Move global vars to all live under the 'app' var

MANIFEST.in

@@ -1,4 +1,5 @@
 recursive-include changedetectionio/api *
+recursive-include changedetectionio/apprise_plugin *
 recursive-include changedetectionio/blueprint *
 recursive-include changedetectionio/content_fetchers *
 recursive-include changedetectionio/model *

changedetectionio/__init__.py

@@ -2,7 +2,7 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
-__version__ = '0.46.04'
+__version__ = '0.47.03'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError

changedetectionio/api/api_v1.py

@@ -58,7 +58,7 @@ class Watch(Resource):
             abort(404, message='No watch exists with the UUID of {}'.format(uuid))
 
         if request.args.get('recheck'):
-            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
             return "OK", 200
         if request.args.get('paused', '') == 'paused':
             self.datastore.data['watching'].get(uuid).pause()
@@ -246,7 +246,7 @@ class CreateWatch(Resource):
 
         new_uuid = self.datastore.add_watch(url=url, extras=extras, tag=tags)
         if new_uuid:
-            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
+            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
             return {'uuid': new_uuid}, 201
         else:
             return "Invalid or unsupported URL", 400
@@ -303,7 +303,7 @@ class CreateWatch(Resource):
 
         if request.args.get('recheck_all'):
             for uuid in self.datastore.data['watching'].keys():
-                self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
+                self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
             return {'status': "OK"}, 200
 
         return list, 200

changedetectionio/blueprint/check_proxies/__init__.py

@@ -1,4 +1,7 @@
+import importlib
 from concurrent.futures import ThreadPoolExecutor
+
+from changedetectionio.processors.text_json_diff.processor import FilterNotFoundInResponse
 from changedetectionio.store import ChangeDetectionStore
 
 from functools import wraps
@@ -30,7 +33,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     def long_task(uuid, preferred_proxy):
         import time
         from changedetectionio.content_fetchers import exceptions as content_fetcher_exceptions
-        from changedetectionio.processors.text_json_diff import text_json_diff
         from changedetectionio.safe_jinja import render as jinja_render
 
         status = {'status': '', 'length': 0, 'text': ''}
@@ -38,8 +40,12 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         contents = ''
         now = time.time()
         try:
-            update_handler = text_json_diff.perform_site_check(datastore=datastore, watch_uuid=uuid)
-            update_handler.call_browser()
+            processor_module = importlib.import_module("changedetectionio.processors.text_json_diff.processor")
+            update_handler = processor_module.perform_site_check(datastore=datastore,
+                                                                 watch_uuid=uuid
+                                                                 )
+
+            update_handler.call_browser(preferred_proxy_id=preferred_proxy)
         # title, size is len contents not len xfer
         except content_fetcher_exceptions.Non200ErrorCodeReceived as e:
             if e.status_code == 404:
@@ -48,7 +54,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                 status.update({'status': 'ERROR', 'length': len(contents), 'text': f"{e.status_code} - Access denied"})
             else:
                 status.update({'status': 'ERROR', 'length': len(contents), 'text': f"Status code: {e.status_code}"})
-        except text_json_diff.FilterNotFoundInResponse:
+        except FilterNotFoundInResponse:
             status.update({'status': 'OK', 'length': len(contents), 'text': f"OK but CSS/xPath filter not found (page changed layout?)"})
         except content_fetcher_exceptions.EmptyReply as e:
             if e.status_code == 403 or e.status_code == 401:

changedetectionio/blueprint/price_data_follower/__init__.py

@@ -19,7 +19,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q: PriorityQueue
         datastore.data['watching'][uuid]['track_ldjson_price_data'] = PRICE_DATA_TRACK_ACCEPT
         datastore.data['watching'][uuid]['processor'] = 'restock_diff'
         datastore.data['watching'][uuid].clear_watch()
-        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
+        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
         return redirect(url_for("index"))
 
     @login_required

changedetectionio/content_fetchers/requests.py

@@ -75,6 +75,7 @@ class fetcher(Fetcher):
         self.headers = r.headers
 
         if not r.content or not len(r.content):
+            logger.debug(f"Requests returned empty content for '{url}'")
             if not empty_pages_are_a_change:
                 raise EmptyReply(url=url, status_code=r.status_code)
             else:

changedetectionio/forms.py

@@ -496,7 +496,7 @@ class processor_text_json_diff_form(commonSettingsForm):
     text_should_not_be_present = StringListField('Block change-detection while text matches', [validators.Optional(), ValidateListRegex()])
     webdriver_js_execute_code = TextAreaField('Execute JavaScript before change detection', render_kw={"rows": "5"}, validators=[validators.Optional()])
 
-    save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
+    save_button = SubmitField('Save', render_kw={"class": "pure-button button-small pure-button-primary"})
 
     proxy = RadioField('Proxy')
     filter_failure_notification_send = BooleanField(
@@ -616,7 +616,7 @@ class globalSettingsForm(Form):
 
     requests = FormField(globalSettingsRequestForm)
     application = FormField(globalSettingsApplicationForm)
-    save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
+    save_button = SubmitField('Save', render_kw={"class": "pure-button button-small pure-button-primary"})
 
 
 class extractDataForm(Form):

changedetectionio/processors/__init__.py

@@ -18,6 +18,7 @@ class difference_detection_processor():
     screenshot = None
     watch = None
     xpath_data = None
+    preferred_proxy = None
 
     def __init__(self, *args, datastore, watch_uuid, **kwargs):
         super().__init__(*args, **kwargs)
@@ -26,7 +27,8 @@ class difference_detection_processor():
         # Generic fetcher that should be extended (requests, playwright etc)
         self.fetcher = Fetcher()
 
-    def call_browser(self):
+    def call_browser(self, preferred_proxy_id=None):
+
         from requests.structures import CaseInsensitiveDict
 
         # Protect against file:// access
@@ -42,7 +44,7 @@ class difference_detection_processor():
         prefer_fetch_backend = self.watch.get('fetch_backend', 'system')
 
         # Proxy ID "key"
-        preferred_proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=self.watch.get('uuid'))
+        preferred_proxy_id = preferred_proxy_id if preferred_proxy_id else self.datastore.get_preferred_proxy_for_watch(uuid=self.watch.get('uuid'))
 
         # Pluggable content self.fetcher
         if not prefer_fetch_backend or prefer_fetch_backend == 'system':
@@ -155,7 +157,7 @@ class difference_detection_processor():
         # After init, call run_changedetection() which will do the actual change-detection
 
     @abstractmethod
-    def run_changedetection(self, watch, skip_when_checksum_same: bool = True):
+    def run_changedetection(self, watch):
         update_obj = {'last_notification_error': False, 'last_error': False}
         some_data = 'xxxxx'
         update_obj["previous_md5"] = hashlib.md5(some_data.encode('utf-8')).hexdigest()

changedetectionio/processors/restock_diff/processor.py

@@ -27,22 +27,27 @@ def _search_prop_by_value(matches, value):
                 return prop[1]  # Yield the desired value and exit the function
 
 def _deduplicate_prices(data):
-    seen = set()
-    unique_data = []
+    import re
 
