Merge branch 'master' into regex-cleanup-311

.github/workflows/codeql-analysis.yml

@@ -30,11 +30,11 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v2
+      uses: actions/checkout@v4
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v1
+      uses: github/codeql-action/init@v2
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
@@ -45,7 +45,7 @@ jobs:
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@v1
+      uses: github/codeql-action/autobuild@v2
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 https://git.io/JvXDl
@@ -59,4 +59,4 @@ jobs:
     #   make release
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v1
+      uses: github/codeql-action/analyze@v2

.github/workflows/containers.yml

@@ -39,9 +39,9 @@ jobs:
     # Or if we are in a tagged release scenario.
     if: ${{ github.event.workflow_run.conclusion == 'success' }} || ${{ github.event.release.tag_name }} != ''
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - name: Set up Python 3.9
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: 3.9
 
@@ -58,27 +58,27 @@ jobs:
           echo ${{ github.ref }} > changedetectionio/tag.txt
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v1
+        uses: docker/setup-qemu-action@v3
         with:
           image: tonistiigi/binfmt:latest
           platforms: all
 
       - name: Login to GitHub Container Registry
-        uses: docker/login-action@v1
+        uses: docker/login-action@v3
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Login to Docker Hub Container Registry
-        uses: docker/login-action@v1
+        uses: docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_HUB_USERNAME }}
           password: ${{ secrets.DOCKER_HUB_ACCESS_TOKEN }}
 
       - name: Set up Docker Buildx
         id: buildx
-        uses: docker/setup-buildx-action@v1
+        uses: docker/setup-buildx-action@v3
         with:
           install: true
           version: latest
@@ -88,7 +88,7 @@ jobs:
       - name: Build and push :dev
         id: docker_build
         if: ${{ github.ref }} == "refs/heads/master"
-        uses: docker/build-push-action@v2
+        uses: docker/build-push-action@v5
         with:
           context: ./
           file: ./Dockerfile
@@ -105,7 +105,7 @@ jobs:
       - name: Build and push :tag
         id: docker_build_tag_release
         if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
-        uses: docker/build-push-action@v2
+        uses: docker/build-push-action@v5
         with:
           context: ./
           file: ./Dockerfile
@@ -125,7 +125,7 @@ jobs:
         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 }}
 
       - name: Cache Docker layers
-        uses: actions/cache@v2
+        uses: actions/cache@v3
         with:
           path: /tmp/.buildx-cache
           key: ${{ runner.os }}-buildx-${{ github.sha }}

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

@@ -24,22 +24,22 @@ jobs:
   test-container-build:
     runs-on: ubuntu-latest
     steps:
-        - uses: actions/checkout@v2
+        - uses: actions/checkout@v4
         - name: Set up Python 3.9
-          uses: actions/setup-python@v2
+          uses: actions/setup-python@v4
           with:
             python-version: 3.9
 
         # Just test that the build works, some libraries won't compile on ARM/rPi etc
         - name: Set up QEMU
-          uses: docker/setup-qemu-action@v1
+          uses: docker/setup-qemu-action@v3
           with:
             image: tonistiigi/binfmt:latest
             platforms: all
 
         - name: Set up Docker Buildx
           id: buildx
-          uses: docker/setup-buildx-action@v1
+          uses: docker/setup-buildx-action@v3
           with:
             install: true
             version: latest
@@ -49,7 +49,7 @@ jobs:
         # Check we can still build under alpine/musl
         - name: Test that the docker containers can build (musl via alpine check)
           id: docker_build_musl
-          uses: docker/build-push-action@v2
+          uses: docker/build-push-action@v5
           with:
             context: ./
             file: ./.github/test/Dockerfile-alpine
@@ -57,7 +57,7 @@ jobs:
 
         - name: Test that the docker containers can build
           id: docker_build
-          uses: docker/build-push-action@v2
+          uses: docker/build-push-action@v5
           # https://github.com/docker/build-push-action#customizing
           with:
             context: ./

