remove debug

.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: |         
@@ -58,11 +58,6 @@ jobs:
           # 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: |
           cd changedetectionio

.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

@@ -65,7 +65,6 @@ Requires Playwright to be enabled.
 - Get notified when certain keywords appear in Twitter search results
 - Proactively search for jobs, get notified when companies update their careers page, search job portals for keywords.
 - Get alerts when new job positions are open on Bamboo HR and other job platforms
-- Website defacement monitoring
 
 _Need an actual Chrome runner with Javascript support? We support fetching via WebDriver and Playwright!</a>_
 

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__ = '0.40.3'
 
 datastore = None
 
@@ -421,10 +419,6 @@ 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 +429,16 @@ 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'])
-
-        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
-
+        return output
 
 
     # AJAX endpoint for sending a test
@@ -481,19 +463,11 @@ 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)
@@ -627,16 +601,6 @@ 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)
 
@@ -1284,13 +1248,6 @@ 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 +1270,6 @@ 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/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 = {}
-io_interface_context = None
+def cleanup_playwright_session():
 
+    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'])
-    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'])
+    @browser_steps_blueprint.route("/browsersteps_update", methods=['GET', '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):
-            return make_response('No session exists under that ID', 500)
-
+        # Because we don't "really" run in a context manager ( we make the playwright interface global/long-living )
+        # 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':
@@ -132,7 +112,12 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             # @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:
-#            cleanup_playwright_session()
-#            return make_response('Browser session ran out of time :( Please reload this page.', 401)
+        # Setup interface
+        if request.method == 'GET':
 
-        # Screenshots and other info only needed on requesting a step (POST)
-        try:
-            state = browsersteps_sessions[browsersteps_session_id]['browserstepper'].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)
+            if not browsersteps_playwright_browser_interface:
+                print("Starting connection with playwright")
+                logging.debug("browser_steps.py connecting")
 
-        # 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-")
+                global browsersteps_playwright_browser_interface_context
+                from . import nonContext
+                browsersteps_playwright_browser_interface_context = nonContext.c_sync_playwright()
+                browsersteps_playwright_browser_interface = browsersteps_playwright_browser_interface_context.start()
 
-        output = json.dumps({'screenshot': "data:image/jpeg;base64,{}".format(
-            base64.b64encode(state[0]).decode('ascii')),
-            'xpath_data': state[1],
-            'session_age_start': browsersteps_sessions[browsersteps_session_id]['browserstepper'].age_start,
-            'browser_time_remaining': round(remaining)
-        })
+                time.sleep(1)
+                # At 20 minutes, some other variable is closing it
+                # @todo find out what it is and set it
+                seconds_keepalive = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
 
-        with os.fdopen(tmp_fd, 'w') as f:
-            f.write(output)
+                # 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_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,
-                                           mimetype='application/json; charset=UTF-8',
-                                           etag=True))
-        # No longer needed
-        os.unlink(tmp_file)
+                browsersteps_playwright_browser_interface_end_time = time.time() + (seconds_keepalive-3)
+                print("Starting connection with playwright - done")
+
+            if not browsersteps_live_ui_o.get(browsersteps_session_id):
+                # 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

@@ -71,10 +71,10 @@ 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, selector, value):
         # self.page.set_viewport_size({"width": 1280, "height": 5000})
         now = time.time()
         response = self.page.goto(value, timeout=0, wait_until='commit')
@@ -105,8 +105,7 @@ class steppable_browser_interface():
         print("Clicking element")
         if not len(selector.strip()):
             return
-
-        self.page.click(selector=selector, timeout=30 * 1000, delay=randint(200, 500))
+        self.page.click(selector, timeout=10 * 1000, delay=randint(200, 500))
 
     def action_click_element_if_exists(self, selector, value):
         import playwright._impl._api_types as _api_types

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
@@ -84,14 +77,13 @@ class ReplyWithContentButNoText(Exception):
         self.screenshot = screenshot
         return
 
-
 class Fetcher():
     browser_steps = None
     browser_steps_screenshot_path = None
     content = None
     error = None
     fetcher_description = "No description"
-    headers = {}
+    headers = None
     status_code = None
     webdriver_js_execute_code = None
     xpath_data = None
@@ -113,6 +105,7 @@ class Fetcher():
         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):
         return self.error
@@ -159,15 +152,13 @@ class Fetcher():
             interface = steppable_browser_interface()
             interface.page = self.page
 
