Cleanup on both sides

changedetectionio/blueprint/browser_steps/__init__.py

@@ -174,7 +174,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     browser_steps_blueprint = Blueprint('browser_steps', __name__, template_folder="templates")
 
     async def start_browsersteps_session(watch_uuid):
-        from . import browser_steps
+        from changedetectionio.browser_steps import browser_steps
         import time
         from playwright.async_api import async_playwright
 
@@ -238,7 +238,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     @browser_steps_blueprint.route("/browsersteps_start_session", methods=['GET'])
     def browsersteps_start_session():
         # A new session was requested, return sessionID
-        import asyncio
         import uuid
         browsersteps_session_id = str(uuid.uuid4())
         watch_uuid = request.args.get('uuid')
@@ -301,8 +300,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     @browser_steps_blueprint.route("/browsersteps_update", methods=['POST'])
     def browsersteps_ui_update():
         import base64
-        import playwright._impl._errors
-        from changedetectionio.blueprint.browser_steps import browser_steps
 
         remaining =0
         uuid = request.args.get('uuid')

changedetectionio/blueprint/ui/edit.py

@@ -26,7 +26,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
     # https://wtforms.readthedocs.io/en/3.0.x/forms/#wtforms.form.Form.populate_obj ?
     def edit_page(uuid):
         from changedetectionio import forms
-        from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
+        from changedetectionio.browser_steps.browser_steps import browser_step_ui_config
         from changedetectionio import processors
         import importlib
 
@@ -354,6 +354,56 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
         # Return a 500 error
         abort(500)
 
+    @edit_blueprint.route("/edit/<string:uuid>/get-data-package", methods=['GET'])
+    @login_optionally_required
+    def watch_get_data_package(uuid):
+        """Download all data for a single watch as a zip file"""
+        from io import BytesIO
+        from flask import send_file
+        import zipfile
+        from pathlib import Path
+        import datetime
+
+        watch = datastore.data['watching'].get(uuid)
+        if not watch:
+            abort(404)
+
+        # Create zip in memory
+        memory_file = BytesIO()
+
+        with zipfile.ZipFile(memory_file, 'w',
+                           compression=zipfile.ZIP_DEFLATED,
+                           compresslevel=8) as zipObj:
+
+            # Add the watch's JSON file if it exists
+            watch_json_path = os.path.join(watch.data_dir, 'watch.json')
+            if os.path.isfile(watch_json_path):
+                zipObj.write(watch_json_path,
+                           arcname=os.path.join(uuid, 'watch.json'),
+                           compress_type=zipfile.ZIP_DEFLATED,
+                           compresslevel=8)
+
+            # Add all files in the watch data directory
+            if os.path.isdir(watch.data_dir):
+                for f in Path(watch.data_dir).glob('*'):
+                    if f.is_file() and f.name != 'watch.json':  # Skip watch.json since we already added it
+                        zipObj.write(f,
+                                   arcname=os.path.join(uuid, f.name),
+                                   compress_type=zipfile.ZIP_DEFLATED,
+                                   compresslevel=8)
+
+        # Seek to beginning of file
+        memory_file.seek(0)
+
+        # Generate filename with timestamp
+        timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
+        filename = f"watch-data-{uuid[:8]}-{timestamp}.zip"
+
+        return send_file(memory_file,
+                        as_attachment=True,
+                        download_name=filename,
+                        mimetype='application/zip')
+
     # Ajax callback
     @edit_blueprint.route("/edit/<string:uuid>/preview-rendered", methods=['POST'])
     @login_optionally_required

changedetectionio/blueprint/ui/templates/edit.html

@@ -488,6 +488,7 @@ Math: {{ 1 + 1 }}") }}
                     {% if watch.history_n %}
                         <p>
                              <a href="{{url_for('ui.ui_edit.watch_get_latest_html', uuid=uuid)}}" class="pure-button button-small">{{ _('Download latest HTML snapshot') }}</a>
+                             <a href="{{url_for('ui.ui_edit.watch_get_data_package', uuid=uuid)}}" class="pure-button button-small">{{ _('Download watch data package') }}</a>
                         </p>
                     {% endif %}
 

changedetectionio/browser_steps/browser_steps.py

@@ -8,6 +8,17 @@ from changedetectionio.content_fetchers import SCREENSHOT_MAX_HEIGHT_DEFAULT
 from changedetectionio.content_fetchers.base import manage_user_agent
 from changedetectionio.jinja2_custom import render as jinja_render
 
