Shows which items are already in the queue, disables adding to the queue if already in the recheck queue

README.md

@@ -9,18 +9,15 @@ _Know when web pages change! Stay ontop of new information!_
 
 Live your data-life *pro-actively* instead of *re-actively*.
 
-Open source web page monitoring, notification and change detection.
+Free, Open-source web page monitoring, notification and change detection. Don't have time? [**Try our $6.99/month subscription - unlimited checks and watches!**](https://lemonade.changedetection.io/start)
 
 
-<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"  />
+[<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"  />](https://lemonade.changedetection.io/start)
 
 
 **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)
+[**Try our $6.99/month subscription - unlimited checks and watches!**](https://lemonade.changedetection.io/start) , _half the price of other website change monitoring services and comes with unlimited watches & checks!_
 
 
 
@@ -39,13 +36,14 @@ Open source web page monitoring, notification and change detection.
 - COVID related news from government websites
 - University/organisation news from their website
 - Detect and monitor changes in JSON API responses 
-- API monitoring and alerting
+- JSON API monitoring and alerting
 - Changes in legal and other documents
 - Trigger API calls via notifications when text appears on a website
 - Glue together APIs using the JSON filter and JSON notifications
 - Create RSS feeds based on changes in web content
+- Monitor HTML source code for unexpected changes, strengthen your PCI compliance
 - You have a very sensitive list of URLs to watch and you do _not_ want to use the paid alternatives. (Remember, _you_ are the product)
- 
+
 _Need an actual Chrome runner with Javascript support? We support fetching via WebDriver!</a>_
 
 ## Screenshots
@@ -70,6 +68,10 @@ Docker standalone
 $ docker run -d --restart always -p "127.0.0.1:5000:5000" -v datastore-volume:/datastore --name changedetection.io dgtlmoon/changedetection.io
 ```
 
+### Windows
+
+See the install instructions at the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Microsoft-Windows
+
 ### Python Pip
 
 Check out our pypi page https://pypi.org/project/changedetection.io/
@@ -163,9 +165,6 @@ See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configura
 
 Raspberry Pi and linux/arm/v6 linux/arm/v7 arm64 devices are supported! See the wiki for [details](https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver)
 
-## Windows support?
-
-YES! See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Microsoft-Windows
 
 ## Support us
 

changedetectionio/__init__.py

@@ -39,7 +39,7 @@ from flask_wtf import CSRFProtect
 
 from changedetectionio import html_tools
 
-__version__ = '0.39.11'
+__version__ = '0.39.12'
 
 datastore = None
 
@@ -94,16 +94,6 @@ def init_app_secret(datastore_path):
 
     return secret
 
-# Remember python is by reference
-# populate_form in wtfors didnt work for me. (try using a setattr() obj type on datastore.watch?)
-def populate_form_from_watch(form, watch):
-    for i in form.__dict__.keys():
-        if i[0] != '_':
-            p = getattr(form, i)
-            if hasattr(p, 'data') and i in watch:
-                setattr(p, "data", watch[i])
-
-
 # We use the whole watch object from the store/JSON so we can see if there's some related status in terms of a thread
 # running or something similar.
 @app.template_filter('format_last_checked_time')
@@ -272,7 +262,7 @@ def changedetection_app(config=None, datastore_o=None):
     @app.route("/rss", methods=['GET'])
     @login_required
     def rss():
-
+        from . import diff
         limit_tag = request.args.get('tag')
 
         # Sort by last_changed and add the uuid which is usually the key..
@@ -301,6 +291,19 @@ def changedetection_app(config=None, datastore_o=None):
         fg.link(href='https://changedetection.io')
 
         for watch in sorted_watches:
+
+            dates = list(watch['history'].keys())
+            # Re #521 - Don't bother processing this one if theres less than 2 snapshots, means we never had a change detected.
+            if len(dates) < 2:
+                continue
+
+            # Convert to int, sort and back to str again
+            # @todo replace datastore getter that does this automatically
+            dates = [int(i) for i in dates]
+            dates.sort(reverse=True)
+            dates = [str(i) for i in dates]
+            prev_fname = watch['history'][dates[1]]
+
             if not watch['viewed']:
                 # Re #239 - GUID needs to be individual for each event
                 # @todo In the future make this a configurable link back (see work on BASE_URL https://github.com/dgtlmoon/changedetection.io/pull/228)
@@ -316,12 +319,16 @@ def changedetection_app(config=None, datastore_o=None):
 
                 diff_link = {'href': "{}{}".format(base_url, url_for('diff_history_page', uuid=watch['uuid']))}
 
-                # @todo use title if it exists
                 fe.link(link=diff_link)
-                fe.title(title=watch['url'])
 
-                # @todo in the future <description><![CDATA[<html><body>Any code html is valid.</body></html>]]></description>
-                fe.description(description=watch['url'])
+                # @todo watch should be a getter - watch.get('title') (internally if URL else..)
+
+                watch_title = watch.get('title') if watch.get('title') else watch.get('url')
+                fe.title(title=watch_title)
+                latest_fname = watch['history'][dates[0]]
+
+                html_diff = diff.render_diff(prev_fname, latest_fname, include_equal=False, line_feed_sep="</br>")
+                fe.description(description="<![CDATA[<html><body><h4>{}</h4>{}</body></html>".format(watch_title, html_diff))
 
                 fe.guid(guid, permalink=False)
                 dt = datetime.datetime.fromtimestamp(int(watch['newest_history_key']))
@@ -335,6 +342,8 @@ def changedetection_app(config=None, datastore_o=None):
     @app.route("/", methods=['GET'])
     @login_required
     def index():
+        from changedetectionio import forms
+
         limit_tag = request.args.get('tag')
         pause_uuid = request.args.get('pause')
 
@@ -371,7 +380,6 @@ def changedetection_app(config=None, datastore_o=None):
 
         existing_tags = datastore.get_all_tags()
 
-        from changedetectionio import forms
         form = forms.quickWatchForm(request.form)
 
         output = render_template("watch-overview.html",
@@ -383,10 +391,43 @@ def changedetection_app(config=None, datastore_o=None):
                                  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'])
+                                 guid=datastore.data['app_guid'],
+                                 queued_uuids=update_q.queue)
 
         return output
 
+
+    # AJAX endpoint for sending a test
+    @app.route("/notification/send-test", methods=['POST'])
+    @login_required
+    def ajax_callback_send_notification_test():
+
+        import apprise
+        apobj = apprise.Apprise()
+
+        # validate URLS
+        if not len(request.form['notification_urls'].strip()):
+            return make_response({'error': 'No Notification URLs set'}, 400)
+
+        for server_url in request.form['notification_urls'].splitlines():
+            if len(server_url.strip()):
+                if not apobj.add(server_url):
+                    message = '{} is not a valid AppRise URL.'.format(server_url)
+                    return make_response({'error': message}, 400)
+
+        try:
+            n_object = {'watch_url': request.form['window_url'],
+                        'notification_urls': request.form['notification_urls'].splitlines(),
+                        'notification_title': request.form['notification_title'].strip(),
+                        'notification_body': request.form['notification_body'].strip(),
+                        'notification_format': request.form['notification_format'].strip()
+                        }
+            notification_q.put(n_object)
+        except Exception as e:
+            return make_response({'error': str(e)}, 400)
+
+        return 'OK'
+
     @app.route("/scrub", methods=['GET', 'POST'])
     @login_required
     def scrub_page():
@@ -472,49 +513,46 @@ def changedetection_app(config=None, datastore_o=None):
 
     @app.route("/edit/<string:uuid>", methods=['GET', 'POST'])
     @login_required
+    # https://stackoverflow.com/questions/42984453/wtforms-populate-form-with-data-if-data-exists
+    # https://wtforms.readthedocs.io/en/3.0.x/forms/#wtforms.form.Form.populate_obj ?
+
     def edit_page(uuid):
         from changedetectionio import forms
-        form = forms.watchForm(request.form)
+
 
         # More for testing, possible to return the first/only
+        if not datastore.data['watching'].keys():
+            flash("No watches to edit", "error")
+            return redirect(url_for('index'))
+
         if uuid == 'first':
             uuid = list(datastore.data['watching'].keys()).pop()
 
+        if not uuid in datastore.data['watching']:
+            flash("No watch with the UUID %s found." % (uuid), "error")
+            return redirect(url_for('index'))
+
+        form = forms.watchForm(formdata=request.form if request.method == 'POST' else None,
+                                        data=datastore.data['watching'][uuid]
+                                        )
 
         if request.method == 'GET':
-            if not uuid in datastore.data['watching']:
-                flash("No watch with the UUID %s found." % (uuid), "error")
-                return redirect(url_for('index'))
-
-            populate_form_from_watch(form, datastore.data['watching'][uuid])
-
+            # Set some defaults that refer to the main config when None, we do the same in POST,
+            # probably there should be a nice little handler for this.
             if datastore.data['watching'][uuid]['fetch_backend'] is None:
                 form.fetch_backend.data = datastore.data['settings']['application']['fetch_backend']
+            if datastore.data['watching'][uuid]['minutes_between_check'] is None:
+                form.minutes_between_check.data = datastore.data['settings']['requests']['minutes_between_check']
 
         if request.method == 'POST' and form.validate():
 
             # Re #110, if they submit the same as the default value, set it to None, so we continue to follow the default
             if form.minutes_between_check.data == datastore.data['settings']['requests']['minutes_between_check']:
                 form.minutes_between_check.data = None
-
             if form.fetch_backend.data == datastore.data['settings']['application']['fetch_backend']:
                 form.fetch_backend.data = None
 
-            update_obj = {'url': form.url.data.strip(),
-                          'minutes_between_check': form.minutes_between_check.data,
-                          'tag': form.tag.data.strip(),
-                          'title': form.title.data.strip(),
-                          'headers': form.headers.data,
-                          'body': form.body.data,
-                          'method': form.method.data,
-                          'ignore_status_codes': form.ignore_status_codes.data,
-                          'fetch_backend': form.fetch_backend.data,
-                          'trigger_text': form.trigger_text.data,
-                          'notification_title': form.notification_title.data,
-                          'notification_body': form.notification_body.data,
-                          'notification_format': form.notification_format.data,
-                          'extract_title_as_title': form.extract_title_as_title.data,
-                          }
+            extra_update_obj = {}
 
             # Notification URLs
             datastore.data['watching'][uuid]['notification_urls'] = form.notification_urls.data
@@ -526,18 +564,15 @@ def changedetection_app(config=None, datastore_o=None):
             # Reset the previous_md5 so we process a new snapshot including stripping ignore text.
             if form_ignore_text:
                 if len(datastore.data['watching'][uuid]['history']):
-                    update_obj['previous_md5'] = get_current_checksum_include_ignore_text(uuid=uuid)
-
-
-            datastore.data['watching'][uuid]['css_filter'] = form.css_filter.data.strip()
-            datastore.data['watching'][uuid]['subtractive_selectors'] = form.subtractive_selectors.data
+                    extra_update_obj['previous_md5'] = get_current_checksum_include_ignore_text(uuid=uuid)
 
             # 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']:
                 if len(datastore.data['watching'][uuid]['history']):
-                    update_obj['previous_md5'] = get_current_checksum_include_ignore_text(uuid=uuid)
+                    extra_update_obj['previous_md5'] = get_current_checksum_include_ignore_text(uuid=uuid)
 
-            datastore.data['watching'][uuid].update(update_obj)
+            datastore.data['watching'][uuid].update(form.data)
+            datastore.data['watching'][uuid].update(extra_update_obj)
 
             flash("Updated watch.")
 
@@ -548,20 +583,6 @@ def changedetection_app(config=None, datastore_o=None):
             # Queue the watch for immediate recheck
             update_q.put(uuid)
 
-            if form.trigger_check.data:
-                if len(form.notification_urls.data):
-                    n_object = {'watch_url': form.url.data.strip(),
-                                'notification_urls': form.notification_urls.data,
-                                'notification_title': form.notification_title.data,
-                                'notification_body': form.notification_body.data,
-                                'notification_format': form.notification_format.data,
-                                'uuid': uuid
-                                }
-                    notification_q.put(n_object)
-                    flash('Test notification queued.')
-                else:
-                    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' and not form.save_and_preview_button.data:
                 return redirect(url_for('diff_history_page', uuid=uuid))
@@ -576,18 +597,14 @@ def changedetection_app(config=None, datastore_o=None):
             if request.method == 'POST' and not form.validate():
                 flash("An error occurred, please see below.", "error")
 
-            # Re #110 offer the default minutes
-            using_default_minutes = False
-            if form.minutes_between_check.data == None:
-                form.minutes_between_check.data = datastore.data['settings']['requests']['minutes_between_check']
-                using_default_minutes = True
-
+            has_empty_checktime = datastore.data['watching'][uuid].has_empty_checktime
             output = render_template("edit.html",
                                      uuid=uuid,
                                      watch=datastore.data['watching'][uuid],
                                      form=form,
-                                     using_default_minutes=using_default_minutes,
-                                     current_base_url = datastore.data['settings']['application']['base_url']
+                                     has_empty_checktime=has_empty_checktime,
+                                     current_base_url=datastore.data['settings']['application']['base_url'],
+                                     emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False)
                                      )
 
         return output
@@ -595,75 +612,45 @@ def changedetection_app(config=None, datastore_o=None):
     @app.route("/settings", methods=['GET', "POST"])
     @login_required
     def settings_page():
-
         from changedetectionio import content_fetcher, forms
 
-        form = forms.globalSettingsForm(request.form)
+        # Don't use form.data on POST so that it doesnt overrid the checkbox status from the POST status
+        form = forms.globalSettingsForm(formdata=request.form if request.method == 'POST' else None,
+                                        data=datastore.data['settings']
+                                        )
 
-        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']
-            form.fetch_backend.data = datastore.data['settings']['application']['fetch_backend']
-            form.notification_title.data = datastore.data['settings']['application']['notification_title']
-            form.notification_body.data = datastore.data['settings']['application']['notification_body']
-            form.notification_format.data = datastore.data['settings']['application']['notification_format']
-            form.base_url.data = datastore.data['settings']['application']['base_url']
-
-        if request.method == 'POST' and form.data.get('removepassword_button') == True:
+        if request.method == 'POST':
             # Password unset is a GET, but we can lock the session to a salted env password to always need the password
-            if not os.getenv("SALTED_PASS", False):
-                datastore.data['settings']['application']['password'] = False
-                flash("Password protection removed.", 'notice')
-                flask_login.logout_user()
-                return redirect(url_for('settings_page'))
+            if form.application.form.data.get('removepassword_button', False):
+                # SALTED_PASS means the password is "locked" to what we set in the Env var
+                if not os.getenv("SALTED_PASS", False):
+                    datastore.remove_password()
+                    flash("Password protection removed.", 'notice')
+                    flask_login.logout_user()
+                    return redirect(url_for('settings_page'))
 
-        if request.method == 'POST' and form.validate():
-            datastore.data['settings']['application']['notification_urls'] = form.notification_urls.data
-            datastore.data['settings']['requests']['minutes_between_check'] = form.minutes_between_check.data
-            datastore.data['settings']['application']['extract_title_as_title'] = form.extract_title_as_title.data
-            datastore.data['settings']['application']['fetch_backend'] = form.fetch_backend.data
-            datastore.data['settings']['application']['notification_title'] = form.notification_title.data
-            datastore.data['settings']['application']['notification_body'] = form.notification_body.data
-            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
+            if form.validate():
+                datastore.data['settings']['application'].update(form.data['application'])
+                datastore.data['settings']['requests'].update(form.data['requests'])
+                datastore.needs_write = True
 
-            if form.trigger_check.data:
-                if len(form.notification_urls.data):
-                    n_object = {'watch_url': "Test from changedetection.io!",
-                                'notification_urls': form.notification_urls.data,
-                                'notification_title': form.notification_title.data,
-                                'notification_body': form.notification_body.data,
-                                'notification_format': form.notification_format.data,
-                                }
-                    notification_q.put(n_object)
-                    flash('Test notification queued.')
-                else:
-                    flash('No notification URLs set, cannot send test.', 'error')
+                if not os.getenv("SALTED_PASS", False) and len(form.application.form.password.encrypted_password):
+                    datastore.data['settings']['application']['password'] = form.application.form.password.encrypted_password
+                    datastore.needs_write = True
+                    flash("Password protection enabled.", 'notice')
+                    flask_login.logout_user()
+                    return redirect(url_for('index'))
 
-            if not os.getenv("SALTED_PASS", False) and form.password.encrypted_password:
-                datastore.data['settings']['application']['password'] = form.password.encrypted_password
-                flash("Password protection enabled.", 'notice')
-                flask_login.logout_user()
-                return redirect(url_for('index'))
+                flash("Settings updated.")
 
-            datastore.needs_write = True
-            flash("Settings updated.")
-
-        if request.method == 'POST' and not form.validate():
-            flash("An error occurred, please see below.", "error")
+            else:
+                flash("An error occurred, please see below.", "error")
 
         output = render_template("settings.html",
                                  form=form,
                                  current_base_url = datastore.data['settings']['application']['base_url'],
-                                 hide_remove_pass=os.getenv("SALTED_PASS", False))
+                                 hide_remove_pass=os.getenv("SALTED_PASS", False),
+                                 emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False))
 
         return output
 
@@ -676,13 +663,19 @@ def changedetection_app(config=None, datastore_o=None):
         good = 0
 
         if request.method == 'POST':
+            now=time.time()
             urls = request.values.get('urls').split("\n")
+
+            if (len(urls) > 5000):
+                flash("Importing 5,000 of the first URLs from your list, the rest can be imported again.")
+
             for url in urls:
                 url = url.strip()
                 url, *tags = url.split(" ")
                 # Flask wtform validators wont work with basic auth, use validators package
-                if len(url) and validators.url(url):
-                    new_uuid = datastore.add_watch(url=url.strip(), tag=" ".join(tags))
+                # Up to 5000 per batch so we dont flood the server
+                if len(url) and validators.url(url.replace('source:', '')) and good < 5000:
+                    new_uuid = datastore.add_watch(url=url.strip(), tag=" ".join(tags), write_to_disk_now=False)
                     # Straight into the queue.
                     update_q.put(new_uuid)
                     good += 1
@@ -690,7 +683,8 @@ def changedetection_app(config=None, datastore_o=None):
                     if len(url):
                         remaining_urls.append(url)
 
-            flash("{} Imported, {} Skipped.".format(good, len(remaining_urls)))
+            flash("{} Imported in {:.2f}s, {} Skipped.".format(good, time.time()-now,len(remaining_urls)))
+            datastore.needs_write = True
 
             if len(remaining_urls) == 0:
                 # Looking good, redirect to index.
@@ -763,6 +757,9 @@ def changedetection_app(config=None, datastore_o=None):
         except Exception as e:
             previous_version_file_contents = "Unable to read {}.\n".format(previous_file)
 
+
+        screenshot_url = datastore.get_screenshot(uuid)
+
         output = render_template("diff.html", watch_a=watch,
                                  newest=newest_version_file_contents,
                                  previous=previous_version_file_contents,
@@ -773,7 +770,8 @@ 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,
+                                 screenshot=screenshot_url)
 
         return output
 
@@ -833,15 +831,17 @@ def changedetection_app(config=None, datastore_o=None):
         else:
             content.append({'line': "No history found", 'classes': ''})
 
-
+        screenshot_url = datastore.get_screenshot(uuid)
         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'],
+                                 screenshot=screenshot_url,
                                  watch=watch,
                                  uuid=uuid)
+        
         return output
 
     @app.route("/settings/notification-logs", methods=['GET'])
@@ -954,6 +954,28 @@ def changedetection_app(config=None, datastore_o=None):
 
     @app.route("/static/<string:group>/<string:filename>", methods=['GET'])
     def static_content(group, filename):
+        if group == 'screenshot':
+
+            from flask import make_response
+
+            # Could be sensitive, follow password requirements
+            if datastore.data['settings']['application']['password'] and not flask_login.current_user.is_authenticated:
+                abort(403)
+
+            # These files should be in our subdirectory
+            try:
+                # set nocache, set content-type
+                watch_dir = datastore_o.datastore_path + "/" + filename
+                response = make_response(send_from_directory(filename="last-screenshot.png", directory=watch_dir, path=watch_dir + "/last-screenshot.png"))
+                response.headers['Content-type'] = 'image/png'
+                response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
+                response.headers['Pragma'] = 'no-cache'
+                response.headers['Expires'] = 0
+                return response
+
+            except FileNotFoundError:
+                abort(404)
+
         # These files should be in our subdirectory
         try:
             return send_from_directory("static/{}".format(group), path=filename)
@@ -984,10 +1006,14 @@ def changedetection_app(config=None, datastore_o=None):
             flash("Error")
             return redirect(url_for('index'))
 
+
     @app.route("/api/delete", methods=['GET'])
     @login_required
     def api_delete():
         uuid = request.args.get('uuid')
+        # More for testing, possible to return the first/only
+        if uuid == 'first':
+            uuid = list(datastore.data['watching'].keys()).pop()
         datastore.delete(uuid)
         flash('Deleted.')
 
@@ -1113,8 +1139,6 @@ def notification_runner():
                 notification_debug_log = notification_debug_log[-100:]
 
 
-
-
 # Thread runner to check every minute, look for new watches to feed into the Queue.
 def ticker_thread_check_time_launch_checks():
     from changedetectionio import update_worker
@@ -1151,7 +1175,9 @@ def ticker_thread_check_time_launch_checks():
 
         # 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
+
+        recheck_time_minimum_seconds = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 60))
+        recheck_time_system_seconds = int(copied_datastore.data['settings']['requests']['minutes_between_check']) * 60
 
         for uuid, watch in copied_datastore.data['watching'].items():
 
@@ -1160,18 +1186,14 @@ def ticker_thread_check_time_launch_checks():
                 continue
 
             # If they supplied an individual entry minutes to threshold.
-            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
+            threshold = now
+            if watch.threshold_seconds:
+                threshold -= watch.threshold_seconds
             else:
-                # Default system wide.
-                max_time = max_system_wide
-
-            threshold = now - max_time
+                threshold -= recheck_time_system_seconds
 
             # Yeah, put it in the queue, it's more than time
-            if watch['last_checked'] <= threshold:
+            if watch['last_checked'] <= max(threshold, recheck_time_minimum_seconds):
                 if not uuid in running_uuids and uuid not in update_q.queue:
                     update_q.put(uuid)
 
@@ -1179,4 +1201,4 @@ def ticker_thread_check_time_launch_checks():
         time.sleep(3)
 
         # Should be low so we can break this out in testing
-        app.config.exit.wait(1)
+        app.config.exit.wait(1)

changedetectionio/content_fetcher.py

@@ -42,6 +42,14 @@ class Fetcher():
         # Should set self.error, self.status_code and self.content
         pass
 
+    @abstractmethod
+    def quit(self):
+        return
+
+    @abstractmethod
+    def screenshot(self):
+        return
+
     @abstractmethod
     def get_last_status_code(self):
         return self.status_code
@@ -116,16 +124,16 @@ class html_webdriver(Fetcher):
         # request_body, request_method unused for now, until some magic in the future happens.
 
         # check env for WEBDRIVER_URL
-        driver = webdriver.Remote(
+        self.driver = webdriver.Remote(
             command_executor=self.command_executor,
             desired_capabilities=DesiredCapabilities.CHROME,
             proxy=self.proxy)
 
         try:
-            driver.get(url)
+            self.driver.get(url)
         except WebDriverException as e:
             # Be sure we close the session window
-            driver.quit()
+            self.quit()
             raise
 
         # @todo - how to check this? is it possible?
@@ -135,26 +143,33 @@ class html_webdriver(Fetcher):
 
         # @todo - dom wait loaded?
         time.sleep(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
-        self.content = driver.page_source
+        self.content = self.driver.page_source
         self.headers = {}
 
-        driver.quit()
-
+    def screenshot(self):
+        return self.driver.get_screenshot_as_png()
 
+    # Does the connection to the webdriver work? run a test connection.
     def is_ready(self):
         from selenium import webdriver
         from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
         from selenium.common.exceptions import WebDriverException
 
-        driver = webdriver.Remote(
+        self.driver = webdriver.Remote(
             command_executor=self.command_executor,
             desired_capabilities=DesiredCapabilities.CHROME)
 
         # driver.quit() seems to cause better exceptions
-        driver.quit()
-
+        self.quit()
         return True
 
+    def quit(self):
+        if self.driver:
+            try:
+                self.driver.quit()
+            except Exception as e:
+                print("Exception in chrome shutdown/quit" + str(e))
+
 # "html_requests" is listed as the default fetcher in store.py!
 class html_requests(Fetcher):
     fetcher_description = "Basic fast Plaintext/HTTP Client"

changedetectionio/diff.py

@@ -2,22 +2,31 @@
 
 import difflib
 
+
+def same_slicer(l, a, b):
+    if a == b:
+        return [l[a]]
+    else:
+        return l[a:b]
+
 # like .compare but a little different output
 def customSequenceMatcher(before, after, include_equal=False):
     cruncher = difflib.SequenceMatcher(isjunk=lambda x: x in " \\t", a=before, b=after)
 
+    # @todo Line-by-line mode instead of buncghed, including `after` that is not in `before` (maybe unset?)
     for tag, alo, ahi, blo, bhi in cruncher.get_opcodes():
         if include_equal and tag == 'equal':
             g = before[alo:ahi]
             yield g
         elif tag == 'delete':
-            g = "(removed) {}".format(before[alo])
+            g = ["(removed) " + i for i in same_slicer(before, alo, ahi)]
             yield g
         elif tag == 'replace':
-            g = ["(changed) {}".format(before[alo]), "(-> into) {}".format(after[blo])]
+            g = ["(changed) " + i for i in same_slicer(before, alo, ahi)]
+            g += ["(into   ) " + i for i in same_slicer(after, blo, bhi)]
             yield g
         elif tag == 'insert':
-            g = "(added) {}".format(after[blo])
+            g = ["(added  ) " + i for i in same_slicer(after, blo, bhi)]
             yield g
 
 # only_differences - only return info about the differences, no context

changedetectionio/fetch_site_status.py

@@ -4,7 +4,6 @@ import re
 import time
 import urllib3
 
-from inscriptis import get_text
 from changedetectionio import content_fetcher, html_tools
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
@@ -21,6 +20,7 @@ class perform_site_check():
         timestamp = int(time.time())  # used for storage etc too
 
         changed_detected = False
+        screenshot = False  # as bytes
         stripped_text_from_html = ""
 
         watch = self.datastore.data['watching'][uuid]
@@ -46,130 +46,155 @@ class perform_site_check():
         if 'Accept-Encoding' in request_headers and "br" in request_headers['Accept-Encoding']:
             request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
 
-        # @todo check the failures are really handled how we expect
+        timeout = self.datastore.data['settings']['requests']['timeout']
+        url = self.datastore.get_val(uuid, 'url')
+        request_body = self.datastore.get_val(uuid, 'body')
+        request_method = self.datastore.get_val(uuid, 'method')
+        ignore_status_code = self.datastore.get_val(uuid, 'ignore_status_codes')
 
+        # source: support
+        is_source = False
+        if url.startswith('source:'):
+            url = url.replace('source:', '')
+            is_source = True
+
+        # Pluggable content fetcher
+        prefer_backend = watch['fetch_backend']
+        if hasattr(content_fetcher, prefer_backend):
+            klass = getattr(content_fetcher, prefer_backend)
         else:
-            timeout = self.datastore.data['settings']['requests']['timeout']
-            url = self.datastore.get_val(uuid, 'url')
-            request_body = self.datastore.get_val(uuid, 'body')
-            request_method = self.datastore.get_val(uuid, 'method')
-            ignore_status_code = self.datastore.get_val(uuid, 'ignore_status_codes')
+            # If the klass doesnt exist, just use a default
+            klass = getattr(content_fetcher, "html_requests")
 
-            # Pluggable content fetcher
-            prefer_backend = watch['fetch_backend']
-            if hasattr(content_fetcher, prefer_backend):
-                klass = getattr(content_fetcher, prefer_backend)
+        fetcher = klass()
+        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_code)
+        # Fetching complete, now filters
+        # @todo move to class / maybe inside of fetcher abstract base?
+
+        # @note: I feel like the following should be in a more obvious chain system
+        #  - Check filter text
+        #  - Is the checksum different?
+        #  - Do we convert to JSON?
+        # https://stackoverflow.com/questions/41817578/basic-method-chaining ?
+        # return content().textfilter().jsonextract().checksumcompare() ?
