.path.exists(dest):
+                with open(dest, 'wb') as f:
+                    f.write(contents)
 
         # Append to index
         # @todo check last char was \n
@@ -296,7 +330,8 @@ class model(dict):
         # Compare each lines (set) against each history text file (set) looking for something new..
         existing_history = set({})
         for k, v in self.history.items():
-            alist = set([line.decode('utf-8').strip().lower() for line in open(v, 'rb')])
+            content = self.get_history_snapshot(k)
+            alist = set([line.strip().lower() for line in content.splitlines()])
             existing_history = existing_history.union(alist)
 
         # Check that everything in local_lines(new stuff) already exists in existing_history - it should
@@ -311,17 +346,6 @@ class model(dict):
         # False is not an option for AppRise, must be type None
         return None
 
-    def get_screenshot_as_jpeg(self):
-
-        # Created by save_screenshot()
-        fname = os.path.join(self.watch_data_dir, "last-screenshot.jpg")
-        if os.path.isfile(fname):
-            return fname
-
-        # False is not an option for AppRise, must be type None
-        return None
-
-
     def __get_file_ctime(self, filename):
         fname = os.path.join(self.watch_data_dir, filename)
         if os.path.isfile(fname):
@@ -368,6 +392,7 @@ class model(dict):
             return fname
         return False
 
+
     def pause(self):
         self['paused'] = True
 
@@ -397,8 +422,8 @@ class model(dict):
         # self.history will be keyed with the full path
         for k, fname in self.history.items():
             if os.path.isfile(fname):
-                with open(fname, "r") as f:
-                    contents = f.read()
+                if True:
+                    contents = self.get_history_snapshot(k)
                     res = re.findall(regex, contents, re.MULTILINE)
                     if res:
                         if not csv_writer:
@@ -434,3 +459,38 @@ class model(dict):
     # Return list of tags, stripped and lowercase, used for searching
     def all_tags(self):
         return [s.strip().lower() for s in self.get('tag','').split(',')]
+
+    def has_special_diff_filter_options_set(self):
+
+        # All False - nothing would be done, so act like it's not processable
+        if not self.get('filter_text_added', True) and not self.get('filter_text_replaced', True) and not self.get('filter_text_removed', True):
+            return False
+
+        # Or one is set
+        if not self.get('filter_text_added', True) or not self.get('filter_text_replaced', True) or not self.get('filter_text_removed', True):
+            return True
+
+        # None is set
+        return False
+
+
+    def get_last_fetched_before_filters(self):
+        import brotli
+        filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
+
+        if not os.path.isfile(filepath):
+            # If a previous attempt doesnt yet exist, just snarf the previous snapshot instead
+            dates = list(self.history.keys())
+            if len(dates):
+                return self.get_history_snapshot(dates[-1])
+            else:
+                return ''
+
+        with open(filepath, 'rb') as f:
+            return(brotli.decompress(f.read()).decode('utf-8'))
+
+    def save_last_fetched_before_filters(self, contents):
+        import brotli
+        filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
+        with open(filepath, 'wb') as f:
+            f.write(brotli.compress(contents, mode=brotli.MODE_TEXT))

changedetectionio/notification.py

@@ -5,17 +5,18 @@ import json
 
 valid_tokens = {
     'base_url': '',
-    'watch_url': '',
-    'watch_uuid': '',
-    'watch_title': '',
-    'watch_tag': '',
+    'current_snapshot': '',
     'diff': '',
     'diff_added': '',
-    'diff_removed': '',
     'diff_full': '',
+    'diff_removed': '',
     'diff_url': '',
     'preview_url': '',
-    'current_snapshot': ''
+    'triggered_text': '',
+    'watch_tag': '',
+    'watch_title': '',
+    'watch_url': '',
+    'watch_uuid': '',
 }
 
 default_notification_format_for_watch = 'System default'
@@ -88,7 +89,7 @@ def process_notification(n_object, datastore):
     n_body = jinja2_env.from_string(n_object.get('notification_body', default_notification_body)).render(**notification_parameters)
     n_title = jinja2_env.from_string(n_object.get('notification_title', default_notification_title)).render(**notification_parameters)
     n_format = valid_notification_formats.get(
-        n_object['notification_format'],
+        n_object.get('notification_format', default_notification_format),
         valid_notification_formats[default_notification_format],
     )
     
@@ -211,17 +212,18 @@ def create_notification_parameters(n_object, datastore):
     tokens.update(
         {
             'base_url': base_url if base_url is not None else '',
-            'watch_url': watch_url,
-            'watch_uuid': uuid,
-            'watch_title': watch_title if watch_title is not None else '',
-            'watch_tag': watch_tag if watch_tag is not None else '',
-            'diff_url': diff_url,
+            'current_snapshot': n_object['current_snapshot'] if 'current_snapshot' in n_object else '',
             'diff': n_object.get('diff', ''),  # Null default in the case we use a test
             'diff_added': n_object.get('diff_added', ''),  # Null default in the case we use a test
-            'diff_removed': n_object.get('diff_removed', ''),  # Null default in the case we use a test
             'diff_full': n_object.get('diff_full', ''),  # Null default in the case we use a test
+            'diff_removed': n_object.get('diff_removed', ''),  # Null default in the case we use a test
+            'diff_url': diff_url,
             'preview_url': preview_url,
-            'current_snapshot': n_object['current_snapshot'] if 'current_snapshot' in n_object else ''
+            'triggered_text': n_object.get('triggered_text', ''),
+            'watch_tag': watch_tag if watch_tag is not None else '',
+            'watch_title': watch_title if watch_title is not None else '',
+            'watch_url': watch_url,
+            'watch_uuid': uuid,
         })
 
     return tokens

changedetectionio/processors/README.md

@@ -0,0 +1,11 @@
+# Change detection post-processors
+
+The concept here is to be able to switch between different domain specific problems to solve.
+
+- `text_json_diff` The traditional text and JSON comparison handler
+- `restock_diff` Only cares about detecting if a product looks like it has some text that suggests that it's out of stock, otherwise assumes that it's in stock.
+
+Some suggestions for the future
+
+- `graphical` 
+- `restock_and_price` - extract price AND stock text

changedetectionio/processors/__init__.py

@@ -0,0 +1,24 @@
+from abc import abstractmethod
+import hashlib
+
+
+class difference_detection_processor():
+
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+
+    @abstractmethod
+    def run(self, uuid, skip_when_checksum_same=True):
+        update_obj = {'last_notification_error': False, 'last_error': False}
+        some_data = 'xxxxx'
+        update_obj["previous_md5"] = hashlib.md5(some_data.encode('utf-8')).hexdigest()
+        changed_detected = False
+        return changed_detected, update_obj, ''.encode('utf-8')
+
+
+def available_processors():
+    from . import restock_diff, text_json_diff
+    x=[('text_json_diff', text_json_diff.name), ('restock_diff', restock_diff.name)]
+    # @todo Make this smarter with introspection of sorts.
+    return x

changedetectionio/processors/restock_diff.py

@@ -0,0 +1,125 @@
+
+import hashlib
+import os
+import re
+import urllib3
+from . import difference_detection_processor
+from changedetectionio import content_fetcher
+from copy import deepcopy
+
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+
+name = 'Re-stock detection for single product pages'
+description = 'Detects if the product goes back to in-stock'
+
+class perform_site_check(difference_detection_processor):
+    screenshot = None
+    xpath_data = None
+
+    def __init__(self, *args, datastore, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.datastore = datastore
+
+    def run(self, uuid, skip_when_checksum_same=True):
+
+        # DeepCopy so we can be sure we don't accidently change anything by reference
+        watch = deepcopy(self.datastore.data['watching'].get(uuid))
+
+        if not watch:
+            raise Exception("Watch no longer exists.")
+
+        # Protect against file:// access
+        if re.search(r'^file', watch.get('url', ''), re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
+            raise Exception(
+                "file:// type access is denied for security reasons."
+            )
+
+        # Unset any existing notification error
+        update_obj = {'last_notification_error': False, 'last_error': False}
+        extra_headers = watch.get('headers', [])
+
+        # Tweak the base config with the per-watch ones
+        request_headers = deepcopy(self.datastore.data['settings']['headers'])
+        request_headers.update(extra_headers)
+
+        # https://github.com/psf/requests/issues/4525
+        # Requests doesnt yet support brotli encoding, so don't put 'br' here, be totally sure that the user cannot
+        # do this by accident.
+        if 'Accept-Encoding' in request_headers and "br" in request_headers['Accept-Encoding']:
+            request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
+
+        timeout = self.datastore.data['settings']['requests'].get('timeout')
+
+        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)
+
+        # Pluggable content fetcher
+        prefer_backend = watch.get_fetch_backend
+        if not prefer_backend or prefer_backend == 'system':
+            prefer_backend = self.datastore.data['settings']['application']['fetch_backend']
+
+        if hasattr(content_fetcher, prefer_backend):
+            klass = getattr(content_fetcher, prefer_backend)
+        else:
+            # If the klass doesnt exist, just use a default
+            klass = getattr(content_fetcher, "html_requests")
+
+        proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=uuid)
+        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))
+
+        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')
+        elif system_webdriver_delay is not None:
+            fetcher.render_extract_delay = system_webdriver_delay
+
+        # Could be removed if requests/plaintext could also return some info?
+        if prefer_backend != 'html_webdriver':
+            raise Exception("Re-stock detection requires Chrome or compatible webdriver/playwright fetcher to work")
+
+        if watch.get('webdriver_js_execute_code') is not None and watch.get('webdriver_js_execute_code').strip():
+            fetcher.webdriver_js_execute_code = watch.get('webdriver_js_execute_code')
+
+        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch.get('include_filters'))
+        fetcher.quit()
+
+        self.screenshot = fetcher.screenshot
+        self.xpath_data = fetcher.xpath_data
+
+        # Track the content type
+        update_obj['content_type'] = fetcher.headers.get('Content-Type', '')
+        update_obj["last_check_status"] = fetcher.get_last_status_code()
+
+        # Main detection method
+        fetched_md5 = None
+        if fetcher.instock_data:
+            fetched_md5 = hashlib.md5(fetcher.instock_data.encode('utf-8')).hexdigest()
+            # 'Possibly in stock' comes from stock-not-in-stock.js when no string found above the fold.
+            update_obj["in_stock"] = True if fetcher.instock_data == 'Possibly in stock' else False
+
+
+        # The main thing that all this at the moment comes down to :)
+        changed_detected = False
+
+        if watch.get('previous_md5') and watch.get('previous_md5') != fetched_md5:
+            # Yes if we only care about it going to instock, AND we are in stock
+            if watch.get('in_stock_only') and update_obj["in_stock"]:
+                changed_detected = True
+
+            if not watch.get('in_stock_only'):
+                # All cases
+                changed_detected = True
+
+        # Always record the new checksum
+        update_obj["previous_md5"] = fetched_md5
+
+        return changed_detected, update_obj, fetcher.instock_data.encode('utf-8')

changedetectionio/processors/text_json_diff.py

@@ -10,10 +10,14 @@ import urllib3
 from changedetectionio import content_fetcher, html_tools
 from changedetectionio.blueprint.price_data_follower import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
 from copy import deepcopy
+from . import difference_detection_processor
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
 
+name =  'Webpage Text/HTML, JSON and PDF changes'
+description = 'Detects all text changes where possible'
+
 class FilterNotFoundInResponse(ValueError):
     def __init__(self, msg):
         ValueError.__init__(self, msg)
@@ -25,7 +29,7 @@ class PDFToHTMLToolNotFound(ValueError):
 
 # Some common stuff here that can be moved to a base class
 # (set_proxy_from_list)
-class perform_site_check():
+class perform_site_check(difference_detection_processor):
     screenshot = None
     xpath_data = None
 
@@ -55,7 +59,7 @@ class perform_site_check():
         watch = deepcopy(self.datastore.data['watching'].get(uuid))
 
         if not watch:
-            return
+            raise Exception("Watch no longer exists.")
 
