Skip empty notification URLs from being processed

.github/dependabot.yml

@@ -0,0 +1,10 @@
+version: 2
+updates:
+  - package-ecosystem: github-actions
+    directory: /
+    schedule:
+      interval: "weekly"
+    groups:
+      all:
+        patterns:
+        - "*"

.github/workflows/codeql-analysis.yml

@@ -34,7 +34,7 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v2
+      uses: github/codeql-action/init@v3
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
@@ -45,7 +45,7 @@ jobs:
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@v2
+      uses: github/codeql-action/autobuild@v3
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 https://git.io/JvXDl
@@ -59,4 +59,4 @@ jobs:
     #   make release
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v2
+      uses: github/codeql-action/analyze@v3

.github/workflows/containers.yml

@@ -41,7 +41,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - name: Set up Python 3.11
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: 3.11
 

.github/workflows/pypi-release.yml

@@ -0,0 +1,72 @@
+name: Publish Python 🐍distribution 📦 to PyPI and TestPyPI
+
+on: push
+jobs:
+  build:
+    name: Build distribution 📦
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: "3.x"
+    - name: Install pypa/build
+      run: >-
+        python3 -m
+        pip install
+        build
+        --user
+    - name: Build a binary wheel and a source tarball
+      run: python3 -m build
+    - name: Store the distribution packages
+      uses: actions/upload-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+
+
+  test-pypi-package:
+    name: Test the built 📦 package works basically.
+    runs-on: ubuntu-latest
+    needs:
+    - build
+    steps:
+    - name: Download all the dists
+      uses: actions/download-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+    - name: Test that the basic pip built package runs without error
+      run: |
+        set -e
+        pip3 install dist/changedetection.io*.whl
+        changedetection.io -d /tmp -p 10000 &
+        sleep 3
+        curl http://127.0.0.1:10000/static/styles/pure-min.css >/dev/null
+        curl http://127.0.0.1:10000/ >/dev/null
+        killall changedetection.io
+
+
+  publish-to-pypi:
+    name: >-
+      Publish Python 🐍 distribution 📦 to PyPI
+    if: startsWith(github.ref, 'refs/tags/')  # only publish to PyPI on tag pushes
+    needs:
+    - test-pypi-package
+    runs-on: ubuntu-latest
+    environment:
+      name: release
+      url: https://pypi.org/p/changedetection.io
+    permissions:
+      id-token: write  # IMPORTANT: mandatory for trusted publishing
+
+    steps:
+    - name: Download all the dists
+      uses: actions/download-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+    - name: Publish distribution 📦 to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1

.github/workflows/test-container-build.yml

@@ -26,7 +26,7 @@ jobs:
     steps:
         - uses: actions/checkout@v4
         - name: Set up Python 3.11
-          uses: actions/setup-python@v4
+          uses: actions/setup-python@v5
           with:
             python-version: 3.11
 

.github/workflows/test-only.yml

@@ -11,7 +11,7 @@ jobs:
 
       # Mainly just for link/flake8
       - name: Set up Python 3.11
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: '3.11'
 
@@ -38,7 +38,7 @@ jobs:
       - name: Build changedetection.io container for testing
         run: |         
           # Build a changedetection.io container and start testing inside
-          docker build . -t test-changedetectionio
+          docker build --build-arg LOGGER_LEVEL=TRACE -t test-changedetectionio .
           # Debug info
           docker run test-changedetectionio  bash -c 'pip list'
 
@@ -50,9 +50,15 @@ jobs:
       - name: Test built container with pytest
         run: |
           # Unit tests
+          echo "run test with unittest"
           docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_notification_diff'
+          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_watch_model'
           
           # All tests
+          echo "run test with pytest"
+          # The default pytest logger_level is TRACE
+          # To change logger_level for pytest(test/conftest.py),
+          # append the docker option. e.g. '-e LOGGER_LEVEL=DEBUG'
           docker run --network changedet-network  test-changedetectionio  bash -c 'cd changedetectionio && ./run_basic_tests.sh'
 
       - name: Test built container selenium+browserless/playwright
@@ -97,14 +103,68 @@ jobs:
 
       - name: Test changedetection.io container starts+runs basically without error
         run: |
-          docker run -p 5556:5000 -d test-changedetectionio
+          docker run --name test-changedetectionio -p 5556:5000  -d test-changedetectionio
           sleep 3
           # Should return 0 (no error) when grep finds it
           curl -s http://localhost:5556 |grep -q checkbox-uuid
           
           # and IPv6
           curl -s -g -6 "http://[::1]:5556"|grep -q checkbox-uuid
+
+          # Check whether TRACE log is enabled.
+          # Also, check whether TRACE is came from STDERR
+          docker logs test-changedetectionio 2>&1 1>/dev/null | grep 'TRACE log is enabled' || exit 1
+          # Check whether DEBUG is came from STDOUT
+          docker logs test-changedetectionio 2>/dev/null | grep 'DEBUG' || exit 1
+
+          docker kill test-changedetectionio
+
+      - name: Test changedetection.io SIGTERM and SIGINT signal shutdown
+        run: |
           
+          echo SIGINT Shutdown request test
+          docker run --name sig-test -d test-changedetectionio
+          sleep 3
+          echo ">>> Sending SIGINT to sig-test container"
+          docker kill --signal=SIGINT sig-test
+          sleep 3
+          # invert the check (it should be not 0/not running)
+          docker ps
+          # check signal catch(STDERR) log. Because of
+          # changedetectionio/__init__.py: logger.add(sys.stderr, level=logger_level)
+          docker logs sig-test 2>&1 | grep 'Shutdown: Got Signal - SIGINT' || exit 1
+          test -z "`docker ps|grep sig-test`"
+          if [ $? -ne 0 ]
+          then
+            echo "Looks like container was running when it shouldnt be"
+            docker ps
+            exit 1
+          fi
+          
+          # @todo - scan the container log to see the right "graceful shutdown" text exists 
+          docker rm sig-test
+          
+          echo SIGTERM Shutdown request test
+          docker run --name sig-test -d test-changedetectionio
+          sleep 3
+          echo ">>> Sending SIGTERM to sig-test container"
+          docker kill --signal=SIGTERM sig-test
+          sleep 3
+          # invert the check (it should be not 0/not running)
+          docker ps
+          # check signal catch(STDERR) log. Because of
+          # changedetectionio/__init__.py: logger.add(sys.stderr, level=logger_level)
+          docker logs sig-test 2>&1 | grep 'Shutdown: Got Signal - SIGTERM' || exit 1
+          test -z "`docker ps|grep sig-test`"
+          if [ $? -ne 0 ]
+          then
+            echo "Looks like container was running when it shouldnt be"
+            docker ps
+            exit 1
+          fi
+          
+          # @todo - scan the container log to see the right "graceful shutdown" text exists           
+          docker rm sig-test
 
 #export WEBDRIVER_URL=http://localhost:4444/wd/hub
 #pytest tests/fetchers/test_content.py

.github/workflows/test-pip-build.yml

@@ -1,36 +0,0 @@
-name: ChangeDetection.io PIP package test
-
-# Triggers the workflow on push or pull request events
-
-# This line doesnt work, even tho it is the documented one
-on: [push, pull_request]
-
-  # Changes to requirements.txt packages and Dockerfile may or may not always be compatible with arm etc, so worth testing
-  # @todo: some kind of path filter for requirements.txt and Dockerfile
-jobs:
-  test-pip-build-basics:
-    runs-on: ubuntu-latest
-    steps:
-        - uses: actions/checkout@v4
-
-        - name: Set up Python 3.11
-          uses: actions/setup-python@v4
-          with:
-            python-version: 3.11
-
-
-        - name: Test that the basic pip built package runs without error
-          run: |
-            set -e
-            mkdir dist
-            pip3 install wheel
-            python3 setup.py bdist_wheel            
-            pip3 install -r requirements.txt
-            rm ./changedetection.py
-            rm -rf changedetectio
-            
-            pip3 install dist/changedetection.io*.whl
-            changedetection.io -d /tmp -p 10000 &
-            sleep 3
-            curl http://127.0.0.1:10000/static/styles/pure-min.css >/dev/null
-            killall -9 changedetection.io

Dockerfile

@@ -25,7 +25,7 @@ RUN pip install --target=/dependencies -r /requirements.txt
 # Playwright is an alternative to Selenium
 # Excluded this package from requirements.txt to prevent arm/v6 and arm/v7 builds from failing
 # https://github.com/dgtlmoon/changedetection.io/pull/1067 also musl/alpine (not supported)
-RUN pip install --target=/dependencies playwright~=1.39 \
+RUN pip install --target=/dependencies playwright~=1.40 \
     || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
 
 # Final image stage
@@ -53,12 +53,17 @@ ENV PYTHONPATH=/usr/local
 
 EXPOSE 5000
 
-# The actual flask app
+# The actual flask app module
 COPY changedetectionio /app/changedetectionio
-
-# The eventlet server wrapper
+# Starting wrapper
 COPY changedetection.py /app/changedetection.py
 
-WORKDIR /app
+# Github Action test purpose(test-only.yml).
+# On production, it is effectively LOGGER_LEVEL=''.
+ARG LOGGER_LEVEL=''
+ENV LOGGER_LEVEL "$LOGGER_LEVEL"
+
+WORKDIR /app
+CMD ["python", "./changedetection.py", "-d", "/datastore"]
+
 
-CMD [ "python", "./changedetection.py" , "-d", "/datastore"]

MANIFEST.in

@@ -10,6 +10,8 @@ prune changedetectionio/static/package-lock.json
 prune changedetectionio/static/styles/node_modules
 prune changedetectionio/static/styles/package-lock.json
 include changedetection.py
+include requirements.txt
+include README-pip.md
 global-exclude *.pyc
 global-exclude node_modules
 global-exclude venv

Procfile

@@ -1 +0,0 @@
-web: python3 ./changedetection.py -C -d ./datastore -p $PORT

README.md

@@ -11,12 +11,13 @@ _Live your data-life pro-actively._
 
 ![changedetection.io](https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master)
 
-[**Don't have time? Let us host it for you! try our $8.99/month subscription - use our proxies and support!**](https://changedetection.io) , _half the price of other website change monitoring services!_
+[**Get started with website page change monitoring straight away. Don't have time? Try our $8.99/month subscription, use our proxies and support!**](https://changedetection.io) , _half the price of other website change monitoring services!_
 
 - Chrome browser included.
+- Nothing to install, access via browser login after signup.
 - Super fast, no registration needed setup.
 - Get started watching and receiving website change notifications straight away.
-
+- See our [tutorials and how-to page for more inspiration](https://changedetection.io/tutorials) 
 
 ### Target specific parts of the webpage using the Visual Selector tool.
 
@@ -97,7 +98,7 @@ Please :star: star :star: this project and help it grow! https://github.com/dgtl
 With Docker composer, just clone this repository and..
 
 ```bash
-$ docker-compose up -d
+$ docker compose up -d
 ```
 
 Docker standalone
@@ -136,10 +137,10 @@ docker rm $(docker ps -a -f name=changedetection.io -q)
 docker run -d --restart always -p "127.0.0.1:5000:5000" -v datastore-volume:/datastore --name changedetection.io dgtlmoon/changedetection.io
 ```
 
-### docker-compose
+### docker compose
 
