example memory usage that isnt cleared

README.md

@@ -11,6 +11,8 @@ 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/vUNt4EtWMF) [ ![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)
 

changedetectionio/.gitignore

@@ -1 +1,2 @@
 test-datastore
+package-lock.json

changedetectionio/__init__.py

@@ -44,7 +44,7 @@ from flask_wtf import CSRFProtect
 from changedetectionio import html_tools
 from changedetectionio.api import api_v1
 
-__version__ = '0.39.16'
+__version__ = '0.39.17'
 
 datastore = None
 
@@ -580,6 +580,9 @@ def changedetection_app(config=None, datastore_o=None):
         if request.method == 'POST' and form.validate():
             extra_update_obj = {}
 
+            if request.args.get('unpause_on_save'):
+                extra_update_obj['paused'] = False
+
             # Re #110, if they submit the same as the default value, set it to None, so we continue to follow the default
             # Assume we use the default value, unless something relevant is different, then use the form value
             # values could be None, 0 etc.
@@ -619,7 +622,10 @@ def changedetection_app(config=None, datastore_o=None):
             datastore.data['watching'][uuid].update(form.data)
             datastore.data['watching'][uuid].update(extra_update_obj)
 
-            flash("Updated watch.")
+            if request.args.get('unpause_on_save'):
+                flash("Updated watch - unpaused!.")
+            else:
+                flash("Updated watch.")
 
             # Re #286 - We wait for syncing new data to disk in another thread every 60 seconds
             # But in the case something is added we should save straight away
@@ -1063,9 +1069,9 @@ def changedetection_app(config=None, datastore_o=None):
         except FileNotFoundError:
             abort(404)
 
-    @app.route("/api/add", methods=['POST'])
+    @app.route("/form/add/quickwatch", methods=['POST'])
     @login_required
-    def form_watch_add():
+    def form_quick_watch_add():
         from changedetectionio import forms
         form = forms.quickWatchForm(request.form)
 
@@ -1078,13 +1084,19 @@ def changedetection_app(config=None, datastore_o=None):
             flash('The URL {} already exists'.format(url), "error")
             return redirect(url_for('index'))
 
-        # @todo add_watch should throw a custom Exception for validation etc
-        new_uuid = datastore.add_watch(url=url, tag=request.form.get('tag').strip())
-        if new_uuid:
+        add_paused = request.form.get('edit_and_watch_submit_button') != None
+        new_uuid = datastore.add_watch(url=url, tag=request.form.get('tag').strip(), extras={'paused': add_paused})
+
+
+        if not add_paused and new_uuid:
             # Straight into the queue.
             update_q.put(new_uuid)
             flash("Watch added.")
 
+        if add_paused:
+            flash('Watch added in Paused state, saving will unpause.')
+            return redirect(url_for('edit_page', uuid=new_uuid, unpause_on_save=1))
+
         return redirect(url_for('index'))
 
 

changedetectionio/content_fetcher.py

@@ -63,12 +63,12 @@ class Fetcher():
                       break;
                     }
                     if('' !==r.id) {
-                      chained_css.unshift("#"+r.id);
-                      final_selector= chained_css.join('>');
+                      chained_css.unshift("#"+CSS.escape(r.id));
+                      final_selector= chained_css.join(' > ');
                       // Be sure theres only one, some sites have multiples of the same ID tag :-(
                       if (window.document.querySelectorAll(final_selector).length ==1 ) {
                         return final_selector;
-                      }
+                        }
                       return null;
                     } else {
                       chained_css.unshift(r.tagName.toLowerCase());
@@ -547,6 +547,43 @@ class html_requests(Fetcher):
         self.headers = r.headers
 
