0.39.10

README.md

@@ -15,13 +15,19 @@ Open source web page monitoring, notification and change detection.
 <img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />
 
 
-**Get your own instance now on Lemonade!**
+**Get your own private instance now! Let us host it for you!**
 
 [![Deploy to Lemonade](https://lemonade.changedetection.io/static/images/lemonade.svg)](https://lemonade.changedetection.io/start)
 
+
+[_Let us host your own private instance - We accept PayPal and Bitcoin, Support the further development of changedetection.io!_](https://lemonade.changedetection.io/start)
+
+
+
 - Automatic Updates, Automatic Backups, No Heroku "paused application", don't miss a change!
 - Javascript browser included
-- Pay with Bitcoin
+- Unlimited checks and watches!
+
 
 #### Example use cases
 
@@ -99,6 +105,8 @@ See the wiki for more information https://github.com/dgtlmoon/changedetection.io
 ## Filters
 XPath, JSONPath and CSS support comes baked in! You can be as specific as you need, use XPath exported from various XPath element query creation tools.
 
+(We support LXML re:test, re:math and re:replace.)
+
 ## Notifications
 
 ChangeDetection.io supports a massive amount of notifications (including email, office365, custom APIs, etc) when a web-page has a change detected thanks to the <a href="https://github.com/caronc/apprise">apprise</a> library.

changedetectionio/__init__.py

@@ -36,7 +36,9 @@ from flask import (
 )
 from flask_login import login_required
 
-__version__ = '0.39.8'
+from changedetectionio import html_tools
+
+__version__ = '0.39.10'
 
 datastore = None
 
@@ -126,7 +128,7 @@ def _jinja2_filter_datetimestamp(timestamp, format="%Y-%m-%d %H:%M:%S"):
     # return timeago.format(timestamp, time.time())
     # return datetime.datetime.utcfromtimestamp(timestamp).strftime(format)
 
-
+# When nobody is logged in Flask-Login's current_user is set to an AnonymousUser object.
 class User(flask_login.UserMixin):
     id=None
 
@@ -135,7 +137,6 @@ class User(flask_login.UserMixin):
     def get_user(self, email="defaultuser@changedetection.io"):
         return self
     def is_authenticated(self):
-
         return True
     def is_active(self):
         return True
@@ -214,6 +215,10 @@ def changedetection_app(config=None, datastore_o=None):
             return redirect(url_for('index'))
 
         if request.method == 'GET':
+            if flask_login.current_user.is_authenticated:
+                flash("Already logged in")
+                return redirect(url_for("index"))
+
             output = render_template("login.html")
             return output
 
@@ -249,6 +254,11 @@ def changedetection_app(config=None, datastore_o=None):
         # (No password in settings or env var)
         app.config['LOGIN_DISABLED'] = datastore.data['settings']['application']['password'] == False and os.getenv("SALTED_PASS", False) == False
 
+        # Set the auth cookie path if we're running as X-settings/X-Forwarded-Prefix
+        if os.getenv('USE_X_SETTINGS') and 'X-Forwarded-Prefix' in request.headers:
+            app.config['REMEMBER_COOKIE_PATH'] = request.headers['X-Forwarded-Prefix']
+            app.config['SESSION_COOKIE_PATH'] = request.headers['X-Forwarded-Prefix']
+
         # For the RSS path, allow access via a token
         if request.path == '/rss' and request.args.get('token'):
             app_rss_token = datastore.data['settings']['application']['rss_access_token']
@@ -367,7 +377,10 @@ def changedetection_app(config=None, datastore_o=None):
                                  tags=existing_tags,
                                  active_tag=limit_tag,
                                  app_rss_token=datastore.data['settings']['application']['rss_access_token'],
-                                 has_unviewed=datastore.data['has_unviewed'])
+                                 has_unviewed=datastore.data['has_unviewed'],
+                                 # Don't link to hosting when we're on the hosting environment
+                                 hosted_sticky=os.getenv("SALTED_PASS", False) == False,
+                                 guid=datastore.data['app_guid'])
 
         return output
 
@@ -441,7 +454,7 @@ def changedetection_app(config=None, datastore_o=None):
                 raw_content = file.read()
 
                 handler = fetch_site_status.perform_site_check(datastore=datastore)
-                stripped_content = handler.strip_ignore_text(raw_content,
+                stripped_content = html_tools.strip_ignore_text(raw_content,
                                                              datastore.data['watching'][uuid]['ignore_text'])
 
                 if datastore.data['settings']['application'].get('ignore_whitespace', False):
@@ -514,6 +527,7 @@ def changedetection_app(config=None, datastore_o=None):
 
 
             datastore.data['watching'][uuid]['css_filter'] = form.css_filter.data.strip()
+            datastore.data['watching'][uuid]['subtractive_selectors'] = form.subtractive_selectors.data
 
             # Reset the previous_md5 so we process a new snapshot including stripping ignore text.
             if form.css_filter.data.strip() != datastore.data['watching'][uuid]['css_filter']:
@@ -546,10 +560,14 @@ def changedetection_app(config=None, datastore_o=None):
                     flash('No notification URLs set, cannot send test.', 'error')
 
             # Diff page [edit] link should go back to diff page
-            if request.args.get("next") and request.args.get("next") == 'diff':
+            if request.args.get("next") and request.args.get("next") == 'diff' and not form.save_and_preview_button.data:
                 return redirect(url_for('diff_history_page', uuid=uuid))
             else:
-                return redirect(url_for('index'))
+                if form.save_and_preview_button.data:
+                    flash('You may need to reload this page to see the new content.')
+                    return redirect(url_for('preview_page', uuid=uuid))
+                else:
+                    return redirect(url_for('index'))
 
         else:
             if request.method == 'POST' and not form.validate():
@@ -582,6 +600,7 @@ def changedetection_app(config=None, datastore_o=None):
         if request.method == 'GET':
             form.minutes_between_check.data = int(datastore.data['settings']['requests']['minutes_between_check'])
             form.notification_urls.data = datastore.data['settings']['application']['notification_urls']
+            form.global_subtractive_selectors.data = datastore.data['settings']['application']['global_subtractive_selectors']
             form.global_ignore_text.data = datastore.data['settings']['application']['global_ignore_text']
             form.ignore_whitespace.data = datastore.data['settings']['application']['ignore_whitespace']
             form.extract_title_as_title.data = datastore.data['settings']['application']['extract_title_as_title']
@@ -610,6 +629,7 @@ def changedetection_app(config=None, datastore_o=None):
             datastore.data['settings']['application']['notification_format'] = form.notification_format.data
             datastore.data['settings']['application']['notification_urls'] = form.notification_urls.data
             datastore.data['settings']['application']['base_url'] = form.base_url.data
+            datastore.data['settings']['application']['global_subtractive_selectors'] = form.global_subtractive_selectors.data
             datastore.data['settings']['application']['global_ignore_text'] =  form.global_ignore_text.data
             datastore.data['settings']['application']['ignore_whitespace'] = form.ignore_whitespace.data
 
@@ -721,8 +741,12 @@ def changedetection_app(config=None, datastore_o=None):
         # Save the current newest history as the most recently viewed
         datastore.set_last_viewed(uuid, dates[0])
         newest_file = watch['history'][dates[0]]
-        with open(newest_file, 'r') as f:
-            newest_version_file_contents = f.read()
+
+        try:
+            with open(newest_file, 'r') as f:
+                newest_version_file_contents = f.read()
+        except Exception as e:
+            newest_version_file_contents = "Unable to read {}.\n".format(newest_file)
 
         previous_version = request.args.get('previous_version')
         try:
@@ -731,8 +755,11 @@ def changedetection_app(config=None, datastore_o=None):
             # Not present, use a default value, the second one in the sorted list.
             previous_file = watch['history'][dates[1]]
 
