Remove unused function

.github/workflows/containers.yml

@@ -98,8 +98,7 @@ 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
-# Looks like this was disabled
+          provenance: false
-#          provenance: false
 
       # A new tagged release is required, which builds :tag and :latest
       - name: Build and push :tag
@@ -118,8 +117,7 @@ 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
-# Looks like this was disabled
+          provenance: false
-#          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

@@ -0,0 +1,38 @@
+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 "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
+          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
 
       - name: Build changedetection.io container for testing
         run: |         
@@ -50,18 +50,10 @@ jobs:
         run: |
           
           # Selenium fetch
-          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'
+          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'
           
           # Playwright/Browserless fetch
-          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'
+          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'
-          
-          # 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

@@ -1,36 +0,0 @@
-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

@@ -1,7 +1,6 @@
 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, Restock monitoring and notifications.
+## Web Site Change Detection, Monitoring and Notification.
 
 **_Detect website content changes and perform meaningful actions - trigger notifications via Discord, Email, Slack, Telegram, API calls and many more._**
 
@@ -49,7 +49,6 @@ Requires Playwright to be enabled.
 - Governmental department updates (changes are often only on their websites)
 - New software releases, security advisories when you're not on their mailing list.
 - Festivals with changes
-- Discogs restock alerts and monitoring
 - Realestate listing changes
 - Know when your favourite whiskey is on sale, or other special deals are announced before anyone else
 - COVID related news from government websites
@@ -64,8 +63,6 @@ Requires Playwright to be enabled.
 - You have a very sensitive list of URLs to watch and you do _not_ want to use the paid alternatives. (Remember, _you_ are the product)
 - 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>_
 
@@ -103,8 +100,6 @@ $ 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

@@ -33,12 +33,10 @@ 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__ = '0.41.1'
+__version__ = '0.40.2'
 
 datastore = None
 
@@ -66,9 +64,6 @@ 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
@@ -342,6 +337,8 @@ 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)
@@ -362,12 +359,9 @@ 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(previous_version_file_contents=watch.get_history_snapshot(dates[-2]),
+                html_diff = diff.render_diff(prev_fname, latest_fname, include_equal=False, line_feed_sep="</br>")
-                                             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')
 
@@ -421,10 +415,6 @@ 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
@@ -435,28 +425,16 @@ 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
@@ -481,19 +459,11 @@ 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_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()
                         }
-
-            # 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)
@@ -541,9 +511,8 @@ 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 . import forms
+        from changedetectionio import forms
-        from .blueprint.browser_steps.browser_steps import browser_step_ui_config
+        from changedetectionio.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
@@ -558,15 +527,6 @@ 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])
 
@@ -627,16 +587,6 @@ 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)
 
@@ -683,7 +633,6 @@ 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),
@@ -786,8 +735,6 @@ 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
 
@@ -795,7 +742,7 @@ 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, processor=request.values.get('processor'))
+                importer.run(data=request.values.get('urls'), flash=flash, datastore=datastore)
                 for uuid in importer.new_uuids:
                     update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
 
@@ -813,12 +760,9 @@ 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=''
                                  )
@@ -884,22 +828,28 @@ 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:
-            newest_version_file_contents = watch.get_history_snapshot(dates[-1])
+            with open(newest_file, 'r', encoding='utf-8', errors='ignore') as f:
+                newest_version_file_contents = f.read()
         except Exception as e:
-            newest_version_file_contents = "Unable to read {}.\n".format(dates[-1])
+            newest_version_file_contents = "Unable to read {}.\n".format(newest_file)
 
         previous_version = request.args.get('previous_version')
-        previous_timestamp = dates[-2]
+        try:
-        if previous_version:
+            previous_file = history[previous_version]
-            previous_timestamp = previous_version
+        except KeyError:
+            # Not present, use a default value, the second one in the sorted list.
+            previous_file = history[dates[-2]]
 
         try:
-            previous_version_file_contents = watch.get_history_snapshot(previous_timestamp)
+            with open(previous_file, 'r', encoding='utf-8', errors='ignore') as f:
+                previous_version_file_contents = f.read()
         except Exception as e:
-            previous_version_file_contents = "Unable to read {}.\n".format(previous_timestamp)
+            previous_version_file_contents = "Unable to read {}.\n".format(previous_file)
 
 
         screenshot_url = watch.get_screenshot()
@@ -979,35 +929,37 @@ def changedetection_app(config=None, datastore_o=None):
             return output
 
         timestamp = list(watch.history.keys())[-1]
+        filename = watch.history[timestamp]
         try:
-            tmp = watch.get_history_snapshot(timestamp).splitlines()
+            with open(filename, 'r', encoding='utf-8', errors='ignore') as f:
+                tmp = f.readlines()
 
-            # Get what needs to be highlighted
+                # Get what needs to be highlighted
-            ignore_rules = watch.get('ignore_text', []) + datastore.data['settings']['application']['global_ignore_text']
+                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
+                # .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),
+                ignored_line_numbers = html_tools.strip_ignore_text(content="".join(tmp),
-                                                                wordlist=ignore_rules,
+                                                                    wordlist=ignore_rules,
-                                                                mode='line numbers'
+                                                                    mode='line numbers'
-                                                                )
+                                                                    )
 
-            trigger_line_numbers = html_tools.strip_ignore_text(content="\n".join(tmp),
+                trigger_line_numbers = html_tools.strip_ignore_text(content="".join(tmp),
-                                                                wordlist=watch['trigger_text'],
+                                                                    wordlist=watch['trigger_text'],
-                                                                mode='line numbers'
+                                                                    mode='line numbers'
-                                                                )
+                                                                    )
-            # Prepare the classes and lines used in the template
+                # Prepare the classes and lines used in the template
-            i=0
+                i=0
-            for l in tmp:
+                for l in tmp:
-                classes=[]
+                    classes=[]
-                i+=1
+                    i+=1
-                if i in ignored_line_numbers:
+                    if i in ignored_line_numbers:
-                    classes.append('ignored')
+                        classes.append('ignored')
-                if i in trigger_line_numbers:
+                    if i in trigger_line_numbers:
-                    classes.append('triggered')
+                        classes.append('triggered')
-                content.append({'line': l, 'classes': ' '.join(classes)})
+                    content.append({'line': l, 'classes': ' '.join(classes)})
 
         except Exception as e:
-            content.append({'line': f"File doesnt exist or unable to read timestamp {timestamp}", 'classes': ''})
+            content.append({'line': "File doesnt exist or unable to read file {}".format(filename), 'classes': ''})
 
         output = render_template("preview.html",
                                  content=content,
@@ -1049,8 +1001,7 @@ def changedetection_app(config=None, datastore_o=None):
             os.unlink(previous_backup_filename)
 
         # create a ZipFile object
-        timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
+        backupname = "changedetection-backup-{}.zip".format(int(time.time()))
-        backupname = "changedetection-backup-{}.zip".format(timestamp)
         backup_filepath = os.path.join(datastore_o.datastore_path, backupname)
 
         with zipfile.ZipFile(backup_filepath, "w",
@@ -1174,8 +1125,7 @@ def changedetection_app(config=None, datastore_o=None):
             return redirect(url_for('index'))
 
         add_paused = request.form.get('edit_and_watch_submit_button') != None
-        processor = request.form.get('processor', 'text_json_diff')
+        new_uuid = datastore.add_watch(url=url, tag=request.form.get('tag').strip(), extras={'paused': add_paused})
-        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:
@@ -1217,8 +1167,7 @@ def changedetection_app(config=None, datastore_o=None):
 
         new_uuid = datastore.clone(uuid)
         if new_uuid:
-            if not datastore.data['watching'].get(uuid).get('paused'):
+            update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
             flash('Cloned.')
 
         return redirect(url_for('index'))
@@ -1284,13 +1233,6 @@ 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()
@@ -1313,13 +1255,6 @@ 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

@@ -33,7 +33,7 @@ class Watch(Resource):
     @auth.check_token
     def get(self, uuid):
         """
-        @api {get} /api/v1/watch/:uuid Get a single watch data
+        @api {get} /api/v1/watch/:uuid Single watch information
         @apiDescription Retrieve watch information and set muted/paused status
         @apiExample {curl} Example usage:
             curl http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
@@ -70,16 +70,13 @@ class Watch(Resource):
             return "OK", 200
 
         # Return without history, get that via another API call
-        # Properties are not returned as a JSON, so add the required props manually
         watch['history_n'] = watch.history_n
-        watch['last_changed'] = watch.last_changed
-
         return watch
 
     @auth.check_token
     def delete(self, uuid):
         """
-        @api {delete} /api/v1/watch/:uuid Delete a watch and related history
+        @api {delete} /api/v1/watch/:uuid Delete watch information
         @apiExample {curl} Example usage:
             curl http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X DELETE -H"x-api-key:813031b16330fe25e3780cf0325daa45"
         @apiParam {uuid} uuid Watch unique ID.
@@ -93,18 +90,21 @@ class Watch(Resource):
         self.datastore.delete(uuid)
         return 'OK', 204
 
+    # Update an existing
     @auth.check_token
     @expects_json(schema_update_watch)
     def put(self, uuid):
         """
         @api {put} /api/v1/watch/:uuid Update watch information
         @apiExample {curl} Example usage:
+            Create a watch (POST)
+            curl http://localhost:4000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"url": "https://my-nice.com" , "tag": "nice list"}'
             Update (PUT)
             curl http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X PUT -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"url": "https://my-nice.com" , "tag": "new list"}'
 
-        @apiDescription Updates an existing watch using JSON, accepts the same structure as returned in <a href="#api-Watch-Watch">get single watch information</a>
+        @apiDescription Updates an existing watch using JSON, accepts the same structure as at https://github.com/dgtlmoon/changedetection.io/blob/fab7d325f764d6912bef671f1d78bf217689c537/changedetectionio/model/Watch.py#L15
         @apiParam {uuid} uuid Watch unique ID.
-        @apiName Update a watch
+        @apiName Update
         @apiGroup Watch
         @apiSuccess (200) {String} OK Was updated
         @apiSuccess (500) {String} ERR Some other error
@@ -131,21 +131,6 @@ class WatchHistory(Resource):
     # Get a list of available history for a watch by UUID
     # curl http://localhost:4000/api/v1/watch/<string:uuid>/history
     def get(self, uuid):
-        """
-        @api {get} /api/v1/watch/<string:uuid>/history Get a list of all historical snapshots available for a watch
-        @apiDescription Requires `uuid`, returns list
-        @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091/history -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json"
-            {
-                "1676649279": "/tmp/data/6a4b7d5c-fee4-4616-9f43-4ac97046b595/cb7e9be8258368262246910e6a2a4c30.txt",
-                "1677092785": "/tmp/data/6a4b7d5c-fee4-4616-9f43-4ac97046b595/e20db368d6fc633e34f559ff67bb4044.txt",
-                "1677103794": "/tmp/data/6a4b7d5c-fee4-4616-9f43-4ac97046b595/02efdd37dacdae96554a8cc85dc9c945.txt"
-            }
-        @apiName Get list of available stored snapshots for watch
-        @apiGroup Watch History
-        @apiSuccess (200) {String} OK
-        @apiSuccess (404) {String} ERR Not found
-        """
         watch = self.datastore.data['watching'].get(uuid)
         if not watch:
             abort(404, message='No watch exists with the UUID of {}'.format(uuid))
@@ -157,18 +142,11 @@ class WatchSingleHistory(Resource):
         # datastore is a black box dependency
         self.datastore = kwargs['datastore']
 
+    # Read a given history snapshot and return its content
+    # <string:timestamp> or "latest"
+    # curl http://localhost:4000/api/v1/watch/<string:uuid>/history/<int:timestamp>
     @auth.check_token
     def get(self, uuid, timestamp):
-        """
-        @api {get} /api/v1/watch/<string:uuid>/history/<int:timestamp> Get single snapshot from watch
-        @apiDescription Requires watch `uuid` and `timestamp`. `timestamp` of "`latest`" for latest available snapshot, or <a href="#api-Watch_History-Get_list_of_available_stored_snapshots_for_watch">use the list returned here</a>
-        @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091/history/1677092977 -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json"
-        @apiName Get single snapshot content
-        @apiGroup Watch History
-        @apiSuccess (200) {String} OK
-        @apiSuccess (404) {String} ERR Not found
-        """
         watch = self.datastore.data['watching'].get(uuid)
         if not watch:
             abort(404, message='No watch exists with the UUID of {}'.format(uuid))
@@ -179,7 +157,8 @@ class WatchSingleHistory(Resource):
         if timestamp == 'latest':
             timestamp = list(watch.history.keys())[-1]
 
-        content = watch.get_history_snapshot(timestamp)
+        with open(watch.history[timestamp], 'r') as f:
+            content = f.read()
 
         response = make_response(content, 200)
         response.mimetype = "text/plain"
@@ -196,19 +175,21 @@ class CreateWatch(Resource):
     @expects_json(schema_create_watch)
     def post(self):
         """
-        @api {post} /api/v1/watch Create a single watch
+        @api {post} /api/v1/watch Create a watch
-        @apiDescription Requires atleast `url` set, can accept the same structure as <a href="#api-Watch-Watch">get single watch information</a> to create.
+        @apiDescription requires `url`, Creates a watch, also accepts accepts the same structure as at https://github.com/dgtlmoon/changedetection.io/blob/fab7d325f764d6912bef671f1d78bf217689c537/changedetectionio/model/Watch.py#L15
         @apiExample {curl} Example usage:
             curl http://localhost:4000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"url": "https://my-nice.com" , "tag": "nice list"}'
         @apiName Create
-        @apiGroup Watch
+        @apiGroup CreateWatch
         @apiSuccess (200) {String} OK Was created
         @apiSuccess (500) {String} ERR Some other error
         """
 