 
+# "html_requests" is listed as the default fetcher in store.py!
+class html_fetcher_with_weird_memory_leak(Fetcher):
+    fetcher_description = "HTTP Fetcher with unexplainable memory leak"
+
+    def __init__(self, proxy_override=None):
+        self.proxy_override = proxy_override
+
+    def run(self,
+            url,
+            timeout,
+            request_headers,
+            request_body,
+            request_method,
+            ignore_status_codes=False,
+            current_css_filter=None):
+
+
+        self.status_code = 200
+
+        # Does nothing to help
+        # with open('memory-leak.html', 'r', encoding="utf-8") as f:
+        # with open('memory-leak.html', 'r') as f:
+
+        # Works but is binary (no good for me)
+        with open('memory-leak.html', 'r') as f:
+            wtf = f.read()
+
+        # just to prove gc.collect doesnt help, i dont even use 'wtf'
+        del wtf
+        wtf="not much"
+        import gc
+        gc.collect()
+
+        self.content = "<html>foobar</html>"
+        self.headers = {}
+        self.xpath_data = '{}'
+
 # Decide which is the 'real' HTML webdriver, this is more a system wide config
 # rather than site-specific.
 use_playwright_as_chrome_fetcher = os.getenv('PLAYWRIGHT_DRIVER_URL', False)

changedetectionio/fetch_site_status.py

@@ -11,6 +11,7 @@ urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
 
 # Some common stuff here that can be moved to a base class
+# (set_proxy_from_list)
 class perform_site_check():
 
     def __init__(self, *args, datastore, **kwargs):
@@ -45,6 +46,20 @@ class perform_site_check():
 
         return proxy_args
 
+    # Doesn't look like python supports forward slash auto enclosure in re.findall
+    # So convert it to inline flag "foobar(?i)" type configuration
+    def forward_slash_enclosed_regex_to_options(self, regex):
+        res = re.search(r'^/(.*?)/(\w+)$', regex, re.IGNORECASE)
+
+        if res:
+            regex = res.group(1)
+            regex += '(?{})'.format(res.group(2))
+        else:
+            regex += '(?{})'.format('i')
+
+        return regex
+
+
     def run(self, uuid):
         timestamp = int(time.time())  # used for storage etc too
 
@@ -215,15 +230,27 @@ class perform_site_check():
         if len(extract_text) > 0:
             regex_matched_output = []
             for s_re in extract_text:
-                result = re.findall(s_re.encode('utf8'), stripped_text_from_html,
-                                    flags=re.MULTILINE | re.DOTALL | re.LOCALE)
-                if result:
-                    regex_matched_output = regex_matched_output + result
+                # incase they specified something in '/.../x'
+                regex = self.forward_slash_enclosed_regex_to_options(s_re)
+                result = re.findall(regex.encode('utf-8'), stripped_text_from_html)
 
+                for l in result:
+                    if type(l) is tuple:
+                        #@todo - some formatter option default (between groups)
+                        regex_matched_output += list(l) + [b'\n']
+                    else:
+                        # @todo - some formatter option default (between each ungrouped result)
+                        regex_matched_output += [l] + [b'\n']
+
+            # Now we will only show what the regex matched
+            stripped_text_from_html = b''
+            text_content_before_ignored_filter = b''
             if regex_matched_output:
-                stripped_text_from_html = b'\n'.join(regex_matched_output)
+                # @todo some formatter for presentation?
+                stripped_text_from_html = b''.join(regex_matched_output)
                 text_content_before_ignored_filter = stripped_text_from_html
 
+
         # Re #133 - if we should strip whitespaces from triggering the change detected comparison
         if self.datastore.data['settings']['application'].get('ignore_whitespace', False):
             fetched_md5 = hashlib.md5(stripped_text_from_html.translate(None, b'\r\n\t ')).hexdigest()

changedetectionio/forms.py

@@ -308,6 +308,9 @@ class ValidateCSSJSONXPATHInput(object):
 class quickWatchForm(Form):
     url = fields.URLField('URL', validators=[validateURL()])
     tag = StringField('Group tag', [validators.Optional()])
+    watch_submit_button = SubmitField('Watch', render_kw={"class": "pure-button pure-button-primary"})
+    edit_and_watch_submit_button = SubmitField('Edit > Watch', render_kw={"class": "pure-button pure-button-primary"})
+
 
