Re #462 - check encoding

.github/workflows/containers.yml

@@ -2,20 +2,16 @@ name: Build and push containers
 
 on:
   # Automatically triggered by a testing workflow passing, but this is only checked when it lands in the `master`/default branch
-#  workflow_run:
-#    workflows: ["ChangeDetection.io Test"]
-#    branches: [master]
-#    tags: ['0.*']
-#    types: [completed]
+  workflow_run:
+    workflows: ["ChangeDetection.io Test"]
+    branches: [master]
+    tags: ['0.*']
+    types: [completed]
 
   # Or a new tagged release
   release:
     types: [published, edited]
 
-  push:
-    branches:
-      - master
-
 jobs:
   metadata:
     runs-on: ubuntu-latest
@@ -95,7 +91,8 @@ jobs:
           file: ./Dockerfile
           push: true
           tags: |
-            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:latest,ghcr.io/${{ github.repository }}:latest
+            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:latest
+            ghcr.io/${{ github.repository }}:latest
           platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
           cache-from: type=local,src=/tmp/.buildx-cache
           cache-to: type=local,dest=/tmp/.buildx-cache
@@ -110,7 +107,8 @@ jobs:
           file: ./Dockerfile
           push: true
           tags: |
-            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:${{ github.event.release.tag_name }},ghcr.io/dgtlmoon/changedetection.io:${{ github.event.release.tag_name }}
+            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:${{ github.event.release.tag_name }}
+            ghcr.io/dgtlmoon/changedetection.io:${{ github.event.release.tag_name }}
           platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
           cache-from: type=local,src=/tmp/.buildx-cache
           cache-to: type=local,dest=/tmp/.buildx-cache

.gitignore

@@ -7,6 +7,4 @@ __pycache__
 .pytest_cache
 build
 dist
-venv
-*.egg-info*
 .vscode/settings.json

MANIFEST.in

@@ -2,5 +2,5 @@ recursive-include changedetectionio/templates *
 recursive-include changedetectionio/static *
 include changedetection.py
 global-exclude *.pyc
-global-exclude node_modules
+global-exclude *node_modules*
 global-exclude venv

README.md

@@ -9,10 +9,10 @@ _Know when web pages change! Stay ontop of new information!_
 
 Live your data-life *pro-actively* instead of *re-actively*.
 
-Free, Open-source web page monitoring, notification and change detection. Don't have time? [Try our $6.99/month plan - unlimited checks and watches!](https://lemonade.changedetection.io/start)
+Open source web page monitoring, notification and change detection.
 
 
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](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"  />
 
 
 **Get your own private instance now! Let us host it for you!**
@@ -70,10 +70,6 @@ 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/
@@ -167,6 +163,9 @@ 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 native support?
+
+Sorry not yet :( https://github.com/dgtlmoon/changedetection.io/labels/windows
 
 ## Support us
 

changedetection.py

@@ -1,11 +1,110 @@
 #!/usr/bin/python3
 
-# Entry-point for running from the CLI when not installed via Pip, Pip will handle the console_scripts entry_points's from setup.py
-# It's recommended to use `pip3 install changedetection.io` and start with `changedetection.py` instead, it will be linkd to your global path.
-# or Docker.
-# Read more https://github.com/dgtlmoon/changedetection.io/wiki
+# Launch as a eventlet.wsgi server instance.
+
+import getopt
+import os
+import sys
+
+import eventlet
+import eventlet.wsgi
+import changedetectionio
+
+from changedetectionio import store
+
+def main():
+    ssl_mode = False
+    host = ''
+    port = os.environ.get('PORT') or 5000
+    do_cleanup = False
+
+    # Must be absolute so that send_from_directory doesnt try to make it relative to backend/
+    datastore_path = os.path.join(os.getcwd(), "datastore")
+
+    try:
+        opts, args = getopt.getopt(sys.argv[1:], "Ccsd:h:p:", "port")
+    except getopt.GetoptError:
+        print('backend.py -s SSL enable -h [host] -p [port] -d [datastore path]')
+        sys.exit(2)
+
+    create_datastore_dir = False
+
+    for opt, arg in opts:
+        #        if opt == '--purge':
+        # Remove history, the actual files you need to delete manually.
+        #            for uuid, watch in datastore.data['watching'].items():
+        #                watch.update({'history': {}, 'last_checked': 0, 'last_changed': 0, 'previous_md5': None})
+
+        if opt == '-s':
+            ssl_mode = True
+
+        if opt == '-h':
+            host = arg
+
+        if opt == '-p':
+            port = int(arg)
+
+        if opt == '-d':
+            datastore_path = arg
+
+        # Cleanup (remove text files that arent in the index)
+        if opt == '-c':
+            do_cleanup = True
+
+        # Create the datadir if it doesnt exist
+        if opt == '-C':
+            create_datastore_dir = True
+
+    # isnt there some @thingy to attach to each route to tell it, that this route needs a datastore
+    app_config = {'datastore_path': datastore_path}
+
+    if not os.path.isdir(app_config['datastore_path']):
+        if create_datastore_dir:
+            os.mkdir(app_config['datastore_path'])
+        else:
+            print ("ERROR: Directory path for the datastore '{}' does not exist, cannot start, please make sure the directory exists.\n"
+                   "Alternatively, use the -C parameter.".format(app_config['datastore_path']),file=sys.stderr)
+            sys.exit(2)
+
+    datastore = store.ChangeDetectionStore(datastore_path=app_config['datastore_path'], version_tag=changedetectionio.__version__)
+    app = changedetectionio.changedetection_app(app_config, datastore)
+
+    # Go into cleanup mode
+    if do_cleanup:
+        datastore.remove_unused_snapshots()
+
+    app.config['datastore_path'] = datastore_path
+
+
+    @app.context_processor
+    def inject_version():
+        return dict(right_sticky="v{}".format(datastore.data['version_tag']),
+                    new_version_available=app.config['NEW_VERSION_AVAILABLE'],
+                    has_password=datastore.data['settings']['application']['password'] != False
+                    )
+
+    # Proxy sub-directory support
+    # Set environment var USE_X_SETTINGS=1 on this script
+    # And then in your proxy_pass settings
+    #
+    #         proxy_set_header Host "localhost";
+    #         proxy_set_header X-Forwarded-Prefix /app;
+
+    if os.getenv('USE_X_SETTINGS'):
+        print ("USE_X_SETTINGS is ENABLED\n")
+        from werkzeug.middleware.proxy_fix import ProxyFix
+        app.wsgi_app = ProxyFix(app.wsgi_app, x_prefix=1, x_host=1)
+
+    if ssl_mode:
+        # @todo finalise SSL config, but this should get you in the right direction if you need it.
+        eventlet.wsgi.server(eventlet.wrap_ssl(eventlet.listen((host, port)),
+                                               certfile='cert.pem',
+                                               keyfile='privkey.pem',
+                                               server_side=True), app)
+
+    else:
+        eventlet.wsgi.server(eventlet.listen((host, int(port))), app)
 