+
+        is_json = 'application/json' in fetcher.headers.get('Content-Type', '')
+        is_html = not is_json
+
+        # source: support, basically treat it as plaintext
+        if is_source:
+            is_html = False
+            is_json = False
+
+        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
+
+        if has_filter_rule:
+            if 'json:' in css_filter_rule:
+                stripped_text_from_html = html_tools.extract_json_as_string(content=fetcher.content, jsonpath_filter=css_filter_rule)
+                is_html = False
+
+        if is_html or is_source:
+            # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
+            html_content = fetcher.content
+
+            # 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:
-                # If the klass doesnt exist, just use a default
-                klass = getattr(content_fetcher, "html_requests")
+                # 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] == '/':
+                        html_content = html_tools.xpath_filter(xpath_filter=css_filter_rule, html_content=fetcher.content)
+                    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)
 
+                if not is_source:
+                    # extract text
+                    stripped_text_from_html = \
+                        html_tools.html_to_text(
+                            html_content,
+                            render_anchor_tag_content=self.datastore.data["settings"][
+                                "application"].get(
+                                "render_anchor_tag_content", False)
+                        )
 
-            fetcher = klass()
-            fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_code)
-            # Fetching complete, now filters
-            # @todo move to class / maybe inside of fetcher abstract base?
-
-            # @note: I feel like the following should be in a more obvious chain system
-            #  - Check filter text
-            #  - Is the checksum different?
-            #  - Do we convert to JSON?
-            # https://stackoverflow.com/questions/41817578/basic-method-chaining ?
-            # return content().textfilter().jsonextract().checksumcompare() ?
-
-            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
-
-            if has_filter_rule:
-                if 'json:' in css_filter_rule:
-                    stripped_text_from_html = html_tools.extract_json_as_string(content=fetcher.content, jsonpath_filter=css_filter_rule)
-                    is_html = False
-
-            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 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
+                elif is_source:
                     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] == '/':
-                            html_content = html_tools.xpath_filter(xpath_filter=css_filter_rule, html_content=fetcher.content)
-                        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)
 
             # Re #340 - return the content before the 'ignore text' was applied
             text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
 
-            # We rely on the actual text in the html output.. many sites have random script vars etc,
-            # in the future we'll implement other mechanisms.
 
-            update_obj["last_check_status"] = fetcher.get_last_status_code()
+        # Re #340 - return the content before the 'ignore text' was applied
+        text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
 
-            # If there's text to skip
-            # @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 = html_tools.strip_ignore_text(stripped_text_from_html, text_to_ignore)
-            else:
-                stripped_text_from_html = stripped_text_from_html.encode('utf8')
+        # We rely on the actual text in the html output.. many sites have random script vars etc,
+        # in the future we'll implement other mechanisms.
 
-            # Re #133 - if we should strip whitespaces from triggering the change detected comparison
-            if self.datastore.data['settings']['application'].get('ignore_whitespace', False):
-                fetched_md5 = hashlib.md5(stripped_text_from_html.translate(None, b'\r\n\t ')).hexdigest()
-            else:
-                fetched_md5 = hashlib.md5(stripped_text_from_html).hexdigest()
+        update_obj["last_check_status"] = fetcher.get_last_status_code()
 
-            # On the first run of a site, watch['previous_md5'] will be an empty string, set it the current one.
-            if not len(watch['previous_md5']):
-                watch['previous_md5'] = fetched_md5
-                update_obj["previous_md5"] = fetched_md5
+        # If there's text to skip
+        # @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 = html_tools.strip_ignore_text(stripped_text_from_html, text_to_ignore)
+        else:
+            stripped_text_from_html = stripped_text_from_html.encode('utf8')
 
-            blocked_by_not_found_trigger_text = False
+        # Re #133 - if we should strip whitespaces from triggering the change detected comparison
+        if self.datastore.data['settings']['application'].get('ignore_whitespace', False):
+            fetched_md5 = hashlib.md5(stripped_text_from_html.translate(None, b'\r\n\t ')).hexdigest()
+        else:
+            fetched_md5 = hashlib.md5(stripped_text_from_html).hexdigest()
 
-            if len(watch['trigger_text']):
-                # Yeah, lets block first until something matches
-                blocked_by_not_found_trigger_text = True
-                # 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
+        # On the first run of a site, watch['previous_md5'] will be an empty string, set it the current one.
+        if not len(watch['previous_md5']):
+            watch['previous_md5'] = fetched_md5
+            update_obj["previous_md5"] = fetched_md5
 
+        blocked_by_not_found_trigger_text = False
 
-            if not blocked_by_not_found_trigger_text and watch['previous_md5'] != fetched_md5:
-                changed_detected = True
-                update_obj["previous_md5"] = fetched_md5
-                update_obj["last_changed"] = timestamp
+        if len(watch['trigger_text']):
+            # Yeah, lets block first until something matches
+            blocked_by_not_found_trigger_text = True
+            # 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:
+            changed_detected = True
+            update_obj["previous_md5"] = fetched_md5
+            update_obj["last_changed"] = timestamp
 
-            # Extract title as title
-            if is_html:
-                if self.datastore.data['settings']['application']['extract_title_as_title'] or watch['extract_title_as_title']:
-                    if not watch['title'] or not len(watch['title']):
-                        update_obj['title'] = html_tools.extract_element(find='title', html_content=fetcher.content)
+        # Extract title as title
+        if is_html:
+            if self.datastore.data['settings']['application']['extract_title_as_title'] or watch['extract_title_as_title']:
+                if not watch['title'] or not len(watch['title']):
+                    update_obj['title'] = html_tools.extract_element(find='title', html_content=fetcher.content)
 
+        if self.datastore.data['settings']['application'].get('real_browser_save_screenshot', True):
+            screenshot = fetcher.screenshot()
 
-        return changed_detected, update_obj, text_content_before_ignored_filter
+        fetcher.quit()
+
+        return changed_detected, update_obj, text_content_before_ignored_filter, screenshot

changedetectionio/forms.py

@@ -15,7 +15,6 @@ from wtforms import (
     validators,
     widgets,
 )
-from wtforms.fields import html5
 from wtforms.validators import ValidationError
 
 from changedetectionio import content_fetcher
@@ -26,6 +25,8 @@ from changedetectionio.notification import (
     valid_notification_formats,
 )
 
+from wtforms.fields import FormField
+
 valid_method = {
     'GET',
     'POST',
@@ -122,7 +123,6 @@ class ValidateContentFetcherIsReady(object):
 
     def __call__(self, form, field):
         import urllib3.exceptions
-
         from changedetectionio import content_fetcher
 
         # Better would be a radiohandler that keeps a reference to each class
@@ -231,7 +231,7 @@ 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
@@ -293,39 +293,39 @@ class ValidateCSSJSONXPATHInput(object):
                 # 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
-    url = html5.URLField('URL', validators=[validateURL()])
+    url = fields.URLField('URL', validators=[validateURL()])
     tag = StringField('Group tag', [validators.Optional(), validators.Length(max=35)])
 
+# Common to a single watch and the global settings
 class commonSettingsForm(Form):
 
-    notification_urls = StringListField('Notification URL List', validators=[validators.Optional(), ValidateNotificationBodyAndTitleWhenURLisSet(), ValidateAppRiseServers()])
-    notification_title = StringField('Notification Title', default=default_notification_title, validators=[validators.Optional(), ValidateTokensList()])
-    notification_body = TextAreaField('Notification Body', default=default_notification_body, validators=[validators.Optional(), ValidateTokensList()])
-    notification_format = SelectField('Notification Format', choices=valid_notification_formats.keys(), default=default_notification_format)
-    trigger_check = BooleanField('Send test notification on save')
-    fetch_backend = RadioField(u'Fetch Method', choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
+    notification_urls = StringListField('Notification URL list', validators=[validators.Optional(), ValidateNotificationBodyAndTitleWhenURLisSet(), ValidateAppRiseServers()])
+    notification_title = StringField('Notification title', default=default_notification_title, validators=[validators.Optional(), ValidateTokensList()])
+    notification_body = TextAreaField('Notification body', default=default_notification_body, validators=[validators.Optional(), ValidateTokensList()])
+    notification_format = SelectField('Notification format', choices=valid_notification_formats.keys(), default=default_notification_format)
+    fetch_backend = RadioField(u'Fetch method', choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
     extract_title_as_title = BooleanField('Extract <title> from document and use as watch title', default=False)
 
 class watchForm(commonSettingsForm):
 
-    url = html5.URLField('URL', validators=[validateURL()])
-    tag = StringField('Group tag', [validators.Optional(), validators.Length(max=35)])
+    url = fields.URLField('URL', validators=[validateURL()])
+    tag = StringField('Group tag', [validators.Optional(), validators.Length(max=35)], default='')
 
-    minutes_between_check = html5.IntegerField('Maximum time in minutes until recheck',
+    minutes_between_check = fields.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()])
-    headers = StringDictKeyValue('Request Headers')
-    body = TextAreaField('Request Body', [validators.Optional()])
-    method = SelectField('Request Method', choices=valid_method, default=default_method)
-    ignore_status_codes = BooleanField('Ignore Status Codes (process non-2xx status codes as normal)', default=False)
+    css_filter = StringField('CSS/JSON/XPATH Filter', [ValidateCSSJSONXPATHInput()], default='')
+
+    subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
+    title = StringField('Title', default='')
+
+    ignore_text = StringListField('Ignore text', [ValidateListRegex()])
+    headers = StringDictKeyValue('Request headers')
+    body = TextAreaField('Request body', [validators.Optional()])
+    method = SelectField('Request method', choices=valid_method, default=default_method)
+    ignore_status_codes = BooleanField('Ignore status codes (process non-2xx status codes as normal)', default=False)
     trigger_text = StringListField('Trigger/wait for text', [validators.Optional(), ValidateListRegex()])
 
     save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
@@ -344,15 +344,31 @@ class watchForm(commonSettingsForm):
 
         return result
 
-class globalSettingsForm(commonSettingsForm):
 
-    password = SaltyPasswordField()
-    minutes_between_check = html5.IntegerField('Maximum time in minutes until recheck',
+# datastore.data['settings']['requests']..
+class globalSettingsRequestForm(Form):
+    minutes_between_check = fields.IntegerField('Maximum time in minutes until recheck',
                                                [validators.NumberRange(min=1)])
-    extract_title_as_title = BooleanField('Extract <title> from document and use as watch title')
+# datastore.data['settings']['application']..
+class globalSettingsApplicationForm(commonSettingsForm):
+
     base_url = StringField('Base URL', validators=[validators.Optional()])
     global_subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
     global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
     ignore_whitespace = BooleanField('Ignore whitespace')
+    real_browser_save_screenshot = BooleanField('Save last screenshot when using Chrome?')
+    removepassword_button = SubmitField('Remove password', render_kw={"class": "pure-button pure-button-primary"})
+    render_anchor_tag_content = BooleanField('Render anchor tag content', default=False)
+    fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
+    password = SaltyPasswordField()
+
+
+class globalSettingsForm(Form):
+    # Define these as FormFields/"sub forms", this way it matches the JSON storage
+    # datastore.data['settings']['application']..
+    # datastore.data['settings']['requests']..
+
+    requests = FormField(globalSettingsRequestForm)
+    application = FormField(globalSettingsApplicationForm)
     save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
-    removepassword_button = SubmitField('Remove password', render_kw={"class": "pure-button pure-button-primary"})
+

changedetectionio/html_tools.py

@@ -4,6 +4,9 @@ from typing import List
 
 from bs4 import BeautifulSoup
 from jsonpath_ng.ext import parse
+import re
+from inscriptis import get_text
+from inscriptis.model.config import ParserConfig
 
 
 class JSONNotFound(ValueError):
@@ -25,12 +28,12 @@ def subtractive_css_selector(css_selector, html_content):
         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):
@@ -167,3 +170,35 @@ def strip_ignore_text(content, wordlist, mode="content"):
         return ignored_line_numbers
 
     return "\n".encode('utf8').join(output)
+
+
+def html_to_text(html_content: str, render_anchor_tag_content=False) -> str:
+    """Converts html string to a string with just the text. If ignoring
+    rendering anchor tag content is enable, anchor tag content are also
+    included in the text
+
+    :param html_content: string with html content
+    :param render_anchor_tag_content: boolean flag indicating whether to extract
+    hyperlinks (the anchor tag content) together with text. This refers to the
+    'href' inside 'a' tags.
+    Anchor tag content is rendered in the following manner:
+    '[ text ](anchor tag content)'
+    :return: extracted text from the HTML
+    """
+    #  if anchor tag content flag is set to True define a config for
+    #  extracting this content
+    if render_anchor_tag_content:
+
+        parser_config = ParserConfig(
+            annotation_rules={"a": ["hyperlink"]}, display_links=True
+        )
+
+    # otherwise set config to None
+    else:
+        parser_config = None
+
+    # get text and annotations via inscriptis
+    text_content = get_text(html_content, config=parser_config)
+
+    return text_content
+

changedetectionio/model/App.py

@@ -0,0 +1,49 @@
+import collections
+import os
+
+import uuid as uuid_builder
+
+from changedetectionio.notification import (
+    default_notification_body,
+    default_notification_format,
+    default_notification_title,
+)
+
+class model(dict):
+    def __init__(self, *arg, **kw):
+        super(model, self).__init__(*arg, **kw)
+        self.update({
+            'note': "Hello! If you change this file manually, please be sure to restart your changedetection.io instance!",
+            'watching': {},
+            'settings': {
+                'headers': {
+                    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36',
+                    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
+                    'Accept-Encoding': 'gzip, deflate',  # No support for brolti in python requests yet.