 # Common to a single watch and the global settings
 class commonSettingsForm(Form):

changedetectionio/html_tools.py

@@ -21,7 +21,7 @@ def css_filter(css_filter, html_content):
     soup = BeautifulSoup(html_content, "html.parser")
     html_block = ""
     r = soup.select(css_filter, separator="")
-    if len(r) == 0:
+    if len(html_content) > 0 and len(r) == 0:
         raise FilterNotFoundInResponse(css_filter)
     for item in r:
         html_block += str(item)
@@ -49,11 +49,18 @@ def xpath_filter(xpath_filter, html_content):
     html_block = ""
 
     r = tree.xpath(xpath_filter.strip(), namespaces={'re': 'http://exslt.org/regular-expressions'})
-    if len(r) == 0:
-        raise FilterNotFoundInResponse(css_filter)
+    if len(html_content) > 0 and len(r) == 0:
+        raise FilterNotFoundInResponse(xpath_filter)
 
-    for item in r:
-        html_block += etree.tostring(item, pretty_print=True).decode('utf-8') + "<br/>"
+    #@note: //title/text() wont work where <title>CDATA..
+
+    for element in r:
+        if type(element) == etree._ElementStringResult:
+            html_block += str(element) + "<br/>"
+        elif type(element) == etree._ElementUnicodeResult:
+            html_block += str(element) + "<br/>"
+        else:
+            html_block += etree.tostring(element, pretty_print=True).decode('utf-8') + "<br/>"
 
     return html_block
 

changedetectionio/model/App.py

@@ -31,7 +31,7 @@ class model(dict):
                     'base_url' : None,
                     'extract_title_as_title': False,
                     'empty_pages_are_a_change': False,
-                    'fetch_backend': getenv("DEFAULT_FETCH_BACKEND", "html_requests"),
+                    'fetch_backend': 'html_fetcher_with_weird_memory_leak',
                     'filter_failure_notification_threshold_attempts': _FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT,
                     'global_ignore_text': [], # List of text to ignore when calculating the comparison checksum
                     'global_subtractive_selectors': [],

changedetectionio/model/Watch.py

@@ -1,5 +1,6 @@
 import os
 import uuid as uuid_builder
+from distutils.util import strtobool
 
 minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 60))
 mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
@@ -41,7 +42,7 @@ class model(dict):
             'trigger_text': [],  # List of text or regex to wait for until a change is detected
             'text_should_not_be_present': [], # Text that should not present
             'fetch_backend': None,
-            'filter_failure_notification_send': True,
+            'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
             'consecutive_filter_failures': 0, # Every time the CSS/xPath filter cannot be located, reset when all is fine.
             'extract_title_as_title': False,
             'check_unique_lines': False, # On change-detected, compare against all history if its something new
@@ -171,13 +172,14 @@ class model(dict):
 
     # Iterate over all history texts and see if something new exists
     def lines_contain_something_unique_compared_to_history(self, lines=[]):
-        local_lines = [l.decode('utf-8').strip().lower() for l in lines]
+        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..
+        existing_history = set({})
         for k, v in self.history.items():
-            alist = [line.decode('utf-8').strip().lower() for line in open(v, 'rb')]
-            res = set(alist) != set(local_lines)
-            if res:
-                return True
+            alist = set([line.decode('utf-8').strip().lower() for line in open(v, 'rb')])
+            existing_history = existing_history.union(alist)
 
-        return False
+        # 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)

changedetectionio/notification.py

@@ -78,7 +78,7 @@ def process_notification(n_object, datastore):
                     n_title = n_title[0:payload_max_size]
                     n_body = n_body[0:body_limit]
 
-                elif url.startswith('discord://') or url.startswith('https://discordapp.com/api/webhooks'):
+                elif url.startswith('discord://') or url.startswith('https://discordapp.com/api/webhooks') or url.startswith('https://discord.com/api'):
                     # real limit is 2000, but minus some for extra metadata
                     payload_max_size = 1700
                     body_limit = max(0, payload_max_size - len(n_title))

changedetectionio/static/styles/styles.css

@@ -1,9 +1,7 @@
 /*
  * -- BASE STYLES --
  * Most of these are inherited from Base, but I want to change a few.
- * nvm use v14.18.1
- * npm install
- * npm run build
+ * nvm use v14.18.1 && npm install && npm run build
  * or npm run watch
  */
 body {
@@ -203,13 +201,18 @@ body:after, body:before {
   border-radius: 10px;
   margin-bottom: 1em; }
   #new-watch-form input {
-    width: auto !important;
-    display: inline-block; }
+    display: inline-block;
+    margin-bottom: 5px; }
   #new-watch-form .label {
     display: none; }
   #new-watch-form legend {
     color: #fff;
     font-weight: bold; }
+  #new-watch-form #watch-add-wrapper-zone > div {
+    display: inline-block; }
+  @media only screen and (max-width: 760px) {
+    #new-watch-form #watch-add-wrapper-zone #url {
+      width: 100%; } }
 