-from changedetectionio import changedetection
 
 if __name__ == '__main__':
-    changedetection.main()
+    main()

changedetectionio/.gitignore

@@ -1 +0,0 @@
-test-datastore

changedetectionio/__init__.py

@@ -35,11 +35,10 @@ from flask import (
     url_for,
 )
 from flask_login import login_required
-from flask_wtf import CSRFProtect
 
 from changedetectionio import html_tools
 
-__version__ = '0.39.11'
+__version__ = '0.39.10'
 
 datastore = None
 
@@ -53,10 +52,11 @@ update_q = queue.Queue()
 
 notification_q = queue.Queue()
 
+# Needs to be set this way because we also build and publish via pip
+base_path = os.path.dirname(os.path.realpath(__file__))
 app = Flask(__name__,
-            static_url_path="",
-            static_folder="static",
-            template_folder="templates")
+            static_url_path="{}/static".format(base_path),
+            template_folder="{}/templates".format(base_path))
 
 # Stop browser caching of assets
 app.config['SEND_FILE_MAX_AGE_DEFAULT'] = 0
@@ -72,9 +72,6 @@ app.config['LOGIN_DISABLED'] = False
 # Disables caching of the templates
 app.config['TEMPLATES_AUTO_RELOAD'] = True
 
-csrf = CSRFProtect()
-csrf.init_app(app)
-
 notification_debug_log=[]
 
 def init_app_secret(datastore_path):
@@ -272,7 +269,7 @@ 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..
@@ -301,25 +298,13 @@ 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)
                 guid = "{}/{}".format(watch['uuid'], watch['last_changed'])
                 fe = fg.add_entry()
 
+
                 # Include a link to the diff page, they will have to login here to see if password protection is enabled.
                 # Description is the page you watch, link takes you to the diff JS UI page
                 base_url = datastore.data['settings']['application']['base_url']
@@ -328,16 +313,12 @@ 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 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))
+                # @todo in the future <description><![CDATA[<html><body>Any code html is valid.</body></html>]]></description>
+                fe.description(description=watch['url'])
 
                 fe.guid(guid, permalink=False)
                 dt = datetime.datetime.fromtimestamp(int(watch['newest_history_key']))
@@ -403,38 +384,6 @@ def changedetection_app(config=None, datastore_o=None):
 
         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():
@@ -555,13 +504,13 @@ def changedetection_app(config=None, datastore_o=None):
                           '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,
+                          'extract_title_as_title': form.extract_title_as_title.data
+
                           }
 
             # Notification URLs
@@ -596,6 +545,20 @@ 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))
@@ -621,8 +584,7 @@ def changedetection_app(config=None, datastore_o=None):
                                      watch=datastore.data['watching'][uuid],
                                      form=form,
                                      using_default_minutes=using_default_minutes,
-                                     current_base_url=datastore.data['settings']['application']['base_url'],
-                                     emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False)
+                                     current_base_url = datastore.data['settings']['application']['base_url']
                                      )
 
         return output
@@ -647,17 +609,17 @@ def changedetection_app(config=None, datastore_o=None):
             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']
-            form.real_browser_save_screenshot.data = datastore.data['settings']['application']['real_browser_save_screenshot']
 
-        if request.method == 'POST' and form.data.get('removepassword_button') == True:
-            # 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):
+            # Password unset is a GET, but we can lock the session to always need the password
+            if not os.getenv("SALTED_PASS", False) and request.values.get('removepassword') == 'yes':
+                from pathlib import Path
                 datastore.data['settings']['application']['password'] = False
                 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
@@ -670,7 +632,19 @@ def changedetection_app(config=None, datastore_o=None):
             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
-            datastore.data['settings']['application']['real_browser_save_screenshot'] = form.real_browser_save_screenshot.data
+
+            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 form.password.encrypted_password:
                 datastore.data['settings']['application']['password'] = form.password.encrypted_password
@@ -687,8 +661,7 @@ def changedetection_app(config=None, datastore_o=None):
         output = render_template("settings.html",
                                  form=form,
                                  current_base_url = datastore.data['settings']['application']['base_url'],
-                                 hide_remove_pass=os.getenv("SALTED_PASS", False),
-                                 emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False))
+                                 hide_remove_pass=os.getenv("SALTED_PASS", False))
 
         return output
 
@@ -788,9 +761,6 @@ 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,
@@ -801,8 +771,7 @@ 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,
-                                 screenshot=screenshot_url)
+                                 left_sticky=True)
 
         return output
 
@@ -862,17 +831,15 @@ 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'])
@@ -985,28 +952,6 @@ 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)
@@ -1037,14 +982,10 @@ 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.')
 

