WIP

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,42 +1,25 @@
 ---
 name: Bug report
-about: Create a bug report, if you don't follow this template, your report will be DELETED
+about: Create a report to help us improve
 title: ''
-labels: 'triage'
-assignees: 'dgtlmoon'
+labels: ''
+assignees: ''
 
 ---
 
-**DO NOT USE THIS FORM TO REPORT THAT A PARTICULAR WEBSITE IS NOT SCRAPING/WATCHING AS EXPECTED**
-
-This form is only for direct bugs and feature requests todo directly with the software.
-
-Please report watched websites (full URL and _any_ settings) that do not work with changedetection.io as expected [**IN THE DISCUSSION FORUMS**](https://github.com/dgtlmoon/changedetection.io/discussions) or your report will be deleted
-
-CONSIDER TAKING OUT A SUBSCRIPTION FOR A SMALL PRICE PER MONTH, YOU GET THE BENEFIT OF USING OUR PAID PROXIES AND FURTHERING THE DEVELOPMENT OF CHANGEDETECTION.IO
-
-THANK YOU
-
-
-
-
-
 **Describe the bug**
 A clear and concise description of what the bug is.
 
 **Version**
-*Exact version* in the top right area: 0....
+In the top right area: 0....
 
 **To Reproduce**
-
 Steps to reproduce the behavior:
 1. Go to '...'
 2. Click on '....'
 3. Scroll down to '....'
 4. See error
 
-! ALWAYS INCLUDE AN EXAMPLE URL WHERE IT IS POSSIBLE TO RE-CREATE THE ISSUE - USE THE 'SHARE WATCH' FEATURE AND PASTE IN THE SHARE-LINK!
-
 **Expected behavior**
 A clear and concise description of what you expected to happen.
 

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,8 +1,8 @@
 ---
 name: Feature request
 about: Suggest an idea for this project
-title: '[feature]'
-labels: 'enhancement'
+title: ''
+labels: ''
 assignees: ''
 
 ---

.github/test/Dockerfile-alpine

@@ -1,31 +0,0 @@
-# Taken from https://github.com/linuxserver/docker-changedetection.io/blob/main/Dockerfile
-# Test that we can still build on Alpine (musl modified libc https://musl.libc.org/)
-# Some packages wont install via pypi because they dont have a wheel available under this architecture.
-
-FROM ghcr.io/linuxserver/baseimage-alpine:3.16
-ENV PYTHONUNBUFFERED=1
-
-COPY requirements.txt /requirements.txt
-
-RUN \
-  apk add --update --no-cache --virtual=build-dependencies \
-    cargo \
-    g++ \
-    gcc \
-    libc-dev \
-    libffi-dev \
-    libxslt-dev \
-    make \
-    openssl-dev \
-    py3-wheel \
-    python3-dev \
-    zlib-dev && \
-  apk add --update --no-cache \
-    libxslt \
-    python3 \
-    py3-pip && \
-  echo "**** pip3 install test of changedetection.io ****" && \
-  pip3 install -U pip wheel setuptools && \
-  pip3 install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.16/ -r /requirements.txt && \
-  apk del --purge \
-    build-dependencies

.github/workflows/containers.yml

@@ -50,6 +50,7 @@ jobs:
           python -m pip install --upgrade pip
           pip install flake8 pytest
           if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+          if [ -f requirements-dev.txt ]; then pip install -r requirements-dev.txt; fi
 
       - name: Create release metadata
         run: |
@@ -84,8 +85,8 @@ jobs:
           version: latest
           driver-opts: image=moby/buildkit:master
 
-      # master branch -> :dev container tag
-      - name: Build and push :dev
+      # master always builds :latest
+      - name: Build and push :latest
         id: docker_build
         if: ${{ github.ref }} == "refs/heads/master"
         uses: docker/build-push-action@v2
@@ -94,13 +95,12 @@ jobs:
           file: ./Dockerfile
           push: true
           tags: |
-            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:dev,ghcr.io/${{ github.repository }}:dev
+            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:latest,ghcr.io/${{ github.repository }}:latest
           platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
           cache-from: type=local,src=/tmp/.buildx-cache
           cache-to: type=local,dest=/tmp/.buildx-cache
-          provenance: false
 
-      # A new tagged release is required, which builds :tag and :latest
+      # A new tagged release is required, which builds :tag
       - name: Build and push :tag
         id: docker_build_tag_release
         if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
@@ -110,14 +110,10 @@ jobs:
           file: ./Dockerfile
           push: true
           tags: |
-            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:${{ github.event.release.tag_name }}
-            ghcr.io/dgtlmoon/changedetection.io:${{ github.event.release.tag_name }}
-            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:latest
-            ghcr.io/dgtlmoon/changedetection.io:latest
+            ${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:${{ github.event.release.tag_name }},ghcr.io/dgtlmoon/changedetection.io:${{ github.event.release.tag_name }}
           platforms: linux/amd64,linux/arm64,linux/arm/v6,linux/arm/v7
           cache-from: type=local,src=/tmp/.buildx-cache
           cache-to: type=local,dest=/tmp/.buildx-cache
-          provenance: false
 
       - name: Image digest
         run: echo step SHA ${{ steps.vars.outputs.sha_short }} tag ${{steps.vars.outputs.tag}} branch ${{steps.vars.outputs.branch}} digest ${{ steps.docker_build.outputs.digest }}
@@ -129,3 +125,5 @@ jobs:
           key: ${{ runner.os }}-buildx-${{ github.sha }}
           restore-keys: |
             ${{ runner.os }}-buildx-
+
+

.github/workflows/pypi.yml

@@ -19,6 +19,12 @@ jobs:
         with:
           python-version: 3.9
 
+#      - name: Install dependencies
+#        run: |
+#          python -m pip install --upgrade pip
+#          pip install flake8 pytest
+#          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+#          if [ -f requirements-dev.txt ]; then pip install -r requirements-dev.txt; fi
 
       - name: Test that pip builds without error
         run: |

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

@@ -1,68 +0,0 @@
-name: ChangeDetection.io Container Build 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]
-
-on:
-  push:
-    paths:
-      - requirements.txt
-      - Dockerfile
-      - .github/workflows/*
-
-  pull_request:
-    paths:
-      - requirements.txt
-      - Dockerfile
-      - .github/workflows/*
-
-  # 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-container-build:
-    runs-on: ubuntu-latest
-    steps:
-        - uses: actions/checkout@v2
-        - name: Set up Python 3.9
-          uses: actions/setup-python@v2
-          with:
-            python-version: 3.9
-
-        # Just test that the build works, some libraries won't compile on ARM/rPi etc
-        - name: Set up QEMU
-          uses: docker/setup-qemu-action@v1
-          with:
-            image: tonistiigi/binfmt:latest
-            platforms: all
-
-        - name: Set up Docker Buildx
-          id: buildx
-          uses: docker/setup-buildx-action@v1
-          with:
-            install: true
-            version: latest
-            driver-opts: image=moby/buildkit:master
-
-        # https://github.com/dgtlmoon/changedetection.io/pull/1067
-        # Check we can still build under alpine/musl
-        - name: Test that the docker containers can build (musl via alpine check)
-          id: docker_build_musl
-          uses: docker/build-push-action@v2
-          with:
-            context: ./
-            file: ./.github/test/Dockerfile-alpine
-            platforms: linux/amd64,linux/arm64
-
-        - name: Test that the docker containers can build
-          id: docker_build
-          uses: docker/build-push-action@v2
-          # https://github.com/docker/build-push-action#customizing
-          with:
-            context: ./
-            file: ./Dockerfile
-            platforms: linux/arm/v7,linux/arm/v6,linux/amd64,linux/arm64,
-            cache-from: type=local,src=/tmp/.buildx-cache
-            cache-to: type=local,dest=/tmp/.buildx-cache
-

.github/workflows/test-only.yml

@@ -1,77 +1,45 @@
-name: ChangeDetection.io App Test
+name: ChangeDetection.io Test
 
 # Triggers the workflow on push or pull request events
 on: [push, pull_request]
 
 jobs:
-  test-application:
+  test-build:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
 
-      # Mainly just for link/flake8
-      - name: Set up Python 3.10
+      - uses: actions/checkout@v2
+      - name: Set up Python 3.9
         uses: actions/setup-python@v2
         with:
-          python-version: '3.10'
+          python-version: 3.9
 
+      - name: Show env vars
+        run: set
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install flake8 pytest
+          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+          if [ -f requirements-dev.txt ]; then pip install -r requirements-dev.txt; fi
       - name: Lint with flake8
         run: |
-          pip3 install flake8
           # stop the build if there are Python syntax errors or undefined names
           flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
           # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
           flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
 
-      - name: Spin up ancillary testable services
+      - name: Unit tests
         run: |
-          
-          docker network create changedet-network
+          python3 -m unittest changedetectionio.tests.unit.test_notification_diff
 
-          # Selenium+browserless
-          docker run --network changedet-network -d --hostname selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome-debug:3.141.59
-          docker run --network changedet-network -d --hostname browserless -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm  -p 3000:3000  --shm-size="2g"  browserless/chrome:1.53-chrome-stable
-
-      - name: Build changedetection.io container for testing
-        run: |         
-          # Build a changedetection.io container and start testing inside
-          docker build . -t test-changedetectionio
-
-      - name: Test built container with pytest
+      - name: Test with pytest
         run: |
-          
-          # Unit tests
-          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_notification_diff'
-          
-          # All tests
-          docker run --network changedet-network  test-changedetectionio  bash -c 'cd changedetectionio && ./run_basic_tests.sh'
+          # Each test is totally isolated and performs its own cleanup/reset
+          cd changedetectionio; ./run_all_tests.sh
 
-      - name: Test built container selenium+browserless/playwright
-        run: |
-          
-          # Selenium fetch
-          docker run -e "WEBDRIVER_URL=http://selenium:4444/wd/hub" --network changedet-network  test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py'
-          
-          # Playwright/Browserless fetch
-          docker run -e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" --network changedet-network  test-changedetectionio  bash -c 'cd changedetectionio;pytest tests/fetchers/test_content.py && pytest tests/test_errorhandling.py && pytest tests/visualselector/test_fetch_data.py'
+      # https://github.com/docker/build-push-action/blob/master/docs/advanced/test-before-push.md ?
+      # https://github.com/docker/buildx/issues/59 ? Needs to be one platform?
 
-      - name: Test proxy interaction
-        run: |
-          cd changedetectionio
-          ./run_proxy_tests.sh
-          cd ..
-
-      - name: Test changedetection.io container starts+runs basically without error
-        run: |
-          docker run -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
-          
-
-#export WEBDRIVER_URL=http://localhost:4444/wd/hub
-#pytest tests/fetchers/test_content.py
-#pytest tests/test_errorhandling.py
+      # https://github.com/docker/buildx/issues/495#issuecomment-918925854

.gitignore

@@ -8,7 +8,5 @@ __pycache__
 build
 dist
 venv
-test-datastore/*
-test-datastore
 *.egg-info*
 .vscode/settings.json

CONTRIBUTING.md

@@ -6,4 +6,10 @@ Otherwise, it's always best to PR into the `dev` branch.
 
 Please be sure that all new functionality has a matching test!
 
-Use `pytest` to validate/test, you can run the existing tests as `pytest tests/test_notification.py` for example
+Use `pytest` to validate/test, you can run the existing tests as `pytest tests/test_notifications.py` for example
+
+```
+pip3 install -r requirements-dev
+```
+
+this is from https://github.com/dgtlmoon/changedetection.io/blob/master/requirements-dev.txt

Dockerfile

@@ -1,19 +1,17 @@
 # pip dependencies install stage
-FROM python:3.10-slim as builder
+FROM python:3.8-slim as builder
 
-# See `cryptography` pin comment in requirements.txt
+# rustc compiler would be needed on ARM type devices but theres an issue with some deps not building..
 ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    g++ \
+    libssl-dev \
+    libffi-dev \
     gcc \
     libc-dev \
-    libffi-dev \
-    libjpeg-dev \
-    libssl-dev \
     libxslt-dev \
-    make \
-    zlib1g-dev
+    zlib1g-dev \
+    g++
 
 RUN mkdir /install
 WORKDIR /install
@@ -24,21 +22,25 @@ 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~=1.27.1 \
+RUN pip install --target=/dependencies playwright~=1.20 \
     || echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
 
 # Final image stage
-FROM python:3.10-slim
+FROM python:3.8-slim
 
+# Actual packages needed at runtime, usually due to the notification (apprise) backend
+# rustc compiler would be needed on ARM type devices but theres an issue with some deps not building..
+ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
+
+# Re #93, #73, excluding rustc (adds another 430Mb~)
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    libssl1.1 \
-    libxslt1.1 \
-    # For pdftohtml
-    poppler-utils \
-    zlib1g \
-    && apt-get clean && rm -rf /var/lib/apt/lists/*
-
+    libssl-dev \
+    libffi-dev \
+    gcc \
+    libc-dev \
+    libxslt-dev \
+    zlib1g-dev \
+    g++
 
 # https://stackoverflow.com/questions/58701233/docker-logs-erroneously-appears-empty-until-container-stops
 ENV PYTHONUNBUFFERED=1
@@ -56,7 +58,6 @@ EXPOSE 5000
 
 # The actual flask app
 COPY changedetectionio /app/changedetectionio
-
 # The eventlet server wrapper
 COPY changedetection.py /app/changedetection.py
 

MANIFEST.in

@@ -1,14 +1,7 @@
-recursive-include changedetectionio/api *
-recursive-include changedetectionio/blueprint *
-recursive-include changedetectionio/model *
-recursive-include changedetectionio/res *
-recursive-include changedetectionio/static *
 recursive-include changedetectionio/templates *
-recursive-include changedetectionio/tests *
-prune changedetectionio/static/package-lock.json
-prune changedetectionio/static/styles/node_modules
-prune changedetectionio/static/styles/package-lock.json
+recursive-include changedetectionio/static *
+recursive-include changedetectionio/model *
 include changedetection.py
 global-exclude *.pyc
 global-exclude node_modules
-global-exclude venv
+global-exclude venv

README-pip.md

@@ -1,48 +1,45 @@
-## Web Site Change Detection, Monitoring and Notification.
+#  changedetection.io
+![changedetection.io](https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master)
+<a href="https://hub.docker.com/r/dgtlmoon/changedetection.io" target="_blank" title="Change detection docker hub">
+  <img src="https://img.shields.io/docker/pulls/dgtlmoon/changedetection.io" alt="Docker Pulls"/>
+</a>
+<a href="https://hub.docker.com/r/dgtlmoon/changedetection.io" target="_blank" title="Change detection docker hub">
+  <img src="https://img.shields.io/github/v/release/dgtlmoon/changedetection.io" alt="Change detection latest tag version"/> 
+</a>
 
-Live your data-life pro-actively, track website content changes and receive notifications via Discord, Email, Slack, Telegram and 70+ more
+## Self-hosted open source change monitoring of web pages.
 
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start?src=pip)
+_Know when web pages change! Stay ontop of new information!_ 
+
+Live your data-life *pro-actively* instead of *re-actively*, do not rely on manipulative social media for consuming important information.
 
 
-[**Don't have time? Let us host it for you! try our extremely affordable subscription use our proxies and support!**](https://lemonade.changedetection.io/start) 
+<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />
+
+
+**Get your own private instance now! Let us host it for you!**
+
+[**Try our $6.99/month subscription - unlimited checks, watches and notifications!**](https://lemonade.changedetection.io/start), choose from different geographical locations, let us handle everything for you. 
+
 
 
 #### Example use cases
 
-- Products and services have a change in pricing
-- _Out of stock notification_ and _Back In stock notification_
-- Governmental department updates (changes are often only on their websites)
+Know when ...
+
+- Government department updates (changes are often only on their websites)
+- Local government news (changes are often only on their websites)
 - New software releases, security advisories when you're not on their mailing list.
 - Festivals with changes
 - Realestate listing changes
-- Know when your favourite whiskey is on sale, or other special deals are announced before anyone else
 - COVID related news from government websites
-- University/organisation news from their website
 - Detect and monitor changes in JSON API responses 
-- JSON API monitoring and alerting
-- Changes in legal and other documents
-- Trigger API calls via notifications when text appears on a website
-- Glue together APIs using the JSON filter and JSON notifications
-- Create RSS feeds based on changes in web content
-- Monitor HTML source code for unexpected changes, strengthen your PCI compliance
-- You have a very sensitive list of URLs to watch and you do _not_ want to use the paid alternatives. (Remember, _you_ are the product)
-
-_Need an actual Chrome runner with Javascript support? We support fetching via WebDriver and Playwright!</a>_
-
-#### Key Features
-
-- Lots of trigger filters, such as "Trigger on text", "Remove text by selector", "Ignore text", "Extract text", also using regular-expressions!
-- Target elements with xPath and CSS Selectors, Easily monitor complex JSON with JSONPath or jq
-- Switch between fast non-JS and Chrome JS based "fetchers"
-- Easily specify how often a site should be checked
-- Execute JS before extracting text (Good for logging in, see examples in the UI!)
-- Override Request Headers, Specify `POST` or `GET` and other methods
-- Use the "Visual Selector" to help target specific elements
+- API monitoring and alerting
 
+**Get monitoring now!**
 
 ```bash
-$ pip3 install changedetection.io
+$ pip3 install changedetection.io   
 ```
 
 Specify a target for the *datastore path* with `-d` (required) and a *listening port* with `-p` (defaults to `5000`)
@@ -54,5 +51,17 @@ $ changedetection.io -d /path/to/empty/data/dir -p 5000
 
 Then visit http://127.0.0.1:5000 , You should now be able to access the UI.
 
+### Features
+- Website monitoring
+- Change detection of content and analyses
+- Filters on change (Select by CSS or JSON)
+- Triggers (Wait for text, wait for regex)
+- Notification support
+- JSON API Monitoring
+- Parse JSON embedded in HTML
+- (Reverse) Proxy support
+- Javascript support via WebDriver
+- RaspberriPi (arm v6/v7/64 support)
+
 See https://github.com/dgtlmoon/changedetection.io for more information.
 

README.md

@@ -1,56 +1,38 @@
-## Web Site Change Detection, Monitoring and Notification.
-
-**_Detect website content changes and perform meaningful actions - trigger notifications via Discord, Email, Slack, Telegram, API calls and many more._**
-
-_Live your data-life pro-actively._ 
-
-
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start?src=github)
-
+#  changedetection.io
 [![Release Version][release-shield]][release-link] [![Docker Pulls][docker-pulls]][docker-link] [![License][license-shield]](LICENSE.md)
 
 ![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://lemonade.changedetection.io/start) , _half the price of other website change monitoring services and comes with unlimited watches & checks!_
+## Self-Hosted, Open Source, Change Monitoring of Web Pages
 
-- Chrome browser included.
-- Super fast, no registration needed setup.
-- Get started watching and receiving website change notifications straight away.
+_Know when web pages change! Stay ontop of new information!_ 
+
+Live your data-life *pro-actively* instead of *re-actively*.
+
+Free, Open-source web page monitoring, notification and change detection. Don't have time? [**Try our $6.99/month subscription - unlimited checks and watches!**](https://lemonade.changedetection.io/start)
 
 
-### Target specific parts of the webpage using the Visual Selector tool.
-
-Available when connected to a <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Playwright-content-fetcher">playwright content fetcher</a> (included as part of our subscription service)
-
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/visualselector-anim.gif" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />](https://lemonade.changedetection.io/start?src=github)
-
-### Easily see what changed, examine by word, line, or individual character.
-
-[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot-diff.png" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />](https://lemonade.changedetection.io/start?src=github)
+[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring"  title="Self-hosted web page change monitoring"  />](https://lemonade.changedetection.io/start)
 
 
-### Perform interactive browser steps
+**Get your own private instance now! Let us host it for you!**
 
-Fill in text boxes, click buttons and more, setup your changedetection scenario. 
-
-Using the **Browser Steps** configuration, add basic steps before performing change detection, such as logging into websites, adding a product to a cart, accept cookie logins, entering dates and refining searches.
-
-[<img src="docs/browsersteps-anim.gif" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Website change detection with interactive browser steps, login, cookies etc" />](https://lemonade.changedetection.io/start?src=github)
-
-After **Browser Steps** have been run, then visit the **Visual Selector** tab to refine the content you're interested in.
-Requires Playwright to be enabled.
+[**Try our $6.99/month subscription - unlimited checks and watches!**](https://lemonade.changedetection.io/start) , _half the price of other website change monitoring services and comes with unlimited watches & checks!_
 
 
-### Example use cases
+
+- Automatic Updates, Automatic Backups, No Heroku "paused application", don't miss a change!
+- Javascript browser included
+- Unlimited checks and watches!
+
+
+#### Example use cases
 
 - Products and services have a change in pricing
-- _Out of stock notification_ and _Back In stock notification_
-- Monitor and track PDF file changes, know when a PDF file has text changes.
 - Governmental department updates (changes are often only on their websites)
 - New software releases, security advisories when you're not on their mailing list.
 - Festivals with changes
 - Realestate listing changes
-- Know when your favourite whiskey is on sale, or other special deals are announced before anyone else
 - COVID related news from government websites
 - University/organisation news from their website
 - Detect and monitor changes in JSON API responses 
@@ -61,45 +43,31 @@ Requires Playwright to be enabled.
 - Create RSS feeds based on changes in web content
 - Monitor HTML source code for unexpected changes, strengthen your PCI compliance
 - You have a very sensitive list of URLs to watch and you do _not_ want to use the paid alternatives. (Remember, _you_ are the product)
-- Get notified when certain keywords appear in Twitter search results
-- Proactively search for jobs, get notified when companies update their careers page, search job portals for keywords.
 
-_Need an actual Chrome runner with Javascript support? We support fetching via WebDriver and Playwright!</a>_
+_Need an actual Chrome runner with Javascript support? We support fetching via WebDriver!</a>_
 
-#### Key Features
+## Screenshots
 
-- Lots of trigger filters, such as "Trigger on text", "Remove text by selector", "Ignore text", "Extract text", also using regular-expressions!
-- Target elements with xPath and CSS Selectors, Easily monitor complex JSON with JSONPath or jq
-- Switch between fast non-JS and Chrome JS based "fetchers"
-- Track changes in PDF files (Monitor text changed in the PDF, Also monitor PDF filesize and checksums)
-- Easily specify how often a site should be checked
-- Execute JS before extracting text (Good for logging in, see examples in the UI!)
-- Override Request Headers, Specify `POST` or `GET` and other methods
-- Use the "Visual Selector" to help target specific elements
-- Configurable [proxy per watch](https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration)
-- Send a screenshot with the notification when a change is detected in the web page
+Examining differences in content.
 
-We [recommend and use Bright Data](https://brightdata.grsm.io/n0r16zf7eivq) global proxy services, Bright Data will match any first deposit up to $100 using our signup link.
+<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/screenshot-diff.png" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference "  title="Self-hosted web page change monitoring context difference " />
 
 Please :star: star :star: this project and help it grow! https://github.com/dgtlmoon/changedetection.io/
 
+
 ## Installation
 
 ### Docker
 
 With Docker composer, just clone this repository and..
-
 ```bash
 $ docker-compose up -d
 ```
-
 Docker standalone
 ```bash
 $ docker run -d --restart always -p "127.0.0.1:5000:5000" -v datastore-volume:/datastore --name changedetection.io dgtlmoon/changedetection.io
 ```
 
-`:latest` tag is our latest stable release, `:dev` tag is our bleeding edge `master` branch.
-
 ### Windows
 
 See the install instructions at the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Microsoft-Windows
@@ -122,8 +90,8 @@ _Now with per-site configurable support for using a fast built in HTTP fetcher o
 ### Docker
 ```
 docker pull dgtlmoon/changedetection.io
-docker kill $(docker ps -a -f name=changedetection.io -q)
-docker rm $(docker ps -a -f name=changedetection.io -q)
+docker kill $(docker ps -a|grep changedetection.io|awk '{print $1}')
+docker rm $(docker ps -a|grep changedetection.io|awk '{print $1}')
 docker run -d --restart always -p "127.0.0.1:5000:5000" -v datastore-volume:/datastore --name changedetection.io dgtlmoon/changedetection.io
 ```
 
@@ -137,9 +105,9 @@ See the wiki for more information https://github.com/dgtlmoon/changedetection.io
 
 
 ## Filters
+XPath, JSONPath and CSS support comes baked in! You can be as specific as you need, use XPath exported from various XPath element query creation tools.
 
-XPath, JSONPath, jq, and CSS support comes baked in! You can be as specific as you need, use XPath exported from various XPath element query creation tools. 
-(We support LXML `re:test`, `re:math` and `re:replace`.)
+(We support LXML re:test, re:math and re:replace.)
 
 ## Notifications
 
@@ -161,71 +129,42 @@ Just some examples
  
 <a href="https://github.com/caronc/apprise#popular-notification-services">And everything else in this list!</a>
 
-<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot-notifications.png" style="max-width:100%;" alt="Self-hosted web page change monitoring notifications"  title="Self-hosted web page change monitoring notifications"  />
+<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/screenshot-notifications.png" style="max-width:100%;" alt="Self-hosted web page change monitoring notifications"  title="Self-hosted web page change monitoring notifications"  />
 
-Now you can also customise your notification content and use <a target="_new" href="https://jinja.palletsprojects.com/en/3.0.x/templates/">Jinja2 templating</a> for their title and body!
+Now you can also customise your notification content!
 
 ## JSON API Monitoring
 
-Detect changes and monitor data in JSON API's by using either JSONPath or jq to filter, parse, and restructure JSON as needed.
+Detect changes and monitor data in JSON API's by using the built-in JSONPath selectors as a filter / selector.
 