 ```bash
-docker-compose pull && docker-compose up -d
+docker compose pull && docker compose up -d
 ```
 
 See the wiki for more information https://github.com/dgtlmoon/changedetection.io/wiki
@@ -248,7 +249,7 @@ Supports managing the website watch list [via our API](https://changedetection.i
 Do you use changedetection.io to make money? does it save you time or money? Does it make your life easier? less stressful? Remember, we write this software when we should be doing actual paid work, we have to buy food and pay rent just like you.
 
 
-Firstly, consider taking out a [change detection monthly subscription - unlimited checks and watches](https://changedetection.io?src=github) , even if you don't use it, you still get the warm fuzzy feeling of helping out the project. (And who knows, you might just use it!)
+Firstly, consider taking out an officially supported [website change detection subscription](https://changedetection.io?src=github) , even if you don't use it, you still get the warm fuzzy feeling of helping out the project. (And who knows, you might just use it!)
 
 Or directly donate an amount PayPal [![Donate](https://img.shields.io/badge/Donate-PayPal-green.svg)](https://www.paypal.com/donate/?hosted_button_id=7CP6HR9ZCNDYJ)
 
@@ -272,3 +273,9 @@ I offer commercial support, this software is depended on by network security, ae
 ## Third-party licenses
 
 changedetectionio.html_tools.elementpath_tostring: Copyright (c), 2018-2021, SISSA (Scuola Internazionale Superiore di Studi Avanzati), Licensed under [MIT license](https://github.com/sissaschool/elementpath/blob/master/LICENSE)
+
+## Contributors
+
+Recognition of fantastic contributors to the project
+
+- Constantin Hong https://github.com/Constantin1489

app.json

@@ -1,21 +0,0 @@
-{
-  "name": "ChangeDetection.io",
-  "description": "The best and simplest self-hosted open source website change detection monitoring and notification service.",
-  "keywords": [
-    "changedetection",
-    "website monitoring"
-  ],
-  "repository": "https://github.com/dgtlmoon/changedetection.io",
-  "success_url": "/",
-  "scripts": {
-  },
-  "env": {
-  },
-  "formation": {
-    "web": {
-      "quantity": 1,
-      "size": "free"
-    }
-  },
-  "image": "heroku/python"
-}

changedetection.py

@@ -1,44 +1,6 @@
 #!/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
+# Only exists for direct CLI usage
 
-from changedetectionio import changedetection
-import multiprocessing
-import sys
-import os
-
-def sigchld_handler(_signo, _stack_frame):
-    import sys
-    print('Shutdown: Got SIGCHLD')
-    # https://stackoverflow.com/questions/40453496/python-multiprocessing-capturing-signals-to-restart-child-processes-or-shut-do
-    pid, status = os.waitpid(-1, os.WNOHANG | os.WUNTRACED | os.WCONTINUED)
-
-    print('Sub-process: pid %d status %d' % (pid, status))
-    if status != 0:
-        sys.exit(1)
-
-    raise SystemExit
-
-if __name__ == '__main__':
-
-    #signal.signal(signal.SIGCHLD, sigchld_handler)
-
-    # The only way I could find to get Flask to shutdown, is to wrap it and then rely on the subsystem issuing SIGTERM/SIGKILL
-    parse_process = multiprocessing.Process(target=changedetection.main)
-    parse_process.daemon = True
-    parse_process.start()
-    import time
-
-    try:
-        while True:
-            time.sleep(1)
-            if not parse_process.is_alive():
-                # Process died/crashed for some reason, exit with error set
-                sys.exit(1)
-
-    except KeyboardInterrupt:
-        #parse_process.terminate() not needed, because this process will issue it to the sub-process anyway
-        print ("Exited - CTRL+C")
+import changedetectionio
+changedetectionio.main()

changedetectionio/api/api_v1.py

@@ -30,7 +30,7 @@ class Watch(Resource):
         self.update_q = kwargs['update_q']
 
     # Get information about a single watch, excluding the history list (can be large)
-    # curl http://localhost:4000/api/v1/watch/<string:uuid>
+    # curl http://localhost:5000/api/v1/watch/<string:uuid>
     # @todo - version2 - ?muted and ?paused should be able to be called together, return the watch struct not "OK"
     # ?recheck=true
     @auth.check_token
@@ -39,9 +39,9 @@ class Watch(Resource):
         @api {get} /api/v1/watch/:uuid Single watch - get data, recheck, pause, mute.
         @apiDescription Retrieve watch information and set muted/paused status
         @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091?muted=unmuted"  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
-            curl "http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091?paused=unpaused"  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
+            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
+            curl "http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091?muted=unmuted"  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
+            curl "http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091?paused=unpaused"  -H"x-api-key:813031b16330fe25e3780cf0325daa45"
         @apiName Watch
         @apiGroup Watch
         @apiParam {uuid} uuid Watch unique ID.
@@ -76,7 +76,7 @@ class Watch(Resource):
         # Properties are not returned as a JSON, so add the required props manually
         watch['history_n'] = watch.history_n
         watch['last_changed'] = watch.last_changed
-
+        watch['viewed'] = watch.viewed
         return watch
 
     @auth.check_token
@@ -84,7 +84,7 @@ class Watch(Resource):
         """
         @api {delete} /api/v1/watch/:uuid Delete a watch and related history
         @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X DELETE -H"x-api-key:813031b16330fe25e3780cf0325daa45"
+            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X DELETE -H"x-api-key:813031b16330fe25e3780cf0325daa45"
         @apiParam {uuid} uuid Watch unique ID.
         @apiName Delete
         @apiGroup Watch
@@ -103,7 +103,7 @@ class Watch(Resource):
         @api {put} /api/v1/watch/:uuid Update watch information
         @apiExample {curl} Example usage:
             Update (PUT)
-            curl http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X PUT -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"url": "https://my-nice.com" , "tag": "new list"}'
+            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091 -X PUT -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"url": "https://my-nice.com" , "tag": "new list"}'
 
         @apiDescription Updates an existing watch using JSON, accepts the same structure as returned in <a href="#api-Watch-Watch">get single watch information</a>
         @apiParam {uuid} uuid Watch unique ID.
@@ -132,13 +132,14 @@ class WatchHistory(Resource):
         self.datastore = kwargs['datastore']
 
     # Get a list of available history for a watch by UUID
-    # curl http://localhost:4000/api/v1/watch/<string:uuid>/history
+    # curl http://localhost:5000/api/v1/watch/<string:uuid>/history
+    @auth.check_token
     def get(self, uuid):
         """
         @api {get} /api/v1/watch/<string:uuid>/history Get a list of all historical snapshots available for a watch
         @apiDescription Requires `uuid`, returns list
         @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091/history -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json"
+            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091/history -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json"
             {
                 "1676649279": "/tmp/data/6a4b7d5c-fee4-4616-9f43-4ac97046b595/cb7e9be8258368262246910e6a2a4c30.txt",
                 "1677092785": "/tmp/data/6a4b7d5c-fee4-4616-9f43-4ac97046b595/e20db368d6fc633e34f559ff67bb4044.txt",
@@ -166,7 +167,7 @@ class WatchSingleHistory(Resource):
         @api {get} /api/v1/watch/<string:uuid>/history/<int:timestamp> Get single snapshot from watch
         @apiDescription Requires watch `uuid` and `timestamp`. `timestamp` of "`latest`" for latest available snapshot, or <a href="#api-Watch_History-Get_list_of_available_stored_snapshots_for_watch">use the list returned here</a>
         @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091/history/1677092977 -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json"
+            curl http://localhost:5000/api/v1/watch/cc0cfffa-f449-477b-83ea-0caafd1dc091/history/1677092977 -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json"
         @apiName Get single snapshot content
         @apiGroup Watch History
         @apiSuccess (200) {String} OK
@@ -202,7 +203,7 @@ class CreateWatch(Resource):
         @api {post} /api/v1/watch Create a single watch
         @apiDescription Requires atleast `url` set, can accept the same structure as <a href="#api-Watch-Watch">get single watch information</a> to create.
         @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"url": "https://my-nice.com" , "tag": "nice list"}'
+            curl http://localhost:5000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45" -H "Content-Type: application/json" -d '{"url": "https://my-nice.com" , "tag": "nice list"}'
         @apiName Create
         @apiGroup Watch
         @apiSuccess (200) {String} OK Was created
@@ -245,7 +246,7 @@ class CreateWatch(Resource):
         @api {get} /api/v1/watch List watches
         @apiDescription Return concise list of available watches and some very basic info
         @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45"
+            curl http://localhost:5000/api/v1/watch -H"x-api-key:813031b16330fe25e3780cf0325daa45"
             {
                 "6a4b7d5c-fee4-4616-9f43-4ac97046b595": {
                     "last_changed": 1677103794,
@@ -280,11 +281,14 @@ class CreateWatch(Resource):
             if tag_limit and not any(v.get('title').lower() == tag_limit for k, v in tags.items()):
                 continue
 
-            list[uuid] = {'url': watch['url'],
-                       'title': watch['title'],
-                       'last_checked': watch['last_checked'],
-                       'last_changed': watch.last_changed,
-                       'last_error': watch['last_error']}
+            list[uuid] = {
+                'last_changed': watch.last_changed,
+                'last_checked': watch['last_checked'],
+                'last_error': watch['last_error'],
+                'title': watch['title'],
+                'url': watch['url'],
+                'viewed': watch.viewed
+            }
 
         if request.args.get('recheck_all'):
             for uuid in self.datastore.data['watching'].keys():
@@ -293,6 +297,61 @@ class CreateWatch(Resource):
 
         return list, 200
 
+class Import(Resource):
+    def __init__(self, **kwargs):
+        # datastore is a black box dependency
+        self.datastore = kwargs['datastore']
+
+    @auth.check_token
+    def post(self):
+        """
+        @api {post} /api/v1/import Import a list of watched URLs
+        @apiDescription Accepts a line-feed separated list of URLs to import, additionally with ?tag_uuids=(tag  id), ?tag=(name), ?proxy={key}, ?dedupe=true (default true) one URL per line.
+        @apiExample {curl} Example usage:
+            curl http://localhost:5000/api/v1/import --data-binary @list-of-sites.txt -H"x-api-key:8a111a21bc2f8f1dd9b9353bbd46049a"
+        @apiName Import
+        @apiGroup Watch
+        @apiSuccess (200) {List} OK List of watch UUIDs added
+        @apiSuccess (500) {String} ERR Some other error
+        """
+
+        extras = {}
+
+        if request.args.get('proxy'):
+            plist = self.datastore.proxy_list
+            if not request.args.get('proxy') in plist:
+                return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
+            else:
+                extras['proxy'] = request.args.get('proxy')
+
+        dedupe = strtobool(request.args.get('dedupe', 'true'))
+
+        tags = request.args.get('tag')
+        tag_uuids = request.args.get('tag_uuids')
+
+        if tag_uuids:
+            tag_uuids = tag_uuids.split(',')
+
+        urls = request.get_data().decode('utf8').splitlines()
+        added = []
+        allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
+        for url in urls:
+            url = url.strip()
+            if not len(url):
+                continue
+
+            # If hosts that only contain alphanumerics are allowed ("localhost" for example)
+            if not validators.url(url, simple_host=allow_simplehost):
+                return f"Invalid or unsupported URL - {url}", 400
+
+            if dedupe and self.datastore.url_exists(url):
+                continue
+
+            new_uuid = self.datastore.add_watch(url=url, extras=extras, tag=tags, tag_uuids=tag_uuids)
+            added.append(new_uuid)
+
+        return added
+
 class SystemInfo(Resource):
     def __init__(self, **kwargs):
         # datastore is a black box dependency
@@ -305,7 +364,7 @@ class SystemInfo(Resource):
         @api {get} /api/v1/systeminfo Return system info
         @apiDescription Return some info about the current system state
         @apiExample {curl} Example usage:
-            curl http://localhost:4000/api/v1/systeminfo -H"x-api-key:813031b16330fe25e3780cf0325daa45"
+            curl http://localhost:5000/api/v1/systeminfo -H"x-api-key:813031b16330fe25e3780cf0325daa45"
             HTTP/1.0 200
             {
                 'queue_size': 10 ,

changedetectionio/blueprint/browser_steps/__init__.py

@@ -23,12 +23,11 @@
 
 from distutils.util import strtobool
 from flask import Blueprint, request, make_response
-import logging
 import os
-import re
 
 from changedetectionio.store import ChangeDetectionStore
-from changedetectionio import login_optionally_required
+from changedetectionio.flask_app import login_optionally_required
+from loguru import logger
 
 browsersteps_sessions = {}
 io_interface_context = None
@@ -59,7 +58,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             io_interface_context = io_interface_context.start()
 
         keepalive_ms = ((keepalive_seconds + 3) * 1000)
-        base_url = os.getenv('PLAYWRIGHT_DRIVER_URL', '')
+        base_url = os.getenv('PLAYWRIGHT_DRIVER_URL', '').strip('"')
         a = "?" if not '?' in base_url else '&'
         base_url += a + f"timeout={keepalive_ms}"
 
@@ -89,7 +88,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                 if parsed.password:
                     proxy['password'] = parsed.password
 
-                print("Browser Steps: UUID {} selected proxy {}".format(watch_uuid, proxy_url))
+                logger.debug(f"Browser Steps: UUID {watch_uuid} selected proxy {proxy_url}")
 
         # Tell Playwright to connect to Chrome and setup a new session via our stepper interface
         browsersteps_start_session['browserstepper'] = browser_steps.browsersteps_live_ui(
@@ -116,10 +115,10 @@ def construct_blueprint(datastore: ChangeDetectionStore):
         if not watch_uuid:
             return make_response('No Watch UUID specified', 500)
 
-        print("Starting connection with playwright")
-        logging.debug("browser_steps.py connecting")
+        logger.debug("Starting connection with playwright")
+        logger.debug("browser_steps.py connecting")
         browsersteps_sessions[browsersteps_session_id] = start_browsersteps_session(watch_uuid)
-        print("Starting connection with playwright - done")
+        logger.debug("Starting connection with playwright - done")
         return {'browsersteps_session_id': browsersteps_session_id}
 
     @login_optionally_required
@@ -152,7 +151,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
     @browser_steps_blueprint.route("/browsersteps_update", methods=['POST'])
     def browsersteps_ui_update():
         import base64
-        import playwright._impl._api_types
+        import playwright._impl._errors
         global browsersteps_sessions
         from changedetectionio.blueprint.browser_steps import browser_steps
 
@@ -190,7 +189,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
                                          optional_value=step_optional_value)
 
             except Exception as e:
-                print("Exception when calling step operation", step_operation, str(e))
+                logger.error(f"Exception when calling step operation {step_operation} {str(e)}")
                 # Try to find something of value to give back to the user
                 return make_response(str(e).splitlines()[0], 401)
 

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -4,6 +4,7 @@ import os
 import time
 import re
 from random import randint
+from loguru import logger
 
 # Two flags, tell the JS which of the "Selector" or "Value" field should be enabled in the front end
 # 0- off, 1- on
@@ -53,7 +54,7 @@ class steppable_browser_interface():
         if call_action_name == 'choose_one':
             return
 
-        print("> action calling", call_action_name)
+        logger.debug(f"> Action calling '{call_action_name}'")
         # https://playwright.dev/python/docs/selectors#xpath-selectors
         if selector and selector.startswith('/') and not selector.startswith('//'):
             selector = "xpath=" + selector
@@ -72,7 +73,7 @@ class steppable_browser_interface():
 
         action_handler(selector, optional_value)
         self.page.wait_for_timeout(1.5 * 1000)
-        print("Call action done in", time.time() - now)
+        logger.debug(f"Call action done in {time.time()-now:.2f}s")
 
     def action_goto_url(self, selector=None, value=None):
         # self.page.set_viewport_size({"width": 1280, "height": 5000})
@@ -82,7 +83,7 @@ class steppable_browser_interface():
         #and also wait for seconds ?
         #await page.waitForTimeout(1000);
         #await page.waitForTimeout(extra_wait_ms);
-        print("Time to goto URL ", time.time() - now)
+        logger.debug(f"Time to goto URL {time.time()-now:.2f}s")
         return response
 
     def action_click_element_containing_text(self, selector=None, value=''):
@@ -103,15 +104,15 @@ class steppable_browser_interface():
         return response
 
     def action_click_element(self, selector, value):
-        print("Clicking element")
+        logger.debug("Clicking element")
         if not len(selector.strip()):
             return
 
         self.page.click(selector=selector, timeout=30 * 1000, delay=randint(200, 500))
 
     def action_click_element_if_exists(self, selector, value):
-        import playwright._impl._api_types as _api_types
-        print("Clicking element if exists")
+        import playwright._impl._errors as _api_types
+        logger.debug("Clicking element if exists")
         if not len(selector.strip()):
             return
         try:
@@ -123,6 +124,9 @@ class steppable_browser_interface():
             return
 
     def action_click_x_y(self, selector, value):
+        if not re.match(r'^\s?\d+\s?,\s?\d+\s?$', value):
+            raise Exception("'Click X,Y' step should be in the format of '100 , 90'")
+
         x, y = value.strip().split(',')
         x = int(float(x.strip()))
         y = int(float(y.strip()))
@@ -224,11 +228,11 @@ class browsersteps_live_ui(steppable_browser_interface):
         # Listen for all console events and handle errors
         self.page.on("console", lambda msg: print(f"Browser steps console - {msg.type}: {msg.text} {msg.args}"))
 
-        print("Time to browser setup", time.time() - now)
+        logger.debug(f"Time to browser setup {time.time()-now:.2f}s")
         self.page.wait_for_timeout(1 * 1000)
 
     def mark_as_closed(self):
-        print("Page closed, cleaning up..")
+        logger.debug("Page closed, cleaning up..")
 
     @property
     def has_expired(self):
@@ -254,7 +258,7 @@ class browsersteps_live_ui(steppable_browser_interface):
         xpath_data = self.page.evaluate("async () => {" + xpath_element_js + "}")
         # So the JS will find the smallest one first
         xpath_data['size_pos'] = sorted(xpath_data['size_pos'], key=lambda k: k['width'] * k['height'], reverse=True)
-        print("Time to complete get_current_state of browser", time.time() - now)
+        logger.debug(f"Time to complete get_current_state of browser {time.time()-now:.2f}s")
         # except
         # playwright._impl._api_types.Error: Browser closed.
         # @todo show some countdown timer?

changedetectionio/blueprint/tags/__init__.py

@@ -1,6 +1,6 @@
 from flask import Blueprint, request, make_response, render_template, flash, url_for, redirect
 from changedetectionio.store import ChangeDetectionStore
-from changedetectionio import login_optionally_required
+from changedetectionio.flask_app import login_optionally_required
 
 
 def construct_blueprint(datastore: ChangeDetectionStore):

changedetectionio/blueprint/tags/templates/edit-tag.html

@@ -3,7 +3,7 @@
 {% from '_helpers.jinja' import render_field, render_checkbox_field, render_button %}
 {% from '_common_fields.jinja' import render_common_settings_form %}
 <script>
-    const notification_base_url="{{url_for('ajax_callback_send_notification_test')}}";
+    const notification_base_url="{{url_for('ajax_callback_send_notification_test', watch_uuid=uuid)}}";
 </script>
 
 <script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>

changedetectionio/changedetection.py

@@ -1,153 +0,0 @@
-#!/usr/bin/python3
-
-# Launch as a eventlet.wsgi server instance.
-
-from distutils.util import strtobool
-from json.decoder import JSONDecodeError
-
-import eventlet
-import eventlet.wsgi
-import getopt
-import os
-import signal
-import socket
-import sys
-
-from . import store, changedetection_app, content_fetcher
-from . import __version__
-
-# Only global so we can access it in the signal handler
-app = None
-datastore = None
-
-def sigterm_handler(_signo, _stack_frame):
-    global app
-    global datastore
-#    app.config.exit.set()
-    print('Shutdown: Got SIGTERM, DB saved to disk')
-    datastore.sync_to_json()
-#    raise SystemExit
-
-def main():
-    global datastore
-    global app
-
-    datastore_path = None
-    do_cleanup = False
-    host = ''
-    ipv6_enabled = False
-    port = os.environ.get('PORT') or 5000
-    ssl_mode = False
-
-    # 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:], "6Ccsd: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 == '-s':
-            ssl_mode = True
-
-        if opt == '-h':
-            host = arg
-
-        if opt == '-p':
-            port = int(arg)
-
-        if opt == '-d':
-            datastore_path = arg
