tweak

.github/workflows/containers.yml

@@ -98,7 +98,6 @@ jobs:
           platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
           cache-from: type=local,src=/tmp/.buildx-cache
           cache-to: type=local,dest=/tmp/.buildx-cache
-          provenance: false
 
       # A new tagged release is required, which builds :tag and :latest
       - name: Build and push :tag
@@ -117,7 +116,6 @@ jobs:
           platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
           cache-from: type=local,src=/tmp/.buildx-cache
           cache-to: type=local,dest=/tmp/.buildx-cache
-          provenance: false
 
       - 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/test-container-build.yml

@@ -10,13 +10,11 @@ on:
     paths:
       - requirements.txt
       - Dockerfile
-      - .github/workflows/*
 
   pull_request:
     paths:
       - requirements.txt
       - Dockerfile
-      - .github/workflows/*
 
   # 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

.github/workflows/test-only.yml

@@ -67,10 +67,10 @@ jobs:
           sleep 3
           # Should return 0 (no error) when grep finds it
           curl -s http://localhost:5556 |grep -q checkbox-uuid
-          
+          curl -s http://localhost:5556/rss|grep -q rss-specification
           # and IPv6
           curl -s -g -6 "http://[::1]:5556"|grep -q checkbox-uuid
-          
+          curl -s -g -6 "http://[::1]:5556/rss"|grep -q rss-specification
 
 #export WEBDRIVER_URL=http://localhost:4444/wd/hub
 #pytest tests/fetchers/test_content.py

README.md

@@ -1,8 +1,6 @@
 ## Web Site Change Detection, Monitoring and Notification.
 
-**_Detect website content changes and perform meaningful actions - trigger notifications via Discord, Email, Slack, Telegram, API calls and many more._**
+_Live your data-life pro-actively, Detect website changes and perform meaningful actions, trigger notifications via Discord, Email, Slack, Telegram, API calls and many more._
-
-_Live your data-life pro-actively._ 
 
 
 [<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start?src=github)

changedetectionio/__init__.py

@@ -1,15 +1,5 @@
 #!/usr/bin/python3
 
-from changedetectionio import queuedWatchMetaData
-from copy import deepcopy
-from distutils.util import strtobool
-from feedgen.feed import FeedGenerator
-from flask_compress import Compress as FlaskCompress
-from flask_login import current_user
-from flask_restful import abort, Api
-from flask_wtf import CSRFProtect
-from functools import wraps
-from threading import Event
 import datetime
 import flask_login
 import logging
@@ -20,6 +10,12 @@ import threading
 import time
 import timeago
 
+from changedetectionio import queuedWatchMetaData
+from copy import deepcopy
+from distutils.util import strtobool
+from feedgen.feed import FeedGenerator
+from threading import Event
+
 from flask import (
     Flask,
     abort,
@@ -32,11 +28,15 @@ from flask import (
     session,
     url_for,
 )
+from flask_compress import Compress as FlaskCompress
+from flask_login import login_required
+from flask_restful import abort, Api
+from flask_wtf import CSRFProtect
 
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.40.2'
+__version__ = '0.40.0.4'
 
 datastore = None
 
@@ -53,6 +53,7 @@ app = Flask(__name__,
             static_url_path="",
             static_folder="static",
             template_folder="templates")
+from flask_compress import Compress
 
 # Super handy for compressing large BrowserSteps responses and others
 FlaskCompress(app)
@@ -64,6 +65,8 @@ app.config.exit = Event()
 
 app.config['NEW_VERSION_AVAILABLE'] = False
 
+app.config['LOGIN_DISABLED'] = False
+
 #app.config["EXPLAIN_TEMPLATE_LOADING"] = True
 
 # Disables caching of the templates
@@ -71,6 +74,7 @@ app.config['TEMPLATES_AUTO_RELOAD'] = True
 app.jinja_env.add_extension('jinja2.ext.loopcontrols')
 csrf = CSRFProtect()
 csrf.init_app(app)
+
 notification_debug_log=[]
 
 watch_api = Api(app, decorators=[csrf.exempt])
@@ -145,6 +149,7 @@ class User(flask_login.UserMixin):
 
     # Compare given password against JSON store or Env var
     def check_password(self, password):
+
         import base64
         import hashlib
 
@@ -152,9 +157,11 @@ class User(flask_login.UserMixin):
         raw_salt_pass = os.getenv("SALTED_PASS", False)
 
         if not raw_salt_pass:
-            raw_salt_pass = datastore.data['settings']['application'].get('password')
+            raw_salt_pass = datastore.data['settings']['application']['password']
 
         raw_salt_pass = base64.b64decode(raw_salt_pass)
+
+
         salt_from_storage = raw_salt_pass[:32]  # 32 is the length of the salt
 
         # Use the exact same setup you used to generate the key, but this time put in the password to check
@@ -164,44 +171,21 @@ class User(flask_login.UserMixin):
             salt_from_storage,
             100000
         )
-        new_key = salt_from_storage + new_key
+        new_key =  salt_from_storage + new_key
 
         return new_key == raw_salt_pass
 
     pass
 
-
-def login_optionally_required(func):
-    @wraps(func)
-    def decorated_view(*args, **kwargs):
-
-        has_password_enabled = datastore.data['settings']['application'].get('password') or os.getenv("SALTED_PASS", False)
-
-        # Permitted
-        if request.endpoint == 'static_content' and request.view_args['group'] == 'styles':
-            return func(*args, **kwargs)
-        # Permitted
-        elif request.endpoint == 'diff_history_page' and datastore.data['settings']['application'].get('shared_diff_access'):
-            return func(*args, **kwargs)
-
-        elif request.method in flask_login.config.EXEMPT_METHODS:
-            return func(*args, **kwargs)
-        elif app.config.get('LOGIN_DISABLED'):
-            return func(*args, **kwargs)
-        elif has_password_enabled and not current_user.is_authenticated:
-            return app.login_manager.unauthorized()
-
-        return func(*args, **kwargs)
-
-    return decorated_view
-
 def changedetection_app(config=None, datastore_o=None):
     global datastore
     datastore = datastore_o
 