+        #
         json_data = request.get_json()
         url = json_data['url'].strip()
 
+
         if not validators.url(json_data['url'].strip()):
             return "Invalid or unsupported URL", 400
 
@@ -230,32 +211,17 @@ class CreateWatch(Resource):
     @auth.check_token
     def get(self):
         """
-        @api {get} /api/v1/watch List watches
+        @api {get} /api/v1/watch
         @apiDescription Return concise list of available watches and some very basic info
         @apiExample {curl} Example usage:
             curl http://localhost:4000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            {
+            recheck_all=1 to recheck all
-                "6a4b7d5c-fee4-4616-9f43-4ac97046b595": {
-                    "last_changed": 1677103794,
-                    "last_checked": 1677103794,
-                    "last_error": false,
-                    "title": "",
-                    "url": "http://www.quotationspage.com/random.php"
-                },
-                "e6f5fd5c-dbfe-468b-b8f3-f9d6ff5ad69b": {
-                    "last_changed": 0,
-                    "last_checked": 1676662819,
-                    "last_error": false,
-                    "title": "QuickLook",
-                    "url": "https://github.com/QL-Win/QuickLook/tags"
-                }
-            }
-
         @apiParam {String} [recheck_all]       Optional Set to =1 to force recheck of all watches
         @apiParam {String} [tag]               Optional name of tag to limit results
         @apiName ListWatches
-        @apiGroup Watch Management
+        @apiGroup CreateWatch
-        @apiSuccess (200) {String} OK JSON dict
+
+        :return:
         """
         list = {}
 
@@ -286,22 +252,6 @@ class SystemInfo(Resource):
 
     @auth.check_token
     def get(self):
-        """
-        @api {get} /api/v1/systeminfo Return system info
-        @apiDescription Return some info about the current system state
-        @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/systeminfo -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            HTTP/1.0 200
-            {
-                'queue_size': 10 ,
-                'overdue_watches': ["watch-uuid-list"],
-                'uptime': 38344.55,
-                'watch_count': 800,
-                'version': "0.40.1"
-            }
-        @apiName Get Info
-        @apiGroup System Information
-        """
         import time
         overdue_watches = []
 
@@ -320,11 +270,10 @@ class SystemInfo(Resource):
             # Allow 5 minutes of grace time before we decide it's overdue
             if time_since_check - (5 * 60) > t:
                 overdue_watches.append(uuid)
-        from changedetectionio import __version__ as main_version
+
         return {
                    'queue_size': self.update_q.qsize(),
                    'overdue_watches': overdue_watches,
                    'uptime': round(time.time() - self.datastore.start_time, 2),
-                   'watch_count': len(self.datastore.data.get('watching', {})),
+                   'watch_count': len(self.datastore.data.get('watching', {}))
-                   'version': main_version
                }, 200

changedetectionio/blueprint/browser_steps/__init__.py

@@ -27,82 +27,58 @@ import os
 import logging
 from changedetectionio.store import ChangeDetectionStore
 from changedetectionio import login_optionally_required
+browsersteps_live_ui_o = {}
+browsersteps_playwright_browser_interface = None
+browsersteps_playwright_browser_interface_browser = None
+browsersteps_playwright_browser_interface_context = None
+browsersteps_playwright_browser_interface_end_time = None
+browsersteps_playwright_browser_interface_start_time = None
 
-browsersteps_sessions = {}
+def cleanup_playwright_session():
-io_interface_context = None
 
+    global browsersteps_live_ui_o
+    global browsersteps_playwright_browser_interface
+    global browsersteps_playwright_browser_interface_browser
+    global browsersteps_playwright_browser_interface_context
+    global browsersteps_playwright_browser_interface_end_time
+    global browsersteps_playwright_browser_interface_start_time
+
+    browsersteps_live_ui_o = {}
+    browsersteps_playwright_browser_interface = None
+    browsersteps_playwright_browser_interface_browser = None
+    browsersteps_playwright_browser_interface_end_time = None
+    browsersteps_playwright_browser_interface_start_time = None
+
+    print("Cleaning up old playwright session because time was up, calling .goodbye()")
+    try:
+        browsersteps_playwright_browser_interface_context.goodbye()
+    except Exception as e:
+        print ("Got exception in shutdown, probably OK")
+        print (str(e))
+
+    browsersteps_playwright_browser_interface_context = None
+
+    print ("Cleaning up old playwright session because time was up - done")
 
 def construct_blueprint(datastore: ChangeDetectionStore):
+
     browser_steps_blueprint = Blueprint('browser_steps', __name__, template_folder="templates")
 
-    def start_browsersteps_session():
-        from . import nonContext
-        from . import browser_steps
-        import time
-        global browsersteps_sessions
-        global io_interface_context
-
-
-        # We keep the playwright session open for many minutes
-        seconds_keepalive = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
-
-        browsersteps_start_session = {'start_time': time.time()}
-
-        # You can only have one of these running
-        # This should be very fine to leave running for the life of the application
-        # @idea - Make it global so the pool of watch fetchers can use it also
-        if not io_interface_context:
-            io_interface_context = nonContext.c_sync_playwright()
-            # Start the Playwright context, which is actually a nodejs sub-process and communicates over STDIN/STDOUT pipes
-            io_interface_context = io_interface_context.start()
-#Element is outside of the viewport
-
-        # keep it alive for 10 seconds more than we advertise, sometimes it helps to keep it shutting down cleanly
-        keepalive = "&timeout={}".format(((seconds_keepalive + 3) * 1000))
-        try:
-            browsersteps_start_session['browser'] = io_interface_context.chromium.connect_over_cdp(
-                os.getenv('PLAYWRIGHT_DRIVER_URL', '') + keepalive)
-        except Exception as e:
-            if 'ECONNREFUSED' in str(e):
-                return make_response('Unable to start the Playwright Browser session, is it running?', 401)
-            else:
-                return make_response(str(e), 401)
-
-        # Tell Playwright to connect to Chrome and setup a new session via our stepper interface
-        browsersteps_start_session['browserstepper'] = browser_steps.browsersteps_live_ui(
-            playwright_browser=browsersteps_start_session['browser'])
-
-        # For test
-        #browsersteps_start_session['browserstepper'].action_goto_url(value="http://example.com?time="+str(time.time()))
-
-        return browsersteps_start_session
-
     @login_optionally_required
-    @browser_steps_blueprint.route("/browsersteps_start_session", methods=['GET'])
+    @browser_steps_blueprint.route("/browsersteps_update", methods=['GET', 'POST'])
-    def browsersteps_start_session():
-        # A new session was requested, return sessionID
-
-        import uuid
-        browsersteps_session_id = str(uuid.uuid4())
-
-        watch_uuid = request.args.get('uuid')
-        global browsersteps_sessions
-
-        print("Starting connection with playwright")
-        logging.debug("browser_steps.py connecting")
-        browsersteps_sessions[browsersteps_session_id] = start_browsersteps_session()
-        print("Starting connection with playwright - done")
-        return {'browsersteps_session_id': browsersteps_session_id}
-
-    # A request for an action was received
-    @login_optionally_required
-    @browser_steps_blueprint.route("/browsersteps_update", methods=['POST'])
     def browsersteps_ui_update():
         import base64
         import playwright._impl._api_types
-        global browsersteps_sessions
+        import time
+
         from changedetectionio.blueprint.browser_steps import browser_steps
 
+        global browsersteps_live_ui_o, browsersteps_playwright_browser_interface_end_time
+        global browsersteps_playwright_browser_interface_browser
+        global browsersteps_playwright_browser_interface
+        global browsersteps_playwright_browser_interface_start_time
+
+        step_n = None
         remaining =0
         uuid = request.args.get('uuid')
 
@@ -111,9 +87,13 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         if not browsersteps_session_id:
             return make_response('No browsersteps_session_id specified', 500)
 
-        if not browsersteps_sessions.get(browsersteps_session_id):
+        # Because we don't "really" run in a context manager ( we make the playwright interface global/long-living )
-            return make_response('No session exists under that ID', 500)
+        # We need to manage the shutdown when the time is up
-
+        if browsersteps_playwright_browser_interface_end_time:
+            remaining = browsersteps_playwright_browser_interface_end_time-time.time()
+            if browsersteps_playwright_browser_interface_end_time and remaining <= 0:
+                cleanup_playwright_session()
+                return make_response('Browser session expired, please reload the Browser Steps interface', 401)
 
         # Actions - step/apply/etc, do the thing and return state
         if request.method == 'POST':
@@ -126,13 +106,18 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
             if step_operation == 'Goto site':
                 step_operation = 'goto_url'
-                step_optional_value = datastore.data['watching'][uuid].get('url')
+                step_optional_value = None
-                step_selector = None
+                step_selector = datastore.data['watching'][uuid].get('url')
 
             # @todo try.. accept.. nice errors not popups..
             try:
 
-                browsersteps_sessions[browsersteps_session_id]['browserstepper'].call_action(action_name=step_operation,
+                this_session = browsersteps_live_ui_o.get(browsersteps_session_id)
+                if not this_session:
+                    print("Browser exited")
+                    return make_response('Browser session ran out of time :( Please reload this page.', 401)
+
+                this_session.call_action(action_name=step_operation,
                                          selector=step_selector,
                                          optional_value=step_optional_value)
 
@@ -144,43 +129,99 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             # Get visual selector ready/update its data (also use the current filter info from the page?)
             # When the last 'apply' button was pressed
             # @todo this adds overhead because the xpath selection is happening twice
-            u = browsersteps_sessions[browsersteps_session_id]['browserstepper'].page.url
+            u = this_session.page.url
             if is_last_step and u:
-                (screenshot, xpath_data) = browsersteps_sessions[browsersteps_session_id]['browserstepper'].request_visualselector_data()
+                (screenshot, xpath_data) = this_session.request_visualselector_data()
                 datastore.save_screenshot(watch_uuid=uuid, screenshot=screenshot)
                 datastore.save_xpath_data(watch_uuid=uuid, data=xpath_data)
 
-#        if not this_session.page:
+        # Setup interface
-#            cleanup_playwright_session()
+        if request.method == 'GET':
-#            return make_response('Browser session ran out of time :( Please reload this page.', 401)
 
-        # Screenshots and other info only needed on requesting a step (POST)
+            if not browsersteps_playwright_browser_interface:
-        try:
+                print("Starting connection with playwright")
-            state = browsersteps_sessions[browsersteps_session_id]['browserstepper'].get_current_state()
+                logging.debug("browser_steps.py connecting")
-        except playwright._impl._api_types.Error as e:
-            return make_response("Browser session ran out of time :( Please reload this page."+str(e), 401)
 
-        # Use send_file() which is way faster than read/write loop on bytes
+                global browsersteps_playwright_browser_interface_context
-        import json
+                from . import nonContext
-        from tempfile import mkstemp
+                browsersteps_playwright_browser_interface_context = nonContext.c_sync_playwright()
-        from flask import send_file
+                browsersteps_playwright_browser_interface = browsersteps_playwright_browser_interface_context.start()
-        tmp_fd, tmp_file = mkstemp(text=True, suffix=".json", prefix="changedetectionio-")
 
-        output = json.dumps({'screenshot': "data:image/jpeg;base64,{}".format(
+                time.sleep(1)
-            base64.b64encode(state[0]).decode('ascii')),
+                # At 20 minutes, some other variable is closing it
-            'xpath_data': state[1],
+                # @todo find out what it is and set it
-            'session_age_start': browsersteps_sessions[browsersteps_session_id]['browserstepper'].age_start,
+                seconds_keepalive = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
-            'browser_time_remaining': round(remaining)
-        })
 
-        with os.fdopen(tmp_fd, 'w') as f:
+                # keep it alive for 10 seconds more than we advertise, sometimes it helps to keep it shutting down cleanly
-            f.write(output)
+                keepalive = "&timeout={}".format(((seconds_keepalive+3) * 1000))
+                try:
+                    browsersteps_playwright_browser_interface_browser = browsersteps_playwright_browser_interface.chromium.connect_over_cdp(
+                        os.getenv('PLAYWRIGHT_DRIVER_URL', '') + keepalive)
+                except Exception as e:
+                    if 'ECONNREFUSED' in str(e):
+                        return make_response('Unable to start the Playwright session properly, is it running?', 401)
 