+    '''
+    Some price data has multiple entries, OR it has a single entry with ['$159', '159', 159, "$ 159"] or just "159"
+    Get all the values, clean it and add it to a set then return the unique values
+    '''
+    unique_data = set()
+
+    # Return the complete 'datum' where its price was not seen before
     for datum in data:
-        # Convert 'value' to float if it can be a numeric string, otherwise leave it as is
-        try:
-            normalized_value = float(datum.value) if isinstance(datum.value, str) and datum.value.replace('.', '', 1).isdigit() else datum.value
-        except ValueError:
-            normalized_value = datum.value
 
-        # If the normalized value hasn't been seen yet, add it to unique data
-        if normalized_value not in seen:
-            unique_data.append(datum)
-            seen.add(normalized_value)
-    
-    return unique_data
+        if isinstance(datum.value, list):
+            # Process each item in the list
+            normalized_value = set([float(re.sub(r'[^\d.]', '', str(item))) for item in datum.value])
+            unique_data.update(normalized_value)
+        else:
+            # Process single value
+            v = float(re.sub(r'[^\d.]', '', str(datum.value)))
+            unique_data.add(v)
+
+    return list(unique_data)
 
 
 # should return Restock()
@@ -83,14 +88,13 @@ def get_itemprop_availability(html_content) -> Restock:
         if price_result:
             # Right now, we just support single product items, maybe we will store the whole actual metadata seperately in teh future and
             # parse that for the UI?
-            prices_found = set(str(item.value).replace('$', '') for item in price_result)
-            if len(price_result) > 1 and len(prices_found) > 1:
+            if len(price_result) > 1 and len(price_result) > 1:
                 # See of all prices are different, in the case that one product has many embedded data types with the same price
                 # One might have $121.95 and another 121.95 etc
-                logger.warning(f"More than one price found {prices_found}, throwing exception, cant use this plugin.")
+                logger.warning(f"More than one price found {price_result}, throwing exception, cant use this plugin.")
                 raise MoreThanOnePriceFound()
 
-            value['price'] = price_result[0].value
+            value['price'] = price_result[0]
 
         pricecurrency_result = pricecurrency_parse.find(data)
         if pricecurrency_result:
@@ -140,7 +144,7 @@ class perform_site_check(difference_detection_processor):
     screenshot = None
     xpath_data = None
 
-    def run_changedetection(self, watch, skip_when_checksum_same=True):
+    def run_changedetection(self, watch):
         import hashlib
 
         if not watch:
@@ -220,7 +224,7 @@ class perform_site_check(difference_detection_processor):
             itemprop_availability['original_price'] = itemprop_availability.get('price')
             update_obj['restock']["original_price"] = itemprop_availability.get('price')
 
-        if not self.fetcher.instock_data and not itemprop_availability.get('availability'):
+        if not self.fetcher.instock_data and not itemprop_availability.get('availability') and not itemprop_availability.get('price'):
             raise ProcessorException(
                 message=f"Unable to extract restock data for this page unfortunately. (Got code {self.fetcher.get_last_status_code()} from server), no embedded stock information was found and nothing interesting in the text, try using this watch with Chrome.",
                 url=watch.get('url'),

changedetectionio/processors/text_json_diff/__init__.py

@@ -11,10 +11,7 @@ def _task(watch, update_handler):
 
     try:
         # The slow process (we run 2 of these in parallel)
-        changed_detected, update_obj, text_after_filter = update_handler.run_changedetection(
-            watch=watch,
-            skip_when_checksum_same=False,
-        )
+        changed_detected, update_obj, text_after_filter = update_handler.run_changedetection(watch=watch)
     except FilterNotFoundInResponse as e:
         text_after_filter = f"Filter not found in HTML: {str(e)}"
     except ReplyWithContentButNoText as e:

changedetectionio/processors/text_json_diff/processor.py

@@ -35,7 +35,7 @@ class PDFToHTMLToolNotFound(ValueError):
 # (set_proxy_from_list)
 class perform_site_check(difference_detection_processor):
 
-    def run_changedetection(self, watch, skip_when_checksum_same=True):
+    def run_changedetection(self, watch):
         changed_detected = False
         html_content = ""
         screenshot = False  # as bytes
@@ -58,9 +58,6 @@ class perform_site_check(difference_detection_processor):
         # Watches added automatically in the queue manager will skip if its the same checksum as the previous run
         # Saves a lot of CPU
         update_obj['previous_md5_before_filters'] = hashlib.md5(self.fetcher.content.encode('utf-8')).hexdigest()
-        if skip_when_checksum_same:
-            if update_obj['previous_md5_before_filters'] == watch.get('previous_md5_before_filters'):
-                raise content_fetchers.exceptions.checksumFromPreviousCheckWasTheSame()
 
         # Fetching complete, now filters
 
@@ -211,6 +208,7 @@ class perform_site_check(difference_detection_processor):
         # @todo whitespace coming from missing rtrim()?
         # stripped_text_from_html could be based on their preferences, replace the processed text with only that which they want to know about.
         # Rewrite's the processing text based on only what diff result they want to see
+
         if watch.has_special_diff_filter_options_set() and len(watch.history.keys()):
             # Now the content comes from the diff-parser and not the returned HTTP traffic, so could be some differences
             from changedetectionio import diff
@@ -333,13 +331,21 @@ class perform_site_check(difference_detection_processor):
             if result:
                 blocked = True
 
-        # The main thing that all this at the moment comes down to :)
-        if watch.get('previous_md5') != fetched_md5:
-            changed_detected = True
 
         # Looks like something changed, but did it match all the rules?
         if blocked:
             changed_detected = False
+        else:
+            # The main thing that all this at the moment comes down to :)
+            if watch.get('previous_md5') != fetched_md5:
+                changed_detected = True
+
+            # Always record the new checksum
+            update_obj["previous_md5"] = fetched_md5
+
+            # On the first run of a site, watch['previous_md5'] will be None, set it the current one.
+            if not watch.get('previous_md5'):
+                watch['previous_md5'] = fetched_md5
 
         logger.debug(f"Watch UUID {watch.get('uuid')} content check - Previous MD5: {watch.get('previous_md5')}, Fetched MD5 {fetched_md5}")
 
@@ -359,12 +365,6 @@ class perform_site_check(difference_detection_processor):
                 else:
                     logger.debug(f"check_unique_lines: UUID {watch.get('uuid')} had unique content")
 
-        # Always record the new checksum
-        update_obj["previous_md5"] = fetched_md5
-
-        # On the first run of a site, watch['previous_md5'] will be None, set it the current one.
-        if not watch.get('previous_md5'):
-            watch['previous_md5'] = fetched_md5
 