+                    'Accept-Language': 'en-GB,en-US;q=0.9,en;'
+                },
+                'requests': {
+                    'timeout': 15,  # Default 15 seconds
+                    # Default 3 hours
+                    'minutes_between_check': 3 * 60,  # Default 3 hours
+                    'workers': 10  # Number of threads, lower is better for slow connections
+                },
+                'application': {
+                    'password': False,
+                    'base_url' : None,
+                    'extract_title_as_title': False,
+                    'fetch_backend': os.getenv("DEFAULT_FETCH_BACKEND", "html_requests"),
+                    'global_ignore_text': [], # List of text to ignore when calculating the comparison checksum
+                    'global_subtractive_selectors': [],
+                    'ignore_whitespace': False,
+                    'render_anchor_tag_content': False,
+                    'notification_urls': [], # Apprise URL list
+                    # Custom notification content
+                    'notification_title': default_notification_title,
+                    'notification_body': default_notification_body,
+                    'notification_format': default_notification_format,
+                    'real_browser_save_screenshot': True,
+                    'schema_version' : 0
+                }
+            }
+        })

changedetectionio/model/Watch.py

@@ -0,0 +1,62 @@
+import os
+
+import uuid as uuid_builder
+
+minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 5))
+
+from changedetectionio.notification import (
+    default_notification_body,
+    default_notification_format,
+    default_notification_title,
+)
+
+
+class model(dict):
+    def __init__(self, *arg, **kw):
+        self.update({
+            'url': None,
+            'tag': None,
+            'last_checked': 0,
+            'last_changed': 0,
+            'paused': False,
+            'last_viewed': 0,  # history key value of the last viewed via the [diff] link
+            'newest_history_key': "",
+            'title': None,
+            'previous_md5': "",
+            'uuid': str(uuid_builder.uuid4()),
+            'headers': {},  # Extra headers to send
+            'body': None,
+            'method': 'GET',
+            'history': {},  # Dict of timestamp and output stripped filename
+            'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
+            # Custom notification content
+            'notification_urls': [],  # List of URLs to add to the notification Queue (Usually AppRise)
+            'notification_title': default_notification_title,
+            '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,
+            # Re #110, so then if this is set to None, we know to use the default value instead
+            # Requires setting to None on submit if it's the same as the default
+            # Should be all None by default, so we use the system default in this case.
+            'minutes_between_check': None
+        })
+        # goes at the end so we update the default object with the initialiser
+        super(model, self).__init__(*arg, **kw)
+
+
+    @property
+    def has_empty_checktime(self):
+        if self.get('minutes_between_check', None):
+            return False
+        return True
+
+    @property
+    def threshold_seconds(self):
+        sec = self.get('minutes_between_check', None)
+        if sec:
+            sec = sec * 60
+        return sec

changedetectionio/notification.py

@@ -26,13 +26,6 @@ default_notification_title = 'ChangeDetection.io Notification - {watch_url}'
 
 def process_notification(n_object, datastore):
 
-    apobj = apprise.Apprise(debug=True)
-
-    for url in n_object['notification_urls']:
-        url = url.strip()
-        print (">> Process Notification: AppRise notifying {}".format(url))
-        apobj.add(url)
-
     # Get the notification body from datastore
     n_body = n_object.get('notification_body', default_notification_body)
     n_title = n_object.get('notification_title', default_notification_title)
@@ -54,19 +47,49 @@ def process_notification(n_object, datastore):
     # https://github.com/caronc/apprise/wiki/Development_LogCapture
     # Anything higher than or equal to WARNING (which covers things like Connection errors)
     # raise it as an exception
+    apobjs=[]
+    for url in n_object['notification_urls']:
 
-    with apprise.LogCapture(level=apprise.logging.DEBUG) as logs:
-        apobj.notify(
-        body=n_body,
-        title=n_title,
-        body_format=n_format)
+        apobj = apprise.Apprise(debug=True)
+        url = url.strip()
+        if len(url):
+            print(">> Process Notification: AppRise notifying {}".format(url))
+            with apprise.LogCapture(level=apprise.logging.DEBUG) as logs:
+                # Re 323 - Limit discord length to their 2000 char limit total or it wont send.
+                # Because different notifications may require different pre-processing, run each sequentially :(
+                # 2000 bytes minus -
+                #     200 bytes for the overhead of the _entire_ json payload, 200 bytes for {tts, wait, content} etc headers
+                #     Length of URL - Incase they specify a longer custom avatar_url
 
-        # Returns empty string if nothing found, multi-line string otherwise
-        log_value = logs.getvalue()
-        if log_value and 'WARNING' in log_value or 'ERROR' in log_value:
-            raise Exception(log_value)
+                # So if no avatar_url is specified, add one so it can be correctly calculated into the total payload
+                k = '?' if not '?' in url else '&'
+                if not 'avatar_url' in url:
+                    url += k + 'avatar_url=https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png'
 
+                payload_max_size = 1700
+                # Trim everything to a max of 1700 total chars (leave some for padding, control etc)
+                # Incase n_title > 1700
+                # basically trim back the body until the total size fits our threshold
+                # and trim off the n_title to fit always.
+                body_limit = max(0, payload_max_size - len(n_title))
+                body = n_body[0:body_limit] if 'discord://' in url else n_body
 
+                apobj.add(url)
+
+                apobj.notify(
+                    title=n_title[0:payload_max_size],
+                    body=body,
+                    body_format=n_format)
+
+                apobj.clear()
+
+                # Incase it needs to exist in memory for a while after to process(?)
+                apobjs.append(apobj)
+
+                # Returns empty string if nothing found, multi-line string otherwise
+                log_value = logs.getvalue()
+                if log_value and 'WARNING' in log_value or 'ERROR' in log_value:
+                    raise Exception(log_value)
 
 # Notification title + body content parameters get created here.
 def create_notification_parameters(n_object, datastore):

changedetectionio/static/js/notifications.js

@@ -0,0 +1,53 @@
+$(document).ready(function() {
+
+  $('#add-email-helper').click(function (e) {
+    e.preventDefault();
+    email = prompt("Destination email");
+    if(email) {
+      var n = $("#notification_urls");
+      var p=email_notification_prefix;
+      $(n).val( $.trim( $(n).val() )+"\n"+email_notification_prefix+email );
+    }
+  });
+
+  $('#send-test-notification').click(function (e) {
+    e.preventDefault();
+
+    // this can be global
+    var csrftoken = $('input[name=csrf_token]').val();
+    $.ajaxSetup({
+        beforeSend: function(xhr, settings) {
+            if (!/^(GET|HEAD|OPTIONS|TRACE)$/i.test(settings.type) && !this.crossDomain) {
+                xhr.setRequestHeader("X-CSRFToken", csrftoken)
+            }
+        }
+    })
+
+    data = {
+        window_url : window.location.href,
+        notification_urls : $('#notification_urls').val(),
+        notification_title : $('#notification_title').val(),
+        notification_body : $('#notification_body').val(),
+        notification_format : $('#notification_format').val(),
+    }
+    for (key in data) {
+      if (!data[key].length) {
+        alert(key+" is empty, cannot send test.")
+        return;
+      }
+    }
+
+    $.ajax({
+      type: "POST",
+      url: notification_base_url,
+      data : data
+    }).done(function(data){
+      console.log(data);
+      alert('Sent');
+    }).fail(function(data){
+      console.log(data);
+      alert('Error: '+data.responseJSON.error);
+    })
+  });
+});
+

changedetectionio/static/js/tabs.js

@@ -1,6 +1,11 @@
 // Rewrite this is a plugin.. is all this JS really 'worth it?'
 
 
+if(!window.location.hash) {
+  var tab=document.querySelectorAll("#default-tab a");
+  tab[0].click();
+}
+
 window.addEventListener('hashchange', function() {
   var tabs = document.getElementsByClassName('active');
   while (tabs[0]) {
@@ -21,7 +26,6 @@ if (!has_errors.length) {
   focus_error_tab();
 }
 
-
 function set_active_tab() {
   var tab=document.querySelectorAll("a[href='"+location.hash+"']");
   if (tab.length) {

changedetectionio/static/js/watch-overview.js

@@ -0,0 +1,6 @@
+$(function () {
+  // Remove unviewed status when normally clicked
+  $('.diff-link').click(function () {
+    $(this).closest('.unviewed').removeClass('unviewed');
+  });
+});

changedetectionio/static/styles/diff.css

@@ -1,7 +1,8 @@
 #diff-ui {
   background: #fff;
   padding: 2em;
-  margin: 1em;
+  margin-left: 1em;
+  margin-right: 1em;
   border-radius: 5px;
   font-size: 11px; }
   #diff-ui table {
@@ -70,3 +71,8 @@ td#diff-col div {
 /* ignored and triggered? make it obvious error */
 .ignored.triggered {
   background-color: #ff0000; }
+
+.tab-pane-inner#screenshot {
+  text-align: center; }
+  .tab-pane-inner#screenshot img {
+    max-width: 99%; }

changedetectionio/static/styles/diff.scss

@@ -2,7 +2,8 @@
 
     background: #fff;
     padding: 2em;
-    margin: 1em;
+    margin-left: 1em;
+    margin-right: 1em;
     border-radius: 5px;
     font-size: 11px;
 
@@ -85,4 +86,11 @@ td#diff-col div {
 /* ignored and triggered? make it obvious error */
 .ignored.triggered {
   background-color: #ff0000;
+}
+
+.tab-pane-inner#screenshot {
+  text-align: center;
+  img {
+    max-width: 99%;
+  }
 }

changedetectionio/static/styles/styles.css

@@ -31,7 +31,7 @@ a.github-link {
 
 section.content {
   padding-top: 5em;
-  padding-bottom: 5em;
+  padding-bottom: 1em;
   flex-direction: column;
   display: flex;
   align-items: center;
@@ -182,9 +182,15 @@ body:after, body:before {
 
 #notification-customisation {
   border: 1px solid #ccc;
-  padding: 1rem;
+  padding: 0.5rem;
   border-radius: 5px; }
 
+#notification-error-log {
+  border: 1px solid #ccc;
+  padding: 1rem;
+  border-radius: 5px;
+  overflow-wrap: break-word; }
+
 #token-table.pure-table td, #token-table.pure-table th {
   font-size: 80%; }
 
@@ -244,7 +250,7 @@ footer {
 .sticky-tab {
   position: absolute;
   top: 60px;
-  font-size: 8px;
+  font-size: 65%;
   background: #fff;
   padding: 10px; }
   .sticky-tab#left-sticky {
@@ -279,6 +285,11 @@ footer {
     padding-bottom: 1em; }
     .pure-form .pure-control-group div, .pure-form .pure-group div, .pure-form .pure-controls div {
       margin: 0px; }
+    .pure-form .pure-control-group .checkbox > *, .pure-form .pure-group .checkbox > *, .pure-form .pure-controls .checkbox > * {
+      display: inline;
+      vertical-align: middle; }
+    .pure-form .pure-control-group .checkbox > label, .pure-form .pure-group .checkbox > label, .pure-form .pure-controls .checkbox > label {
+      padding-left: 5px; }
   .pure-form .error input {
     background-color: #ffebeb; }
   .pure-form ul.errors {
@@ -310,14 +321,23 @@ footer {
   #nav-menu {
     overflow-x: scroll; } }
 
-/*
+@media only screen and (max-width: 760px), (min-device-width: 768px) and (max-device-width: 800px) {
+  div.sticky-tab#hosted-sticky {
+    top: 60px;
+    left: 0px;
+    right: auto; }
+  section.content {
+    padding-top: 110px; }
+  div.tabs.collapsable ul li {
+    display: block;
+    border-radius: 0px; }
+  input[type='text'] {
+    width: 100%; }
+  /*
 Max width before this PARTICULAR table gets nasty
 This query will take effect for any screen smaller than 760px
 and also iPads specifically.
 */
-@media only screen and (max-width: 760px), (min-device-width: 768px) and (max-device-width: 1024px) {
-  input[type='text'] {
-    width: 100%; }
   .watch-table {
     /* Force table to not be like tables anymore */
     /* Force table to not be like tables anymore */
@@ -394,14 +414,17 @@ and also iPads specifically.
   padding: 20px;
   border-radius: 5px; }
 
+.tab-pane-inner {
+  padding: 0px; }
+  .tab-pane-inner:not(:target) {
+    display: none; }
+  .tab-pane-inner:target {
+    display: block; }
+
 .edit-form {
-  min-width: 70%; }
-  .edit-form .tab-pane-inner {
-    padding: 0px; }
-    .edit-form .tab-pane-inner:not(:target) {
-      display: none; }
-    .edit-form .tab-pane-inner:target {
-      display: block; }
+  min-width: 70%;
+  /* so it cant overflow */
+  max-width: 95%; }
   .edit-form .box-wrap {
     position: relative; }
   .edit-form .inner {

changedetectionio/static/styles/styles.scss

@@ -35,7 +35,7 @@ a.github-link {
 
 section.content {
   padding-top: 5em;
-  padding-bottom: 5em;
+  padding-bottom: 1em;
   flex-direction: column;
   display: flex;
   align-items: center;
@@ -241,10 +241,16 @@ body:after, body:before {
 
 #notification-customisation {
     border: 1px solid #ccc;
-    padding: 1rem;
+    padding: 0.5rem;
     border-radius: 5px;
 }
 
+#notification-error-log {
+    border: 1px solid #ccc;
+    padding: 1rem;
+    border-radius: 5px;
+    overflow-wrap: break-word;
+}
 
 #token-table {
     &.pure-table td, &.pure-table th {
@@ -322,7 +328,7 @@ footer {
 .sticky-tab {
   position: absolute;
   top: 60px;
-  font-size: 8px;
+  font-size: 65%;
   background: #fff;
   padding: 10px;
   &#left-sticky {
@@ -369,6 +375,15 @@ footer {
         div {
             margin: 0px;
         }
+        .checkbox {
+            > * {
+              display: inline;
+              vertical-align: middle;
+            }
+            > label {
+               padding-left: 5px;
+            }
+        }
     }
   /* The input fields with errors */
   .error {
@@ -422,18 +437,35 @@ footer {
   }
 }
 
+
+
+@media only screen and (max-width: 760px), (min-device-width: 768px) and (max-device-width: 800px) {
+
+  div.sticky-tab#hosted-sticky {
+    top: 60px;
+    left: 0px;
+    right: auto;
+  }
+
+  section.content {
+    padding-top: 110px;
+  }
+
+  // Make the tabs easier to hit, they will be all nice and horizontal
+  div.tabs.collapsable ul li {
+    display: block;
+    border-radius: 0px;
+  }
+
+  input[type='text'] {
+    width: 100%;
+  }
+
 /*
 Max width before this PARTICULAR table gets nasty
 This query will take effect for any screen smaller than 760px
 and also iPads specifically.