     # so far just for read-only via tests, but this will be moved eventually to be the main source
     # (instead of the global var)
-    app.config['DATASTORE'] = datastore_o
+    app.config['DATASTORE']=datastore_o
+
+    #app.config.update(config or {})
 
     login_manager = flask_login.LoginManager(app)
     login_manager.login_view = 'login'
@@ -229,8 +213,6 @@ def changedetection_app(config=None, datastore_o=None):
     # https://flask-cors.readthedocs.io/en/latest/
     #    CORS(app)
 
-
-
     @login_manager.user_loader
     def user_loader(email):
         user = User()
@@ -239,7 +221,7 @@ def changedetection_app(config=None, datastore_o=None):
 
     @login_manager.unauthorized_handler
     def unauthorized_handler():
-        flash("You must be logged in, please log in.", 'error')
+        # @todo validate its a URL of this host and use that
         return redirect(url_for('login', next=url_for('index')))
 
     @app.route('/logout')
@@ -252,6 +234,10 @@ def changedetection_app(config=None, datastore_o=None):
     @app.route('/login', methods=['GET', 'POST'])
     def login():
 
+        if not datastore.data['settings']['application']['password'] and not os.getenv("SALTED_PASS", False):
+            flash("Login not required, no password enabled.", "notice")
+            return redirect(url_for('index'))
+
         if request.method == 'GET':
             if flask_login.current_user.is_authenticated:
                 flash("Already logged in")
@@ -286,22 +272,27 @@ def changedetection_app(config=None, datastore_o=None):
         return redirect(url_for('login'))
 
     @app.before_request
-    def before_request_handle_cookie_x_settings():
+    def do_something_whenever_a_request_comes_in():
+
+        # Disable password login if there is not one set
+        # (No password in settings or env var)
+        app.config['LOGIN_DISABLED'] = datastore.data['settings']['application']['password'] == False and os.getenv("SALTED_PASS", False) == False
+
         # Set the auth cookie path if we're running as X-settings/X-Forwarded-Prefix
         if os.getenv('USE_X_SETTINGS') and 'X-Forwarded-Prefix' in request.headers:
             app.config['REMEMBER_COOKIE_PATH'] = request.headers['X-Forwarded-Prefix']
             app.config['SESSION_COOKIE_PATH'] = request.headers['X-Forwarded-Prefix']
 
-        return None
+        # For the RSS path, allow access via a token
+        if request.path == '/rss' and request.args.get('token'):
+            app_rss_token = datastore.data['settings']['application']['rss_access_token']
+            rss_url_token = request.args.get('token')
+            if app_rss_token == rss_url_token:
+                app.config['LOGIN_DISABLED'] = True
 
     @app.route("/rss", methods=['GET'])
+    @login_required
     def rss():
-        # Always requires token set
-        app_rss_token = datastore.data['settings']['application'].get('rss_access_token')
-        rss_url_token = request.args.get('token')
-        if rss_url_token != app_rss_token:
-            return "Access denied, bad token", 403
-
         from . import diff
         limit_tag = request.args.get('tag')
 
@@ -375,7 +366,7 @@ def changedetection_app(config=None, datastore_o=None):
         return response
 
     @app.route("/", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def index():
         from changedetectionio import forms
 
@@ -426,7 +417,6 @@ def changedetection_app(config=None, datastore_o=None):
                                  has_unviewed=datastore.has_unviewed,
                                  hosted_sticky=os.getenv("SALTED_PASS", False) == False,
                                  queued_uuids=[q_uuid.item['uuid'] for q_uuid in update_q.queue],
-                                 system_default_fetcher=datastore.data['settings']['application'].get('fetch_backend'),
                                  tags=existing_tags,
                                  watches=sorted_watches
                                  )
@@ -439,7 +429,7 @@ def changedetection_app(config=None, datastore_o=None):
 
     # AJAX endpoint for sending a test
     @app.route("/notification/send-test", methods=['POST'])
-    @login_optionally_required
+    @login_required
     def ajax_callback_send_notification_test():
 
         import apprise
@@ -472,7 +462,7 @@ def changedetection_app(config=None, datastore_o=None):
 
 
     @app.route("/clear_history/<string:uuid>", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def clear_watch_history(uuid):
         try:
             datastore.clear_watch_history(uuid)
@@ -484,7 +474,7 @@ def changedetection_app(config=None, datastore_o=None):
         return redirect(url_for('index'))
 
     @app.route("/clear_history", methods=['GET', 'POST'])
-    @login_optionally_required
+    @login_required
     def clear_all_history():
 
         if request.method == 'POST':
@@ -505,8 +495,43 @@ def changedetection_app(config=None, datastore_o=None):
         output = render_template("clear_all_history.html")
         return output
 
