Deleting a watch now removes the watches storage directory

changedetectionio/__init__.py

@@ -36,7 +36,7 @@ from flask import (
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.40.1.1'
+__version__ = '0.40.2'
 
 datastore = None
 
@@ -53,7 +53,6 @@ app = Flask(__name__,
             static_url_path="",
             static_folder="static",
             template_folder="templates")
-from flask_compress import Compress
 
 # Super handy for compressing large BrowserSteps responses and others
 FlaskCompress(app)
@@ -506,41 +505,6 @@ def changedetection_app(config=None, datastore_o=None):
         output = render_template("clear_all_history.html")
         return output
 
-
-    # If they edited an existing watch, we need to know to reset the current/previous md5 to include
-    # the excluded text.
-    def get_current_checksum_include_ignore_text(uuid):
-
-        import hashlib
-
-        from changedetectionio import fetch_site_status
-
-        # Get the most recent one
-        newest_history_key = datastore.data['watching'][uuid].get('newest_history_key')
-
-        # 0 means that theres only one, so that there should be no 'unviewed' history available
-        if newest_history_key == 0:
-            newest_history_key = list(datastore.data['watching'][uuid].history.keys())[0]
-
-        if newest_history_key:
-            with open(datastore.data['watching'][uuid].history[newest_history_key],
-                      encoding='utf-8') as file:
-                raw_content = file.read()
-
-                handler = fetch_site_status.perform_site_check(datastore=datastore)
-                stripped_content = html_tools.strip_ignore_text(raw_content,
-                                                             datastore.data['watching'][uuid]['ignore_text'])
-
-                if datastore.data['settings']['application'].get('ignore_whitespace', False):
-                    checksum = hashlib.md5(stripped_content.translate(None, b'\r\n\t ')).hexdigest()
-                else:
-                    checksum = hashlib.md5(stripped_content).hexdigest()
-
-                return checksum
-
-        return datastore.data['watching'][uuid]['previous_md5']
-
-
     @app.route("/edit/<string:uuid>", methods=['GET', 'POST'])
     @login_optionally_required
     # https://stackoverflow.com/questions/42984453/wtforms-populate-form-with-data-if-data-exists
@@ -892,8 +856,9 @@ def changedetection_app(config=None, datastore_o=None):
 
         system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
 
-        is_html_webdriver = True if watch.get('fetch_backend') == 'html_webdriver' or (
-                    watch.get('fetch_backend', None) is None and system_uses_webdriver) else False
+        is_html_webdriver = False
+        if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver':
+            is_html_webdriver = True
 
         password_enabled_and_share_is_off = False
         if datastore.data['settings']['application'].get('password') or os.getenv("SALTED_PASS", False):
@@ -943,8 +908,9 @@ def changedetection_app(config=None, datastore_o=None):
         extra_stylesheets = [url_for('static_content', group='styles', filename='diff.css')]
 
 
-        is_html_webdriver = True if watch.get('fetch_backend') == 'html_webdriver' or (
-                watch.get('fetch_backend', None) is None and system_uses_webdriver) else False
+        is_html_webdriver = False
+        if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver':
+            is_html_webdriver = True
 
         # Never requested successfully, but we detected a fetch error
         if datastore.data['watching'][uuid].history_n == 0 and (watch.get_error_text() or watch.get_error_snapshot()):
@@ -1035,7 +1001,8 @@ def changedetection_app(config=None, datastore_o=None):
             os.unlink(previous_backup_filename)
 
         # create a ZipFile object
-        backupname = "changedetection-backup-{}.zip".format(int(time.time()))
+        timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
+        backupname = "changedetection-backup-{}.zip".format(timestamp)
         backup_filepath = os.path.join(datastore_o.datastore_path, backupname)
 
         with zipfile.ZipFile(backup_filepath, "w",

changedetectionio/content_fetcher.py

@@ -297,8 +297,8 @@ class base_html_playwright(Fetcher):
                 proxy=self.proxy,
                 # This is needed to enable JavaScript execution on GitHub and others
                 bypass_csp=True,
-                # Can't think why we need the service workers for our use case?
-                service_workers='block',
+                # Should be `allow` or `block` - sites like YouTube can transmit large amounts of data via Service Workers
+                service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'),
                 # Should never be needed
                 accept_downloads=False
             )

changedetectionio/model/Watch.py

@@ -153,7 +153,9 @@ class model(dict):
     @property
     def is_pdf(self):
         # content_type field is set in the future
-        return '.pdf' in self.get('url', '').lower() or 'pdf' in self.get('content_type', '').lower()
+        # https://github.com/dgtlmoon/changedetection.io/issues/1392
+        # Not sure the best logic here
+        return self.get('url', '').lower().endswith('.pdf') or 'pdf' in self.get('content_type', '').lower()
 
     @property
     def label(self):

changedetectionio/store.py

@@ -192,27 +192,24 @@ class ChangeDetectionStore:
         tags.sort()
         return tags
 
-    def unlink_history_file(self, path):
-        try:
-            unlink(path)
-        except (FileNotFoundError, IOError):
-            pass
-
     # Delete a single watch by UUID
     def delete(self, uuid):
+        import pathlib
+        import shutil
+
         with self.lock:
             if uuid == 'all':
                 self.__data['watching'] = {}
 
                 # GitHub #30 also delete history records
                 for uuid in self.data['watching']:
-                    for path in self.data['watching'][uuid].history.values():
-                        self.unlink_history_file(path)
+                    path = pathlib.Path(os.path.join(self.datastore_path, uuid))
+                    shutil.rmtree(path)
+                    self.needs_write_urgent = True
 
             else:
-                for path in self.data['watching'][uuid].history.values():
-                    self.unlink_history_file(path)
-
+                path = pathlib.Path(os.path.join(self.datastore_path, uuid))
+                shutil.rmtree(path)
                 del self.data['watching'][uuid]
 
             self.needs_write_urgent = True

docker-compose.yml

@@ -41,7 +41,6 @@ services:
   #
   #        Base URL of your changedetection.io install (Added to the notification alert)
   #      - BASE_URL=https://mysite.com
-
   #        Respect proxy_pass type settings, `proxy_set_header Host "localhost";` and `proxy_set_header X-Forwarded-Prefix /app;`
   #        More here https://github.com/dgtlmoon/changedetection.io/wiki/Running-changedetection.io-behind-a-reverse-proxy-sub-directory
   #      - USE_X_SETTINGS=1
@@ -95,7 +94,10 @@ services:
 #            - CHROME_REFRESH_TIME=600000
 #            - DEFAULT_BLOCK_ADS=true
 #            - DEFAULT_STEALTH=true
-
+#
+#             Ignore HTTPS errors, like for self-signed certs
+#            - DEFAULT_IGNORE_HTTPS_ERRORS=true
+#
 volumes:
   changedetection-data: