Compare commits

..

2 Commits

Author SHA1 Message Date
dgtlmoon
c4a5e4a361 not needed 2026-02-03 11:05:06 +01:00
dgtlmoon
ee2a6fb77f Puppeteer and Playwright browser close/shutdown improvements 2026-02-03 10:51:44 +01:00
21 changed files with 377 additions and 556 deletions

View File

@@ -138,15 +138,6 @@ 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"]

View File

@@ -169,18 +169,58 @@ class Watch(Resource):
# Handle processor-config-* fields separately (save to JSON, not datastore)
from changedetectionio import processors
processor_config_data = {}
regular_data = {}
# 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)
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
# Update watch with regular (non-processor-config) fields
watch.update(json_data)
watch.update(regular_data)
# Save processor config to JSON file
processors.save_processor_config(self.datastore, uuid, processor_config_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}")
return "OK", 200

View File

@@ -26,9 +26,8 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
# URL List import
if request.values.get('urls') and len(request.values.get('urls').strip()):
# Import and push into the queue for immediate update check
from changedetectionio import processors
importer_handler = import_url_list()
importer_handler.run(data=request.values.get('urls'), flash=flash, datastore=datastore, processor=request.values.get('processor', processors.get_default_processor()))
importer_handler.run(data=request.values.get('urls'), flash=flash, datastore=datastore, processor=request.values.get('processor', 'text_json_diff'))
logger.debug(f"Imported {len(importer_handler.new_uuids)} new UUIDs")
# Dont' add to queue because scheduler can see that they haven't been checked and will add them to the queue
# for uuid in importer_handler.new_uuids:

View File

@@ -100,21 +100,23 @@ def construct_blueprint(datastore: ChangeDetectionStore):
# Get the processor type for this watch
processor_name = watch.get('processor', 'text_json_diff')
# 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')
try:
# Try to import the processor's difference module
processor_module = importlib.import_module(f'changedetectionio.processors.{processor_name}.difference')
# 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
)
# 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}")
# 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
@@ -154,21 +156,23 @@ def construct_blueprint(datastore: ChangeDetectionStore):
# Get the processor type for this watch
processor_name = watch.get('processor', 'text_json_diff')
# 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')
try:
# Try to import the processor's extract module
processor_module = importlib.import_module(f'changedetectionio.processors.{processor_name}.extract')
# 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
)
# 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}")
# 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
@@ -208,22 +212,24 @@ def construct_blueprint(datastore: ChangeDetectionStore):
# Get the processor type for this watch
processor_name = watch.get('processor', 'text_json_diff')
# 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')
try:
# Try to import the processor's extract module
processor_module = importlib.import_module(f'changedetectionio.processors.{processor_name}.extract')
# 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
)
# 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}")
# 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
@@ -273,33 +279,38 @@ def construct_blueprint(datastore: ChangeDetectionStore):
# Get the processor type for this watch
processor_name = watch.get('processor', 'text_json_diff')
# 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')
try:
# Try to import the processor's difference module
processor_module = importlib.import_module(f'changedetectionio.processors.{processor_name}.difference')
# 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
)
# 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
)
if result is None:
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()")
from flask import abort
abort(404, description=f"Asset '{asset_name}' not found")
abort(404, description=f"Processor '{processor_name}' does not support assets")
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()")
except (ImportError, ModuleNotFoundError) as e:
logger.warning(f"Processor {processor_name} does not have a difference module: {e}")
from flask import abort
abort(404, description=f"Processor '{processor_name}' does not support assets")
abort(404, description=f"Processor '{processor_name}' not found")
return diff_blueprint