+def browser_steps_get_valid_steps(browser_steps: list):
+    if browser_steps is not None and len(browser_steps):
+        valid_steps = list(filter(
+            lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one'),browser_steps))
+
+        # Just incase they selected Goto site by accident with older JS
+        if valid_steps and valid_steps[0]['operation'] == 'Goto site':
+            del(valid_steps[0])
+
+        return valid_steps
+    return []
 
 
 # Two flags, tell the JS which of the "Selector" or "Value" field should be enabled in the front end

changedetectionio/content_fetchers/base.py

@@ -38,7 +38,6 @@ def manage_user_agent(headers, current_ua=''):
 
     return None
 
-
 class Fetcher():
     browser_connection_is_custom = None
     browser_connection_url = None
@@ -163,30 +162,16 @@ class Fetcher():
         """
         return {k.lower(): v for k, v in self.headers.items()}
 
-    def browser_steps_get_valid_steps(self):
-        if self.browser_steps is not None and len(self.browser_steps):
-            valid_steps = list(filter(
-                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one'),
-                self.browser_steps))
-
-            # Just incase they selected Goto site by accident with older JS
-            if valid_steps and valid_steps[0]['operation'] == 'Goto site':
-                del(valid_steps[0])
-
-            return valid_steps
-
-        return None
-
     async def iterate_browser_steps(self, start_url=None):
-        from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
+        from changedetectionio.browser_steps.browser_steps import steppable_browser_interface, browser_steps_get_valid_steps
         from playwright._impl._errors import TimeoutError, Error
         from changedetectionio.jinja2_custom import render as jinja_render
         step_n = 0
 
-        if self.browser_steps is not None and len(self.browser_steps):
+        if self.browser_steps:
             interface = steppable_browser_interface(start_url=start_url)
             interface.page = self.page
-            valid_steps = self.browser_steps_get_valid_steps()
+            valid_steps = browser_steps_get_valid_steps(self.browser_steps)
 
             for step in valid_steps:
                 step_n += 1

changedetectionio/content_fetchers/playwright.py

@@ -295,7 +295,7 @@ class fetcher(Fetcher):
             self.page.on("console", lambda msg: logger.debug(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
 
             # Re-use as much code from browser steps as possible so its the same
-            from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
+            from changedetectionio.browser_steps.browser_steps import steppable_browser_interface
             browsersteps_interface = steppable_browser_interface(start_url=url)
             browsersteps_interface.page = self.page
 
@@ -362,7 +362,7 @@ class fetcher(Fetcher):
             # Wrap remaining operations in try/finally to ensure cleanup
             try:
                 # Run Browser Steps here
-                if self.browser_steps_get_valid_steps():
+                if self.browser_steps:
                     try:
                         await self.iterate_browser_steps(start_url=url)
                     except BrowserStepsStepException:

changedetectionio/content_fetchers/puppeteer.py

@@ -456,7 +456,7 @@ class fetcher(Fetcher):
 
         # Run Browser Steps here
         # @todo not yet supported, we switch to playwright in this case
-        #            if self.browser_steps_get_valid_steps():
+        #            if self.browser_steps:
         #                self.iterate_browser_steps()
 
 

changedetectionio/content_fetchers/requests.py

@@ -3,7 +3,7 @@ import hashlib
 import os
 import re
 import asyncio
-from functools import partial
+
 from changedetectionio import strtobool
 from changedetectionio.content_fetchers.exceptions import BrowserStepsInUnsupportedFetcher, EmptyReply, Non200ErrorCodeReceived
 from changedetectionio.content_fetchers.base import Fetcher
@@ -36,7 +36,7 @@ class fetcher(Fetcher):
         import requests
         from requests.exceptions import ProxyError, ConnectionError, RequestException
 
-        if self.browser_steps_get_valid_steps():
+        if self.browser_steps:
             raise BrowserStepsInUnsupportedFetcher(url=url)
 
         proxies = {}
@@ -184,7 +184,6 @@ class fetcher(Fetcher):
         )
 
     async def quit(self, watch=None):
-
         # In case they switched to `requests` fetcher from something else
         # Then the screenshot could be old, in any case, it's not used here.
         # REMOVE_REQUESTS_OLD_SCREENSHOTS - Mainly used for testing

changedetectionio/forms.py

@@ -7,8 +7,6 @@ from flask_babel import lazy_gettext as _l, gettext
 from changedetectionio.blueprint.rss import RSS_FORMAT_TYPES, RSS_TEMPLATE_TYPE_OPTIONS, RSS_TEMPLATE_HTML_DEFAULT
 from changedetectionio.conditions.form import ConditionFormRow
 from changedetectionio.notification_service import NotificationContextData
-from changedetectionio.processors.image_ssim_diff import SCREENSHOT_COMPARISON_THRESHOLD_OPTIONS, \
-    SCREENSHOT_COMPARISON_THRESHOLD_OPTIONS_DEFAULT
 from changedetectionio.strtobool import strtobool
 from changedetectionio import processors
 
