Disable pagination

Dockerfile

@@ -22,7 +22,7 @@ RUN pip install --target=/dependencies -r /requirements.txt
 
 # Playwright is an alternative to Selenium
 # Excluded this package from requirements.txt to prevent arm/v6 and arm/v7 builds from failing
-RUN pip install --target=/dependencies playwright~=1.20 \
+RUN pip install --target=/dependencies playwright~=1.24 \
     || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
 
 # Final image stage

README.md

@@ -11,8 +11,6 @@ Live your data-life *pro-actively* instead of *re-actively*.
 
 Free, Open-source web page monitoring, notification and change detection. Don't have time? [**Try our $6.99/month subscription - unlimited checks and watches!**](https://lemonade.changedetection.io/start)
 
-[![Discord](https://img.shields.io/badge/DISCORD-%237289DA.svg?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/XJZy7QK3ja) [ ![YouTube](https://img.shields.io/badge/YouTube-%23FF0000.svg?style=for-the-badge&logo=YouTube&logoColor=white)](https://www.youtube.com/channel/UCbS09q1TRf0o4N2t-WA3emQ) [![LinkedIn](https://img.shields.io/badge/linkedin-%230077B5.svg?style=for-the-badge&logo=linkedin&logoColor=white)](https://www.linkedin.com/company/changedetection-io/)
-
 
 [<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start)
 

changedetection.py

@@ -6,6 +6,36 @@
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
 from changedetectionio import changedetection
+import multiprocessing
+import signal
+import os
+
+def sigchld_handler(_signo, _stack_frame):
+    import sys
+    print('Shutdown: Got SIGCHLD')
+    # https://stackoverflow.com/questions/40453496/python-multiprocessing-capturing-signals-to-restart-child-processes-or-shut-do
+    pid, status = os.waitpid(-1, os.WNOHANG | os.WUNTRACED | os.WCONTINUED)
+
+    print('Sub-process: pid %d status %d' % (pid, status))
+    if status != 0:
+        sys.exit(1)
+
+    raise SystemExit
 
 if __name__ == '__main__':
-    changedetection.main()
+
+    #signal.signal(signal.SIGCHLD, sigchld_handler)
+
+    # The only way I could find to get Flask to shutdown, is to wrap it and then rely on the subsystem issuing SIGTERM/SIGKILL
+    parse_process = multiprocessing.Process(target=changedetection.main)
+    parse_process.daemon = True
+    parse_process.start()
+    import time
+
+    try:
+        while True:
+            time.sleep(1)
+
+    except KeyboardInterrupt:
+        #parse_process.terminate() not needed, because this process will issue it to the sub-process anyway
+        print ("Exited - CTRL+C")

changedetectionio/__init__.py

@@ -44,7 +44,7 @@ from flask_wtf import CSRFProtect
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.39.17.1'
+__version__ = '0.39.17.2'
 
 datastore = None
 
@@ -76,7 +76,7 @@ app.config['LOGIN_DISABLED'] = False
 
 # Disables caching of the templates
 app.config['TEMPLATES_AUTO_RELOAD'] = True
-
+app.jinja_env.add_extension('jinja2.ext.loopcontrols')
 csrf = CSRFProtect()
 csrf.init_app(app)
 
@@ -115,18 +115,19 @@ def _jinja2_filter_datetime(watch_obj, format="%Y-%m-%d %H:%M:%S"):
 
     return timeago.format(int(watch_obj['last_checked']), time.time())
 
-
-# @app.context_processor
-# def timeago():
-#    def _timeago(lower_time, now):
-#        return timeago.format(lower_time, now)
-#    return dict(timeago=_timeago)
-
 @app.template_filter('format_timestamp_timeago')
 def _jinja2_filter_datetimestamp(timestamp, format="%Y-%m-%d %H:%M:%S"):
+    if timestamp == False:
+        return 'Not yet'
+
     return timeago.format(timestamp, time.time())
-    # return timeago.format(timestamp, time.time())
+
-    # return datetime.datetime.utcfromtimestamp(timestamp).strftime(format)
+@app.template_filter('format_seconds_ago')
+def _jinja2_filter_seconds_precise(timestamp):
+    if timestamp == False:
+        return 'Not yet'
+
+    return format(int(time.time()-timestamp), ',d')
 
 # When nobody is logged in Flask-Login's current_user is set to an AnonymousUser object.
 class User(flask_login.UserMixin):
@@ -313,7 +314,7 @@ def changedetection_app(config=None, datastore_o=None):
                 watch['uuid'] = uuid
                 sorted_watches.append(watch)
 
-        sorted_watches.sort(key=lambda x: x['last_changed'], reverse=True)
+        sorted_watches.sort(key=lambda x: x.last_changed, reverse=False)
 
         fg = FeedGenerator()
         fg.title('changedetection.io')
@@ -332,7 +333,7 @@ def changedetection_app(config=None, datastore_o=None):
             if not watch.viewed:
                 # Re #239 - GUID needs to be individual for each event
                 # @todo In the future make this a configurable link back (see work on BASE_URL https://github.com/dgtlmoon/changedetection.io/pull/228)
-                guid = "{}/{}".format(watch['uuid'], watch['last_changed'])
+                guid = "{}/{}".format(watch['uuid'], watch.last_changed)
                 fe = fg.add_entry()
 
                 # Include a link to the diff page, they will have to login here to see if password protection is enabled.
@@ -703,7 +704,14 @@ def changedetection_app(config=None, datastore_o=None):
                     return redirect(url_for('settings_page'))
 
             if form.validate():
-                datastore.data['settings']['application'].update(form.data['application'])
+                # Don't set password to False when a password is set - should be only removed with the `removepassword` button
+                app_update = dict(deepcopy(form.data['application']))
+
+                # Never update password with '' or False (Added by wtforms when not in submission)
+                if 'password' in app_update and not app_update['password']:
+                    del (app_update['password'])
+
+                datastore.data['settings']['application'].update(app_update)
                 datastore.data['settings']['requests'].update(form.data['requests'])
 
                 if not os.getenv("SALTED_PASS", False) and len(form.application.form.password.encrypted_password):
@@ -823,7 +831,7 @@ def changedetection_app(config=None, datastore_o=None):
             previous_version_file_contents = "Unable to read {}.\n".format(previous_file)
 
 
-        screenshot_url = datastore.get_screenshot(uuid)
+        screenshot_url = watch.get_screenshot()
 
         system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
 
@@ -843,7 +851,11 @@ def changedetection_app(config=None, datastore_o=None):
                                  extra_title=" - Diff - {}".format(watch['title'] if watch['title'] else watch['url']),
                                  left_sticky=True,
                                  screenshot=screenshot_url,
-                                 is_html_webdriver=is_html_webdriver)
+                                 is_html_webdriver=is_html_webdriver,
+                                 last_error=watch['last_error'],
+                                 last_error_text=watch.get_error_text(),
+                                 last_error_screenshot=watch.get_error_snapshot()
+                                 )
 
         return output
 
@@ -858,20 +870,34 @@ def changedetection_app(config=None, datastore_o=None):
         if uuid == 'first':
             uuid = list(datastore.data['watching'].keys()).pop()
 