.github/workflows/test-only.yml

@@ -7,11 +7,11 @@ jobs:
   test-application:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
 
       # Mainly just for link/flake8
       - name: Set up Python 3.10
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: '3.10'
 

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

@@ -11,10 +11,10 @@ jobs:
   test-pip-build-basics:
     runs-on: ubuntu-latest
     steps:
-        - uses: actions/checkout@v2
+        - uses: actions/checkout@v4
 
         - name: Set up Python 3.9
-          uses: actions/setup-python@v2
+          uses: actions/setup-python@v4
           with:
             python-version: 3.9
 

changedetectionio/__init__.py

@@ -38,7 +38,9 @@ from flask_paginate import Pagination, get_page_parameter
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.45.1'
+__version__ = '0.45.2'
+
+from changedetectionio.store import BASE_URL_NOT_SET_TEXT
 
 datastore = None
 
@@ -356,11 +358,9 @@ def changedetection_app(config=None, datastore_o=None):
                 # Include a link to the diff page, they will have to login here to see if password protection is enabled.
                 # Description is the page you watch, link takes you to the diff JS UI page
                 # Dict val base_url will get overriden with the env var if it is set.
-                ext_base_url = datastore.data['settings']['application'].get('base_url')
+                ext_base_url = datastore.data['settings']['application'].get('active_base_url')
-                if ext_base_url:
+
-                    # Go with overriden value
+                # Because we are called via whatever web server, flask should figure out the right path (
-                    diff_link = {'href': "{}{}".format(ext_base_url, url_for('diff_history_page', uuid=watch['uuid'], _external=False))}
-                else:
                 diff_link = {'href': url_for('diff_history_page', uuid=watch['uuid'], _external=True)}
 
                 fe.link(link=diff_link)
@@ -714,7 +714,6 @@ def changedetection_app(config=None, datastore_o=None):
             output = render_template("edit.html",
                                      available_processors=processors.available_processors(),
                                      browser_steps_config=browser_step_ui_config,
-                                     current_base_url=datastore.data['settings']['application']['base_url'],
                                      emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
                                      form=form,
                                      has_default_notification_urls=True if len(datastore.data['settings']['application']['notification_urls']) else False,
@@ -804,7 +803,6 @@ def changedetection_app(config=None, datastore_o=None):
 
         output = render_template("settings.html",
                                  form=form,
-                                 current_base_url = datastore.data['settings']['application']['base_url'],
                                  hide_remove_pass=os.getenv("SALTED_PASS", False),
                                  api_key=datastore.data['settings']['application'].get('api_access_token'),
                                  emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
@@ -1270,10 +1268,10 @@ def changedetection_app(config=None, datastore_o=None):
                 update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
             i = 1
 
-        elif tag != None:
+        elif tag:
             # Items that have this current tag
             for watch_uuid, watch in datastore.data['watching'].items():
-                if (tag != None and tag in watch.get('tags', {})):
+                if tag in watch.get('tags', {}):
                     if watch_uuid not in running_uuids and not datastore.data['watching'][watch_uuid]['paused']:
                         update_q.put(
                             queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False})

changedetectionio/blueprint/check_proxies/__init__.py

@@ -57,9 +57,11 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                 status.update({'status': 'ERROR OTHER', 'length': len(contents), 'text': f"Got empty reply with code {e.status_code} - Access denied"})
             else:
                 status.update({'status': 'ERROR OTHER', 'length': len(contents) if contents else 0, 'text': f"Empty reply with code {e.status_code}, needs chrome?"})
-
+        except content_fetcher.ReplyWithContentButNoText as e:
+            txt = f"Got reply but with no content - Status code {e.status_code} - It's possible that the filters were found, but contained no usable text (or contained only an image)."
+            status.update({'status': 'ERROR', 'text': txt})
         except Exception as e:
-            status.update({'status': 'ERROR OTHER', 'length': len(contents) if contents else 0, 'text': 'Error: '+str(e)})
+            status.update({'status': 'ERROR OTHER', 'length': len(contents) if contents else 0, 'text': 'Error: '+type(e).__name__+str(e)})
         else:
             status.update({'status': 'OK', 'length': len(contents), 'text': ''})
 