-![image](https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/json-filter-field-example.png)
+![image](https://user-images.githubusercontent.com/275001/125165842-0ce01980-e1dc-11eb-9e73-d8137dd162dc.png)
 
 This will re-parse the JSON and apply formatting to the text, making it super easy to monitor and detect changes in JSON API results
 
-![image](https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/json-diff-example.png)
-
-### JSONPath or jq?
-
-For more complex parsing, filtering, and modifying of JSON data, jq is recommended due to the built-in operators and functions. Refer to the [documentation](https://stedolan.github.io/jq/manual/) for more specifc information on jq.
-
-One big advantage of `jq` is that you can use logic in your JSON filter, such as filters to only show items that have a value greater than/less than etc.
-
-See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/JSON-Selector-Filter-help for more information and examples
+![image](https://user-images.githubusercontent.com/275001/125165995-d9ea5580-e1dc-11eb-8030-f0deced2661a.png)
 
 ### Parse JSON embedded in HTML!
 
-When you enable a `json:` or `jq:` filter, you can even automatically extract and parse embedded JSON inside a HTML page! Amazingly handy for sites that build content based on JSON, such as many e-commerce websites. 
+When you enable a `json:` filter, you can even automatically extract and parse embedded JSON inside a HTML page! Amazingly handy for sites that build content based on JSON, such as many e-commerce websites. 
 
 ```
 <html>
 ...
 <script type="application/ld+json">
-
-{
-   "@context":"http://schema.org/",
-   "@type":"Product",
-   "offers":{
-      "@type":"Offer",
-      "availability":"http://schema.org/InStock",
-      "price":"3949.99",
-      "priceCurrency":"USD",
-      "url":"https://www.newegg.com/p/3D5-000D-001T1"
-   },
-   "description":"Cobratype King Cobra Hero Desktop Gaming PC",
-   "name":"Cobratype King Cobra Hero Desktop Gaming PC",
-   "sku":"3D5-000D-001T1",
-   "itemCondition":"NewCondition"
-}
+  {"@context":"http://schema.org","@type":"Product","name":"Nan Optipro Stage 1 Baby Formula  800g","price": 23.50 }
 </script>
 ```  
 
-`json:$..price` or `jq:..price` would give `3949.99`, or you can extract the whole structure (use a JSONpath test website to validate with)
+`json:$.price` would give `23.50`, or you can extract the whole structure
 
-The application also supports notifying you that it can follow this information automatically
+## Proxy configuration
 
-
-## Proxy Configuration
-
-See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration , we also support using [BrightData proxy services where possible]( https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support)
+See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration
 
 ## Raspberry Pi support?
 
 Raspberry Pi and linux/arm/v6 linux/arm/v7 arm64 devices are supported! See the wiki for [details](https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver)
 
-## API Support
-
-Supports managing the website watch list [via our API](https://changedetection.io/docs/api_v1/index.html)
 
 ## Support us
 
@@ -238,7 +177,7 @@ Or directly donate an amount PayPal [![Donate](https://img.shields.io/badge/Dona
 
 Or BTC `1PLFN327GyUarpJd7nVe7Reqg9qHx5frNn`
 
-<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/btc-support.png" style="max-width:50%;" alt="Support us!"  />
+<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/btc-support.png" style="max-width:50%;" alt="Support us!"  />
 
 ## Commercial Support
 
@@ -250,5 +189,5 @@ I offer commercial support, this software is depended on by network security, ae
 [test-shield]: https://github.com/dgtlmoon/changedetection.io/actions/workflows/test-only.yml/badge.svg?branch=master
 
 [license-shield]: https://img.shields.io/github/license/dgtlmoon/changedetection.io.svg?style=for-the-badge
-[release-link]: https://github.com/dgtlmoon/changedetection.io/releases
+[release-link]: https://github.com/dgtlmoon.com/changedetection.io/releases
 [docker-link]: https://hub.docker.com/r/dgtlmoon/changedetection.io

changedetection.py

@@ -6,39 +6,6 @@
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
 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")
+    changedetection.main()

changedetectionio/.gitignore

@@ -1,2 +1 @@
 test-datastore
-package-lock.json

changedetectionio/api/api_schema.py

@@ -1,117 +0,0 @@
-# Responsible for building the storage dict into a set of rules ("JSON Schema") acceptable via the API
-# Probably other ways to solve this when the backend switches to some ORM
-
-def build_time_between_check_json_schema():
-    # Setup time between check schema
-    schema_properties_time_between_check = {
-        "type": "object",
-        "additionalProperties": False,
-        "properties": {}
-    }
-    for p in ['weeks', 'days', 'hours', 'minutes', 'seconds']:
-        schema_properties_time_between_check['properties'][p] = {
-            "anyOf": [
-                {
-                    "type": "integer"
-                },
-                {
-                    "type": "null"
-                }
-            ]
-        }
-
-    return schema_properties_time_between_check
-
-def build_watch_json_schema(d):
-    # Base JSON schema
-    schema = {
-        'type': 'object',
-        'properties': {},
-    }
-
-    for k, v in d.items():
-        # @todo 'integer' is not covered here because its almost always for internal usage
-
-        if isinstance(v, type(None)):
-            schema['properties'][k] = {
-                "anyOf": [
-                    {"type": "null"},
-                ]
-            }
-        elif isinstance(v, list):
-            schema['properties'][k] = {
-                "anyOf": [
-                    {"type": "array",
-                     # Always is an array of strings, like text or regex or something
-                     "items": {
-                         "type": "string",
-                         "maxLength": 5000
-                     }
-                     },
-                ]
-            }
-        elif isinstance(v, bool):
-            schema['properties'][k] = {
-                "anyOf": [
-                    {"type": "boolean"},
-                ]
-            }
-        elif isinstance(v, str):
-            schema['properties'][k] = {
-                "anyOf": [
-                    {"type": "string",
-                     "maxLength": 5000},
-                ]
-            }
-
-    # Can also be a string (or None by default above)
-    for v in ['body',
-              'notification_body',
-              'notification_format',
-              'notification_title',
-              'proxy',
-              'tag',
-              'title',
-              'webdriver_js_execute_code'
-              ]:
-        schema['properties'][v]['anyOf'].append({'type': 'string', "maxLength": 5000})
-
-    # None or Boolean
-    schema['properties']['track_ldjson_price_data']['anyOf'].append({'type': 'boolean'})
-
-    schema['properties']['method'] = {"type": "string",
-                                      "enum": ["GET", "POST", "DELETE", "PUT"]
-                                      }
-
-    schema['properties']['fetch_backend']['anyOf'].append({"type": "string",
-                                                           "enum": ["html_requests", "html_webdriver"]
-                                                           })
-
-
-
-    # All headers must be key/value type dict
-    schema['properties']['headers'] = {
-        "type": "object",
-        "patternProperties": {
-            # Should always be a string:string type value
-            ".*": {"type": "string"},
-        }
-    }
-
-    from changedetectionio.notification import valid_notification_formats
-
-    schema['properties']['notification_format'] = {'type': 'string',
-                                                   'enum': list(valid_notification_formats.keys())
-                                                   }
-
-    # Stuff that shouldn't be available but is just state-storage
-    for v in ['previous_md5', 'last_error', 'has_ldjson_price_data', 'previous_md5_before_filters', 'uuid']:
-        del schema['properties'][v]
-
-    schema['properties']['webdriver_delay']['anyOf'].append({'type': 'integer'})
-
-    schema['properties']['time_between_check'] = build_time_between_check_json_schema()
-
-    # headers ?
-    return schema
-

changedetectionio/api/api_v1.py

@@ -1,279 +0,0 @@
-from flask_expects_json import expects_json
-from changedetectionio import queuedWatchMetaData
-from flask_restful import abort, Resource
-from flask import request, make_response
-import validators
-from . import auth
-import copy
-
-# See docs/README.md for rebuilding the docs/apidoc information
-
-from . import api_schema
-
-# Build a JSON Schema atleast partially based on our Watch model
-from changedetectionio.model.Watch import base_config as watch_base_config
-schema = api_schema.build_watch_json_schema(watch_base_config)
-
-schema_create_watch = copy.deepcopy(schema)
-schema_create_watch['required'] = ['url']
-
-schema_update_watch = copy.deepcopy(schema)
-schema_update_watch['additionalProperties'] = False
-
-class Watch(Resource):
-    def __init__(self, **kwargs):
-        # datastore is a black box dependency
-        self.datastore = kwargs['datastore']
-        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>
-    # @todo - version2 - ?muted and ?paused should be able to be called together, return the watch struct not "OK"
-    # ?recheck=true
-    @auth.check_token
-    def get(self, uuid):
-        """
-        @api {get} /api/v1/watch/:uuid Single watch information
-        @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"
-        @apiName Watch
-        @apiGroup Watch
-        @apiParam {uuid} uuid Watch unique ID.
-        @apiQuery {Boolean} [recheck] Recheck this watch `recheck=1`
-        @apiQuery {String} [paused] =`paused` or =`unpaused` , Sets the PAUSED state
-        @apiQuery {String} [muted] =`muted` or =`unmuted` , Sets the MUTE NOTIFICATIONS state
-        @apiSuccess (200) {String} OK When paused/muted/recheck operation OR full JSON object of the watch
-        @apiSuccess (200) {JSON} WatchJSON JSON Full JSON object of the watch
-        """
-        from copy import deepcopy
-        watch = deepcopy(self.datastore.data['watching'].get(uuid))
-        if not watch:
-            abort(404, message='No watch exists with the UUID of {}'.format(uuid))
-
-        if request.args.get('recheck'):
-            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
-            return "OK", 200
-        if request.args.get('paused', '') == 'paused':
-            self.datastore.data['watching'].get(uuid).pause()
-            return "OK", 200
-        elif request.args.get('paused', '') == 'unpaused':
-            self.datastore.data['watching'].get(uuid).unpause()
-            return "OK", 200
-        if request.args.get('muted', '') == 'muted':
-            self.datastore.data['watching'].get(uuid).mute()
-            return "OK", 200
-        elif request.args.get('muted', '') == 'unmuted':
-            self.datastore.data['watching'].get(uuid).unmute()
-            return "OK", 200
-
-        # Return without history, get that via another API call
-        watch['history_n'] = watch.history_n
-        return watch
-
-    @auth.check_token
-    def delete(self, uuid):
-        """
-        @api {delete} /api/v1/watch/:uuid Delete watch information
-        @apiExample {curl} Example usage:
-            curl http://localhost:4000/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
-        @apiSuccess (200) {String} OK Was deleted
-        """
-        if not self.datastore.data['watching'].get(uuid):
-            abort(400, message='No watch exists with the UUID of {}'.format(uuid))
-
-        self.datastore.delete(uuid)
-        return 'OK', 204
-
-    # Update an existing
-    @auth.check_token
-    @expects_json(schema_update_watch)
-    def put(self, uuid):
-        """
-        @api {put} /api/v1/watch/:uuid Update watch information
-        @apiExample {curl} Example usage:
-            Create a watch (POST)
-            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"}'
-            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"}'
-
-        @apiDescription Updates an existing watch using JSON, accepts the same structure as at https://github.com/dgtlmoon/changedetection.io/blob/fab7d325f764d6912bef671f1d78bf217689c537/changedetectionio/model/Watch.py#L15
-        @apiParam {uuid} uuid Watch unique ID.
-        @apiName Update
-        @apiGroup Watch
-        @apiSuccess (200) {String} OK Was updated
-        @apiSuccess (500) {String} ERR Some other error
-        """
-        watch = self.datastore.data['watching'].get(uuid)
-        if not watch:
-            abort(404, message='No watch exists with the UUID of {}'.format(uuid))
-
-        if request.json.get('proxy'):
-            plist = self.datastore.proxy_list
-            if not request.json.get('proxy') in plist:
-                return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
-
-        watch.update(request.json)
-
-        return "OK", 200
-
-
-class WatchHistory(Resource):
-    def __init__(self, **kwargs):
-        # datastore is a black box dependency
-        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
-    def get(self, uuid):
-        watch = self.datastore.data['watching'].get(uuid)
-        if not watch:
-            abort(404, message='No watch exists with the UUID of {}'.format(uuid))
-        return watch.history, 200
-
-
-class WatchSingleHistory(Resource):
-    def __init__(self, **kwargs):
-        # datastore is a black box dependency
-        self.datastore = kwargs['datastore']
-
-    # Read a given history snapshot and return its content
-    # <string:timestamp> or "latest"
-    # curl http://localhost:4000/api/v1/watch/<string:uuid>/history/<int:timestamp>
-    @auth.check_token
-    def get(self, uuid, timestamp):
-        watch = self.datastore.data['watching'].get(uuid)
-        if not watch:
-            abort(404, message='No watch exists with the UUID of {}'.format(uuid))
-
-        if not len(watch.history):
-            abort(404, message='Watch found but no history exists for the UUID {}'.format(uuid))
-
-        if timestamp == 'latest':
-            timestamp = list(watch.history.keys())[-1]
-
-        with open(watch.history[timestamp], 'r') as f:
-            content = f.read()
-
-        response = make_response(content, 200)
-        response.mimetype = "text/plain"
-        return response
-
-
-class CreateWatch(Resource):
-    def __init__(self, **kwargs):
-        # datastore is a black box dependency
-        self.datastore = kwargs['datastore']
-        self.update_q = kwargs['update_q']
-
-    @auth.check_token
-    @expects_json(schema_create_watch)
-    def post(self):
-        """
-        @api {post} /api/v1/watch Create a watch
-        @apiDescription requires `url`, Creates a watch, also accepts accepts the same structure as at https://github.com/dgtlmoon/changedetection.io/blob/fab7d325f764d6912bef671f1d78bf217689c537/changedetectionio/model/Watch.py#L15
-        @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"}'
-        @apiName Create
-        @apiGroup CreateWatch
-        @apiSuccess (200) {String} OK Was created
-        @apiSuccess (500) {String} ERR Some other error
-        """
-
-        #
-        json_data = request.get_json()
-        url = json_data['url'].strip()
-
-
-        if not validators.url(json_data['url'].strip()):
-            return "Invalid or unsupported URL", 400
-
-        if json_data.get('proxy'):
-            plist = self.datastore.proxy_list
-            if not json_data.get('proxy') in plist:
-                return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
-
-        extras = copy.deepcopy(json_data)
-        del extras['url']
-
-        new_uuid = self.datastore.add_watch(url=url, extras=extras)
-        if new_uuid:
-            self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
-            return {'uuid': new_uuid}, 201
-        else:
-            return "Invalid or unsupported URL", 400
-
-    @auth.check_token
-    def get(self):
-        """
-        @api {get} /api/v1/watch
-        @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"
-            recheck_all=1 to recheck all
-        @apiParam {String} [recheck_all]       Optional Set to =1 to force recheck of all watches
-        @apiParam {String} [tag]               Optional name of tag to limit results
-        @apiName ListWatches
-        @apiGroup CreateWatch
-
-        :return:
-        """
-        list = {}
-
-        tag_limit = request.args.get('tag', None)
-        for k, watch in self.datastore.data['watching'].items():
-            if tag_limit:
-                if not tag_limit.lower() in watch.all_tags:
-                    continue
-
-            list[k] = {'url': watch['url'],
-                       'title': watch['title'],
-                       'last_checked': watch['last_checked'],
-                       'last_changed': watch.last_changed,
-                       'last_error': watch['last_error']}
-
-        if request.args.get('recheck_all'):
-            for uuid in self.datastore.data['watching'].keys():
-                self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
-            return {'status': "OK"}, 200
-
-        return list, 200
-
-class SystemInfo(Resource):
-    def __init__(self, **kwargs):
-        # datastore is a black box dependency
-        self.datastore = kwargs['datastore']
-        self.update_q = kwargs['update_q']
-
-    @auth.check_token
-    def get(self):
-        import time
-        overdue_watches = []
-
-        # Check all watches and report which have not been checked but should have been
-
-        for uuid, watch in self.datastore.data.get('watching', {}).items():
-            # see if now - last_checked is greater than the time that should have been
-            # this is not super accurate (maybe they just edited it) but better than nothing
-            t = watch.threshold_seconds()
-            if not t:
-                # Use the system wide default
-                t = self.datastore.threshold_seconds
-
-            time_since_check = time.time() - watch.get('last_checked')
-
-            # Allow 5 minutes of grace time before we decide it's overdue
-            if time_since_check - (5 * 60) > t:
-                overdue_watches.append(uuid)
-
-        return {
-                   'queue_size': self.update_q.qsize(),
-                   'overdue_watches': overdue_watches,
-                   'uptime': round(time.time() - self.datastore.start_time, 2),
-                   'watch_count': len(self.datastore.data.get('watching', {}))
-               }, 200

changedetectionio/api/auth.py

@@ -1,33 +0,0 @@
-from flask import request, make_response, jsonify
-from functools import wraps
-
-
-# Simple API auth key comparison
-# @todo - Maybe short lived token in the future?
-
-def check_token(f):
-    @wraps(f)
-    def decorated(*args, **kwargs):
-        datastore = args[0].datastore
-
-        config_api_token_enabled = datastore.data['settings']['application'].get('api_access_token_enabled')
-        if not config_api_token_enabled:
-            return
-
-        try:
-            api_key_header = request.headers['x-api-key']
-        except KeyError:
-            return make_response(
-                jsonify("No authorization x-api-key header."), 403
-            )
-
-        config_api_token = datastore.data['settings']['application'].get('api_access_token')
-
-        if api_key_header != config_api_token:
-            return make_response(
-                jsonify("Invalid access - API key invalid."), 403
-            )
-
-        return f(*args, **kwargs)
-
-    return decorated

changedetectionio/apprise_asset.py

@@ -1,11 +0,0 @@
-import apprise
-
-# Create our AppriseAsset and populate it with some of our new values:
-# https://github.com/caronc/apprise/wiki/Development_API#the-apprise-asset-object
-asset = apprise.AppriseAsset(
-   image_url_logo='https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png'
-)
-
-asset.app_id = "changedetection.io"
-asset.app_desc = "ChangeDetection.io best and simplest website monitoring and change detection"
-asset.app_url = "https://changedetection.io"

changedetectionio/blueprint/browser_steps/__init__.py

@@ -1,230 +0,0 @@
-
-# HORRIBLE HACK BUT WORKS :-) PR anyone?
-#
-# Why?
-# `browsersteps_playwright_browser_interface.chromium.connect_over_cdp()` will only run once without async()
-# - this flask app is not async()
-# - browserless has a single timeout/keepalive which applies to the session made at .connect_over_cdp()
-#
-# So it means that we must unfortunately for now just keep a single timer since .connect_over_cdp() was run
-# and know when that reaches timeout/keepalive :( when that time is up, restart the connection and tell the user
-# that their time is up, insert another coin. (reload)
-#
-# Bigger picture
-# - It's horrible that we have this click+wait deal, some nice socket.io solution using something similar
-# to what the browserless debug UI already gives us would be smarter..
-#
-# OR
-# - Some API call that should be hacked into browserless or playwright that we can "/api/bump-keepalive/{session_id}/60"
-# So we can tell it that we need more time (run this on each action)
-#
-# OR
-# - use multiprocessing to bump this over to its own process and add some transport layer (queue/pipes)
-
-from distutils.util import strtobool
-from flask import Blueprint, request, make_response
-import os
-import logging
-from changedetectionio.store import ChangeDetectionStore
-from changedetectionio import login_optionally_required
-browsersteps_live_ui_o = {}
-browsersteps_playwright_browser_interface = None
-browsersteps_playwright_browser_interface_browser = None
-browsersteps_playwright_browser_interface_context = None
-browsersteps_playwright_browser_interface_end_time = None
-browsersteps_playwright_browser_interface_start_time = None
-
-def cleanup_playwright_session():
-
-    global browsersteps_live_ui_o
-    global browsersteps_playwright_browser_interface
-    global browsersteps_playwright_browser_interface_browser
-    global browsersteps_playwright_browser_interface_context
-    global browsersteps_playwright_browser_interface_end_time
-    global browsersteps_playwright_browser_interface_start_time
-
-    browsersteps_live_ui_o = {}
-    browsersteps_playwright_browser_interface = None
-    browsersteps_playwright_browser_interface_browser = None
-    browsersteps_playwright_browser_interface_end_time = None
-    browsersteps_playwright_browser_interface_start_time = None
-
-    print("Cleaning up old playwright session because time was up, calling .goodbye()")
-    try:
-        browsersteps_playwright_browser_interface_context.goodbye()
-    except Exception as e:
-        print ("Got exception in shutdown, probably OK")
-        print (str(e))
-
-    browsersteps_playwright_browser_interface_context = None
-
-    print ("Cleaning up old playwright session because time was up - done")
-
-def construct_blueprint(datastore: ChangeDetectionStore):
-
-    browser_steps_blueprint = Blueprint('browser_steps', __name__, template_folder="templates")
-
-    @login_optionally_required
-    @browser_steps_blueprint.route("/browsersteps_update", methods=['GET', 'POST'])
-    def browsersteps_ui_update():
-        import base64
-        import playwright._impl._api_types
-        import time
-
-        from changedetectionio.blueprint.browser_steps import browser_steps
-
-        global browsersteps_live_ui_o, browsersteps_playwright_browser_interface_end_time
-        global browsersteps_playwright_browser_interface_browser
-        global browsersteps_playwright_browser_interface
-        global browsersteps_playwright_browser_interface_start_time
-
-        step_n = None
-        remaining =0
-        uuid = request.args.get('uuid')
-
-        browsersteps_session_id = request.args.get('browsersteps_session_id')
-
-        if not browsersteps_session_id:
-            return make_response('No browsersteps_session_id specified', 500)
-
-        # Because we don't "really" run in a context manager ( we make the playwright interface global/long-living )
-        # We need to manage the shutdown when the time is up
-        if browsersteps_playwright_browser_interface_end_time:
-            remaining = browsersteps_playwright_browser_interface_end_time-time.time()
-            if browsersteps_playwright_browser_interface_end_time and remaining <= 0:
-                cleanup_playwright_session()
-                return make_response('Browser session expired, please reload the Browser Steps interface', 401)
-
-        # Actions - step/apply/etc, do the thing and return state
-        if request.method == 'POST':
-            # @todo - should always be an existing session
-            step_operation = request.form.get('operation')
-            step_selector = request.form.get('selector')
-            step_optional_value = request.form.get('optional_value')
-            step_n = int(request.form.get('step_n'))
-            is_last_step = strtobool(request.form.get('is_last_step'))
-
-            if step_operation == 'Goto site':
-                step_operation = 'goto_url'
-                step_optional_value = None
-                step_selector = datastore.data['watching'][uuid].get('url')
-
-            # @todo try.. accept.. nice errors not popups..
-            try:
-
-                this_session = browsersteps_live_ui_o.get(browsersteps_session_id)
-                if not this_session:
-                    print("Browser exited")
-                    return make_response('Browser session ran out of time :( Please reload this page.', 401)
-
-                this_session.call_action(action_name=step_operation,
-                                         selector=step_selector,
-                                         optional_value=step_optional_value)
-
-            except Exception as e:
-                print("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)
-
-            # Get visual selector ready/update its data (also use the current filter info from the page?)
-            # When the last 'apply' button was pressed
-            # @todo this adds overhead because the xpath selection is happening twice
-            u = this_session.page.url
-            if is_last_step and u:
-                (screenshot, xpath_data) = this_session.request_visualselector_data()
-                datastore.save_screenshot(watch_uuid=uuid, screenshot=screenshot)
-                datastore.save_xpath_data(watch_uuid=uuid, data=xpath_data)
-
-        # Setup interface
-        if request.method == 'GET':
-
-            if not browsersteps_playwright_browser_interface:
-                print("Starting connection with playwright")
-                logging.debug("browser_steps.py connecting")
-
-                global browsersteps_playwright_browser_interface_context
-                from . import nonContext
-                browsersteps_playwright_browser_interface_context = nonContext.c_sync_playwright()
-                browsersteps_playwright_browser_interface = browsersteps_playwright_browser_interface_context.start()
-
-                time.sleep(1)
-                # At 20 minutes, some other variable is closing it
-                # @todo find out what it is and set it
-                seconds_keepalive = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
-
-                # keep it alive for 10 seconds more than we advertise, sometimes it helps to keep it shutting down cleanly
-                keepalive = "&timeout={}".format(((seconds_keepalive+3) * 1000))
-                try:
-                    browsersteps_playwright_browser_interface_browser = browsersteps_playwright_browser_interface.chromium.connect_over_cdp(
-                        os.getenv('PLAYWRIGHT_DRIVER_URL', '') + keepalive)
-                except Exception as e:
-                    if 'ECONNREFUSED' in str(e):
-                        return make_response('Unable to start the Playwright session properly, is it running?', 401)
-
-                browsersteps_playwright_browser_interface_end_time = time.time() + (seconds_keepalive-3)
-                print("Starting connection with playwright - done")
-
-            if not browsersteps_live_ui_o.get(browsersteps_session_id):
-                # Boot up a new session
-                proxy_id = datastore.get_preferred_proxy_for_watch(uuid=uuid)
-                proxy = None
-                if proxy_id:
-                    proxy_url = datastore.proxy_list.get(proxy_id).get('url')
-                    if proxy_url:
-                        proxy = {'server': proxy_url}
-                        print("Browser Steps: UUID {} Using proxy {}".format(uuid, proxy_url))
-
-                # Begin the new "Playwright Context" that re-uses the playwright interface
-                # Each session is a "Playwright Context" as a list, that uses the playwright interface
-                browsersteps_live_ui_o[browsersteps_session_id] = browser_steps.browsersteps_live_ui(
-                    playwright_browser=browsersteps_playwright_browser_interface_browser,
-                    proxy=proxy)
-                this_session = browsersteps_live_ui_o[browsersteps_session_id]
-
-        if not this_session.page:
-            cleanup_playwright_session()
-            return make_response('Browser session ran out of time :( Please reload this page.', 401)
-
-        response = None
-
-        if request.method == 'POST':
-            # Screenshots and other info only needed on requesting a step (POST)
-            try:
-                state = this_session.get_current_state()
-            except playwright._impl._api_types.Error as e:
-                return make_response("Browser session ran out of time :( Please reload this page."+str(e), 401)
-
-            # Use send_file() which is way faster than read/write loop on bytes
-            import json
-            from tempfile import mkstemp
-            from flask import send_file
-            tmp_fd, tmp_file = mkstemp(text=True, suffix=".json", prefix="changedetectionio-")
-
-            output = json.dumps({'screenshot': "data:image/jpeg;base64,{}".format(
-                base64.b64encode(state[0]).decode('ascii')),
-                'xpath_data': state[1],
-                'session_age_start': this_session.age_start,
-                'browser_time_remaining': round(remaining)
-            })
-
-            with os.fdopen(tmp_fd, 'w') as f:
-                f.write(output)
-
-            response = make_response(send_file(path_or_file=tmp_file,
-                                               mimetype='application/json; charset=UTF-8',
-                                               etag=True))
-            # No longer needed
-            os.unlink(tmp_file)
-
-        elif request.method == 'GET':
-            # Just enough to get the session rolling, it will call for goto-site via POST next
-            response = make_response({
-                'session_age_start': this_session.age_start,
-                'browser_time_remaining': round(remaining)
-            })
-
-        return response
-
-    return browser_steps_blueprint
-
-

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -1,268 +0,0 @@
-#!/usr/bin/python3
-
-import os
-import time
-import re
-from random import randint
-
-# Two flags, tell the JS which of the "Selector" or "Value" field should be enabled in the front end
-# 0- off, 1- on
-browser_step_ui_config = {'Choose one': '0 0',
-                          #                 'Check checkbox': '1 0',
-                          #                 'Click button containing text': '0 1',
-                          #                 'Scroll to bottom': '0 0',
-                          #                 'Scroll to element': '1 0',
-                          #                 'Scroll to top': '0 0',
-                          #                 'Switch to iFrame by index number': '0 1'
-                          #                 'Uncheck checkbox': '1 0',
-                          # @todo
-                          'Check checkbox': '1 0',
-                          'Click X,Y': '0 1',
-                          'Click element if exists': '1 0',
-                          'Click element': '1 0',
-                          'Click element containing text': '0 1',
-                          'Enter text in field': '1 1',
-                          'Execute JS': '0 1',
-#                          'Extract text and use as filter': '1 0',
-                          'Goto site': '0 0',
-                          'Press Enter': '0 0',
-                          'Select by label': '1 1',
-                          'Scroll down': '0 0',
-                          'Uncheck checkbox': '1 0',
-                          'Wait for seconds': '0 1',
-                          'Wait for text': '0 1',
-                          #                          'Press Page Down': '0 0',
-                          #                          'Press Page Up': '0 0',
-                          # weird bug, come back to it later
-                          }
-
-
-# Good reference - https://playwright.dev/python/docs/input
-#                  https://pythonmana.com/2021/12/202112162236307035.html
-#
-# ONLY Works in Playwright because we need the fullscreen screenshot
-class steppable_browser_interface():
-    page = None
-
-    # Convert and perform "Click Button" for example
-    def call_action(self, action_name, selector=None, optional_value=None):
-        now = time.time()
-        call_action_name = re.sub('[^0-9a-zA-Z]+', '_', action_name.lower())
-        if call_action_name == 'choose_one':
-            return
-
-        print("> action calling", call_action_name)
-        # https://playwright.dev/python/docs/selectors#xpath-selectors
-        if selector.startswith('/') and not selector.startswith('//'):
-            selector = "xpath=" + selector
-
-        action_handler = getattr(self, "action_" + call_action_name)
-
-        # Support for Jinja2 variables in the value and selector
-        from jinja2 import Environment
-        jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
-
-        if selector and ('{%' in selector or '{{' in selector):
-            selector = str(jinja2_env.from_string(selector).render())
-
-        if optional_value and ('{%' in optional_value or '{{' in optional_value):
-            optional_value = str(jinja2_env.from_string(optional_value).render())
-
-        action_handler(selector, optional_value)
-        self.page.wait_for_timeout(3 * 1000)
-        print("Call action done in", time.time() - now)
-
-    def action_goto_url(self, url, optional_value):
-        # self.page.set_viewport_size({"width": 1280, "height": 5000})
-        now = time.time()
-        response = self.page.goto(url, timeout=0, wait_until='commit')
-
-        # Wait_until = commit
-        # - `'commit'` - consider operation to be finished when network response is received and the document started loading.
-        # Better to not use any smarts from Playwright and just wait an arbitrary number of seconds
-        # This seemed to solve nearly all 'TimeoutErrors'
-        print("Time to goto URL ", time.time() - now)
-
-    def action_click_element_containing_text(self, selector=None, value=''):
-        if not len(value.strip()):
-            return
-        elem = self.page.get_by_text(value)
-        if elem.count():
-            elem.first.click(delay=randint(200, 500), timeout=3000)
-
-    def action_enter_text_in_field(self, selector, value):
-        if not len(selector.strip()):
-            return
-
-        self.page.fill(selector, value, timeout=10 * 1000)
-
-    def action_execute_js(self, selector, value):
-        self.page.evaluate(value)
-
-    def action_click_element(self, selector, value):
-        print("Clicking element")
-        if not len(selector.strip()):
-            return
-        self.page.click(selector, timeout=10 * 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")
-        if not len(selector.strip()):
-            return
-        try:
-            self.page.click(selector, timeout=10 * 1000, delay=randint(200, 500))
-        except _api_types.TimeoutError as e:
-            return
-        except _api_types.Error as e:
-            # Element was there, but page redrew and now its long long gone
-            return
-
-    def action_click_x_y(self, selector, value):
-        x, y = value.strip().split(',')
-        x = int(float(x.strip()))
-        y = int(float(y.strip()))
-        self.page.mouse.click(x=x, y=y, delay=randint(200, 500))
-
-    def action_scroll_down(self, selector, value):
-        # Some sites this doesnt work on for some reason
-        self.page.mouse.wheel(0, 600)
-        self.page.wait_for_timeout(1000)
-
-    def action_wait_for_seconds(self, selector, value):
-        self.page.wait_for_timeout(int(value) * 1000)
-
-    # @todo - in the future make some popout interface to capture what needs to be set
-    # https://playwright.dev/python/docs/api/class-keyboard
-    def action_press_enter(self, selector, value):
-        self.page.keyboard.press("Enter", delay=randint(200, 500))
-
-    def action_press_page_up(self, selector, value):
-        self.page.keyboard.press("PageUp", delay=randint(200, 500))
-
-    def action_press_page_down(self, selector, value):
-        self.page.keyboard.press("PageDown", delay=randint(200, 500))
-
-    def action_check_checkbox(self, selector, value):
-        self.page.locator(selector).check(timeout=1000)
-
-    def action_uncheck_checkbox(self, selector, value):
-        self.page.locator(selector, timeout=1000).uncheck(timeout=1000)
-
-
-# Responsible for maintaining a live 'context' with browserless
-# @todo - how long do contexts live for anyway?
-class browsersteps_live_ui(steppable_browser_interface):
-    context = None
-    page = None
-    render_extra_delay = 1
-    stale = False
-    # bump and kill this if idle after X sec
-    age_start = 0
-
-    # use a special driver, maybe locally etc
-    command_executor = os.getenv(
-        "PLAYWRIGHT_BROWSERSTEPS_DRIVER_URL"
-    )
-    # if not..
-    if not command_executor:
-        command_executor = os.getenv(
-            "PLAYWRIGHT_DRIVER_URL",
-            'ws://playwright-chrome:3000'
-        ).strip('"')
-
-    browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
-
-    def __init__(self, playwright_browser, proxy=None):
-        self.age_start = time.time()
-        self.playwright_browser = playwright_browser
-        if self.context is None:
-            self.connect(proxy=proxy)
-
-    # Connect and setup a new context
-    def connect(self, proxy=None):
-        # Should only get called once - test that
-        keep_open = 1000 * 60 * 5
-        now = time.time()
-
-        # @todo handle multiple contexts, bind a unique id from the browser on each req?
-        self.context = self.playwright_browser.new_context(
-            # @todo
-            #                user_agent=request_headers['User-Agent'] if request_headers.get('User-Agent') else 'Mozilla/5.0',
-            #               proxy=self.proxy,
-            # This is needed to enable JavaScript execution on GitHub and others
-            bypass_csp=True,
-            # Should never be needed
-            accept_downloads=False,
-            proxy=proxy
-        )
-
-        self.page = self.context.new_page()
-
-        # self.page.set_default_navigation_timeout(keep_open)
-        self.page.set_default_timeout(keep_open)
-        # @todo probably this doesnt work
-        self.page.on(
-            "close",
-            self.mark_as_closed,
-        )
-        # 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)
-        self.page.wait_for_timeout(1 * 1000)
-
-    def mark_as_closed(self):
-        print("Page closed, cleaning up..")
-
-    @property
-    def has_expired(self):
-        if not self.page:
-            return True
-
-
-    def get_current_state(self):
-        """Return the screenshot and interactive elements mapping, generally always called after action_()"""
-        from pkg_resources import resource_string
-        xpath_element_js = resource_string(__name__, "../../res/xpath_element_scraper.js").decode('utf-8')
-        now = time.time()
-        self.page.wait_for_timeout(1 * 1000)
-
-        # The actual screenshot
-        screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=40)
-
-        self.page.evaluate("var include_filters=''")
-        # Go find the interactive elements
-        # @todo in the future, something smarter that can scan for elements with .click/focus etc event handlers?
-        elements = 'a,button,input,select,textarea,i,th,td,p,li,h1,h2,h3,h4,div,span'
-        xpath_element_js = xpath_element_js.replace('%ELEMENTS%', elements)
-        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)
-        # except
-        # playwright._impl._api_types.Error: Browser closed.
-        # @todo show some countdown timer?
-        return (screenshot, xpath_data)
-
-    def request_visualselector_data(self):
-        """
-        Does the same that the playwright operation in content_fetcher does
-        This is used to just bump the VisualSelector data so it' ready to go if they click on the tab
-        @todo refactor and remove duplicate code, add include_filters
-        :param xpath_data:
-        :param screenshot:
-        :param current_include_filters:
-        :return:
-        """
-
-        self.page.evaluate("var include_filters=''")
-        from pkg_resources import resource_string
-        # The code that scrapes elements and makes a list of elements/size/position to click on in the VisualSelector
-        xpath_element_js = resource_string(__name__, "../../res/xpath_element_scraper.js").decode('utf-8')
-        from changedetectionio.content_fetcher import visualselector_xpath_selectors
-        xpath_element_js = xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors)
-        xpath_data = self.page.evaluate("async () => {" + xpath_element_js + "}")
-        screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
-
-        return (screenshot, xpath_data)