-        # Normally you would never reach this, because the 'preview' button is not available when there's no history
-        # However they may try to clear snapshots and reload the page
-        if datastore.data['watching'][uuid].history_n == 0:
-            flash("Preview unavailable - No fetch/check completed or triggers not reached", "error")
-            return redirect(url_for('index'))
-
-        extra_stylesheets = [url_for('static_content', group='styles', filename='diff.css')]
-
         try:
             watch = datastore.data['watching'][uuid]
         except KeyError:
             flash("No history found for the specified link, bad link?", "error")
             return redirect(url_for('index'))
 
+        system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
+        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
+
+        # 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()):
+            flash("Preview unavailable - No fetch/check completed or triggers not reached", "error")
+            output = render_template("preview.html",
+                                     content=content,
+                                     history_n=watch.history_n,
+                                     extra_stylesheets=extra_stylesheets,
+#                                     current_diff_url=watch['url'],
+                                     watch=watch,
+                                     uuid=uuid,
+                                     is_html_webdriver=is_html_webdriver,
+                                     last_error=watch['last_error'],
+                                     last_error_text=watch.get_error_text(),
+                                     last_error_screenshot=watch.get_error_snapshot())
+            return output
 
         timestamp = list(watch.history.keys())[-1]
         filename = watch.history[timestamp]
@@ -906,23 +932,20 @@ def changedetection_app(config=None, datastore_o=None):
         except Exception as e:
             content.append({'line': "File doesnt exist or unable to read file {}".format(filename), 'classes': ''})
 
-
-        screenshot_url = datastore.get_screenshot(uuid)
-        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
-
         output = render_template("preview.html",
                                  content=content,
+                                 history_n=watch.history_n,
                                  extra_stylesheets=extra_stylesheets,
                                  ignored_line_numbers=ignored_line_numbers,
                                  triggered_line_numbers=trigger_line_numbers,
                                  current_diff_url=watch['url'],
-                                 screenshot=screenshot_url,
+                                 screenshot=watch.get_screenshot(),
                                  watch=watch,
                                  uuid=uuid,
-                                 is_html_webdriver=is_html_webdriver)
+                                 is_html_webdriver=is_html_webdriver,
+                                 last_error=watch['last_error'],
+                                 last_error_text=watch.get_error_text(),
+                                 last_error_screenshot=watch.get_error_snapshot())
 
         return output
 
@@ -1022,11 +1045,12 @@ def changedetection_app(config=None, datastore_o=None):
             if datastore.data['settings']['application']['password'] and not flask_login.current_user.is_authenticated:
                 abort(403)
 
+            screenshot_filename = "last-screenshot.png" if not request.args.get('error_screenshot') else "last-error-screenshot.png"
+
             # These files should be in our subdirectory
             try:
                 # set nocache, set content-type
-                watch_dir = datastore_o.datastore_path + "/" + filename
+                response = make_response(send_from_directory(os.path.join(datastore_o.datastore_path, filename), screenshot_filename))
-                response = make_response(send_from_directory(filename="last-screenshot.png", directory=watch_dir, path=watch_dir + "/last-screenshot.png"))
                 response.headers['Content-type'] = 'image/png'
                 response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
                 response.headers['Pragma'] = 'no-cache'
@@ -1259,7 +1283,6 @@ def notification_runner():
     global notification_debug_log
     from datetime import datetime
     import json
-
     while not app.config.exit.is_set():
         try:
             # At the moment only one thread runs (single runner)

changedetectionio/api/api_v1.py

@@ -113,7 +113,7 @@ class CreateWatch(Resource):
             list[k] = {'url': v['url'],
                        'title': v['title'],
                        'last_checked': v['last_checked'],
-                       'last_changed': v['last_changed'],
+                       'last_changed': v.last_changed,
                        'last_error': v['last_error']}
 
         if request.args.get('recheck_all'):

changedetectionio/changedetection.py

@@ -4,6 +4,7 @@
 
 import getopt
 import os
+import signal
 import sys
 
 import eventlet
@@ -11,7 +12,21 @@ import eventlet.wsgi
 from . import store, changedetection_app, content_fetcher
 from . import __version__
 
+# Only global so we can access it in the signal handler
+datastore = None
+app = None
+
+def sigterm_handler(_signo, _stack_frame):
+    global app
+    global datastore
+#    app.config.exit.set()
+    print('Shutdown: Got SIGTERM, DB saved to disk')
+    datastore.sync_to_json()
+#    raise SystemExit
+
 def main():
+    global datastore
+    global app
     ssl_mode = False
     host = ''
     port = os.environ.get('PORT') or 5000
@@ -35,11 +50,6 @@ def main():
     create_datastore_dir = False
 
     for opt, arg in opts:
-        #        if opt == '--clear-all-history':
-        # Remove history, the actual files you need to delete manually.
-        #            for uuid, watch in datastore.data['watching'].items():
-        #                watch.update({'history': {}, 'last_checked': 0, 'last_changed': 0, 'previous_md5': None})
-
         if opt == '-s':
             ssl_mode = True
 
@@ -72,9 +82,12 @@ def main():
                 "Or use the -C parameter to create the directory.".format(app_config['datastore_path']), file=sys.stderr)
             sys.exit(2)
 
+
     datastore = store.ChangeDetectionStore(datastore_path=app_config['datastore_path'], version_tag=__version__)
     app = changedetection_app(app_config, datastore)
 
+    signal.signal(signal.SIGTERM, sigterm_handler)
+
     # Go into cleanup mode
     if do_cleanup:
         datastore.remove_unused_snapshots()
@@ -111,4 +124,3 @@ def main():
     else:
         eventlet.wsgi.server(eventlet.listen((host, int(port))), app)
 