-            valid_steps = filter(
-                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
-                self.browser_steps)
+            valid_steps = filter(lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'), self.browser_steps)
 
             for step in valid_steps:
                 step_n += 1
                 print(">> Iterating check - browser Step n {} - {}...".format(step_n, step['operation']))
-                self.screenshot_step("before-" + str(step_n))
-                self.save_step_html("before-" + str(step_n))
+                self.screenshot_step("before-"+str(step_n))
+                self.save_step_html("before-"+str(step_n))
                 try:
                     optional_value = step['optional_value']
                     selector = step['selector']
@@ -182,11 +173,12 @@ class Fetcher():
                                                       optional_value=optional_value)
                     self.screenshot_step(step_n)
                     self.save_step_html(step_n)
-                except TimeoutError as e:
-                    print(str(e))
+                except TimeoutError:
                     # 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 +188,6 @@ 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 +205,6 @@ def available_fetchers():
 
     return p
 
-
 class base_html_playwright(Fetcher):
     fetcher_description = "Playwright {}/Javascript".format(
         os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
@@ -278,118 +268,6 @@ 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 +278,6 @@ 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 +294,7 @@ 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 +324,12 @@ 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 +348,7 @@ 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 +356,7 @@ 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
@@ -510,7 +370,7 @@ 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
@@ -522,8 +382,7 @@ class base_html_playwright(Fetcher):
             else:
                 self.page.evaluate("var include_filters=''")
 
-            self.xpath_data = self.page.evaluate(
-                "async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
+            self.xpath_data = self.page.evaluate("async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
             self.instock_data = self.page.evaluate("async () => {" + self.instock_data_js + "}")
 
             # Bug 3 in Playwright screenshot handling
@@ -535,8 +394,7 @@ class base_html_playwright(Fetcher):
             # acceptable screenshot quality here
             try:
                 # The actual screenshot
-                self.screenshot = self.page.screenshot(type='jpeg', full_page=True,
-                                                       quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
+                self.screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
             except Exception as e:
                 context.close()
                 browser.close()
@@ -545,7 +403,6 @@ 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, include_removed=True, include_added=True):
     cruncher = difflib.SequenceMatcher(isjunk=lambda x: x in " \\t", a=before, b=after)
 
     # @todo Line-by-line mode instead of buncghed, including `after` that is not in `before` (maybe unset?)
@@ -19,23 +19,19 @@ def customSequenceMatcher(before, after, include_equal=False, include_removed=Tr
             g = before[alo:ahi]
             yield g
         elif include_removed and tag == 'delete':
-            row_prefix = "(removed) " if include_change_type_prefix else ''
-            g = [ row_prefix + i for i in same_slicer(before, alo, ahi)]
+            g = ["(removed) " + i for i in same_slicer(before, alo, ahi)]
             yield g
-        elif include_replaced and tag == 'replace':
-            row_prefix = "(changed) " if include_change_type_prefix else ''
-            g = [row_prefix + i for i in same_slicer(before, alo, ahi)]
-            row_prefix = "(into) " if include_change_type_prefix else ''
-            g += [row_prefix + i for i in same_slicer(after, blo, bhi)]
+        elif tag == 'replace':
+            g = ["(changed) " + i for i in same_slicer(before, alo, ahi)]
+            g += ["(into) " + i for i in same_slicer(after, blo, bhi)]
             yield g
         elif include_added and tag == 'insert':
-            row_prefix = "(added) " if include_change_type_prefix else ''
-            g = [row_prefix + i for i in same_slicer(after, blo, bhi)]
+            g = ["(added) " + i for i in same_slicer(after, blo, bhi)]
             yield g
 
 # only_differences - only return info about the differences, no context
 # line_feed_sep could be "<br>" or "<li>" or "\n" etc
-def render_diff(previous_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_version_file_contents, newest_version_file_contents, include_equal=False, include_removed=True, include_added=True, line_feed_sep="\n"):
 
     newest_version_file_contents = [line.rstrip() for line in newest_version_file_contents.splitlines()]
 
@@ -44,13 +40,9 @@ def render_diff(previous_version_file_contents, newest_version_file_contents, in
     else:
         previous_version_file_contents = ""
 