-        with open(previous_file, 'r') as f:
-            previous_version_file_contents = f.read()
+        try:
+            with open(previous_file, 'r') as f:
+                previous_version_file_contents = f.read()
+        except Exception as e:
+            previous_version_file_contents = "Unable to read {}.\n".format(previous_file)
 
         output = render_template("diff.html", watch_a=watch,
                                  newest=newest_version_file_contents,
@@ -744,13 +771,16 @@ def changedetection_app(config=None, datastore_o=None):
                                  current_previous_version=str(previous_version),
                                  current_diff_url=watch['url'],
                                  extra_title=" - Diff - {}".format(watch['title'] if watch['title'] else watch['url']),
-                                 left_sticky= True )
+                                 left_sticky=True)
 
         return output
 
     @app.route("/preview/<string:uuid>", methods=['GET'])
     @login_required
     def preview_page(uuid):
+        content = []
+        ignored_line_numbers = []
+        trigger_line_numbers = []
 
         # More for testing, possible to return the first/only
         if uuid == 'first':
@@ -764,14 +794,51 @@ def changedetection_app(config=None, datastore_o=None):
             flash("No history found for the specified link, bad link?", "error")
             return redirect(url_for('index'))
 
-        newest = list(watch['history'].keys())[-1]
-        with open(watch['history'][newest], 'r') as f:
-            content = f.readlines()
+        if len(watch['history']):
+            timestamps = sorted(watch['history'].keys(), key=lambda x: int(x))
+            filename = watch['history'][timestamps[-1]]
+            try:
+                with open(filename, 'r') as f:
+                    tmp = f.readlines()
+
+                    # Get what needs to be highlighted
+                    ignore_rules = watch.get('ignore_text', []) + datastore.data['settings']['application']['global_ignore_text']
+
+                    # .readlines will keep the \n, but we will parse it here again, in the future tidy this up
+                    ignored_line_numbers = html_tools.strip_ignore_text(content="".join(tmp),
+                                                                        wordlist=ignore_rules,
+                                                                        mode='line numbers'
+                                                                        )
+
+                    trigger_line_numbers = html_tools.strip_ignore_text(content="".join(tmp),
+                                                                        wordlist=watch['trigger_text'],
+                                                                        mode='line numbers'
+                                                                        )
+                    # Prepare the classes and lines used in the template
+                    i=0
+                    for l in tmp:
+                        classes=[]
+                        i+=1
+                        if i in ignored_line_numbers:
+                            classes.append('ignored')
+                        if i in trigger_line_numbers:
+                            classes.append('triggered')
+                        content.append({'line': l, 'classes': ' '.join(classes)})
+
+
+            except Exception as e:
+                content.append({'line': "File doesnt exist or unable to read file {}".format(filename), 'classes': ''})
+        else:
+            content.append({'line': "No history found", 'classes': ''})
+
 
         output = render_template("preview.html",
                                  content=content,
                                  extra_stylesheets=extra_stylesheets,
+                                 ignored_line_numbers=ignored_line_numbers,
+                                 triggered_line_numbers=trigger_line_numbers,
                                  current_diff_url=watch['url'],
+                                 watch=watch,
                                  uuid=uuid)
         return output
 
@@ -783,6 +850,7 @@ def changedetection_app(config=None, datastore_o=None):
                                  logs=notification_debug_log if len(notification_debug_log) else ["No errors or warnings detected"])
 
         return output
+
     @app.route("/api/<string:uuid>/snapshot/current", methods=['GET'])
     @login_required
     def api_snapshot(uuid):
@@ -1066,22 +1134,42 @@ def ticker_thread_check_time_launch_checks():
                 running_uuids.append(t.current_uuid)
 
         # Re #232 - Deepcopy the data incase it changes while we're iterating through it all
-        copied_datastore = deepcopy(datastore)
+        while True:
+            try:
+                copied_datastore = deepcopy(datastore)
+            except RuntimeError as e:
+                # RuntimeError: dictionary changed size during iteration
+                time.sleep(0.1)
+            else:
+                break
+
+        # Re #438 - Don't place more watches in the queue to be checked if the queue is already large
+        while update_q.qsize() >= 2000:
+            time.sleep(1)
 
         # Check for watches outside of the time threshold to put in the thread queue.
+        now = time.time()
+        max_system_wide = int(copied_datastore.data['settings']['requests']['minutes_between_check']) * 60
+
         for uuid, watch in copied_datastore.data['watching'].items():
+
+            # No need todo further processing if it's paused
+            if watch['paused']:
+                continue
+
             # If they supplied an individual entry minutes to threshold.
-            if 'minutes_between_check' in watch and watch['minutes_between_check'] is not None:
+            watch_minutes_between_check = watch.get('minutes_between_check', None)
+            if watch_minutes_between_check is not None:
                 # Cast to int just incase
-                max_time = int(watch['minutes_between_check']) * 60
+                max_time = int(watch_minutes_between_check) * 60
             else:
                 # Default system wide.
-                max_time = int(copied_datastore.data['settings']['requests']['minutes_between_check']) * 60
+                max_time = max_system_wide
 
-            threshold = time.time() - max_time
+            threshold = now - max_time
 
-            # Yeah, put it in the queue, it's more than time.
-            if not watch['paused'] and watch['last_checked'] <= threshold:
+            # Yeah, put it in the queue, it's more than time
+            if watch['last_checked'] <= threshold:
                 if not uuid in running_uuids and uuid not in update_q.queue:
                     update_q.put(uuid)
 

changedetectionio/fetch_site_status.py

@@ -1,10 +1,11 @@
-import time
-from changedetectionio import content_fetcher
 import hashlib
-from inscriptis import get_text
-import urllib3
-from . import html_tools
 import re
+import time
+
+import urllib3
+from inscriptis import get_text
+
+from changedetectionio import content_fetcher, html_tools
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
@@ -16,40 +17,6 @@ class perform_site_check():
         super().__init__(*args, **kwargs)
         self.datastore = datastore
 
-    def strip_ignore_text(self, content, list_ignore_text):
-        import re
-        ignore = []
-        ignore_regex = []
-        for k in list_ignore_text:
-
-            # Is it a regex?
-            if k[0] == '/':
-                ignore_regex.append(k.strip(" /"))
-            else:
-                ignore.append(k)
-
-        output = []
-        for line in content.splitlines():
-
-            # Always ignore blank lines in this mode. (when this function gets called)
-            if len(line.strip()):
-                regex_matches = False
-
-                # if any of these match, skip
-                for regex in ignore_regex:
-                    try:
-                        if re.search(regex, line, re.IGNORECASE):
-                            regex_matches = True
-                    except Exception as e:
-                        continue
-
-                if not regex_matches and not any(skip_text in line for skip_text in ignore):
-                    output.append(line.encode('utf8'))
-
-        return "\n".encode('utf8').join(output)
-
-
-
     def run(self, uuid):
         timestamp = int(time.time())  # used for storage etc too
 
@@ -102,11 +69,18 @@ class perform_site_check():
             # https://stackoverflow.com/questions/41817578/basic-method-chaining ?
             # return content().textfilter().jsonextract().checksumcompare() ?
 