View File

@@ -71,13 +71,8 @@ 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("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'))
flash(gettext("Cannot load the edit form for processor/plugin '{}', plugin missing?").format(processor_classes[1]), 'error')
return redirect(url_for('watchlist.index'))
parent_module = processors.get_parent_module(processor_classes[0])
@@ -154,10 +149,58 @@ 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)
# 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)
# 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)
# Ignore text
form_ignore_text = form.ignore_text.data
@@ -267,13 +310,6 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
# Get fetcher capabilities instead of hardcoded logic
capabilities = get_fetcher_capabilities(watch, datastore)
# Add processor capabilities from module
capabilities['supports_visual_selector'] = getattr(parent_module, 'supports_visual_selector', False)
capabilities['supports_text_filters_and_triggers'] = getattr(parent_module, 'supports_text_filters_and_triggers', False)
capabilities['supports_text_filters_and_triggers_elements'] = getattr(parent_module, 'supports_text_filters_and_triggers_elements', False)
capabilities['supports_request_type'] = getattr(parent_module, 'supports_request_type', False)
app_rss_token = datastore.data['settings']['application'].get('rss_access_token'),
c = [f"processor-{watch.get('processor')}"]

View File

@@ -38,21 +38,24 @@ def construct_blueprint(datastore: ChangeDetectionStore):
# Get the processor type for this watch
processor_name = watch.get('processor', 'text_json_diff')
# 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')
try:
# Try to import the processor's preview module
import importlib
processor_module = importlib.import_module(f'changedetectionio.processors.{processor_name}.preview')
# 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
)
# 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}")
# Fallback: if processor doesn't have preview module, use default text preview
content = []
@@ -157,33 +160,39 @@ def construct_blueprint(datastore: ChangeDetectionStore):
# Get the processor type for this watch
processor_name = watch.get('processor', 'text_json_diff')
# 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')
try:
# Try to import the processor's preview module
import importlib
processor_module = importlib.import_module(f'changedetectionio.processors.{processor_name}.preview')
# 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
)
# 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
)
if result is None:
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()")
from flask import abort
abort(404, description=f"Asset '{asset_name}' not found")
abort(404, description=f"Processor '{processor_name}' does not support assets")
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()")
except (ImportError, ModuleNotFoundError) as e:
logger.warning(f"Processor {processor_name} does not have a preview module: {e}")
from flask import abort
abort(404, description=f"Processor '{processor_name}' does not support assets")
abort(404, description=f"Processor '{processor_name}' not found")
return preview_blueprint

