Merge branch 'master' into processor-plugin-improvements

Dockerfile

@@ -132,6 +132,15 @@ ENV LOGGER_LEVEL="$LOGGER_LEVEL"
 ENV LC_ALL=en_US.UTF-8
 
 WORKDIR /app
+
+# Copy and set up entrypoint script for installing extra packages
+COPY docker-entrypoint.sh /docker-entrypoint.sh
+RUN chmod +x /docker-entrypoint.sh
+
+# Set entrypoint to handle EXTRA_PACKAGES env var
+ENTRYPOINT ["/docker-entrypoint.sh"]
+
+# Default command (can be overridden in docker-compose.yml)
 CMD ["python", "./changedetection.py", "-d", "/datastore"]
 
 

changedetectionio/__init__.py

@@ -2,7 +2,7 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 # Semver means never use .01, or 00. Should be .1.
-__version__ = '0.52.7'
+__version__ = '0.52.6'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError

changedetectionio/api/Watch.py

@@ -140,58 +140,18 @@ class Watch(Resource):
 
         # Handle processor-config-* fields separately (save to JSON, not datastore)
         from changedetectionio import processors
-        processor_config_data = {}
-        regular_data = {}
 
-        for key, value in request.json.items():
-            if key.startswith('processor_config_'):
-                config_key = key.replace('processor_config_', '')
-                if value:  # Only save non-empty values
-                    processor_config_data[config_key] = value
-            else:
-                regular_data[key] = value
+        # Make a mutable copy of request.json for modification
+        json_data = dict(request.json)
+
+        # Extract and remove processor config fields from json_data
+        processor_config_data = processors.extract_processor_config_from_form_data(json_data)
 
         # Update watch with regular (non-processor-config) fields
-        watch.update(regular_data)
+        watch.update(json_data)
 
-        # Save processor config to JSON file if any config data exists
-        if processor_config_data:
-            try:
-                processor_name = request.json.get('processor', watch.get('processor'))
-                if processor_name:
-                    # Create a processor instance to access config methods
-                    from changedetectionio.processors import difference_detection_processor
-                    processor_instance = difference_detection_processor(self.datastore, uuid)
-                    # Use processor name as filename so each processor keeps its own config
-                    config_filename = f'{processor_name}.json'
-                    processor_instance.update_extra_watch_config(config_filename, processor_config_data)
-                    logger.debug(f"API: Saved processor config to {config_filename}: {processor_config_data}")
-
-                    # Call optional edit_hook if processor has one
-                    try:
-                        import importlib
-                        edit_hook_module_name = f'changedetectionio.processors.{processor_name}.edit_hook'
-
-                        try:
-                            edit_hook = importlib.import_module(edit_hook_module_name)
-                            logger.debug(f"API: Found edit_hook module for {processor_name}")
-
-                            if hasattr(edit_hook, 'on_config_save'):
-                                logger.info(f"API: Calling edit_hook.on_config_save for {processor_name}")
-                                # Call hook and get updated config
-                                updated_config = edit_hook.on_config_save(watch, processor_config_data, self.datastore)
-                                # Save updated config back to file
-                                processor_instance.update_extra_watch_config(config_filename, updated_config)
-                                logger.info(f"API: Edit hook updated config: {updated_config}")
-                            else:
-                                logger.debug(f"API: Edit hook module found but no on_config_save function")
-                        except ModuleNotFoundError:
-                            logger.debug(f"API: No edit_hook module for processor {processor_name} (this is normal)")
-                    except Exception as hook_error:
-                        logger.error(f"API: Edit hook error (non-fatal): {hook_error}", exc_info=True)
-
-            except Exception as e:
-                logger.error(f"API: Failed to save processor config: {e}")
+        # Save processor config to JSON file
+        processors.save_processor_config(self.datastore, uuid, processor_config_data)
 
         return "OK", 200
 

changedetectionio/async_update_worker.py

@@ -117,11 +117,14 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
                     processor = watch.get('processor', 'text_json_diff')
 
                     # Init a new 'difference_detection_processor'
-                    try:
-                        processor_module = importlib.import_module(f"changedetectionio.processors.{processor}.processor")
-                    except ModuleNotFoundError as e:
-                        print(f"Processor module '{processor}' not found.")
-                        raise e
+                    # Use get_processor_module() to support both built-in and plugin processors
+                    from changedetectionio.processors import get_processor_module
+                    processor_module = get_processor_module(processor)
+
+                    if not processor_module:
+                        error_msg = f"Processor module '{processor}' not found."
+                        logger.error(error_msg)
+                        raise ModuleNotFoundError(error_msg)
 
                     update_handler = processor_module.perform_site_check(datastore=datastore,
                                                                          watch_uuid=uuid)

changedetectionio/blueprint/ui/diff.py

@@ -101,23 +101,21 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         # Get the processor type for this watch
         processor_name = watch.get('processor', 'text_json_diff')
 
-        try:
-            # Try to import the processor's difference module
-            processor_module = importlib.import_module(f'changedetectionio.processors.{processor_name}.difference')
+        # Try to get the processor's difference module (works for both built-in and plugin processors)
+        from changedetectionio.processors import get_processor_submodule
+        processor_module = get_processor_submodule(processor_name, 'difference')
 
-            # Call the processor's render() function
-            if hasattr(processor_module, 'render'):
-                return processor_module.render(
-                    watch=watch,
-                    datastore=datastore,
-                    request=request,
-                    url_for=url_for,
-                    render_template=render_template,
-                    flash=flash,
-                    redirect=redirect
-                )
-        except (ImportError, ModuleNotFoundError) as e:
-            logger.warning(f"Processor {processor_name} does not have a difference module, falling back to text_json_diff: {e}")
+        # Call the processor's render() function
+        if processor_module and hasattr(processor_module, 'render'):
+            return processor_module.render(
+                watch=watch,
+                datastore=datastore,
+                request=request,
+                url_for=url_for,
+                render_template=render_template,
+                flash=flash,
+                redirect=redirect
+            )
 
         # Fallback: if processor doesn't have difference module, use text_json_diff as default
         from changedetectionio.processors.text_json_diff.difference import render as default_render
@@ -157,23 +155,21 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         # Get the processor type for this watch
         processor_name = watch.get('processor', 'text_json_diff')
 