changedetectionio/blueprint/browser_steps/nonContext.py

@@ -1,18 +0,0 @@
-from playwright.sync_api import PlaywrightContextManager
-import asyncio
-
-# So playwright wants to run as a context manager, but we do something horrible and hacky
-# we are holding the session open for as long as possible, then shutting it down, and opening a new one
-# So it means we don't get to use PlaywrightContextManager' __enter__ __exit__
-# To work around this, make goodbye() act the same as the __exit__()
-#
-# But actually I think this is because the context is opened correctly with __enter__() but we timeout the connection
-# then theres some lock condition where we cant destroy it without it hanging
-
-class c_PlaywrightContextManager(PlaywrightContextManager):
-
-    def goodbye(self) -> None:
-        self.__exit__()
-
-def c_sync_playwright() -> PlaywrightContextManager:
-    return c_PlaywrightContextManager()

changedetectionio/blueprint/price_data_follower/__init__.py

@@ -1,33 +0,0 @@
-
-from distutils.util import strtobool
-from flask import Blueprint, flash, redirect, url_for
-from flask_login import login_required
-from changedetectionio.store import ChangeDetectionStore
-from changedetectionio import queuedWatchMetaData
-from queue import PriorityQueue
-
-PRICE_DATA_TRACK_ACCEPT = 'accepted'
-PRICE_DATA_TRACK_REJECT = 'rejected'
-
-def construct_blueprint(datastore: ChangeDetectionStore, update_q: PriorityQueue):
-
-    price_data_follower_blueprint = Blueprint('price_data_follower', __name__)
-
-    @login_required
-    @price_data_follower_blueprint.route("/<string:uuid>/accept", methods=['GET'])
-    def accept(uuid):
-        datastore.data['watching'][uuid]['track_ldjson_price_data'] = PRICE_DATA_TRACK_ACCEPT
-        update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
-        return redirect(url_for("form_watch_checknow", uuid=uuid))
-
-
-    @login_required
-    @price_data_follower_blueprint.route("/<string:uuid>/reject", methods=['GET'])
-    def reject(uuid):
-        datastore.data['watching'][uuid]['track_ldjson_price_data'] = PRICE_DATA_TRACK_REJECT
-        return redirect(url_for("index"))
-
-
-    return price_data_follower_blueprint
-
-

changedetectionio/changedetection.py

@@ -2,42 +2,21 @@
 
 # Launch as a eventlet.wsgi server instance.
 
-from distutils.util import strtobool
-from json.decoder import JSONDecodeError
+import getopt
+import os
+import sys
 
 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
+    host = ''
+    port = os.environ.get('PORT') or 5000
+    do_cleanup = False
+    datastore_path = None
 
     # On Windows, create and use a default path.
     if os.name == 'nt':
@@ -48,7 +27,7 @@ def main():
         datastore_path = os.path.join(os.getcwd(), "../datastore")
 
     try:
-        opts, args = getopt.getopt(sys.argv[1:], "6Ccsd:h:p:", "port")
+        opts, args = getopt.getopt(sys.argv[1:], "Ccsd:h:p:", "port")
     except getopt.GetoptError:
         print('backend.py -s SSL enable -h [host] -p [port] -d [datastore path]')
         sys.exit(2)
@@ -56,6 +35,11 @@ def main():
     create_datastore_dir = False
 
     for opt, arg in opts:
+        #        if opt == '--purge':
+        # Remove history, the actual files you need to delete manually.
+        #            for uuid, watch in datastore.data['watching'].items():
+        #                watch.update({'history': {}, 'last_checked': 0, 'last_changed': 0, 'previous_md5': None})
+
         if opt == '-s':
             ssl_mode = True
 
@@ -68,10 +52,6 @@ def main():
         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
@@ -92,18 +72,9 @@ def main():
                 "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
-
+    datastore = store.ChangeDetectionStore(datastore_path=app_config['datastore_path'], version_tag=__version__)
     app = changedetection_app(app_config, datastore)
 
-    signal.signal(signal.SIGTERM, sigterm_handler)
-
     # Go into cleanup mode
     if do_cleanup:
         datastore.remove_unused_snapshots()
@@ -118,15 +89,6 @@ def main():
                     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
@@ -139,15 +101,14 @@ def main():
         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),
+        eventlet.wsgi.server(eventlet.wrap_ssl(eventlet.listen((host, port)),
                                                certfile='cert.pem',
                                                keyfile='privkey.pem',
                                                server_side=True), app)
 
     else:
-        eventlet.wsgi.server(eventlet.listen((host, int(port)), s_type), app)
+        eventlet.wsgi.server(eventlet.listen((host, int(port))), app)
+
 

changedetectionio/content_fetcher.py

@@ -1,110 +1,33 @@
-import hashlib
-from abc import abstractmethod
+from abc import ABC, abstractmethod
 import chardet
-import json
-import logging
 import os
 import requests
-import sys
 import time
+import urllib3.exceptions
+import sys
 
-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'
-
-class Non200ErrorCodeReceived(Exception):
-    def __init__(self, status_code, url, screenshot=None, xpath_data=None, page_html=None):
-        # Set this so we can use it in other parts of the app
-        self.status_code = status_code
-        self.url = url
-        self.screenshot = screenshot
-        self.xpath_data = xpath_data
-        self.page_text = None
-
-        if page_html:
-            from changedetectionio import html_tools
-            self.page_text = html_tools.html_to_text(page_html)
-        return
-
-class checksumFromPreviousCheckWasTheSame(Exception):
-    def __init__(self):
-        return
-
-class JSActionExceptions(Exception):
-    def __init__(self, status_code, url, screenshot, message=''):
-        self.status_code = status_code
-        self.url = url
-        self.screenshot = screenshot
-        self.message = message
-        return
-
-class BrowserStepsStepTimout(Exception):
-    def __init__(self, step_n):
-        self.step_n = step_n
-        return
-
-
-class PageUnloadable(Exception):
-    def __init__(self, status_code, url, message, screenshot=False):
-        # Set this so we can use it in other parts of the app
-        self.status_code = status_code
-        self.url = url
-        self.screenshot = screenshot
-        self.message = message
-        return
 
 class EmptyReply(Exception):
-    def __init__(self, status_code, url, screenshot=None):
+    def __init__(self, status_code, url):
         # Set this so we can use it in other parts of the app
         self.status_code = status_code
         self.url = url
-        self.screenshot = screenshot
         return
 
-class ScreenshotUnavailable(Exception):
-    def __init__(self, status_code, url, page_html=None):
-        # Set this so we can use it in other parts of the app
-        self.status_code = status_code
-        self.url = url
-        if page_html:
-            from html_tools import html_to_text
-            self.page_text = html_to_text(page_html)
-        return
+    pass
 
-class ReplyWithContentButNoText(Exception):
-    def __init__(self, status_code, url, screenshot=None):
-        # Set this so we can use it in other parts of the app
-        self.status_code = status_code
-        self.url = url
-        self.screenshot = screenshot
-        return
 
 class Fetcher():
     error = None
     status_code = None
     content = None
     headers = None
-    browser_steps = None
-    browser_steps_screenshot_path = None
-
-    fetcher_description = "No description"
-    webdriver_js_execute_code = None
-    xpath_element_js = ""
-
-    xpath_data = None
-
     # Will be needed in the future by the VisualSelector, always get this where possible.
     screenshot = False
+    fetcher_description = "No description"
     system_http_proxy = os.getenv('HTTP_PROXY')
     system_https_proxy = os.getenv('HTTPS_PROXY')
 
-    # Time ONTOP of the system defined env minimum time
-    render_extract_delay = 0
-
-    def __init__(self):
-        from pkg_resources import resource_string
-        # The code that scrapes elements and makes a list of elements/size/position to click on in the VisualSelector
-        self.xpath_element_js = resource_string(__name__, "res/xpath_element_scraper.js").decode('utf-8')
-
-
     @abstractmethod
     def get_error(self):
         return self.error
@@ -116,9 +39,7 @@ class Fetcher():
             request_headers,
             request_body,
             request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
+            ignore_status_codes=False):
         # Should set self.error, self.status_code and self.content
         pass
 
@@ -130,62 +51,11 @@ class Fetcher():
     def get_last_status_code(self):
         return self.status_code
 
-    @abstractmethod
-    def screenshot_step(self, step_n):
-        return None
-
     @abstractmethod
     # Return true/false if this checker is ready to run, in the case it needs todo some special config check etc
     def is_ready(self):
         return True
 
-    def iterate_browser_steps(self):
-        from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
-        from playwright._impl._api_types import TimeoutError
-        from jinja2 import Environment
-        jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
-
-        step_n = 0
-
-        if self.browser_steps is not None and len(self.browser_steps):
-            interface = steppable_browser_interface()
-            interface.page = self.page
-
-            valid_steps = filter(lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'), self.browser_steps)
-
-            for step in valid_steps:
-                step_n += 1
-                print(">> Iterating check - browser Step n {} - {}...".format(step_n, step['operation']))
-                self.screenshot_step("before-"+str(step_n))
-                self.save_step_html("before-"+str(step_n))
-                try:
-                    optional_value = step['optional_value']
-                    selector = step['selector']
-                    # Support for jinja2 template in step values, with date module added
-                    if '{%' in step['optional_value'] or '{{' in step['optional_value']:
-                        optional_value = str(jinja2_env.from_string(step['optional_value']).render())
-                    if '{%' in step['selector'] or '{{' in step['selector']:
-                        selector = str(jinja2_env.from_string(step['selector']).render())
-
-                    getattr(interface, "call_action")(action_name=step['operation'],
-                                                      selector=selector,
-                                                      optional_value=optional_value)
-                    self.screenshot_step(step_n)
-                    self.save_step_html(step_n)
-                except TimeoutError:
-                    # Stop processing here
-                    raise BrowserStepsStepTimout(step_n=step_n)
-
-
-
-    # It's always good to reset these
-    def delete_browser_steps_screenshots(self):
-        import glob
-        if self.browser_steps_screenshot_path is not None:
-            dest = os.path.join(self.browser_steps_screenshot_path, 'step_*.jpeg')
-            files = glob.glob(dest)
-            for f in files:
-                os.unlink(f)
 
 #   Maybe for the future, each fetcher provides its own diff output, could be used for text, image
 #   the current one would return javascript output (as we use JS to generate the diff)
@@ -204,6 +74,7 @@ def available_fetchers():
 
     return p
 
+
 class base_html_playwright(Fetcher):
     fetcher_description = "Playwright {}/Javascript".format(
         os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
@@ -221,12 +92,12 @@ class base_html_playwright(Fetcher):
     proxy = None
 
     def __init__(self, proxy_override=None):
-        super().__init__()
+
         # .strip('"') is going to save someone a lot of time when they accidently wrap the env value
         self.browser_type = os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').strip('"')
         self.command_executor = os.getenv(
             "PLAYWRIGHT_DRIVER_URL",
-            'ws://playwright-chrome:3000'
+            'ws://playwright-chrome:3000/playwright'
         ).strip('"')
 
         # If any proxy settings are enabled, then we should setup the proxy object
@@ -243,165 +114,59 @@ class base_html_playwright(Fetcher):
         if proxy_override:
             self.proxy = {'server': proxy_override}
 
-        if self.proxy:
-            # Playwright needs separate username and password values
-            from urllib.parse import urlparse
-            parsed = urlparse(self.proxy.get('server'))
-            if parsed.username:
-                self.proxy['username'] = parsed.username
-                self.proxy['password'] = parsed.password
-
-    def screenshot_step(self, step_n=''):
-        screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=85)
-
-        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))
-            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))
-        with open(destination, 'w') as f:
-            f.write(content)
-
     def run(self,
             url,
             timeout,
             request_headers,
             request_body,
             request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
+            ignore_status_codes=False):
 
         from playwright.sync_api import sync_playwright
         import playwright._impl._api_types
+        from playwright._impl._api_types import Error, TimeoutError
 
-        self.delete_browser_steps_screenshots()
-        response = None
         with sync_playwright() as p:
             browser_type = getattr(p, self.browser_type)
 
             # Seemed to cause a connection Exception even tho I can see it connect
             # self.browser = browser_type.connect(self.command_executor, timeout=timeout*1000)
-            # 60,000 connection timeout only
-            browser = browser_type.connect_over_cdp(self.command_executor, timeout=60000)
+            browser = browser_type.connect_over_cdp(self.command_executor, timeout=timeout * 1000)
 
             # Set user agent to prevent Cloudflare from blocking the browser
             # Use the default one configured in the App.py model that's passed from fetch_site_status.py
             context = browser.new_context(
                 user_agent=request_headers['User-Agent'] if request_headers.get('User-Agent') else 'Mozilla/5.0',
-                proxy=self.proxy,
-                # This is needed to enable JavaScript execution on GitHub and others
-                bypass_csp=True,
-                # Should be `allow` or `block` - sites like YouTube can transmit large amounts of data via Service Workers
-                service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'),
-                # Should never be needed
-                accept_downloads=False
+                proxy=self.proxy
             )
-
-            self.page = context.new_page()
-            if len(request_headers):
-                context.set_extra_http_headers(request_headers)
-
-                self.page.set_default_navigation_timeout(90000)
-                self.page.set_default_timeout(90000)
-
-                # Listen for all console events and handle errors
-                self.page.on("console", lambda msg: print(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
-
-            # Goto page
+            page = context.new_page()
+            page.set_viewport_size({"width": 1280, "height": 1024})
             try:
+                response = page.goto(url, timeout=timeout * 1000, wait_until='commit')
                 # Wait_until = commit
                 # - `'commit'` - consider operation to be finished when network response is received and the document started loading.
                 # Better to not use any smarts from Playwright and just wait an arbitrary number of seconds
                 # This seemed to solve nearly all 'TimeoutErrors'
-                response = self.page.goto(url, wait_until='commit')
-            except playwright._impl._api_types.Error as e:
-                # Retry once - https://github.com/browserless/chrome/issues/2485
-                # Sometimes errors related to invalid cert's and other can be random
-                print ("Content Fetcher > retrying request got error - ", str(e))
-                time.sleep(1)
-                response = self.page.goto(url, wait_until='commit')
-
-            except Exception as e:
-                print ("Content Fetcher > Other exception when page.goto", str(e))
-                context.close()
-                browser.close()
-                raise PageUnloadable(url=url, status_code=None, message=str(e))
-
-            # Execute any browser steps
-            try:
-                extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
-                self.page.wait_for_timeout(extra_wait * 1000)
-
-                if self.webdriver_js_execute_code is not None and len(self.webdriver_js_execute_code):
-                    self.page.evaluate(self.webdriver_js_execute_code)
-
+                extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5))
+                page.wait_for_timeout(extra_wait * 1000)
             except playwright._impl._api_types.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))
-                context.close()
-                browser.close()
-                raise PageUnloadable(url=url, status_code=None, message=str(e))
-
-            if response is None:
-                context.close()
-                browser.close()
-                print ("Content Fetcher > Response object was none")
                 raise EmptyReply(url=url, status_code=None)
 
-            # Run Browser Steps here
-            self.iterate_browser_steps()
-
-            extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
-            time.sleep(extra_wait)
-
-            self.content = self.page.content()
-            self.status_code = response.status
-            if len(self.page.content().strip()) == 0:
-                context.close()
-                browser.close()
-                print ("Content Fetcher > Content was empty")
-                raise EmptyReply(url=url, status_code=response.status)
+            if response is None:
+                raise EmptyReply(url=url, status_code=None)
 
             self.status_code = response.status
-            self.content = self.page.content()
+            self.content = page.content()
             self.headers = response.all_headers()
 
-            # So we can find an element on the page where its selector was entered manually (maybe not xPath etc)
-            if current_include_filters is not None:
-                self.page.evaluate("var include_filters={}".format(json.dumps(current_include_filters)))
-            else:
-                self.page.evaluate("var include_filters=''")
-
-            self.xpath_data = self.page.evaluate("async () => {" + self.xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors) + "}")
-
-            # Bug 3 in Playwright screenshot handling
             # Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
             # JPEG is better here because the screenshots can be very very large
-
-            # Screenshots also travel via the ws:// (websocket) meaning that the binary data is base64 encoded
-            # which will significantly increase the IO size between the server and client, it's recommended to use the lowest
-            # acceptable screenshot quality here
-            try:
-                # The actual screenshot
-                self.screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
-            except Exception as e:
-                context.close()
-                browser.close()
-                raise ScreenshotUnavailable(url=url, status_code=None)
-
+            page.screenshot(type='jpeg', clip={'x': 1.0, 'y': 1.0, 'width': 1280, 'height': 1024})
+            self.screenshot = page.screenshot(type='jpeg', full_page=True, quality=90)
             context.close()
             browser.close()
 
+
 class base_html_webdriver(Fetcher):
     if os.getenv("WEBDRIVER_URL"):
         fetcher_description = "WebDriver Chrome/Javascript via '{}'".format(os.getenv("WEBDRIVER_URL"))
@@ -418,7 +183,6 @@ class base_html_webdriver(Fetcher):
     proxy = None
 
     def __init__(self, proxy_override=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
@@ -450,9 +214,7 @@ class base_html_webdriver(Fetcher):
             request_headers,
             request_body,
             request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
+            ignore_status_codes=False):
 
         from selenium import webdriver
         from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
@@ -472,30 +234,23 @@ class base_html_webdriver(Fetcher):
             self.quit()
             raise
 
-        self.driver.set_window_size(1280, 1024)
-        self.driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
-
-        if self.webdriver_js_execute_code is not None:
-            self.driver.execute_script(self.webdriver_js_execute_code)
-            # Selenium doesn't automatically wait for actions as good as Playwright, so wait again
-            self.driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
-
         # @todo - how to check this? is it possible?
         self.status_code = 200
         # @todo somehow we should try to get this working for WebDriver
         # raise EmptyReply(url=url, status_code=r.status_code)
 
         # @todo - dom wait loaded?
-        time.sleep(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay)
+        time.sleep(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
         self.content = self.driver.page_source
         self.headers = {}
-
         self.screenshot = self.driver.get_screenshot_as_png()
+        self.quit()
 
     # Does the connection to the webdriver work? run a test connection.
     def is_ready(self):
         from selenium import webdriver
         from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
+        from selenium.common.exceptions import WebDriverException
 
         self.driver = webdriver.Remote(
             command_executor=self.command_executor,
@@ -510,7 +265,7 @@ class base_html_webdriver(Fetcher):
             try:
                 self.driver.quit()
             except Exception as e:
-                print("Content Fetcher > Exception in chrome shutdown/quit" + str(e))
+                print("Exception in chrome shutdown/quit" + str(e))
 
 
 # "html_requests" is listed as the default fetcher in store.py!
@@ -526,16 +281,9 @@ class html_requests(Fetcher):
             request_headers,
             request_body,
             request_method,
-            ignore_status_codes=False,
-            current_include_filters=None,
-            is_binary=False):
+            ignore_status_codes=False):
 
-        # Make requests use a more modern looking user-agent
-        if not 'User-Agent' in request_headers:
-            request_headers['User-Agent'] = os.getenv("DEFAULT_SETTINGS_HEADERS_USERAGENT",
-                                                      'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36')
-
-        proxies = {}
+        proxies={}
 
         # Allows override the proxy on a per-request basis
         if self.proxy_override:
@@ -558,31 +306,19 @@ class html_requests(Fetcher):
         # For example - some sites don't tell us it's utf-8, but return utf-8 content
         # This seems to not occur when using webdriver/selenium, it seems to detect the text encoding more reliably.
         # https://github.com/psf/requests/issues/1604 good info about requests encoding detection
-        if not is_binary:
-            # Don't run this for PDF (and requests identified as binary) takes a _long_ time
-            if not r.headers.get('content-type') or not 'charset=' in r.headers.get('content-type'):
-                encoding = chardet.detect(r.content)['encoding']
-                if encoding:
-                    r.encoding = encoding
-
-        if not r.content or not len(r.content):
-            raise EmptyReply(url=url, status_code=r.status_code)
+        if not r.headers.get('content-type') or not 'charset=' in r.headers.get('content-type'):
+            encoding = chardet.detect(r.content)['encoding']
+            if encoding:
+                r.encoding = encoding
 
         # @todo test this
         # @todo maybe you really want to test zero-byte return pages?
-        if r.status_code != 200 and not ignore_status_codes:
-            # maybe check with content works?
-            raise Non200ErrorCodeReceived(url=url, status_code=r.status_code, page_html=r.text)
+        if (not ignore_status_codes and not r) or not r.content or not len(r.content):
+            raise EmptyReply(url=url, status_code=r.status_code)
 
         self.status_code = r.status_code
-        if is_binary:
-            # Binary files just return their checksum until we add something smarter
-            self.content = hashlib.md5(r.content).hexdigest()
-        else:
-            self.content = r.text
-
+        self.content = r.text
         self.headers = r.headers
-        self.raw_content = r.content
 
 
 # Decide which is the 'real' HTML webdriver, this is more a system wide config

changedetectionio/dev-docker/Dockerfile

@@ -0,0 +1,14 @@
+FROM python:3.8-slim
+
+# https://stackoverflow.com/questions/58701233/docker-logs-erroneously-appears-empty-until-container-stops
+ENV PYTHONUNBUFFERED=1
+
+WORKDIR /app
+
+RUN [ ! -d "/datastore" ] && mkdir /datastore
+
+COPY sleep.py /
+CMD [ "python", "/sleep.py" ]
+
+
+

changedetectionio/dev-docker/sleep.py

@@ -0,0 +1,7 @@
+import time
+
+print ("Sleep loop, you should run your script from the console")
+
+while True: 
+    # Wait for 5 seconds
+    time.sleep(2)

changedetectionio/fetch_site_status.py

@@ -1,62 +1,60 @@
 import hashlib
-import json
-import logging
 import os
 import re
+import time
 import urllib3
 
 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
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
 
-class FilterNotFoundInResponse(ValueError):
-    def __init__(self, msg):
-        ValueError.__init__(self, msg)
-
-class PDFToHTMLToolNotFound(ValueError):
-    def __init__(self, msg):
-        ValueError.__init__(self, msg)
-
-
 # Some common stuff here that can be moved to a base class
-# (set_proxy_from_list)
 class perform_site_check():
-    screenshot = None
-    xpath_data = None
 
     def __init__(self, *args, datastore, **kwargs):
         super().__init__(*args, **kwargs)
         self.datastore = datastore
 
-    # Doesn't look like python supports forward slash auto enclosure in re.findall
-    # So convert it to inline flag "foobar(?i)" type configuration
-    def forward_slash_enclosed_regex_to_options(self, regex):
-        res = re.search(r'^/(.*?)/(\w+)$', regex, re.IGNORECASE)
+    # If there was a proxy list enabled, figure out what proxy_args/which proxy to use
+    # if watch.proxy use that
+    # fetcher.proxy_override = watch.proxy or main config proxy
+    # Allows override the proxy on a per-request basis
+    # ALWAYS use the first one is nothing selected
 
-        if res:
-            regex = res.group(1)
-            regex += '(?{})'.format(res.group(2))
+    def set_proxy_from_list(self, watch):
+        proxy_args = None
+        if self.datastore.proxy_list is None:
+            return None
+
+        # If its a valid one
+        if any([watch['proxy'] in p for p in self.datastore.proxy_list]):
+            proxy_args = watch['proxy']
+
+        # not valid (including None), try the system one
         else:
-            regex += '(?{})'.format('i')
+            system_proxy = self.datastore.data['settings']['requests']['proxy']
+            # Is not None and exists
+            if any([system_proxy in p for p in self.datastore.proxy_list]):
+                proxy_args = system_proxy
 
-        return regex
+        # Fallback - Did not resolve anything, use the first available
+        if proxy_args is None:
+            proxy_args = self.datastore.proxy_list[0][0]
+
+        return proxy_args
+
+    def run(self, uuid):
+        timestamp = int(time.time())  # used for storage etc too
 
-    def run(self, uuid, skip_when_checksum_same=True):
         changed_detected = False
         screenshot = False  # as bytes
         stripped_text_from_html = ""
 
-        # DeepCopy so we can be sure we don't accidently change anything by reference
-        watch = deepcopy(self.datastore.data['watching'].get(uuid))
-
-        if not watch:
-            return
+        watch = self.datastore.data['watching'][uuid]
 
         # Protect against file:// access
-        if re.search(r'^file', watch.get('url', ''), re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
+        if re.search(r'^file', watch['url'], re.IGNORECASE) and not os.getenv('ALLOW_FILE_URI', False):
             raise Exception(
                 "file:// type access is denied for security reasons."
             )
@@ -64,10 +62,10 @@ class perform_site_check():
         # Unset any existing notification error
         update_obj = {'last_notification_error': False, 'last_error': False}
 
-        extra_headers = watch.get('headers', [])
+        extra_headers = self.datastore.get_val(uuid, 'headers')
 
         # Tweak the base config with the per-watch ones
-        request_headers = deepcopy(self.datastore.data['settings']['headers'])
+        request_headers = self.datastore.data['settings']['headers'].copy()
         request_headers.update(extra_headers)
 
         # https://github.com/psf/requests/issues/4525
@@ -76,13 +74,11 @@ class perform_site_check():
         if 'Accept-Encoding' in request_headers and "br" in request_headers['Accept-Encoding']:
             request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
 
-        timeout = self.datastore.data['settings']['requests'].get('timeout')
-
-        url = watch.link
-
-        request_body = self.datastore.data['watching'][uuid].get('body')
-        request_method = self.datastore.data['watching'][uuid].get('method')
-        ignore_status_codes = self.datastore.data['watching'][uuid].get('ignore_status_codes', False)
+        timeout = self.datastore.data['settings']['requests']['timeout']
+        url = self.datastore.get_val(uuid, 'url')
+        request_body = self.datastore.get_val(uuid, 'body')
+        request_method = self.datastore.get_val(uuid, 'method')
+        ignore_status_code = self.datastore.get_val(uuid, 'ignore_status_codes')
 
         # source: support
         is_source = False
@@ -91,58 +87,18 @@ class perform_site_check():
             is_source = True
 
         # Pluggable content fetcher
-        prefer_backend = watch.get_fetch_backend
-        if not prefer_backend or prefer_backend == 'system':
-            prefer_backend = self.datastore.data['settings']['application']['fetch_backend']
-
+        prefer_backend = watch['fetch_backend']
         if hasattr(content_fetcher, prefer_backend):
             klass = getattr(content_fetcher, prefer_backend)
         else:
             # If the klass doesnt exist, just use a default
             klass = getattr(content_fetcher, "html_requests")
 
-        proxy_id = self.datastore.get_preferred_proxy_for_watch(uuid=uuid)
-        proxy_url = None
-        if proxy_id:
-            proxy_url = self.datastore.proxy_list.get(proxy_id).get('url')
-            print("UUID {} Using proxy {}".format(uuid, proxy_url))
-
-        fetcher = klass(proxy_override=proxy_url)
-
-        # Configurable per-watch or global extra delay before extracting text (for webDriver types)
-        system_webdriver_delay = self.datastore.data['settings']['application'].get('webdriver_delay', None)
-        if watch['webdriver_delay'] is not None:
-            fetcher.render_extract_delay = watch.get('webdriver_delay')
-        elif system_webdriver_delay is not None:
-            fetcher.render_extract_delay = system_webdriver_delay
-
-        # Possible conflict
-        if prefer_backend == 'html_webdriver':
-            fetcher.browser_steps = watch.get('browser_steps', None)
-            fetcher.browser_steps_screenshot_path = os.path.join(self.datastore.datastore_path, uuid)
-
-        if watch.get('webdriver_js_execute_code') is not None and watch.get('webdriver_js_execute_code').strip():
-            fetcher.webdriver_js_execute_code = watch.get('webdriver_js_execute_code')
-
-        # requests for PDF's, images etc should be passwd the is_binary flag
-        is_binary = watch.is_pdf
-
-        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch.get('include_filters'), is_binary=is_binary)
-        fetcher.quit()
-
-        self.screenshot = fetcher.screenshot
-        self.xpath_data = fetcher.xpath_data
-
-        # Track the content type
-        update_obj['content_type'] = fetcher.headers.get('Content-Type', '')
-
-        # Watches added automatically in the queue manager will skip if its the same checksum as the previous run
-        # Saves a lot of CPU
-        update_obj['previous_md5_before_filters'] = hashlib.md5(fetcher.content.encode('utf-8')).hexdigest()
-        if skip_when_checksum_same:
-            if update_obj['previous_md5_before_filters'] == watch.get('previous_md5_before_filters'):
-                raise content_fetcher.checksumFromPreviousCheckWasTheSame()
+        proxy_args = self.set_proxy_from_list(watch)
+        fetcher = klass(proxy_override=proxy_args)
 