+
+    # If they edited an existing watch, we need to know to reset the current/previous md5 to include
+    # the excluded text.
+    def get_current_checksum_include_ignore_text(uuid):
+
+        import hashlib
+
+        from changedetectionio import fetch_site_status
+
+        # Get the most recent one
+        newest_history_key = datastore.data['watching'][uuid].get('newest_history_key')
+
+        # 0 means that theres only one, so that there should be no 'unviewed' history available
+        if newest_history_key == 0:
+            newest_history_key = list(datastore.data['watching'][uuid].history.keys())[0]
+
+        if newest_history_key:
+            with open(datastore.data['watching'][uuid].history[newest_history_key],
+                      encoding='utf-8') as file:
+                raw_content = file.read()
+
+                handler = fetch_site_status.perform_site_check(datastore=datastore)
+                stripped_content = html_tools.strip_ignore_text(raw_content,
+                                                             datastore.data['watching'][uuid]['ignore_text'])
+
+                if datastore.data['settings']['application'].get('ignore_whitespace', False):
+                    checksum = hashlib.md5(stripped_content.translate(None, b'\r\n\t ')).hexdigest()
+                else:
+                    checksum = hashlib.md5(stripped_content).hexdigest()
+
+                return checksum
+
+        return datastore.data['watching'][uuid]['previous_md5']
+
+
     @app.route("/edit/<string:uuid>", methods=['GET', 'POST'])
-    @login_optionally_required
+    @login_required
     # https://stackoverflow.com/questions/42984453/wtforms-populate-form-with-data-if-data-exists
     # https://wtforms.readthedocs.io/en/3.0.x/forms/#wtforms.form.Form.populate_obj ?
 
@@ -560,7 +585,6 @@ def changedetection_app(config=None, datastore_o=None):
 
 
         if request.method == 'POST' and form.validate():
-
             extra_update_obj = {}
 
             if request.args.get('unpause_on_save'):
@@ -614,6 +638,8 @@ def changedetection_app(config=None, datastore_o=None):
 
             visualselector_data_is_ready = datastore.visualselector_data_is_ready(uuid)
 
+            # Only works reliably with Playwright
+            visualselector_enabled = os.getenv('PLAYWRIGHT_DRIVER_URL', False) and default['fetch_backend'] == 'html_webdriver'
 
             # JQ is difficult to install on windows and must be manually added (outside requirements.txt)
             jq_support = True
@@ -626,12 +652,9 @@ def changedetection_app(config=None, datastore_o=None):
             system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
 
             is_html_webdriver = False
-            if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver':
+            if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_requests':
                 is_html_webdriver = True
 
-            # Only works reliably with Playwright
-            visualselector_enabled = os.getenv('PLAYWRIGHT_DRIVER_URL', False) and is_html_webdriver
-
             output = render_template("edit.html",
                                      browser_steps_config=browser_step_ui_config,
                                      current_base_url=datastore.data['settings']['application']['base_url'],
@@ -652,7 +675,7 @@ def changedetection_app(config=None, datastore_o=None):
         return output
 
     @app.route("/settings", methods=['GET', "POST"])
-    @login_optionally_required
+    @login_required
     def settings_page():
         from changedetectionio import content_fetcher, forms
 
@@ -732,7 +755,7 @@ def changedetection_app(config=None, datastore_o=None):
         return output
 
     @app.route("/import", methods=['GET', "POST"])
-    @login_optionally_required
+    @login_required
     def import_page():
         remaining_urls = []
         if request.method == 'POST':
@@ -770,7 +793,7 @@ def changedetection_app(config=None, datastore_o=None):
 
     # Clear all statuses, so we do not see the 'unviewed' class
     @app.route("/form/mark-all-viewed", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def mark_all_viewed():
 
         # Save the current newest history as the most recently viewed
@@ -780,7 +803,7 @@ def changedetection_app(config=None, datastore_o=None):
         return redirect(url_for('index'))
 
     @app.route("/diff/<string:uuid>", methods=['GET', 'POST'])
-    @login_optionally_required
+    @login_required
     def diff_history_page(uuid):
 
         from changedetectionio import forms
@@ -856,13 +879,8 @@ def changedetection_app(config=None, datastore_o=None):
 
         system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
 
-        is_html_webdriver = False
+        is_html_webdriver = True if watch.get('fetch_backend') == 'html_webdriver' or (
-        if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver':
+                    watch.get('fetch_backend', None) is None and system_uses_webdriver) else False
-            is_html_webdriver = True
-
-        password_enabled_and_share_is_off = False
-        if datastore.data['settings']['application'].get('password') or os.getenv("SALTED_PASS", False):
-            password_enabled_and_share_is_off = not datastore.data['settings']['application'].get('shared_diff_access')
 
         output = render_template("diff.html",
                                  current_diff_url=watch['url'],
@@ -877,7 +895,6 @@ def changedetection_app(config=None, datastore_o=None):
                                  left_sticky=True,
                                  newest=newest_version_file_contents,
                                  newest_version_timestamp=dates[-1],
-                                 password_enabled_and_share_is_off=password_enabled_and_share_is_off,
                                  previous=previous_version_file_contents,
                                  screenshot=screenshot_url,
                                  uuid=uuid,
@@ -888,7 +905,7 @@ def changedetection_app(config=None, datastore_o=None):
         return output
 
     @app.route("/preview/<string:uuid>", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def preview_page(uuid):
         content = []
         ignored_line_numbers = []
@@ -908,9 +925,8 @@ def changedetection_app(config=None, datastore_o=None):
         extra_stylesheets = [url_for('static_content', group='styles', filename='diff.css')]
 