changedetectionio/changedetection.py

@@ -1,114 +0,0 @@
-#!/usr/bin/python3
-
-# Launch as a eventlet.wsgi server instance.
-
-import getopt
-import os
-import sys
-
-import eventlet
-import eventlet.wsgi
-from . import store, changedetection_app
-from . import __version__
-
-def main():
-    ssl_mode = False
-    host = ''
-    port = os.environ.get('PORT') or 5000
-    do_cleanup = False
-    datastore_path = None
-
-    # On Windows, create and use a default path.
-    if os.name == 'nt':
-        datastore_path = os.path.expandvars(r'%APPDATA%\changedetection.io')
-        os.makedirs(datastore_path, exist_ok=True)
-    else:
-        # Must be absolute so that send_from_directory doesnt try to make it relative to backend/
-        datastore_path = os.path.join(os.getcwd(), "../datastore")
-
-    try:
-        opts, args = getopt.getopt(sys.argv[1:], "Ccsd:h:p:", "port")
-    except getopt.GetoptError:
-        print('backend.py -s SSL enable -h [host] -p [port] -d [datastore path]')
-        sys.exit(2)
-
-    create_datastore_dir = False
-
-    for opt, arg in opts:
-        #        if opt == '--purge':
-        # Remove history, the actual files you need to delete manually.
-        #            for uuid, watch in datastore.data['watching'].items():
-        #                watch.update({'history': {}, 'last_checked': 0, 'last_changed': 0, 'previous_md5': None})
-
-        if opt == '-s':
-            ssl_mode = True
-
-        if opt == '-h':
-            host = arg
-
-        if opt == '-p':
-            port = int(arg)
-
-        if opt == '-d':
-            datastore_path = arg
-
-        # Cleanup (remove text files that arent in the index)
-        if opt == '-c':
-            do_cleanup = True
-
-        # Create the datadir if it doesnt exist
-        if opt == '-C':
-            create_datastore_dir = True
-
-    # isnt there some @thingy to attach to each route to tell it, that this route needs a datastore
-    app_config = {'datastore_path': datastore_path}
-
-    if not os.path.isdir(app_config['datastore_path']):
-        if create_datastore_dir:
-            os.mkdir(app_config['datastore_path'])
-        else:
-            print(
-                "ERROR: Directory path for the datastore '{}' does not exist, cannot start, please make sure the directory exists or specify a directory with the -d option.\n"
-                "Or use the -C parameter to create the directory.".format(app_config['datastore_path']), file=sys.stderr)
-            sys.exit(2)
-
-    datastore = store.ChangeDetectionStore(datastore_path=app_config['datastore_path'], version_tag=__version__)
-    app = changedetection_app(app_config, datastore)
-
-    # Go into cleanup mode
-    if do_cleanup:
-        datastore.remove_unused_snapshots()
-
-    app.config['datastore_path'] = datastore_path
-
-
-    @app.context_processor
-    def inject_version():
-        return dict(right_sticky="v{}".format(datastore.data['version_tag']),
-                    new_version_available=app.config['NEW_VERSION_AVAILABLE'],
-                    has_password=datastore.data['settings']['application']['password'] != False
-                    )
-
-    # Proxy sub-directory support
-    # Set environment var USE_X_SETTINGS=1 on this script
-    # And then in your proxy_pass settings
-    #
-    #         proxy_set_header Host "localhost";
-    #         proxy_set_header X-Forwarded-Prefix /app;
-
-    if os.getenv('USE_X_SETTINGS'):
-        print ("USE_X_SETTINGS is ENABLED\n")
-        from werkzeug.middleware.proxy_fix import ProxyFix
-        app.wsgi_app = ProxyFix(app.wsgi_app, x_prefix=1, x_host=1)
-
-    if ssl_mode:
-        # @todo finalise SSL config, but this should get you in the right direction if you need it.
-        eventlet.wsgi.server(eventlet.wrap_ssl(eventlet.listen((host, port)),
-                                               certfile='cert.pem',
-                                               keyfile='privkey.pem',
-                                               server_side=True), app)
-
-    else:
-        eventlet.wsgi.server(eventlet.listen((host, int(port))), app)
-
-

changedetectionio/content_fetcher.py

@@ -1,12 +1,10 @@
-from abc import ABC, abstractmethod
-import chardet
 import os
+import time
+from abc import ABC, abstractmethod
 from selenium import webdriver
 from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
 from selenium.webdriver.common.proxy import Proxy as SeleniumProxy
 from selenium.common.exceptions import WebDriverException
-import requests
-import time
 import urllib3.exceptions
 
 
@@ -22,7 +20,7 @@ class EmptyReply(Exception):
 class Fetcher():
     error = None
     status_code = None
-    content = None
+    content = None # Should always be bytes.
     headers = None
 
     fetcher_description ="No description"
@@ -32,24 +30,10 @@ class Fetcher():
         return self.error
 
     @abstractmethod
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False):
+    def run(self, url, timeout, request_headers, request_body, request_method):
         # 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
@@ -113,27 +97,21 @@ class html_webdriver(Fetcher):
         if proxy_args:
             self.proxy = SeleniumProxy(raw=proxy_args)
 
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False):
+    def run(self, url, timeout, request_headers, request_body, request_method):
 
         # request_body, request_method unused for now, until some magic in the future happens.
 
         # check env for WEBDRIVER_URL
-        self.driver = webdriver.Remote(
+        driver = webdriver.Remote(
             command_executor=self.command_executor,
             desired_capabilities=DesiredCapabilities.CHROME,
             proxy=self.proxy)
 
         try:
-            self.driver.get(url)
+            driver.get(url)
         except WebDriverException as e:
             # Be sure we close the session window
-            self.quit()
+            driver.quit()
             raise
 
         # @todo - how to check this? is it possible?
@@ -143,44 +121,32 @@ class html_webdriver(Fetcher):
 
         # @todo - dom wait loaded?
         time.sleep(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
-        self.content = self.driver.page_source
+        self.content = driver.page_source
         self.headers = {}
 
-    def screenshot(self):
-        return self.driver.get_screenshot_as_png()
+        driver.quit()
+
 
-    # 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
 
-        self.driver = webdriver.Remote(
+        driver = webdriver.Remote(
             command_executor=self.command_executor,
             desired_capabilities=DesiredCapabilities.CHROME)
 
         # driver.quit() seems to cause better exceptions
-        self.quit()
-        return True
+        driver.quit()
 
-    def quit(self):
-        if self.driver:
-            try:
-                self.driver.quit()
-            except Exception as e:
-                print("Exception in chrome shutdown/quit" + str(e))
+        return True
 
 # "html_requests" is listed as the default fetcher in store.py!
 class html_requests(Fetcher):
     fetcher_description = "Basic fast Plaintext/HTTP Client"
 
-    def run(self,
-            url,
-            timeout,
-            request_headers,
-            request_body,
-            request_method,
-            ignore_status_codes=False):
+    def run(self, url, timeout, request_headers, request_body, request_method):
+        import requests
 
         r = requests.request(method=request_method,
                          data=request_body,
@@ -189,21 +155,16 @@ class html_requests(Fetcher):
                          timeout=timeout,
                          verify=False)
 
-        # If the response did not tell us what encoding format to expect, Then use chardet to override what `requests` thinks.
-        # For example - some sites don't tell us it's utf-8, but return utf-8 content
-        # This seems to not occur when using webdriver/selenium, it seems to detect the text encoding more reliably.
-        # https://github.com/psf/requests/issues/1604 good info about requests encoding detection
-        if not r.headers.get('content-type') or not 'charset=' in r.headers.get('content-type'):
-            encoding = chardet.detect(r.content)['encoding']
-            if encoding:
-                r.encoding = encoding
+        # https://stackoverflow.com/questions/44203397/python-requests-get-returns-improperly-decoded-text-instead-of-utf-8
+        # Return bytes here
+        html = r.text
 