-            is_json = fetcher.headers.get('Content-Type', '') == 'application/json'
+            is_json = 'application/json' in fetcher.headers.get('Content-Type', '')
             is_html = not is_json
             css_filter_rule = watch['css_filter']
+            subtractive_selectors = watch.get(
+                "subtractive_selectors", []
+            ) + self.datastore.data["settings"]["application"].get(
+                "global_subtractive_selectors", []
+            )
 
             has_filter_rule = css_filter_rule and len(css_filter_rule.strip())
+            has_subtractive_selectors = subtractive_selectors and len(subtractive_selectors[0].strip())
+            
             if is_json and not has_filter_rule:
                 css_filter_rule = "json:$"
                 has_filter_rule = True
@@ -119,8 +93,13 @@ class perform_site_check():
             if is_html:
                 # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
                 html_content = fetcher.content
-                if not fetcher.headers.get('Content-Type', '') == 'text/plain':
 
+                # If not JSON,  and if it's not text/plain..
+                if 'text/plain' in fetcher.headers.get('Content-Type', '').lower():
+                    # Don't run get_text or xpath/css filters on plaintext
+                    stripped_text_from_html = html_content
+                else:
+                    # Then we assume HTML
                     if has_filter_rule:
                         # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
                         if css_filter_rule[0] == '/':
@@ -128,12 +107,10 @@ class perform_site_check():
                         else:
                             # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
                             html_content = html_tools.css_filter(css_filter=css_filter_rule, html_content=fetcher.content)
-
+                    if has_subtractive_selectors:
+                        html_content = html_tools.element_removal(subtractive_selectors, html_content)
                     # get_text() via inscriptis
                     stripped_text_from_html = get_text(html_content)
-                else:
-                    # Don't run get_text or xpath/css filters on plaintext
-                    stripped_text_from_html = html_content
 
             # Re #340 - return the content before the 'ignore text' was applied
             text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
@@ -147,7 +124,7 @@ class perform_site_check():
             # @todo we could abstract out the get_text() to handle this cleaner
             text_to_ignore = watch.get('ignore_text', []) + self.datastore.data['settings']['application'].get('global_ignore_text', [])
             if len(text_to_ignore):
-                stripped_text_from_html = self.strip_ignore_text(stripped_text_from_html, text_to_ignore)
+                stripped_text_from_html = html_tools.strip_ignore_text(stripped_text_from_html, text_to_ignore)
             else:
                 stripped_text_from_html = stripped_text_from_html.encode('utf8')
 
@@ -165,22 +142,14 @@ class perform_site_check():
             blocked_by_not_found_trigger_text = False
 
             if len(watch['trigger_text']):
+                # Yeah, lets block first until something matches
                 blocked_by_not_found_trigger_text = True
-                for line in watch['trigger_text']:
-                    # Because JSON wont serialize a re.compile object
-                    if line[0] == '/' and line[-1] == '/':
-                        regex = re.compile(line.strip('/'), re.IGNORECASE)
-                        # Found it? so we don't wait for it anymore
-                        r = re.search(regex, str(stripped_text_from_html))
-                        if r:
-                            blocked_by_not_found_trigger_text = False
-                            break
-
-                    elif line.lower() in str(stripped_text_from_html).lower():
-                        # We found it don't wait for it.
-                        blocked_by_not_found_trigger_text = False
-                        break
-
+                # Filter and trigger works the same, so reuse it
+                result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
+                                                      wordlist=watch['trigger_text'],
+                                                      mode="line numbers")
+                if result:
+                    blocked_by_not_found_trigger_text = False
 
 
             if not blocked_by_not_found_trigger_text and watch['previous_md5'] != fetched_md5:

changedetectionio/forms.py

@@ -1,12 +1,30 @@
-from wtforms import Form, SelectField, RadioField, BooleanField, StringField, PasswordField, validators, IntegerField, fields, TextAreaField, \
-    Field
-from wtforms import widgets
-from wtforms.validators import ValidationError
-from wtforms.fields import html5
-from changedetectionio import content_fetcher
 import re
 
-from changedetectionio.notification import default_notification_format, valid_notification_formats, default_notification_body, default_notification_title
+from wtforms import (
+    BooleanField,
+    Field,
+    Form,
+    IntegerField,
+    PasswordField,
+    RadioField,
+    SelectField,
+    StringField,
+    SubmitField,
+    TextAreaField,
+    fields,
+    validators,
+    widgets,
+)
+from wtforms.fields import html5
+from wtforms.validators import ValidationError
+
+from changedetectionio import content_fetcher
+from changedetectionio.notification import (
+    default_notification_body,
+    default_notification_format,
+    default_notification_title,
+    valid_notification_formats,
+)
 
 valid_method = {
     'GET',
@@ -44,8 +62,8 @@ class SaltyPasswordField(StringField):
     encrypted_password = ""
 
     def build_password(self, password):
-        import hashlib
         import base64
+        import hashlib
         import secrets
 
         # Make a new salt on every new password and store it with the password
@@ -103,9 +121,10 @@ class ValidateContentFetcherIsReady(object):
         self.message = message
 
     def __call__(self, form, field):
-        from changedetectionio import content_fetcher
         import urllib3.exceptions
 
+        from changedetectionio import content_fetcher
+
         # Better would be a radiohandler that keeps a reference to each class
         if field.data is not None:
             klass = getattr(content_fetcher, field.data)
@@ -212,52 +231,69 @@ class ValidateListRegex(object):
                 except re.error:
                     message = field.gettext('RegEx \'%s\' is not a valid regular expression.')
                     raise ValidationError(message % (line))
-
+              
 class ValidateCSSJSONXPATHInput(object):
     """
     Filter validation
     @todo CSS validator ;)
     """
 
-    def __init__(self, message=None):
+    def __init__(self, message=None, allow_xpath=True, allow_json=True):
         self.message = message
+        self.allow_xpath = allow_xpath
+        self.allow_json = allow_json
 
     def __call__(self, form, field):
 
+        if isinstance(field.data, str):
+            data = [field.data]
+        else:
+            data = field.data
+
+        for line in data:
         # Nothing to see here
-        if not len(field.data.strip()):
-            return
+            if not len(line.strip()):
+                return
 
-        # Does it look like XPath?
-        if field.data.strip()[0] == '/':
-            from lxml import html, etree
-            tree = html.fromstring("<html></html>")
+            # Does it look like XPath?
+            if line.strip()[0] == '/':
+                if not self.allow_xpath:
+                    raise ValidationError("XPath not permitted in this field!")
+                from lxml import etree, html
+                tree = html.fromstring("<html></html>")
 
-            try:
-                tree.xpath(field.data.strip())
-            except etree.XPathEvalError as e:
-                message = field.gettext('\'%s\' is not a valid XPath expression. (%s)')
-                raise ValidationError(message % (field.data, str(e)))
-            except:
-                raise ValidationError("A system-error occurred when validating your XPath expression")
+                try:
+                    tree.xpath(line.strip())
+                except etree.XPathEvalError as e:
+                    message = field.gettext('\'%s\' is not a valid XPath expression. (%s)')
+                    raise ValidationError(message % (line, str(e)))
+                except:
+                    raise ValidationError("A system-error occurred when validating your XPath expression")
 
-        if 'json:' in field.data:
-            from jsonpath_ng.exceptions import JsonPathParserError, JsonPathLexerError
-            from jsonpath_ng.ext import parse
+            if 'json:' in line:
+                if not self.allow_json:
+                    raise ValidationError("JSONPath not permitted in this field!")
 