View File

@@ -45,19 +45,14 @@
<div class="tabs collapsable">
<ul>
<li class="tab"><a href="#general">{{ _('General') }}</a></li>
{% if capabilities.supports_request_type %}
<li class="tab"><a href="#request">{{ _('Request') }}</a></li>
{% endif %}
{% if extra_tab_content %}
<li class="tab"><a href="#extras_tab">{{ extra_tab_content }}</a></li>
{% endif %}
{% if capabilities.supports_browser_steps %}
<li class="tab"><a id="browsersteps-tab" href="#browser-steps">{{ _('Browser Steps') }}</a></li>
{% endif %}
{% if capabilities.supports_visual_selector %}
<!-- should goto extra forms? -->
{% if watch['processor'] == 'text_json_diff' or watch['processor'] == 'image_ssim_diff' %}
<li class="tab"><a id="visualselector-tab" href="#visualselector">{{ _('Visual Filter Selector') }}</a></li>
{% endif %}
{% if capabilities.supports_text_filters_and_triggers %}
<li class="tab" id="filters-and-triggers-tab"><a href="#filters-and-triggers">{{ _('Filters & Triggers') }}</a></li>
<li class="tab" id="conditions-tab"><a href="#conditions">{{ _('Conditions') }}</a></li>
{% endif %}
@@ -121,7 +116,6 @@
</fieldset>
</div>
{% if capabilities.supports_request_type %}
<div class="tab-pane-inner" id="request">
<div class="pure-control-group inline-radio">
{{ render_field(form.fetch_backend, class="fetch-backend") }}
@@ -209,7 +203,6 @@ Math: {{ 1 + 1 }}") }}
</div>
</fieldset>
</div>
{% endif %}
<div class="tab-pane-inner" id="browser-steps">
{% if capabilities.supports_browser_steps %}
@@ -290,7 +283,8 @@ Math: {{ 1 + 1 }}") }}
</fieldset>
</div>
{% if capabilities.supports_text_filters_and_triggers %}
{% if watch['processor'] == 'text_json_diff' or watch['processor'] == 'image_ssim_diff' %}
<div class="tab-pane-inner" id="conditions">
<script>
const verify_condition_rule_url="{{url_for('conditions.verify_condition_single_rule', watch_uuid=uuid)}}";
@@ -309,9 +303,7 @@ Math: {{ 1 + 1 }}") }}
<span id="activate-text-preview" class="pure-button pure-button-primary button-xsmall">{{ _('Activate preview') }}</span>
<div>
<div id="edit-text-filter">
{% if capabilities.supports_text_filters_and_triggers_elements %}
<div class="pure-control-group" id="pro-tips">
<div class="pure-control-group" id="pro-tips">
<strong>{{ _('Pro-tips:') }}</strong><br>
<ul>
<li>
@@ -322,8 +314,8 @@ Math: {{ 1 + 1 }}") }}
</li>
</ul>
</div>
{% include "edit/include_subtract.html" %}
{% endif %}
<div class="text-filtering border-fieldset">
<fieldset class="pure-group" id="text-filtering-type-options">
<h3>{{ _('Text filtering') }}</h3>
@@ -382,7 +374,7 @@ Math: {{ 1 + 1 }}") }}
{{ extra_form_content|safe }}
</div>
{% endif %}
{% if capabilities.supports_visual_selector %}
{% if watch['processor'] == 'text_json_diff' or watch['processor'] == 'image_ssim_diff' %}
<div class="tab-pane-inner visual-selector-ui" id="visualselector">
<img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}" alt="New beta functionality">
@@ -394,7 +386,7 @@ Math: {{ 1 + 1 }}") }}
{{ _('The Visual Selector tool lets you select the') }} <i>{{ _('text') }}</i> {{ _('elements that will be used for the change detection. It automatically fills-in the filters in the "CSS/JSONPath/JQ/XPath Filters" box of the') }} <a href="#filters-and-triggers">{{ _('Filters & Triggers') }}</a> {{ _('tab. Use') }} <strong>{{ _('Shift+Click') }}</strong> {{ _('to select multiple items.') }}
</span>
{% if watch['processor'] == 'image_ssim_diff' %} {# @todo, integrate with image_ssim_diff selector better, use some extra form ? #}
{% if watch['processor'] == 'image_ssim_diff' %}
<div id="selection-mode-controls" style="margin: 10px 0; padding: 10px; background: var(--color-background-tab); border-radius: 5px;">
<label style="font-weight: 600; margin-right: 15px;">{{ _('Selection Mode:') }}</label>
<label style="margin-right: 15px;">

View File

@@ -24,8 +24,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
flash(gettext('Warning, URL {} already exists').format(url), "notice")
add_paused = request.form.get('edit_and_watch_submit_button') != None
from changedetectionio import processors
processor = request.form.get('processor', processors.get_default_processor())
processor = request.form.get('processor', 'text_json_diff')
new_uuid = datastore.add_watch(url=url, tag=request.form.get('tags').strip(), extras={'paused': add_paused, 'processor': processor})
if new_uuid:

View File

@@ -205,24 +205,23 @@ html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
</div>
{% endif %}
<div>
{%- 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>
<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() -%}
<a href="{{url_for('watchlist.index', tag=watch_tag_uuid) }}" class="watch-tag-list tag-{{ watch_tag.title|sanitize_tag_class }}">{{ watch_tag.title }}</a>
{%- endfor -%}