-        try:
-            # Try to import the processor's extract module
-            processor_module = importlib.import_module(f'changedetectionio.processors.{processor_name}.extract')
+        # Try to get the processor's extract module (works for both built-in and plugin processors)
+        from changedetectionio.processors import get_processor_submodule
+        processor_module = get_processor_submodule(processor_name, 'extract')
 
-            # Call the processor's render_form() function
-            if hasattr(processor_module, 'render_form'):
-                return processor_module.render_form(
-                    watch=watch,
-                    datastore=datastore,
-                    request=request,
-                    url_for=url_for,
-                    render_template=render_template,
-                    flash=flash,
-                    redirect=redirect
-                )
-        except (ImportError, ModuleNotFoundError) as e:
-            logger.warning(f"Processor {processor_name} does not have an extract module, falling back to base extractor: {e}")
+        # Call the processor's render_form() function
+        if processor_module and hasattr(processor_module, 'render_form'):
+            return processor_module.render_form(
+                watch=watch,
+                datastore=datastore,
+                request=request,
+                url_for=url_for,
+                render_template=render_template,
+                flash=flash,
+                redirect=redirect
+            )
 
         # Fallback: if processor doesn't have extract module, use base processors.extract as default
         from changedetectionio.processors.extract import render_form as default_render_form
@@ -213,24 +209,22 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         # Get the processor type for this watch
         processor_name = watch.get('processor', 'text_json_diff')
 
-        try:
-            # Try to import the processor's extract module
-            processor_module = importlib.import_module(f'changedetectionio.processors.{processor_name}.extract')
+        # Try to get the processor's extract module (works for both built-in and plugin processors)
+        from changedetectionio.processors import get_processor_submodule
+        processor_module = get_processor_submodule(processor_name, 'extract')
 
-            # Call the processor's process_extraction() function
-            if hasattr(processor_module, 'process_extraction'):
-                return processor_module.process_extraction(
-                    watch=watch,
-                    datastore=datastore,
-                    request=request,
-                    url_for=url_for,
-                    make_response=make_response,
-                    send_from_directory=send_from_directory,
-                    flash=flash,
-                    redirect=redirect
-                )
-        except (ImportError, ModuleNotFoundError) as e:
-            logger.warning(f"Processor {processor_name} does not have an extract module, falling back to base extractor: {e}")
+        # Call the processor's process_extraction() function
+        if processor_module and hasattr(processor_module, 'process_extraction'):
+            return processor_module.process_extraction(
+                watch=watch,
+                datastore=datastore,
+                request=request,
+                url_for=url_for,
+                make_response=make_response,
+                send_from_directory=send_from_directory,
+                flash=flash,
+                redirect=redirect
+            )
 
         # Fallback: if processor doesn't have extract module, use base processors.extract as default
         from changedetectionio.processors.extract import process_extraction as default_process_extraction
@@ -280,38 +274,33 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         # Get the processor type for this watch
         processor_name = watch.get('processor', 'text_json_diff')
 
-        try:
-            # Try to import the processor's difference module
-            processor_module = importlib.import_module(f'changedetectionio.processors.{processor_name}.difference')
+        # Try to get the processor's difference module (works for both built-in and plugin processors)
+        from changedetectionio.processors import get_processor_submodule
+        processor_module = get_processor_submodule(processor_name, 'difference')
 
-            # Call the processor's get_asset() function
-            if hasattr(processor_module, 'get_asset'):
-                result = processor_module.get_asset(
-                    asset_name=asset_name,
-                    watch=watch,
-                    datastore=datastore,
-                    request=request
-                )
+        # Call the processor's get_asset() function
+        if processor_module and hasattr(processor_module, 'get_asset'):
+            result = processor_module.get_asset(
+                asset_name=asset_name,
+                watch=watch,
+                datastore=datastore,
+                request=request
+            )
 
-                if result is None:
-                    from flask import abort
-                    abort(404, description=f"Asset '{asset_name}' not found")
-
-                binary_data, content_type, cache_control = result
-
-                response = make_response(binary_data)
-                response.headers['Content-Type'] = content_type
-                if cache_control:
-                    response.headers['Cache-Control'] = cache_control
-                return response
-            else:
-                logger.warning(f"Processor {processor_name} does not implement get_asset()")
+            if result is None:
                 from flask import abort
-                abort(404, description=f"Processor '{processor_name}' does not support assets")
+                abort(404, description=f"Asset '{asset_name}' not found")
 
-        except (ImportError, ModuleNotFoundError) as e:
-            logger.warning(f"Processor {processor_name} does not have a difference module: {e}")
+            binary_data, content_type, cache_control = result
+
+            response = make_response(binary_data)
+            response.headers['Content-Type'] = content_type
+            if cache_control:
+                response.headers['Cache-Control'] = cache_control
+            return response
+        else:
+            logger.warning(f"Processor {processor_name} does not implement get_asset()")
             from flask import abort
-            abort(404, description=f"Processor '{processor_name}' not found")
+            abort(404, description=f"Processor '{processor_name}' does not support assets")
 
     return diff_blueprint

changedetectionio/blueprint/ui/edit.py

@@ -72,8 +72,13 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
         processor_name = datastore.data['watching'][uuid].get('processor', '')
         processor_classes = next((tpl for tpl in processors.find_processors() if tpl[1] == processor_name), None)
         if not processor_classes:
-            flash(gettext("Cannot load the edit form for processor/plugin '{}', plugin missing?").format(processor_classes[1]), 'error')
-            return redirect(url_for('watchlist.index'))
+            flash(gettext("Could not load '{}' processor, processor plugin might be missing. Please select a different processor.").format(processor_name), 'error')
+            # Fall back to default processor so user can still edit and change processor
+            processor_classes = next((tpl for tpl in processors.find_processors() if tpl[1] == 'text_json_diff'), None)
+            if not processor_classes:
+                # If even text_json_diff is missing, something is very wrong
+                flash(gettext("Could not load '{}' processor, processor plugin might be missing.").format(processor_name), 'error')
+                return redirect(url_for('watchlist.index'))
 
         parent_module = processors.get_parent_module(processor_classes[0])
 