 
-        is_html_webdriver = False
+        is_html_webdriver = True if watch.get('fetch_backend') == 'html_webdriver' or (
-        if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver':
+                watch.get('fetch_backend', None) is None and system_uses_webdriver) else False
-            is_html_webdriver = True
 
         # Never requested successfully, but we detected a fetch error
         if datastore.data['watching'][uuid].history_n == 0 and (watch.get_error_text() or watch.get_error_snapshot()):
@@ -979,7 +995,7 @@ def changedetection_app(config=None, datastore_o=None):
         return output
 
     @app.route("/settings/notification-logs", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def notification_logs():
         global notification_debug_log
         output = render_template("notification-log.html",
@@ -989,7 +1005,7 @@ def changedetection_app(config=None, datastore_o=None):
 
     # We're good but backups are even better!
     @app.route("/backup", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def get_backup():
 
         import zipfile
@@ -1109,14 +1125,13 @@ def changedetection_app(config=None, datastore_o=None):
             abort(404)
 
     @app.route("/form/add/quickwatch", methods=['POST'])
-    @login_optionally_required
+    @login_required
     def form_quick_watch_add():
         from changedetectionio import forms
         form = forms.quickWatchForm(request.form)
 
         if not form.validate():
-            for widget, l in form.errors.items():
+            flash("Error")
-                flash(','.join(l), 'error')
             return redirect(url_for('index'))
 
         url = request.form.get('url').strip()
@@ -1127,21 +1142,22 @@ def changedetection_app(config=None, datastore_o=None):
         add_paused = request.form.get('edit_and_watch_submit_button') != None
         new_uuid = datastore.add_watch(url=url, tag=request.form.get('tag').strip(), extras={'paused': add_paused})
 
-        if new_uuid:
+
-            if add_paused:
+        if not add_paused and new_uuid:
-                flash('Watch added in Paused state, saving will unpause.')
+            # Straight into the queue.
-                return redirect(url_for('edit_page', uuid=new_uuid, unpause_on_save=1))
+            update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
-            else:
+            flash("Watch added.")
-                # Straight into the queue.
+
-                update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
+        if add_paused:
-                flash("Watch added.")
+            flash('Watch added in Paused state, saving will unpause.')
+            return redirect(url_for('edit_page', uuid=new_uuid, unpause_on_save=1))
 
         return redirect(url_for('index'))
 
 
 
     @app.route("/api/delete", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def form_delete():
         uuid = request.args.get('uuid')
 
@@ -1158,7 +1174,7 @@ def changedetection_app(config=None, datastore_o=None):
         return redirect(url_for('index'))
 
     @app.route("/api/clone", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def form_clone():
         uuid = request.args.get('uuid')
         # More for testing, possible to return the first/only
@@ -1166,14 +1182,13 @@ def changedetection_app(config=None, datastore_o=None):
             uuid = list(datastore.data['watching'].keys()).pop()
 
         new_uuid = datastore.clone(uuid)
-        if new_uuid:
+        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
-            update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
+        flash('Cloned.')
-            flash('Cloned.')
 
         return redirect(url_for('index'))
 
     @app.route("/api/checknow", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def form_watch_checknow():
         # Forced recheck will skip the 'skip if content is the same' rule (, 'reprocess_existing_data': True})))
         tag = request.args.get('tag')
@@ -1207,7 +1222,7 @@ def changedetection_app(config=None, datastore_o=None):
         return redirect(url_for('index', tag=tag))
 
     @app.route("/form/checkbox-operations", methods=['POST'])
-    @login_optionally_required
+    @login_required
     def form_watch_list_checkbox_operations():
         op = request.form['op']
         uuids = request.form.getlist('uuids')
@@ -1271,7 +1286,7 @@ def changedetection_app(config=None, datastore_o=None):
         return redirect(url_for('index'))
 
     @app.route("/api/share-url", methods=['GET'])
-    @login_optionally_required
+    @login_required
     def form_share_put_watch():
         """Given a watch UUID, upload the info and return a share-link
            the share-link can be imported/added"""

changedetectionio/api/api_v1.py

@@ -202,11 +202,8 @@ class CreateWatch(Resource):
         del extras['url']
 
         new_uuid = self.datastore.add_watch(url=url, extras=extras)
-        if new_uuid:
+        self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
-            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
+        return {'uuid': new_uuid}, 201
-            return {'uuid': new_uuid}, 201
-        else:
-            return "Invalid or unsupported URL", 400
 
     @auth.check_token
     def get(self):

changedetectionio/blueprint/browser_steps/__init__.py

@@ -23,10 +23,11 @@
 
 from distutils.util import strtobool
 from flask import Blueprint, request, make_response
+from flask_login import login_required
 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
@@ -64,7 +65,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
     browser_steps_blueprint = Blueprint('browser_steps', __name__, template_folder="templates")
 
-    @login_optionally_required
+    @login_required
     @browser_steps_blueprint.route("/browsersteps_update", methods=['GET', 'POST'])
     def browsersteps_ui_update():
         import base64

changedetectionio/changedetection.py

@@ -31,13 +31,11 @@ def sigterm_handler(_signo, _stack_frame):
 def main():
     global datastore
     global app
-
-    datastore_path = None
-    do_cleanup = False
-    host = ''
-    ipv6_enabled = False
-    port = os.environ.get('PORT') or 5000
     ssl_mode = False
+    host = ''
+    port = os.environ.get('PORT') or 5000
+    do_cleanup = False
+    datastore_path = None
 