View File

@@ -1,3 +1,4 @@
import asyncio
import gc
import json
import os
@@ -349,12 +350,7 @@ class fetcher(Fetcher):
if self.status_code != 200 and not ignore_status_codes:
screenshot = await capture_full_page_async(self.page, screenshot_format=self.screenshot_format, watch_uuid=watch_uuid, lock_viewport_elements=self.lock_viewport_elements)
# Cleanup before raising to prevent memory leak
await self.page.close()
await context.close()
await browser.close()
# Force garbage collection to release Playwright resources immediately
gc.collect()
# Finally block will handle cleanup
raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
if not empty_pages_are_a_change and len((await self.page.content()).strip()) == 0:
@@ -370,12 +366,7 @@ class fetcher(Fetcher):
try:
await self.iterate_browser_steps(start_url=url)
except BrowserStepsStepException:
try:
await context.close()
await browser.close()
except Exception as e:
# Fine, could be messy situation
pass
# Finally block will handle cleanup
raise
await self.page.wait_for_timeout(extra_wait * 1000)
@@ -424,35 +415,40 @@ class fetcher(Fetcher):
raise ScreenshotUnavailable(url=url, status_code=self.status_code)
finally:
# Request garbage collection one more time before closing
# Clean up resources properly with timeouts to prevent hanging
try:
await self.page.request_gc()
except:
pass
# Clean up resources properly
try:
await self.page.request_gc()
except:
pass
if hasattr(self, 'page') and self.page:
await self.page.request_gc()
await asyncio.wait_for(self.page.close(), timeout=5.0)
logger.debug(f"Successfully closed page for {url}")
except asyncio.TimeoutError:
logger.warning(f"Timed out closing page for {url} (5s)")
except Exception as e:
logger.warning(f"Error closing page for {url}: {e}")
finally:
self.page = None
try:
await self.page.close()
except:
pass
self.page = None
if context:
await asyncio.wait_for(context.close(), timeout=5.0)
logger.debug(f"Successfully closed context for {url}")
except asyncio.TimeoutError:
logger.warning(f"Timed out closing context for {url} (5s)")
except Exception as e:
logger.warning(f"Error closing context for {url}: {e}")
finally:
context = None
try:
await context.close()
except:
pass
context = None
try:
await browser.close()
except:
pass
browser = None
if browser:
await asyncio.wait_for(browser.close(), timeout=5.0)
logger.debug(f"Successfully closed browser connection for {url}")
except asyncio.TimeoutError:
logger.warning(f"Timed out closing browser connection for {url} (5s)")
except Exception as e:
logger.warning(f"Error closing browser for {url}: {e}")
finally:
browser = None
# Force Python GC to release Playwright resources immediately
# Playwright objects can have circular references that delay cleanup