-
-        if opt == '-6':
-            print ("Enabling IPv6 listen support")
-            ipv6_enabled = True
-
-        # 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)
-
-    try:
-        datastore = store.ChangeDetectionStore(datastore_path=app_config['datastore_path'], version_tag=__version__)
-    except JSONDecodeError as e:
-        # Dont' start if the JSON DB looks corrupt
-        print ("ERROR: JSON DB or Proxy List JSON at '{}' appears to be corrupt, aborting".format(app_config['datastore_path']))
-        print(str(e))
-        return
-
-    app = changedetection_app(app_config, datastore)
-
-    signal.signal(signal.SIGTERM, sigterm_handler)
-
-    # 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
-                    )
-
-    # Monitored websites will not receive a Referer header when a user clicks on an outgoing link.
-    # @Note: Incompatible with password login (and maybe other features) for now, submit a PR!
-    @app.after_request
-    def hide_referrer(response):
-        if strtobool(os.getenv("HIDE_REFERER", 'false')):
-            response.headers["Referrer-Policy"] = "no-referrer"
-
-        return response
-
-    # 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)
-
-    s_type = socket.AF_INET6 if ipv6_enabled else socket.AF_INET
-
-    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), s_type),
-                                               certfile='cert.pem',
-                                               keyfile='privkey.pem',
-                                               server_side=True), app)
-
-    else:
-        eventlet.wsgi.server(eventlet.listen((host, int(port)), s_type), app)
-

changedetectionio/content_fetcher.py

@@ -4,12 +4,12 @@ from urllib.parse import urlparse
 import chardet
 import hashlib
 import json
-import logging
 import os
 import requests
 import sys
 import time
 import urllib.parse
+from loguru import logger
 
 visualselector_xpath_selectors = 'div,span,form,table,tbody,tr,td,a,p,ul,li,h1,h2,h3,h4, header, footer, section, article, aside, details, main, nav, section, summary'
 
@@ -43,9 +43,11 @@ class JSActionExceptions(Exception):
         return
 
 
-class BrowserStepsStepTimout(Exception):
-    def __init__(self, step_n):
+class BrowserStepsStepException(Exception):
+    def __init__(self, step_n, original_e):
         self.step_n = step_n
+        self.original_e = original_e
+        logger.debug(f"Browser Steps exception at step {self.step_n} {str(original_e)}")
         return
 
 
@@ -91,19 +93,20 @@ class ReplyWithContentButNoText(Exception):
 
 
 class Fetcher():
+    browser_connection_is_custom = None
+    browser_connection_url = None
     browser_steps = None
     browser_steps_screenshot_path = None
     content = None
     error = None
     fetcher_description = "No description"
-    browser_connection_url = None
     headers = {}
+    instock_data = None
+    instock_data_js = ""
     status_code = None
     webdriver_js_execute_code = None
     xpath_data = None
     xpath_element_js = ""
-    instock_data = None
-    instock_data_js = ""
 
     # Will be needed in the future by the VisualSelector, always get this where possible.
     screenshot = False
@@ -172,7 +175,7 @@ class Fetcher():
 
     def iterate_browser_steps(self):
         from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
-        from playwright._impl._api_types import TimeoutError
+        from playwright._impl._errors import TimeoutError, Error
         from jinja2 import Environment
         jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
 
@@ -185,7 +188,7 @@ class Fetcher():
 
             for step in valid_steps:
                 step_n += 1
-                print(">> Iterating check - browser Step n {} - {}...".format(step_n, step['operation']))
+                logger.debug(f">> Iterating check - browser Step n {step_n} - {step['operation']}...")
                 self.screenshot_step("before-" + str(step_n))
                 self.save_step_html("before-" + str(step_n))
                 try:
@@ -202,10 +205,10 @@ class Fetcher():
                                                       optional_value=optional_value)
                     self.screenshot_step(step_n)
                     self.save_step_html(step_n)
-                except TimeoutError as e:
-                    print(str(e))
+                except (Error, TimeoutError) as e:
+                    logger.debug(str(e))
                     # Stop processing here
-                    raise BrowserStepsStepTimout(step_n=step_n)
+                    raise BrowserStepsStepException(step_n=step_n, original_e=e)
 
     # It's always good to reset these
     def delete_browser_steps_screenshots(self):
@@ -252,16 +255,19 @@ class base_html_playwright(Fetcher):
 
     proxy = None
 
-    def __init__(self, proxy_override=None, browser_connection_url=None):
+    def __init__(self, proxy_override=None, custom_browser_connection_url=None):
         super().__init__()
 
         self.browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
 
-        # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
-        if not browser_connection_url:
-            self.browser_connection_url = os.getenv("PLAYWRIGHT_DRIVER_URL", 'ws://playwright-chrome:3000').strip('"')
+        if custom_browser_connection_url:
+            self.browser_connection_is_custom = True
+            self.browser_connection_url = custom_browser_connection_url
         else:
-            self.browser_connection_url = browser_connection_url
+            # Fallback to fetching from system
+            # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
+            self.browser_connection_url = os.getenv("PLAYWRIGHT_DRIVER_URL", 'ws://playwright-chrome:3000').strip('"')
+
 
         # If any proxy settings are enabled, then we should setup the proxy object
         proxy_args = {}
@@ -289,14 +295,14 @@ class base_html_playwright(Fetcher):
 
         if self.browser_steps_screenshot_path is not None:
             destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.jpeg'.format(step_n))
-            logging.debug("Saving step screenshot to {}".format(destination))
+            logger.debug(f"Saving step screenshot to {destination}")
             with open(destination, 'wb') as f:
                 f.write(screenshot)
 
     def save_step_html(self, step_n):
         content = self.page.content()
         destination = os.path.join(self.browser_steps_screenshot_path, 'step_{}.html'.format(step_n))
-        logging.debug("Saving step HTML to {}".format(destination))
+        logger.debug(f"Saving step HTML to {destination}")
         with open(destination, 'w') as f:
             f.write(content)
 
@@ -421,8 +427,10 @@ class base_html_playwright(Fetcher):
             current_include_filters=None,
             is_binary=False):
 
+
         # For now, USE_EXPERIMENTAL_PUPPETEER_FETCH is not supported by watches with BrowserSteps (for now!)
-        if not self.browser_steps and os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH'):
+        # browser_connection_is_custom doesnt work with puppeteer style fetch (use playwright native too in this case)
+        if not self.browser_connection_is_custom and not self.browser_steps and os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH'):
             if strtobool(os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH')):
                 # Temporary backup solution until we rewrite the playwright code
                 return self.run_fetch_browserless_puppeteer(
@@ -436,7 +444,7 @@ class base_html_playwright(Fetcher):
                     is_binary)
 
         from playwright.sync_api import sync_playwright
-        import playwright._impl._api_types
+        import playwright._impl._errors
 
         self.delete_browser_steps_screenshots()
         response = None
@@ -483,19 +491,19 @@ class base_html_playwright(Fetcher):
             if response is None:
                 context.close()
                 browser.close()
-                print("Content Fetcher > Response object was none")
+                logger.debug("Content Fetcher > Response object was none")
                 raise EmptyReply(url=url, status_code=None)
 
             try:
                 if self.webdriver_js_execute_code is not None and len(self.webdriver_js_execute_code):
                     browsersteps_interface.action_execute_js(value=self.webdriver_js_execute_code, selector=None)
-            except playwright._impl._api_types.TimeoutError as e:
+            except playwright._impl._errors.TimeoutError as e:
                 context.close()
                 browser.close()
                 # This can be ok, we will try to grab what we could retrieve
                 pass
             except Exception as e:
-                print("Content Fetcher > Other exception when executing custom JS code", str(e))
+                logger.debug(f"Content Fetcher > Other exception when executing custom JS code {str(e)}")
                 context.close()
                 browser.close()
                 raise PageUnloadable(url=url, status_code=None, message=str(e))
@@ -503,8 +511,13 @@ class base_html_playwright(Fetcher):
             extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
             self.page.wait_for_timeout(extra_wait * 1000)
 
-
-            self.status_code = response.status
+            try:
+                self.status_code = response.status
+            except Exception as e:
+                # https://github.com/dgtlmoon/changedetection.io/discussions/2122#discussioncomment-8241962
+                logger.critical(f"Response from browserless/playwright did not have a status_code! Response follows.")
+                logger.critical(response)
+                raise PageUnloadable(url=url, status_code=None, message=str(e))
 
             if self.status_code != 200 and not ignore_status_codes:
 
@@ -516,7 +529,7 @@ class base_html_playwright(Fetcher):
             if len(self.page.content().strip()) == 0:
                 context.close()
                 browser.close()
-                print("Content Fetcher > Content was empty")
+                logger.debug("Content Fetcher > Content was empty")
                 raise EmptyReply(url=url, status_code=response.status)
 
             # Run Browser Steps here
@@ -569,15 +582,16 @@ class base_html_webdriver(Fetcher):
                                         'socksProxy', 'socksVersion', 'socksUsername', 'socksPassword']
     proxy = None
 
-    def __init__(self, proxy_override=None, browser_connection_url=None):
+    def __init__(self, proxy_override=None, custom_browser_connection_url=None):
         super().__init__()
         from selenium.webdriver.common.proxy import Proxy as SeleniumProxy
 
         # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
-        if not browser_connection_url:
+        if not custom_browser_connection_url:
             self.browser_connection_url = os.getenv("WEBDRIVER_URL", 'http://browser-chrome:4444/wd/hub').strip('"')
         else:
-            self.browser_connection_url = browser_connection_url
+            self.browser_connection_is_custom = True
+            self.browser_connection_url = custom_browser_connection_url
 
         # If any proxy settings are enabled, then we should setup the proxy object
         proxy_args = {}
@@ -667,14 +681,14 @@ class base_html_webdriver(Fetcher):
             try:
                 self.driver.quit()
             except Exception as e:
-                print("Content Fetcher > Exception in chrome shutdown/quit" + str(e))
+                logger.debug(f"Content Fetcher > Exception in chrome shutdown/quit {str(e)}")
 
 
 # "html_requests" is listed as the default fetcher in store.py!
 class html_requests(Fetcher):
     fetcher_description = "Basic fast Plaintext/HTTP Client"
 
-    def __init__(self, proxy_override=None, browser_connection_url=None):
+    def __init__(self, proxy_override=None, custom_browser_connection_url=None):
         super().__init__()
         self.proxy_override = proxy_override
         # browser_connection_url is none because its always 'launched locally'

changedetectionio/forms.py

@@ -43,6 +43,7 @@ valid_method = {
     'PUT',
     'PATCH',
     'DELETE',
+    'OPTIONS',
 }
 
 default_method = 'GET'

changedetectionio/importer.py

@@ -2,6 +2,7 @@ from abc import ABC, abstractmethod
 import time
 import validators
 from wtforms import ValidationError
+from loguru import logger
 
 from changedetectionio.forms import validate_url
 
@@ -195,7 +196,7 @@ class import_xlsx_wachete(Importer):
                     try:
                         validate_url(data.get('url'))
                     except ValidationError as e:
-                        print(">> import URL error", data.get('url'), str(e))
+                        logger.error(f">> Import URL error {data.get('url')} {str(e)}")
                         flash(f"Error processing row number {row_id}, URL value was incorrect, row was skipped.", 'error')
                         # Don't bother processing anything else on this row
                         continue
@@ -209,7 +210,7 @@ class import_xlsx_wachete(Importer):
                         self.new_uuids.append(new_uuid)
                         good += 1
             except Exception as e:
-                print(e)
+                logger.error(e)
                 flash(f"Error processing row number {row_id}, check all cell data types are correct, row was skipped.", 'error')
             else:
                 row_id += 1
@@ -264,7 +265,7 @@ class import_xlsx_custom(Importer):
                         try:
                             validate_url(url)
                         except ValidationError as e:
-                            print(">> Import URL error", url, str(e))
+                            logger.error(f">> Import URL error {url} {str(e)}")
                             flash(f"Error processing row number {row_i}, URL value was incorrect, row was skipped.", 'error')
                             # Don't bother processing anything else on this row
                             url = None
@@ -293,7 +294,7 @@ class import_xlsx_custom(Importer):
                         self.new_uuids.append(new_uuid)
                         good += 1
         except Exception as e:
-            print(e)
+            logger.error(e)
             flash(f"Error processing row number {row_i}, check all cell data types are correct, row was skipped.", 'error')
         else:
             row_i += 1

changedetectionio/model/Watch.py

@@ -1,10 +1,10 @@
 from distutils.util import strtobool
-import logging
 import os
 import re
 import time
 import uuid
 from pathlib import Path
+from loguru import logger
 
 # Allowable protocols, protects against javascript: etc
 # file:// is further checked by ALLOW_FILE_URI
@@ -38,6 +38,7 @@ base_config = {
     'track_ldjson_price_data': None,
     'headers': {},  # Extra headers to send
     'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
+    'in_stock' : None,
     'in_stock_only' : True, # Only trigger change on going to instock from out-of-stock
     'include_filters': [],
     'last_checked': 0,
@@ -113,14 +114,15 @@ class model(dict):
 
     @property
     def viewed(self):
-        if int(self['last_viewed']) >= int(self.newest_history_key) :
+        # Don't return viewed when last_viewed is 0 and newest_key is 0
+        if int(self['last_viewed']) and int(self['last_viewed']) >= int(self.newest_history_key) :
             return True
 
         return False
 
     def ensure_data_dir_exists(self):
         if not os.path.isdir(self.watch_data_dir):
-            print ("> Creating data dir {}".format(self.watch_data_dir))
+            logger.debug(f"> Creating data dir {self.watch_data_dir}")
             os.mkdir(self.watch_data_dir)
 
     @property
@@ -209,7 +211,7 @@ class model(dict):
         # Read the history file as a dict
         fname = os.path.join(self.watch_data_dir, "history.txt")
         if os.path.isfile(fname):
-            logging.debug("Reading history index " + str(time.time()))
+            logger.debug(f"Reading watch history index for {self.get('uuid')}")
             with open(fname, "r") as f:
                 for i in f.readlines():
                     if ',' in i:
@@ -244,10 +246,10 @@ class model(dict):
     @property
     def has_browser_steps(self):
         has_browser_steps = self.get('browser_steps') and list(filter(
-                lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
-                self.get('browser_steps')))
+            lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
+            self.get('browser_steps')))
 
-        return  has_browser_steps
+        return has_browser_steps
 
     # Returns the newest key, but if theres only 1 record, then it's counted as not being new, so return 0.
     @property
@@ -262,6 +264,38 @@ class model(dict):
         bump = self.history
         return self.__newest_history_key
 
+    # Given an arbitrary timestamp, find the closest next key
+    # For example, last_viewed = 1000 so it should return the next 1001 timestamp
+    #
+    # used for the [diff] button so it can preset a smarter from_version
+    @property
+    def get_next_snapshot_key_to_last_viewed(self):
+
+        """Unfortunately for now timestamp is stored as string key"""
+        keys = list(self.history.keys())
+        if not keys:
+            return None
+
+        last_viewed = int(self.get('last_viewed'))
+        prev_k = keys[0]
+        sorted_keys = sorted(keys, key=lambda x: int(x))
+        sorted_keys.reverse()
+
+        # When the 'last viewed' timestamp is greater than the newest snapshot, return second last
+        if last_viewed > int(sorted_keys[0]):
+            return sorted_keys[1]
+
+        for k in sorted_keys:
+            if int(k) < last_viewed:
+                if prev_k == sorted_keys[0]:
+                    # Return the second last one so we dont recommend the same version compares itself
+                    return sorted_keys[1]
+
+                return prev_k
+            prev_k = k
+
+        return keys[0]
+
     def get_history_snapshot(self, timestamp):
         import brotli
         filepath = self.history[timestamp]

changedetectionio/notification.py

@@ -1,7 +1,9 @@
 import apprise
+import time
 from jinja2 import Environment, BaseLoader
 from apprise import NotifyFormat
 import json
+from loguru import logger
 
 valid_tokens = {
     'base_url': '',
@@ -46,6 +48,9 @@ from apprise.decorators import notify
 @notify(on="puts")
 def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
     import requests
+    from apprise.utils import parse_url as apprise_parse_url
+    from apprise.URLBase import URLBase
+
     url = kwargs['meta'].get('url')
 
     if url.startswith('post'):
@@ -68,27 +73,59 @@ def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
     url = url.replace('delete://', 'http://')
     url = url.replace('deletes://', 'https://')
 
-    # Try to auto-guess if it's JSON
     headers = {}
+    params = {}
+    auth = None
+
+    # Convert /foobar?+some-header=hello to proper header dictionary
+    results = apprise_parse_url(url)
+    if results:
+        # Add our headers that the user can potentially over-ride if they wish
+        # to to our returned result set and tidy entries by unquoting them
+        headers = {URLBase.unquote(x): URLBase.unquote(y)
+                   for x, y in results['qsd+'].items()}
+
+        # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
+        # In Apprise, it relies on prefixing each request arg with "-", because it uses say &method=update as a flag for apprise
+        # but here we are making straight requests, so we need todo convert this against apprise's logic
+        for k, v in results['qsd'].items():
+            if not k.strip('+-') in results['qsd+'].keys():
+                params[URLBase.unquote(k)] = URLBase.unquote(v)
+
+        # Determine Authentication
+        auth = ''
+        if results.get('user') and results.get('password'):
+            auth = (URLBase.unquote(results.get('user')), URLBase.unquote(results.get('user')))
+        elif results.get('user'):
+            auth = (URLBase.unquote(results.get('user')))
+
+    # Try to auto-guess if it's JSON
     try:
         json.loads(body)
-        headers = {'Content-Type': 'application/json; charset=utf-8'}
+        headers['Content-Type'] = 'application/json; charset=utf-8'
     except ValueError as e:
         pass
 
-
-    r(url, headers=headers, data=body)
+    r(results.get('url'),
+      auth=auth,
+      data=body,
+      headers=headers,
+      params=params
+      )
 
 
 def process_notification(n_object, datastore):
 
+    now = time.time()
+    if n_object.get('notification_timestamp'):
+        logger.trace(f"Time since queued {now-n_object['notification_timestamp']:.3f}s")
     # Insert variables into the notification content
     notification_parameters = create_notification_parameters(n_object, datastore)
 
     # Get the notification body from datastore
     jinja2_env = Environment(loader=BaseLoader)
-    n_body = jinja2_env.from_string(n_object.get('notification_body', default_notification_body)).render(**notification_parameters)
-    n_title = jinja2_env.from_string(n_object.get('notification_title', default_notification_title)).render(**notification_parameters)
+    n_body = jinja2_env.from_string(n_object.get('notification_body', '')).render(**notification_parameters)
+    n_title = jinja2_env.from_string(n_object.get('notification_title', '')).render(**notification_parameters)
     n_format = valid_notification_formats.get(
         n_object.get('notification_format', default_notification_format),
         valid_notification_formats[default_notification_format],
@@ -99,103 +136,114 @@ def process_notification(n_object, datastore):
         # Initially text or whatever
         n_format = datastore.data['settings']['application'].get('notification_format', valid_notification_formats[default_notification_format])
 
+    logger.trace(f"Complete notification body including Jinja and placeholders calculated in  {time.time() - now:.3f}s")
 
     # https://github.com/caronc/apprise/wiki/Development_LogCapture
     # Anything higher than or equal to WARNING (which covers things like Connection errors)
     # raise it as an exception
-    apobjs=[]
-    sent_objs=[]
+
+    sent_objs = []
     from .apprise_asset import asset
-    for url in n_object['notification_urls']:
-        url = jinja2_env.from_string(url).render(**notification_parameters)
-        apobj = apprise.Apprise(debug=True, asset=asset)
-        url = url.strip()
-        if len(url):
-            print(">> Process Notification: AppRise notifying {}".format(url))
-            with apprise.LogCapture(level=apprise.logging.DEBUG) as logs:
-                # Re 323 - Limit discord length to their 2000 char limit total or it wont send.
-                # Because different notifications may require different pre-processing, run each sequentially :(
-                # 2000 bytes minus -
-                #     200 bytes for the overhead of the _entire_ json payload, 200 bytes for {tts, wait, content} etc headers
-                #     Length of URL - Incase they specify a longer custom avatar_url
+    apobj = apprise.Apprise(debug=True, asset=asset)
 
-                # So if no avatar_url is specified, add one so it can be correctly calculated into the total payload
-                k = '?' if not '?' in url else '&'
-                if not 'avatar_url' in url \
-                        and not url.startswith('mail') \
-                        and not url.startswith('post') \
-                        and not url.startswith('get') \
-                        and not url.startswith('delete') \
-                        and not url.startswith('put'):
-                    url += k + 'avatar_url=https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png'
+    if not n_object.get('notification_urls'):
+        return None
 
-                if url.startswith('tgram://'):
-                    # Telegram only supports a limit subset of HTML, remove the '<br>' we place in.
-                    # re https://github.com/dgtlmoon/changedetection.io/issues/555
-                    # @todo re-use an existing library we have already imported to strip all non-allowed tags
-                    n_body = n_body.replace('<br>', '\n')
-                    n_body = n_body.replace('</br>', '\n')
-                    # real limit is 4096, but minus some for extra metadata
-                    payload_max_size = 3600
-                    body_limit = max(0, payload_max_size - len(n_title))
-                    n_title = n_title[0:payload_max_size]
-                    n_body = n_body[0:body_limit]
+    with apprise.LogCapture(level=apprise.logging.DEBUG) as logs:
+        for url in n_object['notification_urls']:
+            url = url.strip()
+            if not url:
+                logger.warning(f"Process Notification: skipping empty notification URL.")
+                continue
 
-                elif url.startswith('discord://') or url.startswith('https://discordapp.com/api/webhooks') or url.startswith('https://discord.com/api'):
-                    # real limit is 2000, but minus some for extra metadata
-                    payload_max_size = 1700
-                    body_limit = max(0, payload_max_size - len(n_title))
-                    n_title = n_title[0:payload_max_size]
-                    n_body = n_body[0:body_limit]
+            logger.info(">> Process Notification: AppRise notifying {}".format(url))
+            url = jinja2_env.from_string(url).render(**notification_parameters)
 
-                elif url.startswith('mailto'):
-                    # Apprise will default to HTML, so we need to override it
-                    # So that whats' generated in n_body is in line with what is going to be sent.
-                    # https://github.com/caronc/apprise/issues/633#issuecomment-1191449321
-                    if not 'format=' in url and (n_format == 'Text' or n_format == 'Markdown'):
-                        prefix = '?' if not '?' in url else '&'
-                        # Apprise format is lowercase text https://github.com/caronc/apprise/issues/633
-                        n_format = n_format.tolower()
-                        url = "{}{}format={}".format(url, prefix, n_format)
-                    # If n_format == HTML, then apprise email should default to text/html and we should be sending HTML only
+            # Re 323 - Limit discord length to their 2000 char limit total or it wont send.
+            # Because different notifications may require different pre-processing, run each sequentially :(
+            # 2000 bytes minus -
+            #     200 bytes for the overhead of the _entire_ json payload, 200 bytes for {tts, wait, content} etc headers
+            #     Length of URL - Incase they specify a longer custom avatar_url
 
-                apobj.add(url)
+            # So if no avatar_url is specified, add one so it can be correctly calculated into the total payload
+            k = '?' if not '?' in url else '&'
+            if not 'avatar_url' in url \
+                    and not url.startswith('mail') \
+                    and not url.startswith('post') \
+                    and not url.startswith('get') \
+                    and not url.startswith('delete') \
+                    and not url.startswith('put'):
+                url += k + 'avatar_url=https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png'
 
-                apobj.notify(
-                    title=n_title,
-                    body=n_body,
-                    body_format=n_format,
-                    # False is not an option for AppRise, must be type None
-                    attach=n_object.get('screenshot', None)
-                )
+            if url.startswith('tgram://'):
+                # Telegram only supports a limit subset of HTML, remove the '<br>' we place in.
+                # re https://github.com/dgtlmoon/changedetection.io/issues/555
+                # @todo re-use an existing library we have already imported to strip all non-allowed tags
+                n_body = n_body.replace('<br>', '\n')
+                n_body = n_body.replace('</br>', '\n')
+                # real limit is 4096, but minus some for extra metadata
+                payload_max_size = 3600
+                body_limit = max(0, payload_max_size - len(n_title))
+                n_title = n_title[0:payload_max_size]
+                n_body = n_body[0:body_limit]
 
-                apobj.clear()
+            elif url.startswith('discord://') or url.startswith('https://discordapp.com/api/webhooks') or url.startswith(
+                    'https://discord.com/api'):
+                # real limit is 2000, but minus some for extra metadata
+                payload_max_size = 1700
+                body_limit = max(0, payload_max_size - len(n_title))
+                n_title = n_title[0:payload_max_size]
+                n_body = n_body[0:body_limit]
 
-                # Incase it needs to exist in memory for a while after to process(?)
-                apobjs.append(apobj)
+            elif url.startswith('mailto'):
+                # Apprise will default to HTML, so we need to override it
+                # So that whats' generated in n_body is in line with what is going to be sent.
+                # https://github.com/caronc/apprise/issues/633#issuecomment-1191449321
+                if not 'format=' in url and (n_format == 'Text' or n_format == 'Markdown'):
+                    prefix = '?' if not '?' in url else '&'
+                    # Apprise format is lowercase text https://github.com/caronc/apprise/issues/633
+                    n_format = n_format.lower()
+                    url = f"{url}{prefix}format={n_format}"
+                # If n_format == HTML, then apprise email should default to text/html and we should be sending HTML only
 
-                # Returns empty string if nothing found, multi-line string otherwise
-                log_value = logs.getvalue()
-                if log_value and 'WARNING' in log_value or 'ERROR' in log_value:
-                    raise Exception(log_value)
+            apobj.add(url)
 
-                sent_objs.append({'title': n_title,
-                                  'body': n_body,
-                                  'url' : url,
-                                  'body_format': n_format})
+            sent_objs.append({'title': n_title,
+                              'body': n_body,
+                              'url': url,
+                              'body_format': n_format})
+
+        # Blast off the notifications tht are set in .add()
+        apobj.notify(
+            title=n_title,
+            body=n_body,
+            body_format=n_format,
+            # False is not an option for AppRise, must be type None
+            attach=n_object.get('screenshot', None)
+        )
+
+        # Give apprise time to register an error
+        time.sleep(3)
+
+        # Returns empty string if nothing found, multi-line string otherwise
+        log_value = logs.getvalue()
+
+        if log_value and 'WARNING' in log_value or 'ERROR' in log_value:
+            raise Exception(log_value)
 
     # Return what was sent for better logging - after the for loop
     return sent_objs
 
 
 # Notification title + body content parameters get created here.
+# ( Where we prepare the tokens in the notification to be replaced with actual values )
 def create_notification_parameters(n_object, datastore):
     from copy import deepcopy
 
     # in the case we send a test notification from the main settings, there is no UUID.
     uuid = n_object['uuid'] if 'uuid' in n_object else ''
 
-    if uuid != '':
+    if uuid:
         watch_title = datastore.data['watching'][uuid].get('title', '')
         tag_list = []
         tags = datastore.get_all_tags_for_watch(uuid)
@@ -223,7 +271,7 @@ def create_notification_parameters(n_object, datastore):
     tokens.update(
         {
             'base_url': base_url,
-            'current_snapshot': n_object['current_snapshot'] if 'current_snapshot' in n_object else '',
+            'current_snapshot': n_object.get('current_snapshot', ''),
             'diff': n_object.get('diff', ''),  # Null default in the case we use a test
             'diff_added': n_object.get('diff_added', ''),  # Null default in the case we use a test
             'diff_full': n_object.get('diff_full', ''),  # Null default in the case we use a test

changedetectionio/processors/__init__.py

@@ -5,6 +5,7 @@ import re
 from changedetectionio import content_fetcher
 from copy import deepcopy
 from distutils.util import strtobool
+from loguru import logger
 
 class difference_detection_processor():
 
@@ -43,15 +44,20 @@ class difference_detection_processor():
 
         # In the case that the preferred fetcher was a browser config with custom connection URL..
         # @todo - on save watch, if its extra_browser_ then it should be obvious it will use playwright (like if its requests now..)
-        browser_connection_url = None
+        custom_browser_connection_url = None
         if prefer_fetch_backend.startswith('extra_browser_'):
             (t, key) = prefer_fetch_backend.split('extra_browser_')
             connection = list(
                 filter(lambda s: (s['browser_name'] == key), self.datastore.data['settings']['requests'].get('extra_browsers', [])))
             if connection:
                 prefer_fetch_backend = 'base_html_playwright'
-                browser_connection_url = connection[0].get('browser_connection_url')
+                custom_browser_connection_url = connection[0].get('browser_connection_url')
 
+        # PDF should be html_requests because playwright will serve it up (so far) in a embedded page
+        # @todo https://github.com/dgtlmoon/changedetection.io/issues/2019
+        # @todo needs test to or a fix
+        if self.watch.is_pdf:
+           prefer_fetch_backend = "html_requests"
 
         # Grab the right kind of 'fetcher', (playwright, requests, etc)
         if hasattr(content_fetcher, prefer_fetch_backend):
@@ -64,12 +70,12 @@ class difference_detection_processor():
         proxy_url = None
         if preferred_proxy_id:
             proxy_url = self.datastore.proxy_list.get(preferred_proxy_id).get('url')
-            print(f"Using proxy Key: {preferred_proxy_id} as Proxy URL {proxy_url}")
+            logger.debug(f"Selected proxy key '{preferred_proxy_id}' as proxy URL '{proxy_url}' for {url}")
 
         # Now call the fetcher (playwright/requests/etc) with arguments that only a fetcher would need.
         # When browser_connection_url is None, it method should default to working out whats the best defaults (os env vars etc)
         self.fetcher = fetcher_obj(proxy_override=proxy_url,
-                                   browser_connection_url=browser_connection_url
+                                   custom_browser_connection_url=custom_browser_connection_url
                                    )
 
         if self.watch.has_browser_steps:

changedetectionio/processors/restock_diff.py

@@ -1,8 +1,9 @@
 
-import hashlib
-import urllib3
 from . import difference_detection_processor
 from copy import deepcopy
+from loguru import logger
+import hashlib
+import urllib3
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
@@ -43,11 +44,13 @@ class perform_site_check(difference_detection_processor):
             fetched_md5 = hashlib.md5(self.fetcher.instock_data.encode('utf-8')).hexdigest()
             # 'Possibly in stock' comes from stock-not-in-stock.js when no string found above the fold.
             update_obj["in_stock"] = True if self.fetcher.instock_data == 'Possibly in stock' else False
+            logger.debug(f"Watch UUID {uuid} restock check returned '{self.fetcher.instock_data}' from JS scraper.")
         else:
             raise UnableToExtractRestockData(status_code=self.fetcher.status_code)
 
         # The main thing that all this at the moment comes down to :)
         changed_detected = False
+        logger.debug(f"Watch UUID {uuid} restock check - Previous MD5: {watch.get('previous_md5')}, Fetched MD5 {fetched_md5}")
 
         if watch.get('previous_md5') and watch.get('previous_md5') != fetched_md5:
             # Yes if we only care about it going to instock, AND we are in stock
@@ -60,5 +63,4 @@ class perform_site_check(difference_detection_processor):
 
         # Always record the new checksum
         update_obj["previous_md5"] = fetched_md5
-
-        return changed_detected, update_obj, self.fetcher.instock_data.encode('utf-8')
+        return changed_detected, update_obj, self.fetcher.instock_data.encode('utf-8').strip()

changedetectionio/processors/text_json_diff.py

@@ -2,16 +2,16 @@
 
 import hashlib
 import json
-import logging
 import os
 import re
 import urllib3
 
+from . import difference_detection_processor
+from ..html_tools import PERL_STYLE_REGEX, cdata_in_document_to_text
 from changedetectionio import content_fetcher, html_tools
 from changedetectionio.blueprint.price_data_follower import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
 from copy import deepcopy
-from . import difference_detection_processor
-from ..html_tools import PERL_STYLE_REGEX, cdata_in_document_to_text
+from loguru import logger
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
@@ -335,15 +335,17 @@ class perform_site_check(difference_detection_processor):
                 if not watch['title'] or not len(watch['title']):
                     update_obj['title'] = html_tools.extract_element(find='title', html_content=self.fetcher.content)
 
+        logger.debug(f"Watch UUID {uuid} content check - Previous MD5: {watch.get('previous_md5')}, Fetched MD5 {fetched_md5}")
+
         if changed_detected:
             if watch.get('check_unique_lines', False):
                 has_unique_lines = watch.lines_contain_something_unique_compared_to_history(lines=stripped_text_from_html.splitlines())
                 # One or more lines? unsure?
                 if not has_unique_lines:
-                    logging.debug("check_unique_lines: UUID {} didnt have anything new setting change_detected=False".format(uuid))
+                    logger.debug(f"check_unique_lines: UUID {uuid} didnt have anything new setting change_detected=False")
                     changed_detected = False
                 else:
-                    logging.debug("check_unique_lines: UUID {} had unique content".format(uuid))
+                    logger.debug(f"check_unique_lines: UUID {uuid} had unique content")
 
         # Always record the new checksum
         update_obj["previous_md5"] = fetched_md5

changedetectionio/res/stock-not-in-stock.js

@@ -1,108 +1,132 @@
+// Restock Detector
+// (c) Leigh Morresi dgtlmoon@gmail.com
+//
+// Assumes the product is in stock to begin with, unless the following appears above the fold ;
+// - outOfStockTexts appears above the fold (out of stock)
+// - negateOutOfStockRegex (really is in stock)
+
 function isItemInStock() {
-  // @todo Pass these in so the same list can be used in non-JS fetchers
-  const outOfStockTexts = [
-    '0 in stock',
-    'agotado',
-    'artikel zurzeit vergriffen',
-    'as soon as stock is available',
-    'ausverkauft', // sold out
-    'available for back order',
-    'back-order or out of stock',
-    'backordered',
-    'benachrichtigt mich', // notify me
-    'brak na stanie',
-    'brak w magazynie',
-    'coming soon',
-    'currently have any tickets for this',
-    'currently unavailable',
-    'dostępne wkrótce',
-    'en rupture de stock',
-    'ist derzeit nicht auf lager',
-    'item is no longer available',
-    'message if back in stock',
-    'nachricht bei',
-    'nicht auf lager',
-    'nicht lieferbar',
-    'nicht zur verfügung',
-    'no disponible temporalmente',
-    'no longer in stock',
-    'no tickets available',
-    'not available',
-    'not currently available',
-    'not in stock',
-    'notify me when available',
-    'não estamos a aceitar encomendas',
-    'out of stock',
-    'out-of-stock',
-    'produkt niedostępny',
-    'sold out',
-    'temporarily out of stock',
-    'temporarily unavailable',
-    'tickets unavailable',
-    'unavailable tickets',
-    'we do not currently have an estimate of when this product will be back in stock.',
-    'zur zeit nicht an lager',
-    '已售完',
-  ];
+    // @todo Pass these in so the same list can be used in non-JS fetchers
+    const outOfStockTexts = [
+        ' أخبرني عندما يتوفر',
+        '0 in stock',
+        'agotado',
+        'article épuisé',
+        'artikel zurzeit vergriffen',
+        'as soon as stock is available',
+        'ausverkauft', // sold out
+        'available for back order',
+        'back-order or out of stock',
+        'backordered',
+        'benachrichtigt mich', // notify me
+        'brak na stanie',
+        'brak w magazynie',
+        'coming soon',
+        'currently have any tickets for this',
+        'currently unavailable',
+        'dostępne wkrótce',
+        'en rupture de stock',
+        'ist derzeit nicht auf lager',
+        'item is no longer available',
+        'let me know when it\'s available',
+        'message if back in stock',
+        'nachricht bei',
+        'nicht auf lager',
+        'nicht lieferbar',
+        'nicht zur verfügung',
+        'niet beschikbaar',
+        'niet leverbaar',
+        'no disponible temporalmente',
+        'no longer in stock',
+        'no tickets available',
+        'not available',
+        'not currently available',
+        'not in stock',        
+        'notify me when available',
+        'notify when available',            
+        'não estamos a aceitar encomendas',
+        'out of stock',
+        'out-of-stock',
+        'produkt niedostępny',
+        'sold out',
+        'sold-out',
+        'temporarily out of stock',
+        'temporarily unavailable',
+        'tickets unavailable',
+        'tijdelijk uitverkocht',
+        'unavailable tickets',
+        'we do not currently have an estimate of when this product will be back in stock.',
+        'we don\'t know when or if this item will be back in stock.',
+        'zur zeit nicht an lager',
+        '品切れ',
+        '已售完',
+        '품절'
+    ];
 
-
-  const negateOutOfStockRegexs = [
-      '[0-9] in stock'
-  ]
-  var negateOutOfStockRegexs_r = [];
-  for (let i = 0; i < negateOutOfStockRegexs.length; i++) {
-    negateOutOfStockRegexs_r.push(new RegExp(negateOutOfStockRegexs[0], 'g'));
-  }
-
-
-  const elementsWithZeroChildren = Array.from(document.getElementsByTagName('*')).filter(element => element.children.length === 0);
-
-  // REGEXS THAT REALLY MEAN IT'S IN STOCK
-  for (let i = elementsWithZeroChildren.length - 1; i >= 0; i--) {
-    const element = elementsWithZeroChildren[i];
-    if (element.offsetWidth > 0 || element.offsetHeight > 0 || element.getClientRects().length > 0) {
-      var elementText="";
-      if (element.tagName.toLowerCase() === "input") {
-        elementText = element.value.toLowerCase();
-      } else {
-        elementText = element.textContent.toLowerCase();
-      }
-
-      if (elementText.length) {
-        // try which ones could mean its in stock
-        for (let i = 0; i < negateOutOfStockRegexs.length; i++) {
-          if (negateOutOfStockRegexs_r[i].test(elementText)) {
-            return 'Possibly in stock';
-          }
-        }
-      }
+    const vh = Math.max(document.documentElement.clientHeight || 0, window.innerHeight || 0);
+    function getElementBaseText(element) {
+        // .textContent can include text from children which may give the wrong results
+        // scan only immediate TEXT_NODEs, which will be a child of the element
+        var text = "";
+        for (var i = 0; i < element.childNodes.length; ++i)
+            if (element.childNodes[i].nodeType === Node.TEXT_NODE)
+                text += element.childNodes[i].textContent;
+        return text.toLowerCase().trim();
     }
-  }
 
-  // OTHER STUFF THAT COULD BE THAT IT'S OUT OF STOCK
-  for (let i = elementsWithZeroChildren.length - 1; i >= 0; i--) {
-    const element = elementsWithZeroChildren[i];
-    if (element.offsetWidth > 0 || element.offsetHeight > 0 || element.getClientRects().length > 0) {
-      var elementText="";
-      if (element.tagName.toLowerCase() === "input") {
-        elementText = element.value.toLowerCase();
-      } else {
-        elementText = element.textContent.toLowerCase();
-      }
+    const negateOutOfStockRegex = new RegExp('([0-9] in stock|add to cart)', 'ig');
 
-      if (elementText.length) {
-        // and these mean its out of stock
-        for (const outOfStockText of outOfStockTexts) {
-          if (elementText.includes(outOfStockText)) {
-            return elementText; // item is out of stock
-          }