@@ -150,58 +155,10 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
 
             extra_update_obj['time_between_check'] = form.time_between_check.data
 
-             # Handle processor-config-* fields separately (save to JSON, not datastore)
-            processor_config_data = {}
-            fields_to_remove = []
-            for field_name, field_value in form.data.items():
-                if field_name.startswith('processor_config_'):
-                    config_key = field_name.replace('processor_config_', '')
-                    if field_value:  # Only save non-empty values
-                        processor_config_data[config_key] = field_value
-                    fields_to_remove.append(field_name)
-
-            # Save processor config to JSON file if any config data exists
-            if processor_config_data:
-                try:
-                    processor_name = form.data.get('processor')
-                    # Create a processor instance to access config methods
-                    processor_instance = processors.difference_detection_processor(datastore, uuid)
-                    # Use processor name as filename so each processor keeps its own config
-                    config_filename = f'{processor_name}.json'
-                    processor_instance.update_extra_watch_config(config_filename, processor_config_data)
-                    logger.debug(f"Saved processor config to {config_filename}: {processor_config_data}")
-
-                    # Call optional edit_hook if processor has one
-                    try:
-                        # Try to import the edit_hook module from the processor package
-                        import importlib
-                        edit_hook_module_name = f'changedetectionio.processors.{processor_name}.edit_hook'
-
-                        try:
-                            edit_hook = importlib.import_module(edit_hook_module_name)
-                            logger.debug(f"Found edit_hook module for {processor_name}")
-
-                            if hasattr(edit_hook, 'on_config_save'):
-                                logger.info(f"Calling edit_hook.on_config_save for {processor_name}")
-                                watch_obj = datastore.data['watching'][uuid]
-                                # Call hook and get updated config
-                                updated_config = edit_hook.on_config_save(watch_obj, processor_config_data, datastore)
-                                # Save updated config back to file
-                                processor_instance.update_extra_watch_config(config_filename, updated_config)
-                                logger.info(f"Edit hook updated config: {updated_config}")
-                            else:
-                                logger.debug(f"Edit hook module found but no on_config_save function")
-                        except ModuleNotFoundError:
-                            logger.debug(f"No edit_hook module for processor {processor_name} (this is normal)")
-                    except Exception as hook_error:
-                        logger.error(f"Edit hook error (non-fatal): {hook_error}", exc_info=True)
-
-                except Exception as e:
-                    logger.error(f"Failed to save processor config: {e}")
-
-            # Remove processor-config-* fields from form.data before updating datastore
-            for field_name in fields_to_remove:
-                form.data.pop(field_name, None)
+            # Handle processor-config-* fields separately (save to JSON, not datastore)
+            # IMPORTANT: These must NOT be saved to url-watches.json, only to the processor-specific JSON file
+            processor_config_data = processors.extract_processor_config_from_form_data(form.data)
+            processors.save_processor_config(datastore, uuid, processor_config_data)
 
             # Ignore text
             form_ignore_text = form.ignore_text.data

changedetectionio/blueprint/ui/preview.py

@@ -39,24 +39,21 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         # Get the processor type for this watch
         processor_name = watch.get('processor', 'text_json_diff')
 
-        try:
-            # Try to import the processor's preview module
-            import importlib
-            processor_module = importlib.import_module(f'changedetectionio.processors.{processor_name}.preview')
+        # Try to get the processor's preview module (works for both built-in and plugin processors)
+        from changedetectionio.processors import get_processor_submodule
+        processor_module = get_processor_submodule(processor_name, 'preview')
 
-            # Call the processor's render() function
-            if hasattr(processor_module, 'render'):
-                return processor_module.render(
-                    watch=watch,
-                    datastore=datastore,
-                    request=request,
-                    url_for=url_for,
-                    render_template=render_template,
-                    flash=flash,
-                    redirect=redirect
-                )
-        except (ImportError, ModuleNotFoundError) as e:
-            logger.debug(f"Processor {processor_name} does not have a preview module, using default preview: {e}")
+        # Call the processor's render() function
+        if processor_module and hasattr(processor_module, 'render'):
+            return processor_module.render(
+                watch=watch,
+                datastore=datastore,
+                request=request,
+                url_for=url_for,
+                render_template=render_template,
+                flash=flash,
+                redirect=redirect
+            )
 
         # Fallback: if processor doesn't have preview module, use default text preview
         content = []
@@ -163,39 +160,33 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         # Get the processor type for this watch
         processor_name = watch.get('processor', 'text_json_diff')
 
-        try:
-            # Try to import the processor's preview module
-            import importlib
-            processor_module = importlib.import_module(f'changedetectionio.processors.{processor_name}.preview')
+        # Try to get the processor's preview module (works for both built-in and plugin processors)
+        from changedetectionio.processors import get_processor_submodule
+        processor_module = get_processor_submodule(processor_name, 'preview')
 
-            # Call the processor's get_asset() function
-            if hasattr(processor_module, 'get_asset'):
-                result = processor_module.get_asset(
-                    asset_name=asset_name,
-                    watch=watch,
-                    datastore=datastore,
-                    request=request
-                )
+        # Call the processor's get_asset() function
+        if processor_module and hasattr(processor_module, 'get_asset'):
+            result = processor_module.get_asset(
+                asset_name=asset_name,
+                watch=watch,
+                datastore=datastore,
+                request=request
+            )
 
-                if result is None:
-                    from flask import abort
-                    abort(404, description=f"Asset '{asset_name}' not found")
-
-                binary_data, content_type, cache_control = result
-
-                response = make_response(binary_data)
-                response.headers['Content-Type'] = content_type
-                if cache_control:
-                    response.headers['Cache-Control'] = cache_control
-                return response
-            else:
-                logger.warning(f"Processor {processor_name} does not implement get_asset()")
+            if result is None:
                 from flask import abort
-                abort(404, description=f"Processor '{processor_name}' does not support assets")
+                abort(404, description=f"Asset '{asset_name}' not found")
 