     # On Windows, create and use a default path.
     if os.name == 'nt':
@@ -48,7 +46,7 @@ def main():
         datastore_path = os.path.join(os.getcwd(), "../datastore")
 
     try:
-        opts, args = getopt.getopt(sys.argv[1:], "6Ccsd:h:p:", "port")
+        opts, args = getopt.getopt(sys.argv[1:], "Ccsd:h:p:", "port")
     except getopt.GetoptError:
         print('backend.py -s SSL enable -h [host] -p [port] -d [datastore path]')
         sys.exit(2)
@@ -68,10 +66,6 @@ def main():
         if opt == '-d':
             datastore_path = arg
 
-        if opt == '-6':
-            print ("Enabling IPv6 listen support")
-            ipv6_enabled = True
-
         # Cleanup (remove text files that arent in the index)
         if opt == '-c':
             do_cleanup = True
@@ -139,15 +133,13 @@ def main():
         from werkzeug.middleware.proxy_fix import ProxyFix
         app.wsgi_app = ProxyFix(app.wsgi_app, x_prefix=1, x_host=1)
 
-    s_type = socket.AF_INET6 if ipv6_enabled else socket.AF_INET
-
     if ssl_mode:
         # @todo finalise SSL config, but this should get you in the right direction if you need it.
-        eventlet.wsgi.server(eventlet.wrap_ssl(eventlet.listen((host, port), s_type),
+        eventlet.wsgi.server(eventlet.wrap_ssl(eventlet.listen((host, port), socket.AF_INET6),
                                                certfile='cert.pem',
                                                keyfile='privkey.pem',
                                                server_side=True), app)
 
     else:
-        eventlet.wsgi.server(eventlet.listen((host, int(port)), s_type), app)
+        eventlet.wsgi.server(eventlet.listen((host, int(port)), socket.AF_INET6), app)
 

changedetectionio/content_fetcher.py

@@ -252,6 +252,9 @@ class base_html_playwright(Fetcher):
                 self.proxy['password'] = parsed.password
 
     def screenshot_step(self, step_n=''):
+
+        # There's a bug where we need to do it twice or it doesnt take the whole page, dont know why.
+        self.page.screenshot(type='jpeg', clip={'x': 1.0, 'y': 1.0, 'width': 1280, 'height': 1024})
         screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=85)
 
         if self.browser_steps_screenshot_path is not None:
@@ -297,8 +300,8 @@ class base_html_playwright(Fetcher):
                 proxy=self.proxy,
                 # This is needed to enable JavaScript execution on GitHub and others
                 bypass_csp=True,
-                # Should be `allow` or `block` - sites like YouTube can transmit large amounts of data via Service Workers
+                # Can't think why we need the service workers for our use case?
-                service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'),
+                service_workers='block',
                 # Should never be needed
                 accept_downloads=False
             )
@@ -358,20 +361,28 @@ class base_html_playwright(Fetcher):
                 print ("Content Fetcher > Response object was none")
                 raise EmptyReply(url=url, status_code=None)
 
+            # Bug 2(?) Set the viewport size AFTER loading the page
+            self.page.set_viewport_size({"width": 1280, "height": 1024})
+
             # Run Browser Steps here
             self.iterate_browser_steps()
 
             extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
             time.sleep(extra_wait)
 
+
             self.content = self.page.content()
             self.status_code = response.status
+
             if len(self.page.content().strip()) == 0:
                 context.close()
                 browser.close()
                 print ("Content Fetcher > Content was empty")
                 raise EmptyReply(url=url, status_code=response.status)
 
+            # Bug 2(?) Set the viewport size AFTER loading the page
+            self.page.set_viewport_size({"width": 1280, "height": 1024})
+
             self.status_code = response.status
             self.content = self.page.content()
             self.headers = response.all_headers()
@@ -392,6 +403,8 @@ class base_html_playwright(Fetcher):
             # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
             # acceptable screenshot quality here
             try:
+                # Quality set to 1 because it's not used, just used as a work-around for a bug, no need to change this.
+                self.page.screenshot(type='jpeg', clip={'x': 1.0, 'y': 1.0, 'width': 1280, 'height': 1024}, quality=1)
                 # The actual screenshot
                 self.screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
             except Exception as e:

changedetectionio/forms.py

@@ -232,17 +232,12 @@ class validateURL(object):
 
     def __call__(self, form, field):
         import validators
-
         try:
             validators.url(field.data.strip())
         except validators.ValidationFailure:
             message = field.gettext('\'%s\' is not a valid URL.' % (field.data.strip()))
             raise ValidationError(message)
 
-        from .model.Watch import is_safe_url
-        if not is_safe_url(field.data):
-            raise ValidationError('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX')
-
 
 class ValidateListRegex(object):
     """
@@ -459,17 +454,17 @@ class globalSettingsRequestForm(Form):
 # datastore.data['settings']['application']..
 class globalSettingsApplicationForm(commonSettingsForm):
 