-        response = make_response(send_file(path_or_file=tmp_file,
+                browsersteps_playwright_browser_interface_end_time = time.time() + (seconds_keepalive-3)
-                                           mimetype='application/json; charset=UTF-8',
+                print("Starting connection with playwright - done")
-                                           etag=True))
+
-        # No longer needed
+            if not browsersteps_live_ui_o.get(browsersteps_session_id):
-        os.unlink(tmp_file)
+                # Boot up a new session
+                proxy_id = datastore.get_preferred_proxy_for_watch(uuid=uuid)
+                proxy = None
+                if proxy_id:
+                    proxy_url = datastore.proxy_list.get(proxy_id).get('url')
+                    if proxy_url:
+                        proxy = {'server': proxy_url}
+                        print("Browser Steps: UUID {} Using proxy {}".format(uuid, proxy_url))
+
+                # Begin the new "Playwright Context" that re-uses the playwright interface
+                # Each session is a "Playwright Context" as a list, that uses the playwright interface
+                browsersteps_live_ui_o[browsersteps_session_id] = browser_steps.browsersteps_live_ui(
+                    playwright_browser=browsersteps_playwright_browser_interface_browser,
+                    proxy=proxy)
+                this_session = browsersteps_live_ui_o[browsersteps_session_id]
+
+        if not this_session.page:
+            cleanup_playwright_session()
+            return make_response('Browser session ran out of time :( Please reload this page.', 401)
+
+        response = None
+
+        if request.method == 'POST':
+            # Screenshots and other info only needed on requesting a step (POST)
+            try:
+                state = this_session.get_current_state()
+            except playwright._impl._api_types.Error as e:
+                return make_response("Browser session ran out of time :( Please reload this page."+str(e), 401)
+
+            # Use send_file() which is way faster than read/write loop on bytes
+            import json
+            from tempfile import mkstemp
+            from flask import send_file
+            tmp_fd, tmp_file = mkstemp(text=True, suffix=".json", prefix="changedetectionio-")
+
+            output = json.dumps({'screenshot': "data:image/jpeg;base64,{}".format(
+                base64.b64encode(state[0]).decode('ascii')),
+                'xpath_data': state[1],
+                'session_age_start': this_session.age_start,
+                'browser_time_remaining': round(remaining)
+            })
+
+            with os.fdopen(tmp_fd, 'w') as f:
+                f.write(output)
+
+            response = make_response(send_file(path_or_file=tmp_file,
+                                               mimetype='application/json; charset=UTF-8',
+                                               etag=True))
+            # No longer needed
+            os.unlink(tmp_file)
+
+        elif request.method == 'GET':
+            # Just enough to get the session rolling, it will call for goto-site via POST next
+            response = make_response({
+                'session_age_start': this_session.age_start,
+                'browser_time_remaining': round(remaining)
+            })
 
         return response
 

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -25,14 +25,12 @@ browser_step_ui_config = {'Choose one': '0 0',
                           'Execute JS': '0 1',
 #                          'Extract text and use as filter': '1 0',
                           'Goto site': '0 0',
-                          'Goto URL': '0 1',
                           'Press Enter': '0 0',
                           'Select by label': '1 1',
                           'Scroll down': '0 0',
                           'Uncheck checkbox': '1 0',
                           'Wait for seconds': '0 1',
                           'Wait for text': '0 1',
-                          'Wait for text in element': '1 1',
                           #                          'Press Page Down': '0 0',
                           #                          'Press Page Up': '0 0',
                           # weird bug, come back to it later
@@ -55,7 +53,7 @@ class steppable_browser_interface():
 
         print("> action calling", call_action_name)
         # https://playwright.dev/python/docs/selectors#xpath-selectors
-        if selector and selector.startswith('/') and not selector.startswith('//'):
+        if selector.startswith('/') and not selector.startswith('//'):
             selector = "xpath=" + selector
 
         action_handler = getattr(self, "action_" + call_action_name)
@@ -71,13 +69,13 @@ class steppable_browser_interface():
             optional_value = str(jinja2_env.from_string(optional_value).render())
 
         action_handler(selector, optional_value)
-        self.page.wait_for_timeout(1.5 * 1000)
+        self.page.wait_for_timeout(3 * 1000)
         print("Call action done in", time.time() - now)
 
-    def action_goto_url(self, selector=None, value=None):
+    def action_goto_url(self, url, optional_value):
         # self.page.set_viewport_size({"width": 1280, "height": 5000})
         now = time.time()
-        response = self.page.goto(value, timeout=0, wait_until='commit')
+        response = self.page.goto(url, timeout=0, wait_until='commit')
 
         # Wait_until = commit
         # - `'commit'` - consider operation to be finished when network response is received and the document started loading.
@@ -105,8 +103,7 @@ class steppable_browser_interface():
         print("Clicking element")
         if not len(selector.strip()):
             return
-
+        self.page.click(selector, timeout=10 * 1000, delay=randint(200, 500))
-        self.page.click(selector=selector, timeout=30 * 1000, delay=randint(200, 500))
 
     def action_click_element_if_exists(self, selector, value):
         import playwright._impl._api_types as _api_types
@@ -135,17 +132,6 @@ class steppable_browser_interface():
     def action_wait_for_seconds(self, selector, value):
         self.page.wait_for_timeout(int(value) * 1000)
 
-    def action_wait_for_text(self, selector, value):
-        import json
-        v = json.dumps(value)
-        self.page.wait_for_function(f'document.querySelector("body").innerText.includes({v});', timeout=30000)
-
-    def action_wait_for_text_in_element(self, selector, value):
-        import json
-        s = json.dumps(selector)
-        v = json.dumps(value)
-        self.page.wait_for_function(f'document.querySelector({s}).innerText.includes({v});', timeout=30000)
-
     # @todo - in the future make some popout interface to capture what needs to be set
     # https://playwright.dev/python/docs/api/class-keyboard
     def action_press_enter(self, selector, value):

changedetectionio/content_fetcher.py

@@ -10,7 +10,6 @@ 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
@@ -25,12 +24,10 @@ 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
@@ -39,7 +36,6 @@ class JSActionExceptions(Exception):
         self.message = message
         return
 
-
 class BrowserStepsStepTimout(Exception):
     def __init__(self, step_n):
         self.step_n = step_n
@@ -55,7 +51,6 @@ 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
@@ -64,7 +59,6 @@ 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
@@ -75,7 +69,6 @@ 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
@@ -84,20 +77,19 @@ 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_data = None
     xpath_element_js = ""
-    instock_data = None
+
-    instock_data_js = ""
+    xpath_data = None
 
     # Will be needed in the future by the VisualSelector, always get this where possible.
     screenshot = False
@@ -111,7 +103,7 @@ 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):
@@ -159,15 +151,13 @@ class Fetcher():
             interface = steppable_browser_interface()
             interface.page = self.page
 
-            valid_steps = filter(
+            valid_steps = filter(lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'), self.browser_steps)
-                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.screenshot_step("before-"+str(step_n))
-                self.save_step_html("before-" + str(step_n))
+                self.save_step_html("before-"+str(step_n))
                 try:
                     optional_value = step['optional_value']
                     selector = step['selector']
@@ -182,11 +172,12 @@ class Fetcher():
                                                       optional_value=optional_value)
                     self.screenshot_step(step_n)
                     self.save_step_html(step_n)
-                except TimeoutError as e:
+                except TimeoutError:
-                    print(str(e))
                     # Stop processing here
                     raise BrowserStepsStepTimout(step_n=step_n)
 
+
+
     # It's always good to reset these
     def delete_browser_steps_screenshots(self):
         import glob
@@ -196,7 +187,6 @@ 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)
 #
@@ -214,7 +204,6 @@ def available_fetchers():
 
     return p
 
-
 class base_html_playwright(Fetcher):
     fetcher_description = "Playwright {}/Javascript".format(
         os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
@@ -278,118 +267,6 @@ 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,
@@ -400,24 +277,6 @@ 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
 
@@ -434,7 +293,7 @@ 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.get('User-Agent', 'Mozilla/5.0'),
+                user_agent=request_headers['User-Agent'] if request_headers.get('User-Agent') else 'Mozilla/5.0',
                 proxy=self.proxy,
                 # This is needed to enable JavaScript execution on GitHub and others
                 bypass_csp=True,
@@ -464,12 +323,12 @@ 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))
@@ -488,7 +347,7 @@ 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))
@@ -496,7 +355,7 @@ 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
@@ -510,10 +369,11 @@ 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)
@@ -522,9 +382,7 @@ class base_html_playwright(Fetcher):
             else:
                 self.page.evaluate("var include_filters=''")
 
-            self.xpath_data = self.page.evaluate(
+            self.xpath_data = self.page.evaluate("async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
-                "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
@@ -535,8 +393,7 @@ class base_html_playwright(Fetcher):
             # acceptable screenshot quality here
             try:
                 # The actual screenshot
-                self.screenshot = self.page.screenshot(type='jpeg', full_page=True,
+                self.screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
-                                                       quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
             except Exception as e:
                 context.close()
                 browser.close()
@@ -545,7 +402,6 @@ 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, include_replaced=True, include_change_type_prefix=True):
+def customSequenceMatcher(before, after, include_equal=False):
     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?)
@@ -18,39 +18,34 @@ def customSequenceMatcher(before, after, include_equal=False, include_removed=Tr
         if include_equal and tag == 'equal':
             g = before[alo:ahi]
             yield g
-        elif include_removed and tag == 'delete':
+        elif tag == 'delete':
-            row_prefix = "(removed) " if include_change_type_prefix else ''
+            g = ["(removed) " + i for i in same_slicer(before, alo, ahi)]
-            g = [ row_prefix + i for i in same_slicer(before, alo, ahi)]
             yield g
-        elif include_replaced and tag == 'replace':
+        elif tag == 'replace':
-            row_prefix = "(changed) " if include_change_type_prefix else ''
+            g = ["(changed) " + i for i in same_slicer(before, alo, ahi)]
-            g = [row_prefix + i for i in same_slicer(before, alo, ahi)]
+            g += ["(into   ) " + i for i in same_slicer(after, blo, bhi)]
-            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':
+        elif tag == 'insert':
-            row_prefix = "(added) " if include_change_type_prefix else ''
+            g = ["(added  ) " + i for i in same_slicer(after, blo, bhi)]
-            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
+# line_feed_sep could be "<br/>" or "<li>" or "\n" etc
-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):
+def render_diff(previous_file, newest_file, include_equal=False, 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()]
 
-    newest_version_file_contents = [line.rstrip() for line in newest_version_file_contents.splitlines()]
+    if previous_file:
-
+        with open(previous_file, 'r') as f:
-    if previous_version_file_contents:
+            previous_version_file_contents = f.read()
             previous_version_file_contents = [line.rstrip() for line in previous_version_file_contents.splitlines()]
     else:
         previous_version_file_contents = ""
 
-    rendered_diff = customSequenceMatcher(before=previous_version_file_contents,
+    rendered_diff = customSequenceMatcher(previous_version_file_contents,
-                                          after=newest_version_file_contents,
+                                          newest_version_file_contents,
-                                          include_equal=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/fetch_site_status.py

@@ -1,5 +1,3 @@
-# HTML to TEXT/JSON DIFFERENCE FETCHER
-
 import hashlib
 import json
 import logging
@@ -10,14 +8,10 @@ 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)
@@ -29,7 +23,7 @@ class PDFToHTMLToolNotFound(ValueError):
 
 # Some common stuff here that can be moved to a base class
 # (set_proxy_from_list)
-class perform_site_check(difference_detection_processor):
+class perform_site_check():
     screenshot = None
     xpath_data = None
 
@@ -59,7 +53,7 @@ class perform_site_check(difference_detection_processor):
         watch = deepcopy(self.datastore.data['watching'].get(uuid))
 
         if not watch:
-            raise Exception("Watch no longer exists.")
+            return
 
         # Protect against file:// access
         if re.search(r'^file', watch.get('url', ''), re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
@@ -279,34 +273,6 @@ class perform_site_check(difference_detection_processor):
         # 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:
@@ -365,7 +331,6 @@ class perform_site_check(difference_detection_processor):
             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/forms.py

@@ -147,12 +147,12 @@ class ValidateContentFetcherIsReady(object):
             except urllib3.exceptions.MaxRetryError as e:
                 driver_url = some_object.command_executor
                 message = field.gettext('Content fetcher \'%s\' did not respond.' % (field.data))
-                message += '<br>' + field.gettext(
+                message += '<br/>' + field.gettext(
                     'Be sure that the selenium/webdriver runner is running and accessible via network from this container/host.')
-                message += '<br>' + field.gettext('Did you follow the instructions in the wiki?')
+                message += '<br/>' + field.gettext('Did you follow the instructions in the wiki?')
-                message += '<br><br>' + field.gettext('WebDriver Host: %s' % (driver_url))
+                message += '<br/><br/>' + field.gettext('WebDriver Host: %s' % (driver_url))
-                message += '<br><a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">Go here for more information</a>'
+                message += '<br/><a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">Go here for more information</a>'
-                message += '<br>'+field.gettext('Content fetcher did not respond properly, unable to use it.\n %s' % (str(e)))
+                message += '<br/>'+field.gettext('Content fetcher did not respond properly, unable to use it.\n %s' % (str(e)))
 
                 raise ValidationError(message)
 
@@ -344,15 +344,13 @@ 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()])
@@ -363,10 +361,6 @@ 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):
 
@@ -399,19 +393,11 @@ 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 unique lines appear', default=False)
+    check_unique_lines = BooleanField('Only trigger when new 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 while text matches', [validators.Optional(), ValidateListRegex()])
+    text_should_not_be_present = StringListField('Block change-detection if 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

@@ -8,7 +8,7 @@ import json
 import re
 
 # HTML added to be sure each result matching a filter (.example) gets converted to a new line by Inscriptis
-TEXT_FILTER_LIST_LINE_SUFFIX = "<br>"
+TEXT_FILTER_LIST_LINE_SUFFIX = "<br/>"
 