changedetectionio/content_fetcher.py

@@ -77,11 +77,13 @@ class ScreenshotUnavailable(Exception):
 
 
 class ReplyWithContentButNoText(Exception):
-    def __init__(self, status_code, url, screenshot=None):
+    def __init__(self, status_code, url, screenshot=None, has_filters=False, html_content=''):
         # Set this so we can use it in other parts of the app
         self.status_code = status_code
         self.url = url
         self.screenshot = screenshot
+        self.has_filters = has_filters
+        self.html_content = html_content
         return
 
 
@@ -343,7 +345,7 @@ class base_html_playwright(Fetcher):
                         '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'),
+                        'user_agent': {k.lower(): v for k, v in request_headers.items()}.get('user-agent', None),
                         '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': [
@@ -443,7 +445,7 @@ 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={k.lower(): v for k, v in request_headers.items()}.get('user-agent', None),
                 proxy=self.proxy,
                 # This is needed to enable JavaScript execution on GitHub and others
                 bypass_csp=True,
@@ -684,7 +686,7 @@ class html_requests(Fetcher):
             is_binary=False):
 
         # Make requests use a more modern looking user-agent
-        if not 'User-Agent' in request_headers:
+        if not {k.lower(): v for k, v in request_headers.items()}.get('user-agent', None):
             request_headers['User-Agent'] = os.getenv("DEFAULT_SETTINGS_HEADERS_USERAGENT",
                                                       'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36')
 

changedetectionio/forms.py

@@ -229,16 +229,19 @@ class ValidateJinja2Template(object):
     def __call__(self, form, field):
         from changedetectionio import notification
 
-        from jinja2 import Environment, BaseLoader, TemplateSyntaxError
+        from jinja2 import Environment, BaseLoader, TemplateSyntaxError, UndefinedError
         from jinja2.meta import find_undeclared_variables
 
 
         try:
             jinja2_env = Environment(loader=BaseLoader)
             jinja2_env.globals.update(notification.valid_tokens)
+
             rendered = jinja2_env.from_string(field.data).render()
         except TemplateSyntaxError as e:
             raise ValidationError(f"This is not a valid Jinja2 template: {e}") from e
+        except UndefinedError as e:
+            raise ValidationError(f"A variable or function is not defined: {e}") from e
 
         ast = jinja2_env.parse(field.data)
         undefined = ", ".join(find_undeclared_variables(ast))
@@ -502,7 +505,10 @@ class globalSettingsRequestForm(Form):
 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()])
+    base_url = StringField('Notification base URL override',
+                           validators=[validators.Optional()],
+                           render_kw={"placeholder": os.getenv('BASE_URL', 'Not set')}
+                           )
     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()])

changedetectionio/notification.py

@@ -208,15 +208,11 @@ def create_notification_parameters(n_object, datastore):
         watch_tag = ''
 
     # Create URLs to customise the notification with
-    base_url = datastore.data['settings']['application']['base_url']
+    # active_base_url - set in store.py data property
+    base_url = datastore.data['settings']['application'].get('active_base_url')
 
     watch_url = n_object['watch_url']
 
-    # Re #148 - Some people have just {{ base_url }} in the body or title, but this may break some notification services
-    #           like 'Join', so it's always best to atleast set something obvious so that they are not broken.
-    if base_url == '':
-        base_url = "<base-url-env-var-not-set>"
-
     diff_url = "{}/diff/{}".format(base_url, uuid)
     preview_url = "{}/preview/{}".format(base_url, uuid)
 