         # Protect against file:// access
         if re.search(r'^file', watch.get('url', ''), re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
@@ -275,6 +279,34 @@ class perform_site_check():
         # Re #340 - return the content before the 'ignore text' was applied
         text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
 
+
+        # @todo whitespace coming from missing rtrim()?
+        # stripped_text_from_html could be based on their preferences, replace the processed text with only that which they want to know about.
+        # Rewrite's the processing text based on only what diff result they want to see
+        if watch.has_special_diff_filter_options_set() and len(watch.history.keys()):
+            # Now the content comes from the diff-parser and not the returned HTTP traffic, so could be some differences
+            from .. import diff
+            # needs to not include (added) etc or it may get used twice
+            # Replace the processed text with the preferred result
+            rendered_diff = diff.render_diff(previous_version_file_contents=watch.get_last_fetched_before_filters(),
+                                                       newest_version_file_contents=stripped_text_from_html,
+                                                       include_equal=False,  # not the same lines
+                                                       include_added=watch.get('filter_text_added', True),
+                                                       include_removed=watch.get('filter_text_removed', True),
+                                                       include_replaced=watch.get('filter_text_replaced', True),
+                                                       line_feed_sep="\n",
+                                                       include_change_type_prefix=False)
+
+            watch.save_last_fetched_before_filters(text_content_before_ignored_filter)
+
+            if not rendered_diff and stripped_text_from_html:
+                # We had some content, but no differences were found
+                # Store our new file as the MD5 so it will trigger in the future
+                c = hashlib.md5(text_content_before_ignored_filter.translate(None, b'\r\n\t ')).hexdigest()
+                return False, {'previous_md5': c}, stripped_text_from_html.encode('utf-8')
+            else:
+                stripped_text_from_html = rendered_diff
+
         # Treat pages with no renderable text content as a change? No by default
         empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
         if not is_json and not empty_pages_are_a_change and len(stripped_text_from_html.strip()) == 0:
@@ -333,6 +365,7 @@ class perform_site_check():
             blocked = True
             # Filter and trigger works the same, so reuse it
             # It should return the line numbers that match
+            # Unblock flow if the trigger was found (some text remained after stripped what didnt match)
             result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
                                                   wordlist=trigger_text,
                                                   mode="line numbers")

changedetectionio/res/puppeteer_fetch.js

@@ -0,0 +1,179 @@
+module.exports = async ({page, context}) => {
+
+    var {
+        url,
+        execute_js,
+        user_agent,
+        extra_wait_ms,
+        req_headers,
+        include_filters,
+        xpath_element_js,
+        screenshot_quality,
+        proxy_username,
+        proxy_password,
+        disk_cache_dir,
+        no_cache_list,
+        block_url_list,
+    } = context;
+
+    await page.setBypassCSP(true)
+    await page.setExtraHTTPHeaders(req_headers);
+    await page.setUserAgent(user_agent);
+    // https://ourcodeworld.com/articles/read/1106/how-to-solve-puppeteer-timeouterror-navigation-timeout-of-30000-ms-exceeded
+
+    await page.setDefaultNavigationTimeout(0);
+
+    if (proxy_username) {
+        await page.authenticate({
+            username: proxy_username,
+            password: proxy_password
+        });
+    }
+
+    await page.setViewport({
+        width: 1024,
+        height: 768,
+        deviceScaleFactor: 1,
+    });
+
+    await page.setRequestInterception(true);
+    if (disk_cache_dir) {
+        console.log(">>>>>>>>>>>>>>> LOCAL DISK CACHE ENABLED <<<<<<<<<<<<<<<<<<<<<");
+    }
+    const fs = require('fs');
+    const crypto = require('crypto');
+
+    function file_is_expired(file_path) {
+        if (!fs.existsSync(file_path)) {
+            return true;
+        }
+        var stats = fs.statSync(file_path);
+        const now_date = new Date();
+        const expire_seconds = 300;
+        if ((now_date / 1000) - (stats.mtime.getTime() / 1000) > expire_seconds) {
+            console.log("CACHE EXPIRED: " + file_path);
+            return true;
+        }
+        return false;
+
+    }
+
+    page.on('request', async (request) => {
+        // General blocking of requests that waste traffic
+        if (block_url_list.some(substring => request.url().toLowerCase().includes(substring))) return request.abort();
+
+        if (disk_cache_dir) {
+            const url = request.url();
+            const key = crypto.createHash('md5').update(url).digest("hex");
+            const dir_path = disk_cache_dir + key.slice(0, 1) + '/' + key.slice(1, 2) + '/' + key.slice(2, 3) + '/';
+
+            // https://stackoverflow.com/questions/4482686/check-synchronously-if-file-directory-exists-in-node-js
+
+            if (fs.existsSync(dir_path + key)) {
+                console.log("* CACHE HIT , using - " + dir_path + key + " - " + url);
+                const cached_data = fs.readFileSync(dir_path + key);
+                // @todo headers can come from dir_path+key+".meta" json file
+                request.respond({
+                    status: 200,
+                    //contentType: 'text/html', //@todo
+                    body: cached_data
+                });
+                return;
+            }
+        }
+        request.continue();
+    });
+
+
+    if (disk_cache_dir) {
+        page.on('response', async (response) => {
+            const url = response.url();
+            // Basic filtering for sane responses
+            if (response.request().method() != 'GET' || response.request().resourceType() == 'xhr' || response.request().resourceType() == 'document' || response.status() != 200) {
+                console.log("Skipping (not useful) - Status:" + response.status() + " Method:" + response.request().method() + " ResourceType:" + response.request().resourceType() + " " + url);
+                return;
+            }
+            if (no_cache_list.some(substring => url.toLowerCase().includes(substring))) {
+                console.log("Skipping (no_cache_list) - " + url);
+                return;
+            }
+            response.buffer().then(buffer => {
+                if (buffer.length > 100) {
+                    console.log("Cache - Saving " + response.request().method() + " - " + url + " - " + response.request().resourceType());
+
+                    const key = crypto.createHash('md5').update(url).digest("hex");
+                    const dir_path = disk_cache_dir + key.slice(0, 1) + '/' + key.slice(1, 2) + '/' + key.slice(2, 3) + '/';
+
+                    if (!fs.existsSync(dir_path)) {
+                        fs.mkdirSync(dir_path, {recursive: true})
+                    }
+
+                    if (fs.existsSync(dir_path + key)) {
+                        if (file_is_expired(dir_path + key)) {
+                            fs.writeFileSync(dir_path + key, buffer);
+                        }
+                    } else {
+                        fs.writeFileSync(dir_path + key, buffer);
+                    }
+                }
+            });
+        });
+    }
+
+    const r = await page.goto(url, {
+        waitUntil: 'load'
+    });
+
+    await page.waitForTimeout(1000);
+    await page.waitForTimeout(extra_wait_ms);
+
+    if (execute_js) {
+        await page.evaluate(execute_js);
+        await page.waitForTimeout(200);
+    }
+
+    var xpath_data;
+    var instock_data;
+    try {
+        // Not sure the best way here, in the future this should be a new package added to npm then run in browserless
+        // (Once the old playwright is removed)
+        xpath_data = await page.evaluate((include_filters) => {%xpath_scrape_code%}, include_filters);
+        instock_data = await page.evaluate(() => {%instock_scrape_code%});
+    } catch (e) {
+        console.log(e);
+    }
+
+    // Protocol error (Page.captureScreenshot): Cannot take screenshot with 0 width can come from a proxy auth failure
+    // Wrap it here (for now)
+
+    var b64s = false;
+    try {
+        b64s = await page.screenshot({encoding: "base64", fullPage: true, quality: screenshot_quality, type: 'jpeg'});
+    } catch (e) {
+        console.log(e);
+    }
+
+    // May fail on very large pages with 'WARNING: tile memory limits exceeded, some content may not draw'
+    if (!b64s) {
+        // @todo after text extract, we can place some overlay text with red background to say 'croppped'
+        console.error('ERROR: content-fetcher page was maybe too large for a screenshot, reverting to viewport only screenshot');
+        try {
+            b64s = await page.screenshot({encoding: "base64", quality: screenshot_quality, type: 'jpeg'});
+        } catch (e) {
+            console.log(e);
+        }
+    }
+
+    var html = await page.content();
+    return {
+        data: {
+            'content': html,
+            'headers': r.headers(),
+            'instock_data': instock_data,
+            'screenshot': b64s,
+            'status_code': r.status(),
+            'xpath_data': xpath_data
+        },
+        type: 'application/json',
+    };
+};

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

@@ -0,0 +1,97 @@
+function isItemInStock() {
+  // @todo Pass these in so the same list can be used in non-JS fetchers
+  const outOfStockTexts = [
+    '0 in stock',
+    'agotado',
+    'artikel zurzeit vergriffen',
+    'as soon as stock is available',
+    'available for back order',
+    'backordered',
+    'brak na stanie',
+    'brak w magazynie',
+    'coming soon',
+    'currently unavailable',
+    'en rupture de stock',
+    'item is no longer available',
+    'message if back in stock',
+    'nachricht bei',
+    'nicht auf lager',
+    'nicht lieferbar',
+    'nicht zur verfügung',
+    'no disponible temporalmente',
+    'no longer in stock',
+    'not available',
+    'not in stock',
+    'notify me when available',
+    'não estamos a aceitar encomendas',
+    'out of stock',
+    'out-of-stock',
+    'produkt niedostępny',
+    'sold out',
+    'temporarily out of stock',
+    'temporarily unavailable',
+    'we do not currently have an estimate of when this product will be back in stock.',
+    'zur zeit nicht an lager',
+  ];
+
+
+  const negateOutOfStockRegexs = [
+      '[0-9] in stock'
+  ]
+  var negateOutOfStockRegexs_r = [];
+  for (let i = 0; i < negateOutOfStockRegexs.length; i++) {
+    negateOutOfStockRegexs_r.push(new RegExp(negateOutOfStockRegexs[0], 'g'));
+  }
+
+
+  const elementsWithZeroChildren = Array.from(document.getElementsByTagName('*')).filter(element => element.children.length === 0);
+
+  // REGEXS THAT REALLY MEAN IT'S IN STOCK
+  for (let i = elementsWithZeroChildren.length - 1; i >= 0; i--) {
+    const element = elementsWithZeroChildren[i];
+    if (element.offsetWidth > 0 || element.offsetHeight > 0 || element.getClientRects().length > 0) {
+      var elementText="";
+      if (element.tagName.toLowerCase() === "input") {
+        elementText = element.value.toLowerCase();
+      } else {
+        elementText = element.textContent.toLowerCase();
+      }
+
+      if (elementText.length) {
+        // try which ones could mean its in stock
+        for (let i = 0; i < negateOutOfStockRegexs.length; i++) {
+          if (negateOutOfStockRegexs_r[i].test(elementText)) {
+            return 'Possibly in stock';
+          }
+        }
+      }
+    }
+  }
+
+  // OTHER STUFF THAT COULD BE THAT IT'S OUT OF STOCK
+  for (let i = elementsWithZeroChildren.length - 1; i >= 0; i--) {
+    const element = elementsWithZeroChildren[i];
+    if (element.offsetWidth > 0 || element.offsetHeight > 0 || element.getClientRects().length > 0) {
+      var elementText="";
+      if (element.tagName.toLowerCase() === "input") {
+        elementText = element.value.toLowerCase();
+      } else {
+        elementText = element.textContent.toLowerCase();
+      }
+
+      if (elementText.length) {
+        // and these mean its out of stock
+        for (const outOfStockText of outOfStockTexts) {
+          if (elementText.includes(outOfStockText)) {
+            return elementText; // item is out of stock
+          }
+        }
+      }
+    }
+  }
+
+  return 'Possibly in stock'; // possibly in stock, cant decide otherwise.
+}
+
+// returns the element text that makes it think it's out of stock
+return isItemInStock();

changedetectionio/res/xpath_element_scraper.js

@@ -8,8 +8,14 @@
 // Some pages like https://www.londonstockexchange.com/stock/NCCL/ncondezi-energy-limited/analysis
 // will automatically force a scroll somewhere, so include the position offset
 // Lets hope the position doesnt change while we iterate the bbox's, but this is better than nothing
+var scroll_y = 0;
+try {
+    scroll_y = +document.documentElement.scrollTop || document.body.scrollTop
+} catch (e) {
+    console.log(e);
+}
+
 