-    rendered_diff = customSequenceMatcher(before=previous_version_file_contents,
-                                          after=newest_version_file_contents,
-                                          include_equal=include_equal,
-                                          include_removed=include_removed,
-                                          include_added=include_added,
-                                          include_replaced=include_replaced,
-                                          include_change_type_prefix=include_change_type_prefix)
+    rendered_diff = customSequenceMatcher(previous_version_file_contents,
+                                          newest_version_file_contents,
+                                          include_equal, include_removed, include_added)
 
     # Recursively join lists
     f = lambda L: line_feed_sep.join([f(x) if type(x) is list else x for x in L])

changedetectionio/forms.py

@@ -399,19 +399,13 @@ 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)
-
-    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
+    check_unique_lines = BooleanField('Only trigger when new lines appear', default=False)
     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

@@ -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/model/Watch.py

@@ -20,16 +20,12 @@ 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
     '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
@@ -330,8 +326,7 @@ 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.strip().lower() for line in content.splitlines()])
+            alist = set([line.decode('utf-8').strip().lower() for line in open(v, 'rb')])
             existing_history = existing_history.union(alist)
 
         # Check that everything in local_lines(new stuff) already exists in existing_history - it should
@@ -459,38 +454,3 @@ 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 +5,17 @@ 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_added': '',
+    'diff_removed': '',
+    'diff_full': '',
+    'diff_url': '',
+    'preview_url': '',
+    'current_snapshot': ''
 }
 
 default_notification_format_for_watch = 'System default'
@@ -89,7 +88,7 @@ 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],
     )
     
@@ -212,18 +211,17 @@ 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_added': n_object.get('diff_added', ''),  # Null default in the case we use a test
+            'diff_removed': n_object.get('diff_removed', ''),  # Null default in the case we use a test
+            'diff_full': n_object.get('diff_full', ''),  # Null default in the case we use a test
+            'preview_url': preview_url,
+            'current_snapshot': n_object['current_snapshot'] if 'current_snapshot' in n_object else ''
         })
 
     return tokens

changedetectionio/processors/restock_diff.py

@@ -9,7 +9,7 @@ from copy import deepcopy
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
-name = 'Re-stock detection for single product pages'
+name = 'Re-stock detection'
 description = 'Detects if the product goes back to in-stock'
 
 class perform_site_check(difference_detection_processor):

changedetectionio/processors/text_json_diff.py

@@ -279,34 +279,6 @@ 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 +337,6 @@ 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/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

@@ -4,29 +4,26 @@ function isItemInStock() {
     '0 in stock',
     'agotado',
     'artikel zurzeit vergriffen',
-    'as soon as stock is available',
     'available for back order',
     'backordered',
-    'brak na stanie',
     'brak w magazynie',
+    'brak na stanie',
     'coming soon',
     'currently unavailable',
     'en rupture de stock',
-    'item is no longer available',
+    'as soon as stock is 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',
+    'não estamos a aceitar encomendas',
     'produkt niedostępny',
+    'no longer in stock',
     'sold out',
     'temporarily out of stock',
     'temporarily unavailable',
@@ -34,19 +31,7 @@ function isItemInStock() {
     '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) {
@@ -57,39 +42,13 @@ function isItemInStock() {
         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';
-          }
+      for (const outOfStockText of outOfStockTexts) {
+        if (elementText.includes(outOfStockText)) {
+          return elementText; // item is out of 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.
 }
 

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

@@ -35,4 +35,3 @@ 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 @@ $(document).ready(function () {
             current_selected_i = false;
             // Reverse order - the most specific one should be deeper/"laster"
             // Basically, find the most 'deepest'
-            var possible_elements = [];
-            xpath_data['size_pos'].forEach(function (item, index) {
+            //$('#browsersteps-selector-canvas').css('cursor', 'pointer');
+            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'
-                    // (input, textarea, button, A etc)
-                    possible_elements.push(item);
+                    // Only highlight these interesting types
+                    if (1) {
+                        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
-                    // 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') {
+                    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";
 
@@ -894,21 +893,6 @@ 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 {
@@ -1069,15 +1053,12 @@ ul {
   color: #fff;
   ul {
     padding: 0.3rem;
-
     li {
-      list-style: none;
-      font-size: 0.8rem;
-    }
+    list-style: none;
+}
   }
 