@@ -226,7 +222,7 @@ def create_notification_parameters(n_object, datastore):
     # Valid_tokens also used as a field validator
     tokens.update(
         {
-            'base_url': base_url if base_url is not None else '',
+            'base_url': base_url,
             'current_snapshot': n_object['current_snapshot'] if 'current_snapshot' in n_object else '',
             'diff': n_object.get('diff', ''),  # Null default in the case we use a test
             'diff_added': n_object.get('diff_added', ''),  # Null default in the case we use a test

changedetectionio/processors/text_json_diff.py

@@ -314,7 +314,12 @@ class perform_site_check(difference_detection_processor):
         # 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:
-            raise content_fetcher.ReplyWithContentButNoText(url=url, status_code=fetcher.get_last_status_code(), screenshot=screenshot)
+            raise content_fetcher.ReplyWithContentButNoText(url=url,
+                                                            status_code=fetcher.get_last_status_code(),
+                                                            screenshot=screenshot,
+                                                            has_filters=has_filter_rule,
+                                                            html_content=html_content
+                                                            )
 
         # We rely on the actual text in the html output.. many sites have random script vars etc,
         # in the future we'll implement other mechanisms.

changedetectionio/res/puppeteer_fetch.js

@@ -18,7 +18,9 @@ module.exports = async ({page, context}) => {
 
     await page.setBypassCSP(true)
     await page.setExtraHTTPHeaders(req_headers);
+    if (user_agent) {
         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);

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

@@ -5,14 +5,19 @@ function isItemInStock() {
     'agotado',
     'artikel zurzeit vergriffen',
     'as soon as stock is available',
+    'ausverkauft', // sold out
     'available for back order',
+    'back-order or out of stock',
     'backordered',
+    'benachrichtigt mich', // notify me
     'brak na stanie',
     'brak w magazynie',
     'coming soon',
     'currently have any tickets for this',
     'currently unavailable',
+    'dostępne wkrótce',
     'en rupture de stock',
+    'ist derzeit nicht auf lager',
     'item is no longer available',
     'message if back in stock',
     'nachricht bei',
@@ -37,6 +42,7 @@ function isItemInStock() {
     'unavailable tickets',
     'we do not currently have an estimate of when this product will be back in stock.',
     'zur zeit nicht an lager',
+    '已售完',
   ];
 
 

changedetectionio/static/js/browser-steps.js

@@ -208,7 +208,7 @@ $(document).ready(function () {
             console.log(x);
             if (x && first_available.length) {
                 // @todo will it let you click shit that has a layer ontop? probably not.
-                if (x['tagtype'] === 'text' || x['tagtype'] === 'email' || x['tagName'] === 'textarea' || x['tagtype'] === 'password' || x['tagtype'] === 'search') {
+                if (x['tagtype'] === 'text' || x['tagtype'] === 'number' || x['tagtype'] === 'email' || x['tagName'] === 'textarea' || x['tagtype'] === 'password' || x['tagtype'] === 'search') {
                     $('select', first_available).val('Enter text in field').change();
                     $('input[type=text]', first_available).first().val(x['xpath']);
                     $('input[placeholder="Value"]', first_available).addClass('ok').click().focus();

changedetectionio/static/js/global-settings.js

@@ -32,5 +32,10 @@ $(document).ready(function () {
         window.getSelection().removeAllRanges();
 
     });
+
+    $("#notification-token-toggle").click(function (e) {
+        e.preventDefault();
+        $('#notification-tokens-info').toggle();
+    });
 });
 

changedetectionio/static/js/watch-settings.js

@@ -42,4 +42,8 @@ $(document).ready(function () {
         $('#notification_urls').val('');
         e.preventDefault();
     });
+    $("#notification-token-toggle").click(function (e) {
+        e.preventDefault();
+        $('#notification-tokens-info').toggle();
+    });
 });

changedetectionio/static/styles/scss/parts/_browser-steps.scss

@@ -44,7 +44,7 @@
 #browser-steps .flex-wrapper {
   display: flex;
   flex-flow: row;
-  height: 600px; /*@todo make this dynamic */
+  height: 70vh;
 }
 