-    api_access_token_enabled = BooleanField('API access token security check enabled', default=True, validators=[validators.Optional()])
     base_url = StringField('Base URL', validators=[validators.Optional()])
-    empty_pages_are_a_change =  BooleanField('Treat empty pages as a change?', default=False)
-    fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
-    global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
     global_subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
+    global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
     ignore_whitespace = BooleanField('Ignore whitespace')
-    password = SaltyPasswordField()
     removepassword_button = SubmitField('Remove password', render_kw={"class": "pure-button pure-button-primary"})
+    empty_pages_are_a_change =  BooleanField('Treat empty pages as a change?', default=False)
     render_anchor_tag_content = BooleanField('Render anchor tag content', default=False)
-    shared_diff_access = BooleanField('Allow access to view diff page when password is enabled', default=False, validators=[validators.Optional()])
+    fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
+    api_access_token_enabled = BooleanField('API access token security check enabled', default=True, validators=[validators.Optional()])
+    password = SaltyPasswordField()
+
     filter_failure_notification_threshold_attempts = IntegerField('Number of times the filter can be missing before sending a notification',
                                                                   render_kw={"style": "width: 5em;"},
                                                                   validators=[validators.NumberRange(min=0,

changedetectionio/model/App.py

@@ -40,7 +40,6 @@ class model(dict):
                     'notification_body': default_notification_body,
                     'notification_format': default_notification_format,
                     'schema_version' : 0,
-                    'shared_diff_access': False,
                     'webdriver_delay': None  # Extra delay in seconds before extracting text
                 }
             }

changedetectionio/model/Watch.py

@@ -1,14 +1,9 @@
 from distutils.util import strtobool
 import logging
 import os
-import re
 import time
 import uuid
 
-# Allowable protocols, protects against javascript: etc
-# file:// is further checked by ALLOW_FILE_URI
-SAFE_PROTOCOL_REGEX='^(http|https|ftp|file):'
-
 minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 60))
 mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
 
@@ -23,7 +18,7 @@ base_config = {
     'consecutive_filter_failures': 0,  # Every time the CSS/xPath filter cannot be located, reset when all is fine.
     'extract_text': [],  # Extract text by regex after filters
     'extract_title_as_title': False,
-    'fetch_backend': 'system',
+    'fetch_backend': None,
     'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
     'has_ldjson_price_data': None,
     'track_ldjson_price_data': None,
@@ -60,22 +55,6 @@ base_config = {
     'webdriver_js_execute_code': None,  # Run before change-detection
 }
 
-
-def is_safe_url(test_url):
-    # See https://github.com/dgtlmoon/changedetection.io/issues/1358
-
-    # Remove 'source:' prefix so we dont get 'source:javascript:' etc
-    # 'source:' is a valid way to tell us to return the source
-
-    r = re.compile(re.escape('source:'), re.IGNORECASE)
-    test_url = r.sub('', test_url)
-
-    pattern = re.compile(os.getenv('SAFE_PROTOCOL_REGEX', SAFE_PROTOCOL_REGEX), re.IGNORECASE)
-    if not pattern.match(test_url.strip()):
-        return False
-
-    return True
-
 class model(dict):
     __newest_history_key = None
     __history_n = 0
@@ -114,11 +93,7 @@ class model(dict):
 
     @property
     def link(self):
-
         url = self.get('url', '')
-        if not is_safe_url(url):
-            return 'DISABLED'
-
         ready_url = url
         if '{%' in url or '{{' in url:
             from jinja2 import Environment

changedetectionio/static/js/watch-settings.js

@@ -1,7 +1,7 @@
-$(document).ready(function () {
+$(document).ready(function() {
     function toggle() {
         if ($('input[name="fetch_backend"]:checked').val() == 'html_webdriver') {
-            if (playwright_enabled) {
+            if(playwright_enabled) {
                 // playwright supports headers, so hide everything else
                 // See #664
                 $('#requests-override-options #request-method').hide();
@@ -14,14 +14,9 @@ $(document).ready(function () {
                 $('#requests-override-options').hide();
             }
 
+
             $('#webdriver-override-options').show();
 
-        } else if ($('input[name="fetch_backend"]:checked').val() == 'system') {
-            $('#requests-override-options #request-method').hide();
-            $('#requests-override-options #request-body').hide();
-            $('#ignore-status-codes-option').hide();
-            $('#requests-override-options').hide();
-            $('#webdriver-override-options').hide();
         } else {
 
             $('#requests-override-options').show();

changedetectionio/store.py

@@ -1,20 +1,20 @@
 from flask import (
     flash
 )
-
-from . model import App, Watch
-from copy import deepcopy
-from os import path, unlink
-from threading import Lock
 import json
 import logging
 import os
-import re
-import requests
-import secrets
 import threading
 import time
 import uuid as uuid_builder
+from copy import deepcopy
+from os import path, unlink
+from threading import Lock
+import re
+import requests
+import secrets
+
+from . model import App, Watch
 
 # Is there an existing library to ensure some data store (JSON etc) is in sync with CRUD methods?
 # Open a github issue if you know something :)
@@ -309,12 +309,9 @@ class ChangeDetectionStore:
                 logging.error("Error fetching metadata for shared watch link", url, str(e))
                 flash("Error fetching metadata for {}".format(url), 'error')
                 return False
-        from .model.Watch import is_safe_url
-        if not is_safe_url(url):
-            flash('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX', 'error')
-            return None
 
         with self.lock:
+
             # #Re 569
             new_watch = Watch.model(datastore_path=self.datastore_path, default={
                 'url': url,
@@ -676,13 +673,3 @@ class ChangeDetectionStore:
                 self.data['settings']['application']['notification_urls'][i] = re.sub(r, r'{{\1}}', url)
 
         return
-
-    # Some setups may have missed the correct default, so it shows the wrong config in the UI, although it will default to system-wide
-    def update_10(self):
-        for uuid, watch in self.data['watching'].items():
-            try:
-                if not watch.get('fetch_backend', ''):
-                    watch['fetch_backend'] = 'system'
-            except:
-                continue
-        return

changedetectionio/templates/diff.html

@@ -76,12 +76,8 @@
     </div>
 
      <div class="tab-pane-inner" id="text">
-         <div class="tip">Pro-tip: Use <strong>show current snapshot</strong> tab to visualise what will be ignored.</div>
+         <div class="tip">Pro-tip: Use <strong>show current snapshot</strong> tab to visualise what will be ignored.
-
+         </div>
-         {% if password_enabled_and_share_is_off %}
-           <div class="tip">Pro-tip: You can enable <strong>"share access when password is enabled"</strong> from settings</div>
-         {% endif %}
-
          <div class="snapshot-age">{{watch_a.snapshot_text_ctime|format_timestamp_timeago}}</div>
 