-

changedetectionio/content_fetcher.py

@@ -6,38 +6,63 @@ import requests
 import time
 import sys
 
-class PageUnloadable(Exception):
+
-    def __init__(self, status_code, url):
+class Non200ErrorCodeReceived(Exception):
+    def __init__(self, status_code, url, screenshot=None, xpath_data=None, page_html=None):
         # Set this so we can use it in other parts of the app
         self.status_code = status_code
         self.url = url
+        self.screenshot = screenshot
+        self.xpath_data = xpath_data
+        self.page_text = None
+
+        if page_html:
+            from changedetectionio import html_tools
+            self.page_text = html_tools.html_to_text(page_html)
+        return
+
+
+class JSActionExceptions(Exception):
+    def __init__(self, status_code, url, screenshot, message=''):
+        self.status_code = status_code
+        self.url = url
+        self.screenshot = screenshot
+        self.message = message
+        return
+
+class PageUnloadable(Exception):
+    def __init__(self, status_code, url, screenshot=False):
+        # Set this so we can use it in other parts of the app
+        self.status_code = status_code
+        self.url = url
+        self.screenshot = screenshot
         return
-    pass
 
 class EmptyReply(Exception):
-    def __init__(self, status_code, url):
+    def __init__(self, status_code, url, screenshot=None):
         # Set this so we can use it in other parts of the app
         self.status_code = status_code
         self.url = url
+        self.screenshot = screenshot
         return
-    pass
 
 class ScreenshotUnavailable(Exception):
-    def __init__(self, status_code, url):
+    def __init__(self, status_code, url, page_html=None):
         # Set this so we can use it in other parts of the app
         self.status_code = status_code
         self.url = url
+        if page_html:
+            from html_tools import html_to_text
+            self.page_text = html_to_text(page_html)
         return
-    pass
 
 class ReplyWithContentButNoText(Exception):
-    def __init__(self, status_code, url):
+    def __init__(self, status_code, url, screenshot=None):
         # Set this so we can use it in other parts of the app
         self.status_code = status_code
         self.url = url
+        self.screenshot = screenshot
         return
-    pass
-
 
 class Fetcher():
     error = None
@@ -180,7 +205,7 @@ class Fetcher():
     system_https_proxy = os.getenv('HTTPS_PROXY')
 
     # Time ONTOP of the system defined env minimum time
-    render_extract_delay=0
+    render_extract_delay = 0
 
     @abstractmethod
     def get_error(self):
@@ -319,17 +344,16 @@ class base_html_playwright(Fetcher):
                 with page.expect_navigation():
                     response = page.goto(url, wait_until='load')
 
-                if self.webdriver_js_execute_code is not None:
-                    page.evaluate(self.webdriver_js_execute_code)
 
             except playwright._impl._api_types.TimeoutError as e:
                 context.close()
                 browser.close()
                 # This can be ok, we will try to grab what we could retrieve
                 pass
+
             except Exception as e:
-                print ("other exception when page.goto")
+                print("other exception when page.goto")
-                print (str(e))
+                print(str(e))
                 context.close()
                 browser.close()
                 raise PageUnloadable(url=url, status_code=None)
@@ -337,22 +361,36 @@ class base_html_playwright(Fetcher):
             if response is None:
                 context.close()
                 browser.close()
-                print ("response object was none")
+                print("response object was none")
                 raise EmptyReply(url=url, status_code=None)
 
             # Bug 2(?) Set the viewport size AFTER loading the page
-            page.set_viewport_size({"width": 1280, "height": 1024})            
+            page.set_viewport_size({"width": 1280, "height": 1024})
             extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
             time.sleep(extra_wait)
+
+            if self.webdriver_js_execute_code is not None:
+                try:
+                    page.evaluate(self.webdriver_js_execute_code)
+                except Exception as e:
+                    # Is it possible to get a screenshot?
+                    error_screenshot = False
+                    try:
+                        page.screenshot(type='jpeg',
+                                        clip={'x': 1.0, 'y': 1.0, 'width': 1280, 'height': 1024},
+                                        quality=1)
+
+                        # The actual screenshot
+                        error_screenshot = page.screenshot(type='jpeg',
+                                                           full_page=True,
+                                                           quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
+                    except Exception as s:
+                        pass
+
+                    raise JSActionExceptions(status_code=response.status, screenshot=error_screenshot, message=str(e), url=url)
+
             self.content = page.content()
             self.status_code = response.status
-
-            if len(self.content.strip()) == 0:
-                context.close()
-                browser.close()
-                print ("Content was empty")
-                raise EmptyReply(url=url, status_code=None)
-            
             self.headers = response.all_headers()
 
             if current_css_filter is not None:
@@ -379,9 +417,17 @@ class base_html_playwright(Fetcher):
                 browser.close()
                 raise ScreenshotUnavailable(url=url, status_code=None)
 
+            if len(self.content.strip()) == 0:
+                context.close()
+                browser.close()
+                print("Content was empty")
+                raise EmptyReply(url=url, status_code=None, screenshot=self.screenshot)
+
             context.close()
             browser.close()
 
+            if not ignore_status_codes and self.status_code!=200:
+                raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, page_html=self.content, screenshot=self.screenshot)
 
 class base_html_webdriver(Fetcher):
     if os.getenv("WEBDRIVER_URL"):
@@ -509,7 +555,7 @@ class html_requests(Fetcher):
             ignore_status_codes=False,
             current_css_filter=None):
 
-        proxies={}
+        proxies = {}
 
         # Allows override the proxy on a per-request basis
         if self.proxy_override:
@@ -537,10 +583,14 @@ class html_requests(Fetcher):
             if encoding:
                 r.encoding = encoding
 
+        if not r.content or not len(r.content):
+            raise EmptyReply(url=url, status_code=r.status_code)
+
         # @todo test this
         # @todo maybe you really want to test zero-byte return pages?
-        if (not ignore_status_codes and not r) or not r.content or not len(r.content):
+        if r.status_code != 200 and not ignore_status_codes:
-            raise EmptyReply(url=url, status_code=r.status_code)
+            # maybe check with content works?
+            raise Non200ErrorCodeReceived(url=url, status_code=r.status_code, page_html=r.text)
 
         self.status_code = r.status_code
         self.content = r.text

changedetectionio/fetch_site_status.py

@@ -94,7 +94,7 @@ class perform_site_check():
         url = self.datastore.get_val(uuid, 'url')
         request_body = self.datastore.get_val(uuid, 'body')
         request_method = self.datastore.get_val(uuid, 'method')
-        ignore_status_code = self.datastore.get_val(uuid, 'ignore_status_codes')
+        ignore_status_codes = self.datastore.data['watching'][uuid].get('ignore_status_codes', False)
 
         # source: support
         is_source = False
@@ -124,7 +124,7 @@ class perform_site_check():
         if watch['webdriver_js_execute_code'] is not None and watch['webdriver_js_execute_code'].strip():
             fetcher.webdriver_js_execute_code = watch['webdriver_js_execute_code']
 
-        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_code, watch['css_filter'])
+        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch['css_filter'])
         fetcher.quit()
 
         # Fetching complete, now filters
@@ -210,7 +210,7 @@ class perform_site_check():
         # Treat pages with no renderable text content as a change? No by default
         empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
         if not is_json and not empty_pages_are_a_change and len(stripped_text_from_html.strip()) == 0:
-            raise content_fetcher.ReplyWithContentButNoText(url=url, status_code=200)
+            raise content_fetcher.ReplyWithContentButNoText(url=url, status_code=fetcher.get_last_status_code(), screenshot=screenshot)
 