 /*  this is duplicate :( */

changedetectionio/static/styles/styles.css

@@ -50,8 +50,7 @@
 #browser-steps .flex-wrapper {
   display: flex;
   flex-flow: row;
-  height: 600px;
+  height: 70vh; }
-  /*@todo make this dynamic */ }
 
 /*  this is duplicate :( */
 #browsersteps-selector-wrapper {

changedetectionio/store.py

@@ -18,6 +18,9 @@ import threading
 import time
 import uuid as uuid_builder
 
+# Because the server will run as a daemon and wont know the URL for notification links when firing off a notification
+BASE_URL_NOT_SET_TEXT = '("Base URL" not set - see settings - notifications)'
+
 dictfilt = lambda x, y: dict([ (i,x[i]) for i in x if i in set(y) ])
 
 # Is there an existing library to ensure some data store (JSON etc) is in sync with CRUD methods?
@@ -175,12 +178,21 @@ class ChangeDetectionStore:
 
     @property
     def data(self):
-        # Re #152, Return env base_url if not overriden, @todo also prefer the proxy pass url
+        # Re #152, Return env base_url if not overriden
-        env_base_url = os.getenv('BASE_URL','')
+        # Re #148 - Some people have just {{ base_url }} in the body or title, but this may break some notification services
-        if not self.__data['settings']['application']['base_url']:
+        #           like 'Join', so it's always best to atleast set something obvious so that they are not broken.
-          self.__data['settings']['application']['base_url'] = env_base_url.strip('" ')
+
-
+        active_base_url = BASE_URL_NOT_SET_TEXT
-        return self.__data
+        if self.__data['settings']['application'].get('base_url'):
+            active_base_url = self.__data['settings']['application'].get('base_url')
+        elif os.getenv('BASE_URL'):
+            active_base_url = os.getenv('BASE_URL')
+
+        # I looked at various ways todo the following, but in the end just copying the dict seemed simplest/most reliable
+        # even given the memory tradeoff - if you know a better way.. maybe return d|self.__data.. or something
+        d = self.__data
+        d['settings']['application']['active_base_url'] = active_base_url.strip('" ')
+        return d
 
     # Delete a single watch by UUID
     def delete(self, uuid):
@@ -327,6 +339,9 @@ class ChangeDetectionStore:
             if k in apply_extras:
                 del apply_extras[k]
 
+        if not apply_extras.get('date_created'):
+            apply_extras['date_created'] = int(time.time())
+
         new_watch.update(apply_extras)
         new_watch.ensure_data_dir_exists()
         self.__data['watching'][new_uuid] = new_watch

changedetectionio/templates/_common_fields.jinja

@@ -13,9 +13,9 @@
                             <div class="pure-form-message-inline">
                               <ul>
                                 <li>Use <a target=_new href="https://github.com/caronc/apprise">AppRise URLs</a> for notification to just about any service! <i><a target=_new href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes">Please read the notification services wiki here for important configuration notes</a></i>.</li>
-                                <li><code>discord://</code> only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
+                                <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_discord">discord://</a></code> (or <code>https://discord.com/api/webhooks...</code>)) </code> only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
-                                <li><code>tgram://</code> bots cant send messages to other bots, so you should specify chat ID of non-bot user.</li>
+                                <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> bots can't 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><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></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>
@@ -35,18 +35,14 @@
                             </div>
                             <div class="pure-control-group">
                                 {{ render_field(form.notification_body , rows=5, class="notification-body", placeholder=settings_application['notification_body']) }}
-                                <span class="pure-form-message-inline">Body for all notifications</span>
+                                <span class="pure-form-message-inline">Body for all notifications &dash; You can use <a target="_new" href="https://jinja.palletsprojects.com/en/3.0.x/templates/">Jinja2</a> templating in the notification title, body and URL, and tokens from below.
-                            </div>
+                                </span>
-                            <div class="pure-control-group">
+
-                            <!-- unsure -->
-                                {{ render_field(form.notification_format , class="notification-format") }}
-                                <span class="pure-form-message-inline">Format for all notifications</span>
                             </div>
                             <div class="pure-controls">
-                            <p class="pure-form-message-inline">
+                                <div id="notification-token-toggle" class="pure-button button-tag button-xsmall">Show token/placeholders</div>
-                                You can use <a target="_new" href="https://jinja.palletsprojects.com/en/3.0.x/templates/">Jinja2</a> templating in the notification title, body and URL.
+                            </div>
-                            </p>
+                            <div class="pure-controls" style="display: none;" id="notification-tokens-info">
-
                                 <table class="pure-table" id="token-table">
                                     <thead>
                                     <tr>
@@ -105,7 +101,7 @@
                                     </tr>
                                     <tr>
                                         <td><code>{{ '{{current_snapshot}}' }}</code></td>
-                                        <td>The current snapshot value, useful when combined with JSON or CSS filters
+                                        <td>The current snapshot text contents value, useful when combined with JSON or CSS filters
                                         </td>
                                     </tr>
                                     <tr>
@@ -115,12 +111,15 @@
                                     </tbody>
                                 </table>
                                 <div class="pure-form-message-inline">
-                                    <br>
+                                    <p>
-                                    URLs generated by changedetection.io (such as <code>{{ '{{diff_url}}' }}</code>) require the <code>BASE_URL</code> environment variable set.<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. <br>
-                                    Your <code>BASE_URL</code> var is currently "{{settings_application['current_base_url']}}"
+                                    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_removed%7D%7D-notification-tokens">More Here</a> <br>
-									<br>
+                                    </p>
-									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_removed%7D%7D-notification-tokens">More Here</a> <br>
+                                </div>
                             </div>
+                            <div class="pure-control-group">
+                                {{ render_field(form.notification_format , class="notification-format") }}
+                                <span class="pure-form-message-inline">Format for all notifications</span>
                             </div>
                         </div>
 {% endmacro %}

changedetectionio/templates/settings.html

@@ -62,14 +62,6 @@
                         <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") }}
-                        <span class="pure-form-message-inline">
-                            Base URL used for the <code>{{ '{{ base_url }}' }}</code> token in notifications and RSS links.<br>Default value is the ENV var 'BASE_URL' (Currently "{{settings_application['current_base_url']}}"),
-                            <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Configurable-BASE_URL-setting">read more here</a>.
-                        </span>
-                    </div>
                     <div class="pure-control-group">
                         {{ render_field(form.application.form.pager_size) }}
                         <span class="pure-form-message-inline">Number of items per page in the watch overview list, 0 to disable.</span>
@@ -100,6 +92,13 @@
                         {{ render_common_settings_form(form.application.form, emailprefix, settings_application) }}
                     </div>
                 </fieldset>
+                <div class="pure-control-group" id="notification-base-url">
+                    {{ render_field(form.application.form.base_url, class="m-d") }}
+                    <span class="pure-form-message-inline">
+                        Base URL used for the <code>{{ '{{ base_url }}' }}</code> token in notification links.<br>
+                        Default value is the system environment variable '<code>BASE_URL</code>' - <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Configurable-BASE_URL-setting">read more here</a>.
+                    </span>
+                </div>
             </div>
 
             <div class="tab-pane-inner" id="fetching">

changedetectionio/templates/watch-overview.html

@@ -119,6 +119,9 @@
                             <a href="{{ url_for('settings_page', uuid=watch.uuid) }}#proxies">Try adding external proxies/locations</a>
                         
                         {% endif %}
+                        {% if 'empty result or contain only an image' in watch.last_error %}
+                            <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Detecting-changes-in-images">more help here</a>.
+                        {% endif %}
                     </div>
                     {% endif %}
                     {% if watch.last_notification_error is defined and watch.last_notification_error != False %}

changedetectionio/tests/test_backup.py

@@ -1,6 +1,6 @@
 #!/usr/bin/python3
 
-from .util import set_original_response, set_modified_response, live_server_setup
+from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
 from flask import url_for
 from urllib.request import urlopen
 from zipfile import ZipFile
@@ -19,12 +19,12 @@ def test_backup(client, live_server):
     # Add our URL to the import page
     res = client.post(
         url_for("import_page"),
-        data={"urls": url_for('test_endpoint', _external=True)},
+        data={"urls": url_for('test_endpoint', _external=True)+"?somechar=őőőőőőőő"},
         follow_redirects=True
     )
 
     assert b"1 Imported" in res.data
-    time.sleep(3)
+    wait_for_all_checks(client)
 
     res = client.get(
         url_for("get_backup"),

changedetectionio/tests/test_css_selector.py

@@ -2,7 +2,7 @@
 
 import time
 from flask import url_for
-from . util import live_server_setup
+from .util import live_server_setup, wait_for_all_checks
 
 from ..html_tools import *
 
@@ -176,3 +176,77 @@ def test_check_multiple_filters(client, live_server):
     assert b"Blob A" in res.data # CSS was ok
     assert b"Blob B" in res.data # xPath was ok
     assert b"Blob C" not in res.data # Should not be included
+
+# The filter exists, but did not contain anything useful
+# Mainly used when the filter contains just an IMG, this can happen when someone selects an image in the visual-selector
+# Tests fetcher can throw a "ReplyWithContentButNoText" exception after applying filter and extracting text
+def test_filter_is_empty_help_suggestion(client, live_server):
+    #live_server_setup(live_server)
+
+    include_filters = "#blob-a"
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write("""<html><body>
+         <div id="blob-a">
+           <img src="something.jpg">
+         </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": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+    wait_for_all_checks(client)
+
+    # Goto the edit page, add our ignore text
+    # Add our URL to the import page
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"include_filters": include_filters,
+              "url": test_url,
+              "tags": "",
+              "headers": "",
+              'fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+
+    wait_for_all_checks(client)
+
+
+    res = client.get(
+        url_for("index"),
+        follow_redirects=True
+    )
+
+    assert b'empty result or contain only an image' in res.data
+
+
+    ### Just an empty selector, no image
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write("""<html><body>
+         <div id="blob-a">
+           <!-- doo doo -->
+         </div>
+         </body>
+         </html>
+        """)
+
+    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    wait_for_all_checks(client)
+
+    res = client.get(
+        url_for("index"),
+        follow_redirects=True
+    )
+
+    assert b'empty result or contain only an image' not in res.data
+    assert b'but contained no usable text' in res.data

changedetectionio/update_worker.py

@@ -3,7 +3,7 @@ import threading
 import queue
 import time
 
-from changedetectionio import content_fetcher
+from changedetectionio import content_fetcher, html_tools
 from .processors.text_json_diff import FilterNotFoundInResponse
 from .processors.restock_diff import UnableToExtractRestockData
 
@@ -251,7 +251,20 @@ class update_worker(threading.Thread):
                         # Totally fine, it's by choice - just continue on, nothing more to care about
                         # Page had elements/content but no renderable text
                         # Backend (not filters) gave zero output
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': "Got HTML content but no text found (With {} reply code).".format(e.status_code)})
+                        extra_help = ""
+                        if e.has_filters:
+                            # Maybe it contains an image? offer a more helpful link
+                            has_img = html_tools.include_filters(include_filters='img',
+                                                                 html_content=e.html_content)
+                            if has_img:
+                                extra_help = ", it's possible that the filters you have give an empty result or contain only an image."
+                            else:
+                                extra_help = ", it's possible that the filters were found, but contained no usable text."
+
+                        self.datastore.update_watch(uuid=uuid, update_obj={
+                            'last_error': f"Got HTML content but no text found (With {e.status_code} reply code){extra_help}"
+                        })
+
                         if e.screenshot:
                             self.datastore.save_screenshot(watch_uuid=uuid, screenshot=e.screenshot)
                         process_changedetection_results = False