         # @todo test this
         # @todo maybe you really want to test zero-byte return pages?
-        if (not ignore_status_codes and not r) or not r.content or not len(r.content):
+        if not r or not html or not len(html):
             raise EmptyReply(url=url, status_code=r.status_code)
 
         self.status_code = r.status_code
-        self.content = r.text
+        self.content = html
         self.headers = r.headers
 

changedetectionio/diff.py

@@ -2,31 +2,22 @@
 
 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) " + i for i in same_slicer(before, alo, ahi)]
+            g = "(removed) {}".format(before[alo])
             yield g
         elif tag == 'replace':
-            g = ["(changed) " + i for i in same_slicer(before, alo, ahi)]
-            g += ["(into   ) " + i for i in same_slicer(after, blo, bhi)]
+            g = ["(changed) {}".format(before[alo]), "(-> into) {}".format(after[blo])]
             yield g
         elif tag == 'insert':
-            g = ["(added  ) " + i for i in same_slicer(after, blo, bhi)]
+            g = "(added) {}".format(after[blo])
             yield g
 
 # only_differences - only return info about the differences, no context

changedetectionio/fetch_site_status.py

@@ -1,10 +1,10 @@
 import hashlib
-import os
 import re
 import time
-import urllib3
 
+import urllib3
 from inscriptis import get_text
+
 from changedetectionio import content_fetcher, html_tools
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
@@ -21,18 +21,11 @@ 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]
-
-        # Protect against file:// access
-        if re.search(r'^file', watch['url'], re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
-            raise Exception(
-                "file:// type access is denied for security reasons."
-            )
-
         # Unset any existing notification error
+
         update_obj = {'last_notification_error': False, 'last_error': False}
 
         extra_headers = self.datastore.get_val(uuid, 'headers')
@@ -54,7 +47,6 @@ class perform_site_check():
             url = self.datastore.get_val(uuid, 'url')
             request_body = self.datastore.get_val(uuid, 'body')
             request_method = self.datastore.get_val(uuid, 'method')
-            ignore_status_code = self.datastore.get_val(uuid, 'ignore_status_codes')
 
             # Pluggable content fetcher
             prefer_backend = watch['fetch_backend']
@@ -66,7 +58,7 @@ class perform_site_check():
 
 
             fetcher = klass()
-            fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_code)
+            fetcher.run(url, timeout, request_headers, request_body, request_method)
             # Fetching complete, now filters
             # @todo move to class / maybe inside of fetcher abstract base?
 
@@ -172,9 +164,5 @@ class perform_site_check():
                     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()
 
-            fetcher.quit()
-
-        return changed_detected, update_obj, text_content_before_ignored_filter, screenshot
+        return changed_detected, update_obj, text_content_before_ignored_filter

changedetectionio/forms.py

@@ -306,6 +306,7 @@ class commonSettingsForm(Form):
     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()])
     extract_title_as_title = BooleanField('Extract <title> from document and use as watch title', default=False)
 
@@ -324,7 +325,6 @@ class watchForm(commonSettingsForm):
     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"})
@@ -344,14 +344,12 @@ class watchForm(commonSettingsForm):
         return result
 
 class globalSettingsForm(commonSettingsForm):
+
     password = SaltyPasswordField()
     minutes_between_check = html5.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')
     base_url = StringField('Base URL', validators=[validators.Optional()])
-    global_subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
+    global_subtractive_selectors = StringListField('Ignore elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
     global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
     ignore_whitespace = BooleanField('Ignore whitespace')
-    save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
-    real_browser_save_screenshot = BooleanField('Save last screenshot when using Chrome?')
-    removepassword_button = SubmitField('Remove password', render_kw={"class": "pure-button pure-button-primary"})

changedetectionio/static/js/notifications.js

@@ -1,53 +0,0 @@
-$(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

@@ -1,11 +1,6 @@
 // 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]) {
@@ -26,6 +21,7 @@ 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

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

changedetectionio/static/styles/diff.css

@@ -1,8 +1,7 @@
 #diff-ui {
   background: #fff;
   padding: 2em;
-  margin-left: 1em;
-  margin-right: 1em;
+  margin: 1em;
   border-radius: 5px;
   font-size: 11px; }
   #diff-ui table {
@@ -71,8 +70,3 @@ 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

@@ -2,8 +2,7 @@
 
     background: #fff;
     padding: 2em;
-    margin-left: 1em;
-    margin-right: 1em;
+    margin: 1em;
     border-radius: 5px;
     font-size: 11px;
 
@@ -86,11 +85,4 @@ 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

@@ -37,9 +37,6 @@ section.content {
   align-items: center;
   justify-content: center; }
 
-code {
-  background: #eee; }
-
 /* table related */
 .watch-table {
   width: 100%;
@@ -244,7 +241,7 @@ footer {
 .sticky-tab {
   position: absolute;
   top: 60px;
-  font-size: 65%;
+  font-size: 8px;
   background: #fff;
   padding: 10px; }
   .sticky-tab#left-sticky {
@@ -310,23 +307,14 @@ 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 */
@@ -403,15 +391,14 @@ 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; }
   .edit-form .box-wrap {
     position: relative; }
   .edit-form .inner {

changedetectionio/static/styles/styles.scss

@@ -35,17 +35,13 @@ a.github-link {
 
 section.content {
   padding-top: 5em;
-  padding-bottom: 1em;
+  padding-bottom: 5em;
   flex-direction: column;
   display: flex;
   align-items: center;
   justify-content: center;
 }
 
-code {
-  background: #eee;
-}
-
 /* table related */
 .watch-table {
   width: 100%;
@@ -322,7 +318,7 @@ footer {
 .sticky-tab {
   position: absolute;
   top: 60px;
-  font-size: 65%;
+  font-size: 8px;
   background: #fff;
   padding: 10px;
   &#left-sticky {
@@ -422,35 +418,18 @@ 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 {
@@ -573,7 +552,10 @@ $form-edge-padding: 20px;
   }
 }
 
-.tab-pane-inner {
+
+.edit-form {
+  min-width: 70%;
+  .tab-pane-inner {
     &:not(:target) {
         display: none;
     }
@@ -582,11 +564,7 @@ $form-edge-padding: 20px;
     }
     // doesnt need padding because theres another row of buttons/activity
     padding: 0px;
-}
-
-.edit-form {
-  min-width: 70%;
-
+  }
   .box-wrap {
     position: relative;
   }

changedetectionio/store.py

@@ -57,7 +57,6 @@ class ChangeDetectionStore:
                     'notification_title': default_notification_title,
                     'notification_body': default_notification_body,
                     'notification_format': default_notification_format,
-                    'real_browser_save_screenshot': True,
                 }
             }
         }
@@ -382,22 +381,6 @@ 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..")
 