-        except (ImportError, ModuleNotFoundError) as e:
-            logger.warning(f"Processor {processor_name} does not have a preview module: {e}")
+            binary_data, content_type, cache_control = result
+
+            response = make_response(binary_data)
+            response.headers['Content-Type'] = content_type
+            if cache_control:
+                response.headers['Cache-Control'] = cache_control
+            return response
+        else:
+            logger.warning(f"Processor {processor_name} does not implement get_asset()")
             from flask import abort
-            abort(404, description=f"Processor '{processor_name}' not found")
+            abort(404, description=f"Processor '{processor_name}' does not support assets")
 
     return preview_blueprint

changedetectionio/blueprint/watchlist/templates/watch-overview.html

@@ -205,23 +205,24 @@ html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
                         </div>
                     {%  endif %}
                         <div>
-                        <span class="watch-title">
-                            {% if system_use_url_watchlist or watch.get('use_page_title_in_list') %}
-                                {{ watch.label }}
-                            {% else %}
-                                {{ watch.get('title') or watch.link }}
-                            {% endif %}
-                           <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}">&nbsp;</a>
-                        </span>
+                            {%- if watch['processor'] and watch['processor'] in processor_badge_texts -%}
+                                <span class="processor-badge processor-badge-{{ watch['processor'] }}" title="{{ processor_descriptions.get(watch['processor'], watch['processor']) }}">{{ processor_badge_texts[watch['processor']] }}</span>
+                            {%- endif -%}
+                            <span class="watch-title">
+                                {% if system_use_url_watchlist or watch.get('use_page_title_in_list') %}
+                                    {{ watch.label }}
+                                {% else %}
+                                    {{ watch.get('title') or watch.link }}
+                                {% endif %}
+                               <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}">&nbsp;</a>
+                            </span>
                             <div class="error-text" style="display:none;">{{ watch.compile_error_texts(has_proxies=datastore.proxy_list)|safe }}</div>
                             {%- if watch['processor'] == 'text_json_diff'  -%}
                                 {%- if watch['has_ldjson_price_data'] and not watch['track_ldjson_price_data']  -%}
                                 <div class="ldjson-price-track-offer">Switch to Restock & Price watch mode? <a href="{{url_for('price_data_follower.accept', uuid=watch.uuid)}}" class="pure-button button-xsmall">Yes</a> <a href="{{url_for('price_data_follower.reject', uuid=watch.uuid)}}" class="">No</a></div>
                                 {%- endif -%}
                             {%- endif -%}
-                            {%- if watch['processor'] and watch['processor'] in processor_badge_texts -%}
-                                <span class="processor-badge processor-badge-{{ watch['processor'] }}" title="{{ processor_descriptions.get(watch['processor'], watch['processor']) }}">{{ processor_badge_texts[watch['processor']] }}</span>
-                            {%- endif -%}
+
                             {%- for watch_tag_uuid, watch_tag in datastore.get_all_tags_for_watch(watch['uuid']).items() -%}
                               <span class="watch-tag-list tag-{{ watch_tag.title|sanitize_tag_class }}">{{ watch_tag.title }}</span>
                             {%- endfor -%}

changedetectionio/flask_app.py

@@ -400,27 +400,11 @@ def changedetection_app(config=None, datastore_o=None):
     language_codes = get_language_codes()
 
     def get_locale():
-        # Locale aliases: map browser language codes to translation directory names
-        # This handles cases where browsers send standard codes (e.g., zh-TW)
-        # but our translations use more specific codes (e.g., zh_Hant_TW)
-        locale_aliases = {
-            'zh-TW': 'zh_Hant_TW',  # Traditional Chinese: browser sends zh-TW, we use zh_Hant_TW
-            'zh_TW': 'zh_Hant_TW',  # Also handle underscore variant
-        }
-
         # 1. Try to get locale from session (user explicitly selected)
         if 'locale' in session:
             return session['locale']
-
         # 2. Fall back to Accept-Language header
-        # Get the best match from browser's Accept-Language header
-        browser_locale = request.accept_languages.best_match(language_codes + list(locale_aliases.keys()))
-
-        # 3. Check if we need to map the browser locale to our internal locale
-        if browser_locale in locale_aliases:
-            return locale_aliases[browser_locale]
-
-        return browser_locale
+        return request.accept_languages.best_match(language_codes)
 
     # Initialize Babel with locale selector
     babel = Babel(app, locale_selector=get_locale)

changedetectionio/pluggy_interface.py

@@ -105,6 +105,30 @@ class ChangeDetectionSpec:
         """
         pass
 
+    @hookspec
+    def register_processor(self):
+        """Register an external processor plugin.
+
+        External packages can implement this hook to register custom processors
+        that will be discovered alongside built-in processors.
+
+        Returns:
+            dict or None: Dictionary with processor information:
+                {
+                    'processor_name': str,      # Machine name (e.g., 'osint_recon')
+                    'processor_module': module, # Module containing processor.py
+                    'processor_class': class,   # The perform_site_check class
+                    'metadata': {               # Optional metadata
+                        'name': str,            # Display name
+                        'description': str,     # Description
+                        'processor_weight': int,# Sort weight (lower = higher priority)
+                        'list_badge_text': str, # Badge text for UI
+                    }
+                }
+                Return None if this plugin doesn't provide a processor
+        """
+        pass
+
 
 # Set up Plugin Manager
 plugin_manager = pluggy.PluginManager(PLUGIN_NAMESPACE)

changedetectionio/processors/__init__.py

@@ -17,9 +17,11 @@ def find_sub_packages(package_name):
     return [name for _, name, is_pkg in pkgutil.iter_modules(package.__path__) if is_pkg]
 
 
+@lru_cache(maxsize=1)
 def find_processors():
     """
     Find all subclasses of DifferenceDetectionProcessor in the specified package.
+    Results are cached to avoid repeated discovery.
 