         # stripped_text_from_html - Everything after filters and NO 'ignored' content
         return changed_detected, update_obj, stripped_text_from_html

changedetectionio/static/js/recheck-proxy.js

@@ -1,14 +1,14 @@
 $(function () {
     /* add container before each proxy location to show status */
-
-    var option_li = $('.fetch-backend-proxy li').filter(function() {
-        return $("input",this)[0].value.length >0;
-    });
-
-    //var option_li = $('.fetch-backend-proxy li');
     var isActive = false;
-    $(option_li).prepend('<div class="proxy-status"></div>');
-    $(option_li).append('<div class="proxy-timing"></div><div class="proxy-check-details"></div>');
+
+    function setup_html_widget() {
+        var option_li = $('.fetch-backend-proxy li').filter(function () {
+            return $("input", this)[0].value.length > 0;
+        });
+        $(option_li).prepend('<div class="proxy-status"></div>');
+        $(option_li).append('<div class="proxy-timing"></div><div class="proxy-check-details"></div>');
+    }
 
     function set_proxy_check_status(proxy_key, state) {
         // select input by value name
@@ -59,8 +59,14 @@ $(function () {
     }
 
     $('#check-all-proxies').click(function (e) {
+
         e.preventDefault()
-        $('body').addClass('proxy-check-active');
+
+        if (!$('body').hasClass('proxy-check-active')) {
+            setup_html_widget();
+            $('body').addClass('proxy-check-active');
+        }
+
         $('.proxy-check-details').html('');
         $('.proxy-status').html('<span class="spinner"></span>').fadeIn();
         $('.proxy-timing').html('');

changedetectionio/static/js/tabs.js

@@ -26,8 +26,7 @@ function set_active_tab() {
     if (tab.length) {
         tab[0].parentElement.className = "active";
     }
-    // hash could move the page down
-    window.scrollTo(0, 0);
+
 }
 
 function focus_error_tab() {

changedetectionio/static/styles/diff.css

@@ -153,7 +153,8 @@ html[data-darkmode="true"] {
     border: 1px solid transparent;
     vertical-align: top;
     font: 1em monospace;
-    text-align: left; }
+    text-align: left;
+    overflow: clip; }
   #diff-ui pre {
     white-space: pre-wrap; }
 
@@ -172,7 +173,9 @@ ins {
   text-decoration: none; }
 
 #result {
-  white-space: pre-wrap; }
+  white-space: pre-wrap;
+  word-break: break-word;
+  overflow-wrap: break-word; }
 
 #settings {
   background: rgba(0, 0, 0, 0.05);
@@ -231,3 +234,12 @@ td#diff-col div {
   border-radius: 5px;
   background: var(--color-background);
   box-shadow: 1px 1px 4px var(--color-shadow-jump); }
+
+.pure-form button.reset-margin {
+  margin: 0px; }
+
+.diff-fieldset {
+  display: flex;
+  align-items: center;
+  gap: 4px;
+  flex-wrap: wrap; }

changedetectionio/static/styles/scss/diff.scss

@@ -24,6 +24,7 @@
     vertical-align: top;
     font: 1em monospace;
     text-align: left;
+    overflow: clip; // clip overflowing contents to cell boundariess
   }
 
   pre {
@@ -50,6 +51,8 @@ ins {
 
 #result {
   white-space: pre-wrap;
+  word-break: break-word;
+  overflow-wrap: break-word;
 
   .change {
     span {}
@@ -134,3 +137,15 @@ td#diff-col div {
   background: var(--color-background);
   box-shadow: 1px 1px 4px var(--color-shadow-jump);
 }
+
+// resets button margin to 0px
+.pure-form button.reset-margin {
+  margin: 0px;
+}
+
+.diff-fieldset {
+  display: flex;
+  align-items: center;
+  gap: 4px;
+  flex-wrap: wrap;
+}

changedetectionio/static/styles/scss/parts/_extra_browsers.scss

@@ -11,7 +11,22 @@ ul#requests-extra_browsers {
   /* each proxy entry is a `table` */
   table {
     tr {
-      display: inline;
+      display: table-row; // default display for small screens
+      input[type=text] {
+        width: 100%;
+      }
+    }
+  }
+  
+  // apply inline display for larger screens
+  @media only screen and (min-width: 1280px) {
+    table {
+      tr {
+        display: inline;
+        input[type=text] {
+          width: 100%;
+        }
+      }
     }
   }
 }

changedetectionio/static/styles/scss/parts/_extra_proxies.scss

@@ -11,7 +11,19 @@ ul#requests-extra_proxies {
   /* each proxy entry is a `table` */
   table {
     tr {
-      display: inline;
+      display: table-row; // default display for small screens
+      input[type=text] {
+        width: 100%;
+      }
+    }
+  }
+  
+  // apply inline display for large screens
+  @media only screen and (min-width: 1024px) {
+    table {
+      tr {
+        display: inline;
+      }
     }
   }
 }
@@ -25,15 +37,19 @@ ul#requests-extra_proxies {
 
 body.proxy-check-active {
   #request {
+    // Padding set by flex layout
+    /*
     .proxy-status {
       width: 2em;
     }
+    */
 
     .proxy-check-details {
       font-size: 80%;
       color: #555;
       display: block;
-      padding-left: 4em;
+      padding-left: 2em;
+      max-width: 500px;
     }
 
     .proxy-timing {

changedetectionio/static/styles/scss/styles.scss

@@ -147,8 +147,14 @@ body.spinner-active {
   }
 }
 
+
+.tab-pane-inner {
+  // .tab-pane-inner will have the #id that the tab button jumps/anchors to
+  scroll-margin-top: 200px;
+}
+
 section.content {
-  padding-top: 5em;
+  padding-top: 100px;
   padding-bottom: 1em;
   flex-direction: column;
   display: flex;
@@ -931,6 +937,7 @@ $form-edge-padding: 20px;
 }
 
 .tab-pane-inner {
+
   &:not(:target) {
     display: none;
   }

changedetectionio/static/styles/styles.css

@@ -112,26 +112,34 @@ ul#requests-extra_proxies {
   ul#requests-extra_proxies li > label {
     display: none; }
   ul#requests-extra_proxies table tr {
-    display: inline; }
+    display: table-row; }
+    ul#requests-extra_proxies table tr input[type=text] {
+      width: 100%; }
+  @media only screen and (min-width: 1024px) {
+    ul#requests-extra_proxies table tr {
+      display: inline; } }
 
 #request {
   /* Auto proxy scan/checker */ }
   #request label[for=proxy] {
     display: inline-block; }
 
-body.proxy-check-active #request .proxy-status {
-  width: 2em; }
-
-body.proxy-check-active #request .proxy-check-details {
-  font-size: 80%;
-  color: #555;
-  display: block;
-  padding-left: 4em; }
-
-body.proxy-check-active #request .proxy-timing {
-  font-size: 80%;
-  padding-left: 1rem;
-  color: var(--color-link); }
+body.proxy-check-active #request {
+  /*
+    .proxy-status {
+      width: 2em;
+    }
+    */ }
+  body.proxy-check-active #request .proxy-check-details {
+    font-size: 80%;
+    color: #555;
+    display: block;
+    padding-left: 2em;
+    max-width: 500px; }
+  body.proxy-check-active #request .proxy-timing {
+    font-size: 80%;
+    padding-left: 1rem;
+    color: var(--color-link); }
 