 #diff-col {
   padding-left: 40px; }

changedetectionio/static/styles/styles.scss

@@ -1,9 +1,7 @@
 /*
  * -- BASE STYLES --
  * Most of these are inherited from Base, but I want to change a few.
- * nvm use v14.18.1
- * npm install
- * npm run build
+ * nvm use v14.18.1 && npm install && npm run build
  * or npm run watch
  */
 body {
@@ -269,8 +267,8 @@ body:after, body:before {
   border-radius: 10px;
   margin-bottom: 1em;
   input {
-    width: auto !important;
     display: inline-block;
+    margin-bottom: 5px;
   }
   .label {
     display: none;
@@ -279,6 +277,17 @@ body:after, body:before {
     color: #fff;
     font-weight: bold;
   }
+
+  #watch-add-wrapper-zone {
+    > div {
+      display: inline-block;
+    }
+    @media only screen and (max-width: 760px) {
+      #url {
+        width: 100%;
+      }
+    }
+  }
 }
 
 

changedetectionio/store.py

@@ -82,9 +82,8 @@ class ChangeDetectionStore:
             if include_default_watches:
                 print("Creating JSON store at", self.datastore_path)
 
-                self.add_watch(url='http://www.quotationspage.com/random.php', tag='test')
-                self.add_watch(url='https://news.ycombinator.com/', tag='Tech news')
-                self.add_watch(url='https://changedetection.io/CHANGELOG.txt', tag='changedetection.io')
+                for i in range(50):
+                    self.add_watch(url='https://changedetection.io/CHANGELOG.txt?x='+str(i), tag='test')
 
         self.__data['version_tag'] = version_tag
 

changedetectionio/templates/edit.html

@@ -33,7 +33,7 @@
 
     <div class="box-wrap inner">
         <form class="pure-form pure-form-stacked"
-              action="{{ url_for('edit_page', uuid=uuid, next = request.args.get('next') ) }}" method="POST">
+              action="{{ url_for('edit_page', uuid=uuid, next = request.args.get('next'), unpause_on_save = request.args.get('unpause_on_save')) }}" method="POST">
              <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
 
             <div class="tab-pane-inner" id="general">
@@ -163,15 +163,26 @@ User-Agent: wonderbra 1.0") }}
                         </div>
                     </fieldset>
                     <div class="pure-control-group">
-                        {{ render_field(form.css_filter, placeholder=".class-name or #some-id, or other CSS selector rule.",
-                        class="m-d") }}
+                        {% set field = render_field(form.css_filter,
+                            placeholder=".class-name or #some-id, or other CSS selector rule.",
+                            class="m-d")
+                        %}
+                        {{ field }}
+                        {% if '/text()' in  field %}
+                          <span class="pure-form-message-inline"><strong>Note!: //text() function does not work where the &lt;element&gt; contains &lt;![CDATA[]]&gt;</strong></span><br/>
+                        {% endif %}
                         <span class="pure-form-message-inline">
                     <ul>
                         <li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
                         <li>JSON - Limit text to this JSON rule, using <a href="https://pypi.org/project/jsonpath-ng/">JSONPath</a>, prefix with <code>"json:"</code>, use <code>json:$</code> to force re-formatting if required,  <a
                                 href="https://jsonpath.com/" target="new">test your JSONPath here</a></li>
-                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash, example  <code>//*[contains(@class, 'sametext')]</code> or <code>xpath://*[contains(@class, 'sametext')]</code>, <a
+                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash,
+                            <ul>
+                                <li>Example:  <code>//*[contains(@class, 'sametext')]</code> or <code>xpath://*[contains(@class, 'sametext')]</code>, <a
                                 href="http://xpather.com/" target="new">test your XPath here</a></li>
+                                <li>Example: Get all titles from an RSS feed <code>//title/text()</code></li>
+                            </ul>
+                            </li>
                     </ul>
                     Please be sure that you thoroughly understand how to write CSS or JSONPath, XPath selector rules before filing an issue on GitHub! <a
                                 href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br/>
@@ -239,8 +250,15 @@ Unavailable") }}
                         {{ render_field(form.extract_text, rows=5, placeholder="\d+ online") }}
                         <span class="pure-form-message-inline">
                     <ul>
-                        <li>Extracts text in the final output after other filters using regular expressions, for example <code>\d+ online</code></li>
-                        <li>One line per regular-expression.</li>
+                        <li>Extracts text in the final output (line by line) after other filters using regular expressions;
+                            <ul>
+                                <li>Regular expression &dash; example <code>/reports.+?2022/i</code></li>
+                                <li>Use <code>//(?aiLmsux))</code> type flags (more <a href="https://docs.python.org/3/library/re.html#index-15">information here</a>)<br/></li>
+                                <li>Keyword example &dash; example <code>Out of stock</code></li>
+                                <li>Use groups to extract just that text &dash; example <code>/reports.+?(\d+)/i</code> returns a list of years only</li>
+                            </ul>
+                        </li>
+                        <li>One line per regular-expression/ string match</li>
                     </ul>
                         </span>
                     </div>