+    // The out-of-stock or in-stock-text is generally always above-the-fold
+    // and often below-the-fold is a list of related products that may or may not contain trigger text
+    // so it's good to filter to just the 'above the fold' elements
+    // and it should be atleast 100px from the top to ignore items in the toolbar, sometimes menu items like "Coming soon" exist
+    const elementsToScan = Array.from(document.getElementsByTagName('*')).filter(element => element.getBoundingClientRect().top + window.scrollY <= vh && element.getBoundingClientRect().top + window.scrollY >= 100);
+
+    var elementText = "";
+
+    // REGEXS THAT REALLY MEAN IT'S IN STOCK
+    for (let i = elementsToScan.length - 1; i >= 0; i--) {
+        const element = elementsToScan[i];
+        elementText = "";
+        if (element.tagName.toLowerCase() === "input") {
+            elementText = element.value.toLowerCase();
+        } else {
+            elementText = getElementBaseText(element);
         }
-      }
-    }
-  }
 
-  return 'Possibly in stock'; // possibly in stock, cant decide otherwise.
+        if (elementText.length) {
+            // try which ones could mean its in stock
+            if (negateOutOfStockRegex.test(elementText)) {
+                return 'Possibly in stock';
+            }
+        }
+    }
+
+    // OTHER STUFF THAT COULD BE THAT IT'S OUT OF STOCK
+    for (let i = elementsToScan.length - 1; i >= 0; i--) {
+        const element = elementsToScan[i];
+        if (element.offsetWidth > 0 || element.offsetHeight > 0 || element.getClientRects().length > 0) {
+            elementText = "";
+            if (element.tagName.toLowerCase() === "input") {
+                elementText = element.value.toLowerCase();
+            } else {
+                elementText = getElementBaseText(element);
+            }
+
+            if (elementText.length) {
+                // and these mean its out of stock
+                for (const outOfStockText of outOfStockTexts) {
+                    if (elementText.includes(outOfStockText)) {
+                        return outOfStockText; // item is out of stock
+                    }
+                }
+            }
+        }
+    }
+
+    return 'Possibly in stock'; // possibly in stock, cant decide otherwise.
 }
 
 // returns the element text that makes it think it's out of stock
-return isItemInStock();
+return isItemInStock().trim()
+

changedetectionio/static/images/bell-off.svg

@@ -1,4 +1,4 @@
 <?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<svg width="15" height="16.363636" viewBox="0 0 15 16.363636" xmlns="http://www.w3.org/2000/svg" xmlns:svg="http://www.w3.org/2000/svg">
+<svg width="15" height="16.363636" viewBox="0 0 15 16.363636" xmlns="http://www.w3.org/2000/svg" >
   <path d="m 14.318182,11.762045 v 1.1925 H 5.4102273 L 11.849318,7.1140909 C 12.234545,9.1561364 12.54,11.181818 14.318182,11.762045 Z m -6.7984093,4.601591 c 1.0759091,0 2.0256823,-0.955909 2.0256823,-2.045454 H 5.4545455 c 0,1.089545 0.9879545,2.045454 2.0652272,2.045454 z M 15,2.8622727 0.9177273,15.636136 0,14.627045 l 1.8443182,-1.6725 h -1.1625 v -1.1925 C 4.0070455,10.677273 2.1784091,4.5388636 5.3611364,2.6897727 5.8009091,2.4347727 6.0709091,1.9609091 6.0702273,1.4488636 v -0.00205 C 6.0702273,0.64772727 6.7104545,0 7.5,0 8.2895455,0 8.9297727,0.64772727 8.9297727,1.4468182 v 0.00205 C 8.9290909,1.9602319 9.199773,2.4354591 9.638864,2.6897773 10.364318,3.111141 10.827273,3.7568228 11.1525,4.5129591 L 14.085682,1.8531818 Z M 6.8181818,1.3636364 C 6.8181818,1.74 7.1236364,2.0454545 7.5,2.0454545 7.8763636,2.0454545 8.1818182,1.74 8.1818182,1.3636364 8.1818182,0.98795455 7.8763636,0.68181818 7.5,0.68181818 c -0.3763636,0 -0.6818182,0.30613637 -0.6818182,0.68181822 z" id="path2" style="fill:#f8321b;stroke-width:0.681818;fill-opacity:1"/>
 </svg>

changedetectionio/static/images/brightdata.svg

@@ -10,7 +10,7 @@
    xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
    xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
    xmlns="http://www.w3.org/2000/svg"
-   xmlns:svg="http://www.w3.org/2000/svg">
+   >
   <defs
      id="defs16" />
   <sodipodi:namedview

changedetectionio/static/images/copy.svg

@@ -12,7 +12,7 @@
    xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
    xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
    xmlns="http://www.w3.org/2000/svg"
-   xmlns:svg="http://www.w3.org/2000/svg"><defs
+   ><defs
      id="defs11" /><sodipodi:namedview
      id="namedview9"
      pagecolor="#ffffff"

changedetectionio/static/images/email.svg

@@ -10,7 +10,7 @@
    viewBox="0 0 7.1975545 4.7993639"
    xml:space="preserve"
    xmlns="http://www.w3.org/2000/svg"
-   xmlns:svg="http://www.w3.org/2000/svg"><defs
+   ><defs
    id="defs19" />
 <g
    id="g14"

changedetectionio/static/images/notice.svg

@@ -9,7 +9,7 @@
    id="svg5"
    xmlns:xlink="http://www.w3.org/1999/xlink"
    xmlns="http://www.w3.org/2000/svg"
-   xmlns:svg="http://www.w3.org/2000/svg">
+   >
   <defs
      id="defs2" />
   <g

changedetectionio/static/images/oxylabs.svg

@@ -10,7 +10,7 @@
    xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
    xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
    xmlns="http://www.w3.org/2000/svg"
-   xmlns:svg="http://www.w3.org/2000/svg">
+   >
   <defs
      id="defs12" />
   <sodipodi:namedview

changedetectionio/static/images/pause.svg

@@ -3,7 +3,6 @@
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:cc="http://creativecommons.org/ns#"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
-   xmlns:svg="http://www.w3.org/2000/svg"
    xmlns="http://www.w3.org/2000/svg"
    version="1.1"
    id="Capa_1"

changedetectionio/static/images/play.svg

@@ -13,7 +13,6 @@
    xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
    xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
    xmlns="http://www.w3.org/2000/svg"
-   xmlns:svg="http://www.w3.org/2000/svg"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:cc="http://creativecommons.org/ns#"
    xmlns:dc="http://purl.org/dc/elements/1.1/"><sodipodi:namedview

changedetectionio/static/images/spread-white.svg

@@ -6,7 +6,7 @@
    version="1.1"
    id="svg6"
    xmlns="http://www.w3.org/2000/svg"
-   xmlns:svg="http://www.w3.org/2000/svg">
+   >
   <defs
      id="defs10" />
   <path

changedetectionio/static/images/spread.svg

@@ -1,5 +1,5 @@
 <?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<svg width="18" height="19.92" viewBox="0 0 18 19.92" xmlns="http://www.w3.org/2000/svg" xmlns:svg="http://www.w3.org/2000/svg">
+<svg width="18" height="19.92" viewBox="0 0 18 19.92" xmlns="http://www.w3.org/2000/svg" >
   <path d="M -3,-2 H 21 V 22 H -3 Z" fill="none" id="path2"/>
   <path d="m 15,14.08 c -0.76,0 -1.44,0.3 -1.96,0.77 L 5.91,10.7 C 5.96,10.47 6,10.24 6,10 6,9.76 5.96,9.53 5.91,9.3 L 12.96,5.19 C 13.5,5.69 14.21,6 15,6 16.66,6 18,4.66 18,3 18,1.34 16.66,0 15,0 c -1.66,0 -3,1.34 -3,3 0,0.24 0.04,0.47 0.09,0.7 L 5.04,7.81 C 4.5,7.31 3.79,7 3,7 1.34,7 0,8.34 0,10 c 0,1.66 1.34,3 3,3 0.79,0 1.5,-0.31 2.04,-0.81 l 7.12,4.16 c -0.05,0.21 -0.08,0.43 -0.08,0.65 0,1.61 1.31,2.92 2.92,2.92 1.61,0 2.92,-1.31 2.92,-2.92 0,-1.61 -1.31,-2.92 -2.92,-2.92 z" id="path4" style="fill:#0078e7;fill-opacity:1"/>
 </svg>

changedetectionio/static/images/steps.svg

@@ -0,0 +1,44 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   aria-hidden="true"
+   viewBox="0 0 19.966091 17.999964"
+   class="css-1oqmxjn"
+   version="1.1"
+   id="svg4"
+   sodipodi:docname="steps.svg"
+   width="19.966091"
+   height="17.999964"
+   inkscape:version="1.1.2 (0a00cf5339, 2022-02-04)"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg">
+  <defs
+     id="defs8" />
+  <sodipodi:namedview
+     id="namedview6"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageshadow="2"
+     inkscape:pageopacity="0.0"
+     inkscape:pagecheckerboard="0"
+     showgrid="false"
+     fit-margin-top="0"
+     fit-margin-left="0"
+     fit-margin-right="0"
+     fit-margin-bottom="0"
+     inkscape:zoom="8.6354167"
+     inkscape:cx="-1.3896261"
+     inkscape:cy="6.1375151"
+     inkscape:window-width="1280"
+     inkscape:window-height="667"
+     inkscape:window-x="2419"
+     inkscape:window-y="250"
+     inkscape:window-maximized="0"
+     inkscape:current-layer="svg4" />
+  <path
+     d="m 16.95807,12.000003 c -0.7076,0.0019 -1.3917,0.2538 -1.9316,0.7113 -0.5398,0.4575 -0.9005,1.091 -1.0184,1.7887 H 5.60804 c -0.80847,0.0297 -1.60693,-0.1865 -2.29,-0.62 -0.26632,-0.1847 -0.48375,-0.4315 -0.63356,-0.7189 -0.14982,-0.2874 -0.22753,-0.607 -0.22644,-0.9311 -0.02843,-0.3931 0.03646,-0.7873 0.1894,-1.1505 0.15293,-0.3632 0.38957,-0.6851 0.6906,-0.9395 0.66628,-0.4559004 1.4637,-0.6807004 2.27,-0.6400004 h 8.35003 c 0.8515,-0.0223 1.6727,-0.3206 2.34,-0.85 0.3971,-0.3622 0.7076,-0.8091 0.9084,-1.3077 0.2008,-0.49857 0.2868,-1.03596 0.2516,-1.57229 0.0113,-0.47161 -0.0887,-0.93924 -0.292,-1.36493 -0.2033,-0.4257 -0.5041,-0.79745 -0.878,-1.08507 -0.7801,-0.55815 -1.7212,-0.84609 -2.68,-0.82 H 5.95804 c -0.12537,-0.7417 -0.5248,-1.40924 -1.11913,-1.87032996 -0.59434,-0.46108 -1.3402,-0.68207 -2.08979,-0.61917 -0.74958,0.06291 -1.44818,0.40512 -1.95736,0.95881 C 0.28259,1.5230126 0,2.2477926 0,3.0000126 c 0,0.75222 0.28259,1.47699 0.79176,2.03068 0.50918,0.55369 1.20778,0.8959 1.95736,0.95881 0.74959,0.0629 1.49545,-0.15808 2.08979,-0.61917 0.59433,-0.46109 0.99376,-1.12863 1.11913,-1.87032 h 7.70003 c 0.7353,-0.03061 1.4599,0.18397 2.06,0.61 0.2548,0.19335 0.4595,0.445 0.597,0.73385 0.1375,0.28884 0.2036,0.60644 0.193,0.92615 0.0316,0.38842 -0.0247,0.77898 -0.165,1.14258 -0.1402,0.36361 -0.3607,0.69091 -0.645,0.95741 -0.5713,0.4398 -1.2799,0.663 -2,0.63 H 5.69804 c -1.03259,-0.0462 -2.05065,0.2568 -2.89,0.86 -0.43755,0.3361 -0.78838,0.7720004 -1.02322,1.2712004 -0.23484,0.4993 -0.34688,1.0474 -0.32678,1.5988 -0.00726,0.484 0.10591,0.9622 0.32934,1.3916 0.22344,0.4295 0.55012,0.7966 0.95066,1.0684 0.85039,0.5592 1.85274,0.8421 2.87,0.81 h 8.40003 c 0.0954,0.5643 0.3502,1.0896 0.7343,1.5138 0.3842,0.4242 0.8817,0.7297 1.4338,0.8803 0.5521,0.1507 1.1358,0.1403 1.6822,-0.0299 0.5464,-0.1702 1.0328,-0.4932 1.4016,-0.9308 0.3688,-0.4376 0.6048,-0.9716 0.6801,-1.5389 0.0752,-0.5673 -0.0134,-1.1444 -0.2554,-1.663 -0.242,-0.5186 -0.6273,-0.9572 -1.1104,-1.264 -0.4831,-0.3068 -1.0439,-0.469 -1.6162,-0.4675 z m 0,5 c -0.3956,0 -0.7823,-0.1173 -1.1112,-0.3371 -0.3289,-0.2197 -0.5852,-0.5321 -0.7366,-0.8975 -0.1514,-0.3655 -0.191,-0.7676 -0.1138,-1.1556 0.0772,-0.3879 0.2677,-0.7443 0.5474,-1.024 0.2797,-0.2797 0.636,-0.4702 1.024,-0.5474 0.388,-0.0771 0.7901,-0.0375 1.1555,0.1138 0.3655,0.1514 0.6778,0.4078 0.8976,0.7367 0.2198,0.3289 0.3371,0.7155 0.3371,1.1111 0,0.5304 -0.2107,1.0391 -0.5858,1.4142 -0.3751,0.3751 -0.8838,0.5858 -1.4142,0.5858 z"
+     id="path2"
+     style="fill:#777777;fill-opacity:1" />
+</svg>

changedetectionio/static/js/global-settings.js

@@ -1,19 +1,4 @@
 $(document).ready(function () {
-    function toggle() {
-        if ($('input[name="application-fetch_backend"]:checked').val() != 'html_requests') {
-            $('#requests-override-options').hide();
-            $('#webdriver-override-options').show();
-        } else {
-            $('#requests-override-options').show();
-            $('#webdriver-override-options').hide();
-        }
-    }
-
-    $('input[name="application-fetch_backend"]').click(function (e) {
-        toggle();
-    });
-    toggle();
-
     $("#api-key").hover(
         function () {
             $("#api-key-copy").html('copy').fadeIn();

changedetectionio/static/js/notifications.js

@@ -24,14 +24,17 @@ $(document).ready(function() {
     })
 
     data = {
-        window_url : window.location.href,
-        notification_urls : $('.notification-urls').val(),
+      notification_body: $('#notification_body').val(),
+      notification_format: $('#notification_format').val(),
+      notification_title: $('#notification_title').val(),
+      notification_urls: $('.notification-urls').val(),
+      window_url: window.location.href,
     }
-    for (key in data) {
-      if (!data[key].length) {
-        alert(key+" is empty, cannot send test.")
-        return;
-      }
+
+
+    if (!data['notification_urls'].length) {
+      alert("Notification URL list is empty, cannot send test.")
+      return;
     }
 
     $.ajax({

changedetectionio/static/js/vis.js

@@ -0,0 +1,29 @@
+$(document).ready(function () {
+
+    // Lazy Hide/Show elements mechanism
+    $('[data-visible-for]').hide();
+    function show_related_elem(e) {
+        var n = $(e).attr('name') + "=" + $(e).val();
+        if (n === 'fetch_backend=system') {
+            n = "fetch_backend=" + default_system_fetch_backend;
+        }
+        $(`[data-visible-for~="${n}"]`).show();
+    }
+    $(':radio').on('keyup keypress blur change click', function (e) {
+        $(`[data-visible-for]`).hide();
+        $('.advanced-options').hide();
+        show_related_elem(this);
+    });
+
+    $(':radio:checked').each(function (e) {
+       show_related_elem(this);
+    })
+
+
+    // Show advanced
+    $('.show-advanced').click(function (e) {
+        $(this).closest('.tab-pane-inner').find('.advanced-options').each(function (e) {
+            $(this).toggle();
+        })
+    });
+});

changedetectionio/static/js/watch-settings.js

@@ -1,40 +1,4 @@
 $(document).ready(function () {
-    function toggle() {
-        if ($('input[name="fetch_backend"]:checked').val() == 'html_webdriver') {
-            if (playwright_enabled) {
-                // playwright supports headers, so hide everything else
-                // See #664
-                $('#requests-override-options #request-method').hide();
-                $('#requests-override-options #request-body').hide();
-
-                // @todo connect this one up
-                $('#ignore-status-codes-option').hide();
-            } else {
-                // selenium/webdriver doesnt support anything afaik, hide it all
-                $('#requests-override-options').hide();
-            }
-
-            $('#webdriver-override-options').show();
-
-        } else if ($('input[name="fetch_backend"]:checked').val() == 'system') {
-            $('#requests-override-options #request-method').hide();
-            $('#requests-override-options #request-body').hide();
-            $('#ignore-status-codes-option').hide();
-            $('#requests-override-options').hide();
-            $('#webdriver-override-options').hide();
-        } else {
-
-            $('#requests-override-options').show();
-            $('#requests-override-options *:hidden').show();
-            $('#webdriver-override-options').hide();
-        }
-    }
-
-    $('input[name="fetch_backend"]').click(function (e) {
-        toggle();
-    });
-    toggle();
-
     $('#notification-setting-reset-to-default').click(function (e) {
         $('#notification_title').val('');
         $('#notification_body').val('');

changedetectionio/static/styles/diff.css

@@ -126,6 +126,8 @@ html[data-darkmode="true"] {
   html[data-darkmode="true"] .watch-table .title-col a[target="_blank"]::after,
   html[data-darkmode="true"] .watch-table .current-diff-url::after {
     filter: invert(0.5) hue-rotate(10deg) brightness(2); }
+  html[data-darkmode="true"] .watch-table .status-browsersteps {
+    filter: invert(0.5) hue-rotate(10deg) brightness(1.5); }
   html[data-darkmode="true"] .watch-table .watch-controls .state-off img {
     opacity: 0.3; }
   html[data-darkmode="true"] .watch-table .watch-controls .state-on img {

changedetectionio/static/styles/scss/parts/_variables.scss

@@ -152,6 +152,10 @@ html[data-darkmode="true"] {
       filter: invert(.5) hue-rotate(10deg) brightness(2);
     }
 
+    .status-browsersteps {
+      filter: invert(.5) hue-rotate(10deg) brightness(1.5);
+    }
+
     .watch-controls {
       .state-off {
         img {

changedetectionio/static/styles/scss/styles.scss

@@ -402,8 +402,24 @@ label {
   }
 
   #watch-add-wrapper-zone {
-    >div {
-      display: inline-block;
+
+    @media only screen and (min-width: 760px) {
+      display: flex;
+      gap: 0.3rem;
+      flex-direction: row;
+    }
+    /* URL field grows always, other stay static in width */
+    > span {
+      flex-grow: 0;
+
+      input {
+        width: 100%;
+        padding-right: 1em;
+      }
+
+      &:first-child {
+        flex-grow: 1;
+      }
     }
 
     @media only screen and (max-width: 760px) {
@@ -944,10 +960,8 @@ ul {
 
 @import "parts/_visualselector";
 
-#webdriver-override-options {
-  input[type="number"] {
+#webdriver_delay {
     width: 5em;
-  }
 }
 
 #api-key {

changedetectionio/static/styles/styles.css

@@ -342,6 +342,8 @@ html[data-darkmode="true"] {
   html[data-darkmode="true"] .watch-table .title-col a[target="_blank"]::after,
   html[data-darkmode="true"] .watch-table .current-diff-url::after {
     filter: invert(0.5) hue-rotate(10deg) brightness(2); }
+  html[data-darkmode="true"] .watch-table .status-browsersteps {
+    filter: invert(0.5) hue-rotate(10deg) brightness(1.5); }
   html[data-darkmode="true"] .watch-table .watch-controls .state-off img {
     opacity: 0.3; }
   html[data-darkmode="true"] .watch-table .watch-controls .state-on img {
@@ -683,11 +685,23 @@ label:hover {
   #new-watch-form legend {
     color: var(--color-text-legend);
     font-weight: bold; }
-  #new-watch-form #watch-add-wrapper-zone > div {
-    display: inline-block; }
-  @media only screen and (max-width: 760px) {
-    #new-watch-form #watch-add-wrapper-zone #url {
-      width: 100%; } }
+  #new-watch-form #watch-add-wrapper-zone {
+    /* URL field grows always, other stay static in width */ }
+    @media only screen and (min-width: 760px) {
+      #new-watch-form #watch-add-wrapper-zone {
+        display: flex;
+        gap: 0.3rem;
+        flex-direction: row; } }
+    #new-watch-form #watch-add-wrapper-zone > span {
+      flex-grow: 0; }
+      #new-watch-form #watch-add-wrapper-zone > span input {
+        width: 100%;
+        padding-right: 1em; }
+      #new-watch-form #watch-add-wrapper-zone > span:first-child {
+        flex-grow: 1; }
+    @media only screen and (max-width: 760px) {
+      #new-watch-form #watch-add-wrapper-zone #url {
+        width: 100%; } }
 
 #diff-col {
   padding-left: 40px; }
@@ -1065,7 +1079,7 @@ ul {
 #selector-current-xpath {
   font-size: 80%; }
 
-#webdriver-override-options input[type="number"] {
+#webdriver_delay {
   width: 5em; }
 
 #api-key:hover {

changedetectionio/store.py

@@ -9,7 +9,6 @@ from copy import deepcopy, copy
 from os import path, unlink
 from threading import Lock
 import json
-import logging
 import os
 import re
 import requests
@@ -17,6 +16,7 @@ import secrets
 import threading
 import time
 import uuid as uuid_builder
+from loguru import logger
 
 # Because the server will run as a daemon and wont know the URL for notification links when firing off a notification
 BASE_URL_NOT_SET_TEXT = '("Base URL" not set - see settings - notifications)'
@@ -42,7 +42,7 @@ class ChangeDetectionStore:
         self.__data = App.model()
         self.datastore_path = datastore_path
         self.json_store_path = "{}/url-watches.json".format(self.datastore_path)
-        print(">>> Datastore path is ", self.json_store_path)
+        logger.info(f"Datastore path is '{self.json_store_path}'")
         self.needs_write = False
         self.start_time = time.time()
         self.stop_thread = False
@@ -83,12 +83,12 @@ class ChangeDetectionStore:
                 for uuid, watch in self.__data['watching'].items():
                     watch['uuid']=uuid
                     self.__data['watching'][uuid] = Watch.model(datastore_path=self.datastore_path, default=watch)
-                    print("Watching:", uuid, self.__data['watching'][uuid]['url'])
+                    logger.info(f"Watching: {uuid} {self.__data['watching'][uuid]['url']}")
 
         # First time ran, Create the datastore.
         except (FileNotFoundError):
             if include_default_watches:
-                print("No JSON DB found at {}, creating JSON store at {}".format(self.json_store_path, self.datastore_path))
+                logger.critical(f"No JSON DB found at {self.json_store_path}, creating JSON store at {self.datastore_path}")
                 self.add_watch(url='https://news.ycombinator.com/',
                                tag='Tech news',
                                extras={'fetch_backend': 'html_requests'})
@@ -139,7 +139,7 @@ class ChangeDetectionStore:
         save_data_thread = threading.Thread(target=self.save_datastore).start()
 
     def set_last_viewed(self, uuid, timestamp):
-        logging.debug("Setting watch UUID: {} last viewed to {}".format(uuid, int(timestamp)))
+        logger.debug(f"Setting watch UUID: {uuid} last viewed to {int(timestamp)}")
         self.data['watching'][uuid].update({'last_viewed': int(timestamp)})
         self.needs_write = True
 
@@ -234,7 +234,7 @@ class ChangeDetectionStore:
 
         # Probably their should be dict...
         for watch in self.data['watching'].values():
-            if watch['url'] == url:
+            if watch['url'].lower() == url.lower():
                 return True
 
         return False
@@ -248,6 +248,7 @@ class ChangeDetectionStore:
                 'check_count': 0,
                 'fetch_time' : 0.0,
                 'has_ldjson_price_data': None,
+                'in_stock': None,
                 'last_checked': 0,
                 'last_error': False,
                 'last_notification_error': False,
@@ -315,7 +316,7 @@ class ChangeDetectionStore:
                             apply_extras['include_filters'] = [res['css_filter']]
 
             except Exception as e:
-                logging.error("Error fetching metadata for shared watch link", url, str(e))
+                logger.error(f"Error fetching metadata for shared watch link {url} {str(e)}")
                 flash("Error fetching metadata for {}".format(url), 'error')
                 return False
         from .model.Watch import is_safe_url
@@ -333,7 +334,8 @@ class ChangeDetectionStore:
 
         # Or if UUIDs given directly
         if tag_uuids:
-            apply_extras['tags'] = list(set(apply_extras['tags'] + tag_uuids))
+            for t in tag_uuids:
+                apply_extras['tags'] = list(set(apply_extras['tags'] + [t.strip()]))
 
         # Make any uuids unique
         if apply_extras.get('tags'):
@@ -343,7 +345,7 @@ class ChangeDetectionStore:
 
         new_uuid = new_watch.get('uuid')
 