 */
-
-@media only screen and (max-width: 760px), (min-device-width: 768px) and (max-device-width: 1024px) {
-
-  input[type='text'] {
-    width: 100%;
-  }
-    
   .watch-table {
     /* Force table to not be like tables anymore */
     thead, tbody, th, td, tr {
@@ -556,10 +588,7 @@ $form-edge-padding: 20px;
   }
 }
 
-
-.edit-form {
-  min-width: 70%;
-  .tab-pane-inner {
+.tab-pane-inner {
     &:not(:target) {
         display: none;
     }
@@ -568,7 +597,12 @@ $form-edge-padding: 20px;
     }
     // doesnt need padding because theres another row of buttons/activity
     padding: 0px;
-  }
+}
+
+.edit-form {
+  min-width: 70%;
+  /* so it cant overflow */
+  max-width: 95%;
   .box-wrap {
     position: relative;
   }

changedetectionio/store.py

@@ -8,11 +8,7 @@ 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.model import Watch, App
 
 
 # Is there an existing library to ensure some data store (JSON etc) is in sync with CRUD methods?
@@ -29,69 +25,10 @@ class ChangeDetectionStore:
         self.json_store_path = "{}/url-watches.json".format(self.datastore_path)
         self.stop_thread = False
 
-        self.__data = {
-            'note': "Hello! If you change this file manually, please be sure to restart your changedetection.io instance!",
-            'watching': {},
-            'settings': {
-                'headers': {
-                    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36',
-                    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
-                    'Accept-Encoding': 'gzip, deflate',  # No support for brolti in python requests yet.
-                    'Accept-Language': 'en-GB,en-US;q=0.9,en;'
-                },
-                'requests': {
-                    'timeout': 15,  # Default 15 seconds
-                    'minutes_between_check': 3 * 60,  # Default 3 hours
-                    'workers': 10  # Number of threads, lower is better for slow connections
-                },
-                'application': {
-                    'password': False,
-                    'base_url' : None,
-                    '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
-                    'notification_title': default_notification_title,
-                    'notification_body': default_notification_body,
-                    'notification_format': default_notification_format,
-                }
-            }
-        }
+        self.__data = App.model()
 
         # Base definition for all watchers
-        self.generic_definition = {
-            'url': None,
-            'tag': None,
-            'last_checked': 0,
-            'last_changed': 0,
-            'paused': False,
-            'last_viewed': 0,  # history key value of the last viewed via the [diff] link
-            'newest_history_key': "",
-            'title': None,
-            # Re #110, so then if this is set to None, we know to use the default value instead
-            # Requires setting to None on submit if it's the same as the default
-            'minutes_between_check': None,
-            'previous_md5': "",
-            'uuid': str(uuid_builder.uuid4()),
-            'headers': {},  # Extra headers to send
-            'body': None,
-            'method': 'GET',
-            'history': {},  # Dict of timestamp and output stripped filename
-            'ignore_text': [], # List of text to ignore when calculating the comparison checksum
-            # Custom notification content
-            'notification_urls': [], # List of URLs to add to the notification Queue (Usually AppRise)
-            'notification_title': default_notification_title,
-            '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
-        }
+        self.generic_definition = Watch.model()
 
         if path.isfile('changedetectionio/source.txt'):
             with open('changedetectionio/source.txt') as f:
@@ -188,6 +125,10 @@ class ChangeDetectionStore:
         self.data['watching'][uuid].update({'last_viewed': int(timestamp)})
         self.needs_write = True
 
+    def remove_password(self):
+        self.__data['settings']['application']['password'] = False
+        self.needs_write = True
+
     def update_watch(self, uuid, update_obj):
 
         with self.lock:
@@ -331,15 +272,14 @@ class ChangeDetectionStore:
         self.needs_write = True
         return changes_removed
 
-    def add_watch(self, url, tag="", extras=None):
+    def add_watch(self, url, tag="", extras=None, write_to_disk_now=True):
         if extras is None:
             extras = {}
 
         with self.lock:
             # @todo use a common generic version of this
             new_uuid = str(uuid_builder.uuid4())
-            _blank = deepcopy(self.generic_definition)
-            _blank.update({
+            new_watch = Watch.model({
                 'url': url,
                 'tag': tag
             })
@@ -350,9 +290,8 @@ class ChangeDetectionStore:
                 if k in apply_extras:
                     del apply_extras[k]
 
-            _blank.update(apply_extras)
-
-            self.data['watching'][new_uuid] = _blank
+            new_watch.update(apply_extras)
+            self.__data['watching'][new_uuid]=new_watch
 
         # Get the directory ready
         output_path = "{}/{}".format(self.datastore_path, new_uuid)
@@ -361,7 +300,8 @@ class ChangeDetectionStore:
         except FileExistsError:
             print(output_path, "already exists.")
 
-        self.sync_to_json()
+        if write_to_disk_now:
+            self.sync_to_json()
         return new_uuid
 
     # Save some text file to the appropriate path and bump the history
@@ -381,6 +321,22 @@ class ChangeDetectionStore:
 
         return fname
 
+    def get_screenshot(self, watch_uuid):
+        output_path = "{}/{}".format(self.datastore_path, watch_uuid)
+        fname = "{}/last-screenshot.png".format(output_path)
+        if path.isfile(fname):
+            return fname
+
+        return False
+
+    # Save as PNG, PNG is larger but better for doing visual diff in the future
+    def save_screenshot(self, watch_uuid, screenshot: bytes):
+        output_path = "{}/{}".format(self.datastore_path, watch_uuid)
+        fname = "{}/last-screenshot.png".format(output_path)
+        with open(fname, 'wb') as f:
+            f.write(screenshot)
+            f.close()
+
     def sync_to_json(self):
         logging.info("Saving JSON..")
 

changedetectionio/templates/_common_fields.jinja

@@ -1,7 +1,7 @@
 
 {% from '_helpers.jinja' import render_field %}
 
-{% macro render_common_settings_form(form, current_base_url) %}
+{% macro render_common_settings_form(form, current_base_url, emailprefix) %}
 
                         <div class="pure-control-group">
                             {{ render_field(form.notification_urls, rows=5, placeholder="Examples:
@@ -13,13 +13,19 @@
                             <div class="pure-form-message-inline">
                               <ul>
                                 <li>Use <a target=_new href="https://github.com/caronc/apprise">AppRise URLs</a> for notification to just about any service! <i><a target=_new href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes">Please read the notification services wiki here for important configuration notes</a></i>.</li>
-                                <li><code>discord://</code> will silently fail if the total message length is more than 2000 chars.</li>
+                                <li><code>discord://</code> only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
                                 <li><code>tgram://</code> bots cant send messages to other bots, so you should specify chat ID of non-bot user.</li>
-                                <li>Go here for <a href="{{url_for('notification_logs')}}">Notification debug logs</a></li>
+                                <li>Go here for <a href="{{url_for('notification_logs')}}">notification debug logs</a></li>
                               </ul>
                             </div>
+                            <br/>
+                            <a id="send-test-notification" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Send test notification</a>
+{% if emailprefix %}
+                            <a id="add-email-helper" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Add email</a>
+
+{% endif %}
                         </div>
-                        <div id="notification-customisation">
+                        <div id="notification-customisation" class="pure-control-group">
                             <div class="pure-control-group">
                                 {{ render_field(form.notification_title, class="m-d") }}
                                 <span class="pure-form-message-inline">Title for all notifications</span>
@@ -93,7 +99,4 @@
                             </span>
                             </div>
                         </div>
-                        <div class="pure-control-group">
-                            {{ render_field(form.trigger_check) }}
-                        </div>
 {% endmacro %}

changedetectionio/templates/_helpers.jinja

@@ -1,3 +1,30 @@
+{% macro render_field(field) %}
+  <div {% if field.errors %} class="error" {% endif %}>{{ field(**kwargs)|safe }}
+  <div {% if field.errors %} class="error" {% endif %}>{{ field.label }}</div>
+
+  {% if field.errors %}
+    <ul class=errors>
+    {% for error in field.errors %}
+      <li>{{ error }}</li>
+    {% endfor %}
+    </ul>
+  {% endif %}
+  </div>
+{% endmacro %}
+
+{% macro render_checkbox_field(field) %}
+  <div class="checkbox {% if field.errors %} error {% endif %}">
+  {{ field(**kwargs)|safe }} {{ field.label }}
+  {% if field.errors %}
+    <ul class=errors>
+    {% for error in field.errors %}
+      <li>{{ error }}</li>
+    {% endfor %}
+    </ul>
+  {% endif %}
+  </div>
+{% endmacro %}
+
 {% macro render_field(field) %}
   <div {% if field.errors %} class="error" {% endif %}>{{ field.label }}</div>
   <div {% if field.errors %} class="error" {% endif %}>{{ field(**kwargs)|safe }}

changedetectionio/templates/base.html

@@ -5,6 +5,7 @@
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
     <meta name="description" content="Self hosted website change detection.">
     <title>Change Detection{{extra_title}}</title>
+    <link rel="alternate" type="application/rss+xml" title="Changedetection.io » Feed{% if active_tag %}- {{active_tag}}{% endif %}" href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}" />
     <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='pure-min.css')}}">
     <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='styles.css')}}">
     {% if extra_stylesheets %}
@@ -17,6 +18,8 @@
         background-image: url({{url_for('static_content', group='images', filename='gradient-border.png')}});
     }
     </style>
+    <script type="text/javascript" src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
+
 </head>
 
 <body>

changedetectionio/templates/diff.html

@@ -1,7 +1,6 @@
 {% extends 'base.html' %}
 
 {% block content %}
-
 <div id="settings">
     <h1>Differences</h1>
     <form class="pure-form " action="" method="GET">
@@ -35,21 +34,45 @@
 <div id="diff-jump">
     <a onclick="next_diff();">Jump</a>
 </div>
+
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<div class="tabs">
+    <ul>
+        <li class="tab" id="default-tab"><a href="#text">Text</a></li>
+{% if screenshot %}
+        <li class="tab"><a href="#screenshot">Current screenshot</a></li>
+{% endif %}
+    </ul>
+</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>
-            <!-- just proof of concept copied straight from github.com/kpdecker/jsdiff -->
-            <td id="a" style="display: none;">{{previous}}</td>
-            <td id="b" style="display: none;">{{newest}}</td>
-            <td id="diff-col">
-                <span id="result"></span>
-            </td>
-        </tr>
-        </tbody>
-    </table>
-    Diff algorithm from the amazing <a href="https://github.com/kpdecker/jsdiff">github.com/kpdecker/jsdiff</a>
+     <div class="tab-pane-inner" id="text">
+         <div class="tip">Pro-tip: Use <strong>show current snapshot</strong> tab to visualise what will be ignored.
+         </div>
+         <table>
+             <tbody>
+             <tr>
+                 <!-- just proof of concept copied straight from github.com/kpdecker/jsdiff -->
+                 <td id="a" style="display: none;">{{previous}}</td>
+                 <td id="b" style="display: none;">{{newest}}</td>
+                 <td id="diff-col">
+                     <span id="result"></span>
+                 </td>
+             </tr>
+             </tbody>
+         </table>
+         Diff algorithm from the amazing <a href="https://github.com/kpdecker/jsdiff">github.com/kpdecker/jsdiff</a>
+     </div>
+
+{% if screenshot %}
+     <div class="tab-pane-inner" id="screenshot">
+         <p>
+         <i>For now, only the most recent screenshot is saved and displayed.</i>
+             </p>
+
+        <img src="{{url_for('static_content', group='screenshot', filename=uuid)}}">
+     </div>
+{% endif %}
 
 </div>
 

changedetectionio/templates/edit.html

@@ -1,13 +1,19 @@
 {% extends 'base.html' %}
 {% block content %}
-{% from '_helpers.jinja' import render_field %}
-{% from '_helpers.jinja' import render_button %}
+{% from '_helpers.jinja' import render_field, render_checkbox_field, 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>
+<script>
+    const notification_base_url="{{url_for('ajax_callback_send_notification_test')}}";
+{% if emailprefix %}
+    const email_notification_prefix=JSON.parse('{{ emailprefix|tojson }}');
+{% endif %}
+</script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
 
 <div class="edit-form monospaced-textarea">
 
-    <div class="tabs">
+    <div class="tabs collapsable">
         <ul>
             <li class="tab" id="default-tab"><a href="#general">General</a></li>
             <li class="tab"><a href="#request">Request</a></li>
@@ -36,7 +42,7 @@
                     </div>
                     <div class="pure-control-group">
                         {{ render_field(form.minutes_between_check) }}
-                        {% if using_default_minutes %}
+                        {% if has_empty_checktime %}
                         <span class="pure-form-message-inline">Currently using the <a
                                 href="{{ url_for('settings_page', uuid=uuid) }}">default global settings</a>, change to another value if you want to be specific.</span>
                         {% else %}
@@ -45,7 +51,7 @@
                         {% endif %}
                     </div>
                     <div class="pure-control-group">
-                        {{ render_field(form.extract_title_as_title) }}
+                        {{ render_checkbox_field(form.extract_title_as_title) }}
                     </div>
                 </fieldset>
             </div>
@@ -82,7 +88,7 @@ User-Agent: wonderbra 1.0") }}
 }") }}
                     </div>
                     <div>
-                        {{ render_field(form.ignore_status_codes) }}
+                        {{ render_checkbox_field(form.ignore_status_codes) }}
                     </div>
                 </fieldset>
                 <br/>
@@ -92,7 +98,7 @@ User-Agent: wonderbra 1.0") }}
                 <strong>Note: <i>These settings override the global settings for this watch.</i></strong>
                 <fieldset>
                     <div class="field-group">
-                        {{ render_common_settings_form(form, current_base_url) }}
+                        {{ render_common_settings_form(form, current_base_url, emailprefix) }}
                     </div>
                 </fieldset>
             </div>
@@ -162,7 +168,7 @@ nav
                     <ul>
                         <li>Text to wait for before triggering a change/notification, all text and regex are tested <i>case-insensitive</i>.</li>
                         <li>Trigger text is processed from the result-text that comes out of any CSS/JSON Filters for this watch</li>
-                        <li>Each line is process separately (think of each line as "OR")</li>
+                        <li>Each line is processed separately (think of each line as "OR")</li>
                         <li>Note: Wrap in forward slash / to use regex  example: <code>/foo\d/</code></li>
                     </ul>
                         </span>

changedetectionio/templates/login.html

@@ -9,7 +9,7 @@
             <div class="pure-control-group">
                 <label for="password">Password</label>