 # 'price' , 'lowPrice', 'highPrice' are usually under here
 # all of those may or may not appear on different websites
@@ -287,18 +287,3 @@ 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

@@ -29,7 +29,6 @@ class import_url_list(Importer):
             data,
             flash,
             datastore,
-            processor=None
             ):
 
         urls = data.split("\n")
@@ -53,11 +52,7 @@ 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:
-                extras = None
+                new_uuid = datastore.add_watch(url=url.strip(), tag=tags, write_to_disk_now=False)
-                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

@@ -20,21 +20,15 @@ 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', # plaintext, playwright etc
+    'fetch_backend': 'system',
-    '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,
@@ -159,9 +153,7 @@ class model(dict):
     @property
     def is_pdf(self):
         # content_type field is set in the future
-        # https://github.com/dgtlmoon/changedetection.io/issues/1392
+        return '.pdf' in self.get('url', '').lower() or 'pdf' in self.get('content_type', '').lower()
-        # Not sure the best logic here
-        return self.get('url', '').lower().endswith('.pdf') or 'pdf' in self.get('content_type', '').lower()
 
     @property
     def label(self):
@@ -245,32 +237,9 @@ 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):
+    def save_history_text(self, contents, timestamp):
-        import brotli
 
         self.ensure_data_dir_exists()
 
@@ -279,21 +248,13 @@ class model(dict):
         if self.__newest_history_key and int(timestamp) == int(self.__newest_history_key):
             time.sleep(timestamp - self.__newest_history_key)
 
-        threshold = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD', 1024))
+        snapshot_fname = "{}.txt".format(str(uuid.uuid4()))
-        skip_brotli = strtobool(os.getenv('DISABLE_BROTLI_TEXT_SNAPSHOT', 'False'))
 
-        if not skip_brotli and len(contents) > threshold:
+        # in /diff/ and /preview/ we are going to assume for now that it's UTF-8 when reading
-            snapshot_fname = f"{snapshot_id}.txt.br"
+        # most sites are utf-8 and some are even broken utf-8
-            dest = os.path.join(self.watch_data_dir, snapshot_fname)
+        with open(os.path.join(self.watch_data_dir, snapshot_fname), 'wb') as f:
-            if not os.path.exists(dest):
+            f.write(contents)
-                with open(dest, 'wb') as f:
+            f.close()
-                    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
@@ -330,8 +291,7 @@ 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():
-            content = self.get_history_snapshot(k)
+            alist = set([line.decode('utf-8').strip().lower() for line in open(v, 'rb')])
-            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
@@ -346,6 +306,17 @@ 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):
@@ -392,7 +363,6 @@ class model(dict):
             return fname
         return False
 
-
     def pause(self):
         self['paused'] = True
 
@@ -422,8 +392,8 @@ class model(dict):
         # self.history will be keyed with the full path
         for k, fname in self.history.items():
             if os.path.isfile(fname):
-                if True:
+                with open(fname, "r") as f:
-                    contents = self.get_history_snapshot(k)
+                    contents = f.read()
                     res = re.findall(regex, contents, re.MULTILINE)
                     if res:
                         if not csv_writer:
@@ -459,38 +429,3 @@ 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

@@ -5,18 +5,15 @@ import json
 
 valid_tokens = {
     'base_url': '',
-    'current_snapshot': '',
-    'diff': '',
-    'diff_added': '',
-    'diff_full': '',
-    'diff_removed': '',
-    'diff_url': '',
-    'preview_url': '',
-    'triggered_text': '',
-    'watch_tag': '',
-    'watch_title': '',
     'watch_url': '',
     'watch_uuid': '',
+    'watch_title': '',
+    'watch_tag': '',
+    'diff': '',
+    'diff_full': '',
+    'diff_url': '',
+    'preview_url': '',
+    'current_snapshot': ''
 }
 
 default_notification_format_for_watch = 'System default'
@@ -89,7 +86,7 @@ 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.get('notification_format', default_notification_format),
+        n_object['notification_format'],
         valid_notification_formats[default_notification_format],
     )
     
@@ -123,10 +120,10 @@ def process_notification(n_object, datastore):
                     url += k + 'avatar_url=https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png'
 
                 if url.startswith('tgram://'):
-                    # Telegram only supports a limit subset of HTML, remove the '<br>' we place in.
+                    # Telegram only supports a limit subset of HTML, remove the '<br/>' we place in.
                     # re https://github.com/dgtlmoon/changedetection.io/issues/555
                     # @todo re-use an existing library we have already imported to strip all non-allowed tags
-                    n_body = n_body.replace('<br>', '\n')
+                    n_body = n_body.replace('<br/>', '\n')
                     n_body = n_body.replace('</br>', '\n')
                     # real limit is 4096, but minus some for extra metadata
                     payload_max_size = 3600
@@ -212,18 +209,15 @@ def create_notification_parameters(n_object, datastore):
     tokens.update(
         {
             'base_url': base_url if base_url is not None else '',
-            '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_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,
-            '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,
+            '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,
+            'diff': n_object.get('diff', ''),  # 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
+            'preview_url': preview_url,
+            'current_snapshot': n_object['current_snapshot'] if 'current_snapshot' in n_object else ''
         })
 
     return tokens

changedetectionio/processors/README.md

@@ -1,11 +0,0 @@
-# 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

@@ -1,24 +0,0 @@
-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

@@ -1,125 +0,0 @@
-
-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/res/puppeteer_fetch.js

@@ -1,183 +0,0 @@
-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;
-            }
-            if (url.toLowerCase().includes('data:')) {
-                console.log("Skipping (embedded-data) - " + 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

@@ -1,97 +0,0 @@
-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

@@ -8,14 +8,8 @@
 // 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) {
@@ -44,15 +38,15 @@ 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

@@ -28,11 +28,3 @@ 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

@@ -1,37 +0,0 @@
-<?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

@@ -1,3 +0,0 @@
-<?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/browser-steps.js

@@ -114,11 +114,11 @@ $(document).ready(function () {
             e.preventDefault()
         });
 
-        // When the mouse moves we know which element it should be above
-        // mousedown will link that to the UI (select the right action, highlight etc)
         $('#browsersteps-selector-canvas').bind('mousedown', function (e) {
             // https://developer.mozilla.org/en-US/docs/Web/API/MouseEvent
             e.preventDefault()
+            console.log(e);
+            console.log("current xpath in index is " + current_selected_i);
             last_click_xy = {'x': parseInt((1 / x_scale) * e.offsetX), 'y': parseInt((1 / y_scale) * e.offsetY)}
             process_selected(current_selected_i);
             current_selected_i = false;
@@ -132,7 +132,6 @@ $(document).ready(function () {
             }
         });
 
-        // Debounce and find the current most 'interesting' element we are hovering above
         $('#browsersteps-selector-canvas').bind('mousemove', function (e) {
             if (!xpath_data) {
                 return;
@@ -152,38 +151,41 @@ $(document).ready(function () {
             current_selected_i = false;
             // Reverse order - the most specific one should be deeper/"laster"
             // Basically, find the most 'deepest'
-            var possible_elements = [];
+            //$('#browsersteps-selector-canvas').css('cursor', 'pointer');
-            xpath_data['size_pos'].forEach(function (item, index) {
+            for (var i = xpath_data['size_pos'].length; i !== 0; i--) {
+                // draw all of them? let them choose somehow?
+                var sel = xpath_data['size_pos'][i - 1];
                 // If we are in a bounding-box
-                if (e.offsetY > item.top * y_scale && e.offsetY < item.top * y_scale + item.height * y_scale
+                if (e.offsetY > sel.top * y_scale && e.offsetY < sel.top * y_scale + sel.height * y_scale
                     &&
-                    e.offsetX > item.left * y_scale && e.offsetX < item.left * y_scale + item.width * y_scale
+                    e.offsetX > sel.left * y_scale && e.offsetX < sel.left * y_scale + sel.width * y_scale
 
                 ) {
-                    // There could be many elements here, record them all and then we'll find out which is the most 'useful'
+                    // Only highlight these interesting types
-                    // (input, textarea, button, A etc)
+                    if (1) {
-                    possible_elements.push(item);
+                        ctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
+                        ctx.fillRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
+                        current_selected_i = i - 1;
+                        break;
+
+                        // find the smallest one at this x,y
+                        // does it mean sort the xpath list by size (w*h) i think so!
+                    } else {
+
+                        if (include_text_elements[0].checked === true) {
+                            // blue one with background instead?
+                            ctx.fillStyle = 'rgba(0,0,255, 0.1)';
+                            ctx.strokeStyle = 'rgba(0,0,200, 0.7)';
+                            $('#browsersteps-selector-canvas').css('cursor', 'grab');
+                            ctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
+                            ctx.fillRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
+                            current_selected_i = i - 1;
+                            break;
+                        }
+                    }
                 }
-            });
-
-            // Find the best one
-            if (possible_elements.length) {
-                possible_elements.forEach(function (item, index) {
-                  if (["a", "input", "textarea", "button"].includes(item['tagName'])) {
-                      current_selected_i = item;
-                  }
-                });
-
-                if (!current_selected_i) {
-                    current_selected_i = possible_elements[0];
-                }
-
-                sel = xpath_data['size_pos'][current_selected_i];
-                ctx.strokeRect(current_selected_i.left * x_scale, current_selected_i.top * y_scale, current_selected_i.width * x_scale, current_selected_i.height * y_scale);
-                ctx.fillRect(current_selected_i.left * x_scale, current_selected_i.top * y_scale, current_selected_i.width * x_scale, current_selected_i.height * y_scale);
             }
 
-
         }.debounce(10));
     });
 
@@ -193,16 +195,16 @@ $(document).ready(function () {
 
 
     // callback for clicking on an xpath on the canvas
-    function process_selected(selected_in_xpath_list) {
+    function process_selected(xpath_data_index) {
         found_something = false;
         var first_available = $("ul#browser_steps li.empty").first();
 
 
-        if (selected_in_xpath_list !== false) {
+        if (xpath_data_index !== false) {
             // Nothing focused, so fill in a new one
             // if inpt type button or <button>
             // from the top, find the next not used one and use it
-            var x = selected_in_xpath_list;
+            var x = xpath_data['size_pos'][xpath_data_index];
             console.log(x);
             if (x && first_available.length) {
                 // @todo will it let you click shit that has a layer ontop? probably not.
@@ -212,18 +214,26 @@ $(document).ready(function () {
                     $('input[placeholder="Value"]', first_available).addClass('ok').click().focus();
                     found_something = true;
                 } else {
-                    // There's no good way (that I know) to find if this
+                    if (x['isClickable'] || x['tagName'].startsWith('h') || x['tagName'] === 'a' || x['tagName'] === 'button' || x['tagtype'] === 'submit' || x['tagtype'] === 'checkbox' || x['tagtype'] === 'radio' || x['tagtype'] === 'li') {
-                    // see https://stackoverflow.com/questions/446892/how-to-find-event-listeners-on-a-dom-node-in-javascript-or-in-debugging
-                    // https://codepen.io/azaslavsky/pen/DEJVWv
-
-                    // So we dont know if its really a clickable element or not :-(
-                    // Assume it is - then we dont fill the pages with unreliable "Click X,Y" selections
-                    // If you switch to "Click X,y" after an element here is setup, it will give the last co-ords anyway
-                    //if (x['isClickable'] || x['tagName'].startsWith('h') || x['tagName'] === 'a' || x['tagName'] === 'button' || x['tagtype'] === 'submit' || x['tagtype'] === 'checkbox' || x['tagtype'] === 'radio' || x['tagtype'] === 'li') {
                         $('select', first_available).val('Click element').change();
                         $('input[type=text]', first_available).first().val(x['xpath']);
                         found_something = true;
-                    //}
+                    }
+                }
+
+                first_available.xpath_data_index = xpath_data_index;
+
+                if (!found_something) {
+                    if (include_text_elements[0].checked === true) {
+                        // Suggest that we use as filter?
+                        // @todo filters should always be in the last steps, nothing non-filter after it
+                        found_something = true;
+                        ctx.strokeStyle = 'rgba(0,0,255, 0.9)';
+                        ctx.fillStyle = 'rgba(0,0,255, 0.1)';
+                        $('select', first_available).val('Extract text and use as filter').change();
+                        $('input[type=text]', first_available).first().val(x['xpath']);
+                        include_text_elements[0].checked = false;
+                    }
                 }
             }
         }
@@ -238,7 +248,7 @@ $(document).ready(function () {
 
     function start() {
         console.log("Starting browser-steps UI");
-        browsersteps_session_id = false;
+        browsersteps_session_id = Date.now();
         // @todo This setting of the first one should be done at the datalayer but wtforms doesnt wanna play nice
         $('#browser_steps >li:first-child').removeClass('empty');
         set_first_gotosite_disabled();
@@ -246,7 +256,7 @@ $(document).ready(function () {
         $('.clear,.remove', $('#browser_steps >li:first-child')).hide();
         $.ajax({
             type: "GET",
-            url: browser_steps_start_url,
+            url: browser_steps_sync_url + "&browsersteps_session_id=" + browsersteps_session_id,
             statusCode: {
                 400: function () {
                     // More than likely the CSRF token was lost when the server restarted
@@ -254,12 +264,12 @@ $(document).ready(function () {
                 }
             }
         }).done(function (data) {
+            xpath_data = data.xpath_data;
             $("#loading-status-text").fadeIn();
-            browsersteps_session_id = data.browsersteps_session_id;
             // This should trigger 'Goto site'
             console.log("Got startup response, requesting Goto-Site (first) step fake click");
             $('#browser_steps >li:first-child .apply').click();
-            browserless_seconds_remaining = 500;
+            browserless_seconds_remaining = data.browser_time_remaining;
             set_first_gotosite_disabled();
         }).fail(function (data) {
             console.log(data);

changedetectionio/static/js/notifications.js

@@ -26,6 +26,9 @@ $(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 == "") {
-        location.replace(document.querySelector(".tabs ul li:first-child a").hash);
+        document.querySelector(".tabs ul li:first-child a").click();
     } else {
         set_active_tab();
     }