-            input = field.data.replace('json:', '')
+                from jsonpath_ng.exceptions import (
+                    JsonPathLexerError,
+                    JsonPathParserError,
+                )
+                from jsonpath_ng.ext import parse
 
-            try:
-                parse(input)
-            except (JsonPathParserError, JsonPathLexerError) as e:
-                message = field.gettext('\'%s\' is not a valid JSONPath expression. (%s)')
-                raise ValidationError(message % (input, str(e)))
-            except:
-                raise ValidationError("A system-error occurred when validating your JSONPath expression")
+                input = line.replace('json:', '')
 
-            # Re #265 - maybe in the future fetch the page and offer a
-            # warning/notice that its possible the rule doesnt yet match anything?
+                try:
+                    parse(input)
+                except (JsonPathParserError, JsonPathLexerError) as e:
+                    message = field.gettext('\'%s\' is not a valid JSONPath expression. (%s)')
+                    raise ValidationError(message % (input, str(e)))
+                except:
+                    raise ValidationError("A system-error occurred when validating your JSONPath expression")
 
+                # Re #265 - maybe in the future fetch the page and offer a
+                # warning/notice that its possible the rule doesnt yet match anything?
+
+            
 class quickWatchForm(Form):
     # https://wtforms.readthedocs.io/en/2.3.x/fields/#module-wtforms.fields.html5
     # `require_tld` = False is needed even for the test harness "http://localhost:5005.." to run
@@ -282,6 +318,7 @@ class watchForm(commonSettingsForm):
     minutes_between_check = html5.IntegerField('Maximum time in minutes until recheck',
                                                [validators.Optional(), validators.NumberRange(min=1)])
     css_filter = StringField('CSS/JSON/XPATH Filter', [ValidateCSSJSONXPATHInput()])
+    subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
     title = StringField('Title')
 
     ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
@@ -290,6 +327,9 @@ class watchForm(commonSettingsForm):
     method = SelectField('Request Method', choices=valid_method, default=default_method)
     trigger_text = StringListField('Trigger/wait for text', [validators.Optional(), ValidateListRegex()])
 
+    save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
+    save_and_preview_button = SubmitField('Save & Preview', render_kw={"class": "pure-button pure-button-primary"})
+
     def validate(self, **kwargs):
         if not super().validate():
             return False
@@ -310,5 +350,6 @@ class globalSettingsForm(commonSettingsForm):
                                                [validators.NumberRange(min=1)])
     extract_title_as_title = BooleanField('Extract <title> from document and use as watch title')
     base_url = StringField('Base URL', validators=[validators.Optional()])
+    global_subtractive_selectors = StringListField('Ignore elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
     global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
-    ignore_whitespace = BooleanField('Ignore whitespace')
+    ignore_whitespace = BooleanField('Ignore whitespace')

changedetectionio/html_tools.py

@@ -1,4 +1,7 @@
 import json
+import re
+from typing import List
+
 from bs4 import BeautifulSoup
 from jsonpath_ng.ext import parse
 
@@ -16,16 +19,27 @@ def css_filter(css_filter, html_content):
 
     return html_block + "\n"
 
+def subtractive_css_selector(css_selector, html_content):
+    soup = BeautifulSoup(html_content, "html.parser")
+    for item in soup.select(css_selector):
+        item.decompose()
+    return str(soup)
+
+    
+def element_removal(selectors: List[str], html_content):
+    """Joins individual filters into one css filter."""
+    selector = ",".join(selectors)
+    return subtractive_css_selector(selector, html_content)
+    
 
 # Return str Utf-8 of matched rules
 def xpath_filter(xpath_filter, html_content):
-    from lxml import html
-    from lxml import etree
+    from lxml import etree, html
 
     tree = html.fromstring(html_content)
     html_block = ""
 
-    for item in tree.xpath(xpath_filter.strip()):
+    for item in tree.xpath(xpath_filter.strip(), namespaces={'re':'http://exslt.org/regular-expressions'}):
         html_block+= etree.tostring(item, pretty_print=True).decode('utf-8')+"<br/>"
 
     return html_block
@@ -105,3 +119,50 @@ def extract_json_as_string(content, jsonpath_filter):
         return ''
 
     return stripped_text_from_html
+
+# Mode     - "content" return the content without the matches (default)
+#          - "line numbers" return a list of line numbers that match (int list)
+#
+# wordlist - list of regex's (str) or words (str)
+def strip_ignore_text(content, wordlist, mode="content"):
+    ignore = []
+    ignore_regex = []
+
+    # @todo check this runs case insensitive
+    for k in wordlist:
+
+        # Is it a regex?
+        if k[0] == '/':
+            ignore_regex.append(k.strip(" /"))
+        else:
+            ignore.append(k)
+
+    i = 0
+    output = []
+    ignored_line_numbers = []
+    for line in content.splitlines():
+        i += 1
+        # Always ignore blank lines in this mode. (when this function gets called)
+        if len(line.strip()):
+            regex_matches = False
+
+            # if any of these match, skip
+            for regex in ignore_regex:
+                try:
+                    if re.search(regex, line, re.IGNORECASE):
+                        regex_matches = True
+                except Exception as e:
+                    continue
+
+            if not regex_matches and not any(skip_text.lower() in line.lower() for skip_text in ignore):
+                output.append(line.encode('utf8'))
+            else:
+                ignored_line_numbers.append(i)
+
+
+
+    # Used for finding out what to highlight
+    if mode == "line numbers":
+        return ignored_line_numbers
+
+    return "\n".encode('utf8').join(output)

changedetectionio/static/styles/diff.css

@@ -54,3 +54,19 @@ ins {
   body {
     height: 99%;
     /* Hide scroll bar in Firefox */ } }
+
+td#diff-col div {
+  text-align: justify;
+  white-space: pre-wrap; }
+
+.ignored {
+  background-color: #ccc;
+  /*  border: #0d91fa 1px solid; */
+  opacity: 0.7; }
+
+.triggered {
+  background-color: #1b98f8; }
+
+/* ignored and triggered? make it obvious error */
+.ignored.triggered {
+  background-color: #ff0000; }

changedetectionio/static/styles/diff.scss

@@ -66,3 +66,23 @@ ins {
 		height: 99%; /* Hide scroll bar in Firefox */
 	}
 }
+
+td#diff-col div {
+    text-align: justify;
+    white-space: pre-wrap;
+}
+
+.ignored {
+    background-color: #ccc;
+   /*  border: #0d91fa 1px solid; */
+    opacity: 0.7;
+}
+
+.triggered {
+    background-color: #1b98f8;
+}
+
+/* ignored and triggered? make it obvious error */
+.ignored.triggered {
+  background-color: #ff0000;
+}

changedetectionio/static/styles/package.json

@@ -4,8 +4,7 @@
   "description": "",
   "main": "index.js",
   "scripts": {
-    "build": "node-sass styles.scss diff.scss -o .",
-    "watch": "node-sass --watch styles.scss diff.scss -o ."
+    "build": "node-sass styles.scss -o .;node-sass diff.scss -o ."
   },
   "author": "",
   "license": "ISC",

changedetectionio/static/styles/styles.scss

@@ -45,6 +45,7 @@ section.content {
 /* table related */
 .watch-table {
   width: 100%;
+  font-size: 80%;
 
   tr.unviewed {
     font-weight: bold;
@@ -55,7 +56,6 @@ section.content {
   }
 
   td {
-    font-size: 80%;
     white-space: nowrap;
   }
 
@@ -107,12 +107,12 @@ section.content {
 
 body:after {
   content: "";
-  background: linear-gradient(130deg, #ff7a18, #af002d 41.07%, #319197 76.05%)
+  background: linear-gradient(130deg, #5ad8f7, #2f50af 41.07%, #9150bf 84.05%);
 }
 
 body:after, body:before {
   display: block;
-  height: 600px;
+  height: 650px;
   position: absolute;
   top: 0;
   left: 0;
@@ -125,11 +125,8 @@ body::after {
 }
 
 body::before {
+  // background-image set in base.html so it works with reverse proxies etc
   content: "";
-  background-image: url(/static/images/gradient-border.png);
-}
-
-body:before {
   background-size: cover
 }
 
@@ -265,6 +262,7 @@ body:after, body:before {
   }
   legend {
     color: #fff;
+    font-weight: bold;
   }
 }
 