 }
-
 .restock-label {
   &.in-stock {
     background-color: var(--color-background-button-green);

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 {
@@ -898,17 +872,6 @@ 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;
@@ -1026,8 +989,7 @@ ul {
   #quick-watch-processor-type ul {
     padding: 0.3rem; }
     #quick-watch-processor-type ul li {
-      list-style: none;
-      font-size: 0.8rem; }
+      list-style: none; }
 
 .restock-label {
   padding: 3px;

changedetectionio/store.py

@@ -316,8 +316,7 @@ class ChangeDetectionStore:
             # #Re 569
             new_watch = Watch.model(datastore_path=self.datastore_path, default={
                 'url': url,
-                'tag': tag,
-                'date_created': int(time.time())
+                'tag': tag
             })
 
             new_uuid = new_watch['uuid']
@@ -680,13 +679,3 @@ 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

@@ -17,13 +17,12 @@
                                 <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>
                             {% 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" >Add email</a>
                             {% endif %}
                               <a href="{{url_for('notification_logs')}}" class="pure-button button-secondary button-xsmall" >Notification debug logs</a>
                             </div>
@@ -104,10 +103,6 @@
                                         <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">
@@ -115,7 +110,7 @@
                                     URLs generated by changedetection.io (such as <code>{{ '{{diff_url}}' }}</code>) require the <code>BASE_URL</code> environment variable set.<br>
                                     Your <code>BASE_URL</code> var is currently "{{settings_application['current_base_url']}}"
 									<br>
-									Warning: Contents of <code>{{ '{{diff}}' }}</code>, <code>{{ '{{diff_removed}}' }}</code>, and <code>{{ '{{diff_added}}' }}</code> depend on how the difference algorithm perceives the change. For example, an addition or removal could be perceived as a change in some cases. <a target="_new" href="https://github.com/dgtlmoon/changedetection.io/wiki/Using-the-%7B%7Bdiff%7D%7D,-%7B%7Bdiff_added%7D%7D,-and-%7B%7Bdiff_removal%7D%7D-notification-tokens">More Here</a> <br>
+									Warning: Contents of <code>{{ '{{diff}}' }}</code>, <code>{{ '{{diff_removed}}' }}</code>, and <code>{{ '{{diff_added}}' }}</code> depend on how the difference algorithm perceives the change. For example, an addition or removal could be perceived as a change in some cases. <a target="_new" href="https://github.com/dgtlmoon/changedetection.io/wiki/Using-the-%7B%7Bdiff%7D%7D,-%7B%7Bdiff_added%7D%7D,-and-%7B%7Bdiff_removal%7D%7D-notification-tokens">More Here</a> </br>
                                 </div>
                             </div>
                         </div>

changedetectionio/templates/_pagination.jinja

@@ -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 name="viewport" content="width=device-width, initial-scale=1.0" >
-    <meta name="description" content="Self hosted website change detection." >
+    <meta charset="utf-8"/>
+    <meta name="viewport" content="width=device-width, initial-scale=1.0"/>
+    <meta name="description" content="Self hosted website change detection."/>
     <title>Change Detection{{extra_title}}</title>
-    <link rel="alternate" type="application/rss+xml" title="Changedetection.io » Feed{% if active_tag %}- {{active_tag}}{% endif %}" href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}" >
-    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='pure-min.css')}}" >
-    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='styles.css')}}" >
+    <link rel="alternate" type="application/rss+xml" title="Changedetection.io » Feed{% if active_tag %}- {{active_tag}}{% endif %}" href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}"/>
+    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='pure-min.css')}}"/>
+    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='styles.css')}}"/>
     {% if extra_stylesheets %}
       {% for m in extra_stylesheets %}
-        <link rel="stylesheet" href="{{ m }}?ver=1000" >
+        <link rel="stylesheet" href="{{ m }}?ver=1000"/>
       {% endfor %}
     {% endif %}
 