+        # Proxy List support
+        fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_code)
 
         # Fetching complete, now filters
         # @todo move to class / maybe inside of fetcher abstract base?
@@ -162,71 +118,27 @@ class perform_site_check():
             is_html = False
             is_json = False
 
-        if watch.is_pdf or 'application/pdf' in fetcher.headers.get('Content-Type', '').lower():
-            from shutil import which
-            tool = os.getenv("PDF_TO_HTML_TOOL", "pdftohtml")
-            if not which(tool):
-                raise PDFToHTMLToolNotFound("Command-line `{}` tool was not found in system PATH, was it installed?".format(tool))
-
-            import subprocess
-            proc = subprocess.Popen(
-                [tool, '-stdout', '-', '-s', 'out.pdf', '-i'],
-                stdout=subprocess.PIPE,
-                stdin=subprocess.PIPE)
-            proc.stdin.write(fetcher.raw_content)
-            proc.stdin.close()
-            fetcher.content = proc.stdout.read().decode('utf-8')
-            proc.wait(timeout=60)
-
-            # Add a little metadata so we know if the file changes (like if an image changes, but the text is the same
-            # @todo may cause problems with non-UTF8?
-            metadata = "<p>Added by changedetection.io: Document checksum - {} Filesize - {} bytes</p>".format(
-                hashlib.md5(fetcher.raw_content).hexdigest().upper(),
-                len(fetcher.content))
-
-            fetcher.content = fetcher.content.replace('</body>', metadata + '</body>')
-
-
-        include_filters_rule = deepcopy(watch.get('include_filters', []))
-        # include_filters_rule = watch['include_filters']
+        css_filter_rule = watch['css_filter']
         subtractive_selectors = watch.get(
             "subtractive_selectors", []
         ) + self.datastore.data["settings"]["application"].get(
             "global_subtractive_selectors", []
         )
 
-        # Inject a virtual LD+JSON price tracker rule
-        if watch.get('track_ldjson_price_data', '') == PRICE_DATA_TRACK_ACCEPT:
-            include_filters_rule.append(html_tools.LD_JSON_PRODUCT_OFFER_SELECTOR)
-
-        has_filter_rule = include_filters_rule and len("".join(include_filters_rule).strip())
+        has_filter_rule = css_filter_rule and len(css_filter_rule.strip())
         has_subtractive_selectors = subtractive_selectors and len(subtractive_selectors[0].strip())
 
         if is_json and not has_filter_rule:
-            include_filters_rule.append("json:$")
+            css_filter_rule = "json:$"
             has_filter_rule = True
 
-        if is_json:
-            # Sort the JSON so we dont get false alerts when the content is just re-ordered
-            try:
-                fetcher.content = json.dumps(json.loads(fetcher.content), sort_keys=True)
-            except Exception as e:
-                # Might have just been a snippet, or otherwise bad JSON, continue
-                pass
-
         if has_filter_rule:
-            json_filter_prefixes = ['json:', 'jq:']
-            for filter in include_filters_rule:
-                if any(prefix in filter for prefix in json_filter_prefixes):
-                    stripped_text_from_html += html_tools.extract_json_as_string(content=fetcher.content, json_filter=filter)
-                    is_html = False
-
-
+            if 'json:' in css_filter_rule:
+                stripped_text_from_html = html_tools.extract_json_as_string(content=fetcher.content, jsonpath_filter=css_filter_rule)
+                is_html = False
 
         if is_html or is_source:
-
             # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
-            fetcher.content = html_tools.workarounds_for_obfuscations(fetcher.content)
             html_content = fetcher.content
 
             # If not JSON,  and if it's not text/plain..
@@ -234,50 +146,38 @@ class perform_site_check():
                 # Don't run get_text or xpath/css filters on plaintext
                 stripped_text_from_html = html_content
             else:
-                # Does it have some ld+json price data? used for easier monitoring
-                update_obj['has_ldjson_price_data'] = html_tools.has_ldjson_product_info(fetcher.content)
-
                 # Then we assume HTML
                 if has_filter_rule:
-                    html_content = ""
-
-                    for filter_rule in include_filters_rule:
-                        # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
-                        if filter_rule[0] == '/' or filter_rule.startswith('xpath:'):
-                            html_content += html_tools.xpath_filter(xpath_filter=filter_rule.replace('xpath:', ''),
-                                                                    html_content=fetcher.content,
-                                                                    append_pretty_line_formatting=not is_source)
-                        else:
-                            # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
-                            html_content += html_tools.include_filters(include_filters=filter_rule,
-                                                                       html_content=fetcher.content,
-                                                                       append_pretty_line_formatting=not is_source)
-
-                    if not html_content.strip():
-                        raise FilterNotFoundInResponse(include_filters_rule)
+                    # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
+                    if css_filter_rule[0] == '/' or css_filter_rule.startswith('xpath:'):
+                        html_content = html_tools.xpath_filter(xpath_filter=css_filter_rule.replace('xpath:', ''),
+                                                               html_content=fetcher.content)
+                    else:
+                        # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
+                        html_content = html_tools.css_filter(css_filter=css_filter_rule, html_content=fetcher.content)
 
                 if has_subtractive_selectors:
                     html_content = html_tools.element_removal(subtractive_selectors, html_content)
 
-                if is_source:
-                    stripped_text_from_html = html_content
-                else:
+                if not is_source:
                     # extract text
-                    do_anchor = self.datastore.data["settings"]["application"].get("render_anchor_tag_content", False)
                     stripped_text_from_html = \
                         html_tools.html_to_text(
                             html_content,
-                            render_anchor_tag_content=do_anchor
+                            render_anchor_tag_content=self.datastore.data["settings"][
+                                "application"].get(
+                                "render_anchor_tag_content", False)
                         )
 
+                elif is_source:
+                    stripped_text_from_html = html_content
+
+            # Re #340 - return the content before the 'ignore text' was applied
+            text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
+
         # Re #340 - return the content before the 'ignore text' was applied
         text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
 
-        # Treat pages with no renderable text content as a change? No by default
-        empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
-        if not is_json and not empty_pages_are_a_change and len(stripped_text_from_html.strip()) == 0:
-            raise content_fetcher.ReplyWithContentButNoText(url=url, status_code=fetcher.get_last_status_code(), screenshot=screenshot)
-
         # We rely on the actual text in the html output.. many sites have random script vars etc,
         # in the future we'll implement other mechanisms.
 
@@ -291,91 +191,38 @@ class perform_site_check():
         else:
             stripped_text_from_html = stripped_text_from_html.encode('utf8')
 
-        # 615 Extract text by regex
-        extract_text = watch.get('extract_text', [])
-        if len(extract_text) > 0:
-            regex_matched_output = []
-            for s_re in extract_text:
-                # incase they specified something in '/.../x'
-                regex = self.forward_slash_enclosed_regex_to_options(s_re)
-                result = re.findall(regex.encode('utf-8'), stripped_text_from_html)
-
-                for l in result:
-                    if type(l) is tuple:
-                        # @todo - some formatter option default (between groups)
-                        regex_matched_output += list(l) + [b'\n']
-                    else:
-                        # @todo - some formatter option default (between each ungrouped result)
-                        regex_matched_output += [l] + [b'\n']
-
-            # Now we will only show what the regex matched
-            stripped_text_from_html = b''
-            text_content_before_ignored_filter = b''
-            if regex_matched_output:
-                # @todo some formatter for presentation?
-                stripped_text_from_html = b''.join(regex_matched_output)
-                text_content_before_ignored_filter = stripped_text_from_html
-
         # Re #133 - if we should strip whitespaces from triggering the change detected comparison
         if self.datastore.data['settings']['application'].get('ignore_whitespace', False):
             fetched_md5 = hashlib.md5(stripped_text_from_html.translate(None, b'\r\n\t ')).hexdigest()
         else:
             fetched_md5 = hashlib.md5(stripped_text_from_html).hexdigest()
 
-        ############ Blocking rules, after checksum #################
-        blocked = False
-
-        trigger_text = watch.get('trigger_text', [])
-        if len(trigger_text):
-            # Assume blocked
-            blocked = True
-            # Filter and trigger works the same, so reuse it
-            # It should return the line numbers that match
-            result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
-                                                  wordlist=trigger_text,
-                                                  mode="line numbers")
-            # Unblock if the trigger was found
-            if result:
-                blocked = False
-
-        text_should_not_be_present = watch.get('text_should_not_be_present', [])
-        if len(text_should_not_be_present):
-            # If anything matched, then we should block a change from happening
-            result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
-                                                  wordlist=text_should_not_be_present,
-                                                  mode="line numbers")
-            if result:
-                blocked = True
-
-        # The main thing that all this at the moment comes down to :)
-        if watch.get('previous_md5') != fetched_md5:
-            changed_detected = True
-
-        # Looks like something changed, but did it match all the rules?
-        if blocked:
-            changed_detected = False
-
-        # Extract title as title
-        if is_html:
-            if self.datastore.data['settings']['application'].get('extract_title_as_title') or watch['extract_title_as_title']:
-                if not watch['title'] or not len(watch['title']):
-                    update_obj['title'] = html_tools.extract_element(find='title', html_content=fetcher.content)
-
-        if 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))
-                    changed_detected = False
-                else:
-                    logging.debug("check_unique_lines: UUID {} had unique content".format(uuid))
-
-        # Always record the new checksum
-        update_obj["previous_md5"] = fetched_md5
-
         # On the first run of a site, watch['previous_md5'] will be None, set it the current one.
         if not watch.get('previous_md5'):
             watch['previous_md5'] = fetched_md5
+            update_obj["previous_md5"] = fetched_md5
 
-        return changed_detected, update_obj, text_content_before_ignored_filter
+        blocked_by_not_found_trigger_text = False
+
+        if len(watch['trigger_text']):
+            # Yeah, lets block first until something matches
+            blocked_by_not_found_trigger_text = True
+            # Filter and trigger works the same, so reuse it
+            result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
+                                                  wordlist=watch['trigger_text'],
+                                                  mode="line numbers")
+            if result:
+                blocked_by_not_found_trigger_text = False
+
+        if not blocked_by_not_found_trigger_text and watch['previous_md5'] != fetched_md5:
+            changed_detected = True
+            update_obj["previous_md5"] = fetched_md5
+            update_obj["last_changed"] = timestamp
+
+        # Extract title as title
+        if is_html:
+            if self.datastore.data['settings']['application']['extract_title_as_title'] or watch['extract_title_as_title']:
+                if not watch['title'] or not len(watch['title']):
+                    update_obj['title'] = html_tools.extract_element(find='title', html_content=fetcher.content)
+
+        return changed_detected, update_obj, text_content_before_ignored_filter, fetcher.screenshot

changedetectionio/forms.py

@@ -1,10 +1,11 @@
-import os
 import re
 
 from wtforms import (
     BooleanField,
+    Field,
     Form,
     IntegerField,
+    PasswordField,
     RadioField,
     SelectField,
     StringField,
@@ -12,17 +13,15 @@ from wtforms import (
     TextAreaField,
     fields,
     validators,
-    widgets
+    widgets,
 )
-from wtforms.fields import FieldList
 from wtforms.validators import ValidationError
 
-# default
-# each select <option data-enabled="enabled-0-0"
-from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
-
 from changedetectionio import content_fetcher
 from changedetectionio.notification import (
+    default_notification_body,
+    default_notification_format,
+    default_notification_title,
     valid_notification_formats,
 )
 
@@ -138,7 +137,7 @@ class ValidateContentFetcherIsReady(object):
         from changedetectionio import content_fetcher
 
         # Better would be a radiohandler that keeps a reference to each class
-        if field.data is not None and field.data != 'system':
+        if field.data is not None:
             klass = getattr(content_fetcher, field.data)
             some_object = klass()
             try:
@@ -193,7 +192,7 @@ class ValidateAppRiseServers(object):
                 message = field.gettext('\'%s\' is not a valid AppRise URL.' % (server_url))
                 raise ValidationError(message)
 
-class ValidateJinja2Template(object):
+class ValidateTokensList(object):
     """
     Validates that a {token} is from a valid set
     """
@@ -202,27 +201,14 @@ class ValidateJinja2Template(object):
 
     def __call__(self, form, field):
         from changedetectionio import notification
-
-        from jinja2 import Environment, BaseLoader, TemplateSyntaxError
-        from jinja2.meta import find_undeclared_variables
-
-
-        try:
-            jinja2_env = Environment(loader=BaseLoader)
-            jinja2_env.globals.update(notification.valid_tokens)
-            rendered = jinja2_env.from_string(field.data).render()
-        except TemplateSyntaxError as e:
-            raise ValidationError(f"This is not a valid Jinja2 template: {e}") from e
-
-        ast = jinja2_env.parse(field.data)
-        undefined = ", ".join(find_undeclared_variables(ast))
-        if undefined:
-            raise ValidationError(
-                f"The following tokens used in the notification are not valid: {undefined}"
-            )
-
+        regex = re.compile('{.*?}')
+        for p in re.findall(regex, field.data):
+            if not p.strip('{}') in notification.valid_tokens:
+                message = field.gettext('Token \'%s\' is not a valid token.')
+                raise ValidationError(message % (p))
+            
 class validateURL(object):
-
+    
     """
        Flask wtform validators wont work with basic auth
     """
@@ -232,18 +218,12 @@ class validateURL(object):
 
     def __call__(self, form, field):
         import validators
-
         try:
             validators.url(field.data.strip())
         except validators.ValidationFailure:
             message = field.gettext('\'%s\' is not a valid URL.' % (field.data.strip()))
             raise ValidationError(message)
-
-        from .model.Watch import is_safe_url
-        if not is_safe_url(field.data):
-            raise ValidationError('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX')
-
-
+        
 class ValidateListRegex(object):
     """
     Validates that anything that looks like a regex passes as a regex
@@ -323,69 +303,32 @@ class ValidateCSSJSONXPATHInput(object):
 
                 # Re #265 - maybe in the future fetch the page and offer a
                 # warning/notice that its possible the rule doesnt yet match anything?
-                if not self.allow_json:
-                    raise ValidationError("jq not permitted in this field!")
 
-            if 'jq:' in line:
-                try:
-                    import jq
-                except ModuleNotFoundError:
-                    # `jq` requires full compilation in windows and so isn't generally available
-                    raise ValidationError("jq not support not found")
-
-                input = line.replace('jq:', '')
-
-                try:
-                    jq.compile(input)
-                except (ValueError) as e:
-                    message = field.gettext('\'%s\' is not a valid jq expression. (%s)')
-                    raise ValidationError(message % (input, str(e)))
-                except:
-                    raise ValidationError("A system-error occurred when validating your jq expression")
 
 class quickWatchForm(Form):
     url = fields.URLField('URL', validators=[validateURL()])
-    tag = StringField('Group tag', [validators.Optional()])
-    watch_submit_button = SubmitField('Watch', render_kw={"class": "pure-button pure-button-primary"})
-    edit_and_watch_submit_button = SubmitField('Edit > Watch', render_kw={"class": "pure-button pure-button-primary"})
-
-
+    tag = StringField('Group tag', [validators.Optional(), validators.Length(max=35)])
 
 # Common to a single watch and the global settings
 class commonSettingsForm(Form):
-    notification_urls = StringListField('Notification URL List', validators=[validators.Optional(), ValidateAppRiseServers()])
-    notification_title = StringField('Notification Title', default='ChangeDetection.io Notification - {{ watch_url }}', validators=[validators.Optional(), ValidateJinja2Template()])
-    notification_body = TextAreaField('Notification Body', default='{{ watch_url }} had a change.', validators=[validators.Optional(), ValidateJinja2Template()])
-    notification_format = SelectField('Notification format', choices=valid_notification_formats.keys())
-    fetch_backend = RadioField(u'Fetch Method', choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
+
+    notification_urls = StringListField('Notification URL list', validators=[validators.Optional(), ValidateNotificationBodyAndTitleWhenURLisSet(), ValidateAppRiseServers()])
+    notification_title = StringField('Notification title', default=default_notification_title, validators=[validators.Optional(), ValidateTokensList()])
+    notification_body = TextAreaField('Notification body', default=default_notification_body, validators=[validators.Optional(), ValidateTokensList()])
+    notification_format = SelectField('Notification format', choices=valid_notification_formats.keys(), default=default_notification_format)
+    fetch_backend = RadioField(u'Fetch method', choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
     extract_title_as_title = BooleanField('Extract <title> from document and use as watch title', default=False)
-    webdriver_delay = IntegerField('Wait seconds before extracting text', validators=[validators.Optional(), validators.NumberRange(min=1,
-                                                                                                                                    message="Should contain one or more seconds")])
-
-class SingleBrowserStep(Form):
-
-    operation = SelectField('Operation', [validators.Optional()], choices=browser_step_ui_config.keys())
-
-    # maybe better to set some <script>var..
-    selector = StringField('Selector', [validators.Optional()], render_kw={"placeholder": "CSS or xPath selector"})
-    optional_value = StringField('value', [validators.Optional()], render_kw={"placeholder": "Value"})
-#   @todo move to JS? ajax fetch new field?
-#    remove_button = SubmitField('-', render_kw={"type": "button", "class": "pure-button pure-button-primary", 'title': 'Remove'})
-#    add_button = SubmitField('+', render_kw={"type": "button", "class": "pure-button pure-button-primary", 'title': 'Add new step after'})
 
 class watchForm(commonSettingsForm):
 
     url = fields.URLField('URL', validators=[validateURL()])
-    tag = StringField('Group tag', [validators.Optional()], default='')
+    tag = StringField('Group tag', [validators.Optional(), validators.Length(max=35)], default='')
 
     time_between_check = FormField(TimeBetweenCheckForm)
 
-    include_filters = StringListField('CSS/JSONPath/JQ/XPath Filters', [ValidateCSSJSONXPATHInput()], default='')
+    css_filter = StringField('CSS/JSON/XPATH Filter', [ValidateCSSJSONXPATHInput()], default='')
 
     subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
-
-    extract_text = StringListField('Extract text', [ValidateListRegex()])
-
     title = StringField('Title', default='')
 
     ignore_text = StringListField('Ignore text', [ValidateListRegex()])
@@ -393,21 +336,10 @@ class watchForm(commonSettingsForm):
     body = TextAreaField('Request body', [validators.Optional()])
     method = SelectField('Request method', choices=valid_method, default=default_method)
     ignore_status_codes = BooleanField('Ignore status codes (process non-2xx status codes as normal)', default=False)
-    check_unique_lines = BooleanField('Only trigger when new lines appear', default=False)
     trigger_text = StringListField('Trigger/wait for text', [validators.Optional(), ValidateListRegex()])
-    if os.getenv("PLAYWRIGHT_DRIVER_URL"):
-        browser_steps = FieldList(FormField(SingleBrowserStep), min_entries=10)
-    text_should_not_be_present = StringListField('Block change-detection if text matches', [validators.Optional(), ValidateListRegex()])
-    webdriver_js_execute_code = TextAreaField('Execute JavaScript before change detection', render_kw={"rows": "5"}, validators=[validators.Optional()])
-
     save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
-
+    save_and_preview_button = SubmitField('Save & Preview', render_kw={"class": "pure-button pure-button-primary"})
     proxy = RadioField('Proxy')
-    filter_failure_notification_send = BooleanField(
-        'Send a notification when the filter can no longer be found on the page', default=False)
-
-    notification_muted = BooleanField('Notifications Muted / Off', default=False)
-    notification_screenshot = BooleanField('Attach screenshot to notification (where possible)', default=False)
 
     def validate(self, **kwargs):
         if not super().validate():
@@ -420,60 +352,27 @@ class watchForm(commonSettingsForm):
             self.body.errors.append('Body must be empty when Request Method is set to GET')
             result = False
 
-        # Attempt to validate jinja2 templates in the URL
-        from jinja2 import Environment
-        # Jinja2 available in URLs along with https://pypi.org/project/jinja2-time/
-        jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
-        try:
-            ready_url = str(jinja2_env.from_string(self.url.data).render())
-        except Exception as e:
-            self.url.errors.append('Invalid template syntax')
-            result = False
         return result
 
 
-class SingleExtraProxy(Form):
-
-    # maybe better to set some <script>var..
-    proxy_name = StringField('Name', [validators.Optional()], render_kw={"placeholder": "Name"})
-    proxy_url = StringField('Proxy URL', [validators.Optional()], render_kw={"placeholder": "http://user:pass@...:3128", "size":50})
-    # @todo do the validation here instead
-
 # datastore.data['settings']['requests']..
 class globalSettingsRequestForm(Form):
     time_between_check = FormField(TimeBetweenCheckForm)
     proxy = RadioField('Proxy')
-    jitter_seconds = IntegerField('Random jitter seconds ± check',
-                                  render_kw={"style": "width: 5em;"},
-                                  validators=[validators.NumberRange(min=0, message="Should contain zero or more seconds")])
-    extra_proxies = FieldList(FormField(SingleExtraProxy), min_entries=5)
-
-    def validate_extra_proxies(self, extra_validators=None):
-        for e in self.data['extra_proxies']:
-            if e.get('proxy_name') or e.get('proxy_url'):
-                if not e.get('proxy_name','').strip() or not e.get('proxy_url','').strip():
-                    self.extra_proxies.errors.append('Both a name, and a Proxy URL is required.')
-                    return False
 
 
 # datastore.data['settings']['application']..
 class globalSettingsApplicationForm(commonSettingsForm):
 
-    api_access_token_enabled = BooleanField('API access token security check enabled', default=True, validators=[validators.Optional()])
     base_url = StringField('Base URL', validators=[validators.Optional()])
-    empty_pages_are_a_change =  BooleanField('Treat empty pages as a change?', default=False)
-    fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
-    global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
     global_subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
+    global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
     ignore_whitespace = BooleanField('Ignore whitespace')
-    password = SaltyPasswordField()
+    real_browser_save_screenshot = BooleanField('Save last screenshot when using Chrome?')
     removepassword_button = SubmitField('Remove password', render_kw={"class": "pure-button pure-button-primary"})
     render_anchor_tag_content = BooleanField('Render anchor tag content', default=False)
-    shared_diff_access = BooleanField('Allow access to view diff page when password is enabled', default=False, validators=[validators.Optional()])
-    filter_failure_notification_threshold_attempts = IntegerField('Number of times the filter can be missing before sending a notification',
-                                                                  render_kw={"style": "width: 5em;"},
-                                                                  validators=[validators.NumberRange(min=0,
-                                                                                                     message="Should contain zero or more attempts")])
+    fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
+    password = SaltyPasswordField()
 
 
 class globalSettingsForm(Form):
@@ -484,8 +383,3 @@ class globalSettingsForm(Form):
     requests = FormField(globalSettingsRequestForm)
     application = FormField(globalSettingsApplicationForm)
     save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
-
-
-class extractDataForm(Form):
-    extract_regex = StringField('RegEx to extract', validators=[validators.Length(min=1, message="Needs a RegEx")])
-    extract_submit_button = SubmitField('Extract as CSV', render_kw={"class": "pure-button pure-button-primary"})

changedetectionio/html_tools.py

@@ -1,40 +1,26 @@
-
-from bs4 import BeautifulSoup
-from inscriptis import get_text
-from inscriptis.model.config import ParserConfig
-from jsonpath_ng.ext import parse
-from typing import List
 import json
 import re
+from typing import List
 
-# HTML added to be sure each result matching a filter (.example) gets converted to a new line by Inscriptis
-TEXT_FILTER_LIST_LINE_SUFFIX = "<br/>"
+from bs4 import BeautifulSoup
+from jsonpath_ng.ext import parse
+import re
+from inscriptis import get_text
+from inscriptis.model.config import ParserConfig
 
-# 'price' , 'lowPrice', 'highPrice' are usually under here
-# all of those may or may not appear on different websites
-LD_JSON_PRODUCT_OFFER_SELECTOR = "json:$..offers"
 
 class JSONNotFound(ValueError):
     def __init__(self, msg):
         ValueError.__init__(self, msg)
-        
+
 # Given a CSS Rule, and a blob of HTML, return the blob of HTML that matches
-def include_filters(include_filters, html_content, append_pretty_line_formatting=False):
+def css_filter(css_filter, html_content):
     soup = BeautifulSoup(html_content, "html.parser")
     html_block = ""
-    r = soup.select(include_filters, separator="")
+    for item in soup.select(css_filter, separator=""):
+        html_block += str(item)
 
-    for element in r:
-        # When there's more than 1 match, then add the suffix to separate each line
-        # And where the matched result doesn't include something that will cause Inscriptis to add a newline
-        # (This way each 'match' reliably has a new-line in the diff)
-        # Divs are converted to 4 whitespaces by inscriptis
-        if append_pretty_line_formatting and len(html_block) and not element.name in (['br', 'hr', 'div', 'p']):
-            html_block += TEXT_FILTER_LIST_LINE_SUFFIX
-
-        html_block += str(element)
-
-    return html_block
+    return html_block + "\n"
 
 def subtractive_css_selector(css_selector, html_content):
     soup = BeautifulSoup(html_content, "html.parser")
@@ -50,29 +36,14 @@ def element_removal(selectors: List[str], html_content):
 
 
 # Return str Utf-8 of matched rules
-def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False):
+def xpath_filter(xpath_filter, html_content):
     from lxml import etree, html
 
-    tree = html.fromstring(bytes(html_content, encoding='utf-8'))
+    tree = html.fromstring(html_content)
     html_block = ""
 
-    r = tree.xpath(xpath_filter.strip(), namespaces={'re': 'http://exslt.org/regular-expressions'})
-    #@note: //title/text() wont work where <title>CDATA..
-
-    for element in r:
-        # When there's more than 1 match, then add the suffix to separate each line
-        # And where the matched result doesn't include something that will cause Inscriptis to add a newline
-        # (This way each 'match' reliably has a new-line in the diff)
-        # Divs are converted to 4 whitespaces by inscriptis
-        if append_pretty_line_formatting and len(html_block) and (not hasattr( element, 'tag' ) or not element.tag in (['br', 'hr', 'div', 'p'])):
-            html_block += TEXT_FILTER_LIST_LINE_SUFFIX
-
-        if type(element) == etree._ElementStringResult:
-            html_block += str(element)
-        elif type(element) == etree._ElementUnicodeResult:
-            html_block += str(element)
-        else:
-            html_block += etree.tostring(element, pretty_print=True).decode('utf-8')
+    for item in tree.xpath(xpath_filter.strip(), namespaces={'re':'http://exslt.org/regular-expressions'}):
+        html_block+= etree.tostring(item, pretty_print=True).decode('utf-8')+"<br/>"
 
     return html_block
 
@@ -91,35 +62,19 @@ def extract_element(find='title', html_content=''):
     return element_text
 
 #
-def _parse_json(json_data, json_filter):
-    if 'json:' in json_filter:
-        jsonpath_expression = parse(json_filter.replace('json:', ''))
-        match = jsonpath_expression.find(json_data)
-        return _get_stripped_text_from_json_match(match)
+def _parse_json(json_data, jsonpath_filter):
+    s=[]
+    jsonpath_expression = parse(jsonpath_filter.replace('json:', ''))
+    match = jsonpath_expression.find(json_data)
 
-    if 'jq:' in json_filter:
-
-        try:
-            import jq
-        except ModuleNotFoundError:
-            # `jq` requires full compilation in windows and so isn't generally available
-            raise Exception("jq not support not found")
-
-        jq_expression = jq.compile(json_filter.replace('jq:', ''))
-        match = jq_expression.input(json_data).all()
-
-        return _get_stripped_text_from_json_match(match)
-
-def _get_stripped_text_from_json_match(match):
-    s = []
     # More than one result, we will return it as a JSON list.
     if len(match) > 1:
         for i in match:
-            s.append(i.value if hasattr(i, 'value') else i)
+            s.append(i.value)
 
     # Single value, use just the value, as it could be later used in a token in notifications.
     if len(match) == 1:
-        s = match[0].value if hasattr(match[0], 'value') else match[0]
+        s = match[0].value
 
     # Re #257 - Better handling where it does not exist, in the case the original 's' value was False..
     if not match:
@@ -131,26 +86,19 @@ def _get_stripped_text_from_json_match(match):
 
     return stripped_text_from_html
 
-# content - json
-# json_filter - ie json:$..price
-# ensure_is_ldjson_info_type - str "product", optional, "@type == product" (I dont know how to do that as a json selector)
-def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None):
+def extract_json_as_string(content, jsonpath_filter):
+
     stripped_text_from_html = False
 
     # Try to parse/filter out the JSON, if we get some parser error, then maybe it's embedded <script type=ldjson>
     try:
-        stripped_text_from_html = _parse_json(json.loads(content), json_filter)
+        stripped_text_from_html = _parse_json(json.loads(content), jsonpath_filter)
     except json.JSONDecodeError:
 