-var scroll_y=+document.documentElement.scrollTop || document.body.scrollTop
 
 // Include the getXpath script directly, easier than fetching
 function getxpath(e) {
@@ -38,15 +44,15 @@ const findUpTag = (el) => {
     if (el.name !== undefined && el.name.length) {
         var proposed = el.tagName + "[name=" + el.name + "]";
         var proposed_element = window.document.querySelectorAll(proposed);
-        if(proposed_element.length) {
+        if (proposed_element.length) {
             if (proposed_element.length === 1) {
                 return proposed;
             } else {
                 // Some sites change ID but name= stays the same, we can hit it if we know the index
                 // Find all the elements that match and work out the input[n]
-                var n=Array.from(proposed_element).indexOf(el);
+                var n = Array.from(proposed_element).indexOf(el);
                 // Return a Playwright selector for nthinput[name=zipcode]
-                return proposed+" >> nth="+n;
+                return proposed + " >> nth=" + n;
             }
         }
     }

changedetectionio/run_basic_tests.sh

@@ -28,3 +28,11 @@ pytest tests/test_notification.py
 # Re-run with HIDE_REFERER set - could affect login
 export HIDE_REFERER=True
 pytest tests/test_access_control.py
+
+# Re-run a few tests that will trigger brotli based storage
+export SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD=5
+pytest tests/test_access_control.py
+pytest tests/test_notification.py
+pytest tests/test_backend.py
+pytest tests/test_rss.py
+pytest tests/test_unique_lines.py

changedetectionio/static/images/email.svg

@@ -0,0 +1,37 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Uploaded to: SVG Repo, www.svgrepo.com, Generator: SVG Repo Mixer Tools -->
+
+<svg
+   fill="#FFFFFF"
+   height="7.5005589"
+   width="11.248507"
+   version="1.1"
+   id="Layer_1"
+   viewBox="0 0 7.1975545 4.7993639"
+   xml:space="preserve"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg"><defs
+   id="defs19" />
+<g
+   id="g14"
+   transform="matrix(-0.01406065,0,0,0.01406065,7.1975543,-1.1990922)">
+	<g
+   id="g12">
+		<g
+   id="g10">
+			<path
+   d="M 468.373,85.28 H 45.333 C 21.227,85.28 0,105.76 0,129.014 V 383.2 c 0,23.147 21.227,43.413 45.333,43.413 h 422.933 c 23.68,0 43.627,-19.84 43.627,-43.413 V 129.014 C 512,105.334 492.053,85.28 468.373,85.28 Z m 0,320 H 45.333 c -12.373,0 -24,-10.773 -24,-22.08 V 129.014 c 0,-11.307 11.84,-22.4 24,-22.4 h 422.933 c 11.733,0 22.293,10.667 22.293,22.4 V 383.2 h 0.107 c 10e-4,11.734 -10.453,22.08 -22.293,22.08 z"
+   id="path2" />
+			<path
+   d="m 440.853,153.974 c -3.307,-4.907 -9.92,-6.187 -14.827,-2.987 L 256,264.48 85.973,151.094 c -4.907,-3.2 -11.52,-1.707 -14.72,3.2 -3.093,4.8 -1.813,11.307 2.88,14.507 l 176,117.333 c 3.627,2.347 8.213,2.347 11.84,0 l 176,-117.333 c 4.8,-3.201 6.187,-9.921 2.88,-14.827 z"
+   id="path4" />
+			<path
+   d="m 143.573,257.654 c -0.107,0.107 -0.32,0.213 -0.427,0.32 L 68.48,311.307 c -4.907,3.307 -6.187,9.92 -2.88,14.827 3.307,4.907 9.92,6.187 14.827,2.88 0.107,-0.107 0.32,-0.213 0.427,-0.32 l 74.667,-53.333 c 4.907,-3.307 6.187,-9.92 2.88,-14.827 -3.308,-4.907 -9.921,-6.187 -14.828,-2.88 z"
+   id="path6" />
+			<path
+   d="m 443.947,311.627 c -0.107,-0.107 -0.32,-0.213 -0.427,-0.32 l -74.667,-53.333 c -4.693,-3.52 -11.413,-2.56 -14.933,2.133 -3.52,4.693 -2.56,11.413 2.133,14.933 0.107,0.107 0.32,0.213 0.427,0.32 l 74.667,53.333 c 4.693,3.52 11.413,2.56 14.933,-2.133 3.52,-4.693 2.56,-11.413 -2.133,-14.933 z"
+   id="path8" />
+		</g>
+	</g>
+</g>
+</svg>

changedetectionio/static/images/generic-icon.svg

@@ -0,0 +1,3 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+<svg width="61.649mm" height="61.649mm" version="1.1" viewBox="0 0 61.649 61.649" xml:space="preserve" xmlns="http://www.w3.org/2000/svg"><g transform="translate(66.269 -15.463)" fill="#3056d3"><g transform="matrix(1.423 0 0 1.423 101.16 69.23)" fill="#3056d3"><g transform="matrix(.8229 0 0 .8229 -23.378 -2.3935)" fill="#3056d3"><path d="m-88.248-43.007a26.323 26.323 0 0 0-26.323 26.323 26.323 26.323 0 0 0 26.323 26.323 26.323 26.323 0 0 0 26.323-26.323 26.323 26.323 0 0 0-26.323-26.323zm0 2.8417a23.482 23.482 0 0 1 23.482 23.482 23.482 23.482 0 0 1-23.482 23.482 23.482 23.482 0 0 1-23.482-23.482 23.482 23.482 0 0 1 23.482-23.482z"/><g transform="matrix(.26458 0 0 .26458 -115.65 -44.085)"><path d="m33.02 64.43c0.35-0.05 2.04-0.13 2.04-0.13h25.53s3.17 0.32 3.67 0.53c2.5 1.05 3.98 1.89 6.04 3.57 0.72 0.58 4.12 4.01 4.12 4.01l51.67 57.39s1.61 1.65 1.97 1.94c1.2 0.97 2.48 1.96 3.98 2.32 0.5 0.12 2.72 0.21 2.72 0.21h27.32l-8.83-9.04s-1.31-1.65-1.44-1.94c-0.45-0.93-0.59-2.59-0.13-3.51 0.35-0.69 1.46-1.87 2.23-1.98 1.03-0.14 2.12-0.39 3.02 0.14 0.33 0.2 1.64 1.32 1.64 1.32l17.49 17.49s1.35 1.09 1.6 1.6c0.17 0.34 0.29 0.82 0.15 1.18-0.17 0.42-1.42 1.63-1.42 1.63l-0.94 0.98-15.69 16.37s-1.44 1.4-1.79 1.67c-0.76 0.6-1.99 0.89-2.96 0.9-1.03 0-2.62-1.11-3.26-1.91-0.6-0.76-1.1-2.22-0.77-3.13 0.16-0.45 1.28-1.85 1.28-1.85l11.36-11.3-29.47-0.02-1.68 0.09s-4.16-0.66-5.26-1.03c-1.63-0.56-3.44-1.82-4.75-2.93-0.39-0.33-1.8-1.92-1.8-1.92l-51.7-59.28s-2-2.06-2.43-2.43c-1.37-1.17-2-1.62-3.76-2.34-0.44-0.18-3.45-0.55-3.45-0.55l-24.13-0.22s-2.23-0.15-2.61-0.22c-1.08-0.21-2.16-1.07-2.81-1.83-0.79-0.92-0.59-3.06 0.06-4.09 0.57-0.89 2.14-1.52 3.19-1.66z"/><path d="m86.1 109.7-17.13 19.65s-2 2.06-2.43 2.43c-1.37 1.17-2 1.62-3.76 2.34-0.44 0.18-3.45 0.55-3.45 0.55l-24.13 0.22s-2.23 0.15-2.61 0.22c-1.08 0.21-2.16 1.07-2.81 1.83-0.79 0.92-0.59 3.06 0.06 4.09 0.57 0.89 2.14 1.52 3.19 1.66 0.35 0.05 2.04 0.13 2.04 0.13h25.53s3.17-0.32 3.67-0.53c2.5-1.05 3.98-1.89 6.04-3.57 0.72-0.58 4.12-4.01 4.12-4.01l17.38-19.3z"/><path d="m177.81 67.6c-0.17-0.42-1.42-1.63-1.42-1.63l-0.94-0.98-15.69-16.37s-1.44-1.4-1.79-1.67c-0.76-0.6-1.99-0.89-2.96-0.9-1.03 0-2.62 1.11-3.26 1.91-0.6 0.76-1.1 2.22-0.77 3.13 0.16 0.45 1.28 1.85 1.28 1.85l11.36 11.3-29.47 0.02-1.68-0.09s-4.16 0.66-5.26 1.03c-1.63 0.56-3.44 1.82-4.75 2.93-0.39 0.33-1.8 1.92-1.8 1.92l-18.91 21.69 5.98 5.98 18.38-20.41s1.61-1.65 1.97-1.94c1.2-0.97 2.48-1.96 3.98-2.32 0.5-0.12 2.72-0.21 2.72-0.21h27.32l-8.83 9.04s-1.31 1.65-1.44 1.94c-0.45 0.93-0.59 2.59-0.13 3.51 0.35 0.69 1.46 1.87 2.23 1.98 1.03 0.14 2.12 0.39 3.02-0.14 0.33-0.2 1.64-1.32 1.64-1.32l17.49-17.49s1.35-1.09 1.6-1.6c0.17-0.34 0.29-0.82 0.15-1.18z"/></g></g></g></g></svg>

changedetectionio/static/js/notifications.js

@@ -26,9 +26,6 @@ $(document).ready(function() {
     data = {
         window_url : window.location.href,
         notification_urls : $('.notification-urls').val(),
-        notification_title : $('.notification-title').val(),
-        notification_body : $('.notification-body').val(),
-        notification_format : $('.notification-format').val(),
     }
     for (key in data) {
       if (!data[key].length) {

changedetectionio/static/js/tabs.js

@@ -12,7 +12,7 @@ window.addEventListener('hashchange', function () {
 var has_errors = document.querySelectorAll(".messages .error");
 if (!has_errors.length) {
     if (document.location.hash == "") {
-        document.querySelector(".tabs ul li:first-child a").click();
+        location.replace(document.querySelector(".tabs ul li:first-child a").hash);
     } else {
         set_active_tab();
     }

changedetectionio/static/styles/scss/parts/_pagination.scss

@@ -0,0 +1,37 @@
+.pagination-page-info {
+  color: #fff;
+  font-size: 0.85rem;
+  text-transform: capitalize;
+}
+
+.pagination.menu {
+  > * {
+    display: inline-block;
+  }
+
+  li {
+    display: inline-block;
+  }
+
+  a {
+    padding: 0.65rem;
+    margin: 3px;
+    border: none;
+    background: #444;
+    border-radius: 2px;
+    color: var(--color-text-button);
+    &.disabled {
+      display: none;
+    }
+    &.active {
+      font-weight: bold;
+      background: #888;
+    }
+
+    &:hover {
+      background: #999;
+    }
+  }
+
+
+}

changedetectionio/static/styles/scss/styles.scss

@@ -5,6 +5,7 @@
 @import "parts/_arrows";
 @import "parts/_browser-steps";
 @import "parts/_extra_proxies";
+@import "parts/_pagination";
 @import "parts/_spinners";
 @import "parts/_variables";
 
@@ -241,6 +242,10 @@ body:before {
   font-size: 85%;
 }
 
+.button-xsmall {
+  font-size: 70%;
+}
+
 .fetch-error {
   padding-top: 1em;
   font-size: 80%;
@@ -889,6 +894,21 @@ body.full-width {
       font-size: .875em;
     }
   }
+  .text-filtering {
+    h3 {
+      margin-top: 0;
+    }
+    border: 1px solid #ccc;
+    padding: 1rem;
+    border-radius: 5px;
+    margin-bottom: 1rem;
+    fieldset:last-of-type {
+      padding-bottom: 0;
+      .pure-control-group {
+        padding-bottom: 0;
+      }
+    }
+  }
 }
 
 ul {
@@ -1044,3 +1064,30 @@ ul {
   vertical-align: middle;
 }
 
+
+#quick-watch-processor-type {
+  color: #fff;
+  ul {
+    padding: 0.3rem;
+
+    li {
+      list-style: none;
+      font-size: 0.8rem;
+    }
+  }
+
+}
+
+.restock-label {
+  &.in-stock {
+    background-color: var(--color-background-button-green);
+    color: #fff;
+  }
+  &.not-in-stock {
+    background-color: var(--color-background-button-cancel);
+    color: #777;
+  }
+  padding: 3px;
+  border-radius: 3px;
+  white-space: nowrap;
+}

changedetectionio/static/styles/styles.css

@@ -95,6 +95,32 @@ ul#requests-extra_proxies {
   ul#requests-extra_proxies table tr {
     display: inline; }
 
+.pagination-page-info {
+  color: #fff;
+  font-size: 0.85rem;
+  text-transform: capitalize; }
+
+.pagination.menu > * {
+  display: inline-block; }
+
+.pagination.menu li {
+  display: inline-block; }
+
+.pagination.menu a {
+  padding: 0.65rem;
+  margin: 3px;
+  border: none;
+  background: #444;
+  border-radius: 2px;
+  color: var(--color-text-button); }
+  .pagination.menu a.disabled {
+    display: none; }
+  .pagination.menu a.active {
+    font-weight: bold;
+    background: #888; }
+  .pagination.menu a:hover {
+    background: #999; }
+
 /* spinner */
 .spinner,
 .spinner:after {
@@ -432,6 +458,9 @@ body:before {
 .button-small {
   font-size: 85%; }
 