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

@@ -1,37 +0,0 @@
-.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

@@ -5,7 +5,6 @@
 @import "parts/_arrows";
 @import "parts/_browser-steps";
 @import "parts/_extra_proxies";
-@import "parts/_pagination";
 @import "parts/_spinners";
 @import "parts/_variables";
 
@@ -242,10 +241,6 @@ body:before {
   font-size: 85%;
 }
 
-.button-xsmall {
-  font-size: 70%;
-}
-
 .fetch-error {
   padding-top: 1em;
   font-size: 80%;
@@ -894,21 +889,6 @@ 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 {
@@ -1064,30 +1044,3 @@ 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

@@ -95,32 +95,6 @@ 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 {
@@ -458,9 +432,6 @@ body:before {
 .button-small {
   font-size: 85%; }
 
-.button-xsmall {
-  font-size: 70%; }
-
 .fetch-error {
   padding-top: 1em;
   font-size: 80%;
@@ -898,17 +869,6 @@ 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;
@@ -1020,22 +980,3 @@ 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

@@ -192,24 +192,27 @@ class ChangeDetectionStore:
         tags.sort()
         return tags
 
+    def unlink_history_file(self, path):
+        try:
+            unlink(path)
+        except (FileNotFoundError, IOError):
+            pass
+
     # Delete a single watch by UUID
     def delete(self, uuid):
-        import pathlib
-        import shutil
-
         with self.lock:
             if uuid == 'all':
                 self.__data['watching'] = {}
 
                 # GitHub #30 also delete history records
                 for uuid in self.data['watching']:
-                    path = pathlib.Path(os.path.join(self.datastore_path, uuid))
+                    for path in self.data['watching'][uuid].history.values():
-                    shutil.rmtree(path)
+                        self.unlink_history_file(path)
-                    self.needs_write_urgent = True
 
             else:
-                path = pathlib.Path(os.path.join(self.datastore_path, uuid))
+                for path in self.data['watching'][uuid].history.values():
-                shutil.rmtree(path)
+                    self.unlink_history_file(path)
+
                 del self.data['watching'][uuid]
 
             self.needs_write_urgent = True
@@ -287,7 +290,6 @@ class ChangeDetectionStore:
                     'method',
                     'paused',
                     'previous_md5',
-                    'processor',
                     'subtractive_selectors',
                     'tag',
                     'text_should_not_be_present',
@@ -316,8 +318,7 @@ 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']
@@ -362,6 +363,11 @@ 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):
@@ -680,13 +686,3 @@ 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

@@ -17,15 +17,14 @@
                                 <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" >Send test notification</a>
+                              <a id="send-test-notification" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Send test notification</a>
                             {% if emailprefix %}
-                              <a id="add-email-helper" class="pure-button button-secondary button-xsmall" >Add email <img style="height: 1em; display: inline-block" src="{{url_for('static_content', group='images', filename='email.svg')}}" alt="Add an email address"> </a>
+                              <a id="add-email-helper" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Add email</a>
                             {% endif %}
-                              <a href="{{url_for('notification_logs')}}" class="pure-button button-secondary button-xsmall" >Notification debug logs</a>
+                              <a href="{{url_for('notification_logs')}}" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Notification debug logs</a>
                             </div>
                         </div>
                         <div id="notification-customisation" class="pure-control-group">
@@ -56,66 +55,48 @@
                                     </thead>
                                     <tbody>
                                     <tr>
-                                        <td><code>{{ '{{base_url}}' }}</code></td>
+                                        <td><code>{{ '{{ base_url }}' }}</code></td>
                                         <td>The URL of the changedetection.io instance you are running.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{watch_url}}' }}</code></td>
+                                        <td><code>{{ '{{ watch_url }}' }}</code></td>
                                         <td>The URL being watched.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{watch_uuid}}' }}</code></td>
+                                        <td><code>{{ '{{ watch_uuid }}' }}</code></td>
                                         <td>The UUID of the watch.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{watch_title}}' }}</code></td>
+                                        <td><code>{{ '{{ watch_title }}' }}</code></td>
                                         <td>The title of the watch.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{watch_tag}}' }}</code></td>
+                                        <td><code>{{ '{{ watch_tag }}' }}</code></td>
                                         <td>The watch label / tag</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{preview_url}}' }}</code></td>
+                                        <td><code>{{ '{{ preview_url }}' }}</code></td>
                                         <td>The URL of the preview page generated by changedetection.io.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{diff_url}}' }}</code></td>
+                                        <td><code>{{ '{{ diff_url }}' }}</code></td>
-                                        <td>The URL of the diff output for the watch.</td>
+                                        <td>The diff output - differences only</td>
-                                    </tr>
-									<tr>
-                                        <td><code>{{ '{{diff}}' }}</code></td>
-                                        <td>The diff output - only changes, additions, and removals</td>
-                                    </tr>
-									<tr>
-                                        <td><code>{{ '{{diff_added}}' }}</code></td>
-                                        <td>The diff output - only changes and additions</td>
-                                    </tr>
-									<tr>
-                                        <td><code>{{ '{{diff_removed}}' }}</code></td>
-                                        <td>The diff output - only changes and removals</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{diff_full}}' }}</code></td>
+                                        <td><code>{{ '{{ diff_full }}' }}</code></td>
                                         <td>The diff output - full difference output</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{current_snapshot}}' }}</code></td>
+                                        <td><code>{{ '{{ current_snapshot }}' }}</code></td>
                                         <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">
                                     <br>
-                                    URLs generated by changedetection.io (such as <code>{{ '{{diff_url}}' }}</code>) require the <code>BASE_URL</code> environment variable set.<br>
+                                    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>
                                 </div>
                             </div>
                         </div>

changedetectionio/templates/_pagination.jinja

@@ -0,0 +1,7 @@
+{% 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 charset="utf-8"/>
-    <meta name="viewport" content="width=device-width, initial-scale=1.0" >
+    <meta name="viewport" content="width=device-width, initial-scale=1.0"/>
-    <meta name="description" content="Self hosted website change detection." >
+    <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="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='pure-min.css')}}"/>
-    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='styles.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="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="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="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="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="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')}}">
+    <link rel="shortcut icon" href="{{url_for('static_content', group='favicons', filename='favicon.ico')}}"/>
-    <meta name="msapplication-TileColor" content="#da532c">
+    <meta name="msapplication-TileColor" content="#da532c"/>
-    <meta name="msapplication-config" content="favicons/browserconfig.xml">
+    <meta name="msapplication-config" content="favicons/browserconfig.xml"/>
-    <meta name="theme-color" content="#ffffff">
+    <meta name="theme-color" content="#ffffff"/>
 
     <style>
       body::before {
         background-image: url({{url_for('static_content', group='images', filename='gradient-border.png') }});
       }
     </style>
-    <script 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='jquery-3.6.0.min.js')}}"></script>
   </head>
 
   <body>
@@ -137,13 +137,16 @@
           <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 src="{{url_for('static_content', group='js', filename='toggle-theme.js')}}" defer></script>
+    <script
+      type="text/javascript"
+      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 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='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 src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script type="text/javascript" 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 %}
@@ -117,19 +117,19 @@
         <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>
 
             <div class="pure-control-group">
                 {{ render_field(extract_form.extract_regex) }}
                 <span class="pure-form-message-inline">
-                    A <strong>RegEx</strong> is a pattern that identifies exactly which part inside of the text that you want to extract.<br>
+                    A <strong>RegEx</strong> is a pattern that identifies exactly which part inside of the text that you want to extract.<br/>
 
                     <p>
-                        For example, to extract only the numbers from text &dash;<br>
+                        For example, to extract only the numbers from text &dash;</br>
-                        <strong>Raw text</strong>: <code>Temperature <span style="color: red">5.5</span>°C in Sydney</code><br>
+                        <strong>Raw text</strong>: <code>Temperature <span style="color: red">5.5</span>°C in Sydney</code></br>
-                        <strong>RegEx to extract:</strong> <code>Temperature <span style="color: red">([0-9\.]+)</span></code><br>
+                        <strong>RegEx to extract:</strong> <code>Temperature <span style="color: red">([0-9\.]+)</span></code><br/>
                     </p>
                     <p>
                         <a href="https://RegExr.com/">Be sure to test your RegEx here.</a>
@@ -149,9 +149,9 @@
 <script>
     const newest_version_timestamp = {{newest_version_timestamp}};
 </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.min.js')}}"></script>
 
-<script src="{{url_for('static_content', group='js', filename='diff-render.js')}}"></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-render.js')}}"></script>
 
 
-{% endblock %}
+{% 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 src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script type="text/javascript" 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)}}";
@@ -14,17 +14,15 @@
 {% endif %}
 
     const browser_steps_config=JSON.parse('{{ browser_steps_config|tojson }}');
-    const browser_steps_start_url="{{url_for('browser_steps.browsersteps_start_session', uuid=uuid)}}";
     const browser_steps_sync_url="{{url_for('browser_steps.browsersteps_ui_update', uuid=uuid)}}";
-
 </script>
 
-<script 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='watch-settings.js')}}" defer></script>
-<script src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>
+<script type="text/javascript" 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 type="text/javascript" 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>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='visual-selector.js')}}" defer></script>
 {% if playwright_enabled %}
-<script src="{{url_for('static_content', group='js', filename='browser-steps.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='browser-steps.js')}}" defer></script>
 {% endif %}
 
 <div class="edit-form monospaced-textarea">
@@ -36,15 +34,8 @@
             {% 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>
@@ -52,24 +43,14 @@
     <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>
                     <div class="pure-control-group">
                         {{ render_field(form.url, placeholder="https://...", required=true, class="m-d") }}
-                        <span class="pure-form-message-inline">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></span><br>
+                        <span class="pure-form-message-inline">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></span><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">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") }}
@@ -125,10 +106,10 @@
                         {{ render_field(form.webdriver_delay) }}
                         <div class="pure-form-message-inline">
                             <strong>If you're having trouble waiting for the page to be fully rendered (text missing etc), try increasing the 'wait' time here.</strong>
-                            <br>
+                            <br/>
                             This will wait <i>n</i> seconds before extracting the text.
                             {% if using_global_webdriver_wait %}
-                            <br><strong>Using the current global default settings</strong>
+                            <br/><strong>Using the current global default settings</strong>
                             {% endif %}
                         </div>
                     </div>
@@ -165,7 +146,7 @@ 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')}}" alt="New beta functionality">
+                <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}">
                 <fieldset>
                     <div class="pure-control-group">
                         <!--
@@ -188,12 +169,11 @@ User-Agent: wonderbra 1.0") }}
                                     <span class="loader" >
                                         <span id="browsersteps-click-start">
                                             <h2 >Click here to Start</h2>
-                                            <svg style="height: 3.5rem;" version="1.1" viewBox="0 0 32 32"  xml:space="preserve" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g id="Layer_1"/><g id="play_x5F_alt"><path d="M16,0C7.164,0,0,7.164,0,16s7.164,16,16,16s16-7.164,16-16S24.836,0,16,0z M10,24V8l16.008,8L10,24z" style="fill: var(--color-grey-400);"/></g></svg><br>
+                                            Please allow 10-15 seconds for the browser to connect.
-                                            Please allow 10-15 seconds for the browser to connect.<br>
                                         </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>
@@ -223,7 +203,7 @@ 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 %}
@@ -234,10 +214,9 @@ 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>
+                            <strong>Pro-tips:</strong><br/>
                             <ul>
                                 <li>
                                     Use the preview page to see your filters and triggers highlighted.
@@ -247,6 +226,12 @@ 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,
@@ -256,9 +241,9 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                         %}
                         {{ field }}
                         {% if '/text()' in  field %}
-                          <span class="pure-form-message-inline"><strong>Note!: //text() function does not work where the &lt;element&gt; contains &lt;![CDATA[]]&gt;</strong></span><br>
+                          <span class="pure-form-message-inline"><strong>Note!: //text() function does not work where the &lt;element&gt; contains &lt;![CDATA[]]&gt;</strong></span><br/>
                         {% endif %}
-                        <span class="pure-form-message-inline">One rule per line, <i>any</i> rules that matches will be used.<br>
+                        <span class="pure-form-message-inline">One rule per line, <i>any</i> rules that matches will be used.<br/>
 