         # We rely on the actual text in the html output.. many sites have random script vars etc,
         # in the future we'll implement other mechanisms.

changedetectionio/model/Watch.py

@@ -19,7 +19,6 @@ class model(dict):
             'url': None,
             'tag': None,
             'last_checked': 0,
-            'last_changed': 0,
             'paused': False,
             'last_viewed': 0,  # history key value of the last viewed via the [diff] link
             #'newest_history_key': 0,
@@ -38,6 +37,7 @@ class model(dict):
             'notification_format': default_notification_format,
             'notification_muted': False,
             'css_filter': '',
+            'last_error': False,
             'extract_text': [],  # Extract text by regex after filters
             'subtractive_selectors': [],
             'trigger_text': [],  # List of text or regex to wait for until a change is detected
@@ -58,11 +58,11 @@ class model(dict):
     jitter_seconds = 0
 
     def __init__(self, *arg, **kw):
-        import uuid
+
         self.update(self.__base_config)
         self.__datastore_path = kw['datastore_path']
 
-        self['uuid'] = str(uuid.uuid4())
+        self['uuid'] = str(uuid_builder.uuid4())
 
         del kw['datastore_path']
 
@@ -70,7 +70,10 @@ class model(dict):
             self.update(kw['default'])
             del kw['default']
 
-        # goes at the end so we update the default object with the initialiser
+        # Be sure the cached timestamp is ready
+        bump = self.history
+
+        # Goes at the end so we update the default object with the initialiser
         super(model, self).__init__(*arg, **kw)
 
     @property
@@ -80,6 +83,22 @@ class model(dict):
 
         return False
 
+    @property
+    def label(self):
+        # Used for sorting
+        if self['title']:
+            return self['title']
+        return self['url']
+
+    @property
+    def last_changed(self):
+        # last_changed will be the newest snapshot, but when we have just one snapshot, it should be 0
+        if self.__history_n <= 1:
+            return 0
+        if self.__newest_history_key:
+            return int(self.__newest_history_key)
+        return 0
+
     @property
     def history_n(self):
         return self.__history_n
@@ -122,19 +141,17 @@ class model(dict):
         bump = self.history
         return self.__newest_history_key
 
-
     # Save some text file to the appropriate path and bump the history
     # result_obj from fetch_site_status.run()
     def save_history_text(self, contents, timestamp):
         import uuid
-        from os import mkdir, path, unlink
         import logging
 
         output_path = "{}/{}".format(self.__datastore_path, self['uuid'])
 
         # Incase the operator deleted it, check and create.
         if not os.path.isdir(output_path):
-            mkdir(output_path)
+            os.mkdir(output_path)
 
         snapshot_fname = "{}/{}.stripped.txt".format(output_path, uuid.uuid4())
         logging.debug("Saving history text {}".format(snapshot_fname))
@@ -172,7 +189,7 @@ class model(dict):
         return seconds
 
     # Iterate over all history texts and see if something new exists
-    def lines_contain_something_unique_compared_to_history(self, lines=[]):
+    def lines_contain_something_unique_compared_to_history(self, lines: list):
         local_lines = set([l.decode('utf-8').strip().lower() for l in lines])
 
         # Compare each lines (set) against each history text file (set) looking for something new..
@@ -184,3 +201,51 @@ class model(dict):
         # Check that everything in local_lines(new stuff) already exists in existing_history - it should
         # if not, something new happened
         return not local_lines.issubset(existing_history)
+
+    def get_screenshot(self):
+        fname = os.path.join(self.__datastore_path, self['uuid'], "last-screenshot.png")
+        if os.path.isfile(fname):
+            return fname
+
+        return False
+
+    def __get_file_ctime(self, filename):
+        fname = os.path.join(self.__datastore_path, self['uuid'], filename)
+        if os.path.isfile(fname):
+            return int(os.path.getmtime(fname))
+        return False
+
+    @property
+    def error_text_ctime(self):
+        return self.__get_file_ctime('last-error.txt')
+
+    @property
+    def snapshot_text_ctime(self):
+        if self.history_n==0:
+            return False
+
+        timestamp = list(self.history.keys())[-1]
+        return int(timestamp)
+
+    @property
+    def snapshot_screenshot_ctime(self):
+        return self.__get_file_ctime('last-screenshot.png')
+
+    @property
+    def snapshot_error_screenshot_ctime(self):
+        return self.__get_file_ctime('last-error-screenshot.png')
+
+    def get_error_text(self):
+        """Return the text saved from a previous request that resulted in a non-200 error"""
+        fname = os.path.join(self.__datastore_path, self['uuid'], "last-error.txt")
+        if os.path.isfile(fname):
+            with open(fname, 'r') as f:
+                return f.read()
+        return False
+
+    def get_error_snapshot(self):
+        """Return path to the screenshot that resulted in a non-200 error"""
+        fname = os.path.join(self.__datastore_path, self['uuid'], "last-error-screenshot.png")
+        if os.path.isfile(fname):
+            return fname
+        return False

changedetectionio/run_all_tests.sh

@@ -32,6 +32,7 @@ docker run -d --name $$-test_selenium  -p 4444:4444 --rm --shm-size="2g"  seleni
 sleep 5
 export WEBDRIVER_URL=http://localhost:4444/wd/hub
 pytest tests/fetchers/test_content.py
+pytest tests/test_errorhandling.py
 unset WEBDRIVER_URL
 docker kill $$-test_selenium
 
@@ -43,5 +44,7 @@ docker run -d --name $$-test_browserless -e "DEFAULT_LAUNCH_ARGS=[\"--window-siz
 sleep 5
 export PLAYWRIGHT_DRIVER_URL=ws://127.0.0.1:3000
 pytest tests/fetchers/test_content.py
+pytest tests/test_errorhandling.py
+
 unset PLAYWRIGHT_DRIVER_URL
 docker kill $$-test_browserless

changedetectionio/static/js/diff-overview.js

@@ -10,7 +10,13 @@ $(document).ready(function () {
         if (hash_name === '#screenshot') {
             $("img#screenshot-img").attr('src', screenshot_url);
             $("#settings").hide();
-        } else {
+        } else if (hash_name === '#error-screenshot') {
+            $("img#error-screenshot-img").attr('src', error_screenshot_url);
+            $("#settings").hide();
+        }
+
+
+        else {
             $("#settings").show();
         }
     }

changedetectionio/static/js/tabs.js

@@ -1,51 +1,44 @@
 // Rewrite this is a plugin.. is all this JS really 'worth it?'
 