          <table>

changedetectionio/templates/settings.html

@@ -57,11 +57,6 @@
                         {% endif %}
                     </div>
 
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.application.form.shared_diff_access, class="shared_diff_access") }}
-                        <span class="pure-form-message-inline">Allow access to view watch diff page when password is enabled (Good for sharing the diff page)
-                        </span>
-                    </div>
                     <div class="pure-control-group">
                         {{ render_field(form.application.form.base_url, placeholder="http://yoursite.com:5000/",
                         class="m-d") }}

changedetectionio/templates/watch-overview.html

@@ -91,12 +91,7 @@
                     <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}"></a>
                     <a class="link-spread" href="{{url_for('form_share_put_watch', uuid=watch.uuid)}}"><img class="status-icon"  src="{{url_for('static_content', group='images', filename='spread.svg')}}" class="status-icon icon icon-spread" title="Create a link to share watch config with others" /></a>
 
-                    {% if watch.get_fetch_backend == "html_webdriver"
+                    {%if watch.get_fetch_backend == "html_webdriver" %}<img class="status-icon" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" title="Using a chrome browser" />{% endif %}
-                         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" />
-                    {% 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 }}

changedetectionio/tests/test_access_control.py

@@ -1,34 +1,18 @@
-from . util import live_server_setup, extract_UUID_from_client
 from flask import url_for
-import time
+from . util import live_server_setup
 
-def test_check_access_control(app, client, live_server):
+def test_check_access_control(app, client):
     # Still doesnt work, but this is closer.
-    live_server_setup(live_server)
 
     with app.test_client(use_cookies=True) as c:
         # Check we don't have any password protection enabled yet.
         res = c.get(url_for("settings_page"))
         assert b"Remove password" not in res.data
 
-        # add something that we can hit via diff page later
+        # Enable password check.
-        res = c.post(
-            url_for("import_page"),
-            data={"urls": url_for('test_random_content_endpoint', _external=True)},
-            follow_redirects=True
-        )
-
-        assert b"1 Imported" in res.data
-        time.sleep(2)
-        res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
-        assert b'1 watches queued for rechecking.' in res.data
-        time.sleep(2)
-
-        # Enable password check and diff page access bypass
         res = c.post(
             url_for("settings_page"),
             data={"application-password": "foobar",
-                  "application-shared_diff_access": "True",
                   "requests-time_between_check-minutes": 180,
                   'application-fetch_backend': "html_requests"},
             follow_redirects=True
@@ -38,15 +22,9 @@ def test_check_access_control(app, client, live_server):
 
         # Check we hit the login
         res = c.get(url_for("index"), follow_redirects=True)
-        # Should be logged out
+
         assert b"Login" in res.data
 
-        # The diff page should return something valid when logged out
-        res = client.get(url_for("diff_history_page", uuid="first"))
-        assert b'Random content' in res.data
-
-
-
         # Menu should not be available yet
         #        assert b"SETTINGS" not in res.data
         #        assert b"BACKUP" not in res.data
@@ -131,25 +109,3 @@ def test_check_access_control(app, client, live_server):
 
         assert b"Password protection enabled" not in res.data
 
-        # Now checking the diff access
-        # Enable password check and diff page access bypass
-        res = c.post(
-            url_for("settings_page"),
-            data={"application-password": "foobar",
-                  # Should be disabled
-#                  "application-shared_diff_access": "True",
-                  "requests-time_between_check-minutes": 180,
-                  'application-fetch_backend': "html_requests"},
-            follow_redirects=True
-        )
-
-        assert b"Password protection enabled." in res.data
-
-        # Check we hit the login
-        res = c.get(url_for("index"), follow_redirects=True)
-        # Should be logged out
-        assert b"Login" in res.data
-
-        # The diff page should return something valid when logged out
-        res = client.get(url_for("diff_history_page", uuid="first"))
-        assert b'Random content' not in res.data

changedetectionio/tests/test_backend.py

@@ -3,7 +3,7 @@
 import time
 from flask import url_for
 from urllib.request import urlopen
-from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, extract_rss_token_from_UI
+from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
 
 sleep_time_for_fetch_thread = 3
 
@@ -76,8 +76,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
     assert b'unviewed' in res.data
 
     # #75, and it should be in the RSS feed
-    rss_token = extract_rss_token_from_UI(client)
+    res = client.get(url_for("rss"))
-    res = client.get(url_for("rss", token=rss_token, _external=True))
     expected_url = url_for('test_endpoint', _external=True)
     assert b'<rss' in res.data
 

changedetectionio/tests/test_rss.py

@@ -1,39 +0,0 @@
-#!/usr/bin/python3
-
-import time
-from flask import url_for
-from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, extract_rss_token_from_UI
-
-
-def test_rss_and_token(client, live_server):
-    set_original_response()
-    live_server_setup(live_server)
-
-    # Add our URL to the import page
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": url_for('test_random_content_endpoint', _external=True)},
-        follow_redirects=True
-    )
-
-    assert b"1 Imported" in res.data
-    rss_token = extract_rss_token_from_UI(client)
-
-    time.sleep(2)
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(2)
-
-    # Add our URL to the import page
-    res = client.get(
-        url_for("rss", token="bad token", _external=True),
-        follow_redirects=True
-    )
-
-    assert b"Access denied, bad token" in res.data
-
-    res = client.get(
-        url_for("rss", token=rss_token, _external=True),
-        follow_redirects=True
-    )
-    assert b"Access denied, bad token" not in res.data
-    assert b"Random content" in res.data

changedetectionio/tests/test_security.py

@@ -2,9 +2,11 @@ from flask import url_for
 from . util import set_original_response, set_modified_response, live_server_setup
 import time
 