                     <ul>
                         <li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
@@ -281,42 +266,40 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                             </li>
                     </ul>
                     Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath{% if jq_support %}, or jq selector{%endif%} rules before filing an issue on GitHub! <a
-                                href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br>
+                                href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br/>
                 </span>
                     </div>
-                <fieldset class="pure-control-group">
+                    <div class="pure-control-group">
-                    {{ render_field(form.subtractive_selectors, rows=5, placeholder="header
+                      {{ 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>
-                </fieldset>
+                    </div>
-                <div class="text-filtering">
+                <fieldset class="pure-group">
-                <fieldset class="pure-group" id="text-filtering-type-options">
+                    {{ render_field(form.ignore_text, rows=5, placeholder="Some text to ignore in a line
-                    <h3>Text filtering</h3>
+/some.regex\d{2}/ for case-INsensitive regex
-                        Limit trigger/ignore/block/extract to;<br>
+                    ") }}
-                        {{ render_checkbox_field(form.filter_text_added) }}
+                    <span class="pure-form-message-inline">
-                        {{ render_checkbox_field(form.filter_text_replaced) }}
+                        <ul>
-                        {{ render_checkbox_field(form.filter_text_removed) }}
+                            <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
-                    <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>
+                            <li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
-                    <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>
+                            <li>Changing this will affect the comparison checksum which may trigger an alert</li>
-                    <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>
+                            <li>Use the preview/show current tab to see ignores</li>
-                </fieldset>
+                        </ul>
+                </span>
 
-                <fieldset class="pure-control-group">
+            </fieldset>
-                    {{ 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>
@@ -327,21 +310,6 @@ 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
@@ -366,7 +334,7 @@ Unavailable") }}
                         <li>Extracts text in the final output (line by line) after other filters using regular expressions;
                             <ul>
                                 <li>Regular expression &dash; example <code>/reports.+?2022/i</code></li>
-                                <li>Use <code>//(?aiLmsux))</code> type flags (more <a href="https://docs.python.org/3/library/re.html#index-15">information here</a>)<br></li>
+                                <li>Use <code>//(?aiLmsux))</code> type flags (more <a href="https://docs.python.org/3/library/re.html#index-15">information here</a>)<br/></li>
                                 <li>Keyword example &dash; example <code>Out of stock</code></li>
                                 <li>Use groups to extract just that text &dash; example <code>/reports.+?(\d+)/i</code> returns a list of years only</li>
                             </ul>
@@ -376,30 +344,16 @@ 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')}}" alt="New beta functionality">
+                <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}">
 
                 <fieldset>
                     <div class="pure-control-group">
                         {% if visualselector_enabled %}
                             <span class="pure-form-message-inline">
-                                The Visual Selector tool lets you select the <i>text</i> elements that will be used for the change detection &dash; after the <i>Browser Steps</i> has completed.<br><br>
+                                The Visual Selector tool lets you select the <i>text</i> elements that will be used for the change detection &dash; after the <i>Browser Steps</i> has completed.<br/><br/>
                             </span>
 
                             <div id="selector-header">
@@ -410,7 +364,7 @@ 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>
@@ -424,7 +378,6 @@ Unavailable") }}
                     </div>
                 </fieldset>
             </div>
-            {% endif %}
 
             <div id="actions">
                 <div class="pure-control-group">

changedetectionio/templates/import.html

@@ -1,7 +1,6 @@
 {% extends 'base.html' %}
 {% block content %}
-{% from '_helpers.jinja' import render_field %}
+<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="edit-form monospaced-textarea">
 
     <div class="tabs collapsable">
@@ -13,8 +12,9 @@
 
     <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%;
@@ -31,24 +31,22 @@
                                 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>
+                        Copy and Paste your Distill.io watch 'export' file, this should be a JSON file.</br>
                         This is <i>experimental</i>, supported fields are <code>name</code>, <code>uri</code>, <code>tags</code>, <code>config:selections</code>, the rest (including <code>schedule</code>) are ignored.
-                        <br>
+                        <br/>
                         <p>
-                        How to export? <a href="https://distill.io/docs/web-monitor/how-export-and-import-monitors/">https://distill.io/docs/web-monitor/how-export-and-import-monitors/</a><br>
+                        How to export? <a href="https://distill.io/docs/web-monitor/how-export-and-import-monitors/">https://distill.io/docs/web-monitor/how-export-and-import-monitors/</a><br/>
-                        Be sure to set your default fetcher to Chrome if required.<br>
+                        Be sure to set your default fetcher to Chrome if required.</br>
                         </p>
                     </legend>
 
@@ -77,7 +75,7 @@
     ]
 }
 " 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 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='diff-overview.js')}}" defer></script>
 
-<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script type="text/javascript" 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">
@@ -54,11 +54,11 @@
          <div class="tip">
              For now, Differences are performed on text, not graphically, only the latest screenshot is available.
          </div>
-         <br>
+         </br>
          {% 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 %}
@@ -67,4 +67,4 @@
          {% endif %}
      </div>
 </div>
-{% endblock %}
+{% endblock %}

changedetectionio/templates/settings.html

@@ -9,10 +9,10 @@
     const email_notification_prefix=JSON.parse('{{emailprefix|tojson}}');
 {% endif %}
 </script>
-<script src="{{url_for('static_content', group='js', filename='tabs.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='notifications.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='global-settings.js')}}" defer></script>
+<script type="text/javascript" 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">
@@ -40,7 +40,7 @@
                     <div class="pure-control-group">
                         {{ render_field(form.application.form.filter_failure_notification_threshold_attempts, class="filter_failure_notification_threshold_attempts") }}
                         <span class="pure-form-message-inline">After this many consecutive times that the CSS/xPath filter is missing, send a notification
-                            <br>
+                            <br/>
                         Set to <strong>0</strong> to disable
                         </span>
                     </div>
@@ -66,7 +66,7 @@
                         {{ render_field(form.application.form.base_url, placeholder="http://yoursite.com:5000/",
                         class="m-d") }}
                         <span class="pure-form-message-inline">
-                            Base URL used for the <code>{{ '{{ base_url }}' }}</code> token in notifications and RSS links.<br>Default value is the ENV var 'BASE_URL' (Currently "{{settings_application['current_base_url']}}"),
+                            Base URL used for the <code>{{ '{{ base_url }}' }}</code> token in notifications and RSS links.<br/>Default value is the ENV var 'BASE_URL' (Currently "{{settings_application['current_base_url']}}"),
                             <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Configurable-BASE_URL-setting">read more here</a>.
                         </span>
                     </div>
@@ -105,13 +105,13 @@
                         <p>Use the <strong>Basic</strong> method (default) where your watched sites don't need Javascript to render.</p>
                         <p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
                     </span>
-                    <br>
+                    <br/>
                     Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using BrightData Proxies, find out more here.</a>
                 </div>
                 <fieldset class="pure-group" id="webdriver-override-options">
                     <div class="pure-form-message-inline">
                         <strong>If you're having trouble waiting for the page to be fully rendered (text missing etc), try increasing the 'wait' time here.</strong>
-                        <br>
+                        <br/>
                         This will wait <i>n</i> seconds before extracting the text.
                     </div>
                     <div class="pure-control-group">
@@ -124,14 +124,14 @@
 
                     <fieldset class="pure-group">
                     {{ render_checkbox_field(form.application.form.ignore_whitespace) }}
-                    <span class="pure-form-message-inline">Ignore whitespace, tabs and new-lines/line-feeds when considering if a change was detected.<br>
+                    <span class="pure-form-message-inline">Ignore whitespace, tabs and new-lines/line-feeds when considering if a change was detected.<br/>
                     <i>Note:</i> Changing this will change the status of your existing watches, possibly trigger alerts etc.
                     </span>
                     </fieldset>
                 <fieldset class="pure-group">
                     {{ render_checkbox_field(form.application.form.render_anchor_tag_content) }}
                     <span class="pure-form-message-inline">Render anchor tag content, default disabled, when enabled renders links as <code>(link text)[https://somesite.com]</code>
-                        <br>
+                        <br/>
                     <i>Note:</i> Changing this could affect the content of your existing watches, possibly trigger alerts etc.
                     </span>
                     </fieldset>
@@ -151,7 +151,7 @@ nav
                     {{ render_field(form.application.form.global_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">Note: This is applied globally in addition to the per-watch rules.</span><br>
+                    <span class="pure-form-message-inline">Note: This is applied globally in addition to the per-watch rules.</span><br/>
                     <span class="pure-form-message-inline">
                         <ul>
                             <li>Note: This is applied globally in addition to the per-watch rules.</li>
@@ -170,8 +170,8 @@ nav
 
                 <div class="pure-control-group">
                     {{ render_checkbox_field(form.application.form.api_access_token_enabled) }}
-                    <div class="pure-form-message-inline">Restrict API access limit by using <code>x-api-key</code> header</div><br>
+                    <div class="pure-form-message-inline">Restrict API access limit by using <code>x-api-key</code> header</div><br/>
-                    <div class="pure-form-message-inline"><br>API Key <span id="api-key">{{api_key}}</span>
+                    <div class="pure-form-message-inline"><br/>API Key <span id="api-key">{{api_key}}</span>
                         <span style="display:none;" id="api-key-copy" >copy</span>
                     </div>
                 </div>
@@ -181,7 +181,7 @@ nav
                 <p><strong>Tip</strong>: You can connect to websites using <a href="https://brightdata.grsm.io/n0r16zf7eivq">BrightData</a> proxies, their service <strong>WebUnlocker</strong> will solve most CAPTCHAs, whilst their <strong>Residential Proxies</strong> may help to avoid CAPTCHA altogether. </p>
                 <p>It may be easier to try <strong>WebUnlocker</strong> first, WebUnlocker also supports country selection.</p>
                 <p>
-                    When you have <a href="https://brightdata.grsm.io/n0r16zf7eivq">registered</a>, enabled the required services, visit the <A href="https://brightdata.com/cp/api_example?">API example page</A>, then select <strong>Python</strong>, set the country you wish to use, then copy+paste the example URL below<br>
+                    When you have <a href="https://brightdata.grsm.io/n0r16zf7eivq">registered</a>, enabled the required services, visit the <A href="https://brightdata.com/cp/api_example?">API example page</A>, then select <strong>Python</strong>, set the country you wish to use, then copy+paste the example URL below<br/>
                     The Proxy URL with BrightData should start with <code>http://brd-customer...</code>
                 </p>
 

changedetectionio/templates/watch-overview.html

@@ -1,13 +1,14 @@
 {% extends 'base.html' %}
 {% block content %}
 {% from '_helpers.jinja' import render_simple_field, render_field %}
-<script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
+{% from '_pagination.jinja' import pagination %}
-<script src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
+<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>
 
 <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">
@@ -20,30 +21,21 @@
                     {{ 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 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>
+        <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>
     </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"  name="op" value="pause">Pause</button>
+        <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"  name="op" value="unpause">UnPause</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"  name="op" value="mute">Mute</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"  name="op" value="unmute">UnMute</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" name="op" value="recheck">Recheck</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" name="op" value="mark-viewed">Mark viewed</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" 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" 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 %}
@@ -53,55 +45,59 @@
         {% endfor %}
     </div>
 
-    {% set sort_order = sort_order or 'asc' %}
+    {% set sort_order = request.args.get('order', 'asc') == 'asc' %}
-    {% set sort_attribute = sort_attribute or 'last_changed'  %}
+    {% set sort_attribute = request.args.get('sort', '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>
-                {% set link_order = "desc" if sort_order  == 'asc' else "asc" %}
+                <th><input style="vertical-align: middle" type="checkbox" id="check-all"/> #</th>
-                {% 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>
+                {% set link_order = "desc" if sort_order else "asc" %}
-                <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>
+                {% set arrow_span = "" %}
-                <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>
+                <th><a class="{{ 'active '+link_order if sort_attribute == 'label' else 'inactive' }}" href="{{url_for('index', sort='label', order=link_order)}}">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)}}">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)}}">Last Changed <span class='arrow {{link_order}}'></span></a></th>
                 <th></th>
             </tr>
             </thead>
             <tbody>
 
-            {% for watch in (watches|sort(attribute=sort_attribute, reverse=sort_order == 'asc'))[pagination.skip:pagination.skip+pagination.per_page] %}
+            {% 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 %} -->
+             #}
             <tr id="{{ watch.uuid }}"
-                class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }} processor-{{ watch['processor'] }}
+                class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }}
                 {% 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+pagination.skip }}</span></td>
+                <td class="inline checkbox-uuid" ><input name="uuids"  type="checkbox" value="{{ watch.uuid}} "/> <span>{{ loop.index }}</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 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 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>
 
                     {% 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 }}
 
@@ -117,27 +113,12 @@
                     {% 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']  %}
-                    {% if watch['processor'] == 'text_json_diff'  %}
+                    <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['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' %}
-                    {% if watch['processor'] == 'restock_diff'  %}
+                    <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>
-                    <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 %}
@@ -179,7 +160,10 @@
                 <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>
-        {{ pagination.links }}
+        {# WIP for pagination, disabled for now
+         {{ pagination(sorted_watches,3, pagination_page) }}
+         #}
+
     </div>
     </form>
 </div>

changedetectionio/tests/restock/__init__.py

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

changedetectionio/tests/restock/conftest.py

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

changedetectionio/tests/restock/test_restock.py

@@ -1,106 +0,0 @@
-#!/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

@@ -1,176 +0,0 @@
-#!/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_api.py