@@ -37,7 +35,7 @@ from changedetectionio.widgets import TernaryNoneBooleanField
 
 # default
 # each select <option data-enabled="enabled-0-0"
-from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
+from changedetectionio.browser_steps.browser_steps import browser_step_ui_config
 
 from changedetectionio import html_tools, content_fetchers
 
@@ -494,7 +492,6 @@ class ValidateJinja2Template(object):
     Validates that a {token} is from a valid set
     """
     def __call__(self, form, field):
-        from changedetectionio import notification
         from changedetectionio.jinja2_custom import create_jinja_env
         from jinja2 import BaseLoader, TemplateSyntaxError, UndefinedError
         from jinja2.meta import find_undeclared_variables
@@ -820,8 +817,7 @@ class processor_text_json_diff_form(commonSettingsForm):
     filter_text_removed = BooleanField(_l('Removed lines'), default=True)
 
     trigger_text = StringListField(_l('Keyword triggers - Trigger/wait for text'), [validators.Optional(), ValidateListRegex()])
-    if os.getenv("PLAYWRIGHT_DRIVER_URL"):
-        browser_steps = FieldList(FormField(SingleBrowserStep), min_entries=10)
+    browser_steps = FieldList(FormField(SingleBrowserStep), min_entries=10)
     text_should_not_be_present = StringListField(_l('Block change-detection while text matches'), [validators.Optional(), ValidateListRegex()])
     webdriver_js_execute_code = TextAreaField(_l('Execute JavaScript before change detection'), render_kw={"rows": "5"}, validators=[validators.Optional()])
 

changedetectionio/model/__init__.py

@@ -6,6 +6,8 @@ from .persistence import EntityPersistenceMixin, _determine_entity_type
 
 __all__ = ['EntityPersistenceMixin', 'watch_base']
 
+from ..browser_steps.browser_steps import browser_steps_get_valid_steps
+
 USE_SYSTEM_DEFAULT_NOTIFICATION_FORMAT_FOR_WATCH = 'System default'
 CONDITIONS_MATCH_LOGIC_DEFAULT = 'ALL'
 
@@ -364,6 +366,10 @@ class watch_base(dict):
         self._mark_field_as_edited(key)
 
     def update(self, *args, **kwargs):
+
+        if args and args[0].get('browser_steps'):
+            args[0]['browser_steps'] = browser_steps_get_valid_steps(args[0].get('browser_steps'))
+
         """Override dict.update() to track modifications to writable fields."""
         # Call parent update first
         super().update(*args, **kwargs)
@@ -376,6 +382,7 @@ class watch_base(dict):
         for key in kwargs.keys():
             self._mark_field_as_edited(key)
 
+
     def pop(self, key, *args):
         """Override dict.pop() to track removal of writable fields."""
         result = super().pop(key, *args)

changedetectionio/processors/base.py

@@ -1,5 +1,7 @@
 import re
 import hashlib
+
+from changedetectionio.browser_steps.browser_steps import browser_steps_get_valid_steps
 from changedetectionio.content_fetchers.base import Fetcher
 from changedetectionio.strtobool import strtobool
 from copy import deepcopy
@@ -169,7 +171,7 @@ class difference_detection_processor():
                                    )
 
         if self.watch.has_browser_steps:
-            self.fetcher.browser_steps = self.watch.get('browser_steps', [])
+            self.fetcher.browser_steps = browser_steps_get_valid_steps(self.watch.get('browser_steps', []))
             self.fetcher.browser_steps_screenshot_path = os.path.join(self.datastore.datastore_path, self.watch.get('uuid'))
 
         # Tweak the base config with the per-watch ones

changedetectionio/tests/test_backup.py

@@ -75,4 +75,59 @@ def test_backup(client, live_server, measure_memory_usage, datastore_path):
         follow_redirects=True
     )
 