-        # Foreach <script json></script> blob.. just return the first that matches json_filter
+        # Foreach <script json></script> blob.. just return the first that matches jsonpath_filter
         s = []
         soup = BeautifulSoup(content, 'html.parser')
-
-        if ensure_is_ldjson_info_type:
-            bs_result = soup.findAll('script', {"type": "application/ld+json"})
-        else:
-            bs_result = soup.findAll('script')
-
+        bs_result = soup.findAll('script')
 
         if not bs_result:
             raise JSONNotFound("No parsable JSON found in this document")
@@ -166,15 +114,8 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
                 # Just skip it
                 continue
             else:
-                stripped_text_from_html = _parse_json(json_data, json_filter)
-                if ensure_is_ldjson_info_type:
-                    # Could sometimes be list, string or something else random
-                    if isinstance(json_data, dict):
-                        # If it has LD JSON 'key' @type, and @type is 'product', and something was found for the search
-                        # (Some sites have multiple of the same ld+json @type='product', but some have the review part, some have the 'price' part)
-                        if json_data.get('@type', False) and json_data.get('@type','').lower() == ensure_is_ldjson_info_type.lower() and stripped_text_from_html:
-                            break
-                elif stripped_text_from_html:
+                stripped_text_from_html = _parse_json(json_data, jsonpath_filter)
+                if stripped_text_from_html:
                     break
 
     if not stripped_text_from_html:
@@ -261,29 +202,3 @@ def html_to_text(html_content: str, render_anchor_tag_content=False) -> str:
 
     return text_content
 
-
-# Does LD+JSON exist with a @type=='product' and a .price set anywhere?
-def has_ldjson_product_info(content):
-    try:
-        pricing_data = extract_json_as_string(content=content, json_filter=LD_JSON_PRODUCT_OFFER_SELECTOR, ensure_is_ldjson_info_type="product")
-    except JSONNotFound as e:
-        # Totally fine
-        return False
-    x=bool(pricing_data)
-    return x
-
-
-def workarounds_for_obfuscations(content):
-    """
-    Some sites are using sneaky tactics to make prices and other information un-renderable by Inscriptis
-    This could go into its own Pip package in the future, for faster updates
-    """
-
-    # HomeDepot.com style <span>$<!-- -->90<!-- -->.<!-- -->74</span>
-    # https://github.com/weblyzard/inscriptis/issues/45
-    if not content:
-        return content
-
-    content = re.sub('<!--\s+-->', '', content)
-
-    return content

changedetectionio/importer.py

@@ -92,7 +92,7 @@ class import_distill_io_json(Importer):
 
         for d in data.get('data'):
             d_config = json.loads(d['config'])
-            extras = {'title': d.get('name', None)}
+            extras = {'title': d['name']}
 
             if len(d['uri']) and good < 5000:
                 try:
@@ -103,20 +103,23 @@ class import_distill_io_json(Importer):
                     pass
                 except IndexError:
                     pass
-                extras['include_filters'] = []
+
                 try:
+                    extras['css_filter'] = d_config['selections'][0]['frames'][0]['includes'][0]['expr']
                     if d_config['selections'][0]['frames'][0]['includes'][0]['type'] == 'xpath':
-                        extras['include_filters'].append('xpath:' + d_config['selections'][0]['frames'][0]['includes'][0]['expr'])
-                    else:
-                        extras['include_filters'].append(d_config['selections'][0]['frames'][0]['includes'][0]['expr'])
+                        extras['css_filter'] = 'xpath:' + extras['css_filter']
+
                 except KeyError:
                     pass
                 except IndexError:
                     pass
 
-
-                if d.get('tags', False):
+                try:
                     extras['tag'] = ", ".join(d['tags'])
+                except KeyError:
+                    pass
+                except IndexError:
+                    pass
 
                 new_uuid = datastore.add_watch(url=d['uri'].strip(),
                                                extras=extras,

changedetectionio/model/App.py

@@ -1,47 +1,47 @@
-from os import getenv
+import collections
+import os
+
+import uuid as uuid_builder
+
 from changedetectionio.notification import (
     default_notification_body,
     default_notification_format,
     default_notification_title,
 )
 
-_FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT = 6
-
 class model(dict):
     base_config = {
             'note': "Hello! If you change this file manually, please be sure to restart your changedetection.io instance!",
             'watching': {},
             'settings': {
                 'headers': {
+                    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36',
+                    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
+                    'Accept-Encoding': 'gzip, deflate',  # No support for brolti in python requests yet.
+                    'Accept-Language': 'en-GB,en-US;q=0.9,en;'
                 },
                 'requests': {
-                    'extra_proxies': [], # Configurable extra proxies via the UI
-                    'jitter_seconds': 0,
-                    'proxy': None, # Preferred proxy connection
+                    'timeout': 15,  # Default 15 seconds
                     'time_between_check': {'weeks': None, 'days': None, 'hours': 3, 'minutes': None, 'seconds': None},
-                    'timeout': int(getenv("DEFAULT_SETTINGS_REQUESTS_TIMEOUT", "45")),  # Default 45 seconds
-                    'workers': int(getenv("DEFAULT_SETTINGS_REQUESTS_WORKERS", "10")),  # Number of threads, lower is better for slow connections
+                    'workers': 10,  # Number of threads, lower is better for slow connections
+                    'proxy': None # Preferred proxy connection
                 },
                 'application': {
-                    'api_access_token_enabled': True,
                     'password': False,
                     'base_url' : None,
                     'extract_title_as_title': False,
-                    'empty_pages_are_a_change': False,
-                    'fetch_backend': getenv("DEFAULT_FETCH_BACKEND", "html_requests"),
-                    'filter_failure_notification_threshold_attempts': _FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT,
+                    'fetch_backend': os.getenv("DEFAULT_FETCH_BACKEND", "html_requests"),
                     'global_ignore_text': [], # List of text to ignore when calculating the comparison checksum
                     'global_subtractive_selectors': [],
-                    'ignore_whitespace': True,
+                    'ignore_whitespace': False,
                     'render_anchor_tag_content': False,
                     'notification_urls': [], # Apprise URL list
                     # Custom notification content
                     'notification_title': default_notification_title,
                     'notification_body': default_notification_body,
                     'notification_format': default_notification_format,
-                    'schema_version' : 0,
-                    'shared_diff_access': False,
-                    'webdriver_delay': None  # Extra delay in seconds before extracting text
+                    'real_browser_save_screenshot': True,
+                    'schema_version' : 0
                 }
             }
         }

changedetectionio/model/Watch.py

@@ -1,278 +1,57 @@
-from distutils.util import strtobool
-import logging
 import os
-import re
-import time
-import uuid
 
-# Allowable protocols, protects against javascript: etc
-# file:// is further checked by ALLOW_FILE_URI
-SAFE_PROTOCOL_REGEX='^(http|https|ftp|file):'
+import uuid as uuid_builder
 
 minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 60))
-mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
 
 from changedetectionio.notification import (
-    default_notification_format_for_watch
+    default_notification_body,
+    default_notification_format,
+    default_notification_title,
 )
 
-base_config = {
-    'body': None,
-    'check_unique_lines': False,  # On change-detected, compare against all history if its something new
-    'check_count': 0,
-    'consecutive_filter_failures': 0,  # Every time the CSS/xPath filter cannot be located, reset when all is fine.
-    'extract_text': [],  # Extract text by regex after filters
-    'extract_title_as_title': False,
-    'fetch_backend': 'system',
-    'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
-    'has_ldjson_price_data': None,
-    'track_ldjson_price_data': None,
-    'headers': {},  # Extra headers to send
-    'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
-    'include_filters': [],
-    'last_checked': 0,
-    'last_error': False,
-    'last_viewed': 0,  # history key value of the last viewed via the [diff] link
-    'method': 'GET',
-    # Custom notification content
-    'notification_body': None,
-    'notification_format': default_notification_format_for_watch,
-    'notification_muted': False,
-    'notification_title': None,
-    'notification_screenshot': False,  # Include the latest screenshot if available and supported by the apprise URL
-    'notification_urls': [],  # List of URLs to add to the notification Queue (Usually AppRise)
-    'paused': False,
-    'previous_md5': False,
-    'previous_md5_before_filters': False,  # Used for skipping changedetection entirely
-    'proxy': None,  # Preferred proxy connection
-    'subtractive_selectors': [],
-    'tag': None,
-    'text_should_not_be_present': [],  # Text that should not present
-    # Re #110, so then if this is set to None, we know to use the default value instead
-    # Requires setting to None on submit if it's the same as the default
-    # Should be all None by default, so we use the system default in this case.
-    'time_between_check': {'weeks': None, 'days': None, 'hours': None, 'minutes': None, 'seconds': None},
-    'title': None,
-    'trigger_text': [],  # List of text or regex to wait for until a change is detected
-    'url': '',
-    'uuid': str(uuid.uuid4()),
-    'webdriver_delay': None,
-    'webdriver_js_execute_code': None,  # Run before change-detection
-}
-
-
-def is_safe_url(test_url):
-    # See https://github.com/dgtlmoon/changedetection.io/issues/1358
-
-    # Remove 'source:' prefix so we dont get 'source:javascript:' etc
-    # 'source:' is a valid way to tell us to return the source
-
-    r = re.compile(re.escape('source:'), re.IGNORECASE)
-    test_url = r.sub('', test_url)
-
-    pattern = re.compile(os.getenv('SAFE_PROTOCOL_REGEX', SAFE_PROTOCOL_REGEX), re.IGNORECASE)
-    if not pattern.match(test_url.strip()):
-        return False
-
-    return True
 
 class model(dict):
-    __newest_history_key = None
-    __history_n = 0
-    jitter_seconds = 0
+    base_config = {
+            'url': None,
+            'tag': None,
+            'last_checked': 0,
+            'last_changed': 0,
+            'paused': False,
+            'last_viewed': 0,  # history key value of the last viewed via the [diff] link
+            'newest_history_key': 0,
+            'title': None,
+            'previous_md5': False,
+#           UUID not needed, should be generated only as a key
+#            'uuid':
+            'headers': {},  # Extra headers to send
+            'body': None,
+            'method': 'GET',
+            # now stored in a sqlite3 db to reduce memory usage
+            #'history': {},  # Dict of timestamp and output stripped filename
+            'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
+            # Custom notification content
+            'notification_urls': [],  # List of URLs to add to the notification Queue (Usually AppRise)
+            'notification_title': default_notification_title,
+            'notification_body': default_notification_body,
+            'notification_format': default_notification_format,
+            'css_filter': "",
+            'subtractive_selectors': [],
+            'trigger_text': [],  # List of text or regex to wait for until a change is detected
+            'fetch_backend': None,
+            'extract_title_as_title': False,
+            'proxy': None, # Preferred proxy connection
+            # Re #110, so then if this is set to None, we know to use the default value instead
+            # Requires setting to None on submit if it's the same as the default
+            # Should be all None by default, so we use the system default in this case.
+            'time_between_check': {'weeks': None, 'days': None, 'hours': None, 'minutes': None, 'seconds': None}
+        }
 
     def __init__(self, *arg, **kw):
-
-        self.update(base_config)
-        self.__datastore_path = kw['datastore_path']
-
-        self['uuid'] = str(uuid.uuid4())
-
-        del kw['datastore_path']
-
-        if kw.get('default'):
-            self.update(kw['default'])
-            del kw['default']
-
-        # Be sure the cached timestamp is ready
-        bump = self.history
-
-        # Goes at the end so we update the default object with the initialiser
+        self.update(self.base_config)
+        # goes at the end so we update the default object with the initialiser
         super(model, self).__init__(*arg, **kw)
 
-    @property
-    def viewed(self):
-        if 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))
-            os.mkdir(self.watch_data_dir)
-
-    @property
-    def link(self):
-
-        url = self.get('url', '')
-        if not is_safe_url(url):
-            return 'DISABLED'
-
-        ready_url = url
-        if '{%' in url or '{{' in url:
-            from jinja2 import Environment
-            # Jinja2 available in URLs along with https://pypi.org/project/jinja2-time/
-            jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
-            try:
-                ready_url = str(jinja2_env.from_string(url).render())
-            except Exception as e:
-                from flask import (
-                    flash, Markup, url_for
-                )
-                message = Markup('<a href="{}#general">The URL {} is invalid and cannot be used, click to edit</a>'.format(
-                    url_for('edit_page', uuid=self.get('uuid')), self.get('url', '')))
-                flash(message, 'error')
-                return ''
-
-        return ready_url
-
-    @property
-    def get_fetch_backend(self):
-        """
-        Like just using the `fetch_backend` key but there could be some logic
-        :return:
-        """
-        # Maybe also if is_image etc?
-        # This is because chrome/playwright wont render the PDF in the browser and we will just fetch it and use pdf2html to see the text.
-        if self.is_pdf:
-            return 'html_requests'
-
-        return self.get('fetch_backend')
-
-    @property
-    def is_pdf(self):
-        # content_type field is set in the future
-        # https://github.com/dgtlmoon/changedetection.io/issues/1392
-        # Not sure the best logic here
-        return self.get('url', '').lower().endswith('.pdf') or 'pdf' in self.get('content_type', '').lower()
-
-    @property
-    def label(self):
-        # Used for sorting
-        if self['title']:
-            return self['title']
-        return self['url']
-
-    @property
-    def last_changed(self):
-        # last_changed will be the newest snapshot, but when we have just one snapshot, it should be 0
-        if self.__history_n <= 1:
-            return 0
-        if self.__newest_history_key:
-            return int(self.__newest_history_key)
-        return 0
-
-    @property
-    def history_n(self):
-        return self.__history_n
-
-    @property
-    def history(self):
-        """History index is just a text file as a list
-            {watch-uuid}/history.txt
-
-            contains a list like
-
-            {epoch-time},{filename}\n
-
-            We read in this list as the history information
-
-        """
-        tmp_history = {}
-
-        # 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()))
-            with open(fname, "r") as f:
-                for i in f.readlines():
-                    if ',' in i:
-                        k, v = i.strip().split(',', 2)
-
-                        # The index history could contain a relative path, so we need to make the fullpath
-                        # so that python can read it
-                        if not '/' in v and not '\'' in v:
-                            v = os.path.join(self.watch_data_dir, v)
-                        else:
-                            # It's possible that they moved the datadir on older versions
-                            # So the snapshot exists but is in a different path
-                            snapshot_fname = v.split('/')[-1]
-                            proposed_new_path = os.path.join(self.watch_data_dir, snapshot_fname)
-                            if not os.path.exists(v) and os.path.exists(proposed_new_path):
-                                v = proposed_new_path
-
-                        tmp_history[k] = v
-
-        if len(tmp_history):
-            self.__newest_history_key = list(tmp_history.keys())[-1]
-
-        self.__history_n = len(tmp_history)
-
-        return tmp_history
-
-    @property
-    def has_history(self):
-        fname = os.path.join(self.watch_data_dir, "history.txt")
-        return os.path.isfile(fname)
-
-    # Returns the newest key, but if theres only 1 record, then it's counted as not being new, so return 0.
-    @property
-    def newest_history_key(self):
-        if self.__newest_history_key is not None:
-            return self.__newest_history_key
-
-        if len(self.history) <= 1:
-            return 0
-
-
-        bump = self.history
-        return self.__newest_history_key
-
-    # Save some text file to the appropriate path and bump the history
-    # result_obj from fetch_site_status.run()
-    def save_history_text(self, contents, timestamp, snapshot_id):
-
-        self.ensure_data_dir_exists()
-
-        # Small hack so that we sleep just enough to allow 1 second  between history snapshots
-        # this is because history.txt indexes/keys snapshots by epoch seconds and we dont want dupe keys
-        if self.__newest_history_key and int(timestamp) == int(self.__newest_history_key):
-            time.sleep(timestamp - self.__newest_history_key)
-
-        snapshot_fname = f"{snapshot_id}.txt"
-
-        # Only write if it does not exist, this is so that we dont bother re-saving the same data by checksum under different filenames.
-        dest = os.path.join(self.watch_data_dir, snapshot_fname)
-        if not os.path.exists(dest):
-            # in /diff/ and /preview/ we are going to assume for now that it's UTF-8 when reading
-            # most sites are utf-8 and some are even broken utf-8
-            with open(dest, 'wb') as f:
-                f.write(contents)
-                f.close()
-
-        # Append to index
-        # @todo check last char was \n
-        index_fname = os.path.join(self.watch_data_dir, "history.txt")
-        with open(index_fname, 'a') as f:
-            f.write("{},{}\n".format(timestamp, snapshot_fname))
-            f.close()
-
-        self.__newest_history_key = timestamp
-        self.__history_n += 1
-
-        # @todo bump static cache of the last timestamp so we dont need to examine the file to set a proper ''viewed'' status
-        return snapshot_fname
 
     @property
     def has_empty_checktime(self):
@@ -283,154 +62,9 @@ class model(dict):
 
     def threshold_seconds(self):
         seconds = 0
+        mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
         for m, n in mtable.items():
             x = self.get('time_between_check', {}).get(m, None)
             if x:
                 seconds += x * n
         return seconds
-
-    # Iterate over all history texts and see if something new exists
-    def lines_contain_something_unique_compared_to_history(self, lines: list):
-        local_lines = set([l.decode('utf-8').strip().lower() for l in lines])
-
-        # Compare each lines (set) against each history text file (set) looking for something new..
-        existing_history = set({})
-        for k, v in self.history.items():
-            alist = set([line.decode('utf-8').strip().lower() for line in open(v, 'rb')])
-            existing_history = existing_history.union(alist)
-
-        # Check that everything in local_lines(new stuff) already exists in existing_history - it should
-        # if not, something new happened
-        return not local_lines.issubset(existing_history)
-
-    def get_screenshot(self):
-        fname = os.path.join(self.watch_data_dir, "last-screenshot.png")
-        if os.path.isfile(fname):
-            return fname
-
-        # False is not an option for AppRise, must be type None
-        return None
-
-    def get_screenshot_as_jpeg(self):
-
-        # Created by save_screenshot()
-        fname = os.path.join(self.watch_data_dir, "last-screenshot.jpg")
-        if os.path.isfile(fname):
-            return fname
-
-        # False is not an option for AppRise, must be type None
-        return None
-
-
-    def __get_file_ctime(self, filename):
-        fname = os.path.join(self.watch_data_dir, filename)
-        if os.path.isfile(fname):
-            return int(os.path.getmtime(fname))
-        return False
-
-    @property
-    def error_text_ctime(self):
-        return self.__get_file_ctime('last-error.txt')
-
-    @property
-    def snapshot_text_ctime(self):
-        if self.history_n==0:
-            return False
-
-        timestamp = list(self.history.keys())[-1]
-        return int(timestamp)
-
-    @property
-    def snapshot_screenshot_ctime(self):
-        return self.__get_file_ctime('last-screenshot.png')
-
-    @property
-    def snapshot_error_screenshot_ctime(self):
-        return self.__get_file_ctime('last-error-screenshot.png')
-
-    @property
-    def watch_data_dir(self):
-        # The base dir of the watch data
-        return os.path.join(self.__datastore_path, self['uuid'])
-    
-    def get_error_text(self):
-        """Return the text saved from a previous request that resulted in a non-200 error"""
-        fname = os.path.join(self.watch_data_dir, "last-error.txt")
-        if os.path.isfile(fname):
-            with open(fname, 'r') as f:
-                return f.read()
-        return False
-
-    def get_error_snapshot(self):
-        """Return path to the screenshot that resulted in a non-200 error"""
-        fname = os.path.join(self.watch_data_dir, "last-error-screenshot.png")
-        if os.path.isfile(fname):
-            return fname
-        return False
-
-    def pause(self):
-        self['paused'] = True
-
-    def unpause(self):
-        self['paused'] = False
-
-    def toggle_pause(self):
-        self['paused'] ^= True
-
-    def mute(self):
-        self['notification_muted'] = True
-
-    def unmute(self):
-        self['notification_muted'] = False
-
-    def toggle_mute(self):
-        self['notification_muted'] ^= True
-
-    def extract_regex_from_all_history(self, regex):
-        import csv
-        import re
-        import datetime
-        csv_output_filename = False
-        csv_writer = False
-        f = None
-
-        # self.history will be keyed with the full path
-        for k, fname in self.history.items():
-            if os.path.isfile(fname):
-                with open(fname, "r") as f:
-                    contents = f.read()
-                    res = re.findall(regex, contents, re.MULTILINE)
-                    if res:
-                        if not csv_writer:
-                            # A file on the disk can be transferred much faster via flask than a string reply
-                            csv_output_filename = 'report.csv'
-                            f = open(os.path.join(self.watch_data_dir, csv_output_filename), 'w')
-                            # @todo some headers in the future
-                            #fieldnames = ['Epoch seconds', 'Date']
-                            csv_writer = csv.writer(f,
-                                                    delimiter=',',
-                                                    quotechar='"',
-                                                    quoting=csv.QUOTE_MINIMAL,
-                                                    #fieldnames=fieldnames
-                                                    )
-                            csv_writer.writerow(['Epoch seconds', 'Date'])
-                            # csv_writer.writeheader()
-
-                        date_str = datetime.datetime.fromtimestamp(int(k)).strftime('%Y-%m-%d %H:%M:%S')
-                        for r in res:
-                            row = [k, date_str]
-                            if isinstance(r, str):
-                                row.append(r)
-                            else:
-                                row+=r
-                            csv_writer.writerow(row)
-
-        if f:
-            f.close()
-
-        return csv_output_filename
-
-    @property
-    # Return list of tags, stripped and lowercase, used for searching
-    def all_tags(self):
-        return [s.strip().lower() for s in self.get('tag','').split(',')]

changedetectionio/notification.py

@@ -1,7 +1,5 @@
 import apprise
-from jinja2 import Environment, BaseLoader
 from apprise import NotifyFormat
-import json
 
 valid_tokens = {
     'base_url': '',
@@ -16,89 +14,43 @@ valid_tokens = {
     'current_snapshot': ''
 }
 
-default_notification_format_for_watch = 'System default'
-default_notification_format = 'Text'
-default_notification_body = '{{watch_url}} had a change.\n---\n{{diff}}\n---\n'
-default_notification_title = 'ChangeDetection.io Notification - {{watch_url}}'
-
 valid_notification_formats = {
     'Text': NotifyFormat.TEXT,
     'Markdown': NotifyFormat.MARKDOWN,
     'HTML': NotifyFormat.HTML,
-    # Used only for editing a watch (not for global)
-    default_notification_format_for_watch: default_notification_format_for_watch
 }
 
-# include the decorator
-from apprise.decorators import notify
-
-@notify(on="delete")
-@notify(on="deletes")
-@notify(on="get")
-@notify(on="gets")
-@notify(on="post")
-@notify(on="posts")
-@notify(on="put")
-@notify(on="puts")
-def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
-    import requests
-    url = kwargs['meta'].get('url')
-
-    if url.startswith('post'):
-        r = requests.post
-    elif url.startswith('get'):
-        r = requests.get
-    elif url.startswith('put'):
-        r = requests.put
-    elif url.startswith('delete'):
-        r = requests.delete
-
-    url = url.replace('post://', 'http://')
-    url = url.replace('posts://', 'https://')
-    url = url.replace('put://', 'http://')
-    url = url.replace('puts://', 'https://')
-    url = url.replace('get://', 'http://')
-    url = url.replace('gets://', 'https://')
-    url = url.replace('put://', 'http://')
-    url = url.replace('puts://', 'https://')
-    url = url.replace('delete://', 'http://')
-    url = url.replace('deletes://', 'https://')
-
-    # Try to auto-guess if it's JSON
-    headers = {}
-    try:
-        json.loads(body)
-        headers = {'Content-Type': 'application/json; charset=utf-8'}
-    except ValueError as e:
-        pass
-
-
-    r(url, headers=headers, data=body)
-
+default_notification_format = 'Text'
+default_notification_body = '{watch_url} had a change.\n---\n{diff}\n---\n'
+default_notification_title = 'ChangeDetection.io Notification - {watch_url}'
 
 def process_notification(n_object, datastore):
 
-    # 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 = n_object.get('notification_body', default_notification_body)
+    n_title = n_object.get('notification_title', default_notification_title)
     n_format = valid_notification_formats.get(
         n_object['notification_format'],
         valid_notification_formats[default_notification_format],
     )
-    
+
+
+    # Insert variables into the notification content
+    notification_parameters = create_notification_parameters(n_object, datastore)
+
+    for n_k in notification_parameters:
+        token = '{' + n_k + '}'
+        val = notification_parameters[n_k]
+        n_title = n_title.replace(token, val)
+        n_body = n_body.replace(token, val)
+
     # 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=[]
-    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)
+
+        apobj = apprise.Apprise(debug=True)
         url = url.strip()
         if len(url):
             print(">> Process Notification: AppRise notifying {}".format(url))
@@ -111,50 +63,29 @@ def process_notification(n_object, datastore):
 
                 # 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'):
+                if not 'avatar_url' in url:
                     url += k + 'avatar_url=https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/changedetectionio/static/images/avatar-256x256.png'
 
                 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]
 
-                elif url.startswith('discord://') or url.startswith('https://discordapp.com/api/webhooks') or url.startswith('https://discord.com/api'):
+                elif url.startswith('discord://'):
                     # 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]
 
-                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 '&'
-                        url = "{}{}format={}".format(url, prefix, n_format)
-
                 apobj.add(url)
 
                 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)
-                )
+                    body_format=n_format)
 
                 apobj.clear()
 
@@ -165,15 +96,6 @@ def process_notification(n_object, datastore):
                 log_value = logs.getvalue()
                 if log_value and 'WARNING' in log_value or 'ERROR' in log_value:
                     raise Exception(log_value)
-                
-                sent_objs.append({'title': n_title,
-                                  'body': n_body,
-                                  'url' : url,
-                                  'body_format': n_format})
-
-    # Return what was sent for better logging - after the for loop
-    return sent_objs
-
 
 # Notification title + body content parameters get created here.
 def create_notification_parameters(n_object, datastore):
@@ -194,7 +116,7 @@ def create_notification_parameters(n_object, datastore):
 
     watch_url = n_object['watch_url']
 