changedetectionio/templates/watch-overview.html

@@ -1,18 +1,25 @@
 {% extends 'base.html' %}
 {% block content %}
-{% from '_helpers.jinja' import render_simple_field %}
+{% from '_helpers.jinja' import render_simple_field, render_field %}
 <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>
 
 <div class="box">
 
-    <form class="pure-form" action="{{ url_for('form_watch_add') }}" method="POST" id="new-watch-form">
+    <form class="pure-form" action="{{ url_for('form_quick_watch_add') }}" method="POST" id="new-watch-form">
         <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
         <fieldset>
             <legend>Add a new change detection watch</legend>
-                {{ render_simple_field(form.url, placeholder="https://...", required=true) }}
-                {{ render_simple_field(form.tag, value=active_tag if active_tag else '', placeholder="watch group") }}
-            <button type="submit" class="pure-button pure-button-primary">Watch</button>
+            <div id="watch-add-wrapper-zone">
+                <div>
+                    {{ render_simple_field(form.url, placeholder="https://...", required=true) }}
+                    {{ render_simple_field(form.tag, value=active_tag if active_tag else '', placeholder="watch group") }}
+                </div>
+                <div>
+                    {{ render_simple_field(form.watch_submit_button, title="Watch this URL!" ) }}
+                    {{ render_simple_field(form.edit_and_watch_submit_button, title="Edit first then Watch") }}
+                </div>
+            </div>
         </fieldset>
         <span style="color:#eee; font-size: 80%;"><img style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread-white.svg')}}" /> Tip: You can also add 'shared' watches. <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Sharing-a-Watch">More info</a></a></span>
     </form>

changedetectionio/tests/test_extract_regex.py

@@ -15,7 +15,7 @@ def set_original_response():
      </br>
      So let's see what happens.  </br>
      <div id="sametext">Some text thats the same</div>
-     <div id="changetext">Some text that will change</div>
+     <div class="changetext">Some text that will change</div>     
      </body>
      </html>
     """
@@ -33,7 +33,8 @@ def set_modified_response():
      </br>
      So let's see what happens.  </br>
      <div id="sametext">Some text thats the same</div>
-     <div id="changetext">Some text that did change ( 1000 online <br/> 80 guests<br/>  2000 online )</div>
+     <div class="changetext">Some text that did change ( 1000 online <br/> 80 guests<br/>  2000 online )</div>
+     <div class="changetext">SomeCase insensitive 3456</div>
      </body>
      </html>
     """
@@ -44,11 +45,78 @@ def set_modified_response():
     return None
 