-    assert b'No backups found.' in res.data
+    assert b'No backups found.' in res.data
+
+
+def test_watch_data_package_download(client, live_server, measure_memory_usage, datastore_path):
+    """Test downloading a single watch's data as a zip package"""
+    import os
+    import json
+
+    set_original_response(datastore_path=datastore_path)
+
+    # Add a watch
+    res = client.post(
+        url_for("imports.import_page"),
+        data={"urls": url_for('test_endpoint', _external=True)},
+        follow_redirects=True
+    )
+
+    assert b"1 Imported" in res.data
+    wait_for_all_checks(client)
+
+    # Get the UUID directly from the datastore
+    # Find the watch directories
+    uuid = None
+    for item in os.listdir(datastore_path):
+        item_path = os.path.join(datastore_path, item)
+        if os.path.isdir(item_path) and len(item) == 36:  # UUID format
+            uuid = item
+            break
+
+    assert uuid is not None, "Could not find watch UUID in datastore"
+
+    # Download the watch data package
+    res = client.get(url_for("ui.ui_edit.watch_get_data_package", uuid=uuid))
+
+    # Should get the right zip content type
+    assert res.content_type == "application/zip"
+
+    # Should be PK/ZIP stream (PKzip header)
+    assert res.data[:2] == b'PK', "File should start with PK (PKzip header)"
+    assert res.data.count(b'PK') >= 2, "Should have multiple PK markers (zip file structure)"
+
+    # Verify zip contents
+    backup = ZipFile(io.BytesIO(res.data))
+    files = backup.namelist()
+
+    # Should have files in a UUID directory
+    assert any(uuid in f for f in files), f"Files should be in UUID directory: {files}"
+
+    # Should contain watch.json
+    watch_json_path = f"{uuid}/watch.json"
+    assert watch_json_path in files, f"Should contain watch.json, got: {files}"
+
+    # Should contain history/snapshot files
+    uuid4hex_txt = re.compile(f'^{re.escape(uuid)}/.*\\.txt', re.I)
+    txt_files = list(filter(uuid4hex_txt.match, files))
+    assert len(txt_files) > 0, f"Should have at least one .txt file (history/snapshot), got: {files}"

changedetectionio/tests/visualselector/test_fetch_data.py

@@ -88,7 +88,6 @@ def test_visual_selector_content_ready(client, live_server, measure_memory_usage
 
 def test_basic_browserstep(client, live_server, measure_memory_usage, datastore_path):
 
-    assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
 
     test_url = url_for('test_interactive_html_endpoint', _external=True)
     test_url = test_url.replace('localhost.localdomain', 'cdio')
@@ -108,13 +107,13 @@ def test_basic_browserstep(client, live_server, measure_memory_usage, datastore_
             "url": test_url,
             "tags": "",
             'fetch_backend': "html_webdriver",
-            'browser_steps-0-operation': 'Enter text in field',
-            'browser_steps-0-selector': '#test-input-text',
+            'browser_steps-5-operation': 'Enter text in field',
+            'browser_steps-5-selector': '#test-input-text',
             # Should get set to the actual text (jinja2 rendered)
-            'browser_steps-0-optional_value': "Hello-Jinja2-{% now  'Europe/Berlin', '%Y-%m-%d' %}",
-            'browser_steps-1-operation': 'Click element',
-            'browser_steps-1-selector': 'button[name=test-button]',
-            'browser_steps-1-optional_value': '',
+            'browser_steps-5-optional_value': "Hello-Jinja2-{% now  'Europe/Berlin', '%Y-%m-%d' %}",
+            'browser_steps-8-operation': 'Click element',
+            'browser_steps-8-selector': 'button[name=test-button]',
+            'browser_steps-8-optional_value': '',
             # For now, cookies doesnt work in headers because it must be a full cookiejar object
             'headers': "testheader: yes\buser-agent: MyCustomAgent",
             "time_between_check_use_default": "y",
@@ -122,9 +121,18 @@ def test_basic_browserstep(client, live_server, measure_memory_usage, datastore_
         follow_redirects=True
     )
     assert b"unpaused" in res.data
-    wait_for_all_checks(client)
 
+    wait_for_all_checks(client)
     uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
+
+    # 3874 - should have tidied up any blanks
+    watch = live_server.app.config['DATASTORE'].data['watching'][uuid]
+    assert watch['browser_steps'][0].get('operation') == 'Enter text in field'
+    assert watch['browser_steps'][1].get('selector') == 'button[name=test-button]'
+
+
+    # This part actually needs the browser, before this we are just testing data
+    assert os.getenv('PLAYWRIGHT_DRIVER_URL'), "Needs PLAYWRIGHT_DRIVER_URL set for this test"
     assert live_server.app.config['DATASTORE'].data['watching'][uuid].history_n >= 1, "Watch history had atleast 1 (everything fetched OK)"
 
     assert b"This text should be removed" not in res.data