-    # Re #148 - Some people have just {{ base_url }} in the body or title, but this may break some notification services
+    # Re #148 - Some people have just {base_url} in the body or title, but this may break some notification services
     #           like 'Join', so it's always best to atleast set something obvious so that they are not broken.
     if base_url == '':
         base_url = "<base-url-env-var-not-set>"

changedetectionio/queuedWatchMetaData.py

@@ -1,10 +0,0 @@
-from dataclasses import dataclass, field
-from typing import Any
-
-# So that we can queue some metadata in `item`
-# https://docs.python.org/3/library/queue.html#queue.PriorityQueue
-#
-@dataclass(order=True)
-class PrioritizedItem:
-    priority: int
-    item: Any=field(compare=False)

changedetectionio/res/xpath_element_scraper.js

@@ -1,215 +0,0 @@
-// Copyright (C) 2021 Leigh Morresi (dgtlmoon@gmail.com)
-// All rights reserved.
-
-// @file Scrape the page looking for elements of concern (%ELEMENTS%)
-// http://matatk.agrip.org.uk/tests/position-and-width/
-// https://stackoverflow.com/questions/26813480/when-is-element-getboundingclientrect-guaranteed-to-be-updated-accurate
-//
-// Some pages like https://www.londonstockexchange.com/stock/NCCL/ncondezi-energy-limited/analysis
-// will automatically force a scroll somewhere, so include the position offset
-// Lets hope the position doesnt change while we iterate the bbox's, but this is better than nothing
-
-var scroll_y=+document.documentElement.scrollTop || document.body.scrollTop
-
-// Include the getXpath script directly, easier than fetching
-function getxpath(e) {
-        var n = e;
-        if (n && n.id) return '//*[@id="' + n.id + '"]';
-        for (var o = []; n && Node.ELEMENT_NODE === n.nodeType;) {
-            for (var i = 0, r = !1, d = n.previousSibling; d;) d.nodeType !== Node.DOCUMENT_TYPE_NODE && d.nodeName === n.nodeName && i++, d = d.previousSibling;
-            for (d = n.nextSibling; d;) {
-                if (d.nodeName === n.nodeName) {
-                    r = !0;
-                    break
-                }
-                d = d.nextSibling
-            }
-            o.push((n.prefix ? n.prefix + ":" : "") + n.localName + (i || r ? "[" + (i + 1) + "]" : "")), n = n.parentNode
-        }
-        return o.length ? "/" + o.reverse().join("/") : ""
-    }
-
-const findUpTag = (el) => {
-    let r = el
-    chained_css = [];
-    depth = 0;
-
-    //  Strategy 1: If it's an input, with name, and there's only one, prefer that
-    if (el.name !== undefined && el.name.length) {
-        var proposed = el.tagName + "[name=" + el.name + "]";
-        var proposed_element = window.document.querySelectorAll(proposed);
-        if(proposed_element.length) {
-            if (proposed_element.length === 1) {
-                return proposed;
-            } else {
-                // Some sites change ID but name= stays the same, we can hit it if we know the index
-                // Find all the elements that match and work out the input[n]
-                var n=Array.from(proposed_element).indexOf(el);
-                // Return a Playwright selector for nthinput[name=zipcode]
-                return proposed+" >> nth="+n;
-            }
-        }
-    }
-
-    // Strategy 2: Keep going up until we hit an ID tag, imagine it's like  #list-widget div h4
-    while (r.parentNode) {
-        if (depth == 5) {
-            break;
-        }
-        if ('' !== r.id) {
-            chained_css.unshift("#" + CSS.escape(r.id));
-            final_selector = chained_css.join(' > ');
-            // Be sure theres only one, some sites have multiples of the same ID tag :-(
-            if (window.document.querySelectorAll(final_selector).length == 1) {
-                return final_selector;
-            }
-            return null;
-        } else {
-            chained_css.unshift(r.tagName.toLowerCase());
-        }
-        r = r.parentNode;
-        depth += 1;
-    }
-    return null;
-}
-
-
-// @todo - if it's SVG or IMG, go into image diff mode
-// %ELEMENTS% replaced at injection time because different interfaces use it with different settings
-var elements = window.document.querySelectorAll("%ELEMENTS%");
-var size_pos = [];
-// after page fetch, inject this JS
-// build a map of all elements and their positions (maybe that only include text?)
-var bbox;
-for (var i = 0; i < elements.length; i++) {
-    bbox = elements[i].getBoundingClientRect();
-
-    // Exclude items that are not interactable or visible
-    if(elements[i].style.opacity === "0") {
-        continue
-    }
-    if(elements[i].style.display === "none" || elements[i].style.pointerEvents === "none" ) {
-        continue
-    }
-
-    // Skip really small ones, and where width or height ==0
-    if (bbox['width'] * bbox['height'] < 100) {
-        continue;
-    }
-
-    // Don't include elements that are offset from canvas
-    if (bbox['top']+scroll_y < 0 || bbox['left'] < 0) {
-        continue;
-    }
-
-    // @todo the getXpath kind of sucks, it doesnt know when there is for example just one ID sometimes
-    // it should not traverse when we know we can anchor off just an ID one level up etc..
-    // maybe, get current class or id, keep traversing up looking for only class or id until there is just one match
-
-    // 1st primitive - if it has class, try joining it all and select, if theres only one.. well thats us.
-    xpath_result = false;
-
-    try {
-        var d = findUpTag(elements[i]);
-        if (d) {
-            xpath_result = d;
-        }
-    } catch (e) {
-        console.log(e);
-    }
-
-    // You could swap it and default to getXpath and then try the smarter one
-    // default back to the less intelligent one
-    if (!xpath_result) {
-        try {
-            // I've seen on FB and eBay that this doesnt work
-            // ReferenceError: getXPath is not defined at eval (eval at evaluate (:152:29), <anonymous>:67:20) at UtilityScript.evaluate (<anonymous>:159:18) at UtilityScript.<anonymous> (<anonymous>:1:44)
-            xpath_result = getxpath(elements[i]);
-        } catch (e) {
-            console.log(e);
-            continue;
-        }
-    }
-
-    if (window.getComputedStyle(elements[i]).visibility === "hidden") {
-        continue;
-    }
-
-    // @todo Possible to ONLY list where it's clickable to save JSON xfer size
-    size_pos.push({
-        xpath: xpath_result,
-        width: Math.round(bbox['width']),
-        height: Math.round(bbox['height']),
-        left: Math.floor(bbox['left']),
-        top: Math.floor(bbox['top'])+scroll_y,
-        tagName: (elements[i].tagName) ? elements[i].tagName.toLowerCase() : '',
-        tagtype: (elements[i].tagName == 'INPUT' && elements[i].type) ? elements[i].type.toLowerCase() : '',
-        isClickable: (elements[i].onclick) || window.getComputedStyle(elements[i]).cursor == "pointer"
-    });
-
-}
-
-// Inject the current one set in the include_filters, which may be a CSS rule
-// used for displaying the current one in VisualSelector, where its not one we generated.
-if (include_filters.length) {
-    // Foreach filter, go and find it on the page and add it to the results so we can visualise it again
-    for (const f of include_filters) {
-        bbox = false;
-        q = false;
-
-        if (!f.length) {
-            console.log("xpath_element_scraper: Empty filter, skipping");
-            continue;
-        }
-
-        try {
-            // is it xpath?
-            if (f.startsWith('/') || f.startsWith('xpath:')) {
-                q = document.evaluate(f.replace('xpath:', ''), document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
-            } else {
-                q = document.querySelector(f);
-            }
-        } catch (e) {
-            // Maybe catch DOMException and alert?
-            console.log("xpath_element_scraper: Exception selecting element from filter "+f);
-            console.log(e);
-        }
-
-        if (q) {
-            // #1231 - IN the case XPath attribute filter is applied, we will have to traverse up and find the element.
-            if (q.hasOwnProperty('getBoundingClientRect')) {
-                bbox = q.getBoundingClientRect();
-                console.log("xpath_element_scraper: Got filter element, scroll from top was " + scroll_y)
-            } else {
-                try {
-                    // Try and see we can find its ownerElement
-                    bbox = q.ownerElement.getBoundingClientRect();
-                    console.log("xpath_element_scraper: Got filter by ownerElement element, scroll from top was " + scroll_y)
-                } catch (e) {
-                    console.log("xpath_element_scraper: error looking up ownerElement")
-                }
-            }
-        }
-        
-        if(!q) {
-            console.log("xpath_element_scraper: filter element " + f + " was not found");
-        }
-
-        if (bbox && bbox['width'] > 0 && bbox['height'] > 0) {
-            size_pos.push({
-                xpath: f,
-                width: parseInt(bbox['width']),
-                height: parseInt(bbox['height']),
-                left: parseInt(bbox['left']),
-                top: parseInt(bbox['top'])+scroll_y
-            });
-        }
-    }
-}
-
-// Sort the elements so we find the smallest one first, in other words, we find the smallest one matching in that area
-// so that we dont select the wrapping element by mistake and be unable to select what we want
-size_pos.sort((a, b) => (a.width*a.height > b.width*b.height) ? 1 : -1)
-
-// Window.width required for proper scaling in the frontend
-return {'size_pos': size_pos, 'browser_width': window.innerWidth};

changedetectionio/run_all_tests.sh

@@ -9,8 +9,6 @@
 # exit when any command fails
 set -e
 
-SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
-
 find tests/test_*py -type f|while read test_name
 do
   echo "TEST RUNNING $test_name"
@@ -24,7 +22,3 @@ echo "RUNNING WITH BASE_URL SET"
 export BASE_URL="https://really-unique-domain.io"
 pytest tests/test_notification.py
 
-
-# Re-run with HIDE_REFERER set - could affect login
-export HIDE_REFERER=True
-pytest tests/test_access_control.py

changedetectionio/run_proxy_tests.sh

@@ -1,61 +0,0 @@
-#!/bin/bash
-
-# exit when any command fails
-set -e
-
-# Test proxy list handling, starting two squids on different ports
-# Each squid adds a different header to the response, which is the main thing we test for.
-docker run --network changedet-network -d --name squid-one --hostname squid-one --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf ubuntu/squid:4.13-21.10_edge
-docker run --network changedet-network -d --name squid-two --hostname squid-two --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf ubuntu/squid:4.13-21.10_edge
-
-# Used for configuring a custom proxy URL via the UI
-docker run --network changedet-network -d \
-  --name squid-custom \
-  --hostname squid-custom \
-  --rm \
-  -v `pwd`/tests/proxy_list/squid-auth.conf:/etc/squid/conf.d/debian.conf \
-  -v `pwd`/tests/proxy_list/squid-passwords.txt:/etc/squid3/passwords \
-  ubuntu/squid:4.13-21.10_edge
-
-
-## 2nd test actually choose the preferred proxy from proxies.json
-
-docker run --network changedet-network \
-  -v `pwd`/tests/proxy_list/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json \
-  test-changedetectionio \
-  bash -c 'cd changedetectionio && pytest tests/proxy_list/test_multiple_proxy.py'
-
-
-## Should be a request in the default "first" squid
-docker logs squid-one 2>/dev/null|grep chosen.changedetection.io
-if [ $? -ne 0 ]
-then
-  echo "Did not see a request to chosen.changedetection.io in the squid logs (while checking preferred proxy - squid one)"
-  exit 1
-fi
-
-# And one in the 'second' squid (user selects this as preferred)
-docker logs squid-two 2>/dev/null|grep chosen.changedetection.io
-if [ $? -ne 0 ]
-then
-  echo "Did not see a request to chosen.changedetection.io in the squid logs (while checking preferred proxy - squid two)"
-  exit 1
-fi
-
-
-# Test the UI configurable proxies
-
-docker run --network changedet-network \
-  test-changedetectionio \
-  bash -c 'cd changedetectionio && pytest tests/proxy_list/test_select_custom_proxy.py'
-
-
-# Should see a request for one.changedetection.io in there
-docker logs squid-custom 2>/dev/null|grep "TCP_TUNNEL.200.*changedetection.io"
-if [ $? -ne 0 ]
-then
-  echo "Did not see a valid request to changedetection.io in the squid logs (while checking preferred proxy - squid two)"
-  exit 1
-fi
-
-docker kill squid-one squid-two squid-custom

changedetectionio/static/favicons/browserconfig.xml

@@ -1,9 +0,0 @@
-<?xml version="1.0" encoding="utf-8"?>
-<browserconfig>
-    <msapplication>
-        <tile>
-            <square150x150logo src="favicons/mstile-150x150.png"/>
-            <TileColor>#da532c</TileColor>
-        </tile>
-    </msapplication>
-</browserconfig>

changedetectionio/static/favicons/safari-pinned-tab.svg

@@ -1,35 +0,0 @@
-<?xml version="1.0" standalone="no"?>
-<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 20010904//EN"
- "http://www.w3.org/TR/2001/REC-SVG-20010904/DTD/svg10.dtd">
-<svg version="1.0" xmlns="http://www.w3.org/2000/svg"
- width="256.000000pt" height="256.000000pt" viewBox="0 0 256.000000 256.000000"
- preserveAspectRatio="xMidYMid meet">
-<metadata>
-Created by potrace 1.14, written by Peter Selinger 2001-2017
-</metadata>
-<g transform="translate(0.000000,256.000000) scale(0.100000,-0.100000)"
-fill="#000000" stroke="none">
-<path d="M0 1280 l0 -1280 1280 0 1280 0 0 1280 0 1280 -1280 0 -1280 0 0
--1280z m1555 936 c387 -112 675 -426 741 -810 24 -138 15 -352 -20 -470 -106
--353 -360 -606 -713 -712 -75 -22 -113 -27 -253 -31 -144 -5 -176 -2 -252 16
--316 75 -564 271 -707 557 -67 136 -92 237 -98 401 -7 164 5 253 47 378 106
-315 349 556 665 659 114 37 180 45 350 41 125 -2 165 -7 240 -29z"/>
-<path d="M1091 2165 c-364 -82 -629 -328 -738 -682 -24 -80 -27 -103 -27 -258
--1 -146 2 -182 21 -251 74 -271 259 -497 508 -621 477 -238 1061 -35 1294 450
-61 126 83 220 88 379 7 194 -15 307 -93 461 -126 251 -340 428 -614 507 -99
-29 -343 37 -439 15z m829 -473 c55 -54 100 -106 100 -116 0 -21 -184 -213
--212 -222 -24 -7 -48 12 -48 38 0 11 26 47 58 80 l57 60 -151 -3 c-145 -4
--152 -5 -190 -31 -22 -15 -78 -73 -124 -128 l-85 -99 -32 31 -32 31 30 38 c17
-22 70 79 117 128 66 67 97 92 127 100 22 6 106 11 188 11 81 0 147 3 147 8 0
-4 -25 31 -55 61 -55 55 -65 77 -43 99 25 25 50 10 148 -86z m-1002 -101 c46
--24 141 -121 312 -321 203 -236 290 -330 322 -346 22 -11 60 -14 169 -12 l141
-3 -51 58 c-28 32 -51 64 -51 71 0 18 21 36 43 36 24 0 217 -193 217 -217 0
--19 -185 -210 -212 -219 -24 -7 -48 12 -48 38 0 10 23 43 50 72 l50 53 -52 7
-c-29 3 -93 6 -142 6 -104 0 -152 12 -200 52 -19 15 -135 144 -258 286 -274
-316 -305 347 -354 361 -22 6 -94 11 -161 11 -67 0 -128 3 -137 6 -22 9 -21 61
-2 67 9 3 86 5 170 6 133 1 158 -2 190 -18z m227 -468 c23 -34 17 -43 -103
--172 -119 -128 -131 -133 -343 -129 l-154 3 0 35 c0 34 1 35 50 42 28 3 96 7
-153 7 64 1 115 6 136 15 20 8 71 56 127 120 52 58 99 106 105 106 7 0 20 -12
-29 -27z"/>
-</g>
-</svg>

changedetectionio/static/favicons/site.webmanifest

@@ -1,19 +0,0 @@
-{
-    "name": "",
-    "short_name": "",
-    "icons": [
-        {
-            "src": "android-chrome-192x192.png",
-            "sizes": "192x192",
-            "type": "image/png"
-        },
-        {
-            "src": "android-chrome-256x256.png",
-            "sizes": "256x256",
-            "type": "image/png"
-        }
-    ],
-    "theme_color": "#ffffff",
-    "background_color": "#ffffff",
-    "display": "standalone"
-}

changedetectionio/static/images/bell-off.svg

@@ -1,4 +0,0 @@
-<?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">
-  <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/notice.svg

@@ -1,51 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<!-- Created with Inkscape (http://www.inkscape.org/) -->
-
-<svg
-   width="20.108334mm"
-   height="21.43125mm"
-   viewBox="0 0 20.108334 21.43125"
-   version="1.1"
-   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
-     id="layer1"
-     transform="translate(-141.05873,-76.816635)">
-    <image
-       width="20.108334"
-       height="21.43125"
-       preserveAspectRatio="none"
-       style="image-rendering:optimizeQuality"
-       xlink:href="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAEwAAABRCAYAAAB430BuAAAABHNCSVQICAgIfAhkiAAABLxJREFU
-eJztnN2Z2jgUhl8Z7petIGwF0WMXsFBBoIKwFWS2gmQryKSCJRXsTAUDBTDRVBCmgkAB9tkLexh+
-bIONLGwP7xU2RjafpaOjoyNBCxHNQAJEfG5sl+3ZLrAWeAyST5/sF91mFH3bRbZbsAq4ClaQq2B7
-iKYnmg9Z318F20ICRnj8pMOd6E3HscNVsATxmQD/oeghPCnDLO26q2AkYin+TQ7XREyyrn3zgu2J
-BSEjZTBZ179pwQ7EEv7KaoovvFnBUsV6ZHrsd+0WTHhKPV1SLGivYEsA1KEtEs2grFitRjQ65VxP
-fH5JgEjAKsvXupKwFfYxaYJeSeHcWqVSCuwD7/HQQD8lRHLWDStBWG3slbAElkTc5/lTZdkIJhpN
-h6/UUZDyzAgZK8PKVoEKErE8HlD0bBVcI2ZqwdBWYbFgAT+g1UZwrBbcvRyIpofHJ1Sh1rQCZt1k
-lN5msQAm8CoYoFF8KVHOsFtQ5aayExBUhpnopJl6J/3/FREGWCrxmaH40/4z1oyQ320Yf5dDozXC
-P4QMCRkCY4S5w/tbMTtd4L2Ngo6wJmSQ4hfdScAU+OjgGazgOXEl8oJyof3Z6Spx0iTzgnLKsMoK
-w9SRuoR3rHniVVMXwRpDXQR7d+kHOJV6CFZB0khVOBGsTcE6VzWsNVGQizfJptU+N4LlD3AbVfsu
-XsOahhvB8nrB08IrtcGNYNIct+EYl2+S6mr0D8kLUMrV6BfFRTzOGs4Ey8p1aNrUnssaliaMO/vV
-sfNi3AmW5j54DgUTO/dyJ1hab9iwHhLcNskP23ZMND0kewFBXek6vZvHg/hMiUPSN00z+OBasFig
-y8wSRfnZ0adSBz+sUVwFK4jbJhnPP06To1ETczpcCnavHhltHd82LU0AXDbJMGXBU8PSBAA8Jxk0
-wnNaqlGSJuAyg+dsXIV38iZqXU3iWsmodhetSNlDQgJGriZxbWVSe1hS/gQ+S/C6j4QEfES21vxU
-icXsoC4vC5mqJvbybyXgduucG/YWaYmmj+IdHvpoxFdt8ltRP5h3iZjRqfBh60C4t1rNY7rxAU95
-aYnhEp+/u8pgxGfeRCfyJIR5SkLfFOHYXMMzu63PEDF9WQnSo8MUmhduyUWYEzGyvnRmU3683ugG
-GAG/2bqJU4RnFDNCpsfWb5chswUnwb5Xg+hxiyo9w7MGJoSVpmYulam+A8scS+5nPYtf+s9mpZw7
-J1nayDnCVuu4Ck+E6DqIBYDHHR1+is/n8kVUhfBExMBFMzm4taafkXcWL9BSfBG/nNN8sutYcE3S
-d7XI3o6lSpIe/xcAIX/svzDxMVu22BAyLNKL2q9hwrdLiZWwXbP6B99GDLaGSpoOD6JPn4yxK1i8
-B0StY1zKsCJiQNxzQ0HRbAm2BsZN2TBDGVaE5USzIVjsNix2VrzWHmUwB6J5fD32uyKCzQ7OxG5D
-vzZuQ0E2osXjRlBMjvWe5WtYPE4b2BynXQJlMEToTUegmEiwM1mzQ1nBvqvH5ov1wlZHcA+AZHdc
-xQW7vNuQS9kBtzKs1IIRMM7b0q/YvGTzto4qbFutdV5FnLtLk2x3JVWUfXKTbIu9Opc2J6Osj19S
-HLfJKO64r6rg/wFBX3+2ZapW8wAAAABJRU5ErkJggg==
-"
-       id="image832"
-       x="141.05873"
-       y="76.816635" />
-  </g>
-</svg>

changedetectionio/static/images/pdf-icon.svg

@@ -1,9 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<svg xmlns="http://www.w3.org/2000/svg" width="75.320129mm" height="92.604164mm" viewBox="0 0 75.320129 92.604164">
-  <g transform="translate(53.548057 -183.975276) scale(1.4843)">
-    <path fill="#ff2116" d="M-29.632812 123.94727c-3.551967 0-6.44336 2.89347-6.44336 6.44531v49.49804c0 3.55185 2.891393 6.44532 6.44336 6.44532H8.2167969c3.5519661 0 6.4433591-2.89335 6.4433591-6.44532v-40.70117s.101353-1.19181-.416015-2.35156c-.484969-1.08711-1.275391-1.84375-1.275391-1.84375a1.0584391 1.0584391 0 0 0-.0059-.008l-9.3906254-9.21094a1.0584391 1.0584391 0 0 0-.015625-.0156s-.8017392-.76344-1.9902344-1.27344c-1.39939552-.6005-2.8417968-.53711-2.8417968-.53711l.021484-.002z" color="#000" font-family="sans-serif" overflow="visible" paint-order="markers fill stroke" style="line-height:normal;font-variant-ligatures:normal;font-variant-position:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-alternates:normal;font-feature-settings:normal;text-indent:0;text-align:start;text-decoration-line:none;text-decoration-style:solid;text-decoration-color:#000000;text-transform:none;text-orientation:mixed;white-space:normal;shape-padding:0;isolation:auto;mix-blend-mode:normal;solid-color:#000000;solid-opacity:1"/>
-    <path fill="#f5f5f5" d="M-29.632812 126.06445h28.3789058a1.0584391 1.0584391 0 0 0 .021484 0s1.13480448.011 1.96484378.36719c.79889772.34282 1.36536982.86176 1.36914062.86524.0000125.00001.00391.004.00391.004l9.3671868 9.18945s.564354.59582.837891 1.20899c.220779.49491.234375 1.40039.234375 1.40039a1.0584391 1.0584391 0 0 0-.002.0449v40.74609c0 2.41592-1.910258 4.32813-4.3261717 4.32813H-29.632812c-2.415914 0-4.326172-1.91209-4.326172-4.32813v-49.49804c0-2.41603 1.910258-4.32813 4.326172-4.32813z" color="#000" font-family="sans-serif" overflow="visible" paint-order="markers fill stroke" style="line-height:normal;font-variant-ligatures:normal;font-variant-position:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-alternates:normal;font-feature-settings:normal;text-indent:0;text-align:start;text-decoration-line:none;text-decoration-style:solid;text-decoration-color:#000000;text-transform:none;text-orientation:mixed;white-space:normal;shape-padding:0;isolation:auto;mix-blend-mode:normal;solid-color:#000000;solid-opacity:1"/>
-    <path fill="#ff2116" d="M-23.40766 161.09299c-1.45669-1.45669.11934-3.45839 4.39648-5.58397l2.69124-1.33743 1.04845-2.29399c.57665-1.26169 1.43729-3.32036 1.91254-4.5748l.8641-2.28082-.59546-1.68793c-.73217-2.07547-.99326-5.19438-.52872-6.31588.62923-1.51909 2.69029-1.36323 3.50626.26515.63727 1.27176.57212 3.57488-.18329 6.47946l-.6193 2.38125.5455.92604c.30003.50932 1.1764 1.71867 1.9475 2.68743l1.44924 1.80272 1.8033728-.23533c5.72900399-.74758 7.6912472.523 7.6912472 2.34476 0 2.29921-4.4984914 2.48899-8.2760865-.16423-.8499666-.59698-1.4336605-1.19001-1.4336605-1.19001s-2.3665326.48178-3.531704.79583c-1.202707.32417-1.80274.52719-3.564509 1.12186 0 0-.61814.89767-1.02094 1.55026-1.49858 2.4279-3.24833 4.43998-4.49793 5.1723-1.3991.81993-2.86584.87582-3.60433.13733zm2.28605-.81668c.81883-.50607 2.47616-2.46625 3.62341-4.28553l.46449-.73658-2.11497 1.06339c-3.26655 1.64239-4.76093 3.19033-3.98386 4.12664.43653.52598.95874.48237 2.01093-.16792zm21.21809-5.95578c.80089-.56097.68463-1.69142-.22082-2.1472-.70466-.35471-1.2726074-.42759-3.1031574-.40057-1.1249.0767-2.9337647.3034-3.2403347.37237 0 0 .993716.68678 1.434896.93922.58731.33544 2.0145161.95811 3.0565161 1.27706 1.02785.31461 1.6224.28144 2.0729-.0409zm-8.53152-3.54594c-.4847-.50952-1.30889-1.57296-1.83152-2.3632-.68353-.89643-1.02629-1.52887-1.02629-1.52887s-.4996 1.60694-.90948 2.57394l-1.27876 3.16076-.37075.71695s1.971043-.64627 2.97389-.90822c1.0621668-.27744 3.21787-.70134 3.21787-.70134zm-2.74938-11.02573c.12363-1.0375.1761-2.07346-.15724-2.59587-.9246-1.01077-2.04057-.16787-1.85154 2.23517.0636.8084.26443 2.19033.53292 3.04209l.48817 1.54863.34358-1.16638c.18897-.64151.47882-2.02015.64411-3.06364z"/>
-    <path fill="#2c2c2c" d="M-20.930423 167.83862h2.364986q1.133514 0 1.840213.2169.706698.20991 1.189489.9446.482795.72769.482795 1.75625 0 .94459-.391832 1.6233-.391833.67871-1.056548.97958-.65772.30087-2.02913.30087h-.818651v3.72941h-1.581322zm1.581322 1.22447v3.33058h.783664q1.049552 0 1.44838-.39184.405826-.39183.405826-1.27345 0-.65772-.265887-1.06355-.265884-.41282-.587747-.50378-.314866-.098-1.000572-.098zm5.50664-1.22447h2.148082q1.560333 0 2.4909318.55276.9375993.55276 1.4133973 1.6443.482791 1.09153.482791 2.42096 0 1.3994-.4338151 2.49793-.4268149 1.09153-1.3154348 1.76324-.8816233.67172-2.5189212.67172h-2.267031zm1.581326 1.26645v7.018h.657715q1.378411 0 2.001144-.9516.6227329-.95858.6227329-2.5539 0-3.5125-2.6238769-3.5125zm6.4722254-1.26645h5.30372941v1.26645H-4.2075842v2.85478h2.9807225v1.26646h-2.9807225v4.16322h-1.5813254z" font-family="Franklin Gothic Medium Cond" letter-spacing="0" style="line-height:125%;-inkscape-font-specification:'Franklin Gothic Medium Cond'" word-spacing="4.26000023"/>
-  </g>
-</svg>

changedetectionio/static/images/play.svg

@@ -1,122 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<svg
-   version="1.1"
-   id="Capa_1"
-   x="0px"
-   y="0px"
-   viewBox="0 0 15 14.998326"
-   xml:space="preserve"
-   width="15"
-   height="14.998326"
-   sodipodi:docname="play.svg"
-   inkscape:version="1.1.1 (1:1.1+202109281949+c3084ef5ed)"
-   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
-   id="namedview21"
-   pagecolor="#ffffff"
-   bordercolor="#666666"
-   borderopacity="1.0"
-   inkscape:pageshadow="2"
-   inkscape:pageopacity="0.0"
-   inkscape:pagecheckerboard="0"
-   showgrid="false"
-   inkscape:zoom="45.47174"
-   inkscape:cx="7.4991632"
-   inkscape:cy="7.4991632"
-   inkscape:window-width="1554"
-   inkscape:window-height="896"
-   inkscape:window-x="3048"
-   inkscape:window-y="227"
-   inkscape:window-maximized="0"
-   inkscape:current-layer="Capa_1" /><metadata
-   id="metadata39"><rdf:RDF><cc:Work
-       rdf:about=""><dc:format>image/svg+xml</dc:format><dc:type
-         rdf:resource="http://purl.org/dc/dcmitype/StillImage" /></cc:Work></rdf:RDF></metadata><defs
-   id="defs37" />
-<path
-   id="path2"
-   style="fill:#1b98f8;fill-opacity:1;stroke-width:0.0292893"
-   d="M 7.4980469,0 C 4.5496028,-0.04093755 1.7047721,1.8547661 0.58789062,4.5800781 -0.57819305,7.2574082 0.02636631,10.583252 2.0703125,12.671875 4.0368718,14.788335 7.2754393,15.560096 9.9882812,14.572266 12.800219,13.617028 14.874915,10.855516 14.986328,7.8847656 15.172991,4.9968456 13.497714,2.109448 10.910156,0.8203125 9.858961,0.28011352 8.6796569,-0.00179908 7.4980469,0 Z"
-   sodipodi:nodetypes="ccccccc" />
-<g
-   id="g4"
-   transform="translate(-0.01903604,0.02221043)">
-</g>
-<g
-   id="g6"
-   transform="translate(-0.01903604,0.02221043)">
-</g>
-<g
-   id="g8"
-   transform="translate(-0.01903604,0.02221043)">
-</g>
-<g
-   id="g10"
-   transform="translate(-0.01903604,0.02221043)">
-</g>
-<g
-   id="g12"
-   transform="translate(-0.01903604,0.02221043)">
-</g>
-<g
-   id="g14"
-   transform="translate(-0.01903604,0.02221043)">
-</g>
-<g
-   id="g16"
-   transform="translate(-0.01903604,0.02221043)">
-</g>
-<g
-   id="g18"
-   transform="translate(-0.01903604,0.02221043)">
-</g>
-<g
-   id="g20"
-   transform="translate(-0.01903604,0.02221043)">
-</g>
-<g
-   id="g22"
-   transform="translate(-0.01903604,0.02221043)">
-</g>
-<g
-   id="g24"
-   transform="translate(-0.01903604,0.02221043)">
-</g>
-<g
-   id="g26"
-   transform="translate(-0.01903604,0.02221043)">
-</g>
-<g
-   id="g28"
-   transform="translate(-0.01903604,0.02221043)">
-</g>
-<g
-   id="g30"
-   transform="translate(-0.01903604,0.02221043)">
-</g>
-<g
-   id="g32"
-   transform="translate(-0.01903604,0.02221043)">
-</g>
-<path
-   sodipodi:type="star"
-   style="fill:#ffffff;fill-opacity:1;stroke-width:37.7953;paint-order:stroke fill markers"
-   id="path1203"
-   inkscape:flatsided="false"
-   sodipodi:sides="3"
-   sodipodi:cx="7.2964563"
-   sodipodi:cy="7.3240671"
-   sodipodi:r1="3.805218"
-   sodipodi:r2="1.9026089"
-   sodipodi:arg1="-0.0017436774"
-   sodipodi:arg2="1.0454539"
-   inkscape:rounded="0"
-   inkscape:randomized="0"
-   d="M 11.101669,7.317432 8.2506324,8.9701135 5.3995964,10.622795 5.3938504,7.3273846 5.3881041,4.0319742 8.2448863,5.6747033 Z"
-   inkscape:transform-center-x="-0.94843001"
-   inkscape:transform-center-y="0.0033175346" /></svg>

changedetectionio/static/images/price-tag-icon.svg

@@ -1,2 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<svg width="83.39" height="89.648" enable-background="new 0 0 122.406 122.881" version="1.1" viewBox="0 0 83.39 89.648" xml:space="preserve" xmlns="http://www.w3.org/2000/svg"><g transform="translate(5e-4 -33.234)"><path d="m44.239 42.946-39.111 39.896 34.908 34.91 39.09-39.876-1.149-34.931zm-0.91791 42.273c0.979-0.979 1.507-1.99 1.577-3.027 0.077-1.043-0.248-2.424-0.967-4.135-0.725-1.717-1.348-3.346-1.87-4.885s-0.814-3.014-0.897-4.432c-0.07-1.42 0.134-2.768 0.624-4.045 0.477-1.279 1.348-2.545 2.607-3.804 2.099-2.099 4.535-3.123 7.314-3.065 2.773 0.063 5.457 1.158 8.04 3.294l2.881 3.034c1.946 2.607 2.799 5.33 2.557 8.166-0.235 2.83-1.532 5.426-3.893 7.785l-6.296-6.297c1.291-1.291 2.035-2.531 2.238-3.727 0.191-1.197-0.165-2.252-1.081-3.168-0.821-0.82-1.717-1.195-2.69-1.139-0.967 0.064-1.908 0.547-2.817 1.457-0.922 0.922-1.393 1.914-1.412 2.977s0.306 2.416 0.973 4.064c0.661 1.652 1.24 3.25 1.736 4.801 0.496 1.553 0.782 3.035 0.858 4.445 0.076 1.426-0.127 2.787-0.591 4.104-0.477 1.316-1.336 2.596-2.588 3.848-2.125 2.125-4.522 3.186-7.212 3.18s-5.311-1.063-7.855-3.16l-3.747 3.746-2.964-2.965 3.766-3.764c-2.423-2.996-3.568-5.998-3.447-9.02 0.127-3.014 1.476-5.813 4.045-8.383l6.278 6.277c-1.412 1.412-2.175 2.799-2.277 4.16-0.108 1.367 0.414 2.627 1.571 3.783 0.839 0.84 1.755 1.26 2.741 1.242 0.985-0.017 1.92-0.47 2.798-1.347zm21.127-46.435h17.457c-0.0269 2.2368 0.69936 16.025 0.69936 16.025l0.785 23.858c0.019 0.609-0.221 1.164-0.619 1.564l5e-3 4e-3 -41.236 42.022c-0.82213 0.8378-2.175 0.83-3.004 0l-37.913-37.91c-0.83-0.83-0.83-2.176 0-3.006l41.236-42.021c0.39287-0.42671 1.502-0.53568 1.502-0.53568zm18.011 11.59c-59.392-29.687-29.696-14.843 0 0z"/></g></svg>

changedetectionio/static/images/spread-white.svg

@@ -1,20 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<svg
-   width="18"
-   height="19.92"
-   viewBox="0 0 18 19.92"
-   version="1.1"
-   id="svg6"
-   xmlns="http://www.w3.org/2000/svg"
-   xmlns:svg="http://www.w3.org/2000/svg">
-  <defs
-     id="defs10" />
-  <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:#ffffff;fill-opacity:1" />
-</svg>

changedetectionio/static/images/spread.svg

@@ -1,5 +1,46 @@
 <?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">
-  <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
+   width="18"
+   height="19.92"
+   viewBox="0 0 18 19.92"
+   version="1.1"
+   id="svg6"
+   sodipodi:docname="spread.svg"
+   inkscape:version="1.1.1 (1:1.1+202109281949+c3084ef5ed)"
+   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="defs10" />
+  <sodipodi:namedview
+     id="namedview8"
+     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="28.416667"
+     inkscape:cx="9.0087975"
+     inkscape:cy="9.9941348"
+     inkscape:window-width="1920"
+     inkscape:window-height="1056"
+     inkscape:window-x="1920"
+     inkscape:window-y="0"
+     inkscape:window-maximized="1"
+     inkscape:current-layer="svg6" />
+  <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/js/browser-steps.js