@@ -317,11 +315,9 @@ footer {
     */
 }
 
-
-
 .sticky-tab {
   position: absolute;
-  top: 80px;
+  top: 60px;
   font-size: 8px;
   background: #fff;
   padding: 10px;
@@ -331,6 +327,11 @@ footer {
   &#right-sticky {
     right: 0px;
   }
+  &#hosted-sticky {
+    right: 0px;
+    top: 100px;
+    font-weight: bold;
+  }
 }
 
 #new-version-text a {
@@ -542,6 +543,16 @@ $form-edge-padding: 20px;
     display: block;
   }
 }
+
+.login-form {
+  .inner {
+    background: #fff;;
+    padding: $form-edge-padding;
+    border-radius: 5px;
+  }
+}
+
+
 .edit-form {
   min-width: 70%;
   .tab-pane-inner {
@@ -565,5 +576,14 @@ $form-edge-padding: 20px;
     display: block;
     background: #fff;
   }
+
+  .pure-form-message-inline {
+    padding-left: 0;
+  }
 }
 
+ul {
+    padding-left: 1em;
+    padding-top: 0px;
+    margin-top: 4px;
+}

changedetectionio/store.py

@@ -1,15 +1,19 @@
-from os import unlink, path, mkdir
 import json
-import uuid as uuid_builder
-from threading import Lock
-from copy import deepcopy
-
 import logging
-import time
-import threading
 import os
+import threading
+import time
+import uuid as uuid_builder
+from copy import deepcopy
+from os import mkdir, path, unlink
+from threading import Lock
+
+from changedetectionio.notification import (
+    default_notification_body,
+    default_notification_format,
+    default_notification_title,
+)
 
-from changedetectionio.notification import default_notification_format, default_notification_body, default_notification_title
 
 # Is there an existing library to ensure some data store (JSON etc) is in sync with CRUD methods?
 # Open a github issue if you know something :)
@@ -46,6 +50,7 @@ class ChangeDetectionStore:
                     'extract_title_as_title': False,
                     'fetch_backend': 'html_requests',
                     'global_ignore_text': [], # List of text to ignore when calculating the comparison checksum
+                    'global_subtractive_selectors': [],
                     'ignore_whitespace': False,
                     'notification_urls': [], # Apprise URL list
                     # Custom notification content
@@ -82,6 +87,7 @@ class ChangeDetectionStore:
             'notification_body': default_notification_body,
             'notification_format': default_notification_format,
             'css_filter': "",
+            'subtractive_selectors': [],
             'trigger_text': [],  # List of text or regex to wait for until a change is detected
             'fetch_backend': None,
             'extract_title_as_title': False
@@ -144,8 +150,8 @@ class ChangeDetectionStore:
             unlink(password_reset_lockfile)
 
         if not 'app_guid' in self.__data:
-            import sys
             import os
+            import sys
             if "pytest" in sys.modules or "PYTEST_CURRENT_TEST" in os.environ:
                 self.__data['app_guid'] = "test-" + str(uuid_builder.uuid4())
             else:
@@ -184,10 +190,6 @@ class ChangeDetectionStore:
 
     def update_watch(self, uuid, update_obj):
 
-        # Skip if 'paused' state
-        if self.__data['watching'][uuid]['paused']:
-            return
-
         with self.lock:
 
             # In python 3.9 we have the |= dict operator, but that still will lose data on nested structures...
@@ -398,13 +400,10 @@ class ChangeDetectionStore:
                 # system was out of memory, out of RAM etc
                 with open(self.json_store_path+".tmp", 'w') as json_file:
                     json.dump(data, json_file, indent=4)
-
+                os.rename(self.json_store_path+".tmp", self.json_store_path)
             except Exception as e:
                 logging.error("Error writing JSON!! (Main JSON file save was skipped) : %s", str(e))
 
-            else:
-                os.rename(self.json_store_path+".tmp", self.json_store_path)
-
             self.needs_write = False
 
     # Thread runner, this helps with thread/write issues when there are many operations that want to update the JSON
@@ -437,6 +436,7 @@ class ChangeDetectionStore:
                 index.append(self.data['watching'][uuid]['history'][str(id)])
 
         import pathlib
+
         # Only in the sub-directories
         for item in pathlib.Path(self.datastore_path).rglob("*/*txt"):
             if not str(item) in index:

changedetectionio/templates/_common_fields.jinja

@@ -34,9 +34,8 @@
                             </div>
                             <div class="pure-controls">
                             <span class="pure-form-message-inline">
-                                These tokens can be used in the notification body and title to
-                                customise the notification text.
-                            </span>
+                                These tokens can be used in the notification body and title to customise the notification text.
+
                                 <table class="pure-table" id="token-table">
                                     <thead>
                                     <tr>
@@ -88,7 +87,7 @@
                                     </tr>
                                     </tbody>
                                 </table>
-                                <span class="pure-form-message-inline">
+                                <br/>
                                 URLs generated by changedetection.io (such as <code>{diff_url}</code>) require the <code>BASE_URL</code> environment variable set.<br/>
                                 Your <code>BASE_URL</code> var is currently "{{current_base_url}}"
                             </span>

changedetectionio/templates/_helpers.jinja

@@ -25,3 +25,6 @@
 {% endmacro %}
 
 
+{% macro render_button(field) %}
+  {{ field(**kwargs)|safe }}
+{% endmacro %}

changedetectionio/templates/base.html

@@ -12,7 +12,13 @@
         <link rel="stylesheet" href="{{ m }}?ver=1000">
         {% endfor %}
     {% endif %}
+    <style>
+    body::before {
+        background-image: url({{url_for('static_content', group='images', filename='gradient-border.png')}});
+    }
+    </style>
 </head>
+
 <body>
 
 <div class="header">
@@ -35,13 +41,13 @@
         {% if current_user.is_authenticated or not has_password %}
             {% if not current_diff_url %}
             <li class="pure-menu-item">
-                <a href="{{ url_for('get_backup')}}" class="pure-menu-link">BACKUP</a>
+                <a href="{{ url_for('settings_page')}}" class="pure-menu-link">SETTINGS</a>
             </li>
             <li class="pure-menu-item">
                 <a href="{{ url_for('import_page')}}" class="pure-menu-link">IMPORT</a>
             </li>
             <li class="pure-menu-item">
-                <a href="{{ url_for('settings_page')}}" class="pure-menu-link">SETTINGS</a>
+                <a href="{{ url_for('get_backup')}}" class="pure-menu-link">BACKUP</a>
             </li>
             {% else %}
             <li class="pure-menu-item">
@@ -68,7 +74,7 @@
         </ul>
     </div>
 </div>
-
+{% if hosted_sticky %}<div class="sticky-tab" id="hosted-sticky"><a href="https://lemonade.changedetection.io/start?ref={{guid}}">Let us host your instance!</a></div>{% endif %}
 {% if left_sticky %}<div class="sticky-tab" id="left-sticky"><a href="{{url_for('preview_page', uuid=uuid)}}">Show current snapshot</a></div> {% endif %}
 {% if right_sticky %}<div class="sticky-tab" id="right-sticky">{{ right_sticky }}</div> {% endif %}
 <section class="content">

changedetectionio/templates/diff.html

@@ -36,6 +36,7 @@
     <a onclick="next_diff();">Jump</a>
 </div>
 <div id="diff-ui">
+    <div class="tip">Pro-tip: Use <strong>show current snapshot</strong> tab to visualise what will be ignored.</div>
     <table>
         <tbody>
         <tr>

changedetectionio/templates/edit.html

@@ -1,6 +1,7 @@
 {% extends 'base.html' %}
 {% block content %}
 {% from '_helpers.jinja' import render_field %}
+{% from '_helpers.jinja' import render_button %}
 {% from '_common_fields.jinja' import render_common_settings_form %}
 <script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 
@@ -57,24 +58,30 @@
                         </span>
                     </div>
 