-    <link rel="apple-touch-icon" sizes="180x180" href="{{url_for('static_content', group='favicons', filename='apple-touch-icon.png')}}">
-    <link rel="icon" type="image/png" sizes="32x32" href="{{url_for('static_content', group='favicons', filename='favicon-32x32.png')}}">
-    <link rel="icon" type="image/png" sizes="16x16" href="{{url_for('static_content', group='favicons', filename='favicon-16x16.png')}}">
-    <link rel="manifest" href="{{url_for('static_content', group='favicons', filename='site.webmanifest')}}">
-    <link rel="mask-icon" href="{{url_for('static_content', group='favicons', filename='safari-pinned-tab.svg')}}" color="#5bbad5">
-    <link rel="shortcut icon" href="{{url_for('static_content', group='favicons', filename='favicon.ico')}}">
-    <meta name="msapplication-TileColor" content="#da532c">
-    <meta name="msapplication-config" content="favicons/browserconfig.xml">
-    <meta name="theme-color" content="#ffffff">
+    <link rel="apple-touch-icon" sizes="180x180" href="{{url_for('static_content', group='favicons', filename='apple-touch-icon.png')}}"/>
+    <link rel="icon" type="image/png" sizes="32x32" href="{{url_for('static_content', group='favicons', filename='favicon-32x32.png')}}"/>
+    <link rel="icon" type="image/png" sizes="16x16" href="{{url_for('static_content', group='favicons', filename='favicon-16x16.png')}}"/>
+    <link rel="manifest" href="{{url_for('static_content', group='favicons', filename='site.webmanifest')}}"/>
+    <link rel="mask-icon" href="{{url_for('static_content', group='favicons', filename='safari-pinned-tab.svg')}}" color="#5bbad5"/>
+    <link rel="shortcut icon" href="{{url_for('static_content', group='favicons', filename='favicon.ico')}}"/>
+    <meta name="msapplication-TileColor" content="#da532c"/>
+    <meta name="msapplication-config" content="favicons/browserconfig.xml"/>
+    <meta name="theme-color" content="#ffffff"/>
 
     <style>
       body::before {
         background-image: url({{url_for('static_content', group='images', filename='gradient-border.png') }});
       }
     </style>
-    <script 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 %}
@@ -117,7 +117,7 @@
         <form id="extract-data-form" class="pure-form pure-form-stacked edit-form"
               action="{{ url_for('diff_history_page', uuid=uuid) }}#extract"
               method="POST">
-            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
+            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
 
             <p>This tool will extract text data from all of the watch history.</p>
 
@@ -149,9 +149,9 @@
 <script>
     const newest_version_timestamp = {{newest_version_timestamp}};
 </script>
-<script 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 %}

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 src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>
-<script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
-<script src="{{url_for('static_content', group='js', filename='visual-selector.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='visual-selector.js')}}" defer></script>
 {% 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">
@@ -52,7 +50,7 @@
     <div class="box-wrap inner">
         <form class="pure-form pure-form-stacked"
               action="{{ url_for('edit_page', uuid=uuid, next = request.args.get('next'), unpause_on_save = request.args.get('unpause_on_save')) }}" method="POST">
-             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
+             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
 