+.button-xsmall {
+  font-size: 70%; }
+
 .fetch-error {
   padding-top: 1em;
   font-size: 80%;
@@ -869,6 +898,17 @@ body.full-width .edit-form {
     color: var(--color-text-input-description); }
     .edit-form .pure-form-message-inline code {
       font-size: .875em; }
+  .edit-form .text-filtering {
+    border: 1px solid #ccc;
+    padding: 1rem;
+    border-radius: 5px;
+    margin-bottom: 1rem; }
+    .edit-form .text-filtering h3 {
+      margin-top: 0; }
+    .edit-form .text-filtering fieldset:last-of-type {
+      padding-bottom: 0; }
+      .edit-form .text-filtering fieldset:last-of-type .pure-control-group {
+        padding-bottom: 0; }
 
 ul {
   padding-left: 1em;
@@ -980,3 +1020,22 @@ ul {
   display: inline-block;
   height: 0.8rem;
   vertical-align: middle; }
+
+#quick-watch-processor-type {
+  color: #fff; }
+  #quick-watch-processor-type ul {
+    padding: 0.3rem; }
+    #quick-watch-processor-type ul li {
+      list-style: none;
+      font-size: 0.8rem; }
+
+.restock-label {
+  padding: 3px;
+  border-radius: 3px;
+  white-space: nowrap; }
+  .restock-label.in-stock {
+    background-color: var(--color-background-button-green);
+    color: #fff; }
+  .restock-label.not-in-stock {
+    background-color: var(--color-background-button-cancel);
+    color: #777; }

changedetectionio/store.py

@@ -287,6 +287,7 @@ class ChangeDetectionStore:
                     'method',
                     'paused',
                     'previous_md5',
+                    'processor',
                     'subtractive_selectors',
                     'tag',
                     'text_should_not_be_present',
@@ -315,7 +316,8 @@ class ChangeDetectionStore:
             # #Re 569
             new_watch = Watch.model(datastore_path=self.datastore_path, default={
                 'url': url,
-                'tag': tag
+                'tag': tag,
+                'date_created': int(time.time())
             })
 
             new_uuid = new_watch['uuid']
@@ -360,11 +362,6 @@ class ChangeDetectionStore:
             f.write(screenshot)
             f.close()
 
-        # Make a JPEG that's used in notifications (due to being a smaller size) available
-        from PIL import Image
-        im1 = Image.open(target_path)
-        im1.convert('RGB').save(target_path.replace('.png','.jpg'), quality=int(os.getenv("NOTIFICATION_SCREENSHOT_JPG_QUALITY", 75)))
-
 
     def save_error_text(self, watch_uuid, contents):
         if not self.data['watching'].get(watch_uuid):
@@ -683,3 +680,13 @@ class ChangeDetectionStore:
             except:
                 continue
         return
+
+    # We don't know when the date_created was in the past until now, so just add an index number for now.
+    def update_11(self):
+        i = 0
+        for uuid, watch in self.data['watching'].items():
+            if not watch.get('date_created'):
+                watch['date_created'] = i
+            i+=1
+        return
+

changedetectionio/templates/_common_fields.jinja

@@ -17,14 +17,15 @@
                                 <li><code>tgram://</code> bots cant send messages to other bots, so you should specify chat ID of non-bot user.</li>
                                 <li><code>tgram://</code> only supports very limited HTML and can fail when extra tags are sent, <a href="https://core.telegram.org/bots/api#html-style">read more here</a> (or use plaintext/markdown format)</li>
                                 <li><code>gets://</code>, <code>posts://</code>, <code>puts://</code>, <code>deletes://</code> for direct API calls (or omit the "<code>s</code>" for non-SSL ie <code>get://</code>)</li>
+                                  <li>Accepts the <code>{{ '{{token}}' }}</code> placeholders listed below</li>
                               </ul>
                             </div>
                             <div class="notifications-wrapper">
-                              <a id="send-test-notification" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Send test notification</a>
+                              <a id="send-test-notification" class="pure-button button-secondary button-xsmall" >Send test notification</a>
                             {% if emailprefix %}
-                              <a id="add-email-helper" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Add email</a>
+                              <a id="add-email-helper" class="pure-button button-secondary button-xsmall" >Add email <img style="height: 1em; display: inline-block" src="{{url_for('static_content', group='images', filename='email.svg')}}" alt="Add an email address"> </a>
                             {% endif %}
-                              <a href="{{url_for('notification_logs')}}" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Notification debug logs</a>
+                              <a href="{{url_for('notification_logs')}}" class="pure-button button-secondary button-xsmall" >Notification debug logs</a>
                             </div>
                         </div>
                         <div id="notification-customisation" class="pure-control-group">
@@ -103,6 +104,10 @@
                                         <td>The current snapshot value, useful when combined with JSON or CSS filters
                                         </td>
                                     </tr>
+                                    <tr>
+                                        <td><code>{{ '{{triggered_text}}' }}</code></td>
+                                        <td>Text that tripped the trigger from filters</td>
+                                    </tr>
                                     </tbody>
                                 </table>
                                 <div class="pure-form-message-inline">
@@ -110,7 +115,7 @@
                                     URLs generated by changedetection.io (such as <code>{{ '{{diff_url}}' }}</code>) require the <code>BASE_URL</code> environment variable set.<br>
                                     Your <code>BASE_URL</code> var is currently "{{settings_application['current_base_url']}}"
 									<br>
-									Warning: Contents of <code>{{ '{{diff}}' }}</code>, <code>{{ '{{diff_removed}}' }}</code>, and <code>{{ '{{diff_added}}' }}</code> depend on how the difference algorithm perceives the change. For example, an addition or removal could be perceived as a change in some cases. <a target="_new" href="https://github.com/dgtlmoon/changedetection.io/wiki/Using-the-%7B%7Bdiff%7D%7D,-%7B%7Bdiff_added%7D%7D,-and-%7B%7Bdiff_removal%7D%7D-notification-tokens">More Here</a> </br>
+									Warning: Contents of <code>{{ '{{diff}}' }}</code>, <code>{{ '{{diff_removed}}' }}</code>, and <code>{{ '{{diff_added}}' }}</code> depend on how the difference algorithm perceives the change. For example, an addition or removal could be perceived as a change in some cases. <a target="_new" href="https://github.com/dgtlmoon/changedetection.io/wiki/Using-the-%7B%7Bdiff%7D%7D,-%7B%7Bdiff_added%7D%7D,-and-%7B%7Bdiff_removal%7D%7D-notification-tokens">More Here</a> <br>
                                 </div>
                             </div>
                         </div>

changedetectionio/templates/_pagination.jinja

@@ -1,7 +0,0 @@
-{% macro pagination(sorted_watches, total_per_page, current_page) %}
-  {{ sorted_watches|length }}
-
-  {% for row in sorted_watches|batch(total_per_page, ' ') %}
-    {{ loop.index}}
-  {% endfor %}
-{% endmacro %}

changedetectionio/templates/base.html

@@ -2,35 +2,35 @@
 <html lang="en" data-darkmode="{{ get_darkmode_state() }}">
 
   <head>
-    <meta charset="utf-8"/>
-    <meta name="viewport" content="width=device-width, initial-scale=1.0"/>
-    <meta name="description" content="Self hosted website change detection."/>
+    <meta charset="utf-8" >
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" >
+    <meta name="description" content="Self hosted website change detection." >
     <title>Change Detection{{extra_title}}</title>
-    <link rel="alternate" type="application/rss+xml" title="Changedetection.io » Feed{% if active_tag %}- {{active_tag}}{% endif %}" href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}"/>
-    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='pure-min.css')}}"/>
-    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='styles.css')}}"/>
+    <link rel="alternate" type="application/rss+xml" title="Changedetection.io » Feed{% if active_tag %}- {{active_tag}}{% endif %}" href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}" >
+    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='pure-min.css')}}" >
+    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='styles.css')}}" >
     {% if extra_stylesheets %}
       {% for m in extra_stylesheets %}
-        <link rel="stylesheet" href="{{ m }}?ver=1000"/>
+        <link rel="stylesheet" href="{{ m }}?ver=1000" >
       {% endfor %}
     {% endif %}
 
-    <link rel="apple-touch-icon" sizes="180x180" href="{{url_for('static_content', group='favicons', filename='apple-touch-icon.png')}}"/>
-    <link rel="icon" type="image/png" sizes="32x32" href="{{url_for('static_content', group='favicons', filename='favicon-32x32.png')}}"/>
-    <link rel="icon" type="image/png" sizes="16x16" href="{{url_for('static_content', group='favicons', filename='favicon-16x16.png')}}"/>
-    <link rel="manifest" href="{{url_for('static_content', group='favicons', filename='site.webmanifest')}}"/>
-    <link rel="mask-icon" href="{{url_for('static_content', group='favicons', filename='safari-pinned-tab.svg')}}" color="#5bbad5"/>
-    <link rel="shortcut icon" href="{{url_for('static_content', group='favicons', filename='favicon.ico')}}"/>
-    <meta name="msapplication-TileColor" content="#da532c"/>
-    <meta name="msapplication-config" content="favicons/browserconfig.xml"/>
-    <meta name="theme-color" content="#ffffff"/>
+    <link rel="apple-touch-icon" sizes="180x180" href="{{url_for('static_content', group='favicons', filename='apple-touch-icon.png')}}">
+    <link rel="icon" type="image/png" sizes="32x32" href="{{url_for('static_content', group='favicons', filename='favicon-32x32.png')}}">
+    <link rel="icon" type="image/png" sizes="16x16" href="{{url_for('static_content', group='favicons', filename='favicon-16x16.png')}}">
+    <link rel="manifest" href="{{url_for('static_content', group='favicons', filename='site.webmanifest')}}">
+    <link rel="mask-icon" href="{{url_for('static_content', group='favicons', filename='safari-pinned-tab.svg')}}" color="#5bbad5">
+    <link rel="shortcut icon" href="{{url_for('static_content', group='favicons', filename='favicon.ico')}}">
+    <meta name="msapplication-TileColor" content="#da532c">
+    <meta name="msapplication-config" content="favicons/browserconfig.xml">
+    <meta name="theme-color" content="#ffffff">
 
     <style>
       body::before {
         background-image: url({{url_for('static_content', group='images', filename='gradient-border.png') }});
       }
     </style>
-    <script type="text/javascript" src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
+    <script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
   </head>
 
   <body>
@@ -137,16 +137,13 @@
           <li class="message">
             Share this link:
             <span id="share-link">{{ session['share-link'] }}</span>
-            <img style="height: 1em; display: inline-block" src="{{url_for('static_content', group='images', filename='copy.svg')}}"/>
+            <img style="height: 1em; display: inline-block" src="{{url_for('static_content', group='images', filename='copy.svg')}}" >
           </li>
         </ul>
       {% endif %}
       {% block content %}{% endblock %}
     </section>
-    <script
-      type="text/javascript"
-      src="{{url_for('static_content', group='js', filename='toggle-theme.js')}}"
-      defer></script>
+    <script src="{{url_for('static_content', group='js', filename='toggle-theme.js')}}" defer></script>
   </body>
 
 </html>

changedetectionio/templates/clear_all_history.html

@@ -6,7 +6,7 @@
       action="{{url_for('clear_all_history')}}"
       method="POST"
     >
-      <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" />
+      <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
       <fieldset>
         <div class="pure-control-group">
           This will remove version history (snapshots) for ALL watches, but keep

changedetectionio/templates/diff.html

@@ -7,7 +7,7 @@
     const error_screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid, error_screenshot=1) }}";
     {% endif %}
 </script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
 
 <div id="settings">
     <h1>Differences</h1>
@@ -15,15 +15,15 @@
         <fieldset>
 
             <label for="diffWords" class="pure-checkbox">
-                <input type="radio" name="diff_type" id="diffWords" value="diffWords"/> Words</label>
+                <input type="radio" name="diff_type" id="diffWords" value="diffWords"> Words</label>
             <label for="diffLines" class="pure-checkbox">
-                <input type="radio" name="diff_type" id="diffLines" value="diffLines" checked=""/> Lines</label>
+                <input type="radio" name="diff_type" id="diffLines" value="diffLines" checked=""> Lines</label>
 
             <label for="diffChars" class="pure-checkbox">
-                <input type="radio" name="diff_type" id="diffChars" value="diffChars"/> Chars</label>
+                <input type="radio" name="diff_type" id="diffChars" value="diffChars"> Chars</label>
             <!-- @todo - when mimetype is JSON, select this by default? -->
             <label for="diffJson" class="pure-checkbox">
-                <input type="radio" name="diff_type" id="diffJson" value="diffJson" /> JSON</label>
+                <input type="radio" name="diff_type" id="diffJson" value="diffJson" > JSON</label>
 
             {% if versions|length >= 1 %}
             <label for="diff-version">Compare newest (<span id="current-v-date"></span>) with</label>
@@ -43,7 +43,7 @@
     <span>
         <!-- https://github.com/kpdecker/jsdiff/issues/389 ? -->
         <label for="ignoreWhitespace" class="pure-checkbox" id="label-diff-ignorewhitespace">
-            <input type="checkbox" id="ignoreWhitespace" name="ignoreWhitespace"/> Ignore Whitespace</label>
+            <input type="checkbox" id="ignoreWhitespace" name="ignoreWhitespace" > Ignore Whitespace</label>
     </span>
 </div>
 
@@ -51,7 +51,7 @@
     <a onclick="next_diff();">Jump</a>
 </div>
 
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <div class="tabs">
     <ul>
         {% if last_error_text %}<li class="tab" id="error-text-tab"><a href="#error-text">Error Text</a></li> {% endif %}
@@ -72,7 +72,7 @@
 