@@ -417,7 +400,7 @@ class ChangeDetectionStore:
                 # system was out of memory, out of RAM etc
                 with open(self.json_store_path+".tmp", 'w') as json_file:
                     json.dump(data, json_file, indent=4)
-                os.replace(self.json_store_path+".tmp", self.json_store_path)
+                os.rename(self.json_store_path+".tmp", self.json_store_path)
             except Exception as e:
                 logging.error("Error writing JSON!! (Main JSON file save was skipped) : %s", str(e))
 

changedetectionio/templates/_common_fields.jinja

@@ -1,7 +1,7 @@
 
 {% from '_helpers.jinja' import render_field %}
 
-{% macro render_common_settings_form(form, current_base_url, emailprefix) %}
+{% macro render_common_settings_form(form, current_base_url) %}
 
                         <div class="pure-control-group">
                             {{ render_field(form.notification_urls, rows=5, placeholder="Examples:
@@ -18,12 +18,6 @@
                                 <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 class="pure-control-group">
@@ -99,4 +93,7 @@
                             </span>
                             </div>
                         </div>
+                        <div class="pure-control-group">
+                            {{ render_field(form.trigger_check) }}
+                        </div>
 {% endmacro %}

changedetectionio/templates/base.html

@@ -17,7 +17,6 @@
         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

@@ -1,6 +1,7 @@
 {% extends 'base.html' %}
 
 {% block content %}
+
 <div id="settings">
     <h1>Differences</h1>
     <form class="pure-form " action="" method="GET">
@@ -34,45 +35,21 @@
 <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">Screenshot</a></li>
-{% endif %}
-    </ul>
-</div>
-
 <div id="diff-ui">
-     <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 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>
 

changedetectionio/templates/edit.html

@@ -4,17 +4,10 @@
 {% from '_helpers.jinja' import render_button %}
 {% from '_common_fields.jinja' import render_common_settings_form %}
 <script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
-<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 collapsable">
+    <div class="tabs">
         <ul>
             <li class="tab" id="default-tab"><a href="#general">General</a></li>
             <li class="tab"><a href="#request">Request</a></li>
@@ -26,7 +19,6 @@
     <div class="box-wrap inner">
         <form class="pure-form pure-form-stacked"
               action="{{ url_for('edit_page', uuid=uuid, next = request.args.get('next') ) }}" method="POST">
-             <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
 
             <div class="tab-pane-inner" id="general">
                 <fieldset>
@@ -88,9 +80,6 @@ User-Agent: wonderbra 1.0") }}
    \"car\":null
 }") }}
                     </div>
-                    <div>
-                        {{ render_field(form.ignore_status_codes) }}
-                    </div>
                 </fieldset>
                 <br/>
             </div>
@@ -99,7 +88,7 @@ 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, emailprefix) }}
+                        {{ render_common_settings_form(form, current_base_url) }}
                     </div>
                 </fieldset>
             </div>
@@ -124,9 +113,9 @@ User-Agent: wonderbra 1.0") }}
                         <span class="pure-form-message-inline">
                     <ul>
                         <li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
-                        <li>JSON - Limit text to this JSON rule, using <a href="https://pypi.org/project/jsonpath-ng/">JSONPath</a>, prefix with <code>"json:"</code>, use <code>json:$</code> to force re-formatting if required,  <a
+                        <li>JSON - Limit text to this JSON rule, using <a href="https://pypi.org/project/jsonpath-ng/">JSONPath</a>, prefix with <b>"json:"</b>, <a
                                 href="https://jsonpath.com/" target="new">test your JSONPath here</a></li>
-                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash, example  <code>//*[contains(@class, 'sametext')]</code>, <a
+                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash, example  <b>//*[contains(@class, 'sametext')]</b>, <a
                                 href="http://xpather.com/" target="new">test your XPath here</a></li>
                     </ul>
                     Please be sure that you thoroughly understand how to write CSS or JSONPath, XPath selector rules before filing an issue on GitHub! <a
@@ -153,7 +142,7 @@ nav
                     <span class="pure-form-message-inline">
                         <ul>
                             <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
-                            <li>Regular Expression support, wrap the line in forward slash <code>/regex/</code></li>
+                            <li>Regular Expression support, wrap the line in forward slash <b>/regex/</b></li>
                             <li>Changing this will affect the comparison checksum which may trigger an alert</li>
                             <li>Use the preview/show current tab to see ignores</li>
                         </ul>
@@ -169,8 +158,8 @@ 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 processed separately (think of each line as "OR")</li>
-                        <li>Note: Wrap in forward slash / to use regex  example: <code>/foo\d/</code></li>
+                        <li>Each line is process separately (think of each line as "OR")</li>
+                        <li>Note: Wrap in forward slash / to use regex  example: <span style="font-family: monospace; background: #eee">/foo\d/</span></li>
                     </ul>
                         </span>
                     </div>

changedetectionio/templates/import.html

@@ -4,7 +4,6 @@
 <div class="edit-form">
      <div class="inner">
         <form class="pure-form pure-form-aligned" action="{{url_for('import_page')}}" method="POST">
-            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
             <fieldset class="pure-group">
               <legend>
                 Enter one URL per line, and optionally add tags for each URL after a space, delineated by comma (,):

changedetectionio/templates/login.html

@@ -4,12 +4,11 @@
 <div class="login-form">
  <div class="inner">
     <form class="pure-form pure-form-stacked" action="{{url_for('login')}}" method="POST">
-        <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
         <fieldset>
             <div class="pure-control-group">
                 <label for="password">Password</label>
                 <input type="password" id="password" required="" name="password" value=""
-                       size="15" autofocus />
+                       size="15"/>
                 <input type="hidden" id="email" name="email" value="defaultuser@changedetection.io" />
             </div>
             <div class="pure-control-group">

changedetectionio/templates/preview.html

@@ -6,40 +6,18 @@
     <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">Screenshot</a></li>
-{% endif %}
-    </ul>
-</div>
-
 <div id="diff-ui">
-    <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">
+    <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>
-    </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 %}
+            </td>
+        </tr>
+        </tbody>
+    </table>
 </div>
 {% endblock %}

changedetectionio/templates/scrub.html

@@ -4,7 +4,6 @@
 <div class="edit-form">
     <div class="box-wrap inner">
     <form class="pure-form pure-form-stacked" action="{{url_for('scrub_page')}}" method="POST">
-        <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
         <fieldset>
             <div class="pure-control-group">
                 This will remove all version snapshots/data, but keep your list of URLs. <br/>