+                <hr/>
                 <fieldset class="pure-group">
-                                    <div class="pure-control-group">
-                    {{ render_field(form.method) }}
-                </div>
-                    <strong>Note: <i>Request Headers and Body settings are ONLY used by Basic fast Plaintext/HTTP Client fetch method.</i></strong>
-                    {{ render_field(form.headers, rows=5, placeholder="Example
+
+                    <span class="pure-form-message-inline">
+                        <strong>Request override is currently only used by the <i>Basic fast Plaintext/HTTP Client</i> method.</strong>
+                    </span>
+                    <div class="pure-control-group">
+                        {{ render_field(form.method) }}
+                    </div>
+                    <div class="pure-control-group">
+{{ render_field(form.headers, rows=5, placeholder="Example
 Cookie: foobar
 User-Agent: wonderbra 1.0") }}
-                </fieldset>
-                <div class="pure-control-group">
-                    {{ render_field(form.body, rows=5, placeholder="Example
+                    </div>
+                    <div class="pure-control-group">
+                                        {{ render_field(form.body, rows=5, placeholder="Example
 {
    \"name\":\"John\",
    \"age\":30,
    \"car\":null
 }") }}
-                </div>
-
+                    </div>
+                </fieldset>
+                <br/>
             </div>
 
             <div class="tab-pane-inner" id="notifications">
@@ -88,6 +95,18 @@ User-Agent: wonderbra 1.0") }}
 
             <div class="tab-pane-inner" id="filters-and-triggers">
                 <fieldset>
+                        <div class="pure-control-group">
+                            <strong>Pro-tips:</strong><br/>
+                            <ul>
+                                <li>
+                                    Use the preview page to see your filters and triggers highlighted.
+                                </li>
+                                <li>
+                                    Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a>
+                                </li>
+                            </ul>
+                    </div>
+
                     <div class="pure-control-group">
                         {{ render_field(form.css_filter, placeholder=".class-name or #some-id, or other CSS selector rule.",
                         class="m-d") }}
@@ -96,14 +115,25 @@ User-Agent: wonderbra 1.0") }}
                         <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 <b>"json:"</b>, <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  <b>//*[contains(@class, 'sametext')]</b>, <a
+                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash, example  <b>//*[contains(@class, 'sametext')]</b>, <a
                                 href="http://xpather.com/" target="new">test your XPath here</a></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/>
                 </span>
                     </div>
-
+                    <fieldset class="pure-group">
+                      {{ render_field(form.subtractive_selectors, rows=5, placeholder="header
+footer
+nav
+.stockticker") }}
+                      <span class="pure-form-message-inline">
+                        <ul>
+                          <li> Remove HTML element(s) by CSS selector before text conversion. </li>
+                          <li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
+                        </ul>
+                      </span>
+                    </fieldset>
                 </fieldset>
                 <fieldset class="pure-group">
                     {{ render_field(form.ignore_text, rows=5, placeholder="Some text to ignore in a line
@@ -114,6 +144,7 @@ User-Agent: wonderbra 1.0") }}
                             <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
                             <li>Regular Expression support, wrap the line in forward slash <b>/regex/</b></li>
                             <li>Changing this will affect the comparison checksum which may trigger an alert</li>
+                            <li>Use the preview/show current tab to see ignores</li>
                         </ul>
                 </span>
 
@@ -138,7 +169,8 @@ User-Agent: wonderbra 1.0") }}
             <div id="actions">
                 <div class="pure-control-group">
 
-                    <button type="submit" class="pure-button pure-button-primary">Save</button>
+                      {{ render_button(form.save_button) }} {{ render_button(form.save_and_preview_button) }}
+
                     <a href="{{url_for('api_delete', uuid=uuid)}}"
                        class="pure-button button-small button-error ">Delete</a>
                     <a href="{{url_for('api_clone', uuid=uuid)}}"

changedetectionio/templates/login.html

@@ -1,8 +1,7 @@
 {% extends 'base.html' %}
 
 {% block content %}
-<div class="edit-form">
-
+<div class="login-form">
  <div class="inner">
     <form class="pure-form pure-form-stacked" action="{{url_for('login')}}" method="POST">
         <fieldset>

changedetectionio/templates/preview.html

@@ -3,19 +3,21 @@
 {% block content %}
 
 <div id="settings">
-    <h1>Current</h1>
+    <h1>Current - {{watch.last_checked|format_timestamp_timeago}}</h1>
 </div>
 
 <div id="diff-ui">
+    <span class="ignored">Grey lines are ignored</span> <span class="triggered">Blue lines are triggers</span>
     <table>
         <tbody>
         <tr>
             <td id="diff-col">
-                <span id="result">{% for row in content %}{{row}}{% endfor %}</span>
+                    {% for row in content %}
+                    <div class="{{row.classes}}">{{row.line}}</div>
+                    {% endfor %}
             </td>
         </tr>
         </tbody>
     </table>
 </div>
-
 {% endblock %}

changedetectionio/templates/settings.html

@@ -83,7 +83,18 @@
                     </span>
                     </fieldset>
 
-
+                    <fieldset class="pure-group">
+                      {{ render_field(form.global_subtractive_selectors, rows=5, placeholder="header
+footer
+nav
+.stockticker") }}
+                      <span class="pure-form-message-inline">
+                        <ul>
+                          <li> Remove HTML element(s) by CSS selector before text conversion. </li>
+                          <li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
+                        </ul>
+                      </span>
+                    </fieldset>
                     <fieldset class="pure-group">
                     {{ render_field(form.global_ignore_text, rows=5, placeholder="Some text to ignore in a line
 /some.regex\d{2}/ for case-INsensitive regex
@@ -95,6 +106,7 @@
                             <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
                             <li>Regular Expression support, wrap the line in forward slash <b>/regex/</b></li>
                             <li>Changing this will affect the comparison checksum which may trigger an alert</li>
+                            <li>Use the preview/show current tab to see ignores</li>
                         </ul>
                      </span>
                     </fieldset>

changedetectionio/tests/test_api.py

@@ -14,7 +14,6 @@ def set_response_data(test_return_data):
 
 
 def test_snapshot_api_detects_change(client, live_server):
-
     test_return_data = "Some initial text"
 
     test_return_data_modified = "Some NEW nice initial text"
@@ -27,7 +26,7 @@ def test_snapshot_api_detects_change(client, live_server):
     time.sleep(1)
 