     <div class="tab-pane-inner" id="error-screenshot">
         <div class="snapshot-age error">{{watch_a.snapshot_error_screenshot_ctime|format_seconds_ago}} seconds ago</div>
-        <img id="error-screenshot-img"  style="max-width: 80%" alt="Current error-ing screenshot from most recent request"/>
+        <img id="error-screenshot-img"  style="max-width: 80%" alt="Current error-ing screenshot from most recent request" >
     </div>
 
      <div class="tab-pane-inner" id="text">
@@ -105,7 +105,7 @@
          {% if is_html_webdriver %}
            {% if screenshot %}
             <div class="snapshot-age">{{watch_a.snapshot_screenshot_ctime|format_timestamp_timeago}}</div>
-            <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request"/>
+            <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request" >
            {% else %}
               No screenshot available just yet! Try rechecking the page.
            {% endif %}
@@ -117,7 +117,7 @@
         <form id="extract-data-form" class="pure-form pure-form-stacked edit-form"
               action="{{ url_for('diff_history_page', uuid=uuid) }}#extract"
               method="POST">
-            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
+            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
 
             <p>This tool will extract text data from all of the watch history.</p>
 
@@ -149,9 +149,9 @@
 <script>
     const newest_version_timestamp = {{newest_version_timestamp}};
 </script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff.min.js')}}"></script>
+<script src="{{url_for('static_content', group='js', filename='diff.min.js')}}"></script>
 
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-render.js')}}"></script>
+<script src="{{url_for('static_content', group='js', filename='diff-render.js')}}"></script>
 
 
 {% endblock %}

changedetectionio/templates/edit.html

@@ -2,7 +2,7 @@
 {% block content %}
 {% from '_helpers.jinja' import render_field, render_checkbox_field, render_button %}
 {% from '_common_fields.jinja' import render_common_settings_form %}
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <script>
     const notification_base_url="{{url_for('ajax_callback_send_notification_test')}}";
     const watch_visual_selector_data_url="{{url_for('static_content', group='visual_selector_data', filename=uuid)}}";
@@ -17,12 +17,12 @@
     const browser_steps_sync_url="{{url_for('browser_steps.browsersteps_ui_update', uuid=uuid)}}";
 </script>
 
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='visual-selector.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='visual-selector.js')}}" defer></script>
 {% if playwright_enabled %}
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='browser-steps.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='browser-steps.js')}}" defer></script>
 {% endif %}
 
 <div class="edit-form monospaced-textarea">
@@ -34,8 +34,15 @@
             {% if playwright_enabled %}
             <li class="tab"><a id="browsersteps-tab" href="#browser-steps">Browser Steps</a></li>
             {% endif %}
+
+            {% if watch['processor'] == 'text_json_diff' %}
             <li class="tab"><a id="visualselector-tab" href="#visualselector">Visual Filter Selector</a></li>
             <li class="tab"><a href="#filters-and-triggers">Filters &amp; Triggers</a></li>
+            {% endif %}
+
+            {% if watch['processor'] == 'restock_diff' %}
+            <li class="tab"><a href="#restock">Restock Detection</a></li>
+            {% endif %}
             <li class="tab"><a href="#notifications">Notifications</a></li>
         </ul>
     </div>
@@ -43,7 +50,7 @@
     <div class="box-wrap inner">
         <form class="pure-form pure-form-stacked"
               action="{{ url_for('edit_page', uuid=uuid, next = request.args.get('next'), unpause_on_save = request.args.get('unpause_on_save')) }}" method="POST">
-             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
+             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
 
             <div class="tab-pane-inner" id="general">
                 <fieldset>
@@ -51,6 +58,16 @@
                         {{ render_field(form.url, placeholder="https://...", required=true, class="m-d") }}
                         <span class="pure-form-message-inline">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></span><br>
                         <span class="pure-form-message-inline">You can use variables in the URL, perfect for inserting the current date and other logic, <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a></span><br>
+                        <span class="pure-form-message-inline">
+                        {% if watch['processor'] == 'text_json_diff' %}
+                            Current mode: <strong>Webpage Text/HTML, JSON and PDF changes.</strong><br>
+                          <a href="{{url_for('edit_page', uuid=uuid)}}?switch_processor=restock_diff" class="pure-button button-xsmall">Switch to re-stock detection mode.</a>
+                        {% else %}
+                        Current mode: <strong>Re-stock detection.</strong><br>
+                          <a href="{{url_for('edit_page', uuid=uuid)}}?switch_processor=text_json_diff" class="pure-button button-xsmall">Switch to Webpage Text/HTML, JSON and PDF changes mode.</a>
+                        {% endif %}
+                        </span>
+
                     </div>
                     <div class="pure-control-group">
                         {{ render_field(form.title, class="m-d") }}
@@ -146,7 +163,7 @@ User-Agent: wonderbra 1.0") }}
             </div>
             {% if playwright_enabled %}
             <div class="tab-pane-inner" id="browser-steps">
-                <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}">
+                <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}" alt="New beta functionality">
                 <fieldset>
                     <div class="pure-control-group">
                         <!--
@@ -173,7 +190,7 @@ User-Agent: wonderbra 1.0") }}
                                         </span>
                                         <div class="spinner"  style="display: none;"></div>
                                     </span>
-                                    <img  class="noselect" id="browsersteps-img" src="" style="max-width: 100%; width: 100%;" />
+                                    <img class="noselect" id="browsersteps-img" src="" style="max-width: 100%; width: 100%;" >
                                     <canvas  class="noselect" id="browsersteps-selector-canvas" style="max-width: 100%; width: 100%;"></canvas>
                                 </div>
                             </div>
@@ -203,7 +220,7 @@ User-Agent: wonderbra 1.0") }}
                     <div class="field-group" id="notification-field-group">
                         {% if has_default_notification_urls %}
                         <div class="inline-warning">
-                            <img class="inline-warning-icon" src="{{url_for('static_content', group='images', filename='notice.svg')}}" alt="Look out!" title="Lookout!"/>
+                            <img class="inline-warning-icon" src="{{url_for('static_content', group='images', filename='notice.svg')}}" alt="Look out!" title="Lookout!" >
                             There are <a href="{{ url_for('settings_page')}}#notifications">system-wide notification URLs enabled</a>, this form will override notification settings for this watch only &dash; an empty Notification URL list here will still send notifications.
                         </div>
                         {% endif %}
@@ -214,6 +231,7 @@ User-Agent: wonderbra 1.0") }}
                 </fieldset>
             </div>
 
+            {% if watch['processor'] == 'text_json_diff' %}
             <div class="tab-pane-inner" id="filters-and-triggers">
                     <div class="pure-control-group">
                             <strong>Pro-tips:</strong><br>
@@ -226,12 +244,6 @@ User-Agent: wonderbra 1.0") }}
                                 </li>
                             </ul>
                     </div>
-                    <fieldset>
-                        <div class="pure-control-group">
-                            {{ render_checkbox_field(form.check_unique_lines) }}
-                            <span class="pure-form-message-inline">Good for websites that just move the content around, and you want to know when NEW content is added, compares new lines against all history for this watch.</span>
-                        </div>
-                    </fieldset>
                     <div class="pure-control-group">
                         {% set field = render_field(form.include_filters,
                             rows=5,
@@ -269,37 +281,39 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                                 href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br>
                 </span>
                     </div>
-                    <div class="pure-control-group">
-                      {{ render_field(form.subtractive_selectors, rows=5, placeholder="header
+                <fieldset class="pure-control-group">
+                    {{ render_field(form.subtractive_selectors, rows=5, placeholder="header
 footer
 nav
 .stockticker") }}
-                      <span class="pure-form-message-inline">
+                    <span class="pure-form-message-inline">
                         <ul>
                           <li> Remove HTML element(s) by CSS selector before text conversion. </li>
                           <li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
                         </ul>
                       </span>
-                    </div>
-                <fieldset class="pure-group">
-                    {{ render_field(form.ignore_text, rows=5, placeholder="Some text to ignore in a line
-/some.regex\d{2}/ for case-INsensitive regex
-                    ") }}
-                    <span class="pure-form-message-inline">
-                        <ul>
-                            <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
-                            <li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
-                            <li>Changing this will affect the comparison checksum which may trigger an alert</li>
-                            <li>Use the preview/show current tab to see ignores</li>
-                        </ul>
-                </span>
+                </fieldset>
+                <div class="text-filtering">
+                <fieldset class="pure-group" id="text-filtering-type-options">
+                    <h3>Text filtering</h3>
+                        Limit trigger/ignore/block/extract to;<br>
+                        {{ render_checkbox_field(form.filter_text_added) }}
+                        {{ render_checkbox_field(form.filter_text_replaced) }}
+                        {{ render_checkbox_field(form.filter_text_removed) }}
+                    <span class="pure-form-message-inline">Note: Depending on the length and similarity of the text on each line, the algorithm may consider an <strong>addition</strong> instead of <strong>replacement</strong> for example.</span>
+                    <span class="pure-form-message-inline">So it's always better to select <strong>Added</strong>+<strong>Replaced</strong> when you're interested in new content.</span><br>
+                    <span class="pure-form-message-inline">When content is merely moved in a list, it will also trigger an <strong>addition</strong>, consider enabling <code><strong>Only trigger when unique lines appear</strong></code></span>
+                </fieldset>
 
-            </fieldset>
+                <fieldset class="pure-control-group">
+                    {{ render_checkbox_field(form.check_unique_lines) }}
+                    <span class="pure-form-message-inline">Good for websites that just move the content around, and you want to know when NEW content is added, compares new lines against all history for this watch.</span>
+                </fieldset>
                 <fieldset>
                     <div class="pure-control-group">
                         {{ render_field(form.trigger_text, rows=5, placeholder="Some text to wait for in a line
 /some.regex\d{2}/ for case-INsensitive regex
-                    ") }}
+") }}
                         <span class="pure-form-message-inline">
                     <ul>
                         <li>Text to wait for before triggering a change/notification, all text and regex are tested <i>case-insensitive</i>.</li>
@@ -310,6 +324,21 @@ nav
                         </span>
                     </div>
                 </fieldset>
+                <fieldset class="pure-group">
+                    {{ render_field(form.ignore_text, rows=5, placeholder="Some text to ignore in a line
+/some.regex\d{2}/ for case-INsensitive regex
+") }}
+                    <span class="pure-form-message-inline">
+                        <ul>
+                            <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
+                            <li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
+                            <li>Changing this will affect the comparison checksum which may trigger an alert</li>
+                            <li>Use the preview/show current tab to see ignores</li>
+                        </ul>
+                </span>
+
+                </fieldset>
+
                 <fieldset>
                     <div class="pure-control-group">
                         {{ render_field(form.text_should_not_be_present, rows=5, placeholder="For example: Out of stock
@@ -344,10 +373,24 @@ Unavailable") }}
                         </span>
                     </div>
                 </fieldset>
+                </div>
             </div>
+            {% endif %}
 
+            {% if watch['processor'] == 'restock_diff' %}
+            <div class="tab-pane-inner" id="restock">
+                    <fieldset>
+                        <div class="pure-control-group">
+                            {{ render_checkbox_field(form.in_stock_only) }}
+                            <span class="pure-form-message-inline">Only trigger notifications when page changes from <strong>out of stock</strong> to <strong>back in stock</strong></span>
+                        </div>
+                    </fieldset>
+            </div>
+            {% endif %}
+
+            {% if watch['processor'] == 'text_json_diff' %}
             <div class="tab-pane-inner visual-selector-ui" id="visualselector">
-                <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}">
+                <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}" alt="New beta functionality">
 
                 <fieldset>
                     <div class="pure-control-group">
@@ -364,7 +407,7 @@ Unavailable") }}
                                 <!-- request the screenshot and get the element offset info ready -->
                                 <!-- use img src ready load to know everything is ready to map out -->
                                 <!-- @todo: maybe something interesting like a field to select 'elements that contain text... and their parents n' -->
-                                <img id="selector-background" />
+                                <img id="selector-background" >
                                 <canvas id="selector-canvas"></canvas>
                             </div>
                             <div id="selector-current-xpath" style="overflow-x: hidden"><strong>Currently:</strong>&nbsp;<span class="text">Loading...</span></div>
@@ -378,6 +421,7 @@ Unavailable") }}
                     </div>
                 </fieldset>
             </div>
+            {% endif %}
 
             <div id="actions">
                 <div class="pure-control-group">

changedetectionio/templates/import.html

@@ -1,6 +1,7 @@
 {% extends 'base.html' %}
 {% block content %}
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+{% from '_helpers.jinja' import render_field %}
+<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <div class="edit-form monospaced-textarea">
 