                 <input type="password" id="password" required="" name="password" value=""
-                       size="15"/>
+                       size="15" autofocus />
                 <input type="hidden" id="email" name="email" value="defaultuser@changedetection.io" />
             </div>
             <div class="pure-control-group">

changedetectionio/templates/notification-log.html

@@ -5,7 +5,7 @@
      <div class="inner">
 
          <h4 style="margin-top: 0px;">The following issues were detected when sending notifications</h4>
-                <div id="notification-customisation">
+                <div id="notification-error-log">
                 <ul style="font-size: 80%; margin:0px; padding: 0 0 0 7px">
                 {% for log in logs|reverse %}
                     <li>{{log}}</li>

changedetectionio/templates/preview.html

@@ -6,18 +6,40 @@
     <h1>Current - {{watch.last_checked|format_timestamp_timeago}}</h1>
 </div>
 
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<div class="tabs">
+    <ul>
+        <li class="tab" id="default-tab"><a href="#text">Text</a></li>
+{% if screenshot %}
+        <li class="tab"><a href="#screenshot">Current screenshot</a></li>
+{% endif %}
+    </ul>
+</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">
+    <div class="tab-pane-inner" id="text">
+        <span class="ignored">Grey lines are ignored</span> <span class="triggered">Blue lines are triggers</span>
+        <table>
+            <tbody>
+            <tr>
+                <td id="diff-col">
                     {% for row in content %}
                     <div class="{{row.classes}}">{{row.line}}</div>
                     {% endfor %}
-            </td>
-        </tr>
-        </tbody>
-    </table>
+                </td>
+            </tr>
+            </tbody>
+        </table>
+    </div>
+
+{% if screenshot %}
+     <div class="tab-pane-inner" id="screenshot">
+         <p>
+         <i>For now, only the most recent screenshot is saved and displayed.</i>
+             </p>
+
+        <img src="{{url_for('static_content', group='screenshot', filename=uuid)}}">
+     </div>
+{% endif %}
 </div>
 {% endblock %}

changedetectionio/templates/settings.html

@@ -1,14 +1,20 @@
 {% extends 'base.html' %}
 
 {% block content %}
-{% from '_helpers.jinja' import render_field, render_button %}
+{% from '_helpers.jinja' import render_field, render_checkbox_field, render_button %}
 {% from '_common_fields.jinja' import render_common_settings_form %}
-
+<script>
+    const notification_base_url="{{url_for('ajax_callback_send_notification_test')}}";
+{% if emailprefix %}
+    const email_notification_prefix=JSON.parse('{{emailprefix|tojson}}');
+{% endif %}
+</script>
 <script type="text/javascript" src="{{url_for('static_content', group='js', filename='settings.js')}}" defer></script>
 <script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
 
 <div class="edit-form">
-    <div class="tabs">
+    <div class="tabs collapsable">
         <ul>
             <li class="tab" id="default-tab"><a href="#general">General</a></li>
             <li class="tab"><a href="#notifications">Notifications</a></li>
@@ -22,15 +28,15 @@
             <div class="tab-pane-inner" id="general">
                 <fieldset>
                     <div class="pure-control-group">
-                        {{ render_field(form.minutes_between_check) }}
+                        {{ render_field(form.requests.form.minutes_between_check) }}
                         <span class="pure-form-message-inline">Default time for all watches, when the watch does not have a specific time setting.</span>
                     </div>
                     <div class="pure-control-group">
                         {% if not hide_remove_pass %}
                             {% if current_user.is_authenticated %}
-                                {{ render_button(form.removepassword_button) }}
+                                {{ render_button(form.application.form.removepassword_button) }}
                             {% else %}
-                            {{ render_field(form.password) }}
+                            {{ render_field(form.application.form.password) }}
                             <span class="pure-form-message-inline">Password protection for your changedetection.io application.</span>
                             {% endif %}
                         {% else %}
@@ -38,7 +44,7 @@
                         {% endif %}
                     </div>
                     <div class="pure-control-group">
-                        {{ render_field(form.base_url, placeholder="http://yoursite.com:5000/",
+                        {{ render_field(form.application.form.base_url, placeholder="http://yoursite.com:5000/",
                         class="m-d") }}
                         <span class="pure-form-message-inline">
                             Base URL used for the {base_url} token in notifications and RSS links.<br/>Default value is the ENV var 'BASE_URL' (Currently "{{current_base_url}}"),
@@ -47,25 +53,29 @@
                     </div>
 
                     <div class="pure-control-group">
-                        {{ render_field(form.extract_title_as_title) }}
+                        {{ render_checkbox_field(form.application.form.extract_title_as_title) }}
                         <span class="pure-form-message-inline">Note: This will automatically apply to all existing watches.</span>
                     </div>
+
+                    <div class="pure-control-group">
+                        {{ render_checkbox_field(form.application.form.real_browser_save_screenshot) }}
+                        <span class="pure-form-message-inline">When using a Chrome browser, a screenshot from the last check will be available on the Diff page</span>
+                    </div>
+
                 </fieldset>
             </div>
 
             <div class="tab-pane-inner" id="notifications">
                 <fieldset>
                     <div class="field-group">
-                        {{ render_common_settings_form(form, current_base_url) }}
+                        {{ render_common_settings_form(form.application.form, current_base_url, emailprefix) }}
                     </div>
                 </fieldset>
-                <a href="{{url_for('notification_logs')}}">Notification debug logs</a>
-
             </div>
 
             <div class="tab-pane-inner" id="fetching">
                 <div class="pure-control-group">
-                    {{ render_field(form.fetch_backend) }}
+                    {{ render_field(form.application.form.fetch_backend) }}
                     <span class="pure-form-message-inline">
                         <p>Use the <strong>Basic</strong> method (default) where your watched sites don't need Javascript to render.</p>
                         <p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
@@ -77,14 +87,20 @@
             <div class="tab-pane-inner" id="filters">
 
                     <fieldset class="pure-group">
-                    {{ render_field(form.ignore_whitespace) }}
+                    {{ render_checkbox_field(form.application.form.ignore_whitespace) }}
                     <span class="pure-form-message-inline">Ignore whitespace, tabs and new-lines/line-feeds when considering if a change was detected.<br/>
-                    <i>Note:</i> Changing this will change the status of your existing watches, possibily trigger alerts etc.
+                    <i>Note:</i> Changing this will change the status of your existing watches, possibly trigger alerts etc.
+                    </span>
+                    </fieldset>
+                <fieldset class="pure-group">
+                    {{ render_checkbox_field(form.application.form.render_anchor_tag_content) }}
+                    <span class="pure-form-message-inline">Render anchor tag content, default disabled, when enabled renders links as <code>(link text)[https://somesite.com]</code>
+                        <br/>
+                    <i>Note:</i> Changing this could affect the content of your existing watches, possibly trigger alerts etc.
                     </span>
                     </fieldset>
-
                     <fieldset class="pure-group">
-                      {{ render_field(form.global_subtractive_selectors, rows=5, placeholder="header
+                      {{ render_field(form.application.form.global_subtractive_selectors, rows=5, placeholder="header
 footer
 nav
 .stockticker") }}
@@ -96,7 +112,7 @@ nav
                       </span>
                     </fieldset>
                     <fieldset class="pure-group">
-                    {{ render_field(form.global_ignore_text, rows=5, placeholder="Some text to ignore in a line
+                    {{ render_field(form.application.form.global_ignore_text, rows=5, placeholder="Some text to ignore in a line
 /some.regex\d{2}/ for case-INsensitive regex
                     ") }}
                     <span class="pure-form-message-inline">Note: This is applied globally in addition to the per-watch rules.</span><br/>

changedetectionio/templates/watch-overview.html

@@ -1,7 +1,8 @@
 {% extends 'base.html' %}
 {% block content %}
 {% from '_helpers.jinja' import render_simple_field %}
-
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
 <div class="box">
 
     <form class="pure-form" action="{{ url_for('api_watch_add') }}" method="POST" id="new-watch-form">
@@ -9,7 +10,7 @@
         <fieldset>
             <legend>Add a new change detection watch</legend>
                 {{ render_simple_field(form.url, placeholder="https://...", required=true) }}
-                {{ render_simple_field(form.tag, value=active_tag if active_tag else '', placeholder="tag") }}
+                {{ render_simple_field(form.tag, value=active_tag if active_tag else '', placeholder="watch group") }}
             <button type="submit" class="pure-button pure-button-primary">Watch</button>
         </fieldset>
         <!-- add extra stuff, like do a http POST and send headers -->
@@ -45,12 +46,13 @@
                 {% if watch.last_error is defined and watch.last_error != False %}error{% endif %}
                 {% if watch.last_notification_error is defined and watch.last_notification_error != False %}error{% endif %}
                 {% if watch.paused is defined and watch.paused != False %}paused{% endif %}
-                {% if watch.newest_history_key| int > watch.last_viewed| int %}unviewed{% endif %}">
+                {% if watch.newest_history_key| int > watch.last_viewed| int %}unviewed{% endif %}
+                {% if watch.uuid in queued_uuids %}queued{% endif %}">
                 <td class="inline">{{ loop.index }}</td>
                 <td class="inline paused-state state-{{watch.paused}}"><a href="{{url_for('index', pause=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="Pause" title="Pause"/></a></td>
 
                 <td class="title-col inline">{{watch.title if watch.title is not none and watch.title|length > 0 else watch.url}}
-                    <a class="external" target="_blank" rel="noopener" href="{{ watch.url }}"></a>
+                    <a class="external" target="_blank" rel="noopener" href="{{ watch.url.replace('source:','') }}"></a>
                     {%if watch.fetch_backend == "html_webdriver" %}<img style="height: 1em; display:inline-block;" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" />{% endif %}
 
                     {% if watch.last_error is defined and watch.last_error != False %}
@@ -71,11 +73,11 @@
                     {% endif %}
                 </td>
                 <td>
-                    <a href="{{ url_for('api_watch_checknow', uuid=watch.uuid, tag=request.args.get('tag')) }}"
-                       class="pure-button button-small pure-button-primary">Recheck</a>
+                    <a {% if watch.uuid in queued_uuids %}disabled="true"{% endif %} href="{{ url_for('api_watch_checknow', uuid=watch.uuid, tag=request.args.get('tag')) }}"
+                       class="recheck pure-button button-small pure-button-primary">{% if watch.uuid in queued_uuids %}Queued{% else %}Recheck{% endif %}</a>
                     <a href="{{ url_for('edit_page', uuid=watch.uuid)}}" class="pure-button button-small pure-button-primary">Edit</a>
                     {% if watch.history|length >= 2 %}
-                    <a href="{{ url_for('diff_history_page', uuid=watch.uuid) }}" target="{{watch.uuid}}" class="pure-button button-small pure-button-primary">Diff</a>
+                    <a href="{{ url_for('diff_history_page', uuid=watch.uuid) }}" target="{{watch.uuid}}" class="pure-button button-small pure-button-primary diff-link">Diff</a>
                     {% else %}
                         {% if watch.history|length == 1 %}
                             <a href="{{ url_for('preview_page', uuid=watch.uuid)}}" target="{{watch.uuid}}" class="pure-button button-small pure-button-primary">Preview</a>

changedetectionio/tests/conftest.py

@@ -16,6 +16,7 @@ def cleanup(datastore_path):
     # Unlink test output files
     files = ['output.txt',
              'url-watches.json',
+             'secret.txt',
              'notification.txt',
              'count.txt',
              'endpoint-content.txt'

changedetectionio/tests/test_access_control.py

@@ -1,5 +1,5 @@
 from flask import url_for
-
+from . util import live_server_setup
 
 def test_check_access_control(app, client):
     # Still doesnt work, but this is closer.
@@ -12,9 +12,9 @@ def test_check_access_control(app, client):
         # Enable password check.
         res = c.post(
             url_for("settings_page"),
-            data={"password": "foobar",
-                  "minutes_between_check": 180,
-                  'fetch_backend': "html_requests"},
+            data={"application-password": "foobar",
+                  "requests-minutes_between_check": 180,
+                  'application-fetch_backend': "html_requests"},
             follow_redirects=True
         )
 
@@ -49,74 +49,31 @@ def test_check_access_control(app, client):
         assert b"minutes_between_check" in res.data
         assert b"fetch_backend" in res.data
 
+        ##################################################
+        # Remove password button, and check that it worked
+        ##################################################
         res = c.post(
             url_for("settings_page"),
             data={
-                "minutes_between_check": 180,
-                "tag": "",
-                "headers": "",
-                "fetch_backend": "html_webdriver",
-                "removepassword_button": "Remove password"
+                "requests-minutes_between_check": 180,
+                "application-fetch_backend": "html_webdriver",
+                "application-removepassword_button": "Remove password"
             },
             follow_redirects=True,
         )
+        assert b"Password protection removed." in res.data
+        assert b"LOG OUT" not in res.data
 
-# There was a bug where saving the settings form would submit a blank password
-def test_check_access_control_no_blank_password(app, client):
-    # Still doesnt work, but this is closer.
-
-    with app.test_client() as c:
-        # Check we dont have any password protection enabled yet.
-        res = c.get(url_for("settings_page"))
-        assert b"Remove password" not in res.data
-
-        # Enable password check.
+        ############################################################
+        # Be sure a blank password doesnt setup password protection
+        ############################################################
         res = c.post(
             url_for("settings_page"),
-            data={"password": "",
-                  "minutes_between_check": 180,
-                  'fetch_backend': "html_requests"},
+            data={"application-password": "",
+                  "requests-minutes_between_check": 180,
+                  'application-fetch_backend': "html_requests"},
             follow_redirects=True
         )
 
-        assert b"Password protection enabled." not in res.data
-        assert b"Login" not in res.data
+        assert b"Password protection enabled" not in res.data
 
-
-# There was a bug where saving the settings form would submit a blank password
-def test_check_access_no_remote_access_to_remove_password(app, client):
-    # Still doesnt work, but this is closer.
-
-    with app.test_client() as c:
-        # Check we dont have any password protection enabled yet.
-        res = c.get(url_for("settings_page"))
-        assert b"Remove password" not in res.data
-
-        # Enable password check.