-
+window.addEventListener('hashchange', function () {
-if(!window.location.hash) {
+    var tabs = document.getElementsByClassName('active');
-  var tab=document.querySelectorAll("#default-tab a");
+    while (tabs[0]) {
-  tab[0].click();
+        tabs[0].classList.remove('active')
-}
+    }
-
+    set_active_tab();
-window.addEventListener('hashchange', function() {
-  var tabs = document.getElementsByClassName('active');
-  while (tabs[0]) {
-    tabs[0].classList.remove('active')
-  }
-  set_active_tab();
 }, false);
 
-var has_errors=document.querySelectorAll(".messages .error");
+var has_errors = document.querySelectorAll(".messages .error");
 if (!has_errors.length) {
-    if (document.location.hash == "" ) {
+    if (document.location.hash == "") {
-        document.location.hash = "#general";
+        document.querySelector(".tabs ul li:first-child a").click();
-        document.getElementById("default-tab").className = "active";
     } else {
         set_active_tab();
     }
 } else {
-  focus_error_tab();
+    focus_error_tab();
 }
 
 function set_active_tab() {
-  var tab=document.querySelectorAll("a[href='"+location.hash+"']");
+    var tab = document.querySelectorAll("a[href='" + location.hash + "']");
-  if (tab.length) {
+    if (tab.length) {
-    tab[0].parentElement.className="active";
+        tab[0].parentElement.className = "active";
-  }
+    }
     // hash could move the page down
     window.scrollTo(0, 0);
 }
 
 function focus_error_tab() {
-  // time to use jquery or vuejs really,
+    // time to use jquery or vuejs really,
-  // activate the tab with the error
+    // activate the tab with the error
-    var tabs = document.querySelectorAll('.tabs li a'),i;
+    var tabs = document.querySelectorAll('.tabs li a'), i;
     for (i = 0; i < tabs.length; ++i) {
-      var tab_name=tabs[i].hash.replace('#','');
+        var tab_name = tabs[i].hash.replace('#', '');
-      var pane_errors=document.querySelectorAll('#'+tab_name+' .error')
+        var pane_errors = document.querySelectorAll('#' + tab_name + ' .error')
-      if (pane_errors.length) {
+        if (pane_errors.length) {
-        document.location.hash = '#'+tab_name;
+            document.location.hash = '#' + tab_name;
-        return true;
+            return true;
-      }
+        }
     }
     return false;
 }

changedetectionio/static/styles/styles.css

@@ -539,3 +539,13 @@ ul {
   100% {
     -webkit-transform: rotate(360deg);
     transform: rotate(360deg); } }
+
+.snapshot-age {
+  padding: 4px;
+  background-color: #dfdfdf;
+  border-radius: 3px;
+  font-weight: bold;
+  margin-bottom: 4px; }
+  .snapshot-age.error {
+    background-color: #ff0000;
+    color: #fff; }

changedetectionio/static/styles/styles.scss

@@ -771,3 +771,15 @@ ul {
   }
 }
 
+.snapshot-age {
+  padding: 4px;
+  background-color: #dfdfdf;
+  border-radius: 3px;
+  font-weight: bold;
+  margin-bottom: 4px;
+  &.error {
+    background-color: #ff0000;
+    color: #fff;
+  }
+}
+

changedetectionio/store.py

@@ -254,7 +254,6 @@ class ChangeDetectionStore:
 
         self.__data['watching'][uuid].update(
             {'last_checked': 0,
-             'last_changed': 0,
              'last_viewed': 0,
              'previous_md5': False,
              'last_notification_error': False,
@@ -336,14 +335,6 @@ class ChangeDetectionStore:
             self.sync_to_json()
         return new_uuid
 
-    def get_screenshot(self, watch_uuid):
-        output_path = "{}/{}".format(self.datastore_path, watch_uuid)
-        fname = "{}/last-screenshot.png".format(output_path)
-        if path.isfile(fname):
-            return fname
-
-        return False
-
     def visualselector_data_is_ready(self, watch_uuid):
         output_path = "{}/{}".format(self.datastore_path, watch_uuid)
         screenshot_filename = "{}/last-screenshot.png".format(output_path)
@@ -354,17 +345,32 @@ class ChangeDetectionStore:
         return False
 
     # Save as PNG, PNG is larger but better for doing visual diff in the future
-    def save_screenshot(self, watch_uuid, screenshot: bytes):
+    def save_screenshot(self, watch_uuid, screenshot: bytes, as_error=False):
-        output_path = "{}/{}".format(self.datastore_path, watch_uuid)
+
-        fname = "{}/last-screenshot.png".format(output_path)
+        if as_error:
-        with open(fname, 'wb') as f:
+            target_path = os.path.join(self.datastore_path, watch_uuid, "last-error-screenshot.png")
+        else:
+            target_path = os.path.join(self.datastore_path, watch_uuid, "last-screenshot.png")
+
+        with open(target_path, 'wb') as f:
             f.write(screenshot)
             f.close()
 
-    def save_xpath_data(self, watch_uuid, data):
+    def save_error_text(self, watch_uuid, contents):
-        output_path = "{}/{}".format(self.datastore_path, watch_uuid)
+
-        fname = "{}/elements.json".format(output_path)
+        target_path = os.path.join(self.datastore_path, watch_uuid, "last-error.txt")
-        with open(fname, 'w') as f:
+
+        with open(target_path, 'w') as f:
+            f.write(contents)
+
+    def save_xpath_data(self, watch_uuid, data, as_error=False):
+
+        if as_error:
+            target_path = os.path.join(self.datastore_path, watch_uuid, "elements.json")
+        else:
+            target_path = os.path.join(self.datastore_path, watch_uuid, "elements-error.json")
+
+        with open(target_path, 'w') as f:
             f.write(json.dumps(data))
             f.close()
 
@@ -521,8 +527,15 @@ class ChangeDetectionStore:
 
     # We incorrectly stored last_changed when there was not a change, and then confused the output list table
     def update_3(self):
+        # see https://github.com/dgtlmoon/changedetection.io/pull/835
+        return
+
+    # `last_changed` not needed, we pull that information from the history.txt index
+    def update_4(self):
         for uuid, watch in self.data['watching'].items():
-            # Be sure it's recalculated
+            try:
-            p = watch.history
+                # Remove it from the struct
-            if watch.history_n < 2:
+                del(watch['last_changed'])
-                watch['last_changed'] = 0
+            except:
+                continue
+        return

changedetectionio/templates/_pagination.jinja

@@ -0,0 +1,7 @@
+{% macro pagination(sorted_watches, total_per_page, current_page) %}
+  {{ sorted_watches|length }}
+
+  {% for row in sorted_watches|batch(total_per_page, ' ') %}
+    {{ loop.index}}
+  {% endfor %}
+{% endmacro %}

changedetectionio/templates/diff.html

@@ -3,6 +3,9 @@
 {% block content %}
 <script>
     const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
+    {% if last_error_screenshot %}
+    const error_screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid, error_screenshot=1) }}";
+    {% endif %}
 </script>
 <script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
 