     # Add our URL to the import page
-    test_url = url_for('test_endpoint', _external=True)
+    test_url = url_for('test_endpoint', content_type="text/plain", _external=True)
     res = client.post(
         url_for("import_page"),
         data={"urls": test_url},

changedetectionio/tests/test_backend.py

@@ -7,6 +7,13 @@ from . util import set_original_response, set_modified_response, live_server_set
 
 sleep_time_for_fetch_thread = 3
 
+# Basic test to check inscriptus is not adding return line chars, basically works etc
+def test_inscriptus():
+    from inscriptis import get_text
+    html_content="<html><body>test!<br/>ok man</body></html>"
+    stripped_text_from_html = get_text(html_content)
+    assert stripped_text_from_html == 'test!\nok man'
+
 
 def test_check_basic_change_detection_functionality(client, live_server):
     set_original_response()

changedetectionio/tests/test_element_removal.py

@@ -0,0 +1,168 @@
+#!/usr/bin/python3
+
+import time
+
+from flask import url_for
+
+from ..html_tools import *
+from .util import live_server_setup
+
+
+def test_setup(live_server):
+    live_server_setup(live_server)
+
+
+def set_original_response():
+    test_return_data = """<html>
+    <header>
+    <h2>Header</h2>
+    </header>
+    <nav>
+    <ul>
+      <li><a href="#">A</a></li>
+      <li><a href="#">B</a></li>
+      <li><a href="#">C</a></li>
+    </ul>
+    </nav>
+       <body>
+     Some initial text</br>
+     <p>Which is across multiple lines</p>
+     </br>
+     So let's see what happens.  </br>
+    <div id="changetext">Some text that will change</div>
+     </body>
+    <footer>
+    <p>Footer</p>
+    </footer>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+
+def set_modified_response():
+    test_return_data = """<html>
+    <header>
+    <h2>Header changed</h2>
+    </header>
+    <nav>
+    <ul>
+      <li><a href="#">A changed</a></li>
+      <li><a href="#">B</a></li>
+      <li><a href="#">C</a></li>
+    </ul>
+    </nav>
+       <body>
+     Some initial text</br>
+     <p>Which is across multiple lines</p>
+     </br>
+     So let's see what happens.  </br>
+    <div id="changetext">Some text that changes</div>
+     </body>
+    <footer>
+    <p>Footer changed</p>
+    </footer>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+
+def test_element_removal_output():
+    from changedetectionio import fetch_site_status
+    from inscriptis import get_text
+
+    # Check text with sub-parts renders correctly
+    content = """<html>
+    <header>
+    <h2>Header</h2>
+    </header>
+    <nav>
+    <ul>
+      <li><a href="#">A</a></li>
+    </ul>
+    </nav>
+       <body>
+     Some initial text</br>
+     <p>across multiple lines</p>
+     <div id="changetext">Some text that changes</div>
+     </body>
+    <footer>
+    <p>Footer</p>
+    </footer>
+     </html>
+    """
+    html_blob = element_removal(
+        ["header", "footer", "nav", "#changetext"], html_content=content
+    )
+    text = get_text(html_blob)
+    assert (
+        text
+        == """Some initial text
+
+across multiple lines
+"""
+    )
+
+
+def test_element_removal_full(client, live_server):
+    sleep_time_for_fetch_thread = 3
+
+    set_original_response()
+
+    # Give the endpoint time to spin up
+    time.sleep(1)
+
+    # Add our URL to the import page
+    test_url = url_for("test_endpoint", _external=True)
+    res = client.post(
+        url_for("import_page"), data={"urls": test_url}, follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    # 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"
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={
+            "subtractive_selectors": subtractive_selectors_data,
+            "url": test_url,
+            "tag": "",
+            "headers": "",
+            "fetch_backend": "html_requests",
+        },
+        follow_redirects=True,
+    )
+    assert b"Updated watch." in res.data
+
+    # Check it saved
+    res = client.get(
+        url_for("edit_page", uuid="first"),
+    )
+    assert bytes(subtractive_selectors_data.encode("utf-8")) in res.data
+
+    # Trigger a check
+    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # No change yet - first check
+    res = client.get(url_for("index"))
+    assert b"unviewed" not in res.data
+
+    #  Make a change to header/footer/nav
+    set_modified_response()
+
+    # Trigger a check
+    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+
+    # Give the thread time to pick it up
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # There should not be an unviewed change, as changes should be removed
+    res = client.get(url_for("index"))
+    assert b"unviewed" not in res.data

changedetectionio/tests/test_ignore_regex_text.py

@@ -3,6 +3,7 @@
 import time
 from flask import url_for
 from . util import live_server_setup
+from changedetectionio import html_tools
 
 def test_setup(live_server):
     live_server_setup(live_server)
@@ -23,7 +24,7 @@ def test_strip_regex_text_func():
     ignore_lines = ["sometimes", "/\s\d{2,3}\s/", "/ignore-case text/"]
 
     fetcher = fetch_site_status.perform_site_check(datastore=False)
-    stripped_content = fetcher.strip_ignore_text(test_content, ignore_lines)
+    stripped_content = html_tools.strip_ignore_text(test_content, ignore_lines)
 
     assert b"but 1 lines" in stripped_content
     assert b"igNORe-cAse text" not in stripped_content

changedetectionio/tests/test_ignore_text.py

@@ -3,6 +3,7 @@
 import time
 from flask import url_for
 from . util import live_server_setup
+from changedetectionio import html_tools
 
 def test_setup(live_server):
     live_server_setup(live_server)
@@ -23,7 +24,7 @@ def test_strip_text_func():
     ignore_lines = ["sometimes"]
 
     fetcher = fetch_site_status.perform_site_check(datastore=False)
-    stripped_content = fetcher.strip_ignore_text(test_content, ignore_lines)
+    stripped_content = html_tools.strip_ignore_text(test_content, ignore_lines)
 
     assert b"sometimes" not in stripped_content
     assert b"Some content" in stripped_content
@@ -52,6 +53,8 @@ def set_modified_original_ignore_response():
      <p>Which is across multiple lines</p>
      </br>
      So let's see what happens.  </br>
+     <p>new ignore stuff</p>
+     <p>blah</p>
      </body>
      </html>
 
@@ -67,7 +70,7 @@ def set_modified_ignore_response():
        <body>
      Some initial text</br>
      <p>Which is across multiple lines</p>
-     <P>ZZZZZ</P>
+     <P>ZZZZz</P>
      </br>
      So let's see what happens.  </br>
      </body>
@@ -82,7 +85,8 @@ def set_modified_ignore_response():
 def test_check_ignore_text_functionality(client, live_server):
     sleep_time_for_fetch_thread = 3
 
-    ignore_text = "XXXXX\r\nYYYYY\r\nZZZZZ"
+    # Use a mix of case in ZzZ to prove it works case-insensitive.
+    ignore_text = "XXXXX\r\nYYYYY\r\nzZzZZ\r\nnew ignore stuff"
     set_original_ignore_response()
 
     # Give the endpoint time to spin up
@@ -142,13 +146,25 @@ def test_check_ignore_text_functionality(client, live_server):
     assert b'unviewed' not in res.data
     assert b'/test-endpoint' in res.data
 
+
+
+
+
     # Just to be sure.. set a regular modified change..
     set_modified_original_ignore_response()
     client.get(url_for("api_watch_checknow"), follow_redirects=True)
     time.sleep(sleep_time_for_fetch_thread)
+
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
 
+    # Check the preview/highlighter, we should be able to see what we ignored, but it should be highlighted
+    # We only introduce the "modified" content that includes what we ignore so we can prove the newest version also displays
+    # at /preview
+    res = client.get(url_for("preview_page", uuid="first"))
+    # We should be able to see what we ignored
+    assert b'<div class="ignored">new ignore stuff' in res.data
+
     res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data
 

changedetectionio/tests/test_jsonpath_selector.py

@@ -162,7 +162,7 @@ def test_check_json_without_filter(client, live_server):
     time.sleep(1)
 
     # Add our URL to the import page
-    test_url = url_for('test_endpoint_json', _external=True)
+    test_url = url_for('test_endpoint', content_type="application/json", _external=True)
     client.post(
         url_for("import_page"),
         data={"urls": test_url},
@@ -193,7 +193,7 @@ def test_check_json_filter(client, live_server):
     time.sleep(1)
 
     # Add our URL to the import page
-    test_url = url_for('test_endpoint', _external=True)
+    test_url = url_for('test_endpoint', content_type="application/json", _external=True)
     res = client.post(
         url_for("import_page"),
         data={"urls": test_url},
@@ -258,7 +258,7 @@ def test_check_json_filter_bool_val(client, live_server):
     # Give the endpoint time to spin up
     time.sleep(1)
 
-    test_url = url_for('test_endpoint', _external=True)
+    test_url = url_for('test_endpoint', content_type="application/json", _external=True)
 
     res = client.post(
         url_for("import_page"),
@@ -313,7 +313,7 @@ def test_check_json_ext_filter(client, live_server):
     time.sleep(1)
 
     # Add our URL to the import page
-    test_url = url_for('test_endpoint', _external=True)
+    test_url = url_for('test_endpoint', content_type="application/json", _external=True)
     res = client.post(
         url_for("import_page"),
         data={"urls": test_url},

changedetectionio/tests/test_request.py

@@ -77,14 +77,6 @@ def test_body_in_request(client, live_server):
     # Add our URL to the import page
     test_url = url_for('test_body', _external=True)
 
-    # Add the test URL twice, we will check
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-    assert b"1 Imported" in res.data
-
     res = client.post(
         url_for("import_page"),
         data={"urls": test_url},
@@ -94,19 +86,6 @@ def test_body_in_request(client, live_server):
 
     body_value = 'Test Body Value'
 
-    # Attempt to add a body with a GET method
-    res = client.post(
-        url_for("edit_page", uuid="first"),
-        data={
-              "url": test_url,
-              "tag": "",
-              "method": "GET",
-              "fetch_backend": "html_requests",
-              "body": "invalid"},
-        follow_redirects=True
-    )
-    assert b"Body must be empty when Request Method is set to GET" in res.data
-
     # Add a properly formatted body with a proper method
     res = client.post(
         url_for("edit_page", uuid="first"),
@@ -120,8 +99,7 @@ def test_body_in_request(client, live_server):
     )
     assert b"Updated watch." in res.data
 
-    # Give the thread time to pick up the first version
-    time.sleep(5)
+    time.sleep(3)
 
     # The service should echo back the body
     res = client.get(
@@ -129,9 +107,20 @@ def test_body_in_request(client, live_server):
         follow_redirects=True
     )
 
-    # Check if body returned contains the specified data
+    # If this gets stuck something is wrong, something should always be there
+    assert b"No history found" not in res.data
+    # We should see what we sent in the reply
     assert str.encode(body_value) in res.data
 
+    ####### data sanity checks
+    # Add the test URL twice, we will check
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
     watches_with_body = 0
     with open('test-datastore/url-watches.json') as f:
         app_struct = json.load(f)
@@ -142,6 +131,20 @@ def test_body_in_request(client, live_server):
     # Should be only one with body set
     assert watches_with_body==1
 
+    # Attempt to add a body with a GET method
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={
+              "url": test_url,
+              "tag": "",
+              "method": "GET",
+              "fetch_backend": "html_requests",
+              "body": "invalid"},
+        follow_redirects=True
+    )
+    assert b"Body must be empty when Request Method is set to GET" in res.data
+
+
 def test_method_in_request(client, live_server):
     # Add our URL to the import page
     test_url = url_for('test_method', _external=True)

changedetectionio/tests/test_trigger.py

@@ -129,3 +129,8 @@ def test_trigger_functionality(client, live_server):
     time.sleep(sleep_time_for_fetch_thread)
     res = client.get(url_for("index"))
     assert b'unviewed' in res.data
+
+    # Check the preview/highlighter, we should be able to see what we triggered on, but it should be highlighted
+    res = client.get(url_for("preview_page", uuid="first"))
+    # We should be able to see what we ignored
+    assert b'<div class="triggered">foobar' in res.data

changedetectionio/tests/test_xpath_selector.py

@@ -96,6 +96,7 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
     res = client.get(url_for("index"))
     assert b'unviewed' not in res.data
 
+
 def test_xpath_validation(client, live_server):
 
     # Give the endpoint time to spin up

changedetectionio/tests/util.py

@@ -1,5 +1,6 @@
 #!/usr/bin/python3
 
+from flask import make_response, request
 
 def set_original_response():
     test_return_data = """<html>
@@ -40,24 +41,16 @@ def live_server_setup(live_server):
 
     @live_server.app.route('/test-endpoint')
     def test_endpoint():
+        ctype = request.args.get('content_type')
+
         # Tried using a global var here but didn't seem to work, so reading from a file instead.
-        with open("test-datastore/endpoint-content.txt", "r") as f:
-            return f.read()
-
-    @live_server.app.route('/test-endpoint-json')
-    def test_endpoint_json():
-
-        from flask import make_response
-
         with open("test-datastore/endpoint-content.txt", "r") as f:
             resp = make_response(f.read())
-            resp.headers['Content-Type'] = 'application/json'
+            resp.headers['Content-Type'] = ctype if ctype else 'text/html'
             return resp
 
     @live_server.app.route('/test-403')
     def test_endpoint_403_error():
-
-        from flask import make_response
         resp = make_response('', 403)
         return resp
 
@@ -65,7 +58,6 @@ def live_server_setup(live_server):
     @live_server.app.route('/test-headers')
     def test_headers():
 
-        from flask import request
         output= []
 
         for header in request.headers:
@@ -76,24 +68,16 @@ def live_server_setup(live_server):
     # Just return the body in the request
     @live_server.app.route('/test-body', methods=['POST', 'GET'])
     def test_body():
-
-        from flask import request
-
         return request.data
 
     # Just return the verb in the request
     @live_server.app.route('/test-method', methods=['POST', 'GET', 'PATCH'])
     def test_method():
-
-        from flask import request
-
         return request.method
 
     # Where we POST to as a notification
     @live_server.app.route('/test_notification_endpoint', methods=['POST', 'GET'])
     def test_notification_endpoint():
-        from flask import request
-
         with open("test-datastore/notification.txt", "wb") as f:
             # Debug method, dump all POST to file also, used to prove #65
             data = request.stream.read()
@@ -107,8 +91,6 @@ def live_server_setup(live_server):
     # Just return the verb in the request
     @live_server.app.route('/test-basicauth', methods=['GET'])
     def test_basicauth_method():
-
-        from flask import request
         auth = request.authorization
         ret = " ".join([auth.username, auth.password, auth.type])
         return ret

changedetectionio/update_worker.py

@@ -136,6 +136,8 @@ class update_worker(threading.Thread):
                         except Exception as e:
                             # Catch everything possible here, so that if a worker crashes, we don't lose it until restart!
                             print("!!!! Exception in update_worker !!!\n", 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)})
 
                     finally:
                         # Always record that we atleast tried
@@ -145,4 +147,7 @@ class update_worker(threading.Thread):
                 self.current_uuid = None  # Done
                 self.q.task_done()
 
+                # Give the CPU time to interrupt
+                time.sleep(0.1)
+
             self.app.config.exit.wait(1)

docker-compose.yml

@@ -1,9 +1,9 @@
 version: '2'
 services:
-    changedetection.io:
+    changedetection:
       image: ghcr.io/dgtlmoon/changedetection.io
       container_name: changedetection.io
-      hostname: changedetection.io
+      hostname: changedetection
       volumes:
         - changedetection-data:/datastore
 

requirements.txt

@@ -3,7 +3,7 @@ flask~= 2.0
 eventlet>=0.31.0
 validators
 timeago ~=1.0
-inscriptis ~= 1.2
+inscriptis ~= 2.2
 feedgen ~= 0.9
 flask-login ~= 0.5
 pytz
@@ -17,7 +17,7 @@ wtforms ~= 2.3.3
 jsonpath-ng ~= 1.5.3
 
 # Notification library
-apprise ~= 0.9.6
+apprise ~= 0.9.7
 
 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
 paho-mqtt
@@ -34,5 +34,4 @@ lxml
 
 # 3.141 was missing socksVersion, 3.150 was not in pypi, so we try 4.1.0
 selenium ~= 4.1.0
-pytest ~=6.2
-pytest-flask ~=1.2
+