-
+def test_setup(live_server):
-def test_bad_access(client, live_server):
     live_server_setup(live_server)
+
+def test_file_access(client, live_server):
+
     res = client.post(
         url_for("import_page"),
         data={"urls": 'https://localhost'},
@@ -17,49 +19,18 @@ def test_bad_access(client, live_server):
     res = client.post(
         url_for("edit_page", uuid="first"),
         data={
-              "url": 'javascript:alert(document.domain)',
+              "url": 'file:///etc/passwd',
               "tag": "",
               "method": "GET",
               "fetch_backend": "html_requests",
               "body": ""},
         follow_redirects=True
     )
+    time.sleep(3)
 
-    assert b'Watch protocol is not permitted by SAFE_PROTOCOL_REGEX' in res.data
+    res = client.get(
-
+        url_for("index", uuid="first"),
-    res = client.post(
-        url_for("form_quick_watch_add"),
-        data={"url": '            javascript:alert(123)', "tag": ''},
         follow_redirects=True
     )
 
-    assert b'Watch protocol is not permitted by SAFE_PROTOCOL_REGEX' in res.data
+    assert b'denied for security reasons' in res.data
-
-    res = client.post(
-        url_for("form_quick_watch_add"),
-        data={"url": '%20%20%20javascript:alert(123)%20%20', "tag": ''},
-        follow_redirects=True
-    )
-
-    assert b'Watch protocol is not permitted by SAFE_PROTOCOL_REGEX' in res.data
-
-
-    res = client.post(
-        url_for("form_quick_watch_add"),
-        data={"url": ' source:javascript:alert(document.domain)', "tag": ''},
-        follow_redirects=True
-    )
-
-    assert b'Watch protocol is not permitted by SAFE_PROTOCOL_REGEX' in res.data
-
-    # file:// is permitted by default, but it will be caught by ALLOW_FILE_URI
-
-    client.post(
-        url_for("form_quick_watch_add"),
-        data={"url": 'file:///tasty/disk/drive', "tag": ''},
-        follow_redirects=True
-    )
-    time.sleep(1)
-    res = client.get(url_for("index"))
-
-    assert b'file:// type access is denied for security reasons.' in res.data

changedetectionio/tests/util.py

@@ -70,15 +70,6 @@ def extract_api_key_from_UI(client):
     api_key = m.group(1)
     return api_key.strip()
 
-# kinda funky, but works for now
-def extract_rss_token_from_UI(client):
-    import re
-    res = client.get(
-        url_for("index"),
-    )
-    m = re.search('token=(.+?)"', str(res.data))
-    token_key = m.group(1)
-    return token_key.strip()
 
 # kinda funky, but works for now
 def extract_UUID_from_client(client):
@@ -107,12 +98,6 @@ def wait_for_all_checks(client):
 
 def live_server_setup(live_server):
 
-    @live_server.app.route('/test-random-content-endpoint')
-    def test_random_content_endpoint():
-        import secrets
-        return "Random content - {}\n".format(secrets.token_hex(64))
-
-
     @live_server.app.route('/test-endpoint')
     def test_endpoint():
         ctype = request.args.get('content_type')

changedetectionio/tests/visualselector/test_fetch_data.py

@@ -52,12 +52,3 @@ def test_visual_selector_content_ready(client, live_server):
     # Open it and see if it roughly looks correct
     with open(os.path.join('test-datastore', uuid, 'elements.json'), 'r') as f:
         json.load(f)
-
-    # Some options should be enabled
-    # @todo - in the future, the visibility should be toggled by JS from the request type setting
-    res = client.get(
-        url_for("edit_page", uuid="first"),
-        follow_redirects=True
-    )
-    assert b'notification_screenshot' in res.data
-

docker-compose.yml

@@ -1,4 +1,3 @@
-version: '3.2'
 services:
     changedetection:
       image: ghcr.io/dgtlmoon/changedetection.io
@@ -41,6 +40,7 @@ services:
   #
   #        Base URL of your changedetection.io install (Added to the notification alert)
   #      - BASE_URL=https://mysite.com
+
   #        Respect proxy_pass type settings, `proxy_set_header Host "localhost";` and `proxy_set_header X-Forwarded-Prefix /app;`
   #        More here https://github.com/dgtlmoon/changedetection.io/wiki/Running-changedetection.io-behind-a-reverse-proxy-sub-directory
   #      - USE_X_SETTINGS=1
@@ -94,10 +94,7 @@ services:
 #            - CHROME_REFRESH_TIME=600000
 #            - DEFAULT_BLOCK_ADS=true
 #            - DEFAULT_STEALTH=true
-#
+
-#             Ignore HTTPS errors, like for self-signed certs
-#            - DEFAULT_IGNORE_HTTPS_ERRORS=true
-#
 volumes:
   changedetection-data: