'skip_when_checksum_same': should be False so that 'FilterNotFoundInResponse' can be checked

.github/workflows/containers.yml

@@ -95,7 +95,7 @@ jobs:
           push: true
           tags: |
             ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:dev,ghcr.io/${{ github.repository }}:dev
-          platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
+          platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7,linux/arm/v8
           cache-from: type=local,src=/tmp/.buildx-cache
           cache-to: type=local,dest=/tmp/.buildx-cache
 # Looks like this was disabled
@@ -115,7 +115,7 @@ jobs:
             ghcr.io/dgtlmoon/changedetection.io:${{ github.event.release.tag_name }}
             ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:latest
             ghcr.io/dgtlmoon/changedetection.io:latest
-          platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
+          platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7,linux/arm/v8
           cache-from: type=local,src=/tmp/.buildx-cache
           cache-to: type=local,dest=/tmp/.buildx-cache
 # Looks like this was disabled

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

@@ -62,7 +62,7 @@ jobs:
           with:
             context: ./
             file: ./Dockerfile
-            platforms: linux/arm/v7,linux/arm/v6,linux/amd64,linux/arm64,
+            platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7,linux/arm/v8
             cache-from: type=local,src=/tmp/.buildx-cache
             cache-to: type=local,dest=/tmp/.buildx-cache
 

.github/workflows/test-only.yml

@@ -36,6 +36,8 @@ jobs:
         run: |         
           # Build a changedetection.io container and start testing inside
           docker build . -t test-changedetectionio
+          # Debug info
+          docker run test-changedetectionio  bash -c 'pip list'
 
       - name: Spin up ancillary SMTP+Echo message test server
         run: |
@@ -44,7 +46,6 @@ jobs:
 
       - name: Test built container with pytest
         run: |
-          
           # Unit tests
           docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_notification_diff'
           

README-pip.md

@@ -54,5 +54,5 @@ $ changedetection.io -d /path/to/empty/data/dir -p 5000
 
 Then visit http://127.0.0.1:5000 , You should now be able to access the UI.
 
-See https://github.com/dgtlmoon/changedetection.io for more information.
+See https://changedetection.io for more information.
 

README.md

@@ -67,6 +67,7 @@ Requires Playwright to be enabled.
 - Get alerts when new job positions are open on Bamboo HR and other job platforms
 - Website defacement monitoring
 - Pokémon Card Restock Tracker / Pokémon TCG Tracker
+- RegTech - stay ahead of regulatory changes, regulatory compliance
 
 _Need an actual Chrome runner with Javascript support? We support fetching via WebDriver and Playwright!</a>_
 

changedetectionio/__init__.py

@@ -38,7 +38,7 @@ from flask_paginate import Pagination, get_page_parameter
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.44'
+__version__ = '0.44.1'
 
 datastore = None
 
@@ -677,6 +677,7 @@ def changedetection_app(config=None, datastore_o=None):
             datastore.needs_write_urgent = True
 
             # Queue the watch for immediate recheck, with a higher priority
+            # 'False' - fully reprocess the diff so we can see any new filters added
             update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
 
             # Diff page [edit] link should go back to diff page
@@ -1254,6 +1255,9 @@ def changedetection_app(config=None, datastore_o=None):
     @app.route("/api/checknow", methods=['GET'])
     @login_optionally_required
     def form_watch_checknow():
+
+        # 'skip_when_checksum_same': should be False so that 'FilterNotFoundInResponse' can be checked
+
         # Forced recheck will skip the 'skip if content is the same' rule (, 'reprocess_existing_data': True})))
         tag = request.args.get('tag')
         uuid = request.args.get('uuid')
@@ -1430,6 +1434,27 @@ def changedetection_app(config=None, datastore_o=None):
         # paste in etc
         return redirect(url_for('index'))
 
+    @app.route("/highlight_submit_ignore_url", methods=['POST'])
+    def highlight_submit_ignore_url():
+        import re
+        mode = request.form.get('mode')
+        selection = request.form.get('selection')
+
+        uuid = request.args.get('uuid','')
+        if datastore.data["watching"].get(uuid):
+            if mode == 'exact':
+                for l in selection.splitlines():
+                    datastore.data["watching"][uuid]['ignore_text'].append(l.strip())
+            elif mode == 'digit-regex':
+                for l in selection.splitlines():
+                    # Replace any series of numbers with a regex
+                    s = re.escape(l.strip())
+                    s = re.sub(r'[0-9]+', r'\\d+', s)
+                    datastore.data["watching"][uuid]['ignore_text'].append('/' + s + '/')
+
+        return f"<a href={url_for('preview_page', uuid=uuid)}>Click to preview</a>"
+
+
     import changedetectionio.blueprint.browser_steps as browser_steps
     app.register_blueprint(browser_steps.construct_blueprint(datastore), url_prefix='/browser-steps')
 

changedetectionio/api/api_v1.py

@@ -1,3 +1,6 @@
+import os
+from distutils.util import strtobool
+
 from flask_expects_json import expects_json
 from changedetectionio import queuedWatchMetaData
 from flask_restful import abort, Resource
@@ -209,7 +212,9 @@ class CreateWatch(Resource):
         json_data = request.get_json()
         url = json_data['url'].strip()
 
-        if not validators.url(json_data['url'].strip()):
+        # If hosts that only contain alphanumerics are allowed ("localhost" for example)
+        allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
+        if not validators.url(url, simple_host=allow_simplehost):
             return "Invalid or unsupported URL", 400
 
         if json_data.get('proxy'):

changedetectionio/forms.py

@@ -1,5 +1,6 @@
 import os
 import re
+from distutils.util import strtobool
 
 from wtforms import (
     BooleanField,
@@ -257,9 +258,10 @@ class validateURL(object):
 
     def __call__(self, form, field):
         import validators
-
+        # If hosts that only contain alphanumerics are allowed ("localhost" for example)
+        allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
         try:
-            validators.url(field.data.strip())
+            validators.url(field.data.strip(), simple_host=allow_simplehost)
         except validators.ValidationFailure:
             message = field.gettext('\'%s\' is not a valid URL.' % (field.data.strip()))
             raise ValidationError(message)

changedetectionio/processors/text_json_diff.py

@@ -306,8 +306,8 @@ class perform_site_check(difference_detection_processor):
             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')
+                update_obj['previous_md5'] = hashlib.md5(text_content_before_ignored_filter.translate(None, b'\r\n\t ')).hexdigest()
+                return False, update_obj, stripped_text_from_html.encode('utf-8')
             else:
                 stripped_text_from_html = rendered_diff
 

changedetectionio/static/js/diff-overview.js

@@ -1,4 +1,13 @@
 $(document).ready(function () {
+    var csrftoken = $('input[name=csrf_token]').val();
+    $.ajaxSetup({
+        beforeSend: function (xhr, settings) {
+            if (!/^(GET|HEAD|OPTIONS|TRACE)$/i.test(settings.type) && !this.crossDomain) {
+                xhr.setRequestHeader("X-CSRFToken", csrftoken)
+            }
+        }
+    })
+
     // Load it when the #screenshot tab is in use, so we dont give a slow experience when waiting for the text diff to load
     window.addEventListener('hashchange', function (e) {
         toggle(location.hash);
@@ -15,11 +24,71 @@ $(document).ready(function () {
             $("#settings").hide();
         } else if (hash_name === '#extract') {
             $("#settings").hide();
-        }
-
-
-        else {
+        } else {
             $("#settings").show();
         }
     }
+
+    const article = $('.highlightable-filter')[0];
+
+    // We could also add the  'touchend' event for touch devices, but since
+    // most iOS/Android browsers already show a dialog when you select
+    // text (often with a Share option) we'll skip that
+    article.addEventListener('mouseup', dragTextHandler, false);
+    article.addEventListener('mousedown', clean, false);
+
+    function clean(event) {
+      $("#highlightSnippet").remove();
+    }
+
+
+    function dragTextHandler(event) {
+        console.log('mouseupped');
+
+        // Check if any text was selected
+        if (window.getSelection().toString().length > 0) {
+
+            // Find out how much (if any) user has scrolled
+            var scrollTop = (window.pageYOffset !== undefined) ? window.pageYOffset : (document.documentElement || document.body.parentNode || document.body).scrollTop;
+
+            // Get cursor position
+            const posX = event.clientX;
+            const posY = event.clientY + 20 + scrollTop;
+
+            // Append HTML to the body, create the "Tweet Selection" dialog
+            document.body.insertAdjacentHTML('beforeend', '<div id="highlightSnippet" style="position: absolute; top: ' + posY + 'px; left: ' + posX + 'px;"><div class="pure-form-message-inline" style="font-size: 70%">Ignore any change on any line which contains the selected text.</div><br><a data-mode="exact" href="javascript:void(0);" class="pure-button button-secondary button-xsmall">Ignore exact text</a>&nbsp;</div>');
+
+            if (/\d/.test(window.getSelection().toString())) {
+                // Offer regex replacement
+                document.getElementById("highlightSnippet").insertAdjacentHTML('beforeend', '<a data-mode="digit-regex"  href="javascript:void(0);" class="pure-button button-secondary button-xsmall">Ignore text including number changes</a>');
+            }
+
+            $('#highlightSnippet a').bind('click', function (e) {
+                if(!window.getSelection().toString().trim().length) {
+                    alert('Oops no text selected!');
+                    return;
+                }
+
+                $.ajax({
+                    type: "POST",
+                    url: highlight_submit_ignore_url,
+                    data: {'mode': $(this).data('mode'), 'selection': window.getSelection().toString()},
+                    statusCode: {
+                        400: function () {
+                            // More than likely the CSRF token was lost when the server restarted
+                            alert("There was a problem processing the request, please reload the page.");
+                        }
+                    }
+                }).done(function (data) {
+                    $("#highlightSnippet").append(data)
+                }).fail(function (data) {
+                    console.log(data);
+                    alert('There was an error communicating with the server.');
+                });
+            });
+
+        }
+    }
+
+
 });

changedetectionio/static/styles/diff.css

@@ -218,3 +218,10 @@ td#diff-col div {
   text-align: center; }
   .tab-pane-inner#screenshot img {
     max-width: 99%; }
+
+#highlightSnippet {
+  background: var(--color-background);
+  padding: 1em;
+  border-radius: 5px;
+  background: var(--color-background);
+  box-shadow: 1px 1px 4px var(--color-shadow-jump); }

changedetectionio/static/styles/scss/diff.scss

@@ -119,3 +119,11 @@ td#diff-col div {
     max-width: 99%;
   }
 }
+
+#highlightSnippet {
+  background: var(--color-background);
+  padding: 1em;
+  border-radius: 5px;
+  background: var(--color-background);
+  box-shadow: 1px 1px 4px var(--color-shadow-jump);
+}

changedetectionio/templates/base.html

@@ -37,7 +37,7 @@
     <div class="header">
       <div class="home-menu pure-menu pure-menu-horizontal pure-menu-fixed" id="nav-menu">
         {% if has_password and not current_user.is_authenticated %}
-          <a class="pure-menu-heading" href="https://github.com/dgtlmoon/changedetection.io" rel="noopener">
+          <a class="pure-menu-heading" href="https://changedetection.io" rel="noopener">
             <strong>Change</strong>Detection.io</a>
         {% else %}
           <a class="pure-menu-heading" href="{{url_for('index')}}">
@@ -49,7 +49,7 @@
         {% else %}
           {% if new_version_available and not(has_password and not current_user.is_authenticated) %}
             <span id="new-version-text" class="pure-menu-heading">
-              <a href="https://github.com/dgtlmoon/changedetection.io">A new version is available</a>
+              <a href="https://changedetection.io">A new version is available</a>
             </span>
           {% endif %}
         {% endif %}
@@ -77,7 +77,7 @@
             {% endif %}
           {% else %}
             <li class="pure-menu-item">
-              <a class="pure-menu-link" href="https://github.com/dgtlmoon/changedetection.io">Website Change Detection and Notification.</a>
+              <a class="pure-menu-link" href="https://changedetection.io">Website Change Detection and Notification.</a>
             </li>
           {% endif %}
           {% if current_user.is_authenticated %}

changedetectionio/templates/diff.html

@@ -6,6 +6,9 @@
     {% if last_error_screenshot %}
     const error_screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid, error_screenshot=1) }}";
     {% endif %}
+
+    const highlight_submit_ignore_url="{{url_for('highlight_submit_ignore_url', uuid=uuid)}}";
+
 </script>
 <script src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
 
@@ -76,7 +79,7 @@
     </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, highlight text to add to ignore filters</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>
@@ -91,7 +94,7 @@
                  <td id="a" style="display: none;">{{previous}}</td>
                  <td id="b" style="display: none;">{{newest}}</td>
                  <td id="diff-col">
-                     <span id="result"></span>
+                     <span id="result" class="highlightable-filter"></span>
                  </td>
              </tr>
              </tbody>

changedetectionio/templates/preview.html

@@ -6,6 +6,7 @@
     {% if last_error_screenshot %}
     const error_screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid, error_screenshot=1) }}";
     {% endif %}
+    const highlight_submit_ignore_url="{{url_for('highlight_submit_ignore_url', uuid=uuid)}}";
 </script>
 <script src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
 
@@ -20,7 +21,7 @@
         {% endif %}
     </ul>
 </div>
-
+<form><input type="hidden" name="csrf_token" value="{{ csrf_token() }}"></form>
 <div id="diff-ui">
     <div class="tab-pane-inner" id="error-text">
         <div class="snapshot-age error">{{watch.error_text_ctime|format_seconds_ago}} seconds ago</div>
@@ -36,11 +37,12 @@
 
     <div class="tab-pane-inner" id="text">
         <div class="snapshot-age">{{watch.snapshot_text_ctime|format_timestamp_timeago}}</div>
-        <span class="ignored">Grey lines are ignored</span> <span class="triggered">Blue lines are triggers</span>
+        <span class="ignored">Grey lines are ignored</span> <span class="triggered">Blue lines are triggers</span> <span class="tip"><strong>Pro-tip</strong>: Highlight text to add to ignore filters</span>
+
         <table>
             <tbody>
             <tr>
-                <td id="diff-col">
+                <td id="diff-col" class="highlightable-filter">
                     {% for row in content %}
                     <div class="{{row.classes}}">{{row.line}}</div>
                     {% endfor %}

changedetectionio/tests/test_add_replace_remove_filter.py

@@ -29,7 +29,6 @@ def set_original(excluding=None, add_line=None):
         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:
@@ -39,9 +38,8 @@ def test_setup(client, live_server):
     live_server_setup(live_server)
 
 def test_check_removed_line_contains_trigger(client, live_server):
-
+    #live_server_setup(live_server)
     # 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)
@@ -52,9 +50,14 @@ def test_check_removed_line_contains_trigger(client, live_server):
     )
     assert b"1 Imported" in res.data
 
+    from .util import extract_UUID_from_client
+    uuid = extract_UUID_from_client(client)
+
     # Give the thread time to pick it up
     wait_for_all_checks(client)
 
+    #assert live_server.app.config['DATASTORE'].data['watching'][uuid]['previous_md5_before_filters'] == '3f10f9d7e3bc2b04197f525b30ca05af'
+
     # Goto the edit page, add our ignore text
     # Add our URL to the import page
     res = client.post(
@@ -67,12 +70,13 @@ def test_check_removed_line_contains_trigger(client, live_server):
     )
     assert b"Updated watch." in res.data
     wait_for_all_checks(client)
-    set_original(excluding='Something irrelevant')
 
+    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
     wait_for_all_checks(client)
+    assert live_server.app.config['DATASTORE'].data['watching'][uuid]['previous_md5_before_filters'] == '1262fa651e226e126fabe0275e131e82'
     res = client.get(url_for("index"))
     assert b'unviewed' not in res.data
 
@@ -92,10 +96,14 @@ def test_check_removed_line_contains_trigger(client, live_server):
     res = client.get(url_for("index"))
     assert b'unviewed' not in res.data
 
-    # Remove it again, and we should get a trigger
+    # It should now have 'The golden line' back, so we remove it, check again
+    # We should get a trigger
     set_original(excluding='The golden line')
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
+    #assert live_server.app.config['DATASTORE'].data['watching'][uuid]['previous_md5_before_filters'] == '2288c23519a6a90809defb37d79f98f4'
+    res = client.get(url_for("preview_page", uuid="first"))
+    assert b'The golden line' not in res.data
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
 
@@ -107,7 +115,7 @@ def test_check_add_line_contains_trigger(client, live_server):
     #live_server_setup(live_server)
 
     # Give the endpoint time to spin up
-    time.sleep(1)
+    #time.sleep(1)
     test_notification_url = url_for('test_notification_endpoint', _external=True).replace('http://', 'post://') + "?xxx={{ watch_url }}"
 
     res = client.post(

changedetectionio/tests/test_ignorehighlighter.py

@@ -0,0 +1,57 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from .util import live_server_setup, wait_for_all_checks
+from changedetectionio import html_tools
+from . util import  extract_UUID_from_client
+
+def set_original_ignore_response():
+    test_return_data = """<html>
+       <body>
+     Some initial text<br>
+     <p>Which is across multiple lines</p>
+     <br>
+     So let's see what happens.  <br>
+     <p>oh yeah 456</p>
+     </body>
+     </html>
+
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+
+def test_highlight_ignore(client, live_server):
+    live_server_setup(live_server)
+    set_original_ignore_response()
+    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
+    wait_for_all_checks(client)
+    uuid = extract_UUID_from_client(client)
+    # use the highlighter endpoint
+    res = client.post(
+        url_for("highlight_submit_ignore_url", uuid=uuid),
+        data={"mode": 'digit-regex', 'selection': 'oh yeah 123'},
+        follow_redirects=True
+    )
+
+    res = client.get(url_for("edit_page", uuid=uuid))
+
+    # should be a regex now
+    assert b'/oh\ yeah\ \d+/' in res.data
+
+    # Should return a link
+    assert b'href' in res.data
+
+    # And it should register in the preview page
+    res = client.get(url_for("preview_page", uuid=uuid))
+    assert b'<div class="ignored">oh yeah 456' in res.data

changedetectionio/update_worker.py

@@ -427,7 +427,6 @@ class update_worker(threading.Thread):
                         if update_handler.xpath_data:
                             self.datastore.save_xpath_data(watch_uuid=uuid, data=update_handler.xpath_data)
 
-
                 self.current_uuid = None  # Done
                 self.q.task_done()
 

requirements.txt

@@ -10,7 +10,8 @@ flask~=2.0
 inscriptis~=2.2
 pytz
 timeago~=1.0
-validators
+validators~=0.21
+
 
 # Set these versions together to avoid a RequestsDependencyWarning
 # >= 2.26 also adds Brotli support if brotli is installed
@@ -71,3 +72,6 @@ pillow
 # Include pytest, so if theres a support issue we can ask them to run these tests on their setup
 pytest ~=7.2
 pytest-flask ~=1.2
+
+# Pin jsonschema version to prevent build errors on armv6 while rpds-py wheels aren't available (1708)
+jsonschema==4.17.3