     :param package_name: The name of the package to scan for processor modules.
     :return: A list of (module, class) tuples.
@@ -46,6 +48,22 @@ def find_processors():
         except (ModuleNotFoundError, ImportError) as e:
             logger.warning(f"Failed to import module {module_name}: {e} (find_processors())")
 
+    # Discover plugin processors via pluggy
+    try:
+        from changedetectionio.pluggy_interface import plugin_manager
+        plugin_results = plugin_manager.hook.register_processor()
+
+        for result in plugin_results:
+            if result and isinstance(result, dict):
+                processor_module = result.get('processor_module')
+                processor_name = result.get('processor_name')
+
+                if processor_module and processor_name:
+                    processors.append((processor_module, processor_name))
+                    logger.info(f"Registered plugin processor: {processor_name}")
+    except Exception as e:
+        logger.warning(f"Error loading plugin processors: {e}")
+
     return processors
 
 
@@ -97,54 +115,137 @@ def find_processor_module(processor_name):
     return None
 
 
+def get_processor_module(processor_name):
+    """
+    Get the actual processor module (with perform_site_check class) by name.
+    Works for both built-in and plugin processors.
+
+    Args:
+        processor_name: Processor machine name (e.g., 'text_json_diff', 'osint_recon')
+
+    Returns:
+        module: The processor module containing perform_site_check, or None if not found
+    """
+    processor_classes = find_processors()
+    processor_tuple = next((tpl for tpl in processor_classes if tpl[1] == processor_name), None)
+
+    if processor_tuple:
+        # Return the actual processor module (first element of tuple)
+        return processor_tuple[0]
+
+    return None
+
+
+def get_processor_submodule(processor_name, submodule_name):
+    """
+    Get an optional submodule from a processor (e.g., 'difference', 'extract', 'preview').
+    Works for both built-in and plugin processors.
+
+    Args:
+        processor_name: Processor machine name (e.g., 'text_json_diff', 'osint_recon')
+        submodule_name: Name of the submodule (e.g., 'difference', 'extract', 'preview')
+
+    Returns:
+        module: The submodule if it exists, or None if not found
+    """
+    processor_classes = find_processors()
+    processor_tuple = next((tpl for tpl in processor_classes if tpl[1] == processor_name), None)
+
+    if not processor_tuple:
+        return None
+
+    processor_module = processor_tuple[0]
+    parent_module = get_parent_module(processor_module)
+
+    if not parent_module:
+        return None
+
+    # Try to import the submodule
+    try:
+        # For built-in processors: changedetectionio.processors.text_json_diff.difference
+        # For plugin processors: changedetectionio_osint.difference
+        parent_module_name = parent_module.__name__
+        submodule_full_name = f"{parent_module_name}.{submodule_name}"
+        return importlib.import_module(submodule_full_name)
+    except (ModuleNotFoundError, ImportError):
+        return None
+
+
+@lru_cache(maxsize=1)
+def get_plugin_processor_metadata():
+    """Get metadata from plugin processors."""
+    metadata = {}
+    try:
+        from changedetectionio.pluggy_interface import plugin_manager
+        plugin_results = plugin_manager.hook.register_processor()
+
+        for result in plugin_results:
+            if result and isinstance(result, dict):
+                processor_name = result.get('processor_name')
+                meta = result.get('metadata', {})
+                if processor_name:
+                    metadata[processor_name] = meta
+    except Exception as e:
+        logger.warning(f"Error getting plugin processor metadata: {e}")
+    return metadata
+
+
 def available_processors():
     """
     Get a list of processors by name and description for the UI elements.
-    Can be filtered via ALLOWED_PROCESSORS environment variable (comma-separated list).
+    Can be filtered via DISABLED_PROCESSORS environment variable (comma-separated list).
     :return: A list :)
     """
 
     processor_classes = find_processors()
 
-    # Check if ALLOWED_PROCESSORS env var is set
-    # For now we disable it, need to make a deploy with lots of new code and this will be an overload
-    allowed_processors_env = os.getenv('ALLOWED_PROCESSORS', 'text_json_diff, restock_diff').strip()
-    allowed_processors = None
-    if allowed_processors_env:
+    # Check if DISABLED_PROCESSORS env var is set
+    disabled_processors_env = os.getenv('DISABLED_PROCESSORS', 'image_ssim_diff').strip()
+    disabled_processors = []
+    if disabled_processors_env:
         # Parse comma-separated list and strip whitespace
-        allowed_processors = [p.strip() for p in allowed_processors_env.split(',') if p.strip()]
-        logger.info(f"ALLOWED_PROCESSORS set, filtering to: {allowed_processors}")
+        disabled_processors = [p.strip() for p in disabled_processors_env.split(',') if p.strip()]
+        logger.info(f"DISABLED_PROCESSORS set, disabling: {disabled_processors}")
 
     available = []
+    plugin_metadata = get_plugin_processor_metadata()
+
     for module, sub_package_name in processor_classes:
-        # Filter by allowed processors if set
-        if allowed_processors and sub_package_name not in allowed_processors:
-            logger.debug(f"Skipping processor '{sub_package_name}' (not in ALLOWED_PROCESSORS)")
+        # Skip disabled processors
+        if sub_package_name in disabled_processors:
+            logger.debug(f"Skipping processor '{sub_package_name}' (in DISABLED_PROCESSORS)")
             continue
 
-        # Try to get the 'name' attribute from the processor module first
-        if hasattr(module, 'name'):
-            description = gettext(module.name)
+        # Check if this is a plugin processor
+        if sub_package_name in plugin_metadata:
+            meta = plugin_metadata[sub_package_name]
+            description = gettext(meta.get('name', sub_package_name))
+            # Plugin processors start from weight 10 to separate them from built-in processors
+            weight = 100 + meta.get('processor_weight', 0)
         else:
-            # Fall back to processor_description from parent module's __init__.py
-            parent_module = get_parent_module(module)
-            if parent_module and hasattr(parent_module, 'processor_description'):
-                description = gettext(parent_module.processor_description)
+            # Try to get the 'name' attribute from the processor module first
+            if hasattr(module, 'name'):
+                description = gettext(module.name)
             else:
-                # Final fallback to a readable name
-                description = sub_package_name.replace('_', ' ').title()
+                # Fall back to processor_description from parent module's __init__.py
+                parent_module = get_parent_module(module)
+                if parent_module and hasattr(parent_module, 'processor_description'):
+                    description = gettext(parent_module.processor_description)
+                else:
+                    # Final fallback to a readable name
+                    description = sub_package_name.replace('_', ' ').title()
 
-        # Get weight for sorting (lower weight = higher in list)
-        weight = 0  # Default weight for processors without explicit weight
+            # Get weight for sorting (lower weight = higher in list)
+            weight = 0  # Default weight for processors without explicit weight
 