 #recommended-proxy {
   display: grid;
@@ -158,7 +166,14 @@ ul#requests-extra_browsers {
   ul#requests-extra_browsers li > label {
     display: none; }
   ul#requests-extra_browsers table tr {
-    display: inline; }
+    display: table-row; }
+    ul#requests-extra_browsers table tr input[type=text] {
+      width: 100%; }
+  @media only screen and (min-width: 1280px) {
+    ul#requests-extra_browsers table tr {
+      display: inline; }
+      ul#requests-extra_browsers table tr input[type=text] {
+        width: 100%; } }
 
 #extra-browsers-setting {
   border: 1px solid var(--color-grey-800);
@@ -602,8 +617,11 @@ body.spinner-active #pure-menu-horizontal-spinner {
     background-color: var(--color-background-menu-link-hover);
     color: var(--color-text-menu-link-hover); }
 
+.tab-pane-inner {
+  scroll-margin-top: 200px; }
+
 section.content {
-  padding-top: 5em;
+  padding-top: 100px;
   padding-bottom: 1em;
   flex-direction: column;
   display: flex;

changedetectionio/templates/diff.html

@@ -14,7 +14,7 @@
 
 <div id="settings">
     <form class="pure-form " action="" method="GET" id="diff-form">
-        <fieldset>
+        <fieldset class="diff-fieldset">
             {% if versions|length >= 1 %}
                 <strong>Compare</strong>
                 <del class="change"><span>from</span></del>
@@ -33,7 +33,7 @@
                         </option>
                     {% endfor %}
                 </select>
-                <button type="submit" class="pure-button pure-button-primary">Go</button>
+                <button type="submit" class="pure-button pure-button-primary reset-margin">Go</button>
             {% endif %}
         </fieldset>
         <fieldset>

changedetectionio/templates/settings.html

@@ -276,7 +276,7 @@ nav
                 <div class="pure-control-group">
                     {{ render_button(form.save_button) }}
                     <a href="{{url_for('index')}}" class="pure-button button-small button-cancel">Back</a>
-                    <a href="{{url_for('clear_all_history')}}" class="pure-button button-small button-cancel">Clear Snapshot History</a>
+                    <a href="{{url_for('clear_all_history')}}" class="pure-button button-small button-error">Clear Snapshot History</a>
                 </div>
             </div>
         </form>

changedetectionio/tests/itemprop_test_examples/README.md

@@ -0,0 +1,6 @@
+# A list of real world examples!
+
+Always the price should be 666.66 for our tests
+
+see test_restock_itemprop.py::test_special_prop_examples
+

changedetectionio/tests/itemprop_test_examples/a.txt

@@ -0,0 +1,25 @@
+<div class="PriceSection PriceSection_PriceSection__Vx1_Q PriceSection_variantHuge__P9qxg PdpPriceSection"
+     data-testid="price-section"
+     data-optly-product-tile-price-section="true"><span
+        class="PriceRange ProductPrice variant-huge" itemprop="offers"
+        itemscope="" itemtype="http://schema.org/Offer"><div
+        class="VisuallyHidden_VisuallyHidden__VBD83">$155.55</div><span
+        aria-hidden="true" class="Price variant-huge" data-testid="price"
+        itemprop="price"><sup class="sup" data-testid="price-symbol"
+                              itemprop="priceCurrency" content="AUD">$</sup><span
+        class="dollars" data-testid="price-value" itemprop="price"
+        content="155.55">155.55</span><span class="extras"><span class="sup"
+                                                              data-testid="price-sup"></span></span></span></span>
+</div>
+
+<script type="application/ld+json">{
+                                "@type": "Product",
+                                "@context": "https://schema.org",
+                                "name": "test",
+                                "description": "test",
+                                "offers": {
+                                    "@type": "Offer",
+                                    "priceCurrency": "AUD",
+                                    "price": 155.55
+                                },
+                            }</script>

changedetectionio/tests/proxy_list/test_proxy.py

@@ -16,4 +16,4 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
     )
 
     assert b"1 Imported" in res.data
-    time.sleep(3)
+    wait_for_all_checks(client)

changedetectionio/tests/proxy_socks5/test_socks5_proxy.py

@@ -1,7 +1,8 @@
 #!/usr/bin/env python3
+import json
 import os
 from flask import url_for
-from changedetectionio.tests.util import live_server_setup, wait_for_all_checks
+from changedetectionio.tests.util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
 
 
 def set_response():
@@ -18,7 +19,6 @@ def set_response():
         f.write(data)
     time.sleep(1)
 
-
 def test_socks5(client, live_server, measure_memory_usage):
     live_server_setup(live_server)
     set_response()
@@ -79,3 +79,24 @@ def test_socks5(client, live_server, measure_memory_usage):
 
     # Should see the proper string
     assert "Awesome, you made it".encode('utf-8') in res.data
+
+    # PROXY CHECKER WIDGET CHECK - this needs more checking
+    uuid = extract_UUID_from_client(client)
+
+    res = client.get(
+        url_for("check_proxies.start_check", uuid=uuid),
+        follow_redirects=True
+    )
+    # It's probably already finished super fast :(
+    #assert b"RUNNING" in res.data
+    
+    wait_for_all_checks(client)
+    res = client.get(
+        url_for("check_proxies.get_recheck_status", uuid=uuid),
+        follow_redirects=True
+    )
+    assert b"OK" in res.data
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+

changedetectionio/tests/test_add_replace_remove_filter.py

@@ -77,6 +77,8 @@ def test_check_removed_line_contains_trigger(client, live_server, measure_memory
 
     # The trigger line is REMOVED,  this should trigger
     set_original(excluding='The golden line')
+
+    # Check in the processor here what's going on, its triggering empty-reply and no change.
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
@@ -151,7 +153,6 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
 
     # A line thats not the trigger should not trigger anything
     res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
-
     assert b'1 watches queued for rechecking.' in res.data
 
     wait_for_all_checks(client)
@@ -173,6 +174,5 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
         assert b'-Oh yes please-' in response
         assert '网站监测 内容更新了'.encode('utf-8') in response
 
-
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data

changedetectionio/tests/test_block_while_text_present.py

@@ -65,11 +65,8 @@ def test_check_block_changedetection_text_NOT_present(client, live_server, measu
     live_server_setup(live_server)
     # Use a mix of case in ZzZ to prove it works case-insensitive.
     ignore_text = "out of stoCk\r\nfoobar"
-
     set_original_ignore_response()
 
-    # Give the endpoint time to spin up
-    time.sleep(1)
 