changedetectionio/templates/settings.html

@@ -1,20 +1,14 @@
 {% extends 'base.html' %}
 
 {% block content %}
-{% from '_helpers.jinja' import render_field, render_button %}
+{% from '_helpers.jinja' import render_field %}
 {% 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 collapsable">
+    <div class="tabs">
         <ul>
             <li class="tab" id="default-tab"><a href="#general">General</a></li>
             <li class="tab"><a href="#notifications">Notifications</a></li>
@@ -24,7 +18,6 @@
     </div>
     <div class="box-wrap inner">
         <form class="pure-form pure-form-stacked settings" action="{{url_for('settings_page')}}" method="POST">
-            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
             <div class="tab-pane-inner" id="general">
                 <fieldset>
                     <div class="pure-control-group">
@@ -34,7 +27,8 @@
                     <div class="pure-control-group">
                         {% if not hide_remove_pass %}
                             {% if current_user.is_authenticated %}
-                                {{ render_button(form.removepassword_button) }}
+                            <a href="{{url_for('settings_page', removepassword='yes')}}"
+                               class="pure-button pure-button-primary">Remove password</a>
                             {% else %}
                             {{ render_field(form.password) }}
                             <span class="pure-form-message-inline">Password protection for your changedetection.io application.</span>
@@ -56,19 +50,13 @@
                         {{ render_field(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_field(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, emailprefix) }}
+                        {{ render_common_settings_form(form, current_base_url) }}
                     </div>
                 </fieldset>
                 <a href="{{url_for('notification_logs')}}">Notification debug logs</a>
@@ -116,7 +104,7 @@ nav
                         <ul>
                             <li>Note: This is applied globally in addition to the per-watch rules.</li>
                             <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
-                            <li>Regular Expression support, wrap the line in forward slash <code>/regex/</code></li>
+                            <li>Regular Expression support, wrap the line in forward slash <b>/regex/</b></li>
                             <li>Changing this will affect the comparison checksum which may trigger an alert</li>
                             <li>Use the preview/show current tab to see ignores</li>
                         </ul>
@@ -126,9 +114,11 @@ nav
 
             <div id="actions">
                 <div class="pure-control-group">
-                    {{ render_button(form.save_button) }}
-                    <a href="{{url_for('index')}}" class="pure-button button-small button-cancel">Back</a>
-                    <a href="{{url_for('scrub_page')}}" class="pure-button button-small button-cancel">Delete History Snapshot Data</a>
+                    <button type="submit" class="pure-button pure-button-primary">Save</button>
+                                           <a href="{{url_for('index')}}" class="pure-button button-small button-cancel">Back</a>
+                        <a href="{{url_for('scrub_page')}}" class="pure-button button-small button-cancel">Delete
+                            History
+                            Snapshot Data</a>
                 </div>
             </div>
         </form>

changedetectionio/templates/watch-overview.html

@@ -1,12 +1,10 @@
 {% 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">
-        <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
         <fieldset>
             <legend>Add a new change detection watch</legend>
                 {{ render_simple_field(form.url, placeholder="https://...", required=true) }}
@@ -76,7 +74,7 @@
                        class="pure-button button-small pure-button-primary">Recheck</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-link">Diff</a>
+                    <a href="{{ url_for('diff_history_page', uuid=watch.uuid) }}" target="{{watch.uuid}}" class="pure-button button-small pure-button-primary">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

@@ -42,9 +42,6 @@ def app(request):
     cleanup(app_config['datastore_path'])
     datastore = store.ChangeDetectionStore(datastore_path=app_config['datastore_path'], include_default_watches=False)
     app = changedetection_app(app_config, datastore)
-
-    # Disable CSRF while running tests
-    app.config['WTF_CSRF_ENABLED'] = False
     app.config['STOP_THREADS'] = True
 
     def teardown():

changedetectionio/tests/test_access_control.py

@@ -4,8 +4,8 @@ from flask import url_for
 def test_check_access_control(app, client):
     # Still doesnt work, but this is closer.
 
-    with app.test_client(use_cookies=True) as c:
-        # Check we don't have any password protection enabled yet.
+    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
 
@@ -46,20 +46,15 @@ def test_check_access_control(app, client):
         assert b"BACKUP" in res.data
         assert b"IMPORT" in res.data
         assert b"LOG OUT" in res.data
-        assert b"minutes_between_check" in res.data
-        assert b"fetch_backend" 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,
-        )
+        # Now remove the password so other tests function, @todo this should happen before each test automatically
+        res = c.get(url_for("settings_page", removepassword="yes"),
+              follow_redirects=True)
+        assert b"Password protection removed." in res.data
+
+        res = c.get(url_for("index"))
+        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):
@@ -76,7 +71,8 @@ def test_check_access_control_no_blank_password(app, client):
             data={"password": "",
                   "minutes_between_check": 180,
                   'fetch_backend': "html_requests"},
-            follow_redirects=True
+
+        follow_redirects=True
         )
 
         assert b"Password protection enabled." not in res.data
@@ -95,8 +91,7 @@ def test_check_access_no_remote_access_to_remove_password(app, client):
         # Enable password check.
         res = c.post(
             url_for("settings_page"),
-            data={"password": "password",
-                  "minutes_between_check": 180,
+            data={"password": "password", "minutes_between_check": 180,
                   'fetch_backend': "html_requests"},
             follow_redirects=True
         )
@@ -104,17 +99,8 @@ def test_check_access_no_remote_access_to_remove_password(app, client):
         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,
-        )
+        res = c.get(url_for("settings_page", removepassword="yes"),
+              follow_redirects=True)
         assert b"Password protection removed." not in res.data
 
         res = c.get(url_for("index"),

changedetectionio/tests/test_backend.py

@@ -25,7 +25,6 @@ def test_check_basic_change_detection_functionality(client, live_server):
         data={"urls": url_for('test_endpoint', _external=True)},
         follow_redirects=True
     )
-
     assert b"1 Imported" in res.data
 
     time.sleep(sleep_time_for_fetch_thread)
@@ -70,11 +69,6 @@ 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