-        logging.debug("Added URL {} - {}".format(url, new_uuid))
+        logger.debug(f"Adding URL {url} - {new_uuid}")
 
         for k in ['uuid', 'history', 'last_checked', 'last_changed', 'newest_history_key', 'previous_md5', 'viewed']:
             if k in apply_extras:
@@ -360,7 +362,7 @@ class ChangeDetectionStore:
         if write_to_disk_now:
             self.sync_to_json()
 
-        print("added ", url)
+        logger.debug(f"Added '{url}'")
 
         return new_uuid
 
@@ -414,14 +416,13 @@ class ChangeDetectionStore:
 
 
     def sync_to_json(self):
-        logging.info("Saving JSON..")
-        print("Saving JSON..")
+        logger.info("Saving JSON..")
         try:
             data = deepcopy(self.__data)
         except RuntimeError as e:
             # Try again in 15 seconds
             time.sleep(15)
-            logging.error ("! Data changed when writing to JSON, trying again.. %s", str(e))
+            logger.error(f"! Data changed when writing to JSON, trying again.. {str(e)}")
             self.sync_to_json()
             return
         else:
@@ -434,7 +435,7 @@ class ChangeDetectionStore:
                     json.dump(data, json_file, indent=4)
                 os.replace(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))
+                logger.error(f"Error writing JSON!! (Main JSON file save was skipped) : {str(e)}")
 
             self.needs_write = False
             self.needs_write_urgent = False
@@ -445,7 +446,16 @@ class ChangeDetectionStore:
 
         while True:
             if self.stop_thread:
-                print("Shutting down datastore thread")
+                # Suppressing "Logging error in Loguru Handler #0" during CICD.
+                # Not a meaningful difference for a real use-case just for CICD.
+                # the side effect is a "Shutting down datastore thread" message
+                # at the end of each test.
+                # But still more looking better.
+                import sys
+                logger.remove()
+                logger.add(sys.stderr)
+
+                logger.critical("Shutting down datastore thread")
                 return
 
             if self.needs_write or self.needs_write_urgent:
@@ -461,7 +471,7 @@ class ChangeDetectionStore:
     # Go through the datastore path and remove any snapshots that are not mentioned in the index
     # This usually is not used, but can be handy.
     def remove_unused_snapshots(self):
-        print ("Removing snapshots from datastore that are not in the index..")
+        logger.info("Removing snapshots from datastore that are not in the index..")
 
         index=[]
         for uuid in self.data['watching']:
@@ -474,7 +484,7 @@ class ChangeDetectionStore:
         for uuid in self.data['watching']:
             for item in pathlib.Path(self.datastore_path).rglob(uuid+"/*.txt"):
                 if not str(item) in index:
-                    print ("Removing",item)
+                    logger.info(f"Removing {item}")
                     unlink(item)
 
     @property
@@ -560,7 +570,7 @@ class ChangeDetectionStore:
             if os.path.isfile(filepath):
                 headers.update(parse_headers_from_text_file(filepath))
         except Exception as e:
-            print(f"ERROR reading headers.txt at {filepath}", str(e))
+            logger.error(f"ERROR reading headers.txt at {filepath} {str(e)}")
 
         watch = self.data['watching'].get(uuid)
         if watch:
@@ -571,7 +581,7 @@ class ChangeDetectionStore:
                 if os.path.isfile(filepath):
                     headers.update(parse_headers_from_text_file(filepath))
             except Exception as e:
-                print(f"ERROR reading headers.txt at {filepath}", str(e))
+                logger.error(f"ERROR reading headers.txt at {filepath} {str(e)}")
 
             # In /datastore/tag-name.txt
             tags = self.get_all_tags_for_watch(uuid=uuid)
@@ -582,7 +592,7 @@ class ChangeDetectionStore:
                     if os.path.isfile(filepath):
                         headers.update(parse_headers_from_text_file(filepath))
                 except Exception as e:
-                    print(f"ERROR reading headers.txt at {filepath}", str(e))
+                    logger.error(f"ERROR reading headers.txt at {filepath} {str(e)}")
 
         return headers
 
@@ -600,13 +610,13 @@ class ChangeDetectionStore:
     def add_tag(self, name):
         # If name exists, return that
         n = name.strip().lower()
-        print (f">>> Adding new tag - '{n}'")
+        logger.debug(f">>> Adding new tag - '{n}'")
         if not n:
             return False
 
         for uuid, tag in self.__data['settings']['application'].get('tags', {}).items():
             if n == tag.get('title', '').lower().strip():
-                print (f">>> Tag {name} already exists")
+                logger.warning(f"Tag '{name}' already exists, skipping creation.")
                 return uuid
 
         # Eventually almost everything todo with a watch will apply as a Tag
@@ -668,7 +678,7 @@ class ChangeDetectionStore:
         updates_available = self.get_updates_available()
         for update_n in updates_available:
             if update_n > self.__data['settings']['application']['schema_version']:
-                print ("Applying update_{}".format((update_n)))
+                logger.critical(f"Applying update_{update_n}")
                 # Wont exist on fresh installs
                 if os.path.exists(self.json_store_path):
                     shutil.copyfile(self.json_store_path, self.datastore_path+"/url-watches-before-{}.json".format(update_n))
@@ -676,8 +686,8 @@ class ChangeDetectionStore:
                 try:
                     update_method = getattr(self, "update_{}".format(update_n))()
                 except Exception as e:
-                    print("Error while trying update_{}".format((update_n)))
-                    print(e)
+                    logger.error(f"Error while trying update_{update_n}")
+                    logger.error(e)
                     # Don't run any more updates
                     return
                 else:
@@ -715,7 +725,7 @@ class ChangeDetectionStore:
                         with open(os.path.join(target_path, "history.txt"), "w") as f:
                             f.writelines(history)
                     else:
-                        logging.warning("Datastore history directory {} does not exist, skipping history import.".format(target_path))
+                        logger.warning(f"Datastore history directory {target_path} does not exist, skipping history import.")
 
                 # No longer needed, dynamically pulled from the disk when needed.
                 # But we should set it back to a empty dict so we don't break if this schema runs on an earlier version.

changedetectionio/templates/_common_fields.jinja

@@ -13,10 +13,10 @@
                             <div class="pure-form-message-inline">
                               <ul>
                                 <li>Use <a target=_new href="https://github.com/caronc/apprise">AppRise URLs</a> for notification to just about any service! <i><a target=_new href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes">Please read the notification services wiki here for important configuration notes</a></i>.</li>
-                                <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_discord">discord://</a></code> (or <code>https://discord.com/api/webhooks...</code>)) </code> only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
+                                <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_discord">discord://</a></code> (or <code>https://discord.com/api/webhooks...</code>)) only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
                                 <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> bots can't send messages to other bots, so you should specify chat ID of non-bot user.</li>
                                 <li><code><a target=_new href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> only supports very limited HTML and can fail when extra tags are sent, <a href="https://core.telegram.org/bots/api#html-style">read more here</a> (or use plaintext/markdown format)</li>
-                                <li><code>gets://</code>, <code>posts://</code>, <code>puts://</code>, <code>deletes://</code> for direct API calls (or omit the "<code>s</code>" for non-SSL ie <code>get://</code>)</li>
+                                <li><code>gets://</code>, <code>posts://</code>, <code>puts://</code>, <code>deletes://</code> for direct API calls (or omit the "<code>s</code>" for non-SSL ie <code>get://</code>) <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes#postposts">more help here</a></li>
                                   <li>Accepts the <code>{{ '{{token}}' }}</code> placeholders listed below</li>
                               </ul>
                             </div>
@@ -115,6 +115,12 @@
 									Warning: Contents of <code>{{ '{{diff}}' }}</code>, <code>{{ '{{diff_removed}}' }}</code>, and <code>{{ '{{diff_added}}' }}</code> depend on how the difference algorithm perceives the change. <br>
                                     For example, an addition or removal could be perceived as a change in some cases. <a target="_new" href="https://github.com/dgtlmoon/changedetection.io/wiki/Using-the-%7B%7Bdiff%7D%7D,-%7B%7Bdiff_added%7D%7D,-and-%7B%7Bdiff_removed%7D%7D-notification-tokens">More Here</a> <br>
                                     </p>
+                                    <p>
+                                        For JSON payloads, use <strong>|tojson</strong> without quotes for automatic escaping, for example - <code>{ "name": {{ '{{ watch_title|tojson }}' }} }</code>
+                                    </p>
+                                    <p>
+                                        URL encoding, use <strong>|urlencode</strong>, for example - <code>gets://hook-website.com/test.php?title={{ '{{ watch_title|urlencode }}' }}</code>
+                                    </p>
                                 </div>
                             </div>
                             <div class="pure-control-group">

changedetectionio/templates/_helpers.jinja

@@ -39,6 +39,24 @@
 {% endmacro %}
 
 
+{% macro render_nolabel_field(field) %}
+    <span>
+    {{ field(**kwargs)|safe }}
+        {% if field.errors %}
+            <span class="error">
+      {% if field.errors %}
+          <ul class=errors>
+        {% for error in field.errors %}
+            <li>{{ error }}</li>
+        {% endfor %}
+        </ul>
+      {% endif %}
+      </span>
+        {% endif %}
+    </span>
+{% endmacro %}
+
+
 {% macro render_button(field) %}
   {{ field(**kwargs)|safe }}
 {% endmacro %}

changedetectionio/templates/base.html

@@ -116,7 +116,7 @@
                    viewBox="0 0 16.9 16.1"
                    id="svg-heart"
                    xmlns="http://www.w3.org/2000/svg"
-                   xmlns:svg="http://www.w3.org/2000/svg">
+                   >
                   <path id="heartpath" d="M 5.338316,0.50302766 C 0.71136983,0.50647126 -3.9576371,7.2707777 8.5004254,15.503028 23.833425,5.3700277 13.220206,-2.5384409 8.6762066,1.6475589 c -0.060791,0.054322 -0.11943,0.1110064 -0.1757812,0.1699219 -0.057,-0.059 -0.1157813,-0.116875 -0.1757812,-0.171875 C 7.4724566,0.86129334 6.4060729,0.50223298 5.338316,0.50302766 Z"
                      style="fill:var(--color-background);fill-opacity:1;stroke:#ff0000;stroke-opacity:1" />
                 </svg>
@@ -170,7 +170,6 @@
                     And tell your friends and colleagues :)
                 </li>
                 </ul>
-                </p>
                 <p>
                     The more popular changedetection.io is, the more time we can dedicate to adding amazing features!
                 </p>

changedetectionio/templates/edit.html

@@ -3,6 +3,7 @@
 {% from '_helpers.jinja' import render_field, render_checkbox_field, render_button %}
 {% from '_common_fields.jinja' import render_common_settings_form %}
 <script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
+<script src="{{url_for('static_content', group='js', filename='vis.js')}}" defer></script>
 <script>
     const browser_steps_available_screenshots=JSON.parse('{{ watch.get_browsersteps_available_screenshots|tojson }}');
     const browser_steps_config=JSON.parse('{{ browser_steps_config|tojson }}');
@@ -13,13 +14,13 @@
 {% if emailprefix %}
     const email_notification_prefix=JSON.parse('{{ emailprefix|tojson }}');
 {% endif %}
-    const notification_base_url="{{url_for('ajax_callback_send_notification_test')}}";
+    const notification_base_url="{{url_for('ajax_callback_send_notification_test', watch_uuid=uuid)}}";
     const playwright_enabled={% if playwright_enabled %} true {% else %} false {% endif %};
     const recheck_proxy_start_url="{{url_for('check_proxies.start_check', uuid=uuid)}}";
     const proxy_recheck_status_url="{{url_for('check_proxies.get_recheck_status', uuid=uuid)}}";
     const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
     const watch_visual_selector_data_url="{{url_for('static_content', group='visual_selector_data', filename=uuid)}}";
-
+    const default_system_fetch_backend="{{ settings_application['fetch_backend'] }}";
 </script>
 
 <script src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
@@ -124,10 +125,9 @@
                         </span>
                     </div>
                 {% endif %}
-                    <div  class="pure-control-group inline-radio">
-                        {{ render_checkbox_field(form.ignore_status_codes) }}
-                    </div>
-                <fieldset id="webdriver-override-options">
+
+                <!-- webdriver always -->
+                <fieldset data-visible-for="fetch_backend=html_webdriver"  style="display: none;">
                     <div class="pure-control-group">
                         {{ render_field(form.webdriver_delay) }}
                         <div class="pure-form-message-inline">
@@ -140,23 +140,40 @@
                         </div>
                     </div>
                     <div class="pure-control-group">
+                        <a class="pure-button button-secondary button-xsmall show-advanced">Show advanced options</a>
+                    </div>
+                    <div class="advanced-options"  style="display: none;">
                         {{ render_field(form.webdriver_js_execute_code) }}
                         <div class="pure-form-message-inline">
-                            Run this code before performing change detection, handy for filling in fields and other actions <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Run-JavaScript-before-change-detection">More help and examples here</a>
+                            Run this code before performing change detection, handy for filling in fields and other
+                            actions <a
+                                href="https://github.com/dgtlmoon/changedetection.io/wiki/Run-JavaScript-before-change-detection">More
+                            help and examples here</a>
                         </div>
                     </div>
                 </fieldset>
-                <fieldset class="pure-group" id="requests-override-options">
-                    {% if not playwright_enabled %}
-                        <div class="pure-form-message-inline">
-                            <strong>Request override is currently only used by the <i>Basic fast Plaintext/HTTP Client</i> method.</strong>
-                        </div>
-                    {% endif %}
-                    <div class="pure-control-group" id="request-method">
-                        {{ render_field(form.method) }}
+                <!-- html requests always -->
+                <fieldset data-visible-for="fetch_backend=html_requests">
+                    <div class="pure-control-group">
+                        <a class="pure-button button-secondary button-xsmall show-advanced">Show advanced options</a>
                     </div>
-                    <div class="pure-control-group" id="request-headers">
-{{ render_field(form.headers, rows=5, placeholder="Example
+                    <div class="advanced-options"  style="display: none;">
+                        <div class="pure-control-group" id="request-method">
+                            {{ render_field(form.method) }}
+                        </div>
+                        <div id="request-body">
+                                            {{ render_field(form.body, rows=5, placeholder="Example
+{
+   \"name\":\"John\",
+   \"age\":30,
+   \"car\":null
+}") }}
+                        </div>
+                    </div>
+                </fieldset>
+            <!-- hmm -->
+                <div class="pure-control-group advanced-options"  style="display: none;">
+                    {{ render_field(form.headers, rows=5, placeholder="Example
 Cookie: foobar
 User-Agent: wonderbra 1.0") }}
 
@@ -169,17 +186,12 @@ User-Agent: wonderbra 1.0") }}
                             <br>
                             (Not supported by Selenium browser)
                         </div>
-
                     </div>
-                    <div class="pure-control-group" id="request-body">
-                                        {{ render_field(form.body, rows=5, placeholder="Example
-{
-   \"name\":\"John\",
-   \"age\":30,
-   \"car\":null
-}") }}
+            <fieldset data-visible-for="fetch_backend=html_requests fetch_backend=html_webdriver" >
+                    <div class="pure-control-group inline-radio advanced-options"  style="display: none;">
+                    {{ render_checkbox_field(form.ignore_status_codes) }}
                     </div>
-                </fieldset>
+            </fieldset>
             </div>
             {% if playwright_enabled %}
             <div class="tab-pane-inner" id="browser-steps">

changedetectionio/templates/settings.html

@@ -4,14 +4,14 @@
 {% from '_helpers.jinja' import render_field, render_checkbox_field, render_button %}
 {% from '_common_fields.jinja' import render_common_settings_form %}
 <script>
-    const notification_base_url="{{url_for('ajax_callback_send_notification_test')}}";
+    const notification_base_url="{{url_for('ajax_callback_send_notification_test', watch_uuid=uuid)}}";
 {% if emailprefix %}
     const email_notification_prefix=JSON.parse('{{emailprefix|tojson}}');
 {% endif %}
 </script>
 <script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
-
+<script src="{{url_for('static_content', group='js', filename='vis.js')}}" defer></script>
 <script src="{{url_for('static_content', group='js', filename='global-settings.js')}}" defer></script>
 <div class="edit-form">
     <div class="tabs collapsable">
@@ -111,7 +111,7 @@
                     <br>
                     Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using Bright Data and Oxylabs Proxies, find out more here.</a>
                 </div>
-                <fieldset class="pure-group" id="webdriver-override-options">
+                <fieldset class="pure-group" id="webdriver-override-options" data-visible-for="application-fetch_backend=html_webdriver">
                     <div class="pure-form-message-inline">
                         <strong>If you're having trouble waiting for the page to be fully rendered (text missing etc), try increasing the 'wait' time here.</strong>
                         <br>
@@ -236,8 +236,11 @@ nav
                 <span class="pure-form-message-inline">SOCKS5 proxies with authentication are only supported with 'plain requests' fetcher, for other fetchers you should whitelist the IP access instead</span>
                 </div>
                 <div class="pure-control-group" id="extra-browsers-setting">
-                    <span class="pure-form-message-inline"><i>Extra Browsers</i> allow changedetection.io to communicate with a different web-browser.</span><br>
-                  {{ render_field(form.requests.form.extra_browsers) }}
+                    <p>
+                    <span class="pure-form-message-inline"><i>Extra Browsers</i> can be attached to further defeat CAPTCHA's on websites that are particularly hard to scrape.</span><br>
+                    <span class="pure-form-message-inline">Simply paste the connection address into the box, <a href="https://changedetection.io/tutorial/using-bright-datas-scraping-browser-pass-captchas-and-other-protection-when-monitoring">More instructions and examples here</a> </span>
+                    </p>
+                    {{ render_field(form.requests.form.extra_browsers) }}
                 </div>
             </div>
             <div id="actions">

changedetectionio/templates/svgs/search-icon.svg

@@ -1 +1 @@
-<?xml version="1.0" encoding="utf-8"?><svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" viewBox="0 0 122.879 119.799" enable-background="new 0 0 122.879 119.799" xml:space="preserve"><g><path d="M49.988,0h0.016v0.007C63.803,0.011,76.298,5.608,85.34,14.652c9.027,9.031,14.619,21.515,14.628,35.303h0.007v0.033v0.04 h-0.007c-0.005,5.557-0.917,10.905-2.594,15.892c-0.281,0.837-0.575,1.641-0.877,2.409v0.007c-1.446,3.66-3.315,7.12-5.547,10.307 l29.082,26.139l0.018,0.016l0.157,0.146l0.011,0.011c1.642,1.563,2.536,3.656,2.649,5.78c0.11,2.1-0.543,4.248-1.979,5.971 l-0.011,0.016l-0.175,0.203l-0.035,0.035l-0.146,0.16l-0.016,0.021c-1.565,1.642-3.654,2.534-5.78,2.646 c-2.097,0.111-4.247-0.54-5.971-1.978l-0.015-0.011l-0.204-0.175l-0.029-0.024L78.761,90.865c-0.88,0.62-1.778,1.209-2.687,1.765 c-1.233,0.755-2.51,1.466-3.813,2.115c-6.699,3.342-14.269,5.222-22.272,5.222v0.007h-0.016v-0.007 c-13.799-0.004-26.296-5.601-35.338-14.645C5.605,76.291,0.016,63.805,0.007,50.021H0v-0.033v-0.016h0.007 c0.004-13.799,5.601-26.296,14.645-35.338C23.683,5.608,36.167,0.016,49.955,0.007V0H49.988L49.988,0z M50.004,11.21v0.007h-0.016 h-0.033V11.21c-10.686,0.007-20.372,4.35-27.384,11.359C15.56,29.578,11.213,39.274,11.21,49.973h0.007v0.016v0.033H11.21 c0.007,10.686,4.347,20.367,11.359,27.381c7.009,7.012,16.705,11.359,27.403,11.361v-0.007h0.016h0.033v0.007 c10.686-0.007,20.368-4.348,27.382-11.359c7.011-7.009,11.358-16.702,11.36-27.4h-0.006v-0.016v-0.033h0.006 c-0.006-10.686-4.35-20.372-11.358-27.384C70.396,15.56,60.703,11.213,50.004,11.21L50.004,11.21z"/></g></svg>