@@ -1,454 +0,0 @@
-$(document).ready(function () {
-
-    // duplicate
-    var csrftoken = $('input[name=csrf_token]').val();
-    $.ajaxSetup({
-        beforeSend: function (xhr, settings) {
-            if (!/^(GET|HEAD|OPTIONS|TRACE)$/i.test(settings.type) && !this.crossDomain) {
-                xhr.setRequestHeader("X-CSRFToken", csrftoken)
-            }
-        }
-    })
-    var browsersteps_session_id;
-    var browserless_seconds_remaining = 0;
-    var apply_buttons_disabled = false;
-    var include_text_elements = $("#include_text_elements");
-    var xpath_data = false;
-    var current_selected_i;
-    var state_clicked = false;
-    var c;
-
-    // redline highlight context
-    var ctx;
-    var last_click_xy = {'x': -1, 'y': -1}
-
-    $(window).resize(function () {
-        set_scale();
-    });
-    // Should always be disabled
-    $('#browser_steps >li:first-child select').val('Goto site').attr('disabled', 'disabled');
-
-    $('#browsersteps-click-start').click(function () {
-        $("#browsersteps-click-start").fadeOut();
-        $("#browsersteps-selector-wrapper .spinner").fadeIn();
-        start();
-    });
-
-    $('a#browsersteps-tab').click(function () {
-        reset();
-    });
-
-    window.addEventListener('hashchange', function () {
-        if (window.location.hash == '#browser-steps') {
-            reset();
-        }
-    });
-
-    function reset() {
-        xpath_data = false;
-        $('#browsersteps-img').removeAttr('src');
-        $("#browsersteps-click-start").show();
-        $("#browsersteps-selector-wrapper .spinner").hide();
-        browserless_seconds_remaining = 0;
-        browsersteps_session_id = false;
-        apply_buttons_disabled = false;
-        ctx.clearRect(0, 0, c.width, c.height);
-        set_first_gotosite_disabled();
-    }
-
-    function set_first_gotosite_disabled() {
-        $('#browser_steps >li:first-child select').val('Goto site').attr('disabled', 'disabled');
-        $('#browser_steps >li:first-child').css('opacity', '0.5');
-    }
-
-    // Show seconds remaining until playwright/browserless needs to restart the session
-    // (See comment at the top of changedetectionio/blueprint/browser_steps/__init__.py )
-    setInterval(() => {
-        if (browserless_seconds_remaining >= 1) {
-            document.getElementById('browserless-seconds-remaining').innerText = browserless_seconds_remaining + " seconds remaining in session";
-            browserless_seconds_remaining -= 1;
-        }
-    }, "1000")
-
-
-    function set_scale() {
-
-        // some things to check if the scaling doesnt work
-        // - that the widths/sizes really are about the actual screen size cat elements.json |grep -o width......|sort|uniq
-        selector_image = $("img#browsersteps-img")[0];
-        selector_image_rect = selector_image.getBoundingClientRect();
-
-        // make the canvas and input steps the same size as the image
-        $('#browsersteps-selector-canvas').attr('height', selector_image_rect.height).attr('width', selector_image_rect.width);
-        //$('#browsersteps-selector-wrapper').attr('width', selector_image_rect.width);
-        $('#browser-steps-ui').attr('width', selector_image_rect.width);
-
-        x_scale = selector_image_rect.width / xpath_data['browser_width'];
-        y_scale = selector_image_rect.height / selector_image.naturalHeight;
-        ctx.strokeStyle = 'rgba(255,0,0, 0.9)';
-        ctx.fillStyle = 'rgba(255,0,0, 0.1)';
-        ctx.lineWidth = 3;
-        console.log("scaling set  x: " + x_scale + " by y:" + y_scale);
-    }
-
-    // bootstrap it, this will trigger everything else
-    $('#browsersteps-img').bind('load', function () {
-        $('body').addClass('full-width');
-        console.log("Loaded background...");
-
-        document.getElementById("browsersteps-selector-canvas");
-        c = document.getElementById("browsersteps-selector-canvas");
-        // redline highlight context
-        ctx = c.getContext("2d");
-        // @todo is click better?
-        $('#browsersteps-selector-canvas').off("mousemove mousedown click");
-        // Undo disable_browsersteps_ui
-        $("#browser-steps-ui").css('opacity', '1.0');
-
-        // init
-        set_scale();
-
-        // @todo click ? some better library?
-        $('#browsersteps-selector-canvas').bind('click', function (e) {
-            // https://developer.mozilla.org/en-US/docs/Web/API/MouseEvent
-            e.preventDefault()
-        });
-
-        $('#browsersteps-selector-canvas').bind('mousedown', function (e) {
-            // https://developer.mozilla.org/en-US/docs/Web/API/MouseEvent
-            e.preventDefault()
-            console.log(e);
-            console.log("current xpath in index is " + current_selected_i);
-            last_click_xy = {'x': parseInt((1 / x_scale) * e.offsetX), 'y': parseInt((1 / y_scale) * e.offsetY)}
-            process_selected(current_selected_i);
-            current_selected_i = false;
-
-            // if process selected returned false, then best we can do is offer a x,y click :(
-            if (!found_something) {
-                var first_available = $("ul#browser_steps li.empty").first();
-                $('select', first_available).val('Click X,Y').change();
-                $('input[type=text]', first_available).first().val(last_click_xy['x'] + ',' + last_click_xy['y']);
-                draw_circle_on_canvas(e.offsetX, e.offsetY);
-            }
-        });
-
-        $('#browsersteps-selector-canvas').bind('mousemove', function (e) {
-            if (!xpath_data) {
-                return;
-            }
-
-            // checkbox if find elements is enabled
-            ctx.clearRect(0, 0, c.width, c.height);
-            ctx.fillStyle = 'rgba(255,0,0, 0.1)';
-            ctx.strokeStyle = 'rgba(255,0,0, 0.9)';
-
-            // Add in offset
-            if ((typeof e.offsetX === "undefined" || typeof e.offsetY === "undefined") || (e.offsetX === 0 && e.offsetY === 0)) {
-                var targetOffset = $(e.target).offset();
-                e.offsetX = e.pageX - targetOffset.left;
-                e.offsetY = e.pageY - targetOffset.top;
-            }
-            current_selected_i = false;
-            // Reverse order - the most specific one should be deeper/"laster"
-            // Basically, find the most 'deepest'
-            //$('#browsersteps-selector-canvas').css('cursor', 'pointer');
-            for (var i = xpath_data['size_pos'].length; i !== 0; i--) {
-                // draw all of them? let them choose somehow?
-                var sel = xpath_data['size_pos'][i - 1];
-                // If we are in a bounding-box
-                if (e.offsetY > sel.top * y_scale && e.offsetY < sel.top * y_scale + sel.height * y_scale
-                    &&
-                    e.offsetX > sel.left * y_scale && e.offsetX < sel.left * y_scale + sel.width * y_scale
-
-                ) {
-                    // Only highlight these interesting types
-                    if (1) {
-                        ctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-                        ctx.fillRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-                        current_selected_i = i - 1;
-                        break;
-
-                        // find the smallest one at this x,y
-                        // does it mean sort the xpath list by size (w*h) i think so!
-                    } else {
-
-                        if (include_text_elements[0].checked === true) {
-                            // blue one with background instead?
-                            ctx.fillStyle = 'rgba(0,0,255, 0.1)';
-                            ctx.strokeStyle = 'rgba(0,0,200, 0.7)';
-                            $('#browsersteps-selector-canvas').css('cursor', 'grab');
-                            ctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-                            ctx.fillRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-                            current_selected_i = i - 1;
-                            break;
-                        }
-                    }
-                }
-            }
-
-        }.debounce(10));
-    });
-
-//    $("#browser-steps-fieldlist").bind('mouseover', function(e) {
-//        console.log(e.xpath_data_index);
-    // });
-
-
-    // callback for clicking on an xpath on the canvas
-    function process_selected(xpath_data_index) {
-        found_something = false;
-        var first_available = $("ul#browser_steps li.empty").first();
-
-
-        if (xpath_data_index !== false) {
-            // Nothing focused, so fill in a new one
-            // if inpt type button or <button>
-            // from the top, find the next not used one and use it
-            var x = xpath_data['size_pos'][xpath_data_index];
-            console.log(x);
-            if (x && first_available.length) {
-                // @todo will it let you click shit that has a layer ontop? probably not.
-                if (x['tagtype'] === 'text' || x['tagtype'] === 'email' || x['tagName'] === 'textarea' || x['tagtype'] === 'password' || x['tagtype'] === 'search') {
-                    $('select', first_available).val('Enter text in field').change();
-                    $('input[type=text]', first_available).first().val(x['xpath']);
-                    $('input[placeholder="Value"]', first_available).addClass('ok').click().focus();
-                    found_something = true;
-                } else {
-                    if (x['isClickable'] || x['tagName'].startsWith('h') || x['tagName'] === 'a' || x['tagName'] === 'button' || x['tagtype'] === 'submit' || x['tagtype'] === 'checkbox' || x['tagtype'] === 'radio' || x['tagtype'] === 'li') {
-                        $('select', first_available).val('Click element').change();
-                        $('input[type=text]', first_available).first().val(x['xpath']);
-                        found_something = true;
-                    }
-                }
-
-                first_available.xpath_data_index = xpath_data_index;
-
-                if (!found_something) {
-                    if (include_text_elements[0].checked === true) {
-                        // Suggest that we use as filter?
-                        // @todo filters should always be in the last steps, nothing non-filter after it
-                        found_something = true;
-                        ctx.strokeStyle = 'rgba(0,0,255, 0.9)';
-                        ctx.fillStyle = 'rgba(0,0,255, 0.1)';
-                        $('select', first_available).val('Extract text and use as filter').change();
-                        $('input[type=text]', first_available).first().val(x['xpath']);
-                        include_text_elements[0].checked = false;
-                    }
-                }
-            }
-        }
-    }
-
-    function draw_circle_on_canvas(x, y) {
-        ctx.beginPath();
-        ctx.arc(x, y, 8, 0, 2 * Math.PI, false);
-        ctx.fillStyle = 'rgba(255,0,0, 0.6)';
-        ctx.fill();
-    }
-
-    function start() {
-        console.log("Starting browser-steps UI");
-        browsersteps_session_id = Date.now();
-        // @todo This setting of the first one should be done at the datalayer but wtforms doesnt wanna play nice
-        $('#browser_steps >li:first-child').removeClass('empty');
-        set_first_gotosite_disabled();
-        $('#browser-steps-ui .loader .spinner').show();
-        $('.clear,.remove', $('#browser_steps >li:first-child')).hide();
-        $.ajax({
-            type: "GET",
-            url: browser_steps_sync_url + "&browsersteps_session_id=" + browsersteps_session_id,
-            statusCode: {
-                400: function () {
-                    // More than likely the CSRF token was lost when the server restarted
-                    alert("There was a problem processing the request, please reload the page.");
-                }
-            }
-        }).done(function (data) {
-            xpath_data = data.xpath_data;
-            $("#loading-status-text").fadeIn();
-            // This should trigger 'Goto site'
-            console.log("Got startup response, requesting Goto-Site (first) step fake click");
-            $('#browser_steps >li:first-child .apply').click();
-            browserless_seconds_remaining = data.browser_time_remaining;
-            set_first_gotosite_disabled();
-        }).fail(function (data) {
-            console.log(data);
-            alert('There was an error communicating with the server.');
-        });
-
-    }
-
-    function disable_browsersteps_ui() {
-        set_first_gotosite_disabled();
-        $("#browser-steps-ui").css('opacity', '0.3');
-        $('#browsersteps-selector-canvas').off("mousemove mousedown click");
-    }
-
-
-    ////////////////////////// STEPS UI ////////////////////
-    $('ul#browser_steps [type="text"]').keydown(function (e) {
-        if (e.keyCode === 13) {
-            // hitting [enter] in a browser-step input should trigger the 'Apply'
-            e.preventDefault();
-            $(".apply", $(this).closest('li')).click();
-            return false;
-        }
-    });
-
-    // Look up which step was selected, and enable or disable the related extra fields
-    // So that people using it dont' get confused
-    $('ul#browser_steps select').on("change", function () {
-        var config = browser_steps_config[$(this).val()].split(' ');
-        var elem_selector = $('tr:nth-child(2) input', $(this).closest('tbody'));
-        var elem_value = $('tr:nth-child(3) input', $(this).closest('tbody'));
-
-        if (config[0] == 0) {
-            $(elem_selector).fadeOut();
-        } else {
-            $(elem_selector).fadeIn();
-        }
-        if (config[1] == 0) {
-            $(elem_value).fadeOut();
-        } else {
-            $(elem_value).fadeIn();
-        }
-
-        if ($(this).val() === 'Click X,Y' && last_click_xy['x'] > 0 && $(elem_value).val().length === 0) {
-            // @todo handle scale
-            $(elem_value).val(last_click_xy['x'] + ',' + last_click_xy['y']);
-        }
-    }).change();
-
-    function set_greyed_state() {
-        $('ul#browser_steps select').not('option:selected[value="Choose one"]').closest('li').removeClass('empty');
-        $('ul#browser_steps select option:selected[value="Choose one"]').closest('li').addClass('empty');
-    }
-
-    // Add the extra buttons to the steps
-    $('ul#browser_steps li').each(function (i) {
-            var s = '<div class="control">' + '<a data-step-index=' + i + ' class="pure-button button-secondary button-green button-xsmall apply" >Apply</a>&nbsp;';
-            if (i > 0) {
-                // The first step never gets these (Goto-site)
-                s += '<a data-step-index=' + i + ' class="pure-button button-secondary button-xsmall clear" >Clear</a>&nbsp;' +
-                    '<a data-step-index=' + i + ' class="pure-button button-secondary button-red button-xsmall remove" >Remove</a>';
-            }
-            s += '</div>';
-            $(this).append(s)
-        }
-    );
-
-    $('ul#browser_steps li .control .clear').click(function (element) {
-        $("select", $(this).closest('li')).val("Choose one").change();
-        $(":text", $(this).closest('li')).val('');
-    });
-
-
-    $('ul#browser_steps li .control .remove').click(function (element) {
-        // so you wanna remove the 2nd (3rd spot 0,1,2,...)
-        var p = $("#browser_steps li").index($(this).closest('li'));
-
-        var elem_to_remove = $("#browser_steps li")[p];
-        $('.clear', elem_to_remove).click();
-        $("#browser_steps li").slice(p, 10).each(function (index) {
-            // get the next one's value from where we clicked
-            var next = $("#browser_steps li")[p + index + 1];
-            if (next) {
-                // and set THIS ones value from the next one
-                var n = $('input', next);
-                $("select", $(this)).val($('select', next).val());
-                $('input', this)[0].value = $(n)[0].value;
-                $('input', this)[1].value = $(n)[1].value;
-                // Triggers reconfiguring the field based on the system config
-                $("select", $(this)).change();
-            }
-
-        });
-
-        // Reset their hidden/empty states
-        set_greyed_state();
-    });
-
-    $('ul#browser_steps li .control .apply').click(function (event) {
-        // sequential requests @todo refactor
-        if (apply_buttons_disabled) {
-            return;
-        }
-
-        var current_data = $(event.currentTarget).closest('li');
-        $('#browser-steps-ui .loader .spinner').fadeIn();
-        apply_buttons_disabled = true;
-        $('ul#browser_steps li .control .apply').css('opacity', 0.5);
-        $("#browsersteps-img").css('opacity', 0.65);
-
-        var is_last_step = 0;
-        var step_n = $(event.currentTarget).data('step-index');
-
-        // On the last step, we should also be getting data ready for the visual selector
-        $('ul#browser_steps li select').each(function (i) {
-            if ($(this).val() !== 'Choose one') {
-                is_last_step += 1;
-            }
-        });
-
-        if (is_last_step == (step_n + 1)) {
-            is_last_step = true;
-        } else {
-            is_last_step = false;
-        }
-
-        console.log("Requesting step via POST " + $("select[id$='operation']", current_data).first().val());
-        // POST the currently clicked step form widget back and await response, redraw
-        $.ajax({
-            method: "POST",
-            url: browser_steps_sync_url + "&browsersteps_session_id=" + browsersteps_session_id,
-            data: {
-                'operation': $("select[id$='operation']", current_data).first().val(),
-                'selector': $("input[id$='selector']", current_data).first().val(),
-                'optional_value': $("input[id$='optional_value']", current_data).first().val(),
-                'step_n': step_n,
-                'is_last_step': is_last_step
-            },
-            statusCode: {
-                400: function () {
-                    // More than likely the CSRF token was lost when the server restarted
-                    alert("There was a problem processing the request, please reload the page.");
-                    $("#loading-status-text").hide();
-                    $('#browser-steps-ui .loader .spinner').fadeOut();
-                },
-                401: function (data) {
-                    // More than likely the CSRF token was lost when the server restarted
-                    alert(data.responseText);
-                    $("#loading-status-text").hide();
-                    $('#browser-steps-ui .loader .spinner').fadeOut();
-                }
-            }
-        }).done(function (data) {
-            // it should return the new state (selectors available and screenshot)
-            xpath_data = data.xpath_data;
-            $('#browsersteps-img').attr('src', data.screenshot);
-            $('#browser-steps-ui .loader .spinner').fadeOut();
-            apply_buttons_disabled = false;
-            $("#browsersteps-img").css('opacity', 1);
-            $('ul#browser_steps li .control .apply').css('opacity', 1);
-            browserless_seconds_remaining = data.browser_time_remaining;
-            $("#loading-status-text").hide();
-            set_first_gotosite_disabled();
-        }).fail(function (data) {
-            console.log(data);
-            if (data.responseText.includes("Browser session expired")) {
-                disable_browsersteps_ui();
-            }
-            apply_buttons_disabled = false;
-            $("#loading-status-text").hide();
-            $('ul#browser_steps li .control .apply').css('opacity', 1);
-            $("#browsersteps-img").css('opacity', 1);
-        });
-
-    });
-
-
-    $("ul#browser_steps select").change(function () {
-        set_greyed_state();
-    }).change();
-
-});

changedetectionio/static/js/diff-overview.js

@@ -1,25 +0,0 @@
-$(document).ready(function () {
-    // Load it when the #screenshot tab is in use, so we dont give a slow experience when waiting for the text diff to load
-    window.addEventListener('hashchange', function (e) {
-        toggle(location.hash);
-    }, false);
-
-    toggle(location.hash);
-
-    function toggle(hash_name) {
-        if (hash_name === '#screenshot') {
-            $("img#screenshot-img").attr('src', screenshot_url);
-            $("#settings").hide();
-        } else if (hash_name === '#error-screenshot') {
-            $("img#error-screenshot-img").attr('src', error_screenshot_url);
-            $("#settings").hide();
-        } else if (hash_name === '#extract') {
-            $("#settings").hide();
-        }
-
-
-        else {
-            $("#settings").show();
-        }
-    }
-});

changedetectionio/static/js/diff-render.js

@@ -1,110 +0,0 @@
-var a = document.getElementById("a");
-var b = document.getElementById("b");
-var result = document.getElementById("result");
-
-function changed() {
-  // https://github.com/kpdecker/jsdiff/issues/389
-  // I would love to use `{ignoreWhitespace: true}` here but it breaks the formatting
-  options = {
-    ignoreWhitespace: document.getElementById("ignoreWhitespace").checked,
-  };
-
-  var diff = Diff[window.diffType](a.textContent, b.textContent, options);
-  var fragment = document.createDocumentFragment();
-  for (var i = 0; i < diff.length; i++) {
-    if (diff[i].added && diff[i + 1] && diff[i + 1].removed) {
-      var swap = diff[i];
-      diff[i] = diff[i + 1];
-      diff[i + 1] = swap;
-    }
-
-    var node;
-    if (diff[i].removed) {
-      node = document.createElement("del");
-      node.classList.add("change");
-      const wrapper = node.appendChild(document.createElement("span"));
-      wrapper.appendChild(document.createTextNode(diff[i].value));
-    } else if (diff[i].added) {
-      node = document.createElement("ins");
-      node.classList.add("change");
-      const wrapper = node.appendChild(document.createElement("span"));
-      wrapper.appendChild(document.createTextNode(diff[i].value));
-    } else {
-      node = document.createTextNode(diff[i].value);
-    }
-    fragment.appendChild(node);
-  }
-
-  result.textContent = "";
-  result.appendChild(fragment);
-
-  // Jump at start
-  inputs.current = 0;
-  next_diff();
-}
-
-window.onload = function () {
-  /* Convert what is options from UTC time.time() to local browser time */
-  var diffList = document.getElementById("diff-version");
-  if (typeof diffList != "undefined" && diffList != null) {
-    for (var option of diffList.options) {
-      var dateObject = new Date(option.value * 1000);
-      option.label = dateObject.toLocaleString();
-    }
-  }
-
-  /* Set current version date as local time in the browser also */
-  var current_v = document.getElementById("current-v-date");
-  var dateObject = new Date(newest_version_timestamp * 1000);
-  current_v.innerHTML = dateObject.toLocaleString();
-  onDiffTypeChange(
-    document.querySelector('#settings [name="diff_type"]:checked'),
-  );
-  changed();
-};
-
-a.onpaste = a.onchange = b.onpaste = b.onchange = changed;
-
-if ("oninput" in a) {
-  a.oninput = b.oninput = changed;
-} else {
-  a.onkeyup = b.onkeyup = changed;
-}
-
-function onDiffTypeChange(radio) {
-  window.diffType = radio.value;
-  // Not necessary
-  //	document.title = "Diff " + radio.value.slice(4);
-}
-
-var radio = document.getElementsByName("diff_type");
-for (var i = 0; i < radio.length; i++) {
-  radio[i].onchange = function (e) {
-    onDiffTypeChange(e.target);
-    changed();
-  };
-}
-
-document.getElementById("ignoreWhitespace").onchange = function (e) {
-  changed();
-};
-
-var inputs = document.getElementsByClassName("change");
-inputs.current = 0;
-
-function next_diff() {
-  var element = inputs[inputs.current];
-  var headerOffset = 80;
-  var elementPosition = element.getBoundingClientRect().top;
-  var offsetPosition = elementPosition - headerOffset + window.scrollY;
-
-  window.scrollTo({
-    top: offsetPosition,
-    behavior: "smooth",
-  });
-
-  inputs.current++;
-  if (inputs.current >= inputs.length) {
-    inputs.current = 0;
-  }
-}

changedetectionio/static/js/global-settings.js

@@ -1,36 +0,0 @@
-$(document).ready(function () {
-    function toggle() {
-        if ($('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();
-        },
-        function () {
-            $("#api-key-copy").hide();
-        }
-    ).click(function (e) {
-        $("#api-key-copy").html('copied');
-        var range = document.createRange();
-        var n = $("#api-key")[0];
-        range.selectNode(n);
-        window.getSelection().removeAllRanges();
-        window.getSelection().addRange(range);
-        document.execCommand("copy");
-        window.getSelection().removeAllRanges();
-
-    });
-});
-

changedetectionio/static/js/limit.js

@@ -1,56 +0,0 @@
-/**
- * debounce
- * @param {integer} milliseconds This param indicates the number of milliseconds
- *     to wait after the last call before calling the original function.
- * @param {object} What "this" refers to in the returned function.
- * @return {function} This returns a function that when called will wait the
- *     indicated number of milliseconds after the last call before
- *     calling the original function.
- */
-Function.prototype.debounce = function (milliseconds, context) {
-    var baseFunction = this,
-        timer = null,
-        wait = milliseconds;
-
-    return function () {
-        var self = context || this,
-            args = arguments;
-
-        function complete() {
-            baseFunction.apply(self, args);
-            timer = null;
-        }
-
-        if (timer) {
-            clearTimeout(timer);
-        }
-
-        timer = setTimeout(complete, wait);
-    };
-};
-
-/**
-* throttle
-* @param {integer} milliseconds This param indicates the number of milliseconds
-*     to wait between calls before calling the original function.
-* @param {object} What "this" refers to in the returned function.
-* @return {function} This returns a function that when called will wait the
-*     indicated number of milliseconds between calls before
-*     calling the original function.
-*/
-Function.prototype.throttle = function (milliseconds, context) {
-    var baseFunction = this,
-        lastEventTimestamp = null,
-        limit = milliseconds;
-
-    return function () {
-        var self = context || this,
-            args = arguments,
-            now = Date.now();
-
-        if (!lastEventTimestamp || now - lastEventTimestamp >= limit) {
-            lastEventTimestamp = now;
-            baseFunction.apply(self, args);
-        }
-    };
-};

changedetectionio/static/js/notifications.js

@@ -40,19 +40,13 @@ $(document).ready(function() {
     $.ajax({
       type: "POST",
       url: notification_base_url,
-      data : data,
-        statusCode: {
-        400: function() {
-            // More than likely the CSRF token was lost when the server restarted
-          alert("There was a problem processing the request, please reload the page.");
-        }
-      }
+      data : data
     }).done(function(data){
       console.log(data);
       alert('Sent');
     }).fail(function(data){
       console.log(data);
-      alert('There was an error communicating with the server.');
+      alert('Error: '+data.responseJSON.error);
     })
   });
 });

changedetectionio/static/js/stepper.js

@@ -1,34 +0,0 @@
-$(document).ready(function(){
-   checkUserVal();
-   $('#fetch_backend input').on('change', checkUserVal);
-});
-
-var checkUserVal = function(){
-    if($('#fetch_backend input:checked').val()=='html_requests') {
-      $('#request-override').show();
-      $('#webdriver-stepper').hide();
-    } else {
-      $('#request-override').hide();
-      $('#webdriver-stepper').show();
-    }
-};
-
-$('a.row-options').on('click', function(){
-    var row=$(this.closest('tr'));
-    switch($(this).data("action")) {
-      case 'remove':
-        $(row).remove();
-      break;
-      case 'add':
-        var new_row=$(row).clone(true).insertAfter($(row));
-        $('input', new_new).val("");
-      break;
-      case 'add':
-        var new_row=$(row).clone(true).insertAfter($(row));
-        $('input', new_new).val("");
-      break;
-      case 'resend-step':
-
-      break;
-    }
-});

changedetectionio/static/js/tabs.js

@@ -1,49 +1,55 @@
 // Rewrite this is a plugin.. is all this JS really 'worth it?'
 