View File

@@ -1,4 +1,5 @@
import asyncio
import gc
import json
import os
import websockets.exceptions
@@ -221,19 +222,36 @@ class fetcher(Fetcher):
self.browser_connection_url += f"{r}--proxy-server={proxy_url}"
async def quit(self, watch=None):
try:
await self.page.close()
del self.page
except Exception as e:
pass
watch_uuid = watch.get('uuid') if watch else 'unknown'
# Close page
try:
await self.browser.close()
del self.browser
if hasattr(self, 'page') and self.page:
await asyncio.wait_for(self.page.close(), timeout=5.0)
logger.debug(f"[{watch_uuid}] Page closed successfully")
except asyncio.TimeoutError:
logger.warning(f"[{watch_uuid}] Timed out closing page (5s)")
except Exception as e:
pass
logger.warning(f"[{watch_uuid}] Error closing page: {e}")
finally:
self.page = None
logger.info("Cleanup puppeteer complete.")
# Close browser connection
try:
if hasattr(self, 'browser') and self.browser:
await asyncio.wait_for(self.browser.close(), timeout=5.0)
logger.debug(f"[{watch_uuid}] Browser closed successfully")
except asyncio.TimeoutError:
logger.warning(f"[{watch_uuid}] Timed out closing browser (5s)")
except Exception as e:
logger.warning(f"[{watch_uuid}] Error closing browser: {e}")
finally:
self.browser = None
logger.info(f"[{watch_uuid}] Cleanup puppeteer complete")
# Force garbage collection to release resources
gc.collect()
async def fetch_page(self,
current_include_filters,
@@ -263,9 +281,11 @@ class fetcher(Fetcher):
# Connect directly using the specified browser_ws_endpoint
# @todo timeout
try:
logger.debug(f"[{watch_uuid}] Connecting to browser at {self.browser_connection_url}")
self.browser = await pyppeteer_instance.connect(browserWSEndpoint=self.browser_connection_url,
ignoreHTTPSErrors=True
)
logger.debug(f"[{watch_uuid}] Browser connected successfully")
except websockets.exceptions.InvalidStatusCode as e:
raise BrowserConnectError(msg=f"Error while trying to connect the browser, Code {e.status_code} (check your access, whitelist IP, password etc)")
except websockets.exceptions.InvalidURI:
@@ -274,7 +294,18 @@ class fetcher(Fetcher):
raise BrowserConnectError(msg=f"Error connecting to the browser - Exception '{str(e)}'")
# more reliable is to just request a new page
self.page = await self.browser.newPage()
try:
logger.debug(f"[{watch_uuid}] Creating new page")
self.page = await self.browser.newPage()
logger.debug(f"[{watch_uuid}] Page created successfully")
except Exception as e:
logger.error(f"[{watch_uuid}] Failed to create new page: {e}")
# Browser is connected but page creation failed - must cleanup browser
try:
await asyncio.wait_for(self.browser.close(), timeout=3.0)
except Exception as cleanup_error:
logger.error(f"[{watch_uuid}] Failed to cleanup browser after page creation failure: {cleanup_error}")
raise
# Add console handler to capture console.log from favicon fetcher
#self.page.on('console', lambda msg: logger.debug(f"Browser console [{msg.type}]: {msg.text}"))
@@ -343,6 +374,12 @@ class fetcher(Fetcher):
w = extra_wait - 2 if extra_wait > 4 else 2
logger.debug(f"Waiting {w} seconds before calling Page.stopLoading...")
await asyncio.sleep(w)
# Check if page still exists (might have been closed due to error during sleep)
if not self.page or not hasattr(self.page, '_client'):
logger.debug("Page already closed, skipping stopLoading")
return
logger.debug("Issuing stopLoading command...")
await self.page._client.send('Page.stopLoading')
logger.debug("stopLoading command sent!")
@@ -368,7 +405,9 @@ class fetcher(Fetcher):
asyncio.create_task(handle_frame_navigation())
response = await self.page.goto(url, timeout=0)
await asyncio.sleep(1 + extra_wait)
await self.page._client.send('Page.stopLoading')
# Check if page still exists before sending command
if self.page and hasattr(self.page, '_client'):
await self.page._client.send('Page.stopLoading')
if response:
break
@@ -437,15 +476,9 @@ class fetcher(Fetcher):
logger.debug(f"Screenshot format {self.screenshot_format}")
self.screenshot = await capture_full_page(page=self.page, screenshot_format=self.screenshot_format, watch_uuid=watch_uuid, lock_viewport_elements=self.lock_viewport_elements)
# Force aggressive memory cleanup - pyppeteer base64 decode creates temporary buffers
# Force garbage collection - pyppeteer base64 decode creates temporary buffers
import gc
gc.collect()
# Release C-level memory from base64 decode back to OS
try:
import ctypes
ctypes.CDLL('libc.so.6').malloc_trim(0)
except Exception:
pass
self.xpath_data = await self.page.evaluate(XPATH_ELEMENT_JS, {
"visualselector_xpath_selectors": visualselector_xpath_selectors,
"max_height": MAX_TOTAL_HEIGHT