             <div class="tab-pane-inner" id="general">
                 <fieldset>
@@ -165,7 +163,7 @@ User-Agent: wonderbra 1.0") }}
             </div>
             {% if playwright_enabled %}
             <div class="tab-pane-inner" id="browser-steps">
-                <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}" 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 +186,11 @@ 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.<br>
+                                            Please allow 10-15 seconds for the browser to connect.
                                         </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 +220,7 @@ User-Agent: wonderbra 1.0") }}
                     <div class="field-group" id="notification-field-group">
                         {% if has_default_notification_urls %}
                         <div class="inline-warning">
-                            <img class="inline-warning-icon" src="{{url_for('static_content', group='images', filename='notice.svg')}}" alt="Look out!" title="Lookout!" >
+                            <img class="inline-warning-icon" src="{{url_for('static_content', group='images', filename='notice.svg')}}" alt="Look out!" title="Lookout!"/>
                             There are <a href="{{ url_for('settings_page')}}#notifications">system-wide notification URLs enabled</a>, this form will override notification settings for this watch only &dash; an empty Notification URL list here will still send notifications.
                         </div>
                         {% endif %}
@@ -247,6 +244,12 @@ 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,
@@ -284,39 +287,37 @@ xpath://body/div/span[contains(@class, 'example-class')]",
                                 href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br>
                 </span>
                     </div>
-                <fieldset class="pure-control-group">
-                    {{ render_field(form.subtractive_selectors, rows=5, placeholder="header
+                    <div class="pure-control-group">
+                      {{ render_field(form.subtractive_selectors, rows=5, placeholder="header
 footer
 nav
 .stockticker") }}
-                    <span class="pure-form-message-inline">
+                      <span class="pure-form-message-inline">
                         <ul>
                           <li> Remove HTML element(s) by CSS selector before text conversion. </li>
                           <li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
                         </ul>
                       </span>
-                </fieldset>
-                <div class="text-filtering">
-                <fieldset class="pure-group" id="text-filtering-type-options">
-                    <h3>Text filtering</h3>
-                        Limit trigger/ignore/block/extract to;<br>
-                        {{ render_checkbox_field(form.filter_text_added) }}
-                        {{ render_checkbox_field(form.filter_text_replaced) }}
-                        {{ render_checkbox_field(form.filter_text_removed) }}
-                    <span class="pure-form-message-inline">Note: Depending on the length and similarity of the text on each line, the algorithm may consider an <strong>addition</strong> instead of <strong>replacement</strong> for example.</span>
-                    <span class="pure-form-message-inline">So it's always better to select <strong>Added</strong>+<strong>Replaced</strong> when you're interested in new content.</span><br>
-                    <span class="pure-form-message-inline">When content is merely moved in a list, it will also trigger an <strong>addition</strong>, consider enabling <code><strong>Only trigger when unique lines appear</strong></code></span>
-                </fieldset>
+                    </div>
+                <fieldset class="pure-group">
+                    {{ render_field(form.ignore_text, rows=5, placeholder="Some text to ignore in a line
+/some.regex\d{2}/ for case-INsensitive regex
+                    ") }}
+                    <span class="pure-form-message-inline">
+                        <ul>
+                            <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
+                            <li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
+                            <li>Changing this will affect the comparison checksum which may trigger an alert</li>
+                            <li>Use the preview/show current tab to see ignores</li>
+                        </ul>
+                </span>
 
-                <fieldset class="pure-control-group">
-                    {{ render_checkbox_field(form.check_unique_lines) }}
-                    <span class="pure-form-message-inline">Good for websites that just move the content around, and you want to know when NEW content is added, compares new lines against all history for this watch.</span>
-                </fieldset>
+            </fieldset>
                 <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 +328,6 @@ 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
@@ -376,7 +362,6 @@ Unavailable") }}
                         </span>
                     </div>
                 </fieldset>
-                </div>
             </div>
             {% endif %}
 
@@ -393,7 +378,7 @@ Unavailable") }}
 
             {% 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">
@@ -410,7 +395,7 @@ 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>

changedetectionio/templates/import.html

@@ -1,7 +1,7 @@
 {% extends 'base.html' %}
 {% block content %}
 {% from '_helpers.jinja' import render_field %}
-<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="edit-form monospaced-textarea">
 
     <div class="tabs collapsable">
@@ -13,7 +13,7 @@
 
     <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">
                     <legend>
                         Enter one URL per line, and optionally add tags for each URL after a space, delineated by comma

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">
@@ -58,7 +58,7 @@
          {% if is_html_webdriver %}
            {% if screenshot %}
              <div class="snapshot-age">{{watch.snapshot_screenshot_ctime|format_timestamp_timeago}}</div>
-             <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request" >
+             <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request"/>
            {% else %}
               No screenshot available just yet! Try rechecking the page.
            {% endif %}

changedetectionio/templates/settings.html

@@ -9,10 +9,10 @@
     const email_notification_prefix=JSON.parse('{{emailprefix|tojson}}');
 {% endif %}
 </script>
-<script 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='tabs.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
 
-<script src="{{url_for('static_content', group='js', filename='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">

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>
-<script src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
+{% from '_pagination.jinja' import pagination %}
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
 
 <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">
@@ -25,25 +26,20 @@
             </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"  name="op" value="unpause">UnPause</button>
         <button class="pure-button button-secondary button-xsmall"  name="op" value="mute">Mute</button>
         <button class="pure-button button-secondary button-xsmall"  name="op" value="unmute">UnMute</button>
         <button class="pure-button button-secondary button-xsmall" name="op" value="recheck">Recheck</button>
-        <button class="pure-button button-secondary button-xsmall" name="op" value="mark-viewed">Mark viewed</button>
         <button class="pure-button button-secondary button-xsmall" name="op" value="notification-default">Use default notification</button>
-        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="clear-history">Clear/reset history</button>
-        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242;" name="op" value="delete">Delete</button>
+        <button class="pure-button button-secondary button-xsmall" style="background: #dd4242; font-size: 70%" 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 %}
@@ -53,19 +49,18 @@
         {% endfor %}
     </div>
 