+<svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" viewBox="0 0 122.879 119.799" enable-background="new 0 0 122.879 119.799" xml:space="preserve"><g><path d="M49.988,0h0.016v0.007C63.803,0.011,76.298,5.608,85.34,14.652c9.027,9.031,14.619,21.515,14.628,35.303h0.007v0.033v0.04 h-0.007c-0.005,5.557-0.917,10.905-2.594,15.892c-0.281,0.837-0.575,1.641-0.877,2.409v0.007c-1.446,3.66-3.315,7.12-5.547,10.307 l29.082,26.139l0.018,0.016l0.157,0.146l0.011,0.011c1.642,1.563,2.536,3.656,2.649,5.78c0.11,2.1-0.543,4.248-1.979,5.971 l-0.011,0.016l-0.175,0.203l-0.035,0.035l-0.146,0.16l-0.016,0.021c-1.565,1.642-3.654,2.534-5.78,2.646 c-2.097,0.111-4.247-0.54-5.971-1.978l-0.015-0.011l-0.204-0.175l-0.029-0.024L78.761,90.865c-0.88,0.62-1.778,1.209-2.687,1.765 c-1.233,0.755-2.51,1.466-3.813,2.115c-6.699,3.342-14.269,5.222-22.272,5.222v0.007h-0.016v-0.007 c-13.799-0.004-26.296-5.601-35.338-14.645C5.605,76.291,0.016,63.805,0.007,50.021H0v-0.033v-0.016h0.007 c0.004-13.799,5.601-26.296,14.645-35.338C23.683,5.608,36.167,0.016,49.955,0.007V0H49.988L49.988,0z M50.004,11.21v0.007h-0.016 h-0.033V11.21c-10.686,0.007-20.372,4.35-27.384,11.359C15.56,29.578,11.213,39.274,11.21,49.973h0.007v0.016v0.033H11.21 c0.007,10.686,4.347,20.367,11.359,27.381c7.009,7.012,16.705,11.359,27.403,11.361v-0.007h0.016h0.033v0.007 c10.686-0.007,20.368-4.348,27.382-11.359c7.011-7.009,11.358-16.702,11.36-27.4h-0.006v-0.016v-0.033h0.006 c-0.006-10.686-4.35-20.372-11.358-27.384C70.396,15.56,60.703,11.213,50.004,11.21L50.004,11.21z"/></g></svg>

changedetectionio/templates/watch-overview.html

@@ -1,6 +1,6 @@
 {% extends 'base.html' %}
 {% block content %}
-{% from '_helpers.jinja' import render_simple_field, render_field %}
+{% from '_helpers.jinja' import render_simple_field, render_field, render_nolabel_field %}
 <script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
 <script src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
 
@@ -11,17 +11,14 @@
         <fieldset>
             <legend>Add a new change detection watch</legend>
             <div id="watch-add-wrapper-zone">
-                <div>
-                    {{ render_simple_field(form.url, placeholder="https://...", required=true) }}
-                    {{ render_simple_field(form.tags, value=tags[active_tag].title if active_tag else '', placeholder="watch label / tag") }}
-                </div>
-                <div>
-                    {{ render_simple_field(form.watch_submit_button, title="Watch this URL!" ) }}
-                    {{ render_simple_field(form.edit_and_watch_submit_button, title="Edit first then Watch") }}
-                </div>
+
+                    {{ render_nolabel_field(form.url, placeholder="https://...", required=true) }}
+                    {{ render_nolabel_field(form.tags, value=tags[active_tag].title if active_tag else '', placeholder="watch label / tag") }}
+                    {{ render_nolabel_field(form.watch_submit_button, title="Watch this URL!" ) }}
+                    {{ render_nolabel_field(form.edit_and_watch_submit_button, title="Edit first then Watch") }}
             </div>
             <div id="quick-watch-processor-type">
-                {{ render_simple_field(form.processor, title="Edit first then Watch") }}
+                {{ render_simple_field(form.processor) }}
             </div>
 
         </fieldset>
@@ -82,12 +79,15 @@
             </tr>
             {% endif %}
             {% for watch in (watches|sort(attribute=sort_attribute, reverse=sort_order == 'asc'))|pagination_slice(skip=pagination.skip) %}
+
+                {% set is_unviewed =  watch.newest_history_key| int > watch.last_viewed and watch.history_n>=2 %}
+
             <tr id="{{ watch.uuid }}"
                 class="{{ loop.cycle('pure-table-odd', 'pure-table-even') }} processor-{{ watch['processor'] }}
                 {% if watch.last_error is defined and watch.last_error != False %}error{% endif %}
                 {% if watch.last_notification_error is defined and watch.last_notification_error != False %}error{% endif %}
                 {% if watch.paused is defined and watch.paused != False %}paused{% endif %}
-                {% if watch.newest_history_key| int > watch.last_viewed and watch.history_n>=2 %}unviewed{% endif %}
+                {% if is_unviewed %}unviewed{% endif %}
                 {% if watch.uuid in queued_uuids %}queued{% endif %}">
                 <td class="inline checkbox-uuid" ><input name="uuids"  type="checkbox" value="{{ watch.uuid}} " > <span>{{ loop.index+pagination.skip }}</span></td>
                 <td class="inline watch-controls">
@@ -110,6 +110,7 @@
                     {% endif %}
 
                     {%if watch.is_pdf  %}<img class="status-icon" src="{{url_for('static_content', group='images', filename='pdf-icon.svg')}}" title="Converting PDF to text" >{% endif %}
+                    {% if watch.has_browser_steps %}<img class="status-icon status-browsersteps" src="{{url_for('static_content', group='images', filename='steps.svg')}}" title="Browser Steps is enabled" >{% endif %}
                     {% if watch.last_error is defined and watch.last_error != False %}
                     <div class="fetch-error">{{ watch.last_error }}
 
@@ -141,7 +142,7 @@
                     {% if watch['processor'] == 'restock_diff'  %}
                     <span class="restock-label {{'in-stock' if watch['in_stock'] else 'not-in-stock' }}" title="detecting restock conditions">
                         <!-- maybe some object watch['processor'][restock_diff] or.. -->
-                        {% if watch['last_checked'] %}
+                        {% if watch['last_checked'] and watch['in_stock'] != None %}
                             {% if watch['in_stock'] %} In stock {% else %} Not in stock {% endif %}
                         {% else %}
                             Not yet checked
@@ -167,7 +168,13 @@
                        class="recheck pure-button pure-button-primary">{% if watch.uuid in queued_uuids %}Queued{% else %}Recheck{% endif %}</a>
                     <a href="{{ url_for('edit_page', uuid=watch.uuid)}}" class="pure-button pure-button-primary">Edit</a>
                     {% if watch.history_n >= 2 %}
-                    <a href="{{ url_for('diff_history_page', uuid=watch.uuid) }}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">Diff</a>
+
+                        {%  if is_unviewed %}
+                           <a href="{{ url_for('diff_history_page', uuid=watch.uuid, from_version=watch.get_next_snapshot_key_to_last_viewed) }}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">Diff</a>
+                        {% else %}
+                           <a href="{{ url_for('diff_history_page', uuid=watch.uuid)}}" target="{{watch.uuid}}" class="pure-button pure-button-primary diff-link">Diff</a>
+                        {% endif %}
+
                     {% else %}
                         {% if watch.history_n == 1 or (watch.history_n ==0 and watch.error_text_ctime )%}
                             <a href="{{ url_for('preview_page', uuid=watch.uuid)}}" target="{{watch.uuid}}" class="pure-button pure-button-primary">Preview</a>

changedetectionio/tests/conftest.py

@@ -4,6 +4,8 @@ import pytest
 from changedetectionio import changedetection_app
 from changedetectionio import store
 import os
+import sys
+from loguru import logger
 
 # https://github.com/pallets/flask/blob/1.1.2/examples/tutorial/tests/test_auth.py
 # Much better boilerplate than the docs
@@ -11,24 +13,28 @@ import os
 
 global app
 
+# https://loguru.readthedocs.io/en/latest/resources/migration.html#replacing-caplog-fixture-from-pytest-library
+# Show loguru logs only if CICD pytest fails.
+from loguru import logger
+@pytest.fixture
+def reportlog(pytestconfig):
+    logging_plugin = pytestconfig.pluginmanager.getplugin("logging-plugin")
+    handler_id = logger.add(logging_plugin.report_handler, format="{message}")
+    yield
+    logger.remove(handler_id)
 
 def cleanup(datastore_path):
+    import glob
     # Unlink test output files
-    files = [
-        'count.txt',
-        'endpoint-content.txt'
-        'headers.txt',
-        'headers-testtag.txt',
-        'notification.txt',
-        'secret.txt',
-        'url-watches.json',
-        'output.txt',
-    ]
-    for file in files:
-        try:
-            os.unlink("{}/{}".format(datastore_path, file))
-        except FileNotFoundError:
-            pass
+
+    for g in ["*.txt", "*.json", "*.pdf"]:
+        files = glob.glob(os.path.join(datastore_path, g))
+        for f in files:
+            if 'proxies.json' in f:
+                # Usually mounted by docker container during test time
+                continue
+            if os.path.isfile(f):
+                os.unlink(f)
 
 @pytest.fixture(scope='session')
 def app(request):
@@ -46,6 +52,18 @@ def app(request):
 
     app_config = {'datastore_path': datastore_path, 'disable_checkver' : True}
     cleanup(app_config['datastore_path'])
+
+    logger_level = 'TRACE'
+
+    logger.remove()
+    log_level_for_stdout = { 'DEBUG', 'SUCCESS' }
+    logger.configure(handlers=[
+        {"sink": sys.stdout, "level": logger_level,
+         "filter" : lambda record: record['level'].name in log_level_for_stdout},
+        {"sink": sys.stderr, "level": logger_level,
+         "filter": lambda record: record['level'].name not in log_level_for_stdout},
+        ])
+
     datastore = store.ChangeDetectionStore(datastore_path=app_config['datastore_path'], include_default_watches=False)
     app = changedetection_app(app_config, datastore)
 

changedetectionio/tests/fetchers/test_content.py

@@ -37,4 +37,4 @@ def test_fetch_webdriver_content(client, live_server):
     )
     logging.getLogger().info("Looking for correct fetched HTML (text) from server")
 
-    assert b'cool it works' in res.data
+    assert b'cool it works' in res.data

changedetectionio/tests/smtp/test_notification_smtp.py

@@ -97,6 +97,17 @@ def test_check_notification_email_formats_default_Text_override_HTML(client, liv
     set_original_response()
     global smtp_test_server
     notification_url = f'mailto://changedetection@{smtp_test_server}:11025/?to=fff@home.com'
+    notification_body = f"""<!DOCTYPE html>
+<html lang="en">
+<head>
+    <title>My Webpage</title>
+</head>
+<body>
+    <h1>Test</h1>
+    {default_notification_body}
+</body>
+</html>
+"""
 
     #####################
     # Set this up for when we remove the notification from the watch, it should fallback with these details
@@ -104,7 +115,7 @@ def test_check_notification_email_formats_default_Text_override_HTML(client, liv
         url_for("settings_page"),
         data={"application-notification_urls": notification_url,
               "application-notification_title": "fallback-title " + default_notification_title,
-              "application-notification_body": default_notification_body,
+              "application-notification_body": notification_body,
               "application-notification_format": 'Text',
               "requests-time_between_check-minutes": 180,
               'application-fetch_backend': "html_requests"},
@@ -161,5 +172,10 @@ def test_check_notification_email_formats_default_Text_override_HTML(client, liv
     assert 'Content-Type: text/html' in msg
     assert '(removed) So let\'s see what happens.<br>' in msg  # the html part
 
+    # https://github.com/dgtlmoon/changedetection.io/issues/2103
+    assert '<h1>Test</h1>' in msg
+    assert '&lt;' not in msg
+    assert 'Content-Type: text/html' in msg
+
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data

changedetectionio/tests/test_api.py

@@ -96,7 +96,9 @@ def test_api_simple(client, live_server):
     )
     assert watch_uuid in res.json.keys()
     before_recheck_info = res.json[watch_uuid]
+
     assert before_recheck_info['last_checked'] != 0
+
     #705 `last_changed` should be zero on the first check
     assert before_recheck_info['last_changed'] == 0
     assert before_recheck_info['title'] == 'My test URL'
@@ -157,6 +159,18 @@ def test_api_simple(client, live_server):
     # @todo how to handle None/default global values?
     assert watch['history_n'] == 2, "Found replacement history section, which is in its own API"
 
+    assert watch.get('viewed') == False
+    # Loading the most recent snapshot should force viewed to become true
+    client.get(url_for("diff_history_page", uuid="first"), follow_redirects=True)
+
+    # Fetch the whole watch again, viewed should be true
+    res = client.get(
+        url_for("watch", uuid=watch_uuid),
+        headers={'x-api-key': api_key}
+    )
+    watch = res.json
+    assert watch.get('viewed') == True
+
     # basic systeminfo check
     res = client.get(
         url_for("systeminfo"),
@@ -343,3 +357,25 @@ def test_api_watch_PUT_update(client, live_server):
     # Cleanup everything
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data
+
+
+def test_api_import(client, live_server):
+    api_key = extract_api_key_from_UI(client)
+
+    res = client.post(
+        url_for("import") + "?tag=import-test",
+        data='https://website1.com\r\nhttps://website2.com',
+        headers={'x-api-key': api_key},
+        follow_redirects=True
+    )
+
+    assert res.status_code == 200
+    assert len(res.json) == 2
+    res = client.get(url_for("index"))
+    assert b"https://website1.com" in res.data
+    assert b"https://website2.com" in res.data
+
+    # Should see the new tag in the tag/groups list
+    res = client.get(url_for('tags.tags_overview_page'))
+    assert b'import-test' in res.data
+    

changedetectionio/tests/test_backup.py

@@ -1,8 +1,8 @@
 #!/usr/bin/python3
 
-from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
+from .util import set_original_response, live_server_setup, wait_for_all_checks
 from flask import url_for
-from urllib.request import urlopen
+import io
 from zipfile import ZipFile
 import re
 import time
@@ -37,15 +37,10 @@ def test_backup(client, live_server):
     # Should be PK/ZIP stream
     assert res.data.count(b'PK') >= 2
 
-    # ZipFile from buffer seems non-obvious, just save it instead
-    with open("download.zip", 'wb') as f:
-        f.write(res.data)
-
-    zip = ZipFile('download.zip')
-    l = zip.namelist()
+    backup = ZipFile(io.BytesIO(res.data))
+    l = backup.namelist()
     uuid4hex = re.compile('^[a-f0-9]{8}-?[a-f0-9]{4}-?4[a-f0-9]{3}-?[89ab][a-f0-9]{3}-?[a-f0-9]{12}.*txt', re.I)
     newlist = list(filter(uuid4hex.match, l))  # Read Note below
 
     # Should be two txt files in the archive (history and the snapshot)
     assert len(newlist) == 2
-

changedetectionio/tests/test_notification.py

@@ -281,7 +281,8 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server):
 
     # CUSTOM JSON BODY CHECK for POST://
     set_original_response()
-    test_notification_url = url_for('test_notification_endpoint', _external=True).replace('http://', 'post://')+"?xxx={{ watch_url }}"
+    # https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#header-manipulation
+    test_notification_url = url_for('test_notification_endpoint', _external=True).replace('http://', 'post://')+"?xxx={{ watch_url }}&+custom-header=123"
 
     res = client.post(
         url_for("settings_page"),
@@ -297,10 +298,7 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server):
         follow_redirects=True
     )
     assert b'Settings updated' in res.data
-    client.get(
-        url_for("form_delete", uuid="all"),
-        follow_redirects=True
-    )
+
     # Add a watch and trigger a HTTP POST
     test_url = url_for('test_endpoint', _external=True)
     res = client.post(
@@ -315,7 +313,9 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server):
     set_modified_response()
 
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    time.sleep(2)
+    wait_for_all_checks(client)
+
+    time.sleep(2) # plus extra delay for notifications to fire
 
     with open("test-datastore/notification.txt", 'r') as f:
         x = f.read()
@@ -328,6 +328,13 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server):
     with open("test-datastore/notification-url.txt", 'r') as f:
         notification_url = f.read()
         assert 'xxx=http' in notification_url
+        # apprise style headers should be stripped
+        assert 'custom-header' not in notification_url
+
+    with open("test-datastore/notification-headers.txt", 'r') as f:
+        notification_headers = f.read()
+        assert 'custom-header: 123' in notification_headers.lower()
+
 
     # Should always be automatically detected as JSON content type even when we set it as 'Text' (default)
     assert os.path.isfile("test-datastore/notification-content-type.txt")
@@ -335,3 +342,8 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server):
         assert 'application/json' in f.read()
 
     os.unlink("test-datastore/notification-url.txt")
+
+    client.get(
+        url_for("form_delete", uuid="all"),
+        follow_redirects=True
+    )

changedetectionio/tests/test_notification_errors.py

@@ -1,8 +1,7 @@
 import os
 import time
-import re
 from flask import url_for
-from . util import set_original_response, set_modified_response, live_server_setup
+from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
 import logging
 
 def test_check_notification_error_handling(client, live_server):
@@ -11,7 +10,7 @@ def test_check_notification_error_handling(client, live_server):
     set_original_response()
 
     # Give the endpoint time to spin up
-    time.sleep(2)
+    time.sleep(1)
 
     # Set a URL and fetch it, then set a notification URL which is going to give errors
     test_url = url_for('test_endpoint', _external=True)
@@ -22,12 +21,16 @@ def test_check_notification_error_handling(client, live_server):
     )
     assert b"Watch added" in res.data
 
-    time.sleep(2)
+    wait_for_all_checks(client)
     set_modified_response()
 
+    working_notification_url = url_for('test_notification_endpoint', _external=True).replace('http', 'json')
+    broken_notification_url = "jsons://broken-url-xxxxxxxx123/test"
+
     res = client.post(
         url_for("edit_page", uuid="first"),
-        data={"notification_urls": "jsons://broken-url-xxxxxxxx123/test",
+        # A URL with errors should not block the one that is working
+        data={"notification_urls": f"{broken_notification_url}\r\n{working_notification_url}",
               "notification_title": "xxx",
               "notification_body": "xxxxx",
               "notification_format": "Text",
@@ -63,4 +66,10 @@ def test_check_notification_error_handling(client, live_server):
     found_name_resolution_error = b"Temporary failure in name resolution" in res.data or b"Name or service not known" in res.data
     assert found_name_resolution_error
 
+    # And the working one, which is after the 'broken' one should still have fired
+    with open("test-datastore/notification.txt", "r") as f:
+        notification_submission = f.read()
+    os.unlink("test-datastore/notification.txt")
+    assert 'xxxxx' in notification_submission
+
     client.get(url_for("form_delete", uuid="all"), follow_redirects=True)

changedetectionio/tests/test_pdf.py

@@ -2,9 +2,8 @@
 
 import time
 from flask import url_for
-from .util import set_original_response, set_modified_response, live_server_setup
+from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
 
-sleep_time_for_fetch_thread = 3
 
 # `subtractive_selectors` should still work in `source:` type requests
 def test_fetch_pdf(client, live_server):
@@ -22,7 +21,9 @@ def test_fetch_pdf(client, live_server):
 
     assert b"1 Imported" in res.data
 
-    time.sleep(sleep_time_for_fetch_thread)
+
+    wait_for_all_checks(client)
+
     res = client.get(
         url_for("preview_page", uuid="first"),
         follow_redirects=True
@@ -33,8 +34,42 @@ def test_fetch_pdf(client, live_server):
 
     # So we know if the file changes in other ways
     import hashlib
-    md5 = hashlib.md5(open("test-datastore/endpoint-test.pdf", 'rb').read()).hexdigest().upper()
+    original_md5 = hashlib.md5(open("test-datastore/endpoint-test.pdf", 'rb').read()).hexdigest().upper()
     # We should have one
-    assert len(md5) >0
+    assert len(original_md5) >0
     # And it's going to be in the document
-    assert b'Document checksum - '+bytes(str(md5).encode('utf-8')) in res.data
+    assert b'Document checksum - '+bytes(str(original_md5).encode('utf-8')) in res.data
+
+
+    shutil.copy("tests/test2.pdf", "test-datastore/endpoint-test.pdf")
+    changed_md5 = hashlib.md5(open("test-datastore/endpoint-test.pdf", 'rb').read()).hexdigest().upper()
+    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    assert b'1 watches queued for rechecking.' in res.data
+
+    wait_for_all_checks(client)
+
+    # Now something should be ready, indicated by having a 'unviewed' class
+    res = client.get(url_for("index"))
+    assert b'unviewed' in res.data
+
+    # The original checksum should be not be here anymore (cdio adds it to the bottom of the text)
+
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    assert original_md5.encode('utf-8') not in res.data
+    assert changed_md5.encode('utf-8') in res.data
+
+
+    res = client.get(
+        url_for("diff_history_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    assert original_md5.encode('utf-8') in res.data
+    assert changed_md5.encode('utf-8') in res.data
+
+    assert b'here is a change' in res.data
+    

changedetectionio/tests/unit/test_watch_model.py

@@ -0,0 +1,54 @@
+#!/usr/bin/python3
+
+# run from dir above changedetectionio/ dir
+# python3 -m unittest changedetectionio.tests.unit.test_notification_diff
+
+import unittest
+import os
+
+from changedetectionio.model import Watch
+
+# mostly
+class TestDiffBuilder(unittest.TestCase):
+
+    def test_watch_get_suggested_from_diff_timestamp(self):
+        import uuid as uuid_builder
+        watch = Watch.model(datastore_path='/tmp', default={})
+        watch.ensure_data_dir_exists()
+
+        watch['last_viewed'] = 110
+
+        watch.save_history_text(contents=b"hello world", timestamp=100, snapshot_id=str(uuid_builder.uuid4()))
+        watch.save_history_text(contents=b"hello world", timestamp=105, snapshot_id=str(uuid_builder.uuid4()))
+        watch.save_history_text(contents=b"hello world", timestamp=109, snapshot_id=str(uuid_builder.uuid4()))
+        watch.save_history_text(contents=b"hello world", timestamp=112, snapshot_id=str(uuid_builder.uuid4()))
+        watch.save_history_text(contents=b"hello world", timestamp=115, snapshot_id=str(uuid_builder.uuid4()))
+        watch.save_history_text(contents=b"hello world", timestamp=117, snapshot_id=str(uuid_builder.uuid4()))