     # Add our URL to the import page
     test_url = url_for('test_endpoint', _external=True)
@@ -127,13 +124,24 @@ def test_check_block_changedetection_text_NOT_present(client, live_server, measu
     assert b'unviewed' not in res.data
     assert b'/test-endpoint' in res.data
 
+    # 2548
+    # Going back to the ORIGINAL should NOT trigger a change
+    set_original_ignore_response()
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'unviewed' not in res.data
 
-    # Now we set a change where the text is gone, it should now trigger
+
+    # Now we set a change where the text is gone AND its different content, it should now trigger
     set_modified_response_minus_block_text()
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
 
+
+
+
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data

changedetectionio/tests/test_element_removal.py

@@ -5,7 +5,7 @@ import time
 from flask import url_for
 
 from ..html_tools import *
-from .util import live_server_setup
+from .util import live_server_setup, wait_for_all_checks
 
 
 def test_setup(live_server):
@@ -119,12 +119,10 @@ across multiple lines
 
 
 def test_element_removal_full(client, live_server, measure_memory_usage):
-    sleep_time_for_fetch_thread = 3
+    #live_server_setup(live_server)
 
     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", _external=True)
@@ -132,7 +130,8 @@ def test_element_removal_full(client, live_server, measure_memory_usage):
         url_for("import_page"), data={"urls": test_url}, follow_redirects=True
     )
     assert b"1 Imported" in res.data
-    time.sleep(1)
+    wait_for_all_checks(client)
+
     # Goto the edit page, add the filter data
     # Not sure why \r needs to be added - absent of the #changetext this is not necessary
     subtractive_selectors_data = "header\r\nfooter\r\nnav\r\n#changetext"
@@ -148,6 +147,7 @@ def test_element_removal_full(client, live_server, measure_memory_usage):
         follow_redirects=True,
     )
     assert b"Updated watch." in res.data
+    wait_for_all_checks(client)
 
     # Check it saved
     res = client.get(
@@ -156,10 +156,10 @@ def test_element_removal_full(client, live_server, measure_memory_usage):
     assert bytes(subtractive_selectors_data.encode("utf-8")) in res.data
 
     # Trigger a check
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    assert b'1 watches queued for rechecking.' in res.data
 
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
 
     # so that we set the state to 'unviewed' after all the edits
     client.get(url_for("diff_history_page", uuid="first"))
@@ -168,10 +168,11 @@ def test_element_removal_full(client, live_server, measure_memory_usage):
     set_modified_response()
 
     # Trigger a check
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    assert b'1 watches queued for rechecking.' in res.data
 
     # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
+    wait_for_all_checks(client)
 
     # There should not be an unviewed change, as changes should be removed
     res = client.get(url_for("index"))

changedetectionio/tests/test_live_preview.py

@@ -0,0 +1,78 @@
+#!/usr/bin/env python3
+
+from flask import url_for
+from changedetectionio.tests.util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+
+
+def set_response():
+
+    data = f"""<html>
+       <body>Awesome, you made it<br>
+yeah the socks request worked<br>
+something to ignore<br>
+something to trigger<br>
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(data)
+
+def test_content_filter_live_preview(client, live_server, measure_memory_usage):
+    live_server_setup(live_server)
+    set_response()
+
+    test_url = url_for('test_endpoint', _external=True)
+
+    res = client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": ''},
+        follow_redirects=True
+    )
+    uuid = extract_UUID_from_client(client)
+    res = client.post(
+        url_for("edit_page", uuid=uuid),
+        data={
+            "include_filters": "",
+            "fetch_backend": 'html_requests',
+            "ignore_text": "something to ignore",
+            "trigger_text": "something to trigger",
+            "url": test_url,
+        },
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    wait_for_all_checks(client)
+
+    # The endpoint is a POST and accepts the form values to override the watch preview
+    import json
+
+    # DEFAULT OUTPUT WITHOUT ANYTHING UPDATED/CHANGED - SHOULD SEE THE WATCH DEFAULTS
+    res = client.post(
+        url_for("watch_get_preview_rendered", uuid=uuid)
+    )
+    default_return = json.loads(res.data.decode('utf-8'))
+    assert default_return.get('after_filter')
+    assert default_return.get('before_filter')
+    assert default_return.get('ignore_line_numbers') == [3] # "something to ignore" line 3
+    assert default_return.get('trigger_line_numbers') == [4] # "something to trigger" line 4
+
+    # SEND AN UPDATE AND WE SHOULD SEE THE OUTPUT CHANGE SO WE KNOW TO HIGHLIGHT NEW STUFF
+    res = client.post(
+        url_for("watch_get_preview_rendered", uuid=uuid),
+        data={
+            "include_filters": "",
+            "fetch_backend": 'html_requests',
+            "ignore_text": "sOckS", # Also be sure case insensitive works
+            "trigger_text": "AweSOme",
+            "url": test_url,
+        },
+    )
+    reply = json.loads(res.data.decode('utf-8'))
+    assert reply.get('after_filter')
+    assert reply.get('before_filter')
+    assert reply.get('ignore_line_numbers') == [2]  # Ignored - "socks" on line 2
+    assert reply.get('trigger_line_numbers') == [1]  # Triggers "Awesome" in line 1
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

changedetectionio/tests/test_notification.py

@@ -429,3 +429,24 @@ def test_global_send_test_notification(client, live_server, measure_memory_usage
         follow_redirects=True
     )
 
+    #2727 - be sure a test notification when there are zero watches works ( should all be deleted now)
+
+    os.unlink("test-datastore/notification.txt")
+
+
+    ######### Test global/system settings
+    res = client.post(
+        url_for("ajax_callback_send_notification_test")+"?mode=global-settings",
+        data={"notification_urls": test_notification_url},
+        follow_redirects=True
+    )
+
+    assert res.status_code != 400
+    assert res.status_code != 500
+
+    # Give apprise time to fire
+    time.sleep(4)
+
+    with open("test-datastore/notification.txt", 'r') as f:
+        x = f.read()
+        assert 'change detection is cool 网站监测 内容更新了' in x