-        # Check processor module itself first
-        if hasattr(module, 'processor_weight'):
-            weight = module.processor_weight
-        else:
-            # Fall back to parent module (package __init__.py)
-            parent_module = get_parent_module(module)
-            if parent_module and hasattr(parent_module, 'processor_weight'):
-                weight = parent_module.processor_weight
+            # Check processor module itself first
+            if hasattr(module, 'processor_weight'):
+                weight = module.processor_weight
+            else:
+                # Fall back to parent module (package __init__.py)
+                parent_module = get_parent_module(module)
+                if parent_module and hasattr(parent_module, 'processor_weight'):
+                    weight = parent_module.processor_weight
 
         available.append((sub_package_name, description, weight))
 
@@ -279,3 +380,76 @@ def get_processor_badge_css():
 
     return '\n\n'.join(css_rules)
 
+
+def save_processor_config(datastore, watch_uuid, config_data):
+    """
+    Save processor-specific configuration to JSON file.
+
+    This is a shared helper function used by both the UI edit form and API endpoints
+    to consistently handle processor configuration storage.
+
+    Args:
+        datastore: The application datastore instance
+        watch_uuid: UUID of the watch
+        config_data: Dictionary of configuration data to save (with processor_config_* prefix removed)
+
+    Returns:
+        bool: True if saved successfully, False otherwise
+    """
+    if not config_data:
+        return True
+
+    try:
+        from changedetectionio.processors.base import difference_detection_processor
+
+        # Get processor name from watch
+        watch = datastore.data['watching'].get(watch_uuid)
+        if not watch:
+            logger.error(f"Cannot save processor config: watch {watch_uuid} not found")
+            return False
+
+        processor_name = watch.get('processor', 'text_json_diff')
+
+        # Create a processor instance to access config methods
+        processor_instance = difference_detection_processor(datastore, watch_uuid)
+
+        # Use processor name as filename so each processor keeps its own config
+        config_filename = f'{processor_name}.json'
+        processor_instance.update_extra_watch_config(config_filename, config_data)
+
+        logger.debug(f"Saved processor config to {config_filename}: {config_data}")
+        return True
+
+    except Exception as e:
+        logger.error(f"Failed to save processor config: {e}")
+        return False
+
+
+def extract_processor_config_from_form_data(form_data):
+    """
+    Extract processor_config_* fields from form data and return separate dicts.
+
+    This is a shared helper function used by both the UI edit form and API endpoints
+    to consistently handle processor configuration extraction.
+
+    IMPORTANT: This function modifies form_data in-place by removing processor_config_* fields.
+
+    Args:
+        form_data: Dictionary of form data (will be modified in-place)
+
+    Returns:
+        dict: Dictionary of processor config data (with processor_config_* prefix removed)
+    """
+    processor_config_data = {}
+
+    # Use list() to create a copy of keys since we're modifying the dict
+    for field_name in list(form_data.keys()):
+        if field_name.startswith('processor_config_'):
+            config_key = field_name.replace('processor_config_', '')
+            # Save all values (including empty strings) to allow explicit clearing of settings
+            processor_config_data[config_key] = form_data[field_name]
+            # Remove from form_data to prevent it from reaching datastore
+            del form_data[field_name]
+
+    return processor_config_data
+