changedetectionio/tests/test_encoding.py

@@ -1,87 +0,0 @@
-#!/usr/bin/python3
-# coding=utf-8
-
-import time
-from flask import url_for
-from .util import live_server_setup
-import pytest
-
-
-def test_setup(live_server):
-    live_server_setup(live_server)
-
-
-def set_html_response():
-    test_return_data = """
-<html><body><span class="nav_second_img_text">
-                  &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;铸大国重器，挺制造脊梁，致力能源未来，赋能美好生活。
-                                  </span>
-</body></html>
-    """
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write(test_return_data)
-    return None
-
-
-# In the case the server does not issue a charset= or doesnt have content_type header set
-def test_check_encoding_detection(client, live_server):
-    set_html_response()
-
-    # Give the endpoint time to spin up
-    time.sleep(1)
-
-    # Add our URL to the import page
-    test_url = url_for('test_endpoint', content_type="text/html", _external=True)
-    client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-
-    # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
-
-    # Give the thread time to pick it up
-    time.sleep(2)
-
-    res = client.get(
-        url_for("preview_page", uuid="first"),
-        follow_redirects=True
-    )
-
-    # Should see the proper string
-    assert "铸大国重".encode('utf-8') in res.data
-    # Should not see the failed encoding
-    assert b'\xc2\xa7' not in res.data
-
-
-# In the case the server does not issue a charset= or doesnt have content_type header set
-def test_check_encoding_detection_missing_content_type_header(client, live_server):
-    set_html_response()
-
-    # Give the endpoint time to spin up
-    time.sleep(1)
-
-    # Add our URL to the import page
-    test_url = url_for('test_endpoint', _external=True)
-    client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-
-    # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
-
-    # Give the thread time to pick it up
-    time.sleep(2)
-
-    res = client.get(
-        url_for("preview_page", uuid="first"),
-        follow_redirects=True
-    )
-
-    # Should see the proper string
-    assert "铸大国重".encode('utf-8') in res.data
-    # Should not see the failed encoding
-    assert b'\xc2\xa7' not in res.data

changedetectionio/tests/test_errorhandling.py

@@ -1,7 +1,6 @@
 #!/usr/bin/python3
 
 import time
-
 from flask import url_for
 from . util import live_server_setup
 
@@ -18,9 +17,7 @@ def test_error_handler(client, live_server):
     time.sleep(1)
 
     # Add our URL to the import page
-    test_url = url_for('test_endpoint',
-                       status_code=403,
-                       _external=True)
+    test_url = url_for('test_endpoint_403_error', _external=True)
     res = client.post(
         url_for("import_page"),
         data={"urls": test_url},

changedetectionio/tests/test_ignorestatuscode.py

@@ -1,190 +0,0 @@
-#!/usr/bin/python3
-
-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_response():
-    test_return_data = """<html>
-       <body>
-     Some initial text</br>
-     <p>Which is across multiple lines</p>
-     </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 set_some_changed_response():
-    test_return_data = """<html>
-       <body>
-     Some initial text</br>
-     <p>Which is across multiple lines, and a new thing too.</p>
-     </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_normal_page_check_works_with_ignore_status_code(client, live_server):
-    sleep_time_for_fetch_thread = 3
-
-    # Give the endpoint time to spin up
-    time.sleep(1)
-
-    set_original_response()
-
-    # Goto the settings page, add our ignore text
-    res = client.post(
-        url_for("settings_page"),
-        data={
-            "minutes_between_check": 180,
-            "ignore_status_codes": "y",
-            '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_some_changed_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)
-
-    # It should report nothing found (no new 'unviewed' class)
-    res = client.get(url_for("index"))
-    assert b'unviewed' in res.data
-    assert b'/test-endpoint' in res.data
-
-
-# Tests the whole stack works with staus codes ignored
-def test_403_page_check_works_with_ignore_status_code(client, live_server):
-    sleep_time_for_fetch_thread = 3
-
-    set_original_response()
-
-    # Give the endpoint time to spin up
-    time.sleep(1)
-
-    # Add our URL to the import page
-    test_url = url_for('test_endpoint', status_code=403, _external=True)
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-    assert b"1 Imported" in res.data
-
-    # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
-
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
-
-    # Goto the edit page, check our ignore option
-    # Add our URL to the import page
-    res = client.post(
-        url_for("edit_page", uuid="first"),
-        data={"ignore_status_codes": "y", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
-        follow_redirects=True
-    )
-    assert b"Updated watch." in res.data
-
-    # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
-
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
-    #  Make a change
-    set_some_changed_response()
-
-    # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
-
-    # It should have 'unviewed' still
-    # Because it should be looking at only that 'sametext' id
-    res = client.get(url_for("index"))
-    assert b'unviewed' in res.data
-
-
-# Tests the whole stack works with staus codes ignored
-def test_403_page_check_fails_without_ignore_status_code(client, live_server):
-    sleep_time_for_fetch_thread = 3
-
-    set_original_response()
-
-    # Give the endpoint time to spin up
-    time.sleep(1)
-
-    # Add our URL to the import page
-    test_url = url_for('test_endpoint', status_code=403, _external=True)
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-    assert b"1 Imported" in res.data
-
-    # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
-
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
-
-    # Goto the edit page, check our ignore option
-    # Add our URL to the import page
-    res = client.post(
-        url_for("edit_page", uuid="first"),
-        data={"url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
-        follow_redirects=True
-    )
-    assert b"Updated watch." in res.data
-
-    # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
-
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
-    #  Make a change
-    set_some_changed_response()
-
-    # Trigger a check
-    client.get(url_for("api_watch_checknow"), follow_redirects=True)
-    # Give the thread time to pick it up
-    time.sleep(sleep_time_for_fetch_thread)
-
-    # It should have 'unviewed' still
-    # Because it should be looking at only that 'sametext' id
-    res = client.get(url_for("index"))
-    assert b'Status Code 403' in res.data

changedetectionio/tests/test_notification.py

@@ -2,17 +2,15 @@ import os
 import time
 import re
 from flask import url_for
-from . util import set_original_response, set_modified_response, set_more_modified_response, live_server_setup
+from . util import set_original_response, set_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
@@ -51,76 +49,84 @@ 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_form_data,
+        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"},
         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
 
 
 
-    ## Now recheck, and it should have sent the notification
+    # Because we hit 'send test notification on save'
     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")
 
-    # Did we see the URL that had a change, in the notification?
-    # Diff was correctly executed
+    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
-    assert ':-)' in notification_submission
+
+    # Diff was correctly executed
     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
-    # 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
+    assert "(-> into) which has this one new line" in notification_submission
+
 
     if env_base_url:
         # Re #65 - did we see our BASE_URl ?
@@ -129,17 +135,50 @@ 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
 
-    # This should insert the {current_snapshot}
-    set_more_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)
-    # Verify what was sent as a notification, this file should exist
+
+    # Did the front end see it?
+    res = client.get(
+        url_for("index"))
+
+    assert bytes("just now".encode('utf-8')) in res.data
+
     with open("test-datastore/notification.txt", "r") as f:
         notification_submission = f.read()
-    assert "Ohh yeah awesome" in notification_submission
+        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 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
@@ -147,50 +186,13 @@ def test_check_notification(client, live_server):
 
     # Trigger a check
     client.get(url_for("api_watch_checknow"), follow_redirects=True)
-    time.sleep(1)
+    time.sleep(3)
     client.get(url_for("api_watch_checknow"), follow_redirects=True)
-    time.sleep(1)
+    time.sleep(3)
     client.get(url_for("api_watch_checknow"), follow_redirects=True)
-    time.sleep(1)
+    time.sleep(3)
     assert os.path.exists("test-datastore/notification.txt") == False
 
-    # cleanup for the next
-    client.get(
-        url_for("api_delete", uuid="first"),
-        follow_redirects=True
-    )
-
-
-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": 'json://localhost/foobar',
-              "notification_title": "",
-              "notification_body": "",
-              "notification_format": "Text",
-              "url": test_url,
-              "tag": "my tag",
-              "title": "my title",
-              "headers": "",
-              "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(
@@ -198,8 +200,8 @@ def test_notification_validation(client, live_server):
         data={"notification_title": "New ChangeDetection.io Notification - {watch_url}",
               "notification_body": "Rubbish: {rubbish}\n",
               "notification_format": "Text",
-              "notification_urls": "json://localhost/foobar",
-              "time_between_check": {'seconds': 180},
+              "notification_urls": "json://foobar.com",
+              "minutes_between_check": 180,
               "fetch_backend": "html_requests"
               },
         follow_redirects=True
@@ -207,8 +209,19 @@ def test_notification_validation(client, live_server):
 
     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"),
+    # Re #360 some validation
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"notification_urls": notification_url,
+              "notification_title": "",
+              "notification_body": "",
+              "notification_format": "Text",
+              "url": test_url,
+              "tag": "my tag",
+              "title": "my title",
+              "headers": "",
+              "fetch_backend": "html_requests",
+              "trigger_check": "y"},
         follow_redirects=True
     )
+    assert b"Notification Body and Title is required when a Notification URL is used" in res.data

changedetectionio/tests/test_security.py

@@ -1,36 +0,0 @@
-from flask import url_for
-from . util import set_original_response, set_modified_response, live_server_setup
-import time
-
-def test_setup(live_server):
-    live_server_setup(live_server)
-
-def test_file_access(client, live_server):
-
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": 'https://localhost'},
-        follow_redirects=True
-    )
-
-    assert b"1 Imported" in res.data
-
-    # Attempt to add a body with a GET method
-    res = client.post(
-        url_for("edit_page", uuid="first"),
-        data={
-              "url": 'file:///etc/passwd',
-              "tag": "",
-              "method": "GET",
-              "fetch_backend": "html_requests",
-              "body": ""},
-        follow_redirects=True
-    )
-    time.sleep(3)
-
-    res = client.get(
-        url_for("index", uuid="first"),
-        follow_redirects=True
-    )
-
-    assert b'denied for security reasons' in res.data

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

@@ -1,3 +0,0 @@
-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

@@ -2,6 +2,5 @@ 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

@@ -12,19 +12,12 @@ from changedetectionio import diff
 class TestDiffBuilder(unittest.TestCase):
 
     def test_expected_diff_output(self):
-        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")
+        base_dir=os.path.dirname(__file__)
+        output = diff.render_diff(base_dir+"/test-content/before.txt", base_dir+"/test-content/after.txt")
         output = output.split("\n")
-        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)
+        self.assertIn("(changed) ok", output)
+        self.assertIn("(-> into) xok", output)
+        self.assertIn("(added) and something new", output)
 
         # @todo test blocks of changed, blocks of added, blocks of removed
 

changedetectionio/tests/util.py

@@ -35,40 +35,24 @@ 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):
 
+
     @live_server.app.route('/test-endpoint')
     def test_endpoint():
         ctype = request.args.get('content_type')
-        status_code = request.args.get('status_code')
 
-        try:
-            # Tried using a global var here but didn't seem to work, so reading from a file instead.
-            with open("test-datastore/endpoint-content.txt", "r") as f:
-                resp = make_response(f.read(), status_code)
-                resp.headers['Content-Type'] = ctype if ctype else 'text/html'
-                return resp
-        except FileNotFoundError:
-            return make_response('', status_code)
+        # Tried using a global var here but didn't seem to work, so reading from a file instead.
+        with open("test-datastore/endpoint-content.txt", "r") as f:
+            resp = make_response(f.read())
+            resp.headers['Content-Type'] = ctype if ctype else 'text/html'
+            return resp
+
+    @live_server.app.route('/test-403')
+    def test_endpoint_403_error():
+        resp = make_response('', 403)
+        return resp
 
     # Just return the headers in the request
     @live_server.app.route('/test-headers')
@@ -100,7 +84,7 @@ def live_server_setup(live_server):
             if data != None:
                 f.write(data)
 
-        print("\n>> Test notification endpoint was hit.\n", data)
+        print("\n>> Test notification endpoint was hit.\n")
         return "Text was set"
 
 

changedetectionio/update_worker.py

@@ -38,18 +38,20 @@ class update_worker(threading.Thread):
 
                     changed_detected = False
                     contents = ""
-                    screenshot = False
                     update_obj= {}
                     now = time.time()
 
                     try:
-                        changed_detected, update_obj, contents, screenshot = update_handler.run(uuid)
+
+                        changed_detected, update_obj, contents = 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.
                         # We then convert/.decode('utf-8') for the notification etc
                         if not isinstance(contents, (bytes, bytearray)):
                             raise Exception("Error - returned data from the fetch handler SHOULD be bytes")
+
+
                     except PermissionError as e:
                         self.app.logger.error("File permission error updating", uuid, str(e))
                     except content_fetcher.EmptyReply as e:
@@ -141,9 +143,6 @@ 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()

docker-compose.yml

@@ -2,7 +2,7 @@ version: '2'
 services:
     changedetection:
       image: ghcr.io/dgtlmoon/changedetection.io
-      container_name: changedetection
+      container_name: changedetection.io
       hostname: changedetection
       volumes:
         - changedetection-data:/datastore

requirements.txt

@@ -1,5 +1,5 @@
 flask~= 2.0
-flask_wtf
+
 eventlet>=0.31.0
 validators
 timeago ~=1.0
@@ -35,8 +35,3 @@ 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
-

setup.py

@@ -32,11 +32,11 @@ setup(
     long_description_content_type='text/markdown',
     keywords='website change monitor for changes notification change detection '
              'alerts tracking website tracker change alert website and monitoring',
-    entry_points={"console_scripts": ["changedetection.io=changedetectionio.changedetection:main"]},
-    zip_safe=True,
-    scripts=["changedetection.py"],
+    zip_safe=False,
+    entry_points={"console_scripts": ["changedetection.io=changedetection:main"]},
     author='dgtlmoon',
     url='https://changedetection.io',
+    scripts=['changedetection.py'],
     packages=['changedetectionio'],
     include_package_data=True,
     install_requires=install_requires,