changedetectionio/tests/test_preview_endpoints.py

@@ -0,0 +1,72 @@
+#!/usr/bin/env python3
+
+import time
+from flask import url_for
+from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
+
+
+# `subtractive_selectors` should still work in `source:` type requests
+def test_fetch_pdf(client, live_server, measure_memory_usage):
+    import shutil
+    shutil.copy("tests/test.pdf", "test-datastore/endpoint-test.pdf")
+
+    live_server_setup(live_server)
+    test_url = url_for('test_pdf_endpoint', _external=True)
+    # Add our URL to the import page
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+
+    assert b"1 Imported" in res.data
+
+    wait_for_all_checks(client)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    # PDF header should not be there (it was converted to text)
+    assert b'PDF' not in res.data[:10]
+    assert b'hello world' in res.data
+
+    # So we know if the file changes in other ways
+    import hashlib
+    original_md5 = hashlib.md5(open("test-datastore/endpoint-test.pdf", 'rb').read()).hexdigest().upper()
+    # We should have one
+    assert len(original_md5) > 0
+    # And it's going to be in the document
+    assert b'Document checksum - ' + bytes(str(original_md5).encode('utf-8')) in res.data
+
+    shutil.copy("tests/test2.pdf", "test-datastore/endpoint-test.pdf")
+    changed_md5 = hashlib.md5(open("test-datastore/endpoint-test.pdf", 'rb').read()).hexdigest().upper()
+    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    assert b'1 watches queued for rechecking.' in res.data
+
+    wait_for_all_checks(client)
+
+    # Now something should be ready, indicated by having a 'unviewed' class
+    res = client.get(url_for("index"))
+    assert b'unviewed' in res.data
+
+    # The original checksum should be not be here anymore (cdio adds it to the bottom of the text)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    assert original_md5.encode('utf-8') not in res.data
+    assert changed_md5.encode('utf-8') in res.data
+
+    res = client.get(
+        url_for("diff_history_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    assert original_md5.encode('utf-8') in res.data
+    assert changed_md5.encode('utf-8') in res.data
+
+    assert b'here is a change' in res.data

changedetectionio/tests/test_restock_itemprop.py

@@ -3,7 +3,7 @@ import os
 import time
 
 from flask import url_for
-from .util import live_server_setup, wait_for_all_checks, extract_UUID_from_client, wait_for_notification_endpoint_output
+from .util import live_server_setup, wait_for_all_checks, wait_for_notification_endpoint_output
 from ..notification import default_notification_format
 
 instock_props = [
@@ -413,3 +413,31 @@ def test_data_sanity(client, live_server):
     res = client.get(
         url_for("edit_page", uuid="first"))
     assert test_url2.encode('utf-8') in res.data
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+# All examples should give a prive of 666.66
+def test_special_prop_examples(client, live_server):
+    import glob
+    #live_server_setup(live_server)
+
+    test_url = url_for('test_endpoint', _external=True)
+    check_path = os.path.join(os.path.dirname(__file__), "itemprop_test_examples", "*.txt")
+    files = glob.glob(check_path)
+    assert files
+    for test_example_filename in files:
+        with open(test_example_filename, 'r') as example_f:
+            with open("test-datastore/endpoint-content.txt", "w") as test_f:
+                test_f.write(f"<html><body>{example_f.read()}</body></html>")
+
+            # Now fetch it and check the price worked
+            client.post(
+                url_for("form_quick_watch_add"),
+                data={"url": test_url, "tags": 'restock tests', 'processor': 'restock_diff'},
+                follow_redirects=True
+            )
+            wait_for_all_checks(client)
+            res = client.get(url_for("index"))
+            assert b'ception' not in res.data
+            assert b'155.55' in res.data

changedetectionio/update_worker.py

@@ -19,11 +19,9 @@ from loguru import logger
 class update_worker(threading.Thread):
     current_uuid = None
 
-    def __init__(self, q, notification_q, app, datastore, *args, **kwargs):
-        self.q = q
+    def __init__(self, app, *args, **kwargs):
+
         self.app = app
-        self.notification_q = notification_q
-        self.datastore = datastore
         super().__init__(*args, **kwargs)
 
     def queue_notification_for_watch(self, notification_q, n_object, watch):
@@ -81,7 +79,8 @@ class update_worker(threading.Thread):
             'watch_url': watch.get('url') if watch else None,
         })
 
-        n_object.update(watch.extra_notification_token_values())
+        if watch:
+            n_object.update(watch.extra_notification_token_values())
 
         logger.trace(f"Main rendered notification placeholders (diff_added etc) calculated in {time.time()-now:.3f}s")
         logger.debug("Queued notification for sending")
@@ -101,19 +100,19 @@ class update_worker(threading.Thread):
         v = watch.get(var_name)
         if v and not watch.get('notification_muted'):
             if var_name == 'notification_format' and v == default_notification_format_for_watch:
-                return self.datastore.data['settings']['application'].get('notification_format')
+                return self.app.datastore.data['settings']['application'].get('notification_format')
 
             return v
 
-        tags = self.datastore.get_all_tags_for_watch(uuid=watch.get('uuid'))
+        tags = self.app.datastore.get_all_tags_for_watch(uuid=watch.get('uuid'))
         if tags:
             for tag_uuid, tag in tags.items():
                 v = tag.get(var_name)
                 if v and not tag.get('notification_muted'):
                     return v
 
-        if self.datastore.data['settings']['application'].get(var_name):
-            return self.datastore.data['settings']['application'].get(var_name)
+        if self.app.datastore.data['settings']['application'].get(var_name):
+            return self.app.datastore.data['settings']['application'].get(var_name)
 
         # Otherwise could be defaults
         if var_name == 'notification_format':
@@ -128,7 +127,7 @@ class update_worker(threading.Thread):
     def send_content_changed_notification(self, watch_uuid):
 
         n_object = {}
-        watch = self.datastore.data['watching'].get(watch_uuid)
+        watch = self.app.datastore.data['watching'].get(watch_uuid)
         if not watch:
             return
 
@@ -155,17 +154,17 @@ class update_worker(threading.Thread):
             queued = True
 
             count = watch.get('notification_alert_count', 0) + 1
-            self.datastore.update_watch(uuid=watch_uuid, update_obj={'notification_alert_count': count})
+            self.app.datastore.update_watch(uuid=watch_uuid, update_obj={'notification_alert_count': count})
 
-            self.queue_notification_for_watch(notification_q=self.notification_q, n_object=n_object, watch=watch)
+            self.queue_notification_for_watch(notification_q=self.app.notification_q, n_object=n_object, watch=watch)
 
         return queued
 
 
     def send_filter_failure_notification(self, watch_uuid):
 
-        threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts')
-        watch = self.datastore.data['watching'].get(watch_uuid)
+        threshold = self.app.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts')
+        watch = self.app.datastore.data['watching'].get(watch_uuid)
         if not watch:
             return
 
@@ -178,8 +177,8 @@ class update_worker(threading.Thread):
         if len(watch['notification_urls']):
             n_object['notification_urls'] = watch['notification_urls']
 
-        elif len(self.datastore.data['settings']['application']['notification_urls']):
-            n_object['notification_urls'] = self.datastore.data['settings']['application']['notification_urls']
+        elif len(self.app.datastore.data['settings']['application']['notification_urls']):
+            n_object['notification_urls'] = self.app.datastore.data['settings']['application']['notification_urls']
 