View File

@@ -730,7 +730,7 @@ class quickWatchForm(Form):
url = fields.URLField(_l('URL'), validators=[validateURL()])
tags = StringTagUUID(_l('Group tag'), validators=[validators.Optional()])
watch_submit_button = SubmitField(_l('Watch'), render_kw={"class": "pure-button pure-button-primary"})
processor = RadioField(_l('Processor'), choices=lambda: processors.available_processors(), default=processors.get_default_processor)
processor = RadioField(_l('Processor'), choices=lambda: processors.available_processors(), default="text_json_diff")
edit_and_watch_submit_button = SubmitField(_l('Edit > Watch'), render_kw={"class": "pure-button pure-button-primary"})
@@ -749,7 +749,7 @@ class commonSettingsForm(Form):
notification_format = SelectField(_l('Notification format'), choices=list(valid_notification_formats.items()))
notification_title = StringField(_l('Notification Title'), default='ChangeDetection.io Notification - {{ watch_url }}', validators=[validators.Optional(), ValidateJinja2Template()])
notification_urls = StringListField(_l('Notification URL List'), validators=[validators.Optional(), ValidateAppRiseServers(), ValidateJinja2Template()])
processor = RadioField( label=_l("Processor - What do you want to achieve?"), choices=lambda: processors.available_processors(), default=processors.get_default_processor)
processor = RadioField( label=_l("Processor - What do you want to achieve?"), choices=lambda: processors.available_processors(), default="text_json_diff")
scheduler_timezone_default = StringField(_l("Default timezone for watch check scheduler"), render_kw={"list": "timezones"}, validators=[validateTimeZoneName()])
webdriver_delay = IntegerField(_l('Wait seconds before extracting text'), validators=[validators.Optional(), validators.NumberRange(min=1, message=_l("Should contain one or more seconds"))])
@@ -763,7 +763,7 @@ class commonSettingsForm(Form):
class importForm(Form):
processor = RadioField(_l('Processor'), choices=lambda: processors.available_processors(), default=processors.get_default_processor)
processor = RadioField(_l('Processor'), choices=lambda: processors.available_processors(), default="text_json_diff")
urls = TextAreaField(_l('URLs'))
xlsx_file = FileField(_l('Upload .xlsx file'), validators=[FileAllowed(['xlsx'], _l('Must be .xlsx file!'))])
file_mapping = SelectField(_l('File mapping'), [validators.DataRequired()], choices={('wachete', 'Wachete mapping'), ('custom','Custom mapping')})

View File

@@ -105,30 +105,6 @@ 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)

View File

@@ -17,11 +17,9 @@ 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.
@@ -48,22 +46,6 @@ 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
@@ -115,137 +97,54 @@ 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 DISABLED_PROCESSORS environment variable (comma-separated list).
Can be filtered via ALLOWED_PROCESSORS environment variable (comma-separated list).
:return: A list :)
"""
processor_classes = find_processors()
# 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:
# 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:
# Parse comma-separated list and strip whitespace
disabled_processors = [p.strip() for p in disabled_processors_env.split(',') if p.strip()]
logger.info(f"DISABLED_PROCESSORS set, disabling: {disabled_processors}")
allowed_processors = [p.strip() for p in allowed_processors_env.split(',') if p.strip()]
logger.info(f"ALLOWED_PROCESSORS set, filtering to: {allowed_processors}")
available = []
plugin_metadata = get_plugin_processor_metadata()
for module, sub_package_name in processor_classes:
# Skip disabled processors
if sub_package_name in disabled_processors:
logger.debug(f"Skipping processor '{sub_package_name}' (in DISABLED_PROCESSORS)")
# 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)")
continue
# 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)
# Try to get the 'name' attribute from the processor module first
if hasattr(module, 'name'):
description = gettext(module.name)
else:
# Try to get the 'name' attribute from the processor module first
if hasattr(module, 'name'):
description = gettext(module.name)
# 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:
# 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()
# 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))
@@ -256,20 +155,6 @@ def available_processors():
return [(name, desc) for name, desc, weight in available]
def get_default_processor():
"""
Get the default processor to use when none is specified.
Returns the first available processor based on weight (lowest weight = highest priority).
This ensures forms auto-select a valid processor even when DISABLED_PROCESSORS filters the list.
:return: The processor name string (e.g., 'text_json_diff')
"""
available = available_processors()
if available:
return available[0][0] # Return the processor name from first tuple
return 'text_json_diff' # Fallback if somehow no processors are available
def get_processor_badge_texts():
"""
Get a dictionary mapping processor names to their list_badge_text values.
@@ -394,76 +279,3 @@ 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

View File

@@ -12,13 +12,6 @@ processor_description = "Visual/Screenshot change detection (Fast)"
processor_name = "image_ssim_diff"
processor_weight = 2 # Lower weight = appears at top, heavier weight = appears lower (bottom)
# Processor capabilities
supports_visual_selector = True
supports_browser_steps = True
supports_text_filters_and_triggers = False
supports_text_filters_and_triggers_elements = False
supports_request_type = True
PROCESSOR_CONFIG_NAME = f"{Path(__file__).parent.name}.json"
# Subprocess timeout settings