changedetectionio/tests/test_i18n.py

@@ -325,274 +325,3 @@ def test_time_unit_translations(client, live_server, measure_memory_usage, datas
     assert b"Time Between Check" not in res.data, "Should not have English 'Time Between Check'"
     assert "Chrome 請求".encode() not in res.data, "Should not have incorrect 'Chrome 請求' (Chrome requests)"
     assert "使用預設通知".encode() not in res.data, "Should not have incorrect '使用預設通知' (Use default notification)"
-
-
-def test_accept_language_header_zh_tw(client, live_server, measure_memory_usage, datastore_path):
-    """
-    Test that browsers sending zh-TW in Accept-Language header get Traditional Chinese.
-    This tests the locale alias mapping for issue #3779.
-    """
-    from flask import url_for
-
-    # Clear any session data to simulate a fresh visitor
-    with client.session_transaction() as sess:
-        sess.clear()
-
-    # Request the index page with zh-TW in Accept-Language header (what browsers send)
-    res = client.get(
-        url_for("watchlist.index"),
-        headers={'Accept-Language': 'zh-TW,zh;q=0.9,en;q=0.8'},
-        follow_redirects=True
-    )
-
-    assert res.status_code == 200
-
-    # Should get Traditional Chinese content, not Simplified Chinese
-    # Traditional: 選擇語言, Simplified: 选择语言
-    assert '選擇語言'.encode() in res.data, "Expected Traditional Chinese '選擇語言' (Select Language)"
-    assert '选择语言'.encode() not in res.data, "Should not get Simplified Chinese '选择语言'"
-
-    # Check HTML lang attribute uses BCP 47 format
-    assert b'<html lang="zh-Hant-TW"' in res.data, "Expected BCP 47 language tag zh-Hant-TW in HTML"
-
-    # Check that the correct flag icon is shown (Taiwan flag for Traditional Chinese)
-    assert b'<span class="fi fi-tw fis" id="language-selector-flag">' in res.data, \
-        "Expected Taiwan flag 'fi fi-tw' for Traditional Chinese"
-    assert b'<span class="fi fi-cn fis" id="language-selector-flag">' not in res.data, \
-        "Should not show China flag 'fi fi-cn' for Traditional Chinese"
-
-    # Verify we're getting Traditional Chinese text throughout the page
-    res = client.get(
-        url_for("settings.settings_page"),
-        headers={'Accept-Language': 'zh-TW,zh;q=0.9,en;q=0.8'},
-        follow_redirects=True
-    )
-
-    assert res.status_code == 200
-
-    # Check Traditional Chinese translations (not English)
-    assert "小時".encode() in res.data, "Expected Traditional Chinese '小時' for Hours"
-    assert "分鐘".encode() in res.data, "Expected Traditional Chinese '分鐘' for Minutes"
-    assert b"Hours" not in res.data or "小時".encode() in res.data, "Should have Traditional Chinese, not English"
-
-
-def test_accept_language_header_en_variants(client, live_server, measure_memory_usage, datastore_path):
-    """
-    Test that browsers sending en-GB and en-US in Accept-Language header get the correct English variant.
-    This ensures the locale selector works properly for English variants.
-    """
-    from flask import url_for
-
-    # Test 1: British English (en-GB)
-    with client.session_transaction() as sess:
-        sess.clear()
-
-    res = client.get(
-        url_for("watchlist.index"),
-        headers={'Accept-Language': 'en-GB,en;q=0.9'},
-        follow_redirects=True
-    )
-
-    assert res.status_code == 200
-
-    # Should get English content
-    assert b"Select Language" in res.data, "Expected English text 'Select Language'"
-
-    # Check HTML lang attribute uses BCP 47 format with hyphen
-    assert b'<html lang="en-GB"' in res.data, "Expected BCP 47 language tag en-GB in HTML"
-
-    # Check that the correct flag icon is shown (UK flag for en-GB)
-    assert b'<span class="fi fi-gb fis" id="language-selector-flag">' in res.data, \
-        "Expected UK flag 'fi fi-gb' for British English"
-
-    # Test 2: American English (en-US)
-    with client.session_transaction() as sess:
-        sess.clear()
-
-    res = client.get(
-        url_for("watchlist.index"),
-        headers={'Accept-Language': 'en-US,en;q=0.9'},
-        follow_redirects=True
-    )
-
-    assert res.status_code == 200
-
-    # Should get English content
-    assert b"Select Language" in res.data, "Expected English text 'Select Language'"
-
-    # Check HTML lang attribute uses BCP 47 format with hyphen
-    assert b'<html lang="en-US"' in res.data, "Expected BCP 47 language tag en-US in HTML"
-
-    # Check that the correct flag icon is shown (US flag for en-US)
-    assert b'<span class="fi fi-us fis" id="language-selector-flag">' in res.data, \
-        "Expected US flag 'fi fi-us' for American English"
-
-    # Test 3: Generic 'en' should fall back to one of the English variants
-    with client.session_transaction() as sess:
-        sess.clear()
-
-    res = client.get(
-        url_for("watchlist.index"),
-        headers={'Accept-Language': 'en'},
-        follow_redirects=True
-    )
-
-    assert res.status_code == 200
-
-    # Should get English content (either variant is fine)
-    assert b"Select Language" in res.data, "Expected English text 'Select Language'"
-
-
-def test_accept_language_header_zh_simplified(client, live_server, measure_memory_usage, datastore_path):
-    """
-    Test that browsers sending zh or zh-CN in Accept-Language header get Simplified Chinese.
-    This ensures Simplified Chinese still works correctly and doesn't get confused with Traditional.
-    """
-    from flask import url_for
-
-    # Test 1: Generic 'zh' should get Simplified Chinese
-    with client.session_transaction() as sess:
-        sess.clear()
-
-    res = client.get(
-        url_for("watchlist.index"),
-        headers={'Accept-Language': 'zh,en;q=0.9'},
-        follow_redirects=True
-    )
-
-    assert res.status_code == 200
-
-    # Should get Simplified Chinese content, not Traditional Chinese
-    # Simplified: 选择语言, Traditional: 選擇語言
-    assert '选择语言'.encode() in res.data, "Expected Simplified Chinese '选择语言' (Select Language)"
-    assert '選擇語言'.encode() not in res.data, "Should not get Traditional Chinese '選擇語言'"
-
-    # Check HTML lang attribute
-    assert b'<html lang="zh"' in res.data, "Expected language tag zh in HTML"
-
-    # Check that the correct flag icon is shown (China flag for Simplified Chinese)
-    assert b'<span class="fi fi-cn fis" id="language-selector-flag">' in res.data, \
-        "Expected China flag 'fi fi-cn' for Simplified Chinese"
-    assert b'<span class="fi fi-tw fis" id="language-selector-flag">' not in res.data, \
-        "Should not show Taiwan flag 'fi fi-tw' for Simplified Chinese"
-
-    # Test 2: 'zh-CN' should also get Simplified Chinese
-    with client.session_transaction() as sess:
-        sess.clear()
-
-    res = client.get(
-        url_for("watchlist.index"),
-        headers={'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8'},
-        follow_redirects=True
-    )
-
-    assert res.status_code == 200
-
-    # Should get Simplified Chinese content
-    assert '选择语言'.encode() in res.data, "Expected Simplified Chinese '选择语言' with zh-CN header"
-    assert '選擇語言'.encode() not in res.data, "Should not get Traditional Chinese with zh-CN header"
-
-    # Check that the correct flag icon is shown (China flag for zh-CN)
-    assert b'<span class="fi fi-cn fis" id="language-selector-flag">' in res.data, \
-        "Expected China flag 'fi fi-cn' for zh-CN header"
-
-    # Verify Simplified Chinese in settings page
-    res = client.get(
-        url_for("settings.settings_page"),
-        headers={'Accept-Language': 'zh,en;q=0.9'},
-        follow_redirects=True
-    )
-
-    assert res.status_code == 200
-
-    # Check Simplified Chinese translations (not Traditional or English)
-    # Simplified: 小时, Traditional: 小時
-    assert "小时".encode() in res.data, "Expected Simplified Chinese '小时' for Hours"
-    assert "分钟".encode() in res.data, "Expected Simplified Chinese '分钟' for Minutes"
-    assert "秒".encode() in res.data, "Expected Simplified Chinese '秒' for Seconds"
-    # Make sure it's not Traditional Chinese
-    assert "小時".encode() not in res.data, "Should not have Traditional Chinese '小時'"
-    assert "分鐘".encode() not in res.data, "Should not have Traditional Chinese '分鐘'"
-
-
-def test_session_locale_overrides_accept_language(client, live_server, measure_memory_usage, datastore_path):
-    """
-    Test that session locale preference overrides browser Accept-Language header.
-
-    Scenario:
-    1. Browser auto-detects zh-TW (Traditional Chinese) from Accept-Language header
-    2. User explicitly selects Korean language
-    3. On subsequent page loads, Korean should be shown (not Traditional Chinese)
-       even though the Accept-Language header still says zh-TW
-
-    This tests the session override behavior for issue #3779.
-    """
-    from flask import url_for
-
-    # Step 1: Clear session and make first request with zh-TW header (auto-detect)
-    with client.session_transaction() as sess:
-        sess.clear()
-
-    res = client.get(
-        url_for("watchlist.index"),
-        headers={'Accept-Language': 'zh-TW,zh;q=0.9,en;q=0.8'},
-        follow_redirects=True
-    )
-
-    assert res.status_code == 200
-
-    # Should initially get Traditional Chinese from auto-detect
-    assert '選擇語言'.encode() in res.data, "Expected Traditional Chinese '選擇語言' from auto-detect"
-    assert b'<html lang="zh-Hant-TW"' in res.data, "Expected zh-Hant-TW language tag"
-    assert b'<span class="fi fi-tw fis" id="language-selector-flag">' in res.data, \
-        "Expected Taiwan flag 'fi fi-tw' from auto-detect"
-
-    # Step 2: User explicitly selects Korean language
-    res = client.get(
-        url_for("set_language", locale="ko"),
-        headers={'Accept-Language': 'zh-TW,zh;q=0.9,en;q=0.8'},  # Browser still sends zh-TW
-        follow_redirects=True
-    )
-
-    assert res.status_code == 200
-
-    # Step 3: Make another request with same zh-TW header
-    # Session should override the Accept-Language header
-    res = client.get(
-        url_for("watchlist.index"),
-        headers={'Accept-Language': 'zh-TW,zh;q=0.9,en;q=0.8'},  # Still sending zh-TW!
-        follow_redirects=True
-    )
-
-    assert res.status_code == 200
-
-    # Should now get Korean (session overrides auto-detect)
-    # Korean: 언어 선택, Traditional Chinese: 選擇語言
-    assert '언어 선택'.encode() in res.data, "Expected Korean '언어 선택' (Select Language) from session"
-    assert '選擇語言'.encode() not in res.data, "Should not get Traditional Chinese when Korean is set in session"
-
-    # Check HTML lang attribute is Korean
-    assert b'<html lang="ko"' in res.data, "Expected Korean language tag 'ko' in HTML"
-
-    # Check that Korean flag is shown (not Taiwan flag)
-    assert b'<span class="fi fi-kr fis" id="language-selector-flag">' in res.data, \
-        "Expected Korean flag 'fi fi-kr' from session preference"
-    assert b'<span class="fi fi-tw fis" id="language-selector-flag">' not in res.data, \
-        "Should not show Taiwan flag when Korean is set in session"
-
-    # Verify Korean text on settings page as well
-    res = client.get(
-        url_for("settings.settings_page"),
-        headers={'Accept-Language': 'zh-TW,zh;q=0.9,en;q=0.8'},  # Still zh-TW!
-        follow_redirects=True
-    )
-
-    assert res.status_code == 200
-
-    # Check Korean translations (not Traditional Chinese or English)
-    # Korean: 시간 (Hours), 분 (Minutes), 초 (Seconds)
-    # Traditional Chinese: 小時, 分鐘, 秒
-    assert "시간".encode() in res.data, "Expected Korean '시간' for Hours"
-    assert "분".encode() in res.data, "Expected Korean '분' for Minutes"
-    assert "小時".encode() not in res.data, "Should not have Traditional Chinese '小時' when Korean is set"
-    assert "分鐘".encode() not in res.data, "Should not have Traditional Chinese '分鐘' when Korean is set"