         # Only prepare to notify if the rules above matched
         if 'notification_urls' in n_object:
@@ -188,16 +187,16 @@ class update_worker(threading.Thread):
                 'uuid': watch_uuid,
                 'screenshot': None
             })
-            self.notification_q.put(n_object)
+            self.app.notification_q.put(n_object)
             logger.debug(f"Sent filter not found notification for {watch_uuid}")
         else:
             logger.debug(f"NOT sending filter not found notification for {watch_uuid} - no notification URLs")
 
     def send_step_failure_notification(self, watch_uuid, step_n):
-        watch = self.datastore.data['watching'].get(watch_uuid, False)
+        watch = self.app.datastore.data['watching'].get(watch_uuid, False)
         if not watch:
             return
-        threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts')
+        threshold = self.app.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts')
         n_object = {'notification_title': "Changedetection.io - Alert - Browser step at position {} could not be run".format(step_n+1),
                     'notification_body': "Your configured browser step at position {} for {{{{watch_url}}}} "
                                          "did not appear on the page after {} attempts, did the page change layout? "
@@ -208,8 +207,8 @@ class update_worker(threading.Thread):
         if len(watch['notification_urls']):
             n_object['notification_urls'] = watch['notification_urls']
 
-        elif len(self.datastore.data['settings']['application']['notification_urls']):
-            n_object['notification_urls'] = self.datastore.data['settings']['application']['notification_urls']
+        elif len(self.app.datastore.data['settings']['application']['notification_urls']):
+            n_object['notification_urls'] = self.app.datastore.data['settings']['application']['notification_urls']
 
         # Only prepare to notify if the rules above matched
         if 'notification_urls' in n_object:
@@ -217,7 +216,7 @@ class update_worker(threading.Thread):
                 'watch_url': watch['url'],
                 'uuid': watch_uuid
             })
-            self.notification_q.put(n_object)
+            self.app.notification_q.put(n_object)
             logger.error(f"Sent step not found notification for {watch_uuid}")
 
 
@@ -225,7 +224,7 @@ class update_worker(threading.Thread):
         # 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)
+            full_path = os.path.join(self.app.datastore.datastore_path, uuid, f)
             if os.path.isfile(full_path):
                 os.unlink(full_path)
 
@@ -236,23 +235,23 @@ class update_worker(threading.Thread):
             update_handler = None
 
             try:
-                queued_item_data = self.q.get(block=False)
+                queued_item_data = self.app.update_q.get(block=False)
             except queue.Empty:
                 pass
 
             else:
                 uuid = queued_item_data.item.get('uuid')
                 self.current_uuid = uuid
-                if uuid in list(self.datastore.data['watching'].keys()) and self.datastore.data['watching'][uuid].get('url'):
+                if uuid in list(self.app.datastore.data['watching'].keys()) and self.app.datastore.data['watching'][uuid].get('url'):
                     changed_detected = False
                     contents = b''
                     process_changedetection_results = True
                     update_obj = {}
 
                     # Clear last errors (move to preflight func?)
-                    self.datastore.data['watching'][uuid]['browser_steps_last_error_step'] = None
+                    self.app.datastore.data['watching'][uuid]['browser_steps_last_error_step'] = None
 
-                    watch = self.datastore.data['watching'].get(uuid)
+                    watch = self.app.datastore.data['watching'].get(uuid)
 
                     logger.info(f"Processing watch UUID {uuid} Priority {queued_item_data.priority} URL {watch['url']}")
                     now = time.time()
@@ -260,9 +259,6 @@ class update_worker(threading.Thread):
                     try:
                         # Processor is what we are using for detecting the "Change"
                         processor = watch.get('processor', 'text_json_diff')
-                        # Abort processing when the content was the same as the last fetch
-                        skip_when_same_checksum = queued_item_data.item.get('skip_when_checksum_same')
-
 
                         # Init a new 'difference_detection_processor', first look in processors
                         processor_module_name = f"changedetectionio.processors.{processor}.processor"
@@ -272,16 +268,13 @@ class update_worker(threading.Thread):
                             print(f"Processor module '{processor}' not found.")
                             raise e
 
-                        update_handler = processor_module.perform_site_check(datastore=self.datastore,
+                        update_handler = processor_module.perform_site_check(datastore=self.app.datastore,
                                                                              watch_uuid=uuid
                                                                              )
 
                         update_handler.call_browser()
 
-                        changed_detected, update_obj, contents = update_handler.run_changedetection(
-                            watch=watch,
-                            skip_when_checksum_same=skip_when_same_checksum,
-                        )
+                        changed_detected, update_obj, contents = update_handler.run_changedetection(watch=watch)
 
                         # Re #342
                         # In Python 3, all strings are sequences of Unicode characters. There is a bytes type that holds raw bytes.
@@ -299,7 +292,7 @@ class update_worker(threading.Thread):
                             watch.save_screenshot(screenshot=e.screenshot)
                         if e.xpath_data:
                             watch.save_xpath_data(data=e.xpath_data)
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': e.message})
+                        self.app.datastore.update_watch(uuid=uuid, update_obj={'last_error': e.message})
                         process_changedetection_results = False
 
                     except content_fetchers_exceptions.ReplyWithContentButNoText as e:
@@ -316,7 +309,7 @@ class update_worker(threading.Thread):
                             else:
                                 extra_help = ", it's possible that the filters were found, but contained no usable text."
 
-                        self.datastore.update_watch(uuid=uuid, update_obj={
+                        self.app.datastore.update_watch(uuid=uuid, update_obj={
                             'last_error': f"Got HTML content but no text found (With {e.status_code} reply code){extra_help}"
                         })
 
@@ -348,15 +341,15 @@ class update_worker(threading.Thread):
                         if e.page_text:
                             watch.save_error_text(contents=e.page_text)
 
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
+                        self.app.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
                         process_changedetection_results = False
 
                     except FilterNotFoundInResponse as e:
-                        if not self.datastore.data['watching'].get(uuid):
+                        if not self.app.datastore.data['watching'].get(uuid):
                             continue
 
                         err_text = "Warning, no filters were found, no change detection ran - Did the page change layout? update your Visual Filter if necessary."
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
+                        self.app.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
 
                         # Filter wasnt found, but we should still update the visual selector so that they can have a chance to set it up again
                         if e.screenshot:
@@ -370,7 +363,7 @@ class update_worker(threading.Thread):
                             c = watch.get('consecutive_filter_failures', 0)
                             c += 1
                             # Send notification if we reached the threshold?
-                            threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts', 0)
+                            threshold = self.app.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts', 0)
                             logger.debug(f"Filter for {uuid} not found, consecutive_filter_failures: {c} of threshold {threshold}")
                             if c >= threshold:
                                 if not watch.get('notification_muted'):
@@ -379,7 +372,7 @@ class update_worker(threading.Thread):
                                 c = 0
                                 logger.debug(f"Reset filter failure count back to zero")
 
-                            self.datastore.update_watch(uuid=uuid, update_obj={'consecutive_filter_failures': c})
+                            self.app.datastore.update_watch(uuid=uuid, update_obj={'consecutive_filter_failures': c})
                         else:
                             logger.trace(f"{uuid} - filter_failure_notification_send not enabled, skipping")
 