-        res = c.post(
-            url_for("settings_page"),
-            data={"password": "password",
-                  "minutes_between_check": 180,
-                  'fetch_backend': "html_requests"},
-            follow_redirects=True
-        )
-
-        assert b"Password protection enabled." in res.data
-        assert b"Login" in res.data
-
-        res = c.post(
-            url_for("settings_page"),
-            data={
-                "minutes_between_check": 180,
-                "tag": "",
-                "headers": "",
-                "fetch_backend": "html_webdriver",
-                "removepassword_button": "Remove password"
-            },
-            follow_redirects=True,
-        )
-        assert b"Password protection removed." not in res.data
-
-        res = c.get(url_for("index"),
-              follow_redirects=True)
-        assert b"watch-table-wrapper" not in res.data

changedetectionio/tests/test_api.py

@@ -26,7 +26,8 @@ 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', content_type="text/plain", _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

@@ -50,6 +50,14 @@ def test_check_basic_change_detection_functionality(client, live_server):
 
     #####################
 
+    # Check HTML conversion detected and workd
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+    # Check this class does not appear (that we didnt see the actual source)
+    assert b'foobar-detection' not in res.data
+
     # Make a change
     set_modified_response()
 
@@ -70,6 +78,11 @@ def test_check_basic_change_detection_functionality(client, live_server):
     res = client.get(url_for("rss"))
     expected_url = url_for('test_endpoint', _external=True)
     assert b'<rss' in res.data
+
+    # re #16 should have the diff in here too
+    assert b'(into   ) which has this one new line' in res.data
+    assert b'CDATA' in res.data
+    
     assert expected_url.encode('utf-8') in res.data
 
     # Following the 'diff' link, it should no longer display as 'unviewed' even after we recheck it a few times
@@ -96,7 +109,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
     # Enable auto pickup of <title> in settings
     res = client.post(
         url_for("settings_page"),
-        data={"extract_title_as_title": "1", "minutes_between_check": 180, 'fetch_backend': "html_requests"},
+        data={"application-extract_title_as_title": "1", "requests-minutes_between_check": 180, 'application-fetch_backend': "html_requests"},
         follow_redirects=True
     )
 

changedetectionio/tests/test_html_to_text.py

@@ -0,0 +1,38 @@
+#!/usr/bin/python3
+"""Test suite for the method to extract text from an html string"""
+from ..html_tools import html_to_text
+
+
+def test_html_to_text_func():
+    test_html = """<html>
+       <body>
+     Some initial text</br>
+     <p>Which is across multiple lines</p>
+     <a href="/first_link"> More Text </a>
+     </br>
+     So let's see what happens.  </br>
+     <a href="second_link.com"> Even More Text </a>
+     </body>
+     </html>
+    """
+
+    # extract text, with 'render_anchor_tag_content' set to False
+    text_content = html_to_text(test_html, render_anchor_tag_content=False)
+
+    no_links_text = \
+        "Some initial text\n\nWhich is across multiple " \
+        "lines\n\nMore Text So let's see what happens. Even More Text"
+
+    # check that no links are in the extracted text
+    assert text_content == no_links_text
+
+    # extract text, with 'render_anchor_tag_content' set to True
+    text_content = html_to_text(test_html, render_anchor_tag_content=True)
+
+    links_text = \
+        "Some initial text\n\nWhich is across multiple lines\n\n[ More Text " \
+        "](/first_link) So let's see what happens. [ Even More Text ]" \
+        "(second_link.com)"
+
+    # check that links are present in the extracted text
+    assert text_content == links_text

changedetectionio/tests/test_ignore_text.py

@@ -196,9 +196,9 @@ def test_check_global_ignore_text_functionality(client, live_server):
     res = client.post(
         url_for("settings_page"),
         data={
-            "minutes_between_check": 180,
-            "global_ignore_text": ignore_text,
-            'fetch_backend': "html_requests"
+            "requests-minutes_between_check": 180,
+            "application-global_ignore_text": ignore_text,
+            'application-fetch_backend': "html_requests"
         },
         follow_redirects=True
     )

changedetectionio/tests/test_ignorehyperlinks.py

@@ -0,0 +1,219 @@
+#!/usr/bin/python3
+"""Test suite for the render/not render anchor tag content functionality"""
+
+import time
+from flask import url_for
+from .util import live_server_setup
+
+
+def test_setup(live_server):
+    live_server_setup(live_server)
+
+def set_original_ignore_response():
+    test_return_data = """<html>
+       <body>
+     Some initial text</br>
+     <a href="/original_link"> Some More Text </a>
+     </br>
+     So let's see what happens.  </br>
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+
+# Should be the same as set_original_ignore_response() but with a different
+# link
+def set_modified_ignore_response():
+    test_return_data = """<html>
+       <body>
+     Some initial text</br>
+     <a href="/modified_link"> Some More Text </a>
+     </br>
+     So let's see what happens.  </br>
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+def test_render_anchor_tag_content_true(client, live_server):
+    """Testing that the link changes are detected when
+    render_anchor_tag_content setting is set to true"""
+    sleep_time_for_fetch_thread = 3
+
+    # Give the endpoint time to spin up
+    time.sleep(1)
+
+    # set original html text
+    set_original_ignore_response()
+
+    # Goto the settings page, choose not to ignore links
+    res = client.post(
+        url_for("settings_page"),
+        data={
+            "requests-minutes_between_check": 180,
+            "application-render_anchor_tag_content": "true",
+            "application-fetch_backend": "html_requests",
+        },
+        follow_redirects=True,
+    )
+    assert b"Settings updated." in res.data
+
+    # Add our URL to the import page
+    test_url = url_for("test_endpoint", _external=True)
+    res = client.post(
+        url_for("import_page"), data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    time.sleep(sleep_time_for_fetch_thread)
+    # Trigger a check
+    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+
+    # set a new html text with a modified link
+    set_modified_ignore_response()
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # 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)
+
+    # check that the anchor tag content is rendered
+    res = client.get(url_for("preview_page", uuid="first"))
+    assert '(/modified_link)' in res.data.decode()
+
+    # since the link has changed, and we chose to render anchor tag content,
+    # we should detect a change (new 'unviewed' class)
+    res = client.get(url_for("index"))
+    assert b"unviewed" in res.data
+    assert b"/test-endpoint" in res.data
+
+    # Cleanup everything
+    res = client.get(url_for("api_delete", uuid="all"),
+                     follow_redirects=True)
+    assert b'Deleted' in res.data
+
+
+def test_render_anchor_tag_content_false(client, live_server):
+    """Testing that anchor tag content changes are ignored when
+    render_anchor_tag_content setting is set to false"""
+    sleep_time_for_fetch_thread = 3
+
+    # Give the endpoint time to spin up
+    time.sleep(1)
+
+    # set the original html text
+    set_original_ignore_response()
+
+    # Goto the settings page, choose to ignore hyperlinks
+    res = client.post(
+        url_for("settings_page"),
+        data={
+            "requests-minutes_between_check": 180,
+            "application-render_anchor_tag_content": "false",
+            "application-fetch_backend": "html_requests",
+        },
+        follow_redirects=True,
+    )
+    assert b"Settings updated." in res.data
+
+    # Add our URL to the import page
+    test_url = url_for("test_endpoint", _external=True)
+    res = client.post(
+        url_for("import_page"), data={"urls": test_url}, follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    time.sleep(sleep_time_for_fetch_thread)
+    # Trigger a check
+    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+
+    # set a new html text, with a modified link
+    set_modified_ignore_response()
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # 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)
+
+    # check that the anchor tag content is not rendered
+    res = client.get(url_for("preview_page", uuid="first"))
+    assert '(/modified_link)' not in res.data.decode()
+
+    # even though the link has changed, we shouldn't detect a change since
+    # we selected to not render anchor tag content (no new 'unviewed' class)
+    res = client.get(url_for("index"))
+    assert b"unviewed" not in res.data
+    assert b"/test-endpoint" in res.data
+
+    # Cleanup everything
+    res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+
+def test_render_anchor_tag_content_default(client, live_server):
+    """Testing that anchor tag content changes are ignored when the
+    render_anchor_tag_content setting is not explicitly selected"""
+    sleep_time_for_fetch_thread = 3
+
+    # Give the endpoint time to spin up
+    time.sleep(1)
+
+    # set the original html text
+    set_original_ignore_response()
+
+    # Goto the settings page, not passing the render_anchor_tag_content setting
+    res = client.post(
+        url_for("settings_page"),
+        data={
+            "requests-minutes_between_check": 180,
+            "application-fetch_backend": "html_requests",
+        },
+        follow_redirects=True,
+    )
+    assert b"Settings updated." in res.data
+
+    # Add our URL to the import page
+    test_url = url_for("test_endpoint", _external=True)
+    res = client.post(
+        url_for("import_page"), data={"urls": test_url}, follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    time.sleep(sleep_time_for_fetch_thread)
+    # Trigger a check
+    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+
+    # set a new html text, with a modified link
+    set_modified_ignore_response()
+    time.sleep(sleep_time_for_fetch_thread)
+
+    # 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)
+
+    # check that the anchor tag content is not rendered
+    res = client.get(url_for("preview_page", uuid="first"))
+    assert '(/modified_link)' not in res.data.decode()
+
+    # even though the link has changed, we shouldn't detect a change since
+    # we did not select the setting and the default behaviour is to not
+    # render anchor tag content (no new 'unviewed' class)
+    res = client.get(url_for("index"))
+    assert b"unviewed" not in res.data
+    assert b"/test-endpoint" in res.data
+
+    # Cleanup everything
+    res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data

changedetectionio/tests/test_ignorestatuscode.py

@@ -51,9 +51,9 @@ def test_normal_page_check_works_with_ignore_status_code(client, live_server):
     res = client.post(
         url_for("settings_page"),
         data={
-            "minutes_between_check": 180,
-            "ignore_status_codes": "y",
-            'fetch_backend': "html_requests"
+            "requests-minutes_between_check": 180,
+            "application-ignore_status_codes": "y",
+            'application-fetch_backend': "html_requests"
         },
         follow_redirects=True
     )

changedetectionio/tests/test_ignorewhitespace.py

@@ -61,9 +61,9 @@ def test_check_ignore_whitespace(client, live_server):
     res = client.post(
         url_for("settings_page"),
         data={
-            "minutes_between_check": 180,
-            "ignore_whitespace": "y",
-            'fetch_backend': "html_requests"
+            "requests-minutes_between_check": 180,
+            "application-ignore_whitespace": "y",
+            "application-fetch_backend": "html_requests"
         },
         follow_redirects=True
     )

changedetectionio/tests/test_notification.py

@@ -2,15 +2,17 @@ import os
 import time
 import re
 from flask import url_for
-from . util import set_original_response, set_modified_response, live_server_setup
+from . util import set_original_response, set_modified_response, set_more_modified_response, live_server_setup
 import logging
 from changedetectionio.notification import default_notification_body, default_notification_title
 
+def test_setup(live_server):
+    live_server_setup(live_server)
+
 # Hard to just add more live server URLs when one test is already running (I think)
 # So we add our test here (was in a different file)
 def test_check_notification(client, live_server):
 
-    live_server_setup(live_server)
     set_original_response()
 
     # Give the endpoint time to spin up
@@ -49,84 +51,76 @@ def test_check_notification(client, live_server):
     notification_url = url.replace('http', 'json')
 
     print (">>>> Notification URL: "+notification_url)
+
+    notification_form_data = {"notification_urls": notification_url,
+                              "notification_title": "New ChangeDetection.io Notification - {watch_url}",
+                              "notification_body": "BASE URL: {base_url}\n"
+                                                   "Watch URL: {watch_url}\n"
+                                                   "Watch UUID: {watch_uuid}\n"
+                                                   "Watch title: {watch_title}\n"
+                                                   "Watch tag: {watch_tag}\n"
+                                                   "Preview: {preview_url}\n"
+                                                   "Diff URL: {diff_url}\n"
+                                                   "Snapshot: {current_snapshot}\n"
+                                                   "Diff: {diff}\n"
+                                                   "Diff Full: {diff_full}\n"
+                                                   ":-)",
+                              "notification_format": "Text"}
+
+    notification_form_data.update({
+        "url": test_url,
+        "tag": "my tag",
+        "title": "my title",
+        "headers": "",
+        "fetch_backend": "html_requests"})
+
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"notification_urls": notification_url,
-              "notification_title": "New ChangeDetection.io Notification - {watch_url}",
-              "notification_body": "BASE URL: {base_url}\n"
-                                   "Watch URL: {watch_url}\n"
-                                   "Watch UUID: {watch_uuid}\n"
-                                   "Watch title: {watch_title}\n"
-                                   "Watch tag: {watch_tag}\n"
-                                   "Preview: {preview_url}\n"
-                                   "Diff URL: {diff_url}\n"
-                                   "Snapshot: {current_snapshot}\n"
-                                   "Diff: {diff}\n"
-                                   "Diff Full: {diff_full}\n"
-                                   ":-)",
-              "notification_format": "Text",
-              "url": test_url,
-              "tag": "my tag",
-              "title": "my title",
-              "headers": "",
-              "fetch_backend": "html_requests",
-              "trigger_check": "y"},
+        data=notification_form_data,
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
-    assert b"Test notification queued" in res.data
+
 
     # Hit the edit page, be sure that we saved it
+    # Re #242 - wasnt saving?
     res = client.get(
         url_for("edit_page", uuid="first"))
     assert bytes(notification_url.encode('utf-8')) in res.data
-
-    # Re #242 - wasnt saving?
     assert bytes("New ChangeDetection.io Notification".encode('utf-8')) in res.data
 
 
 
-    # Because we hit 'send test notification on save'
+    ## Now recheck, and it should have sent the notification
     time.sleep(3)
+    set_modified_response()
 
     notification_submission = None
 
+    # Trigger a check
+    client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    time.sleep(3)
     # Verify what was sent as a notification, this file should exist
     with open("test-datastore/notification.txt", "r") as f:
         notification_submission = f.read()
-        # Did we see the URL that had a change, in the notification?
-
-    assert test_url in notification_submission
-
     os.unlink("test-datastore/notification.txt")
 
-    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(3)
-
-    # Did the front end see it?
-    res = client.get(
-        url_for("index"))
-
-    assert bytes("just now".encode('utf-8')) in res.data
-
-    notification_submission=None
-    # Verify what was sent as a notification
-    with open("test-datastore/notification.txt", "r") as f:
-        notification_submission = f.read()
-        # Did we see the URL that had a change, in the notification?
-
-    assert test_url in notification_submission
-
+    # Did we see the URL that had a change, in the notification?