@@ -11,10 +11,10 @@ import uuid
 def set_original_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      <div id="sametext">Some text thats the same</div>
      <div id="changetext">Some text that will change</div>
      </body>
@@ -29,10 +29,10 @@ def set_original_response():
 def set_modified_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>which has this one new line</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      <div id="sametext">Some text thats the same</div>
      <div id="changetext">Some text that changes</div>
      </body>

changedetectionio/tests/test_automatic_follow_ldjson_price.py

@@ -7,10 +7,10 @@ from .util import live_server_setup, extract_UUID_from_client, extract_api_key_f
 def set_response_with_ldjson():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      <div class="sametext">Some text thats the same</div>
      <div class="changetext">Some text that will change</div>
      <script type="application/ld+json">
@@ -61,10 +61,10 @@ def set_response_with_ldjson():
 def set_response_without_ldjson():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      <div class="sametext">Some text thats the same</div>
      <div class="changetext">Some text that will change</div>     
      </body>
@@ -143,4 +143,4 @@ def test_check_ldjson_price_autodetect(client, live_server):
     assert b'ldjson-price-track-offer' not in res.data
     
     ##########################################################################################
-    client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    client.get(url_for("form_delete", uuid="all"), follow_redirects=True)

changedetectionio/tests/test_backend.py

@@ -11,7 +11,7 @@ sleep_time_for_fetch_thread = 3
 # Basic test to check inscriptus is not adding return line chars, basically works etc
 def test_inscriptus():
     from inscriptis import get_text
-    html_content = "<html><body>test!<br>ok man</body></html>"
+    html_content = "<html><body>test!<br/>ok man</body></html>"
     stripped_text_from_html = get_text(html_content)
     assert stripped_text_from_html == 'test!\nok man'
 
@@ -82,7 +82,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
     assert b'<rss' in res.data
 
     # re #16 should have the diff in here too
-    assert b'(into) which has this one new line' in res.data
+    assert b'(into   ) which has this one new line' in res.data
     assert b'CDATA' in res.data
 
     assert expected_url.encode('utf-8') in res.data

changedetectionio/tests/test_block_while_text_present.py

@@ -8,10 +8,10 @@ from changedetectionio import html_tools
 def set_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      </body>
      </html>
 
@@ -24,10 +24,10 @@ def set_original_ignore_response():
 def set_modified_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some NEW nice initial text<br>
+     Some NEW nice initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      <p>new ignore stuff</p>
      <p>out of stock</p>
      <p>blah</p>
@@ -44,11 +44,11 @@ def set_modified_original_ignore_response():
 def set_modified_response_minus_block_text():
     test_return_data = """<html>
        <body>
-     Some NEW nice initial text<br>
+     Some NEW nice initial text</br>
      <p>Which is across multiple lines</p>
      <p>now on sale $2/p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      <p>new ignore stuff</p>
      <p>blah</p>
      </body>
@@ -87,10 +87,7 @@ 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,
+        data={"text_should_not_be_present": ignore_text, "url": test_url, 'fetch_backend': "html_requests"},
-              "url": test_url,
-              'fetch_backend': "html_requests"
-              },
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -132,6 +129,7 @@ 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_css_selector.py

@@ -12,10 +12,10 @@ def test_setup(live_server):
 def set_original_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      <div id="sametext">Some text thats the same</div>
      <div id="changetext">Some text that will change</div>
      </body>
@@ -29,10 +29,10 @@ def set_original_response():
 def set_modified_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>which has this one new line</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      <div id="sametext">Some text thats the same</div>
      <div id="changetext">Some text that changes</div>
      </body>

changedetectionio/tests/test_element_removal.py

@@ -25,10 +25,10 @@ def set_original_response():
     </ul>
     </nav>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
     <div id="changetext">Some text that will change</div>
      </body>
     <footer>
@@ -54,10 +54,10 @@ def set_modified_response():
     </ul>
     </nav>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
     <div id="changetext">Some text that changes</div>
      </body>
     <footer>
@@ -71,6 +71,7 @@ def set_modified_response():
 
 
 def test_element_removal_output():
+    from changedetectionio import fetch_site_status
     from inscriptis import get_text
 
     # Check text with sub-parts renders correctly
@@ -84,7 +85,7 @@ def test_element_removal_output():
     </ul>
     </nav>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>across multiple lines</p>
      <div id="changetext">Some text that changes</div>
      </body>

changedetectionio/tests/test_errorhandling.py

@@ -59,8 +59,6 @@ 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):
@@ -83,48 +81,4 @@ 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_extract_regex.py

@@ -10,10 +10,10 @@ from ..html_tools import *
 def set_original_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      <div id="sametext">Some text thats the same</div>
      <div class="changetext">Some text that will change</div>     
      </body>
@@ -28,12 +28,12 @@ def set_original_response():
 def set_modified_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>which has this one new line</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      <div id="sametext">Some text thats the same</div>
-     <div class="changetext">Some text that did change ( 1000 online <br> 80 guests<br>  2000 online )</div>
+     <div class="changetext">Some text that did change ( 1000 online <br/> 80 guests<br/>  2000 online )</div>
      <div class="changetext">SomeCase insensitive 3456</div>
      </body>
      </html>
@@ -49,8 +49,8 @@ def set_multiline_response():
     test_return_data = """<html>
        <body>
      
-     <p>Something <br>
+     <p>Something <br/>
-        across 6 billion multiple<br>
+        across 6 billion multiple<br/>
         lines
      </p>
      

changedetectionio/tests/test_filter_exist_changes.py

@@ -11,10 +11,10 @@ from changedetectionio.model import App
 def set_response_without_filter():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      <div id="nope-doesnt-exist">Some text thats the same</div>     
      </body>
      </html>
@@ -28,10 +28,10 @@ def set_response_without_filter():
 def set_response_with_filter():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      <div class="ticket-available">Ticket now on sale!</div>     
      </body>
      </html>
@@ -117,3 +117,18 @@ def test_filter_doesnt_exist_then_exists_should_get_notification(client, live_se
 
     assert 'Ticket now on sale' in notification
     os.unlink("test-datastore/notification.txt")
+
+
+    # Test that if it gets removed, then re-added, we get a notification
+    # Remove the target and re-add it, we should get a new notification
+    set_response_without_filter()
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    time.sleep(3)
+    assert not os.path.isfile("test-datastore/notification.txt")
+
+    set_response_with_filter()
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    time.sleep(3)
+    assert os.path.isfile("test-datastore/notification.txt")
+
+# Also test that the filter was updated after the first one was requested

changedetectionio/tests/test_filter_failure_notification.py

@@ -8,10 +8,10 @@ from changedetectionio.model import App
 def set_response_with_filter():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      <div id="nope-doesnt-exist">Some text thats the same</div>     
      </body>
      </html>
@@ -145,4 +145,4 @@ def test_check_xpath_filter_failure_notification(client, live_server):
     time.sleep(1)
     run_filter_test(client, '//*[@id="nope-doesnt-exist"]')
 
-# Test that notification is never sent
+# Test that notification is never sent

changedetectionio/tests/test_html_to_text.py

@@ -6,11 +6,11 @@ from ..html_tools import html_to_text
 def test_html_to_text_func():
     test_html = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
      <a href="/first_link"> More Text </a>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      <a href="second_link.com"> Even More Text </a>
      </body>
      </html>
@@ -21,7 +21,7 @@ def test_html_to_text_func():
 
     no_links_text = \
         "Some initial text\n\nWhich is across multiple " \
-        "lines\n\nMore Text\nSo let's see what happens.\nEven More Text"
+        "lines\n\nMore Text So let's see what happens. Even More Text"
 
     # check that no links are in the extracted text
     assert text_content == no_links_text
@@ -31,7 +31,7 @@ def test_html_to_text_func():
 
     links_text = \
         "Some initial text\n\nWhich is across multiple lines\n\n[ More Text " \
-        "](/first_link)\nSo let's see what happens.\n[ Even More Text ]" \
+        "](/first_link) So let's see what happens. [ Even More Text ]" \
         "(second_link.com)"
 
     # check that links are present in the extracted text

changedetectionio/tests/test_ignore_regex_text.py

@@ -1,5 +1,7 @@
 #!/usr/bin/python3
 
+import time
+from flask import url_for
 from . util import live_server_setup
 from changedetectionio import html_tools
 
@@ -9,7 +11,7 @@ def test_setup(live_server):
 # Unit test of the stripper
 # Always we are dealing in utf-8
 def test_strip_regex_text_func():
-    from ..processors import text_json_diff as fetch_site_status
+    from changedetectionio import fetch_site_status
 
     test_content = """
     but sometimes we want to remove the lines.

changedetectionio/tests/test_ignore_text.py

@@ -11,8 +11,7 @@ def test_setup(live_server):
 # Unit test of the stripper
 # Always we are dealing in utf-8
 def test_strip_text_func():
-    from ..processors import text_json_diff as fetch_site_status
+    from changedetectionio import fetch_site_status
-
 
     test_content = """
     Some content
@@ -34,10 +33,10 @@ def test_strip_text_func():
 def set_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      </body>
      </html>
 
@@ -50,10 +49,10 @@ def set_original_ignore_response():
 def set_modified_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some NEW nice initial text<br>
+     Some NEW nice initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      <p>new ignore stuff</p>
      <p>blah</p>
      </body>
@@ -69,11 +68,11 @@ def set_modified_original_ignore_response():
 def set_modified_ignore_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
      <P>ZZZZz</P>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      </body>
      </html>
 

changedetectionio/tests/test_ignorehyperlinks.py

@@ -12,10 +12,10 @@ def test_setup(live_server):
 def set_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <a href="/original_link"> Some More Text </a>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      </body>
      </html>
     """
@@ -29,10 +29,10 @@ def set_original_ignore_response():
 def set_modified_ignore_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <a href="/modified_link"> Some More Text </a>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      </body>
      </html>
     """

changedetectionio/tests/test_ignorestatuscode.py

@@ -12,10 +12,10 @@ def test_setup(live_server):
 def set_original_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      </body>
      </html>
     """
@@ -27,10 +27,10 @@ def set_original_response():
 def set_some_changed_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines, and a new thing too.</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      </body>
      </html>
     """

changedetectionio/tests/test_ignorewhitespace.py

@@ -12,15 +12,15 @@ def test_setup(live_server):
 def set_original_ignore_response_but_with_whitespace():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>
 
 
      Which is across multiple lines</p>
      <br>
-     <br>
+     </br>
 
-         So let's see what happens.  <br>
+         So let's see what happens.  </br>
 
 
      </body>
@@ -34,10 +34,10 @@ def set_original_ignore_response_but_with_whitespace():
 def set_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      </body>
      </html>
 

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;html&#34;: &#34;&lt;b&gt;&#34;' in res.data
+    assert b'&#34;&lt;b&gt;' in res.data
-    assert res.data.count(b'{') >= 2
+    assert res.data.count(b'{\n') >= 2
 
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data

changedetectionio/tests/test_notification.py

@@ -73,12 +73,16 @@ 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
@@ -96,8 +100,6 @@ def test_check_notification(client, live_server):
                                                    "Diff URL: {{diff_url}}\n"
                                                    "Snapshot: {{current_snapshot}}\n"
                                                    "Diff: {{diff}}\n"
-                                                   "Diff Added: {{diff_added}}\n"
-                                                   "Diff Removed: {{diff_removed}}\n"
                                                    "Diff Full: {{diff_full}}\n"
                                                    ":-)",
                               "notification_screenshot": True,
@@ -145,7 +147,7 @@ def test_check_notification(client, live_server):
     assert ':-)' in notification_submission
     assert "Diff Full: Some initial text" in notification_submission
     assert "Diff: (changed) Which is across multiple lines" in notification_submission
-    assert "(into) which has this one new line" in notification_submission
+    assert "(into   ) which has this one new line" in notification_submission
     # Re #342 - check for accidental python byte encoding of non-utf8/string
     assert "b'" not in notification_submission
     assert re.search('Watch UUID: [0-9a-f]{8}(-[0-9a-f]{4}){3}-[0-9a-f]{12}', notification_submission, re.IGNORECASE)
@@ -158,12 +160,12 @@ 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)
-    # We keep PNG screenshots for now
+    assert notification_submission_object['attachments'][0]['filename'] == 'last-screenshot.jpg'
-    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/png'
+    assert notification_submission_object['attachments'][0]['mimetype'] == 'image/jpeg'
     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
@@ -295,10 +297,7 @@ 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_trigger.py

@@ -8,10 +8,10 @@ from . util import live_server_setup
 def set_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      </body>
      </html>
 
@@ -24,10 +24,10 @@ def set_original_ignore_response():
 def set_modified_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some NEW nice initial text<br>
+     Some NEW nice initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      </body>
      </html>
 
@@ -40,12 +40,12 @@ def set_modified_original_ignore_response():
 def set_modified_with_trigger_text_response():
     test_return_data = """<html>
        <body>
-     Some NEW nice initial text<br>
+     Some NEW nice initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
      Add to cart
-     <br>
+     <br/>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      </body>
      </html>
 
@@ -142,4 +142,4 @@ def test_trigger_functionality(client, live_server):
     res = client.get(url_for("preview_page", uuid="first"))
 