@@ -391,20 +384,20 @@ class update_worker(threading.Thread):
                         process_changedetection_results = False
                         changed_detected = False
                     except content_fetchers_exceptions.BrowserConnectError as e:
-                        self.datastore.update_watch(uuid=uuid,
+                        self.app.datastore.update_watch(uuid=uuid,
                                                     update_obj={'last_error': e.msg
                                                                 }
                                                     )
                         process_changedetection_results = False
                     except content_fetchers_exceptions.BrowserFetchTimedOut as e:
-                        self.datastore.update_watch(uuid=uuid,
+                        self.app.datastore.update_watch(uuid=uuid,
                                                     update_obj={'last_error': e.msg
                                                                 }
                                                     )
                         process_changedetection_results = False
                     except content_fetchers_exceptions.BrowserStepsStepException as e:
 
-                        if not self.datastore.data['watching'].get(uuid):
+                        if not self.app.datastore.data['watching'].get(uuid):
                             continue
 
                         error_step = e.step_n + 1
@@ -422,7 +415,7 @@ class update_worker(threading.Thread):
 
                         logger.debug(f"BrowserSteps exception at step {error_step} {str(e.original_e)}")
 
-                        self.datastore.update_watch(uuid=uuid,
+                        self.app.datastore.update_watch(uuid=uuid,
                                                     update_obj={'last_error': err_text,
                                                                 'browser_steps_last_error_step': error_step
                                                                 }
@@ -432,7 +425,7 @@ class update_worker(threading.Thread):
                             c = watch.get('consecutive_filter_failures', 0)
                             c += 1
                             # Send notification if we reached the threshold?
-                            threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts',
+                            threshold = self.app.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts',
                                                                                            0)
                             logger.error(f"Step for {uuid} not found, consecutive_filter_failures: {c}")
                             if threshold > 0 and c >= threshold:
@@ -440,26 +433,26 @@ class update_worker(threading.Thread):
                                     self.send_step_failure_notification(watch_uuid=uuid, step_n=e.step_n)
                                 c = 0
 
-                            self.datastore.update_watch(uuid=uuid, update_obj={'consecutive_filter_failures': c})
+                            self.app.datastore.update_watch(uuid=uuid, update_obj={'consecutive_filter_failures': c})
 
                         process_changedetection_results = False
 
                     except content_fetchers_exceptions.EmptyReply as e:
                         # Some kind of custom to-str handler in the exception handler that does this?
                         err_text = "EmptyReply - try increasing 'Wait seconds before extracting text', Status Code {}".format(e.status_code)
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
+                        self.app.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
                     except content_fetchers_exceptions.ScreenshotUnavailable as e:
                         err_text = "Screenshot unavailable, page did not render fully in the expected time or page was too long - try increasing 'Wait seconds before extracting text'"
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
+                        self.app.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
                     except content_fetchers_exceptions.JSActionExceptions as e:
                         err_text = "Error running JS Actions - Page request - "+e.message
                         if e.screenshot:
                             watch.save_screenshot(screenshot=e.screenshot, as_error=True)
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
+                        self.app.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code})
                         process_changedetection_results = False
                     except content_fetchers_exceptions.PageUnloadable as e:
@@ -470,26 +463,26 @@ class update_worker(threading.Thread):
                         if e.screenshot:
                             watch.save_screenshot(screenshot=e.screenshot, as_error=True)
 
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
+                        self.app.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
                                                                            'last_check_status': e.status_code,
                                                                            'has_ldjson_price_data': None})
                         process_changedetection_results = False
                     except content_fetchers_exceptions.BrowserStepsInUnsupportedFetcher as e:
                         err_text = "This watch has Browser Steps configured and so it cannot run with the 'Basic fast Plaintext/HTTP Client', either remove the Browser Steps or select a Chrome fetcher."
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
+                        self.app.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
                         process_changedetection_results = False
                         logger.error(f"Exception (BrowserStepsInUnsupportedFetcher) reached processing watch UUID: {uuid}")
 
                     except Exception as e:
                         logger.error(f"Exception reached processing watch UUID: {uuid}")
                         logger.error(str(e))
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': "Exception: " + str(e)})
+                        self.app.datastore.update_watch(uuid=uuid, update_obj={'last_error': "Exception: " + str(e)})
                         # Other serious error
                         process_changedetection_results = False
 
                     else:
                         # 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):
+                        if not self.app.datastore.data['watching'].get(uuid):
                             continue
 
                         update_obj['content-type'] = update_handler.fetcher.get_all_headers().get('content-type', '').lower()
@@ -503,14 +496,14 @@ class update_worker(threading.Thread):
 
                         self.cleanup_error_artifacts(uuid)
 
-                    if not self.datastore.data['watching'].get(uuid):
+                    if not self.app.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:
 
                         # Extract <title> as title if possible/requested.
-                        if self.datastore.data['settings']['application'].get('extract_title_as_title') or watch['extract_title_as_title']:
+                        if self.app.datastore.data['settings']['application'].get('extract_title_as_title') or watch['extract_title_as_title']:
                             if not watch['title'] or not len(watch['title']):
                                 try:
                                     update_obj['title'] = html_tools.extract_element(find='title', html_content=update_handler.fetcher.content)
@@ -521,7 +514,7 @@ class update_worker(threading.Thread):
                         # Now update after running everything
                         timestamp = round(time.time())
                         try:
-                            self.datastore.update_watch(uuid=uuid, update_obj=update_obj)
+                            self.app.datastore.update_watch(uuid=uuid, update_obj=update_obj)
 
 
                             # Also save the snapshot on the first time checked, "last checked" will always be updated, so we just check history length.
@@ -559,7 +552,7 @@ class update_worker(threading.Thread):
                             # Catch everything possible here, so that if a worker crashes, we don't lose it until restart!
                             logger.critical("!!!! Exception in update_worker while processing process_changedetection_results !!!")
                             logger.critical(str(e))
-                            self.datastore.update_watch(uuid=uuid, update_obj={'last_error': str(e)})
+                            self.app.datastore.update_watch(uuid=uuid, update_obj={'last_error': str(e)})
 
 
                     # Always record that we atleast tried
@@ -568,13 +561,13 @@ class update_worker(threading.Thread):
                     # Record the 'server' header reply, can be used for actions in the future like cloudflare/akamai workarounds
                     try:
                         server_header = update_handler.fetcher.headers.get('server', '').strip().lower()[:255]
-                        self.datastore.update_watch(uuid=uuid,
+                        self.app.datastore.update_watch(uuid=uuid,
                                                     update_obj={'remote_server_reply': server_header}
                                                     )
                     except Exception as e:
                         pass
 
-                    self.datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - now, 3),
+                    self.app.datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - now, 3),
                                                                        'last_checked': round(time.time()),
                                                                        'check_count': count
                                                                        })

requirements.txt

@@ -82,7 +82,7 @@ pytest-flask ~=1.2
 # Anything 4.0 and up but not 5.0
 jsonschema ~= 4.0
 
-
+apscheduler ~= 3.9
 loguru
 
 # For scraping all possible metadata relating to products so we can do better restock detection