@@ -43,15 +46,31 @@
 <script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <div class="tabs">
     <ul>
-        <li class="tab" id="default-tab"><a href="#text">Text</a></li>
+        {% if last_error_text %}<li class="tab" id="error-text-tab"><a href="#error-text">Error Text</a></li> {% endif %}
+        {% if last_error_screenshot %}<li class="tab" id="error-screenshot-tab"><a href="#error-screenshot">Error Screenshot</a></li> {% endif %}
+        <li class="tab" id=""><a href="#text">Text</a></li>
         <li class="tab" id="screenshot-tab"><a href="#screenshot">Screenshot</a></li>
     </ul>
 </div>
 
 <div id="diff-ui">
+    <div class="tab-pane-inner" id="error-text">
+        <div class="snapshot-age error">{{watch_a.error_text_ctime|format_seconds_ago}} seconds ago</div>
+        <pre>
+            {{ last_error_text }}
+        </pre>
+    </div>
+
+    <div class="tab-pane-inner" id="error-screenshot">
+        <div class="snapshot-age error">{{watch_a.snapshot_error_screenshot_ctime|format_seconds_ago}} seconds ago</div>
+        <img id="error-screenshot-img"  style="max-width: 80%" alt="Current error-ing screenshot from most recent request"/>
+    </div>
+
      <div class="tab-pane-inner" id="text">
          <div class="tip">Pro-tip: Use <strong>show current snapshot</strong> tab to visualise what will be ignored.
          </div>
+         <div class="snapshot-age">{{watch_a.snapshot_text_ctime|format_timestamp_timeago}}</div>
+
          <table>
              <tbody>
              <tr>
@@ -70,10 +89,10 @@
          <div class="tip">
              For now, Differences are performed on text, not graphically, only the latest screenshot is available.
          </div>
-         </br>
          {% if is_html_webdriver %}
            {% if screenshot %}
-             <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request"/>
+            <div class="snapshot-age">{{watch_a.snapshot_screenshot_ctime|format_timestamp_timeago}}</div>
+            <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request"/>
            {% else %}
               No screenshot available just yet! Try rechecking the page.
            {% endif %}
@@ -88,7 +107,6 @@
 
 <script defer="">
 
-
 var a = document.getElementById('a');
 var b = document.getElementById('b');
 var result = document.getElementById('result');

changedetectionio/templates/edit.html

@@ -23,7 +23,7 @@
 
     <div class="tabs collapsable">
         <ul>
-            <li class="tab" id="default-tab"><a href="#general">General</a></li>
+            <li class="tab" id=""><a href="#general">General</a></li>
             <li class="tab"><a href="#request">Request</a></li>
             <li class="tab"><a id="visualselector-tab" href="#visualselector">Visual Filter Selector</a></li>
             <li class="tab"><a href="#filters-and-triggers">Filters &amp; Triggers</a></li>
@@ -87,6 +87,9 @@
                         </span>
                     </div>
                 {% endif %}
+                    <div  class="pure-control-group inline-radio">
+                        {{ render_checkbox_field(form.ignore_status_codes) }}
+                    </div>
                 <fieldset id="webdriver-override-options">
                     <div class="pure-control-group">
                         {{ render_field(form.webdriver_delay) }}
@@ -128,11 +131,7 @@ User-Agent: wonderbra 1.0") }}
    \"car\":null
 }") }}
                     </div>
-                    <div id="ignore-status-codes-option">
-                        {{ render_checkbox_field(form.ignore_status_codes) }}
-                    </div>
                 </fieldset>
-                <br/>
             </div>
 
             <div class="tab-pane-inner" id="notifications">

changedetectionio/templates/import.html

@@ -5,7 +5,7 @@
 
     <div class="tabs collapsable">
         <ul>
-            <li class="tab" id="default-tab"><a href="#url-list">URL List</a></li>
+            <li class="tab" id=""><a href="#url-list">URL List</a></li>
             <li class="tab"><a href="#distill-io">Distill.io</a></li>
         </ul>
     </div>

changedetectionio/templates/preview.html

@@ -3,23 +3,39 @@
 {% block content %}
 <script>
     const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
+    {% if last_error_screenshot %}
+    const error_screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid, error_screenshot=1) }}";
+    {% endif %}
 </script>
 <script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
 
-<div id="settings">
-    <h1>Current - {{watch.last_checked|format_timestamp_timeago}}</h1>
-</div>
-
 <script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <div class="tabs">
     <ul>
-        <li class="tab" id="default-tab"><a href="#text">Text</a></li>
+        {% if last_error_text %}<li class="tab" id="error-text-tab"><a href="#error-text">Error Text</a></li> {% endif %}
+        {% if last_error_screenshot %}<li class="tab" id="error-screenshot-tab"><a href="#error-screenshot">Error Screenshot</a></li> {% endif %}
+        {% if history_n > 0 %}
+        <li class="tab" id="text-tab"><a href="#text">Text</a></li>
         <li class="tab" id="screenshot-tab"><a href="#screenshot">Screenshot</a></li>
+        {% endif %}
     </ul>
 </div>
 
 <div id="diff-ui">
+    <div class="tab-pane-inner" id="error-text">
+        <div class="snapshot-age error">{{watch.error_text_ctime|format_seconds_ago}} seconds ago</div>
+        <pre>
+            {{ last_error_text }}
+        </pre>
+    </div>
+
+    <div class="tab-pane-inner" id="error-screenshot">
+        <div class="snapshot-age error">{{watch.snapshot_error_screenshot_ctime|format_seconds_ago}} seconds ago</div>
+        <img id="error-screenshot-img"  style="max-width: 80%" alt="Current erroring screenshot from most recent request"/>
+    </div>
+
     <div class="tab-pane-inner" id="text">
+        <div class="snapshot-age">{{watch.snapshot_text_ctime|format_timestamp_timeago}}</div>
         <span class="ignored">Grey lines are ignored</span> <span class="triggered">Blue lines are triggers</span>
         <table>
             <tbody>
@@ -33,6 +49,7 @@
             </tbody>
         </table>
     </div>
+
      <div class="tab-pane-inner" id="screenshot">
          <div class="tip">
              For now, Differences are performed on text, not graphically, only the latest screenshot is available.

changedetectionio/templates/settings.html

@@ -16,7 +16,7 @@
 <div class="edit-form">
     <div class="tabs collapsable">
         <ul>
-            <li class="tab" id="default-tab"><a href="#general">General</a></li>
+            <li class="tab" id=""><a href="#general">General</a></li>
             <li class="tab"><a href="#notifications">Notifications</a></li>
             <li class="tab"><a href="#fetching">Fetching</a></li>
             <li class="tab"><a href="#filters">Global Filters</a></li>

changedetectionio/templates/watch-overview.html

@@ -1,6 +1,7 @@
 {% extends 'base.html' %}
 {% block content %}
 {% from '_helpers.jinja' import render_simple_field, render_field %}
+{% from '_pagination.jinja' import pagination %}
 <script type="text/javascript" src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
 <script type="text/javascript" src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
 
@@ -32,22 +33,31 @@
         {% endfor %}
     </div>
 
+    {% set sort_order = request.args.get('order', 'desc') == 'desc' %}
+    {% set sort_attribute = request.args.get('sort', 'last_changed')   %}
+    {% set pagination_page = request.args.get('page', 0) %}
+
     <div id="watch-table-wrapper">
         <table class="pure-table pure-table-striped watch-table">
             <thead>
             <tr>
                 <th>#</th>
                 <th></th>
-                <th></th>
+                {% set link_order = "asc" if sort_order else "desc" %}
-                <th>Last Checked</th>
+                <th><a href="{{url_for('index', sort='label', order=link_order)}}">Website</a></th>
-                <th>Last Changed</th>
+                <th><a href="{{url_for('index', sort='last_checked', order=link_order)}}">Last Checked</a></th>
+                <th><a href="{{url_for('index', sort='last_changed', order=link_order)}}">Last Changed</a></th>
                 <th></th>
             </tr>
             </thead>
             <tbody>
 
+            {% set sorted_watches = watches|sort(attribute=sort_attribute, reverse=sort_order) %}
+            {% for watch in sorted_watches %}
 
-            {% for watch in watches|sort(attribute='last_changed', reverse=True) %}
+            {# WIP for pagination, disabled for now
+              {% if not ( loop.index >= 3 and loop.index <=4) %}{% continue %}{% endif %} -->
+             #}
             <tr id="{{ watch.uuid }}"
                 class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }}
                 {% if watch.last_error is defined and watch.last_error != False %}error{% endif %}
@@ -90,7 +100,7 @@
                     {% if watch.history_n >= 2 %}
                     <a href="{{ url_for('diff_history_page', uuid=watch.uuid) }}" target="{{watch.uuid}}" class="pure-button button-small pure-button-primary diff-link">Diff</a>
                     {% else %}
-                        {% if watch.history_n == 1 %}
+                        {% if watch.history_n == 1 or (watch.history_n ==0 and watch.error_text_ctime )%}
                             <a href="{{ url_for('preview_page', uuid=watch.uuid)}}" target="{{watch.uuid}}" class="pure-button button-small pure-button-primary">Preview</a>
                         {% endif %}
                     {% endif %}
@@ -113,6 +123,10 @@
                 <a href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}"><img alt="RSS Feed" id="feed-icon" src="{{url_for('static_content', group='images', filename='Generic_Feed-icon.svg')}}" height="15"></a>
             </li>
         </ul>
+        {# WIP for pagination, disabled for now
+         {{ pagination(sorted_watches,3, pagination_page) }}
+         #}
+
     </div>
 </div>
 {% endblock %}

changedetectionio/tests/test_access_control.py

@@ -19,7 +19,6 @@ def test_check_access_control(app, client):
         )
 
         assert b"Password protection enabled." in res.data
-        assert b"LOG OUT" not in res.data
 
         # Check we hit the login
         res = c.get(url_for("index"), follow_redirects=True)
@@ -38,7 +37,40 @@ def test_check_access_control(app, client):
             follow_redirects=True
         )
 
+        # Yes we are correctly logged in
         assert b"LOG OUT" in res.data
+
+        # 598 - Password should be set and not accidently removed
+        res = c.post(
+            url_for("settings_page"),
+            data={
+                  "requests-time_between_check-minutes": 180,
+                  'application-fetch_backend': "html_requests"},
+            follow_redirects=True
+        )
+
+        res = c.get(url_for("logout"),
+            follow_redirects=True)
+
+        res = c.get(url_for("settings_page"),
+            follow_redirects=True)
+
+
+        assert b"Login" in res.data
+
+        res = c.get(url_for("login"))
+        assert b"Login" in res.data
+
+
+        res = c.post(
+            url_for("login"),
+            data={"password": "foobar"},
+            follow_redirects=True
+        )
+
+        # Yes we are correctly logged in
+        assert b"LOG OUT" in res.data
+
         res = c.get(url_for("settings_page"))
 
         # Menu should be available now

changedetectionio/tests/test_errorhandling.py

@@ -11,16 +11,17 @@ def test_setup(live_server):
     live_server_setup(live_server)
 
 
-def test_error_handler(client, live_server):
+def _runner_test_http_errors(client, live_server, http_code, expected_text):
 
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write("Now you going to get a {} error code\n".format(http_code))
 
-    # Give the endpoint time to spin up
-    time.sleep(1)
 
     # Add our URL to the import page
     test_url = url_for('test_endpoint',
-                       status_code=403,
+                       status_code=http_code,
                        _external=True)
+
     res = client.post(
         url_for("import_page"),
         data={"urls": test_url},
@@ -29,15 +30,38 @@ def test_error_handler(client, live_server):
     assert b"1 Imported" in res.data
 
     # Give the thread time to pick it up
-    time.sleep(3)
+    time.sleep(2)
 
     res = client.get(url_for("index"))
+    # no change
     assert b'unviewed' not in res.data
-    assert b'Status Code 403' in res.data
+    assert bytes(expected_text.encode('utf-8')) in res.data
-    assert bytes("just now".encode('utf-8')) in res.data
+
+
+    # Error viewing tabs should appear
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    assert b'Error Text' in res.data
+
+    # 'Error Screenshot' only when in playwright mode
+    #assert b'Error Screenshot' in res.data
+
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+
+def test_http_error_handler(client, live_server):
+    _runner_test_http_errors(client, live_server, 403, 'Access denied')
+    _runner_test_http_errors(client, live_server, 404, 'Page not found')
+    _runner_test_http_errors(client, live_server, 500, '(Internal server Error) received')
+    _runner_test_http_errors(client, live_server, 400, 'Error - Request returned a HTTP error code 400')
 
 # Just to be sure error text is properly handled
-def test_error_text_handler(client, live_server):
+def test_DNS_errors(client, live_server):
     # Give the endpoint time to spin up
     time.sleep(1)
 
@@ -54,5 +78,6 @@ def test_error_text_handler(client, live_server):
 
     res = client.get(url_for("index"))
     assert b'Name or service not known' in res.data
+    # Should always record that we tried
     assert bytes("just now".encode('utf-8')) in res.data
 

changedetectionio/tests/test_ignorestatuscode.py

@@ -137,54 +137,3 @@ def test_403_page_check_works_with_ignore_status_code(client, live_server):
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
 