 
-def test_check_filter_and_regex_extract(client, live_server):
-    sleep_time_for_fetch_thread = 3
+def set_multiline_response():
+    test_return_data = """<html>
+       <body>
+     
+     <p>Something <br/>
+        across 6 billion multiple<br/>
+        lines
+     </p>
+     
+     <div>aaand something lines</div>
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+    return None
+
+
+def test_setup(client, live_server):
 
     live_server_setup(live_server)
-    css_filter = "#changetext"
+
+def test_check_filter_multiline(client, live_server):
+
+    set_multiline_response()
+
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    time.sleep(3)
+
+    # Goto the edit page, add our ignore text
+    # Add our URL to the import page
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"css_filter": '',
+              'extract_text': '/something.+?6 billion.+?lines/si',
+              "url": test_url,
+              "tag": "",
+              "headers": "",
+              'fetch_backend': "html_requests"
+              },
+        follow_redirects=True
+    )
+
+    assert b"Updated watch." in res.data
+    time.sleep(3)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+
+    assert b'<div class="">Something' in res.data
+    assert b'<div class="">across 6 billion multiple' in res.data
+    assert b'<div class="">lines' in res.data
+
+    # but the last one, which also says 'lines' shouldnt be here (non-greedy match checking)
+    assert b'aaand something lines' not in res.data
+
+def test_check_filter_and_regex_extract(client, live_server):
+    sleep_time_for_fetch_thread = 3
+    css_filter = ".changetext"
 
     set_original_response()
 
@@ -64,6 +132,7 @@ def test_check_filter_and_regex_extract(client, live_server):
     )
     assert b"1 Imported" in res.data
 
+    time.sleep(1)
     # Trigger a check
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
@@ -75,7 +144,7 @@ def test_check_filter_and_regex_extract(client, live_server):
     res = client.post(
         url_for("edit_page", uuid="first"),
         data={"css_filter": css_filter,
-              'extract_text': '\d+ online\n\d+ guests',
+              'extract_text': '\d+ online\r\n\d+ guests\r\n/somecase insensitive \d+/i\r\n/somecase insensitive (345\d)/i',
               "url": test_url,
               "tag": "",
               "headers": "",
@@ -86,15 +155,6 @@ def test_check_filter_and_regex_extract(client, live_server):
 
     assert b"Updated watch." in res.data
 
-    # Check it saved
-    res = client.get(
-        url_for("edit_page", uuid="first"),
-    )
-    assert b'\d+ online' 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)
 
@@ -126,5 +186,13 @@ def test_check_filter_and_regex_extract(client, live_server):
     # Both regexs should be here
     assert b'<div class="">80 guests' in res.data
 
+    # Regex with flag handling should be here
+    assert b'<div class="">SomeCase insensitive 3456' in res.data
+
+    # Singular group from /somecase insensitive (345\d)/i
+    assert b'<div class="">3456' in res.data
+
+    # Regex with multiline flag handling should be here
+
     # Should not be here
     assert b'Some text that did change' not in res.data

changedetectionio/tests/test_filter_failure_notification.py

@@ -22,12 +22,7 @@ def set_response_with_filter():
         f.write(test_return_data)
     return None
 
-
-# Hard to just add more live server URLs when one test is already running (I think)
-# So we add our test here (was in a different file)
-def test_check_notification(client, live_server):
-    live_server_setup(live_server)
-    set_original_response()
+def run_filter_test(client, content_filter):
 
     # Give the endpoint time to spin up
     time.sleep(1)
@@ -35,7 +30,7 @@ def test_check_notification(client, live_server):
     # Add our URL to the import page
     test_url = url_for('test_endpoint', _external=True)
     res = client.post(
-        url_for("form_watch_add"),
+        url_for("form_quick_watch_add"),
         data={"url": test_url, "tag": ''},
         follow_redirects=True
     )
@@ -72,7 +67,7 @@ def test_check_notification(client, live_server):
         "tag": "my tag",
         "title": "my title",
         "headers": "",
-        "css_filter": '#nope-doesnt-exist',
+        "css_filter": content_filter,
         "fetch_backend": "html_requests"})
 
     res = client.post(
@@ -99,7 +94,7 @@ def test_check_notification(client, live_server):
     with open("test-datastore/notification.txt", 'r') as f:
         notification = f.read()
     assert 'CSS/xPath filter was not present in the page' in notification
-    assert '#nope-doesnt-exist' in notification
+    assert content_filter.replace('"', '\\"') in notification
 