+
+        p = watch.get_next_snapshot_key_to_last_viewed
+        assert p == "112", "Correct last-viewed timestamp was detected"
+
+        # When there is only one step of difference from the end of the list, it should return second-last change
+        watch['last_viewed'] = 116
+        p = watch.get_next_snapshot_key_to_last_viewed
+        assert p == "115", "Correct 'second last' last-viewed timestamp was detected when using the last timestamp"
+
+        watch['last_viewed'] = 99
+        p = watch.get_next_snapshot_key_to_last_viewed
+        assert p == "100"
+
+        watch['last_viewed'] = 200
+        p = watch.get_next_snapshot_key_to_last_viewed
+        assert p == "115", "When the 'last viewed' timestamp is greater than the newest snapshot, return second last "
+
+        watch['last_viewed'] = 109
+        p = watch.get_next_snapshot_key_to_last_viewed
+        assert p == "109", "Correct when its the same time"
+
+        # new empty one
+        watch = Watch.model(datastore_path='/tmp', default={})
+        p = watch.get_next_snapshot_key_to_last_viewed
+        assert p == None, "None when no history available"
+
+if __name__ == '__main__':
+    unittest.main()

changedetectionio/tests/util.py

@@ -205,6 +205,9 @@ def live_server_setup(live_server):
         with open("test-datastore/notification-url.txt", "w") as f:
             f.write(request.url)
 
+        with open("test-datastore/notification-headers.txt", "w") as f:
+            f.write(str(request.headers))
+
         if request.content_type:
             with open("test-datastore/notification-content-type.txt", "w") as f:
                 f.write(request.content_type)

changedetectionio/update_worker.py

@@ -12,61 +12,77 @@ from .processors.restock_diff import UnableToExtractRestockData
 # Requests for checking on a single site(watch) from a queue of watches
 # (another process inserts watches into the queue that are time-ready for checking)
 
-import logging
 import sys
+from loguru import logger
 
 class update_worker(threading.Thread):
     current_uuid = None
 
     def __init__(self, q, notification_q, app, datastore, *args, **kwargs):
-        logging.basicConfig(stream=sys.stderr, level=logging.DEBUG)
         self.q = q
         self.app = app
         self.notification_q = notification_q
         self.datastore = datastore
         super().__init__(*args, **kwargs)
 
-    def queue_notification_for_watch(self, n_object, watch):
+    def queue_notification_for_watch(self, notification_q, n_object, watch):
 
         from changedetectionio import diff
+        dates = []
+        trigger_text = ''
+
+        now = time.time()
+
+        if watch:
+            watch_history = watch.history
+            dates = list(watch_history.keys())
+            trigger_text = watch.get('trigger_text', [])
 
-        watch_history = watch.history
-        dates = list(watch_history.keys())
         # Add text that was triggered
-        snapshot_contents = watch.get_history_snapshot(dates[-1])
+        if len(dates):
+            snapshot_contents = watch.get_history_snapshot(dates[-1])
+        else:
+            snapshot_contents = "No snapshot/history available, the watch should fetch atleast once."
 
         # HTML needs linebreak, but MarkDown and Text can use a linefeed
-        if n_object['notification_format'] == 'HTML':
+        if n_object.get('notification_format') == 'HTML':
             line_feed_sep = "<br>"
             # Snapshot will be plaintext on the disk, convert to some kind of HTML
             snapshot_contents = snapshot_contents.replace('\n', line_feed_sep)
         else:
             line_feed_sep = "\n"
 
-        trigger_text = watch.get('trigger_text', [])
         triggered_text = ''
-
         if len(trigger_text):
             from . import html_tools
             triggered_text = html_tools.get_triggered_text(content=snapshot_contents, trigger_text=trigger_text)
             if triggered_text:
                 triggered_text = line_feed_sep.join(triggered_text)
 
+        # Could be called as a 'test notification' with only 1 snapshot available
+        prev_snapshot = "Example text: example test\nExample text: change detection is cool\nExample text: some more examples\n"
+        current_snapshot = "Example text: example test\nExample text: change detection is fantastic\nExample text: even more examples\nExample text: a lot more examples"
+
+        if len(dates) > 1:
+            prev_snapshot = watch.get_history_snapshot(dates[-2])
+            current_snapshot = watch.get_history_snapshot(dates[-1])
 
         n_object.update({
             'current_snapshot': snapshot_contents,
-            'diff': diff.render_diff(watch.get_history_snapshot(dates[-2]), watch.get_history_snapshot(dates[-1]), line_feed_sep=line_feed_sep),
-            'diff_added': diff.render_diff(watch.get_history_snapshot(dates[-2]), watch.get_history_snapshot(dates[-1]), include_removed=False, line_feed_sep=line_feed_sep),
-            'diff_full': diff.render_diff(watch.get_history_snapshot(dates[-2]), watch.get_history_snapshot(dates[-1]), include_equal=True, line_feed_sep=line_feed_sep),
-            'diff_patch': diff.render_diff(watch.get_history_snapshot(dates[-2]), watch.get_history_snapshot(dates[-1]), line_feed_sep=line_feed_sep, patch_format=True),
-            'diff_removed': diff.render_diff(watch.get_history_snapshot(dates[-2]), watch.get_history_snapshot(dates[-1]), include_added=False, line_feed_sep=line_feed_sep),
-            'screenshot': watch.get_screenshot() if watch.get('notification_screenshot') else None,
+            'diff': diff.render_diff(prev_snapshot, current_snapshot, line_feed_sep=line_feed_sep),
+            'diff_added': diff.render_diff(prev_snapshot, current_snapshot, include_removed=False, line_feed_sep=line_feed_sep),
+            'diff_full': diff.render_diff(prev_snapshot, current_snapshot, include_equal=True, line_feed_sep=line_feed_sep),
+            'diff_patch': diff.render_diff(prev_snapshot, current_snapshot, line_feed_sep=line_feed_sep, patch_format=True),
+            'diff_removed': diff.render_diff(prev_snapshot, current_snapshot, include_added=False, line_feed_sep=line_feed_sep),
+            'notification_timestamp': now,
+            'screenshot': watch.get_screenshot() if watch and watch.get('notification_screenshot') else None,
             'triggered_text': triggered_text,
-            'uuid': watch.get('uuid'),
-            'watch_url': watch.get('url'),
+            'uuid': watch.get('uuid') if watch else None,
+            'watch_url': watch.get('url') if watch else None,
         })
-        logging.info (">> SENDING NOTIFICATION")
-        self.notification_q.put(n_object)
+        logger.trace(f"Main rendered notification placeholders (diff_added etc) calculated in {time.time()-now:.3f}s")
+        logger.debug("Queued notification for sending")
+        notification_q.put(n_object)
 
     # Prefer - Individual watch settings > Tag settings >  Global settings (in that order)
     def _check_cascading_vars(self, var_name, watch):
@@ -134,7 +150,7 @@ class update_worker(threading.Thread):
         queued = False
         if n_object and n_object.get('notification_urls'):
             queued = True
-            self.queue_notification_for_watch(n_object, watch)
+            self.queue_notification_for_watch(notification_q=self.notification_q, n_object=n_object, watch=watch)
 
         return queued
 
@@ -166,7 +182,7 @@ class update_worker(threading.Thread):
                 'screenshot': None
             })
             self.notification_q.put(n_object)
-            print("Sent filter not found notification for {}".format(watch_uuid))
+            logger.error(f"Sent filter not found notification for {watch_uuid}")
 
     def send_step_failure_notification(self, watch_uuid, step_n):
         watch = self.datastore.data['watching'].get(watch_uuid, False)
@@ -174,9 +190,9 @@ class update_worker(threading.Thread):
             return
         threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts')
         n_object = {'notification_title': "Changedetection.io - Alert - Browser step at position {} could not be run".format(step_n+1),
-                    'notification_body': "Your configured browser step at position {} for {{watch['url']}} "
+                    'notification_body': "Your configured browser step at position {} for {{{{watch_url}}}} "
                                          "did not appear on the page after {} attempts, did the page change layout? "
-                                         "Does it need a delay added?\n\nLink: {{base_url}}/edit/{{watch_uuid}}\n\n"
+                                         "Does it need a delay added?\n\nLink: {{{{base_url}}}}/edit/{{{{watch_uuid}}}}\n\n"
                                          "Thanks - Your omniscient changedetection.io installation :)\n".format(step_n+1, threshold),
                     'notification_format': 'text'}
 
@@ -193,7 +209,7 @@ class update_worker(threading.Thread):
                 'uuid': watch_uuid
             })
             self.notification_q.put(n_object)
-            print("Sent step not found notification for {}".format(watch_uuid))
+            logger.error(f"Sent step not found notification for {watch_uuid}")
 
 
     def cleanup_error_artifacts(self, uuid):
@@ -207,7 +223,8 @@ class update_worker(threading.Thread):
     def run(self):
 
         from .processors import text_json_diff, restock_diff
-
+        now = time.time()
+        
         while not self.app.config.exit.is_set():
             update_handler = None
 
@@ -219,14 +236,14 @@ class update_worker(threading.Thread):
             else:
                 uuid = queued_item_data.item.get('uuid')
                 self.current_uuid = uuid
-
                 if uuid in list(self.datastore.data['watching'].keys()) and self.datastore.data['watching'][uuid].get('url'):
                     changed_detected = False
                     contents = b''
                     process_changedetection_results = True
                     update_obj = {}
-                    print("> Processing UUID {} Priority {} URL {}".format(uuid, queued_item_data.priority,
-                                                                           self.datastore.data['watching'][uuid]['url']))
+                    logger.info(f"Processing watch UUID {uuid} "
+                            f"Priority {queued_item_data.priority} "
+                            f"URL {self.datastore.data['watching'][uuid]['url']}")
                     now = time.time()
 
                     try:
@@ -266,7 +283,8 @@ class update_worker(threading.Thread):
                         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))
+                        logger.critical(f"File permission error updating file, watch: {uuid}")
+                        logger.critical(str(e))
                         process_changedetection_results = False
                     except content_fetcher.ReplyWithContentButNoText as e:
                         # Totally fine, it's by choice - just continue on, nothing more to care about
@@ -324,7 +342,7 @@ class update_worker(threading.Thread):
                             # Send notification if we reached the threshold?
                             threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts',
                                                                                            0)
-                            print("Filter for {} not found, consecutive_filter_failures: {}".format(uuid, c))
+                            logger.error(f"Filter for {uuid} not found, consecutive_filter_failures: {c}")
                             if threshold > 0 and c >= threshold:
                                 if not self.datastore.data['watching'][uuid].get('notification_muted'):
                                     self.send_filter_failure_notification(uuid)
@@ -340,27 +358,39 @@ class update_worker(threading.Thread):
                         changed_detected = False
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': False})
 
-                    except content_fetcher.BrowserStepsStepTimout as e:
+                    except content_fetcher.BrowserStepsStepException as e:
 
                         if not self.datastore.data['watching'].get(uuid):
                             continue
 
                         error_step = e.step_n + 1
-                        err_text = f"Warning, browser step at position {error_step} could not run, target not found, check the watch, add a delay if necessary, view Browser Steps to see screenshot at that step"
+                        from playwright._impl._errors import TimeoutError, Error
+
+                        # Generally enough info for TimeoutError (couldnt locate the element after default seconds)
+                        err_text = f"Browser step at position {error_step} could not run, check the watch, add a delay if necessary, view Browser Steps to see screenshot at that step."
+
+                        if e.original_e.name == "TimeoutError":
+                            # Just the first line is enough, the rest is the stack trace
+                            err_text += " Could not find the target."
+                        else:
+                            # Other Error, more info is good.
+                            err_text += " " + str(e.original_e).splitlines()[0]
+
+                        logger.debug(f"BrowserSteps exception at step {error_step} {str(e.original_e)}")
+
                         self.datastore.update_watch(uuid=uuid,
                                                     update_obj={'last_error': err_text,
                                                                 'browser_steps_last_error_step': error_step
                                                                 }
                                                     )
 
-
                         if self.datastore.data['watching'][uuid].get('filter_failure_notification_send', False):
                             c = self.datastore.data['watching'][uuid].get('consecutive_filter_failures', 5)
                             c += 1
                             # Send notification if we reached the threshold?
                             threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts',
                                                                                            0)
-                            print("Step for {} not found, consecutive_filter_failures: {}".format(uuid, c))
+                            logger.error(f"Step for {uuid} not found, consecutive_filter_failures: {c}")
                             if threshold > 0 and c >= threshold:
                                 if not self.datastore.data['watching'][uuid].get('notification_muted'):
                                     self.send_step_failure_notification(watch_uuid=uuid, step_n=e.step_n)
@@ -402,11 +432,13 @@ class update_worker(threading.Thread):
                         process_changedetection_results = False
                     except UnableToExtractRestockData as e:
                         # Usually when fetcher.instock_data returns empty
-                        self.app.logger.error("Exception reached processing watch UUID: %s - %s", uuid, str(e))
+                        logger.error(f"Exception (UnableToExtractRestockData) reached processing watch UUID: {uuid}")
+                        logger.error(str(e))
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': f"Unable to extract restock data for this page unfortunately. (Got code {e.status_code} from server)"})
                         process_changedetection_results = False
                     except Exception as e:
-                        self.app.logger.error("Exception reached processing watch UUID: %s - %s", uuid, str(e))
+                        logger.error(f"Exception reached processing watch UUID: {uuid}")
+                        logger.error(str(e))
                         self.datastore.update_watch(uuid=uuid, update_obj={'last_error': str(e)})
                         # Other serious error
                         process_changedetection_results = False
@@ -442,18 +474,18 @@ class update_worker(threading.Thread):
 
                             # A change was detected
                             if changed_detected:
-                                print (">> Change detected in UUID {} - {}".format(uuid, watch['url']))
-
                                 # Notifications should only trigger on the second time (first time, we gather the initial snapshot)
                                 if watch.history_n >= 2:
+                                    logger.info(f"Change detected in UUID {uuid} - {watch['url']}")
                                     if not self.datastore.data['watching'][uuid].get('notification_muted'):
                                         self.send_content_changed_notification(watch_uuid=uuid)
-
+                                else:
+                                    logger.info(f"Change triggered in UUID {uuid} due to first history saving (no notifications sent) - {watch['url']}")
 
                         except Exception as e:
                             # Catch everything possible here, so that if a worker crashes, we don't lose it until restart!
-                            print("!!!! Exception in update_worker !!!\n", e)
-                            self.app.logger.error("Exception reached processing watch UUID: %s - %s", uuid, str(e))
+                            logger.critical("!!!! Exception in update_worker while processing process_changedetection_results !!!")
+                            logger.critical(str(e))
                             self.datastore.update_watch(uuid=uuid, update_obj={'last_error': str(e)})
 
                     if self.datastore.data['watching'].get(uuid):
@@ -473,6 +505,7 @@ class update_worker(threading.Thread):
 
                 self.current_uuid = None  # Done
                 self.q.task_done()
+                logger.debug(f"Watch {uuid} done in {time.time()-now:.2f}s")
 
                 # Give the CPU time to interrupt
                 time.sleep(0.1)

docker-compose.yml

@@ -16,6 +16,10 @@ services:
   #      - PUID=1000
   #      - PGID=1000
   #
+  #        Log levels are in descending order. (TRACE is the most detailed one)
+  #        Log output levels: TRACE, DEBUG(default), INFO, SUCCESS, WARNING, ERROR, CRITICAL
+  #      - LOGGER_LEVEL=DEBUG
+  #
   #       Alternative WebDriver/selenium URL, do not use "'s or 's!
   #      - WEBDRIVER_URL=http://browser-chrome:4444/wd/hub
   #
@@ -90,7 +94,8 @@ services:
 #
 
      # Used for fetching pages via Playwright+Chrome where you need Javascript support.
-     # Note: works well but is deprecated, doesnt fetch full page screenshots and other issues
+     # Note: works well but is deprecated, does not fetch full page screenshots (doesnt work with Visual Selector) and other issues
+     # More information about the advantages of playwright/browserless https://www.browserless.io/blog/2023/12/13/migrating-selenium-to-playwright/
 #    browser-chrome:
 #        hostname: browser-chrome
 #        image: selenium/standalone-chrome:4

docs/api_v1/index.html

@@ -5,13 +5,13 @@
   <meta name="description" content="Manage your changedetection.io watches via API, requires the `x-api-key` header which is found in the settings UI.">
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
-  <link href="assets/bootstrap.min.css?v=1677105736053" rel="stylesheet" media="screen">
-  <link href="assets/prism.css?v=1677105736053" rel="stylesheet" />
-  <link href="assets/main.css?v=1677105736053" rel="stylesheet" media="screen, print">
-  <link href="assets/favicon.ico?v=1677105736053" rel="icon" type="image/x-icon">
-  <link href="assets/apple-touch-icon.png?v=1677105736053" rel="apple-touch-icon" sizes="180x180">
-  <link href="assets/favicon-32x32.png?v=1677105736053" rel="icon" type="image/png" sizes="32x32">
-  <link href="assets/favicon-16x16.png?v=1677105736053" rel="icon" type="image/png" sizes="16x16">
+  <link href="assets/bootstrap.min.css?v=1701595483622" rel="stylesheet" media="screen">
+  <link href="assets/prism.css?v=1701595483622" rel="stylesheet" />
+  <link href="assets/main.css?v=1701595483622" rel="stylesheet" media="screen, print">
+  <link href="assets/favicon.ico?v=1701595483622" rel="icon" type="image/x-icon">
+  <link href="assets/apple-touch-icon.png?v=1701595483622" rel="apple-touch-icon" sizes="180x180">
+  <link href="assets/favicon-32x32.png?v=1701595483622" rel="icon" type="image/png" sizes="32x32">
+  <link href="assets/favicon-16x16.png?v=1701595483622" rel="icon" type="image/png" sizes="16x16">
 </head>
 
 <body class="container-fluid">
@@ -928,6 +928,6 @@
   </div>
 </div>
 
-<script src="assets/main.bundle.js?v=1677105736053"></script>
+<script src="assets/main.bundle.js?v=1701595483622"></script>
 </body>
 </html>

heroku.yml

@@ -1,2 +0,0 @@
-run:
-  changedetection: python3 ./changedetection.py -C -d ./datastore -p $PORT

requirements.txt

@@ -30,7 +30,7 @@ dnspython~=2.4 # related to eventlet fixes
 # jq not available on Windows so must be installed manually
 
 # Notification library
-apprise~=1.6.0
+apprise~=1.7.1
 
 # apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
 paho-mqtt
@@ -72,3 +72,5 @@ pytest-flask ~=1.2
 
 # Pin jsonschema version to prevent build errors on armv6 while rpds-py wheels aren't available (1708)
 jsonschema==4.17.3
+
+loguru

setup.py

@@ -27,12 +27,12 @@ install_requires = open('requirements.txt').readlines()
 setup(
     name='changedetection.io',
     version=find_version("changedetectionio", "__init__.py"),
-    description='Website change detection and monitoring service',
+    description='Website change detection and monitoring service, detect changes to web pages and send alerts/notifications.',
     long_description=open('README-pip.md').read(),
     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"]},
+    entry_points={"console_scripts": ["changedetection.io=changedetectionio:main"]},
     zip_safe=True,
     scripts=["changedetection.py"],
     author='dgtlmoon',
@@ -41,7 +41,7 @@ setup(
     include_package_data=True,
     install_requires=install_requires,
     license="Apache License 2.0",
-    python_requires=">= 3.7",
+    python_requires=">= 3.10",
     classifiers=['Intended Audience :: Customer Service',
                  'Intended Audience :: Developers',
                  'Intended Audience :: Education',