-
-# Tests the whole stack works with staus codes ignored
-def test_403_page_check_fails_without_ignore_status_code(client, live_server):
-    sleep_time_for_fetch_thread = 3
-
-    set_original_response()
-
-    # Give the endpoint time to spin up
-    time.sleep(1)
-
-    # Add our URL to the import page
-    test_url = url_for('test_endpoint', status_code=403, _external=True)
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-    assert b"1 Imported" in res.data
-
-    # Trigger a check
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
-
-    # Goto the edit page, check our ignore option
-    # Add our URL to the import page
-    res = client.post(
-        url_for("edit_page", uuid="first"),
-        data={"url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
-        follow_redirects=True
-    )
-    assert b"Updated watch." in res.data
-
-    # Trigger a check
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
-    #  Make a change
-    set_some_changed_response()
-
-    # Trigger a check
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
-
-    # It should have 'unviewed' still
-    # Because it should be looking at only that 'sametext' id
-    res = client.get(url_for("index"))
-    assert b'Status Code 403' in res.data

changedetectionio/update_worker.py

@@ -1,3 +1,4 @@
+import os
 import threading
 import queue
 import time
@@ -107,6 +108,14 @@ class update_worker(threading.Thread):
             self.notification_q.put(n_object)
             print("Sent filter not found notification for {}".format(watch_uuid))
 
+    def cleanup_error_artifacts(self, uuid):
+        # All went fine, remove error artifacts
+        cleanup_files = ["last-error-screenshot.png", "last-error.txt"]
+        for f in cleanup_files:
+            full_path = os.path.join(self.datastore.datastore_path, uuid, f)
+            if os.path.isfile(full_path):
+                os.unlink(full_path)
+
     def run(self):
         from changedetectionio import fetch_site_status
 
@@ -146,7 +155,31 @@ class update_worker(threading.Thread):
                         # Totally fine, it's by choice - just continue on, nothing more to care about
                         # Page had elements/content but no renderable text
                         # Backend (not filters) gave zero output
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': "Got HTML content but no text found."})
+                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': "Got HTML content but no text found (With {} reply code).".format(e.status_code)})
+                        if e.screenshot:
+                            self.datastore.save_screenshot(watch_uuid=uuid, screenshot=e.screenshot)
+                        process_changedetection_results = False
+
+                    except content_fetcher.Non200ErrorCodeReceived as e:
+                        if e.status_code == 403:
+                            err_text = "Error - 403 (Access denied) received"
+                        elif e.status_code == 404:
+                            err_text = "Error - 404 (Page not found) received"
+                        elif e.status_code == 500:
+                            err_text = "Error - 500 (Internal server Error) received"
+                        else:
+                            err_text = "Error - Request returned a HTTP error code {}".format(str(e.status_code))
+
+                        if e.screenshot:
+                            self.datastore.save_screenshot(watch_uuid=uuid, screenshot=e.screenshot, as_error=True)
+                        if e.xpath_data:
+                            self.datastore.save_xpath_data(watch_uuid=uuid, data=e.xpath_data, as_error=True)
+                        if e.page_text:
+                            self.datastore.save_error_text(watch_uuid=uuid, contents=e.page_text)
+
+                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
+                                                                           # So that we get a trigger when the content is added again
+                                                                           'previous_md5': ''})
                         process_changedetection_results = False
 
                     except FilterNotFoundInResponse as e:
@@ -182,8 +215,17 @@ class update_worker(threading.Thread):
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
+                    except content_fetcher.JSActionExceptions as e:
+                        err_text = "Error running JS Actions - Page request - "+e.message
+                        if e.screenshot:
+                            self.datastore.save_screenshot(watch_uuid=uuid, screenshot=e.screenshot, as_error=True)
+                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
+                                                                           'last_check_status': e.status_code})
                     except content_fetcher.PageUnloadable as e:
                         err_text = "Page request from server didnt respond correctly"
+                        if e.screenshot:
+                            self.datastore.save_screenshot(watch_uuid=uuid, screenshot=e.screenshot, as_error=True)
+
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                     except Exception as e:
@@ -192,8 +234,16 @@ class update_worker(threading.Thread):
                         # Other serious error
                         process_changedetection_results = False
                     else:
+
                         # Mark that we never had any failures
-                        update_obj['consecutive_filter_failures'] = 0
+                        if not self.datastore.data['watching'][uuid].get('ignore_status_codes'):
+                            update_obj['consecutive_filter_failures'] = 0
+
+                        self.cleanup_error_artifacts(uuid)
+
+                    # Crash protection, the watch entry could have been removed by this point (during a slow chrome fetch etc)
+                    if not self.datastore.data['watching'].get(uuid):
+                        continue
 
                     # Different exceptions mean that we may or may not want to bump the snapshot, trigger notifications etc
                     if process_changedetection_results:
@@ -214,8 +264,6 @@ class update_worker(threading.Thread):
 
                                 # Notifications should only trigger on the second time (first time, we gather the initial snapshot)
                                 if watch.history_n >= 2:
-                                    # Atleast 2, means there really was a change
-                                    self.datastore.update_watch(uuid=uuid, update_obj={'last_changed': round(now)})
                                     if not self.datastore.data['watching'][uuid].get('notification_muted'):
                                         self.send_content_changed_notification(self, watch_uuid=uuid)
 
@@ -227,15 +275,15 @@ class update_worker(threading.Thread):
                             self.datastore.update_watch(uuid=uuid, update_obj={'last_error': str(e)})
 
 
-                        # Always record that we atleast tried
+                    # Always record that we atleast tried
-                        self.datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - now, 3),
+                    self.datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - now, 3),
-                                                                           'last_checked': round(time.time())})
+                                                                       'last_checked': round(time.time())})
 
-                        # Always save the screenshot if it's available
+                    # Always save the screenshot if it's available
-                        if screenshot:
+                    if screenshot:
-                            self.datastore.save_screenshot(watch_uuid=uuid, screenshot=screenshot)
+                        self.datastore.save_screenshot(watch_uuid=uuid, screenshot=screenshot)
-                        if xpath_data:
+                    if xpath_data:
-                            self.datastore.save_xpath_data(watch_uuid=uuid, data=xpath_data)
+                        self.datastore.save_xpath_data(watch_uuid=uuid, data=xpath_data)
 
 
                 self.current_uuid = None  # Done

requirements.txt

@@ -18,7 +18,7 @@ wtforms ~= 3.0
 jsonpath-ng ~= 1.5.3
 
 # Notification library
-apprise ~= 0.9.9
+apprise ~= 1.0.0
 
 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
 paho-mqtt