     <div class="tabs collapsable">
@@ -12,9 +13,8 @@
 
     <div class="box-wrap inner">
         <form class="pure-form pure-form-aligned" action="{{url_for('import_page')}}" method="POST">
-            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
+            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
             <div class="tab-pane-inner" id="url-list">
-                <fieldset class="pure-group">
                     <legend>
                         Enter one URL per line, and optionally add tags for each URL after a space, delineated by comma
                         (,):
@@ -23,7 +23,7 @@
                         <br>
                         URLs which do not pass validation will stay in the textarea.
                     </legend>
-
+                {{ render_field(form.processor, class="processor") }}
 
                     <textarea name="urls" class="pure-input-1-2" placeholder="https://"
                               style="width: 100%;
@@ -31,15 +31,17 @@
                                 white-space: pre;
                                 overflow-wrap: normal;
                                 overflow-x: scroll;" rows="25">{{ import_url_list_remaining }}</textarea>
-                </fieldset>
 
+<div id="quick-watch-processor-type">
+
+                    </div>
 
             </div>
 
             <div class="tab-pane-inner" id="distill-io">
 
 
-                <fieldset class="pure-group">
+
                     <legend>
                         Copy and Paste your Distill.io watch 'export' file, this should be a JSON file.<br>
                         This is <i>experimental</i>, supported fields are <code>name</code>, <code>uri</code>, <code>tags</code>, <code>config:selections</code>, the rest (including <code>schedule</code>) are ignored.
@@ -75,7 +77,7 @@
     ]
 }
 " rows="25">{{ original_distill_json }}</textarea>
-                </fieldset>
+
             </div>
             <button type="submit" class="pure-button pure-input-1-2 pure-button-primary">Import</button>
         </form>

changedetectionio/templates/login.html

@@ -4,13 +4,13 @@
 <div class="login-form">
  <div class="inner">
     <form class="pure-form pure-form-stacked" action="{{url_for('login')}}" method="POST">
-        <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
+        <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
         <fieldset>
             <div class="pure-control-group">
                 <label for="password">Password</label>
                 <input type="password" id="password" required="" name="password" value=""
                        size="15" autofocus />
-                <input type="hidden" id="email" name="email" value="defaultuser@changedetection.io" />
+                <input type="hidden" id="email" name="email" value="defaultuser@changedetection.io" >
             </div>
             <div class="pure-control-group">
                 <button type="submit" class="pure-button pure-button-primary">Login</button>

changedetectionio/templates/preview.html

@@ -7,9 +7,9 @@
     const error_screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid, error_screenshot=1) }}";
     {% endif %}
 </script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
 
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <div class="tabs">
     <ul>
         {% if last_error_text %}<li class="tab" id="error-text-tab"><a href="#error-text">Error Text</a></li> {% endif %}
@@ -31,7 +31,7 @@
 
     <div class="tab-pane-inner" id="error-screenshot">
         <div class="snapshot-age error">{{watch.snapshot_error_screenshot_ctime|format_seconds_ago}} seconds ago</div>
-        <img id="error-screenshot-img"  style="max-width: 80%" alt="Current erroring screenshot from most recent request"/>
+        <img id="error-screenshot-img"  style="max-width: 80%" alt="Current erroring screenshot from most recent request" >
     </div>
 
     <div class="tab-pane-inner" id="text">
@@ -58,7 +58,7 @@
          {% if is_html_webdriver %}
            {% if screenshot %}
              <div class="snapshot-age">{{watch.snapshot_screenshot_ctime|format_timestamp_timeago}}</div>
-             <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request"/>
+             <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request" >
            {% else %}
               No screenshot available just yet! Try rechecking the page.
            {% endif %}

changedetectionio/templates/settings.html

@@ -9,10 +9,10 @@
     const email_notification_prefix=JSON.parse('{{emailprefix|tojson}}');
 {% endif %}
 </script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
 
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='global-settings.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='global-settings.js')}}" defer></script>
 <div class="edit-form">
     <div class="tabs collapsable">
         <ul>
@@ -26,7 +26,7 @@
     </div>
     <div class="box-wrap inner">
         <form class="pure-form pure-form-stacked settings" action="{{url_for('settings_page')}}" method="POST">
-            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
+            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
             <div class="tab-pane-inner" id="general">
                 <fieldset>
                     <div class="pure-control-group">

changedetectionio/templates/watch-overview.html

@@ -1,14 +1,13 @@
 {% extends 'base.html' %}
 {% block content %}
 {% from '_helpers.jinja' import render_simple_field, render_field %}
-{% from '_pagination.jinja' import pagination %}
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
+<script src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
 
 <div class="box">
 
     <form class="pure-form" action="{{ url_for('form_quick_watch_add') }}" method="POST" id="new-watch-form">
-        <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
+        <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
         <fieldset>
             <legend>Add a new change detection watch</legend>
             <div id="watch-add-wrapper-zone">
@@ -21,21 +20,30 @@
                     {{ render_simple_field(form.edit_and_watch_submit_button, title="Edit first then Watch") }}
                 </div>
             </div>
+            <div id="quick-watch-processor-type">
+                {{ render_simple_field(form.processor, title="Edit first then Watch") }}
+            </div>
+
         </fieldset>
-        <span style="color:#eee; font-size: 80%;"><img style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread-white.svg')}}" /> Tip: You can also add 'shared' watches. <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Sharing-a-Watch">More info</a></a></span>
+        <span style="color:#eee; font-size: 80%;"><img alt="Create a shareable link" style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread-white.svg')}}" > Tip: You can also add 'shared' watches. <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Sharing-a-Watch">More info</a></span>
     </form>
 
     <form class="pure-form" action="{{ url_for('form_watch_list_checkbox_operations') }}" method="POST" id="watch-list-form">
-    <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
+    <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" >
     <div id="checkbox-operations">
-        <button class="pure-button button-secondary button-xsmall" style="font-size: 70%"  name="op" value="pause">Pause</button>
-        <button class="pure-button button-secondary button-xsmall" style="font-size: 70%"  name="op" value="unpause">UnPause</button>
-        <button class="pure-button button-secondary button-xsmall" style="font-size: 70%"  name="op" value="mute">Mute</button>
-        <button class="pure-button button-secondary button-xsmall" style="font-size: 70%"  name="op" value="unmute">UnMute</button>
-        <button class="pure-button button-secondary button-xsmall" style="font-size: 70%" name="op" value="recheck">Recheck</button>
-        <button class="pure-button button-secondary button-xsmall" style="font-size: 70%" name="op" value="notification-default">Use default notification</button>
-        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242; font-size: 70%" name="op" value="delete">Delete</button>
+        <button class="pure-button button-secondary button-xsmall"  name="op" value="pause">Pause</button>
+        <button class="pure-button button-secondary button-xsmall"  name="op" value="unpause">UnPause</button>
+        <button class="pure-button button-secondary button-xsmall"  name="op" value="mute">Mute</button>
+        <button class="pure-button button-secondary button-xsmall"  name="op" value="unmute">UnMute</button>
+        <button class="pure-button button-secondary button-xsmall" name="op" value="recheck">Recheck</button>
+        <button class="pure-button button-secondary button-xsmall" name="op" value="mark-viewed">Mark viewed</button>
+        <button class="pure-button button-secondary button-xsmall" name="op" value="notification-default">Use default notification</button>
+        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="clear-history">Clear/reset history</button>
+        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="delete">Delete</button>
     </div>
+    {% if watches|length >= pagination.per_page %}
+        {{ pagination.info }}
+    {% endif %}
     <div>
         <a href="{{url_for('index')}}" class="pure-button button-tag {{'active' if not active_tag }}">All</a>
         {% for tag in tags %}
@@ -45,18 +53,19 @@
         {% endfor %}
     </div>
 
-    {% set sort_order = request.args.get('order', 'asc') == 'asc' %}
-    {% set sort_attribute = request.args.get('sort', 'last_changed')   %}
+    {% set sort_order = sort_order or 'asc' %}
+    {% set sort_attribute = sort_attribute or 'last_changed'  %}
     {% set pagination_page = request.args.get('page', 0) %}
 
     <div id="watch-table-wrapper">
+
         <table class="pure-table pure-table-striped watch-table">
             <thead>
             <tr>
-                <th><input style="vertical-align: middle" type="checkbox" id="check-all"/> #</th>
-                <th></th>
-                {% set link_order = "desc" if sort_order else "asc" %}
+                {% set link_order = "desc" if sort_order  == 'asc' else "asc" %}
                 {% set arrow_span = "" %}
+                <th><input style="vertical-align: middle" type="checkbox" id="check-all" > <a class="{{ 'active '+link_order if sort_attribute == 'date_created' else 'inactive' }}"  href="{{url_for('index', sort='date_created', order=link_order, tag=active_tag)}}"># <span class='arrow {{link_order}}'></span></a></th>
+                <th></th>
                 <th><a class="{{ 'active '+link_order if sort_attribute == 'label' else 'inactive' }}" href="{{url_for('index', sort='label', order=link_order, tag=active_tag)}}">Website <span class='arrow {{link_order}}'></span></a></th>
                 <th><a class="{{ 'active '+link_order if sort_attribute == 'last_checked' else 'inactive' }}" href="{{url_for('index', sort='last_checked', order=link_order, tag=active_tag)}}">Last Checked <span class='arrow {{link_order}}'></span></a></th>
                 <th><a class="{{ 'active '+link_order if sort_attribute == 'last_changed' else 'inactive' }}" href="{{url_for('index', sort='last_changed', order=link_order, tag=active_tag)}}">Last Changed <span class='arrow {{link_order}}'></span></a></th>
@@ -65,39 +74,34 @@
             </thead>
             <tbody>
 
-            {% set sorted_watches = watches|sort(attribute=sort_attribute, reverse=sort_order) %}
-            {% for watch in sorted_watches %}
-
-            {# WIP for pagination, disabled for now
-              {% if not ( loop.index >= 3 and loop.index <=4) %}{% continue %}{% endif %} -->
-             #}
+            {% for watch in (watches|sort(attribute=sort_attribute, reverse=sort_order == 'asc'))[pagination.skip:pagination.skip+pagination.per_page] %}
             <tr id="{{ watch.uuid }}"
-                class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }}
+                class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }} processor-{{ watch['processor'] }}
                 {% if watch.last_error is defined and watch.last_error != False %}error{% endif %}
                 {% if watch.last_notification_error is defined and watch.last_notification_error != False %}error{% endif %}
                 {% if watch.paused is defined and watch.paused != False %}paused{% endif %}
                 {% if watch.newest_history_key| int > watch.last_viewed and watch.history_n>=2 %}unviewed{% endif %}
                 {% if watch.uuid in queued_uuids %}queued{% endif %}">
-                <td class="inline checkbox-uuid" ><input name="uuids"  type="checkbox" value="{{ watch.uuid}} "/> <span>{{ loop.index }}</span></td>
+                <td class="inline checkbox-uuid" ><input name="uuids"  type="checkbox" value="{{ watch.uuid}} " > <span>{{ loop.index+pagination.skip }}</span></td>
                 <td class="inline watch-controls">
                     {% if not watch.paused %}
-                    <a class="state-off" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="Pause checks" title="Pause checks" class="icon icon-pause"/></a>
+                    <a class="state-off" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="Pause checks" title="Pause checks" class="icon icon-pause" ></a>
                     {% else %}
-                    <a class="state-on" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='play.svg')}}" alt="UnPause checks" title="UnPause checks" class="icon icon-unpause"/></a>
+                    <a class="state-on" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='play.svg')}}" alt="UnPause checks" title="UnPause checks" class="icon icon-unpause" ></a>
                     {% endif %}
-                    <a class="link-mute state-{{'on' if watch.notification_muted else 'off'}}" href="{{url_for('index', op='mute', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications" class="icon icon-mute"/></a>
+                    <a class="link-mute state-{{'on' if watch.notification_muted else 'off'}}" 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" class="icon icon-mute" ></a>
                 </td>
                 <td class="title-col inline">{{watch.title if watch.title is not none and watch.title|length > 0 else watch.url}}
                     <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}"></a>
-                    <a class="link-spread" href="{{url_for('form_share_put_watch', uuid=watch.uuid)}}"><img class="status-icon"  src="{{url_for('static_content', group='images', filename='spread.svg')}}" class="status-icon icon icon-spread" title="Create a link to share watch config with others" /></a>
+                    <a class="link-spread" href="{{url_for('form_share_put_watch', uuid=watch.uuid)}}"><img src="{{url_for('static_content', group='images', filename='spread.svg')}}" class="status-icon icon icon-spread" title="Create a link to share watch config with others" ></a>
 
                     {% if watch.get_fetch_backend == "html_webdriver"
                          or (  watch.get_fetch_backend == "system" and system_default_fetcher == 'html_webdriver'  )
                     %}
-                    <img class="status-icon" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" title="Using a chrome browser" />
+                    <img class="status-icon" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" title="Using a chrome browser" >
                     {% endif %}
 