docker-compose.yml

@@ -16,6 +16,13 @@ services:
   #        Log output levels: TRACE, DEBUG(default), INFO, SUCCESS, WARNING, ERROR, CRITICAL
   #      - LOGGER_LEVEL=TRACE
   #
+  #        Install additional Python packages (processor plugins, etc.)
+  #        Packages are installed at container startup and cached to avoid reinstalling on every restart
+  #        Example: Install the OSINT reconnaissance processor plugin
+  #      - EXTRA_PACKAGES=changedetection-osint-processor
+  #        Multiple packages can be installed by separating with spaces:
+  #      - EXTRA_PACKAGES=changedetection-osint-processor another-plugin
+  #
   #
   #       Uncomment below and the "sockpuppetbrowser" to use a real Chrome browser (It uses the "playwright" protocol)
   #      - PLAYWRIGHT_DRIVER_URL=ws://browser-sockpuppet-chrome:3000

docker-entrypoint.sh

@@ -0,0 +1,28 @@
+#!/bin/bash
+set -e
+
+# Install additional packages from EXTRA_PACKAGES env var
+# Uses a marker file to avoid reinstalling on every container restart
+INSTALLED_MARKER="/datastore/.extra_packages_installed"
+CURRENT_PACKAGES="$EXTRA_PACKAGES"
+
+if [ -n "$EXTRA_PACKAGES" ]; then
+    # Check if we need to install/update packages
+    if [ ! -f "$INSTALLED_MARKER" ] || [ "$(cat $INSTALLED_MARKER 2>/dev/null)" != "$CURRENT_PACKAGES" ]; then
+        echo "Installing extra packages: $EXTRA_PACKAGES"
+        pip3 install --no-cache-dir $EXTRA_PACKAGES
+
+        if [ $? -eq 0 ]; then
+            echo "$CURRENT_PACKAGES" > "$INSTALLED_MARKER"
+            echo "Extra packages installed successfully"
+        else
+            echo "ERROR: Failed to install extra packages"
+            exit 1
+        fi
+    else
+        echo "Extra packages already installed: $EXTRA_PACKAGES"
+    fi
+fi
+
+# Execute the main command
+exec "$@"

requirements.txt

@@ -51,9 +51,9 @@ linkify-it-py
 
 # - Needed for apprise/spush, and maybe others? hopefully doesnt trigger a rust compile.
 # - Requires extra wheel for rPi, adds build time for arm/v8 which is not in piwheels
-# Pinned to 43.0.1 for ARM compatibility (45.x may not have pre-built ARM wheels)
+# Pinned to 44.x for ARM compatibility and sslyze compatibility (sslyze requires <45)
 # Also pinned because dependabot wants specific versions
-cryptography==46.0.3
+cryptography==44.0.0
 
 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
 # use any version other than 2.0.x due to https://github.com/eclipse/paho.mqtt.python/issues/814