     # We should be able to see what we triggered on
-    assert b'<div class="triggered">Add to cart' in res.data
+    assert b'<div class="triggered">Add to cart' in res.data

changedetectionio/tests/test_trigger_regex.py

@@ -8,10 +8,10 @@ from . util import live_server_setup
 def set_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      </body>
      </html>
 
@@ -72,7 +72,7 @@ def test_trigger_regex_functionality(client, live_server):
     assert b'unviewed' not in res.data
 
     with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write("regex test123<br>\nsomething 123")
+        f.write("regex test123<br/>\nsomething 123")
 
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     time.sleep(sleep_time_for_fetch_thread)
@@ -81,4 +81,4 @@ def test_trigger_regex_functionality(client, live_server):
 
     # Cleanup everything
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-    assert b'Deleted' in res.data
+    assert b'Deleted' in res.data

changedetectionio/tests/test_trigger_regex_with_filter.py

@@ -8,10 +8,10 @@ from . util import live_server_setup
 def set_original_ignore_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      </body>
      </html>
 

changedetectionio/tests/test_unique_lines.py

@@ -94,6 +94,7 @@ 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/test_xpath_selector.py

@@ -12,10 +12,10 @@ def test_setup(live_server):
 def set_original_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      <div class="sametext">Some text thats the same</div>
      <div class="changetext">Some text that will change</div>
      </body>
@@ -29,10 +29,10 @@ def set_original_response():
 def set_modified_response():
     test_return_data = """<html>
        <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  THIS CHANGES AND SHOULDNT TRIGGER A CHANGE<br>
+     So let's see what happens.  THIS CHANGES AND SHOULDNT TRIGGER A CHANGE</br>
      <div class="sametext">Some text thats the same</div>
      <div class="changetext">Some new text</div>
      </body>

changedetectionio/tests/unit/test_notification_diff.py

@@ -13,51 +13,18 @@ class TestDiffBuilder(unittest.TestCase):
 
     def test_expected_diff_output(self):
         base_dir = os.path.dirname(__file__)
-        with open(base_dir + "/test-content/before.txt", 'r') as f:
+        output = diff.render_diff(previous_file=base_dir + "/test-content/before.txt", newest_file=base_dir + "/test-content/after.txt")
-            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   ) xok', output)
-        self.assertIn('(into) next-x-ok', output)
+        self.assertIn('(into   ) next-x-ok', output)
-        self.assertIn('(added) and something new', output)
+        self.assertIn('(added  ) and something new', output)
 
-        with open(base_dir + "/test-content/after-2.txt", 'r') as f:
+
-            newest_version_file_contents = f.read()
+        output = diff.render_diff(previous_file=base_dir + "/test-content/before.txt", newest_file=base_dir + "/test-content/after-2.txt")
-        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
-        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)
-        self.assertIn('(into) next-x-ok', output)
-        self.assertNotIn('(added) and something new', output)
-        
-        #diff_removed
-        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)
-        
 
         # @todo test blocks of changed, blocks of added, blocks of removed
 

changedetectionio/tests/util.py

@@ -9,10 +9,10 @@ def set_original_response():
     test_return_data = """<html>
     <head><title>head title</title></head>
     <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>Which is across multiple lines</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      <span class="foobar-detection" style='display:none'></span>
      </body>
      </html>
@@ -26,10 +26,10 @@ def set_modified_response():
     test_return_data = """<html>
     <head><title>modified head title</title></head>
     <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>which has this one new line</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
      </body>
      </html>
     """
@@ -43,11 +43,11 @@ def set_more_modified_response():
     test_return_data = """<html>
     <head><title>modified head title</title></head>
     <body>
-     Some initial text<br>
+     Some initial text</br>
      <p>which has this one new line</p>
-     <br>
+     </br>
-     So let's see what happens.  <br>
+     So let's see what happens.  </br>
-     Ohh yeah awesome<br>
+     Ohh yeah awesome<br/>
      </body>
      </html>
     """

changedetectionio/update_worker.py

@@ -4,8 +4,8 @@ import queue
 import time
 
 from changedetectionio import content_fetcher
-from .processors.text_json_diff import FilterNotFoundInResponse
+from changedetectionio import queuedWatchMetaData
-
+from changedetectionio.fetch_site_status import FilterNotFoundInResponse
 
 # A single update worker
 #
@@ -65,32 +65,20 @@ class update_worker(threading.Thread):
         if 'notification_urls' in n_object and n_object['notification_urls']:
             # HTML needs linebreak, but MarkDown and Text can use a linefeed
             if n_object['notification_format'] == 'HTML':
-                line_feed_sep = "<br>"
+                line_feed_sep = "</br>"
             else:
                 line_feed_sep = "\n"
 
-            # Add text that was triggered
+            with open(watch_history[dates[-1]], 'rb') as f:
-            snapshot_contents = watch.get_history_snapshot(dates[-1])
+                snapshot_contents = f.read()
-            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({
-                '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,
                 'watch_url': watch['url'],
+                '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_full': diff.render_diff(watch_history[dates[-2]], watch_history[dates[-1]], True, line_feed_sep=line_feed_sep)
             })
             logging.info (">> SENDING NOTIFICATION")
             self.notification_q.put(n_object)
@@ -163,8 +151,9 @@ class update_worker(threading.Thread):
                 os.unlink(full_path)
 
     def run(self):
+        from changedetectionio import fetch_site_status
 
-        from .processors import text_json_diff, restock_diff
+        update_handler = fetch_site_status.perform_site_check(datastore=self.datastore)
 
         while not self.app.config.exit.is_set():
 
@@ -180,22 +169,14 @@ class update_worker(threading.Thread):
                 if uuid in list(self.datastore.data['watching'].keys()):
                     changed_detected = False
                     contents = b''
+                    screenshot = False
+                    update_obj= {}
+                    xpath_data = False
                     process_changedetection_results = True
-                    update_obj = {}
+                    print("> Processing UUID {} Priority {} URL {}".format(uuid, queued_item_data.priority, self.datastore.data['watching'][uuid]['url']))
-                    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.
@@ -231,7 +212,9 @@ class update_worker(threading.Thread):
                         if e.page_text:
                             self.datastore.save_error_text(watch_uuid=uuid, contents=e.page_text)
 
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
+                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
+                                                                           # So that we get a trigger when the content is added again
+                                                                           'previous_md5': ''})
                         process_changedetection_results = False
 
                     except FilterNotFoundInResponse as e:
@@ -239,7 +222,9 @@ class update_worker(threading.Thread):
                             continue
 
                         err_text = "Warning, no filters were found, no change detection ran."
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
+                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
+                                                                           # So that we get a trigger when the content is added again
+                                                                           'previous_md5': ''})
 
                         # Only when enabled, send the notification
                         if self.datastore.data['watching'][uuid].get('filter_failure_notification_send', False):
@@ -256,12 +241,11 @@ class update_worker(threading.Thread):
 
                             self.datastore.update_watch(uuid=uuid, update_obj={'consecutive_filter_failures': c})
 
-                        process_changedetection_results = False
+                        process_changedetection_results = True
 
                     except content_fetcher.checksumFromPreviousCheckWasTheSame as e:
-                        # Yes fine, so nothing todo, don't continue to process.
+                        # Yes fine, so nothing todo
-                        process_changedetection_results = False
+                        pass
-                        changed_detected = False
 
                     except content_fetcher.BrowserStepsStepTimout as e:
 
@@ -269,7 +253,9 @@ class update_worker(threading.Thread):
                             continue
 
                         err_text = "Warning, browser step at position {} could not run, target not found, check the watch, add a delay if necessary.".format(e.step_n+1)
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
+                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
+                                                                           # So that we get a trigger when the content is added again
+                                                                           'previous_md5': ''})
 
 
                         if self.datastore.data['watching'][uuid].get('filter_failure_notification_send', False):
@@ -285,7 +271,6 @@ class update_worker(threading.Thread):
                                 c = 0
 
                             self.datastore.update_watch(uuid=uuid, update_obj={'consecutive_filter_failures': c})
-
                         process_changedetection_results = False
 
                     except content_fetcher.EmptyReply as e:
@@ -293,7 +278,6 @@ class update_worker(threading.Thread):
                         err_text = "EmptyReply - try increasing 'Wait seconds before extracting text', Status Code {}".format(e.status_code)
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
-                        process_changedetection_results = False
                     except content_fetcher.ScreenshotUnavailable as e:
                         err_text = "Screenshot unavailable, page did not render fully in the expected time - try increasing 'Wait seconds before extracting text'"
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
@@ -305,7 +289,6 @@ 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})
-                        process_changedetection_results = False
                     except content_fetcher.PageUnloadable as e:
                         err_text = "Page request from server didnt respond correctly"
                         if e.message:
@@ -315,9 +298,7 @@ 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))
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': str(e)})
@@ -334,18 +315,18 @@ 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:
-                            watch = self.datastore.data['watching'].get(uuid)
+                            watch = self.datastore.data['watching'][uuid]
-                            self.datastore.update_watch(uuid=uuid, update_obj=update_obj)
+                            fname = "" # Saved history text filename
 
-                            # Also save the snapshot on the first time checked
+                            # For the FIRST time we check a site, or a change detected, save the snapshot.
                             if changed_detected or not watch['last_checked']:
-                                watch.save_history_text(contents=contents,
+                                # A change was detected
-                                                        timestamp=str(round(time.time())),
+                                watch.save_history_text(contents=contents, timestamp=str(round(time.time())))
-                                                        snapshot_id=update_obj.get('previous_md5', 'none'))
+
+                            self.datastore.update_watch(uuid=uuid, update_obj=update_obj)
 
                             # A change was detected
                             if changed_detected:

docs/api_v1/assets/main.css

@@ -49,7 +49,6 @@ input[type="date"] {
   src: url('./glyphicons-halflings-regular.eot');
   src: url('./glyphicons-halflings-regular.eot?#iefix') format('embedded-opentype'),
     url('./glyphicons-halflings-regular.woff') format('woff'),
-    url('./glyphicons-halflings-regular.woff2') format('woff2'),
     url('./glyphicons-halflings-regular.ttf') format('truetype'),
     url('./glyphicons-halflings-regular.svg#glyphicons-halflingsregular') format('svg');
 }

docs/api_v1/index.html

@@ -5,13 +5,13 @@
   <meta name="description" content="Manage your changedetection.io watches via API, requires the `x-api-key` header which is found in the settings UI.">
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
-  <link href="assets/bootstrap.min.css?v=1677105736053" rel="stylesheet" media="screen">
+  <link href="assets/bootstrap.min.css" rel="stylesheet" media="screen">
-  <link href="assets/prism.css?v=1677105736053" rel="stylesheet" />
+  <link href="assets/prism.css" rel="stylesheet" />
-  <link href="assets/main.css?v=1677105736053" rel="stylesheet" media="screen, print">
+  <link href="assets/main.css" rel="stylesheet" media="screen, print">
-  <link href="assets/favicon.ico?v=1677105736053" rel="icon" type="image/x-icon">
+  <link href="assets/favicon.ico" rel="icon" type="image/x-icon">
-  <link href="assets/apple-touch-icon.png?v=1677105736053" rel="apple-touch-icon" sizes="180x180">
+  <link href="assets/apple-touch-icon.png" rel="apple-touch-icon" sizes="180x180">
-  <link href="assets/favicon-32x32.png?v=1677105736053" rel="icon" type="image/png" sizes="32x32">
+  <link href="assets/favicon-32x32.png" rel="icon" type="image/png" sizes="32x32">
-  <link href="assets/favicon-16x16.png?v=1677105736053" rel="icon" type="image/png" sizes="16x16">
+  <link href="assets/favicon-16x16.png"rel="icon" type="image/png" sizes="16x16">
 </head>
 
 <body class="container-fluid">
@@ -928,6 +928,6 @@
   </div>
 </div>
 
-<script src="assets/main.bundle.js?v=1677105736053"></script>
+<script src="assets/main.bundle.js"></script>
 </body>
 </html>

docs/apidoc.json

@@ -3,6 +3,5 @@
   "version": "0.1.0",
   "description": "Manage your changedetection.io watches via API, requires the `x-api-key` header which is found in the settings UI.",
   "title": "changedetection.io API",
-  "url" : "",
+  "url" : "https://changedetection.io/docs/api_v1/index.html"
-  "sampleUrl" : false
 }

docs/package.json

@@ -1,5 +1,5 @@
 {
   "dependencies": {
-    "apidoc": "^0.54.0"
+    "apidoc": "^0.53.1"
   }
 }

requirements.txt

@@ -2,7 +2,6 @@ eventlet>=0.31.0
 feedgen~=0.9
 flask-compress
 flask-login~=0.5
-flask-paginate
 flask_expects_json~=1.7
 flask_restful
 flask_wtf
@@ -32,7 +31,7 @@ dnspython<2.3.0
 # jq not available on Windows so must be installed manually
 
 # Notification library
-apprise~=1.3.0
+apprise~=1.2.1
 
 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
 paho-mqtt
@@ -43,7 +42,7 @@ paho-mqtt
 cryptography~=3.4
 
 # Used for CSS filtering
-beautifulsoup4
+bs4
 
 # XPath filtering, lxml is required by bs4 anyway, but put it here to be safe.
 lxml
@@ -69,5 +68,5 @@ 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 ~=7.2
+pytest ~=6.2
 pytest-flask ~=1.2