-    {% set sort_order = sort_order or 'asc' %}
-    {% set sort_attribute = sort_attribute or 'last_changed'  %}
+    {% set sort_order = request.args.get('order', 'asc') == 'asc' %}
+    {% 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" %}
-                {% 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><input style="vertical-align: middle" type="checkbox" id="check-all"/> #</th>
                 <th></th>
+                {% set link_order = "desc" if sort_order else "asc" %}
+                {% set arrow_span = "" %}
                 <th><a class="{{ 'active '+link_order if sort_attribute == 'label' else 'inactive' }}" href="{{url_for('index', sort='label', order=link_order, tag=active_tag)}}">Website <span class='arrow {{link_order}}'></span></a></th>
                 <th><a class="{{ 'active '+link_order if sort_attribute == 'last_checked' else 'inactive' }}" href="{{url_for('index', sort='last_checked', order=link_order, tag=active_tag)}}">Last Checked <span class='arrow {{link_order}}'></span></a></th>
                 <th><a class="{{ 'active '+link_order if sort_attribute == 'last_changed' else 'inactive' }}" href="{{url_for('index', sort='last_changed', order=link_order, tag=active_tag)}}">Last Changed <span class='arrow {{link_order}}'></span></a></th>
@@ -74,7 +69,12 @@
             </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'] }}
                 {% if watch.last_error is defined and watch.last_error != False %}error{% endif %}
@@ -82,26 +82,26 @@
                 {% 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 }}
 
@@ -123,7 +123,7 @@
                         <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>
+                        <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 %}
 
@@ -135,7 +135,6 @@
                         {% else %}
                             Not yet checked
                         {% endif %}
-                    </span>
                     {% endif %}
 
                     {% if not active_tag %}
@@ -179,7 +178,10 @@
                 <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/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_block_while_text_present.py

@@ -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,
-              "url": test_url,
-              'fetch_backend': "html_requests"
-              },
+        data={"text_should_not_be_present": ignore_text, "url": test_url, 'fetch_backend': "html_requests"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -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_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_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/unit/test_notification_diff.py

@@ -19,12 +19,8 @@ class TestDiffBuilder(unittest.TestCase):
         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 = diff.render_diff(previous_version_file_contents, newest_version_file_contents)
         output = output.split("\n")
-
-
         self.assertIn('(changed) ok', output)
         self.assertIn('(into) xok', output)
         self.assertIn('(into) next-x-ok', output)

changedetectionio/update_worker.py

@@ -69,28 +69,17 @@ class update_worker(threading.Thread):
             else:
                 line_feed_sep = "\n"
 
-            # Add text that was triggered
             snapshot_contents = watch.get_history_snapshot(dates[-1])
-            trigger_text = watch.get('trigger_text', [])
-            triggered_text = ''
-
-            if len(trigger_text):
-                from . import html_tools
-                triggered_text = html_tools.get_triggered_text(content=snapshot_contents, trigger_text=trigger_text)
-                if triggered_text:
-                    triggered_text = line_feed_sep.join(triggered_text)
-
 
             n_object.update({
+                'watch_url': watch['url'],
+                'uuid': watch_uuid,
+                'screenshot': watch.get_screenshot() if watch.get('notification_screenshot') else None,
                 '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'],
+                '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)
             })
             logging.info (">> SENDING NOTIFICATION")
             self.notification_q.put(n_object)
@@ -315,8 +304,7 @@ 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,
-                                                                           'has_ldjson_price_data': None})
+                                                                           'last_check_status': e.status_code})
                         process_changedetection_results = False
                     except Exception as e:
                         self.app.logger.error("Exception reached processing watch UUID: %s - %s", uuid, str(e))
@@ -334,7 +322,6 @@ class update_worker(threading.Thread):
 
                         self.cleanup_error_artifacts(uuid)
 
-                    #
                     # Different exceptions mean that we may or may not want to bump the snapshot, trigger notifications etc
                     if process_changedetection_results:
                         try:

requirements.txt

@@ -2,7 +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