-                    {%if watch.is_pdf  %}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" title="Converting PDF to text" />{% endif %}
+                    {%if watch.is_pdf  %}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" title="Converting PDF to text" >{% endif %}
                     {% if watch.last_error is defined and watch.last_error != False %}
                     <div class="fetch-error">{{ watch.last_error }}
 
@@ -113,12 +117,27 @@
                     {% if watch.last_notification_error is defined and watch.last_notification_error != False %}
                     <div class="fetch-error notification-error"><a href="{{url_for('notification_logs')}}">{{ watch.last_notification_error }}</a></div>
                     {% endif %}
-                    {% if watch['has_ldjson_price_data'] and not watch['track_ldjson_price_data']  %}
-                    <div class="ldjson-price-track-offer">Embedded price data detected, follow only price data? <a href="{{url_for('price_data_follower.accept', uuid=watch.uuid)}}" class="pure-button button-xsmall">Yes</a> <a href="{{url_for('price_data_follower.reject', uuid=watch.uuid)}}" class="">No</a></div>
+
+                    {% if watch['processor'] == 'text_json_diff'  %}
+                        {% if watch['has_ldjson_price_data'] and not watch['track_ldjson_price_data']  %}
+                        <div class="ldjson-price-track-offer">Embedded price data detected, follow only price data? <a href="{{url_for('price_data_follower.accept', uuid=watch.uuid)}}" class="pure-button button-xsmall">Yes</a> <a href="{{url_for('price_data_follower.reject', uuid=watch.uuid)}}" class="">No</a></div>
+                        {% endif %}
+                        {% if watch['track_ldjson_price_data'] == 'accepted' %}
+                        <span class="tracking-ldjson-price-data" title="Automatically following embedded price information"><img src="{{url_for('static_content', group='images', filename='price-tag-icon.svg')}}"  class="status-icon price-follow-tag-icon" > Price</span>
+                        {% endif %}
                     {% endif %}
-                    {% if watch['track_ldjson_price_data'] == 'accepted' %}
-                    <span class="tracking-ldjson-price-data" title="Automatically following embedded price information"><img src="{{url_for('static_content', group='images', filename='price-tag-icon.svg')}}"  class="status-icon price-follow-tag-icon"/> Price</span>
+
+                    {% if watch['processor'] == 'restock_diff'  %}
+                    <span class="restock-label {{'in-stock' if watch['in_stock'] else 'not-in-stock' }}" title="detecting restock conditions">
+                        <!-- maybe some object watch['processor'][restock_diff] or.. -->
+                        {% if watch['last_checked'] %}
+                            {% if watch['in_stock'] %} In stock {% else %} Not in stock {% endif %}
+                        {% else %}
+                            Not yet checked
+                        {% endif %}
+                    </span>
                     {% endif %}
+
                     {% if not active_tag %}
                     <span class="watch-tag-list">{{ watch.tag}}</span>
                     {% endif %}
@@ -160,10 +179,7 @@
                 <a href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}"><img alt="RSS Feed" id="feed-icon" src="{{url_for('static_content', group='images', filename='Generic_Feed-icon.svg')}}" height="15"></a>
             </li>
         </ul>
-        {# WIP for pagination, disabled for now
-         {{ pagination(sorted_watches,3, pagination_page) }}
-         #}
-
+        {{ pagination.links }}
     </div>
     </form>
 </div>

changedetectionio/tests/restock/__init__.py

@@ -0,0 +1,2 @@
+"""Tests for the app."""
+

changedetectionio/tests/restock/conftest.py

@@ -0,0 +1,3 @@
+#!/usr/bin/python3
+
+from .. import conftest

changedetectionio/tests/restock/test_restock.py

@@ -0,0 +1,106 @@
+#!/usr/bin/python3
+import os
+import time
+from flask import url_for
+from ..util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+from changedetectionio.notification import (
+    default_notification_body,
+    default_notification_format,
+    default_notification_title,
+    valid_notification_formats,
+)
+
+
+def set_original_response():
+    test_return_data = """<html>
+       <body>
+     Some initial text<br>
+     <p>Which is across multiple lines</p>
+     <br>
+     So let's see what happens.  <br>
+     <div>price: $10.99</div>
+     <div id="sametext">Out of stock</div>
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+    return None
+
+
+
+def set_back_in_stock_response():
+    test_return_data = """<html>
+       <body>
+     Some initial text<br>
+     <p>Which is across multiple lines</p>
+     <br>
+     So let's see what happens.  <br>
+     <div>price: $10.99</div>
+     <div id="sametext">Available!</div>
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+    return None
+
+# Add a site in paused mode, add an invalid filter, we should still have visual selector data ready
+def test_restock_detection(client, live_server):
+
+    set_original_response()
+    #assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
+
+    time.sleep(1)
+    live_server_setup(live_server)
+    #####################
+    notification_url = url_for('test_notification_endpoint', _external=True).replace('http://localhost', 'http://changedet').replace('http', 'json')
+
+
+    #####################
+    # Set this up for when we remove the notification from the watch, it should fallback with these details
+    res = client.post(
+        url_for("settings_page"),
+        data={"application-notification_urls": notification_url,
+              "application-notification_title": "fallback-title "+default_notification_title,
+              "application-notification_body": "fallback-body "+default_notification_body,
+              "application-notification_format": default_notification_format,
+              "requests-time_between_check-minutes": 180,
+              'application-fetch_backend': "html_webdriver"},
+        follow_redirects=True
+    )
+    # Add our URL to the import page, because the docker container (playwright/selenium) wont be able to connect to our usual test url
+    test_url = url_for('test_endpoint', _external=True).replace('http://localhost', 'http://changedet')
+
+
+    client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tag": '', 'processor': 'restock_diff'},
+        follow_redirects=True
+    )
+
+    # Is it correctly show as NOT in stock?
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'not-in-stock' in res.data
+
+    # Is it correctly shown as in stock
+    set_back_in_stock_response()
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'not-in-stock' not in res.data
+
+    # We should have a notification
+    time.sleep(2)
+    assert os.path.isfile("test-datastore/notification.txt")
+    os.unlink("test-datastore/notification.txt")
+
+    # Default behaviour is to only fire notification when it goes OUT OF STOCK -> IN STOCK
+    # So here there should be no file, because we go IN STOCK -> OUT OF STOCK
+    set_original_response()
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    wait_for_all_checks(client)
+    assert not os.path.isfile("test-datastore/notification.txt")

changedetectionio/tests/test_add_replace_remove_filter.py

@@ -0,0 +1,176 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from .util import live_server_setup
+from changedetectionio import html_tools
+
+
+def set_original(excluding=None, add_line=None):
+    test_return_data = """<html>
+     <body>
+     <p>Some initial text</p>
+     <p>So let's see what happens.</p>
+     <p>and a new line!</p>
+     <p>The golden line</p>
+     <p>A BREAK TO MAKE THE TOP LINE STAY AS "REMOVED" OR IT WILL GET COUNTED AS "CHANGED INTO"</p>
+     <p>Something irrelevant</p>          
+     </body>
+     </html>
+    """
+
+    if add_line:
+        c=test_return_data.splitlines()
+        c.insert(5, add_line)
+        test_return_data = "\n".join(c)
+
+    if excluding:
+        output = ""
+        for i in test_return_data.splitlines():
+            if not excluding in i:
+                output += f"{i}\n"
+
+        test_return_data = output
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+def test_setup(client, live_server):
+    live_server_setup(live_server)
+
+def test_check_removed_line_contains_trigger(client, live_server):
+    sleep_time_for_fetch_thread = 3
+
+    # Give the endpoint time to spin up
+    time.sleep(1)
+    set_original()
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # 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={"trigger_text": 'The golden line',
+              "url": test_url,
+              'fetch_backend': "html_requests",
+              'filter_text_removed': 'y'},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    time.sleep(sleep_time_for_fetch_thread)
+    set_original(excluding='Something irrelevant')
+
+    # A line thats not the trigger should not trigger anything
+    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    assert b'1 watches queued for rechecking.' in res.data
+    time.sleep(sleep_time_for_fetch_thread)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
+
+    # The trigger line is REMOVED,  this should trigger
+    set_original(excluding='The golden line')
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    time.sleep(sleep_time_for_fetch_thread)
+    res = client.get(url_for("index"))
+    assert b'unviewed' in res.data
+
+
+    # Now add it back, and we should not get a trigger
+    client.get(url_for("mark_all_viewed"), follow_redirects=True)
+    set_original(excluding=None)
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    time.sleep(sleep_time_for_fetch_thread)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
+
+    # Remove it again, and we should get a trigger
+    set_original(excluding='The golden line')
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    time.sleep(sleep_time_for_fetch_thread)
+    res = client.get(url_for("index"))
+    assert b'unviewed' in res.data
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+
+def test_check_add_line_contains_trigger(client, live_server):
+
+    sleep_time_for_fetch_thread = 3
+
+    # Give the endpoint time to spin up
+    time.sleep(1)
+    test_notification_url = url_for('test_notification_endpoint', _external=True).replace('http://', 'post://') + "?xxx={{ watch_url }}"
+
+    res = client.post(
+        url_for("settings_page"),
+        data={"application-notification_title": "New ChangeDetection.io Notification - {{ watch_url }}",
+              "application-notification_body": 'triggered text was -{{triggered_text}}-',
+              # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
+              "application-notification_urls": test_notification_url,
+              "application-minutes_between_check": 180,
+              "application-fetch_backend": "html_requests"
+              },
+        follow_redirects=True
+    )
+    assert b'Settings updated' in res.data
+
+    set_original()
+    # 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
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # 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={"trigger_text": 'Oh yes please',
+              "url": test_url,
+              'fetch_backend': "html_requests",
+              'filter_text_removed': '',
+              'filter_text_added': 'y'},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    time.sleep(sleep_time_for_fetch_thread)
+    set_original(excluding='Something irrelevant')
+
+    # A line thats not the trigger should not trigger anything
+    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    assert b'1 watches queued for rechecking.' in res.data
+    time.sleep(sleep_time_for_fetch_thread)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
+
+    # The trigger line is ADDED,  this should trigger
+    set_original(add_line='<p>Oh yes please</p>')
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    time.sleep(sleep_time_for_fetch_thread)
+    res = client.get(url_for("index"))
+    assert b'unviewed' in res.data
+
+    with open("test-datastore/notification.txt", 'r') as f:
+        response= f.read()
+        assert '-Oh yes please-' in response
+
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

changedetectionio/tests/test_block_while_text_present.py

@@ -87,7 +87,10 @@ def test_check_block_changedetection_text_NOT_present(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"text_should_not_be_present": ignore_text, "url": test_url, 'fetch_backend': "html_requests"},
+        data={"text_should_not_be_present": ignore_text,
+              "url": test_url,
+              'fetch_backend': "html_requests"
+              },
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -129,7 +132,6 @@ def test_check_block_changedetection_text_NOT_present(client, live_server):
     set_modified_response_minus_block_text()
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(sleep_time_for_fetch_thread)
-
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
 

changedetectionio/tests/test_errorhandling.py

@@ -59,6 +59,8 @@ def test_http_error_handler(client, live_server):
     _runner_test_http_errors(client, live_server, 404, 'Page not found')
     _runner_test_http_errors(client, live_server, 500, '(Internal server Error) received')
     _runner_test_http_errors(client, live_server, 400, 'Error - Request returned a HTTP error code 400')
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
 
 # Just to be sure error text is properly handled
 def test_DNS_errors(client, live_server):
@@ -81,4 +83,48 @@ def test_DNS_errors(client, live_server):
     assert found_name_resolution_error
     # Should always record that we tried
     assert bytes("just now".encode('utf-8')) in res.data
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
 
+# Re 1513
+def test_low_level_errors_clear_correctly(client, live_server):
+    #live_server_setup(live_server)
+    # Give the endpoint time to spin up
+    time.sleep(1)
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write("<html><body><div id=here>Hello world</div></body></html>")
+
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": "https://dfkjasdkfjaidjfsdajfksdajfksdjfDOESNTEXIST.com"},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+    time.sleep(2)
+
+    # We should see the DNS error
+    res = client.get(url_for("index"))
+    found_name_resolution_error = b"Temporary failure in name resolution" in res.data or b"Name or service not known" in res.data
+    assert found_name_resolution_error
+
+    # Update with what should work
+    client.post(
+        url_for("edit_page", uuid="first"),
+        data={
+            "url": test_url,
+            "fetch_backend": "html_requests"},
+        follow_redirects=True
+    )
+
+    # Now the error should be gone
+    time.sleep(2)
+    res = client.get(url_for("index"))
+    found_name_resolution_error = b"Temporary failure in name resolution" in res.data or b"Name or service not known" in res.data
+    assert not found_name_resolution_error
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

changedetectionio/tests/test_ignore_regex_text.py

@@ -9,7 +9,7 @@ def test_setup(live_server):
 # Unit test of the stripper
 # Always we are dealing in utf-8
 def test_strip_regex_text_func():
-    from ..fetchers import text_json_diff as fetch_site_status
+    from ..processors import text_json_diff as fetch_site_status
 
     test_content = """
     but sometimes we want to remove the lines.