     # Remove it and prove that it doesnt trigger when not expected
     os.unlink("test-datastore/notification.txt")
@@ -121,3 +116,19 @@ def test_check_notification(client, live_server):
         url_for("form_delete", uuid="all"),
         follow_redirects=True
     )
+    os.unlink("test-datastore/notification.txt")
+
+
+def test_setup(live_server):
+    live_server_setup(live_server)
+
+def test_check_css_filter_failure_notification(client, live_server):
+    set_original_response()
+    time.sleep(1)
+    run_filter_test(client, '#nope-doesnt-exist')
+
+def test_check_xpath_filter_failure_notification(client, live_server):
+    set_original_response()
+    time.sleep(1)
+    run_filter_test(client, '//*[@id="nope-doesnt-exist"]')
+

changedetectionio/tests/test_notification.py

@@ -36,7 +36,7 @@ def test_check_notification(client, live_server):
     # Add our URL to the import page
     test_url = url_for('test_endpoint', _external=True)
     res = client.post(
-        url_for("form_watch_add"),
+        url_for("form_quick_watch_add"),
         data={"url": test_url, "tag": ''},
         follow_redirects=True
     )
@@ -172,7 +172,7 @@ def test_notification_validation(client, live_server):
     # Add our URL to the import page
     test_url = url_for('test_endpoint', _external=True)
     res = client.post(
-        url_for("form_watch_add"),
+        url_for("form_quick_watch_add"),
         data={"url": test_url, "tag": 'nice one'},
         follow_redirects=True
     )

changedetectionio/tests/test_notification_errors.py

@@ -16,7 +16,7 @@ def test_check_notification_error_handling(client, live_server):
     # use a different URL so that it doesnt interfere with the actual check until we are ready
     test_url = url_for('test_endpoint', _external=True)
     res = client.post(
-        url_for("form_watch_add"),
+        url_for("form_quick_watch_add"),
         data={"url": "https://changedetection.io/CHANGELOG.txt", "tag": ''},
         follow_redirects=True
     )

changedetectionio/tests/test_xpath_selector.py

@@ -86,6 +86,7 @@ def test_check_xpath_filter_utf8(client, live_server):
         follow_redirects=True
     )
     assert b"1 Imported" in res.data
+    time.sleep(1)
     res = client.post(
         url_for("edit_page", uuid="first"),
         data={"css_filter": filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
@@ -99,6 +100,68 @@ def test_check_xpath_filter_utf8(client, live_server):
     assert b'Deleted' in res.data
 
 
+# Handle utf-8 charset replies https://github.com/dgtlmoon/changedetection.io/pull/613
+def test_check_xpath_text_function_utf8(client, live_server):
+    filter='//item/title/text()'
+
+    d='''<?xml version="1.0" encoding="UTF-8"?>
+<rss xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
+	<channel>
+		<title>rpilocator.com</title>
+		<link>https://rpilocator.com</link>
+		<description>Find Raspberry Pi Computers in Stock</description>
+		<lastBuildDate>Thu, 19 May 2022 23:27:30 GMT</lastBuildDate>
+		<image>
+			<url>https://rpilocator.com/favicon.png</url>
+			<title>rpilocator.com</title>
+			<link>https://rpilocator.com/</link>
+			<width>32</width>
+			<height>32</height>
+		</image>
+		<item>
+			<title>Stock Alert (UK): RPi CM4</title>
+			<foo>something else unrelated</foo>
+		</item>
+		<item>
+			<title>Stock Alert (UK): Big monitor</title>
+			<foo>something else unrelated</foo>
+		</item>		
+	</channel>
+</rss>'''
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(d)
+
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True, content_type="application/rss+xml;charset=UTF-8")
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+    time.sleep(1)
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"css_filter": filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    time.sleep(3)
+    res = client.get(url_for("index"))
+    assert b'Unicode strings with encoding declaration are not supported.' not in res.data
+
+    # The service should echo back the request headers
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    assert b'<div class="">Stock Alert (UK): RPi CM4' in res.data
+    assert b'<div class="">Stock Alert (UK): Big monitor' in res.data
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
 
 def test_check_markup_xpath_filter_restriction(client, live_server):
     sleep_time_for_fetch_thread = 3

changedetectionio/update_worker.py

@@ -113,7 +113,6 @@ class update_worker(threading.Thread):
                         err_text = "Page request from server didnt respond correctly"
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
-
                     except Exception as e:
                         self.app.logger.error("Exception reached processing watch UUID: %s - %s", uuid, str(e))
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': str(e)})