View File

@@ -4,13 +4,6 @@ from changedetectionio.model.Watch import model as BaseWatch
from typing import Union
import re
# Processor capabilities
supports_visual_selector = True
supports_browser_steps = True
supports_text_filters_and_triggers = True
supports_text_filters_and_triggers_elements = True
supports_request_type = True
class Restock(dict):
def parse_currency(self, raw_value: str) -> Union[float, None]:

View File

@@ -1,11 +1,5 @@
from loguru import logger
# Processor capabilities
supports_visual_selector = True
supports_browser_steps = True
supports_text_filters_and_triggers = True
supports_text_filters_and_triggers_elements = True
supports_request_type = True
from loguru import logger

View File

@@ -142,14 +142,11 @@ 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'
# 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)
try:
processor_module = importlib.import_module(f"changedetectionio.processors.{processor}.processor")
except ModuleNotFoundError as e:
print(f"Processor module '{processor}' not found.")
raise e
update_handler = processor_module.perform_site_check(datastore=datastore,
watch_uuid=uuid)
@@ -478,14 +475,9 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
del update_handler
update_handler = None
# Force aggressive memory cleanup after clearing
# Force garbage collection
import gc
gc.collect()
try:
import ctypes
ctypes.CDLL('libc.so.6').malloc_trim(0)
except Exception:
pass
except Exception as e:
logger.error(f"Worker {worker_id} unexpected error processing {uuid}: {e}")
@@ -498,6 +490,7 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
finally:
# Always cleanup - this runs whether there was an exception or not
if uuid:
# Call quit() as backup (Puppeteer/Playwright have internal cleanup, but this acts as safety net)
try:
if update_handler and hasattr(update_handler, 'fetcher') and update_handler.fetcher:
await update_handler.fetcher.quit(watch=watch)
@@ -506,35 +499,25 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
try:
# Release UUID from processing (thread-safe)
worker_pool.release_uuid_from_processing(uuid, worker_id=worker_id)
# Send completion signal
if watch:
#logger.info(f"Worker {worker_id} sending completion signal for UUID {watch['uuid']}")
watch_check_update.send(watch_uuid=watch['uuid'])
# Explicitly clean up update_handler and all its references
# Clean up all memory references BEFORE garbage collection
if update_handler:
# Clear fetcher content using the proper method
if hasattr(update_handler, 'fetcher') and update_handler.fetcher:
update_handler.fetcher.clear_content()
# Clear processor references
if hasattr(update_handler, 'content_processor'):
update_handler.content_processor = None
del update_handler
update_handler = None
# Clear local contents variable if it still exists
# Clear large content variables
if 'contents' in locals():
del contents
# Note: We don't set watch = None here because:
# 1. watch is just a local reference to datastore.data['watching'][uuid]
# 2. Setting it to None doesn't affect the datastore
# 3. GC can't collect the object anyway (still referenced by datastore)
# 4. It would just cause confusion
# Force garbage collection after cleanup
# Force garbage collection after all references are cleared
import gc
gc.collect()

View File

@@ -16,13 +16,6 @@ services:
# Log output levels: TRACE, DEBUG(default), INFO, SUCCESS, WARNING, ERROR, CRITICAL
# - LOGGER_LEVEL=TRACE
#
# Plugins! See https://changedetection.io/plugins for more plugins.
# Install additional Python packages (processor plugins, etc.)
# Example: Install the OSINT reconnaissance processor plugin
# - EXTRA_PACKAGES=changedetection.io-osint
# Multiple packages can be installed by separating with spaces:
# - EXTRA_PACKAGES=changedetection.io-osint 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

View File

@@ -1,28 +0,0 @@
#!/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: $EXTRA_PACKAGES"
fi
fi
# Execute the main command
exec "$@"

View File

@@ -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 44.x for ARM compatibility and sslyze compatibility (sslyze requires <45) and (45.x may not have pre-built ARM wheels)
# Pinned to 43.0.1 for ARM compatibility (45.x may not have pre-built ARM wheels)
# Also pinned because dependabot wants specific versions
cryptography==44.0.0
cryptography==46.0.3
# 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