changedetectionio/tests/test_ignore_text.py

@@ -11,7 +11,8 @@ def test_setup(live_server):
 # Unit test of the stripper
 # Always we are dealing in utf-8
 def test_strip_text_func():
-    from ..fetchers import text_json_diff as fetch_site_status
+    from ..processors import text_json_diff as fetch_site_status
+
 
     test_content = """
     Some content

changedetectionio/tests/test_jsonpath_jq_selector.py

@@ -198,8 +198,8 @@ def test_check_json_without_filter(client, live_server):
     )
 
     # Should still see '"html": "<b>"'
-    assert b'&#34;&lt;b&gt;' in res.data
-    assert res.data.count(b'{\n') >= 2
+    assert b'&#34;html&#34;: &#34;&lt;b&gt;&#34;' in res.data
+    assert res.data.count(b'{') >= 2
 
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data

changedetectionio/tests/test_notification.py

@@ -73,16 +73,12 @@ def test_check_notification(client, live_server):
     # We write the PNG to disk, but a JPEG should appear in the notification
     # Write the last screenshot png
     testimage_png = 'iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNkYAAAAAYAAjCB0C8AAAAASUVORK5CYII='
-    # This one is created when we save the screenshot from the webdriver/playwright session (converted from PNG)
-    testimage_jpg = '/9j/4AAQSkZJRgABAQEASABIAAD/2wBDAAMCAgMCAgMDAwMEAwMEBQgFBQQEBQoHBwYIDAoMDAsKCwsNDhIQDQ4RDgsLEBYQERMUFRUVDA8XGBYUGBIUFRT/wAALCAABAAEBAREA/8QAFAABAAAAAAAAAAAAAAAAAAAACf/EABQQAQAAAAAAAAAAAAAAAAAAAAD/2gAIAQEAAD8AKp//2Q=='
 
 
     uuid = extract_UUID_from_client(client)
     datastore = 'test-datastore'
     with open(os.path.join(datastore, str(uuid), 'last-screenshot.png'), 'wb') as f:
         f.write(base64.b64decode(testimage_png))
-    with open(os.path.join(datastore, str(uuid), 'last-screenshot.jpg'), 'wb') as f:
-        f.write(base64.b64decode(testimage_jpg))
 
     # Goto the edit page, add our ignore text
     # Add our URL to the import page
@@ -162,12 +158,12 @@ def test_check_notification(client, live_server):
 
     # Check the attachment was added, and that it is a JPEG from the original PNG
     notification_submission_object = json.loads(notification_submission)
-    assert notification_submission_object['attachments'][0]['filename'] == 'last-screenshot.jpg'
+    # We keep PNG screenshots for now
+    assert notification_submission_object['attachments'][0]['filename'] == 'last-screenshot.png'
     assert len(notification_submission_object['attachments'][0]['base64'])
-    assert notification_submission_object['attachments'][0]['mimetype'] == 'image/jpeg'
+    assert notification_submission_object['attachments'][0]['mimetype'] == 'image/png'
     jpeg_in_attachment = base64.b64decode(notification_submission_object['attachments'][0]['base64'])
-    assert b'JFIF' in jpeg_in_attachment
-    assert testimage_png not in notification_submission
+
     # Assert that the JPEG is readable (didn't get chewed up somewhere)
     from PIL import Image
     import io
@@ -299,7 +295,10 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server):
         follow_redirects=True
     )
     assert b'Settings updated' in res.data
-
+    client.get(
+        url_for("form_delete", uuid="all"),
+        follow_redirects=True
+    )
     # Add a watch and trigger a HTTP POST
     test_url = url_for('test_endpoint', _external=True)
     res = client.post(

changedetectionio/tests/test_unique_lines.py

@@ -94,7 +94,6 @@ def test_unique_lines_functionality(client, live_server):
     res = client.get(url_for("index"))
     assert b'unviewed' not in res.data
 
-
     # Now set the content which contains the new text and re-ordered existing text
     set_modified_with_trigger_text_response()
     client.get(url_for("form_watch_checknow"), follow_redirects=True)

changedetectionio/tests/unit/test_notification_diff.py

@@ -13,21 +13,37 @@ class TestDiffBuilder(unittest.TestCase):
 
     def test_expected_diff_output(self):
         base_dir = os.path.dirname(__file__)
-        output = diff.render_diff(previous_file=base_dir + "/test-content/before.txt", newest_file=base_dir + "/test-content/after.txt")
+        with open(base_dir + "/test-content/before.txt", 'r') as f:
+            previous_version_file_contents = f.read()
+
+        with open(base_dir + "/test-content/after.txt", 'r') as f:
+            newest_version_file_contents = f.read()
+
+        output = diff.render_diff(previous_version_file_contents=previous_version_file_contents,
+                                  newest_version_file_contents=newest_version_file_contents)
+
         output = output.split("\n")
+
+
         self.assertIn('(changed) ok', output)
         self.assertIn('(into) xok', output)
         self.assertIn('(into) next-x-ok', output)
         self.assertIn('(added) and something new', output)
 
-
-        output = diff.render_diff(previous_file=base_dir + "/test-content/before.txt", newest_file=base_dir + "/test-content/after-2.txt")
+        with open(base_dir + "/test-content/after-2.txt", 'r') as f:
+            newest_version_file_contents = f.read()
+        output = diff.render_diff(previous_version_file_contents, newest_version_file_contents)
         output = output.split("\n")
         self.assertIn('(removed) for having learned computerese,', output)
         self.assertIn('(removed) I continue to examine bits, bytes and words', output)
         
         #diff_removed
-        output = diff.render_diff(previous_file=base_dir + "/test-content/before.txt", newest_file=base_dir + "/test-content/after.txt", include_equal=False, include_removed=True, include_added=False)
+        with open(base_dir + "/test-content/before.txt", 'r') as f:
+            previous_version_file_contents = f.read()
+
+        with open(base_dir + "/test-content/after.txt", 'r') as f:
+            newest_version_file_contents = f.read()
+        output = diff.render_diff(previous_version_file_contents, newest_version_file_contents, include_equal=False, include_removed=True, include_added=False)
         output = output.split("\n")
         self.assertIn('(changed) ok', output)
         self.assertIn('(into) xok', output)
@@ -35,7 +51,9 @@ class TestDiffBuilder(unittest.TestCase):
         self.assertNotIn('(added) and something new', output)
         
         #diff_removed
-        output = diff.render_diff(previous_file=base_dir + "/test-content/before.txt", newest_file=base_dir + "/test-content/after-2.txt", include_equal=False, include_removed=True, include_added=False)
+        with open(base_dir + "/test-content/after-2.txt", 'r') as f:
+            newest_version_file_contents = f.read()
+        output = diff.render_diff(previous_version_file_contents, newest_version_file_contents, include_equal=False, include_removed=True, include_added=False)
         output = output.split("\n")
         self.assertIn('(removed) for having learned computerese,', output)
         self.assertIn('(removed) I continue to examine bits, bytes and words', output)

changedetectionio/update_worker.py

@@ -4,7 +4,8 @@ import queue
 import time
 
 from changedetectionio import content_fetcher
-from .fetchers.text_json_diff import FilterNotFoundInResponse
+from .processors.text_json_diff import FilterNotFoundInResponse
+
 
 # A single update worker
 #
@@ -68,18 +69,28 @@ class update_worker(threading.Thread):
             else:
                 line_feed_sep = "\n"
 
-            with open(watch_history[dates[-1]], 'rb') as f:
-                snapshot_contents = f.read()
+            # Add text that was triggered
+            snapshot_contents = watch.get_history_snapshot(dates[-1])
+            trigger_text = watch.get('trigger_text', [])
+            triggered_text = ''
+
+            if len(trigger_text):
+                from . import html_tools
+                triggered_text = html_tools.get_triggered_text(content=snapshot_contents, trigger_text=trigger_text)
+                if triggered_text:
+                    triggered_text = line_feed_sep.join(triggered_text)
+
 
             n_object.update({
-                'watch_url': watch['url'],
+                'current_snapshot': snapshot_contents,
+                'diff': diff.render_diff(watch.get_history_snapshot(dates[-2]), watch.get_history_snapshot(dates[-1]), line_feed_sep=line_feed_sep),
+                'diff_added': diff.render_diff(watch.get_history_snapshot(dates[-2]), watch.get_history_snapshot(dates[-1]), include_removed=False, line_feed_sep=line_feed_sep),
+                'diff_full': diff.render_diff(watch.get_history_snapshot(dates[-2]), watch.get_history_snapshot(dates[-1]), include_equal=True, line_feed_sep=line_feed_sep),
+                'diff_removed': diff.render_diff(watch.get_history_snapshot(dates[-2]), watch.get_history_snapshot(dates[-1]), include_added=False, line_feed_sep=line_feed_sep),
+                'screenshot': watch.get_screenshot() if watch.get('notification_screenshot') else None,
+                'triggered_text': triggered_text,
                 'uuid': watch_uuid,
-                'screenshot': watch.get_screenshot_as_jpeg() if watch.get('notification_screenshot') else None,
-                'current_snapshot': snapshot_contents.decode('utf-8'),
-                'diff': diff.render_diff(watch_history[dates[-2]], watch_history[dates[-1]], line_feed_sep=line_feed_sep),
-                'diff_added': diff.render_diff(watch_history[dates[-2]], watch_history[dates[-1]], include_removed=False, line_feed_sep=line_feed_sep),
-                'diff_removed': diff.render_diff(watch_history[dates[-2]], watch_history[dates[-1]], include_added=False, line_feed_sep=line_feed_sep),
-                'diff_full': diff.render_diff(watch_history[dates[-2]], watch_history[dates[-1]], include_equal=True, line_feed_sep=line_feed_sep)
+                'watch_url': watch['url'],
             })
             logging.info (">> SENDING NOTIFICATION")
             self.notification_q.put(n_object)
@@ -152,9 +163,8 @@ class update_worker(threading.Thread):
                 os.unlink(full_path)
 
     def run(self):
-        from .fetchers import text_json_diff as fetch_site_status
 
-        update_handler = fetch_site_status.perform_site_check(datastore=self.datastore)
+        from .processors import text_json_diff, restock_diff
 
         while not self.app.config.exit.is_set():
 
@@ -171,11 +181,21 @@ class update_worker(threading.Thread):
                     changed_detected = False
                     contents = b''
                     process_changedetection_results = True
-                    update_obj= {}
-                    print("> Processing UUID {} Priority {} URL {}".format(uuid, queued_item_data.priority, self.datastore.data['watching'][uuid]['url']))
+                    update_obj = {}
+                    print("> Processing UUID {} Priority {} URL {}".format(uuid, queued_item_data.priority,
+                                                                           self.datastore.data['watching'][uuid]['url']))
                     now = time.time()
 
                     try:
+                        processor = self.datastore.data['watching'][uuid].get('processor','text_json_diff')
+
+                        # @todo some way to switch by name
+                        if processor == 'restock_diff':
+                            update_handler = restock_diff.perform_site_check(datastore=self.datastore)
+                        else:
+                            # Used as a default and also by some tests
+                            update_handler = text_json_diff.perform_site_check(datastore=self.datastore)
+
                         changed_detected, update_obj, contents = update_handler.run(uuid, skip_when_checksum_same=queued_item_data.item.get('skip_when_checksum_same'))
                         # Re #342
                         # In Python 3, all strings are sequences of Unicode characters. There is a bytes type that holds raw bytes.
@@ -295,7 +315,8 @@ class update_worker(threading.Thread):
                             self.datastore.save_screenshot(watch_uuid=uuid, screenshot=e.screenshot, as_error=True)
 
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
-                                                                           'last_check_status': e.status_code})
+                                                                           'last_check_status': e.status_code,
+                                                                           'has_ldjson_price_data': None})
                         process_changedetection_results = False
                     except Exception as e:
                         self.app.logger.error("Exception reached processing watch UUID: %s - %s", uuid, str(e))
@@ -313,6 +334,7 @@ class update_worker(threading.Thread):
 
                         self.cleanup_error_artifacts(uuid)
 
+                    #
                     # Different exceptions mean that we may or may not want to bump the snapshot, trigger notifications etc
                     if process_changedetection_results:
                         try:

requirements.txt

@@ -2,6 +2,7 @@ eventlet>=0.31.0
 feedgen~=0.9
 flask-compress
 flask-login~=0.5
+flask-paginate
 flask_expects_json~=1.7
 flask_restful
 flask_wtf
@@ -68,5 +69,5 @@ pillow
 # playwright is installed at Dockerfile build time because it's not available on all platforms
 
 # Include pytest, so if theres a support issue we can ask them to run these tests on their setup
-pytest ~=6.2
+pytest ~=7.2
 pytest-flask ~=1.2