     # Diff was correctly executed
+    assert test_url in notification_submission
+    assert ':-)' in notification_submission
     assert "Diff Full: Some initial text" in notification_submission
     assert "Diff: (changed) Which is across multiple lines" in notification_submission
-    assert "(-> into) which has this one new line" in notification_submission
-
+    assert "(into   ) which has this one new line" in notification_submission
+    # Re #342 - check for accidental python byte encoding of non-utf8/string
+    assert "b'" not in notification_submission
+    assert re.search('Watch UUID: [0-9a-f]{8}(-[0-9a-f]{4}){3}-[0-9a-f]{12}', notification_submission, re.IGNORECASE)
+    assert "Watch title: my title" in notification_submission
+    assert "Watch tag: my tag" in notification_submission
+    assert "diff/" in notification_submission
+    assert "preview/" in notification_submission
+    assert ":-)" in notification_submission
+    assert "New ChangeDetection.io Notification - {}".format(test_url) in notification_submission
 
     if env_base_url:
         # Re #65 - did we see our BASE_URl ?
@@ -135,50 +129,17 @@ def test_check_notification(client, live_server):
     else:
         logging.debug(">>> Skipping BASE_URL check")
 
-    ##  Now configure something clever, we go into custom config (non-default) mode, this is returned by the endpoint
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write(";jasdhflkjadshf kjhsdfkjl ahslkjf haslkjd hfaklsj hf\njl;asdhfkasj stuff we will detect\n")
 
-    res = client.post(
-        url_for("settings_page"),
-        data={"notification_title": "New ChangeDetection.io Notification - {watch_url}",
-              "notification_urls": "json://foobar.com", #Re #143 should not see that it sent without [test checkbox]
-              "minutes_between_check": 180,
-              "fetch_backend": "html_requests",
-              },
-        follow_redirects=True
-    )
-    assert b"Settings updated." in res.data
-    # Re #143 - should not see this if we didnt hit the test box
-    assert b"Test notification queued" not in res.data
 
-    # Trigger a check
+    # This should insert the {current_snapshot}
+    set_more_modified_response()
     client.get(url_for("api_watch_checknow"), follow_redirects=True)
-
-    # Give the thread time to pick it up
     time.sleep(3)
-
-    # Did the front end see it?
-    res = client.get(
-        url_for("index"))
-
-    assert bytes("just now".encode('utf-8')) in res.data
-
+    # Verify what was sent as a notification, this file should exist
     with open("test-datastore/notification.txt", "r") as f:
         notification_submission = f.read()
-        print ("Notification submission was:", notification_submission)
-        # Re #342 - check for accidental python byte encoding of non-utf8/string
-        assert "b'" not in notification_submission
+    assert "Ohh yeah awesome" in notification_submission
 
-        assert re.search('Watch UUID: [0-9a-f]{8}(-[0-9a-f]{4}){3}-[0-9a-f]{12}', notification_submission, re.IGNORECASE)
-        assert "Watch title: my title" in notification_submission
-        assert "Watch tag: my tag" in notification_submission
-        assert "diff/" in notification_submission
-        assert "preview/" in notification_submission
-        assert ":-)" in notification_submission
-        assert "New ChangeDetection.io Notification - {}".format(test_url) in notification_submission
-        # This should insert the {current_snapshot}
-        assert "stuff we will detect" in notification_submission
 
     # Prove that "content constantly being marked as Changed with no Updating causes notification" is not a thing
     # https://github.com/dgtlmoon/changedetection.io/discussions/192
@@ -186,33 +147,39 @@ def test_check_notification(client, live_server):
 
     # Trigger a check
     client.get(url_for("api_watch_checknow"), follow_redirects=True)
-    time.sleep(3)
+    time.sleep(1)
     client.get(url_for("api_watch_checknow"), follow_redirects=True)
-    time.sleep(3)
+    time.sleep(1)
     client.get(url_for("api_watch_checknow"), follow_redirects=True)
-    time.sleep(3)
+    time.sleep(1)
     assert os.path.exists("test-datastore/notification.txt") == False
 
-
-    # Now adding a wrong token should give us an error
-    res = client.post(
-        url_for("settings_page"),
-        data={"notification_title": "New ChangeDetection.io Notification - {watch_url}",
-              "notification_body": "Rubbish: {rubbish}\n",
-              "notification_format": "Text",
-              "notification_urls": "json://foobar.com",
-              "minutes_between_check": 180,
-              "fetch_backend": "html_requests"
-              },
+    # cleanup for the next
+    client.get(
+        url_for("api_delete", uuid="first"),
         follow_redirects=True
     )
 
-    assert bytes("is not a valid token".encode('utf-8')) in res.data
+
+def test_notification_validation(client, live_server):
+    #live_server_setup(live_server)
+    time.sleep(3)
+    # re #242 - when you edited an existing new entry, it would not correctly show the notification settings
+    # Add our URL to the import page
+    test_url = url_for('test_endpoint', _external=True)
+    res = client.post(
+        url_for("api_watch_add"),
+        data={"url": test_url, "tag": 'nice one'},
+        follow_redirects=True
+    )
+    with open("xxx.bin", "wb") as f:
+        f.write(res.data)
+    assert b"Watch added" in res.data
 
     # Re #360 some validation
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"notification_urls": notification_url,
+        data={"notification_urls": 'json://localhost/foobar',
               "notification_title": "",
               "notification_body": "",
               "notification_format": "Text",
@@ -220,8 +187,28 @@ def test_check_notification(client, live_server):
               "tag": "my tag",
               "title": "my title",
               "headers": "",
-              "fetch_backend": "html_requests",
-              "trigger_check": "y"},
+              "fetch_backend": "html_requests"},
         follow_redirects=True
     )
     assert b"Notification Body and Title is required when a Notification URL is used" in res.data
+
+    # Now adding a wrong token should give us an error
+    res = client.post(
+        url_for("settings_page"),
+        data={"application-notification_title": "New ChangeDetection.io Notification - {watch_url}",
+              "application-notification_body": "Rubbish: {rubbish}\n",
+              "application-notification_format": "Text",
+              "application-notification_urls": "json://localhost/foobar",
+              "requests-minutes_between_check": 180,
+              "fetch_backend": "html_requests"
+              },
+        follow_redirects=True
+    )
+
+    assert bytes("is not a valid token".encode('utf-8')) in res.data
+
+    # cleanup for the next
+    client.get(
+        url_for("api_delete", uuid="first"),
+        follow_redirects=True
+    )

changedetectionio/tests/test_request.py

@@ -84,9 +84,25 @@ def test_body_in_request(client, live_server):
     )
     assert b"1 Imported" in res.data
 
-    body_value = 'Test Body Value'
+    time.sleep(3)
 
-    # Add a properly formatted body with a proper method
+    # add the first 'version'
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={
+              "url": test_url,
+              "tag": "",
+              "method": "POST",
+              "fetch_backend": "html_requests",
+              "body": "something something"},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+
+    time.sleep(3)
+
+    # Now the change which should trigger a change
+    body_value = 'Test Body Value'
     res = client.post(
         url_for("edit_page", uuid="first"),
         data={

changedetectionio/tests/test_source.py

@@ -0,0 +1,95 @@
+#!/usr/bin/python3
+
+import time
+from flask import url_for
+from urllib.request import urlopen
+from .util import set_original_response, set_modified_response, live_server_setup
+
+sleep_time_for_fetch_thread = 3
+
+def test_setup(live_server):
+    live_server_setup(live_server)
+
+def test_check_basic_change_detection_functionality_source(client, live_server):
+    set_original_response()
+    test_url = 'source:'+url_for('test_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
+
+    time.sleep(sleep_time_for_fetch_thread)
+
+    #####################
+
+    # Check HTML conversion detected and workd
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    # Check this class DOES appear (that we didnt see the actual source)
+    assert b'foobar-detection' in res.data
+
+    # Make a change
+    set_modified_response()
+
+    # Force recheck
+    res = client.get(url_for("api_watch_checknow"), follow_redirects=True)
+    assert b'1 watches are queued for rechecking.' in res.data
+
+    time.sleep(5)
+
+    # Now something should be ready, indicated by having a 'unviewed' class
+    res = client.get(url_for("index"))
+    assert b'unviewed' in res.data
+
+    res = client.get(
+        url_for("diff_history_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    assert b'<title>modified head title' in res.data
+
+
+
+
+def test_check_ignore_elements(client, live_server):
+    set_original_response()
+
+    time.sleep(2)
+    test_url = 'source:'+url_for('test_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
+
+    time.sleep(sleep_time_for_fetch_thread)
+
+    #####################
+    # We want <span> and <p> ONLY, but ignore span with .foobar-detection
+
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"css_filter": 'span,p', "url": test_url, "tag": "", "subtractive_selectors": ".foobar-detection", 'fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+
+    time.sleep(sleep_time_for_fetch_thread)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    assert b'foobar-detection' not in res.data
+    assert b'&lt;br' not in res.data
+    assert b'&lt;p' in res.data

changedetectionio/tests/test_watch_fields_storage.py

@@ -56,8 +56,8 @@ def test_check_recheck_global_setting(client, live_server):
     res = client.post(
         url_for("settings_page"),
         data={
-               "minutes_between_check": 1566,
-               'fetch_backend': "html_requests"
+               "requests-minutes_between_check": 1566,
+               'application-fetch_backend': "html_requests"
                },
         follow_redirects=True
     )
@@ -88,8 +88,8 @@ def test_check_recheck_global_setting(client, live_server):
     res = client.post(
         url_for("settings_page"),
         data={
-               "minutes_between_check": 222,
-                'fetch_backend': "html_requests"
+               "requests-minutes_between_check": 222,
+                'application-fetch_backend': "html_requests"
                },
         follow_redirects=True
     )
@@ -124,8 +124,8 @@ def test_check_recheck_global_setting(client, live_server):
     res = client.post(
         url_for("settings_page"),
         data={
-               "minutes_between_check": 666,
-                'fetch_backend': "html_requests"
+               "requests-minutes_between_check": 666,
+                'application-fetch_backend': "html_requests"
                },
         follow_redirects=True
     )

changedetectionio/tests/unit/test-content/after-2.txt

@@ -0,0 +1,3 @@
+After twenty years, as cursed as I may be
+ok
+and insure that I'm one of those computer nerds.

changedetectionio/tests/unit/test-content/after.txt

@@ -2,5 +2,6 @@ After twenty years, as cursed as I may be
 for having learned computerese,
 I continue to examine bits, bytes and words
 xok
+next-x-ok
 and insure that I'm one of those computer nerds.
 and something new

changedetectionio/tests/unit/test_notification_diff.py

@@ -12,12 +12,19 @@ from changedetectionio import diff
 class TestDiffBuilder(unittest.TestCase):
 
     def test_expected_diff_output(self):
-        base_dir=os.path.dirname(__file__)
-        output = diff.render_diff(base_dir+"/test-content/before.txt", base_dir+"/test-content/after.txt")
+        base_dir = os.path.dirname(__file__)
+        output = diff.render_diff(previous_file=base_dir + "/test-content/before.txt", newest_file=base_dir + "/test-content/after.txt")
         output = output.split("\n")
-        self.assertIn("(changed) ok", output)
-        self.assertIn("(-> into) xok", output)
-        self.assertIn("(added) and something new", output)
+        self.assertIn('(changed) ok', output)
+        self.assertIn('(into   ) xok', output)
+        self.assertIn('(into   ) next-x-ok', output)
+        self.assertIn('(added  ) and something new', output)
+
+
+        output = diff.render_diff(previous_file=base_dir + "/test-content/before.txt", newest_file=base_dir + "/test-content/after-2.txt")
+        output = output.split("\n")
+        self.assertIn('(removed) for having learned computerese,', output)
+        self.assertIn('(removed) I continue to examine bits, bytes and words', output)
 
         # @todo test blocks of changed, blocks of added, blocks of removed
 

changedetectionio/tests/util.py

@@ -10,6 +10,7 @@ def set_original_response():
      <p>Which is across multiple lines</p>
      </br>
      So let's see what happens.  </br>
+     <span class="foobar-detection" style='display:none'></span>
      </body>
      </html>
     """
@@ -35,6 +36,24 @@ def set_modified_response():
 
     return None
 
+def set_more_modified_response():
+    test_return_data = """<html>
+    <head><title>modified head title</title></head>
+    <body>
+     Some initial text</br>
+     <p>which has this one new line</p>
+     </br>
+     So let's see what happens.  </br>
+     Ohh yeah awesome<br/>
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+
+    return None
+
 
 def live_server_setup(live_server):
 
@@ -66,6 +85,7 @@ 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():
+        print ("TEST-BODY GOT", request.data, "returning")
         return request.data
 
     # Just return the verb in the request
@@ -82,7 +102,7 @@ def live_server_setup(live_server):
             if data != None:
                 f.write(data)
 
-        print("\n>> Test notification endpoint was hit.\n")
+        print("\n>> Test notification endpoint was hit.\n", data)
         return "Text was set"
 
 

changedetectionio/update_worker.py

@@ -2,6 +2,7 @@ import threading
 import queue
 import time
 
+from changedetectionio import content_fetcher
 # A single update worker
 #
 # Requests for checking on a single site(watch) from a queue of watches
@@ -32,17 +33,17 @@ class update_worker(threading.Thread):
 
             else:
                 self.current_uuid = uuid
-                from changedetectionio import content_fetcher
 
                 if uuid in list(self.datastore.data['watching'].keys()):
 
                     changed_detected = False
                     contents = ""
+                    screenshot = False
                     update_obj= {}
                     now = time.time()
 
                     try:
-                        changed_detected, update_obj, contents = update_handler.run(uuid)
+                        changed_detected, update_obj, contents, screenshot = update_handler.run(uuid)
 
                         # Re #342
                         # In Python 3, all strings are sequences of Unicode characters. There is a bytes type that holds raw bytes.
@@ -140,6 +141,9 @@ class update_worker(threading.Thread):
                         # Always record that we atleast tried
                         self.datastore.update_watch(uuid=uuid, update_obj={'fetch_time': round(time.time() - now, 3),
                                                                            'last_checked': round(time.time())})
+                        # Always save the screenshot if it's available
+                        if screenshot:
+                            self.datastore.save_screenshot(watch_uuid=uuid, screenshot=screenshot)
 
                 self.current_uuid = None  # Done
                 self.q.task_done()

requirements.txt

@@ -13,11 +13,11 @@ requests[socks] ~= 2.26
 urllib3 > 1.26
 chardet > 2.3.0
 
-wtforms ~= 2.3.3
+wtforms ~= 3.0
 jsonpath-ng ~= 1.5.3
 
 # Notification library
-apprise ~= 0.9.7
+apprise ~= 0.9.8.1
 
 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
 paho-mqtt
@@ -35,3 +35,8 @@ lxml
 # 3.141 was missing socksVersion, 3.150 was not in pypi, so we try 4.1.0
 selenium ~= 4.1.0
 
+# https://stackoverflow.com/questions/71652965/importerror-cannot-import-name-safe-str-cmp-from-werkzeug-security/71653849#71653849
+# ImportError: cannot import name 'safe_str_cmp' from 'werkzeug.security'
+# need to revisit flask login versions
+werkzeug ~= 2.0.0
+