-window.addEventListener('hashchange', function () {
-    var tabs = document.getElementsByClassName('active');
-    while (tabs[0]) {
-        tabs[0].classList.remove('active');
-        document.body.classList.remove('full-width');
-    }
-    set_active_tab();
+
+if(!window.location.hash) {
+  var tab=document.querySelectorAll("#default-tab a");
+  tab[0].click();
+}
+
+window.addEventListener('hashchange', function() {
+  var tabs = document.getElementsByClassName('active');
+  while (tabs[0]) {
+    tabs[0].classList.remove('active')
+  }
+  set_active_tab();
 }, false);
 
-var has_errors = document.querySelectorAll(".messages .error");
+var has_errors=document.querySelectorAll(".messages .error");
 if (!has_errors.length) {
-    if (document.location.hash == "") {
-        document.querySelector(".tabs ul li:first-child a").click();
+    if (document.location.hash == "" ) {
+        document.location.hash = "#general";
+        document.getElementById("default-tab").className = "active";
     } else {
         set_active_tab();
     }
 } else {
-    focus_error_tab();
+  focus_error_tab();
 }
 
 function set_active_tab() {
-    document.body.classList.remove('full-width');
-    var tab = document.querySelectorAll("a[href='" + location.hash + "']");
-    if (tab.length) {
-        tab[0].parentElement.className = "active";
-    }
+  var tab=document.querySelectorAll("a[href='"+location.hash+"']");
+  if (tab.length) {
+    tab[0].parentElement.className="active";
+  }
     // hash could move the page down
     window.scrollTo(0, 0);
 }
 
 function focus_error_tab() {
-    // time to use jquery or vuejs really,
-    // activate the tab with the error
-    var tabs = document.querySelectorAll('.tabs li a'), i;
+  // time to use jquery or vuejs really,
+  // activate the tab with the error
+    var tabs = document.querySelectorAll('.tabs li a'),i;
     for (i = 0; i < tabs.length; ++i) {
-        var tab_name = tabs[i].hash.replace('#', '');
-        var pane_errors = document.querySelectorAll('#' + tab_name + ' .error')
-        if (pane_errors.length) {
-            document.location.hash = '#' + tab_name;
-            return true;
-        }
+      var tab_name=tabs[i].hash.replace('#','');
+      var pane_errors=document.querySelectorAll('#'+tab_name+' .error')
+      if (pane_errors.length) {
+        document.location.hash = '#'+tab_name;
+        return true;
+      }
     }
     return false;
 }
 
 
 
+

changedetectionio/static/js/toggle-theme.js

@@ -1,24 +0,0 @@
-/**
- * @file
- * Toggles theme between light and dark mode.
- */
-$(document).ready(function () {
-  const button = document.getElementsByClassName("toggle-theme")[0];
-
-  button.onclick = () => {
-    const htmlElement = document.getElementsByTagName("html");
-    const isDarkMode = htmlElement[0].dataset.darkmode === "true";
-    htmlElement[0].dataset.darkmode = !isDarkMode;
-    if (isDarkMode) {
-      button.classList.remove("dark");
-      setCookieValue(false);
-    } else {
-      button.classList.add("dark");
-      setCookieValue(true);
-    }
-  };
-
-  const setCookieValue = (value) => {
-    document.cookie = `css_dark_mode=${value};max-age=31536000;path=/`
-  }
-});

changedetectionio/static/js/visual-selector.js

@@ -1,244 +0,0 @@
-// Copyright (C) 2021 Leigh Morresi (dgtlmoon@gmail.com)
-// All rights reserved.
-// yes - this is really a hack, if you are a front-ender and want to help, please get in touch!
-
-$(document).ready(function () {
-
-    var current_selected_i;
-    var state_clicked = false;
-
-    var c;
-
-    // greyed out fill context
-    var xctx;
-    // redline highlight context
-    var ctx;
-
-    var current_default_xpath = [];
-    var x_scale = 1;
-    var y_scale = 1;
-    var selector_image;
-    var selector_image_rect;
-    var selector_data;
-
-    $('#visualselector-tab').click(function () {
-        $("img#selector-background").off('load');
-        state_clicked = false;
-        current_selected_i = false;
-        bootstrap_visualselector();
-    });
-
-    $(document).on('keydown', function (event) {
-        if ($("img#selector-background").is(":visible")) {
-            if (event.key == "Escape") {
-                state_clicked = false;
-                ctx.clearRect(0, 0, c.width, c.height);
-            }
-        }
-    });
-
-    // For when the page loads
-    if (!window.location.hash || window.location.hash != '#visualselector') {
-        $("img#selector-background").attr('src', '');
-        return;
-    }
-
-    // Handle clearing button/link
-    $('#clear-selector').on('click', function (event) {
-        if (!state_clicked) {
-            alert('Oops, Nothing selected!');
-        }
-        state_clicked = false;
-        ctx.clearRect(0, 0, c.width, c.height);
-        xctx.clearRect(0, 0, c.width, c.height);
-        $("#include_filters").val('');
-    });
-
-
-    bootstrap_visualselector();
-
-
-    function bootstrap_visualselector() {
-        if (1) {
-            // bootstrap it, this will trigger everything else
-            $("img#selector-background").bind('load', function () {
-                console.log("Loaded background...");
-                c = document.getElementById("selector-canvas");
-                // greyed out fill context
-                xctx = c.getContext("2d");
-                // redline highlight context
-                ctx = c.getContext("2d");
-                if ($("#include_filters").val().trim().length) {
-                    current_default_xpath = $("#include_filters").val().split(/\r?\n/g);
-                } else {
-                    current_default_xpath = [];
-                }
-                fetch_data();
-                $('#selector-canvas').off("mousemove mousedown");
-                // screenshot_url defined in the edit.html template
-            }).attr("src", screenshot_url);
-        }
-        // Tell visualSelector that the image should update
-        var s = $("img#selector-background").attr('src')+"?"+ new Date().getTime();
-        $("img#selector-background").attr('src',s)
-    }
-
-    function fetch_data() {
-        // Image is ready
-        $('.fetching-update-notice').html("Fetching element data..");
-
-        $.ajax({
-            url: watch_visual_selector_data_url,
-            context: document.body
-        }).done(function (data) {
-            $('.fetching-update-notice').html("Rendering..");
-            selector_data = data;
-            console.log("Reported browser width from backend: " + data['browser_width']);
-            state_clicked = false;
-            set_scale();
-            reflow_selector();
-            $('.fetching-update-notice').fadeOut();
-        });
-    };
-
-
-    function set_scale() {
-
-        // some things to check if the scaling doesnt work
-        // - that the widths/sizes really are about the actual screen size cat elements.json |grep -o width......|sort|uniq
-        $("#selector-wrapper").show();
-        selector_image = $("img#selector-background")[0];
-        selector_image_rect = selector_image.getBoundingClientRect();
-
-        // make the canvas the same size as the image
-        $('#selector-canvas').attr('height', selector_image_rect.height);
-        $('#selector-canvas').attr('width', selector_image_rect.width);
-        $('#selector-wrapper').attr('width', selector_image_rect.width);
-        x_scale = selector_image_rect.width / selector_data['browser_width'];
-        y_scale = selector_image_rect.height / selector_image.naturalHeight;
-        ctx.strokeStyle = 'rgba(255,0,0, 0.9)';
-        ctx.fillStyle = 'rgba(255,0,0, 0.1)';
-        ctx.lineWidth = 3;
-        console.log("scaling set  x: " + x_scale + " by y:" + y_scale);
-        $("#selector-current-xpath").css('max-width', selector_image_rect.width);
-    }
-
-    function reflow_selector() {
-        $(window).resize(function () {
-            set_scale();
-            highlight_current_selected_i();
-        });
-        var selector_currnt_xpath_text = $("#selector-current-xpath span");
-
-        set_scale();
-
-        console.log(selector_data['size_pos'].length + " selectors found");
-
-        // highlight the default one if we can find it in the xPath list
-        // or the xpath matches the default one
-        found = false;
-        if (current_default_xpath.length) {
-            // Find the first one that matches
-            // @todo In the future paint all that match
-            for (const c of current_default_xpath) {
-                for (var i = selector_data['size_pos'].length; i !== 0; i--) {
-                    if (selector_data['size_pos'][i - 1].xpath === c) {
-                        console.log("highlighting " + c);
-                        current_selected_i = i - 1;
-                        highlight_current_selected_i();
-                        found = true;
-                        break;
-                    }
-                }
-                if (found) {
-                    break;
-                }
-            }
-            if (!found) {
-                alert("Unfortunately your existing CSS/xPath Filter was no longer found!");
-            }
-        }
-
-
-        $('#selector-canvas').bind('mousemove', function (e) {
-            if (state_clicked) {
-                return;
-            }
-            ctx.clearRect(0, 0, c.width, c.height);
-            current_selected_i = null;
-
-            // Add in offset
-            if ((typeof e.offsetX === "undefined" || typeof e.offsetY === "undefined") || (e.offsetX === 0 && e.offsetY === 0)) {
-                var targetOffset = $(e.target).offset();
-                e.offsetX = e.pageX - targetOffset.left;
-                e.offsetY = e.pageY - targetOffset.top;
-            }
-
-            // Reverse order - the most specific one should be deeper/"laster"
-            // Basically, find the most 'deepest'
-            var found = 0;
-            ctx.fillStyle = 'rgba(205,0,0,0.35)';
-            // Will be sorted by smallest width*height first
-            for (var i = 0; i <= selector_data['size_pos'].length; i++) {
-                // draw all of them? let them choose somehow?
-                var sel = selector_data['size_pos'][i];
-                // If we are in a bounding-box
-                if (e.offsetY > sel.top * y_scale && e.offsetY < sel.top * y_scale + sel.height * y_scale
-                    &&
-                    e.offsetX > sel.left * y_scale && e.offsetX < sel.left * y_scale + sel.width * y_scale
-
-                ) {
-
-                    // FOUND ONE
-                    set_current_selected_text(sel.xpath);
-                    ctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-                    ctx.fillRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-
-                    // no need to keep digging
-                    // @todo or, O to go out/up, I to go in
-                    // or double click to go up/out the selector?
-                    current_selected_i = i;
-                    found += 1;
-                    break;
-                }
-            }
-
-        }.debounce(5));
-
-        function set_current_selected_text(s) {
-            selector_currnt_xpath_text[0].innerHTML = s;
-        }
-
-        function highlight_current_selected_i() {
-            if (state_clicked) {
-                state_clicked = false;
-                xctx.clearRect(0, 0, c.width, c.height);
-                return;
-            }
-
-            var sel = selector_data['size_pos'][current_selected_i];
-            if (sel[0] == '/') {
-                // @todo - not sure just checking / is right
-                $("#include_filters").val('xpath:' + sel.xpath);
-            } else {
-                $("#include_filters").val(sel.xpath);
-            }
-            xctx.fillStyle = 'rgba(205,205,205,0.95)';
-            xctx.strokeStyle = 'rgba(225,0,0,0.9)';
-            xctx.lineWidth = 3;
-            xctx.fillRect(0, 0, c.width, c.height);
-            // Clear out what only should be seen (make a clear/clean spot)
-            xctx.clearRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-            xctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
-            state_clicked = true;
-            set_current_selected_text(sel.xpath);
-
-        }
-
-
-        $('#selector-canvas').bind('mousedown', function (e) {
-            highlight_current_selected_i();
-        });
-    }
-
-});

changedetectionio/static/js/watch-overview.js

@@ -4,7 +4,6 @@ $(function () {
     $(this).closest('.unviewed').removeClass('unviewed');
   });
 
-
   $('.with-share-link > *').click(function () {
       $("#copied-clipboard").remove();
 
@@ -21,19 +20,5 @@ $(function () {
        $(this).remove();
       });
   });
-
-    // checkboxes - check all
-    $("#check-all").click(function (e) {
-        $('input[type=checkbox]').not(this).prop('checked', this.checked);
-    });
-    // checkboxes - show/hide buttons
-    $("input[type=checkbox]").click(function (e) {
-        if ($('input[type=checkbox]:checked').length) {
-            $('#checkbox-operations').slideDown();
-        } else {
-            $('#checkbox-operations').slideUp();
-        }
-    });
-
 });
 

changedetectionio/static/js/watch-settings.js

@@ -1,45 +1,14 @@
-$(document).ready(function () {
+$(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();
-            $('#ignore-status-codes-option').hide();
+        if ($('input[name="fetch_backend"]:checked').val() != 'html_requests') {
             $('#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('');
-        $('#notification_format').val('System default');
-        $('#notification_urls').val('');
-        e.preventDefault();
-    });
 });

changedetectionio/static/styles/.dockerignore

@@ -1,3 +0,0 @@
-node_modules
-package-lock.json
-

changedetectionio/static/styles/.gitignore

@@ -1,3 +1 @@
 node_modules
-package-lock.json
-

changedetectionio/static/styles/diff.css

@@ -1,148 +1,10 @@
-/**
- * CSS custom properties (aka variables).
- */
-:root {
-  --color-white: #fff;
-  --color-grey-50: #111;
-  --color-grey-100: #262626;
-  --color-grey-200: #333;
-  --color-grey-300: #444;
-  --color-grey-325: #555;
-  --color-grey-350: #565d64;
-  --color-grey-400: #666;
-  --color-grey-500: #777;
-  --color-grey-600: #999;
-  --color-grey-700: #cbcbcb;
-  --color-grey-750: #ddd;
-  --color-grey-800: #e0e0e0;
-  --color-grey-850: #eee;
-  --color-grey-900: #f2f2f2;
-  --color-black: #000;
-  --color-dark-red: #a00;
-  --color-light-red: #dd0000;
-  --color-background-page: var(--color-grey-100);
-  --color-background-gradient-first: #5ad8f7;
-  --color-background-gradient-second: #2f50af;
-  --color-background-gradient-third: #9150bf;
-  --color-background: var(--color-white);
-  --color-text: var(--color-grey-200);
-  --color-link: #1b98f8;
-  --color-menu-accent: #ed5900;
-  --color-background-code: var(--color-grey-850);
-  --color-error: var(--color-dark-red);
-  --color-error-input: #ffebeb;
-  --color-error-list: var(--color-light-red);
-  --color-table-background: var(--color-background);
-  --color-table-stripe: var(--color-grey-900);
-  --color-text-tab: var(--color-white);
-  --color-background-tab: rgba(255, 255, 255, 0.2);
-  --color-background-tab-hover: rgba(255, 255, 255, 0.5);
-  --color-text-tab-active: #222;
-  --color-api-key: #0078e7;
-  --color-background-button-primary: #0078e7;
-  --color-background-button-green: #42dd53;
-  --color-background-button-red: #dd4242;
-  --color-background-button-success: rgb(28, 184, 65);
-  --color-background-button-error: rgb(202, 60, 60);
-  --color-text-button-error: var(--color-white);
-  --color-background-button-warning: rgb(202, 60, 60);
-  --color-text-button-warning: var(--color-white);
-  --color-background-button-secondary: rgb(66, 184, 221);
-  --color-background-button-cancel: rgb(200, 200, 200);
-  --color-text-button: var(--color-white);
-  --color-background-button-tag: rgb(99, 99, 99);
-  --color-background-snapshot-age: #dfdfdf;
-  --color-error-text-snapshot-age: var(--color-white);
-  --color-error-background-snapshot-age: #ff0000;
-  --color-background-button-tag-active: #9c9c9c;
-  --color-text-messages: var(--color-white);
-  --color-background-messages-message: rgba(255, 255, 255, .2);
-  --color-background-messages-error: rgba(255, 1, 1, .5);
-  --color-background-messages-notice: rgba(255, 255, 255, .5);
-  --color-border-notification: #ccc;
-  --color-background-checkbox-operations: rgba(0, 0, 0, 0.05);
-  --color-warning: #ff3300;
-  --color-border-warning: var(--color-warning);
-  --color-text-legend: var(--color-white);
-  --color-link-new-version: #e07171;
-  --color-last-checked: #bbb;
-  --color-text-footer: #444;
-  --color-border-watch-table-cell: #eee;
-  --color-text-watch-tag-list: #e70069;
-  --color-background-new-watch-form: rgba(0, 0, 0, 0.05);
-  --color-background-new-watch-input: var(--color-white);
-  --color-text-new-watch-input: var(--color-text);
-  --color-border-input: var(--color-grey-500);
-  --color-shadow-input: var(--color-grey-400);
-  --color-background-input: var(--color-white);
-  --color-text-input: var(--color-text);
-  --color-text-input-description: var(--color-grey-500);
-  --color-text-input-placeholder: var(--color-grey-600);
-  --color-background-table-thead: var(--color-grey-800);
-  --color-border-table-cell: var(--color-grey-700);
-  --color-text-menu-heading: var(--color-grey-350);
-  --color-text-menu-link: var(--color-grey-500);
-  --color-background-menu-link-hover: var(--color-grey-850);
-  --color-text-menu-link-hover: var(--color-grey-300);
-  --color-shadow-jump: var(--color-grey-500);
-  --color-icon-github: var(--color-black);
-  --color-icon-github-hover: var(--color-grey-300);
-  --color-watch-table-error: var(--color-dark-red);
-  --color-watch-table-row-text: var(--color-grey-100); }
-
-html[data-darkmode="true"] {
-  --color-link: #59bdfb;
-  --color-text: var(--color-white);
-  --color-background-gradient-first: #3f90a5;
-  --color-background-gradient-second: #1e316c;
-  --color-background-gradient-third: #4d2c64;
-  --color-background-new-watch-input: var(--color-grey-100);
-  --color-text-new-watch-input: var(--color-text);
-  --color-background-table-thead: var(--color-grey-200);
-  --color-table-background: var(--color-grey-300);
-  --color-table-stripe: var(--color-grey-325);
-  --color-background: var(--color-grey-300);
-  --color-text-menu-heading: var(--color-grey-850);
-  --color-text-menu-link: var(--color-grey-800);
-  --color-border-table-cell: var(--color-grey-400);
-  --color-text-tab-active: var(--color-text);
-  --color-border-input: var(--color-grey-400);
-  --color-shadow-input: var(--color-grey-50);
-  --color-background-input: var(--color-grey-350);
-  --color-text-input-description: var(--color-grey-600);
-  --color-text-input-placeholder: var(--color-grey-600);
-  --color-text-watch-tag-list: #fa3e92;
-  --color-background-code: var(--color-grey-200);
-  --color-background-tab: rgba(0, 0, 0, 0.2);
-  --color-background-tab-hover: rgba(0, 0, 0, 0.5);
-  --color-background-snapshot-age: var(--color-grey-200);
-  --color-shadow-jump: var(--color-grey-200);
-  --color-icon-github: var(--color-white);
-  --color-icon-github-hover: var(--color-grey-700);
-  --color-watch-table-error: var(--color-light-red);
-  --color-watch-table-row-text: var(--color-grey-800); }
-  html[data-darkmode="true"] .icon-spread {
-    filter: hue-rotate(-10deg) brightness(1.5); }
-  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 .watch-controls .state-off img {
-    opacity: 0.3; }
-  html[data-darkmode="true"] .watch-table .watch-controls .state-on img {
-    opacity: 1.0; }
-  html[data-darkmode="true"] .watch-table .unviewed {
-    color: #fff; }
-    html[data-darkmode="true"] .watch-table .unviewed.error {
-      color: var(--color-watch-table-error); }
-
 #diff-ui {
-  background: var(--color-background);
+  background: #fff;
   padding: 2em;
   margin-left: 1em;
   margin-right: 1em;
-  border-radius: 5px; }
-  #diff-ui #text {
-    font-size: 11px; }
+  border-radius: 5px;
+  font-size: 11px; }
   #diff-ui table {
     table-layout: fixed;
     width: 100%; }
@@ -183,10 +45,6 @@ ins {
     margin-left: 1em;
     display: inline-block;
     font-weight: normal; }
-  #settings del {
-    padding: 0.5em; }
-  #settings ins {
-    padding: 0.5em; }
 
 .source {
   position: absolute;

changedetectionio/static/styles/diff.scss

@@ -0,0 +1,96 @@
+#diff-ui {
+
+    background: #fff;
+    padding: 2em;
+    margin-left: 1em;
+    margin-right: 1em;
+    border-radius: 5px;
+    font-size: 11px;
+
+    table {
+        table-layout: fixed;
+        width: 100%;
+    }
+    td {
+        padding: 3px 4px;
+        border: 1px solid transparent;
+        vertical-align: top;
+        font: 1em monospace;
+        text-align: left;
+    }
+    pre {
+            white-space: pre-wrap;
+    }
+}
+h1 {
+	display: inline;
+	font-size: 100%;
+}
+del {
+	text-decoration: none;
+	color: #b30000;
+	background: #fadad7;
+}
+
+ins {
+	background: #eaf2c2;
+	color: #406619;
+	text-decoration: none;
+}
+
+#result {
+	white-space: pre-wrap;
+}
+
+#settings {
+    background: rgba(0,0,0,.05);
+    padding: 1em;
+    border-radius: 10px;
+    margin-bottom: 1em;
+    color: #fff;
+    font-size: 80%;
+    label {
+	    margin-left: 1em;
+	    display: inline-block;
+	    font-weight: normal;
+    }
+}
+
+.source {
+	position: absolute;
+	right: 1%;
+	top: .2em;
+}
+
+@-moz-document url-prefix() {
+	body {
+		height: 99%; /* Hide scroll bar in Firefox */
+	}
+}
+
+td#diff-col div {
+    text-align: justify;
+    white-space: pre-wrap;
+}
+
+.ignored {
+    background-color: #ccc;
+   /*  border: #0d91fa 1px solid; */
+    opacity: 0.7;
+}
+
+.triggered {
+    background-color: #1b98f8;
+}
+
+/* ignored and triggered? make it obvious error */
+.ignored.triggered {
+  background-color: #ff0000;
+}
+
+.tab-pane-inner#screenshot {
+  text-align: center;
+  img {
+    max-width: 99%;
+  }
+}

changedetectionio/static/styles/package.json

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

changedetectionio/static/styles/scss/diff.scss

@@ -1,121 +0,0 @@
-@import "parts/_variables.scss";
-
-#diff-ui {
-
-  background: var(--color-background);
-  padding: 2em;
-  margin-left: 1em;
-  margin-right: 1em;
-  border-radius: 5px;
-
-  // The first tab 'text' diff
-  #text {
-    font-size: 11px;
-  }
-
-  table {
-    table-layout: fixed;
-    width: 100%;
-  }
-
-  td {
-    padding: 3px 4px;
-    border: 1px solid transparent;
-    vertical-align: top;
-    font: 1em monospace;
-    text-align: left;
-  }
-
-  pre {
-    white-space: pre-wrap;
-  }
-}
-
-h1 {
-  display: inline;
-  font-size: 100%;
-}
-
-del {
-  text-decoration: none;
-  color: #b30000;
-  background: #fadad7;
-}
-
-ins {
-  background: #eaf2c2;
-  color: #406619;
-  text-decoration: none;
-}
-
-#result {
-  white-space: pre-wrap;
-
-  .change {
-    span {}
-  }
-}
-
-#settings {
-  background: rgba(0, 0, 0, .05);
-  padding: 1em;
-  border-radius: 10px;
-  margin-bottom: 1em;
-  color: #fff;
-  font-size: 80%;
-
-  label {
-    margin-left: 1em;
-    display: inline-block;
-    font-weight: normal;
-  }
-
-  del {
-    padding: 0.5em;
-  }
-
-  ins {
-    padding: 0.5em;
-  }
-}
-
-.source {
-  position: absolute;
-  right: 1%;
-  top: .2em;
-}
-
-@-moz-document url-prefix() {
-  body {
-    height: 99%;
-    /* Hide scroll bar in Firefox */
-  }
-}
-
-td#diff-col div {
-  text-align: justify;
-  white-space: pre-wrap;
-}
-
-.ignored {
-  background-color: #ccc;
-  /*  border: #0d91fa 1px solid; */
-  opacity: 0.7;
-}
-
-.triggered {
-  background-color: #1b98f8;
-}
-
-/* ignored and triggered? make it obvious error */
-.ignored.triggered {
-  background-color: #ff0000;
-}
-
-.tab-pane-inner#screenshot {
-  text-align: center;
-
-  img {
-    max-width: 99%;
-  }
-}

changedetectionio/static/styles/scss/parts/_arrows.scss

@@ -1,26 +0,0 @@
-.arrow {
-  border: solid #1b98f8;
-  border-width: 0 2px 2px 0;
-  display: inline-block;
-  padding: 3px;
-
-  &.right {
-    transform: rotate(-45deg);
-    -webkit-transform: rotate(-45deg);
-  }
-
-  &.left {
-    transform: rotate(135deg);
-    -webkit-transform: rotate(135deg);
-  }
-
-  &.up, &.asc {
-    transform: rotate(-135deg);
-    -webkit-transform: rotate(-135deg);
-  }
-
-  &.down, &.desc {
-    transform: rotate(45deg);
-    -webkit-transform: rotate(45deg);
-  }
-}

changedetectionio/static/styles/scss/parts/_browser-steps.scss

@@ -1,95 +0,0 @@
-
-#browser_steps {
-  /* convert rows to horizontal cells */
-  th {
-    display: none;
-  }
-
-  li {
-    &:not(:first-child) {
-      &:hover {
-        opacity: 1.0;
-      }
-    }
-    list-style: decimal;
-    padding: 5px;
-    .control {
-      padding-left: 5px;
-      padding-right: 5px;
-      a {
-        font-size: 70%;
-      }
-    }
-    &.empty {
-      padding: 0px;
-      opacity: 0.35;
-      .control {
-        display: none;
-      }
-    }
-    &:hover {
-      background: #eee;
-    }
-    > label {
-      display: none;
-    }
-  }
-}
-
-#browser-steps-fieldlist {
-  height: 100%;
-  overflow-y: scroll;
-}
-
-#browser-steps .flex-wrapper {
-  display: flex;
-  flex-flow: row;
-  height: 600px; /*@todo make this dynamic */
-}
-
-/*  this is duplicate :( */
-#browsersteps-selector-wrapper {
-  height: 100%;
-  width: 100%;
-  overflow-y: scroll;
-  position: relative;
-  //width: 100%;
-  > img {
-    position: absolute;
-    max-width: 100%;
-  }
-
-  > canvas {
-    position: relative;
-    max-width: 100%;
-
-    &:hover {
-      cursor: pointer;
-    }
-  }
-
-  .loader {
-    position: absolute;
-    left: 50%;
-    top: 50%;
-    transform: translate(-50%, -50%);
-    margin-left: -40px;
-    z-index: 100;
-    max-width: 350px;
-    text-align: center;
-  }
-
-  /* nice tall skinny one */
-  .spinner, .spinner:after {
-    width: 80px;
-    height: 80px;
-    font-size: 3px;
-  }
-
-  #browsersteps-click-start {
-    &:hover {
-      cursor: pointer;
-    }
-    color: var(--color-grey-400);
-  }
-}

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

@@ -1,17 +0,0 @@
-ul#requests-extra_proxies {
-  list-style: none;
-  /* tidy up the table to look more "inline" */
-  li {
-    > label {
-      display: none;
-    }
-
-  }
-  /* each proxy entry is a `table` */
-  table {
-    tr {
-      display: inline;
-    }
-  }
-}
-

changedetectionio/static/styles/scss/parts/_spinners.scss

@@ -1,44 +0,0 @@
-
-/* spinner */
-.spinner,
-.spinner:after {
-  border-radius: 50%;
-  width: 10px;
-  height: 10px;
-}
-.spinner {
-  margin: 0px auto;
-  font-size: 3px;
-  vertical-align: middle;
-  display: inline-block;
-  text-indent: -9999em;
-  border-top: 1.1em solid rgba(38,104,237, 0.2);
-  border-right: 1.1em solid rgba(38,104,237, 0.2);
-  border-bottom: 1.1em solid rgba(38,104,237, 0.2);
-  border-left: 1.1em solid #2668ed;
-  -webkit-transform: translateZ(0);
-  -ms-transform: translateZ(0);
-  transform: translateZ(0);
-  -webkit-animation: load8 1.1s infinite linear;
-  animation: load8 1.1s infinite linear;
-}
-@-webkit-keyframes load8 {
-  0% {
-    -webkit-transform: rotate(0deg);
-    transform: rotate(0deg);
-  }
-  100% {
-    -webkit-transform: rotate(360deg);
-    transform: rotate(360deg);
-  }
-}
-@keyframes load8 {
-  0% {
-    -webkit-transform: rotate(0deg);
-    transform: rotate(0deg);
-  }
-  100% {
-    -webkit-transform: rotate(360deg);
-    transform: rotate(360deg);
-  }
-}

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

@@ -1,175 +0,0 @@
-/**
- * CSS custom properties (aka variables).
- */
-
-:root {
-  --color-white: #fff;
-  --color-grey-50: #111;
-  --color-grey-100: #262626;
-  --color-grey-200: #333;
-  --color-grey-300: #444;
-  --color-grey-325: #555;
-  --color-grey-350: #565d64;
-  --color-grey-400: #666;
-  --color-grey-500: #777;
-  --color-grey-600: #999;
-  --color-grey-700: #cbcbcb;
-  --color-grey-750: #ddd;
-  --color-grey-800: #e0e0e0;
-  --color-grey-850: #eee;
-  --color-grey-900: #f2f2f2;
-  --color-black: #000;
-  --color-dark-red: #a00;
-  --color-light-red: #dd0000;
-
-  --color-background-page: var(--color-grey-100);
-  --color-background-gradient-first: #5ad8f7;
-  --color-background-gradient-second: #2f50af;
-  --color-background-gradient-third: #9150bf;
-  --color-background: var(--color-white);
-  --color-text: var(--color-grey-200);
-  --color-link: #1b98f8;
-  --color-menu-accent: #ed5900;
-  --color-background-code: var(--color-grey-850);
-  --color-error: var(--color-dark-red);
-  --color-error-input: #ffebeb;
-  --color-error-list: var(--color-light-red);
-  --color-table-background: var(--color-background);
-  --color-table-stripe: var(--color-grey-900);
-  --color-text-tab: var(--color-white);
-  --color-background-tab: rgba(255, 255, 255, 0.2);
-  --color-background-tab-hover: rgba(255, 255, 255, 0.5);
-  --color-text-tab-active: #222;
-  --color-api-key: #0078e7;
-
-  --color-background-button-primary: #0078e7;
-  --color-background-button-green: #42dd53;
-  --color-background-button-red: #dd4242;
-  --color-background-button-success: rgb(28, 184, 65);
-  --color-background-button-error: rgb(202, 60, 60);
-  --color-text-button-error: var(--color-white);
-  --color-background-button-warning: rgb(202, 60, 60);
-  --color-text-button-warning: var(--color-white);
-  --color-background-button-secondary: rgb(66, 184, 221);
-  --color-background-button-cancel: rgb(200, 200, 200);
-  --color-text-button: var(--color-white);
-  --color-background-button-tag: rgb(99, 99, 99);
-  --color-background-snapshot-age: #dfdfdf;
-  --color-error-text-snapshot-age: var(--color-white);
-  --color-error-background-snapshot-age: #ff0000;
-  --color-background-button-tag-active: #9c9c9c;
-
-  --color-text-messages: var(--color-white);
-  --color-background-messages-message: rgba(255, 255, 255, .2);
-  --color-background-messages-error: rgba(255, 1, 1, .5);
-  --color-background-messages-notice: rgba(255, 255, 255, .5);
-  --color-border-notification: #ccc;
-
-  --color-background-checkbox-operations: rgba(0, 0, 0, 0.05);
-  --color-warning: #ff3300;
-  --color-border-warning: var(--color-warning);
-  --color-text-legend: var(--color-white);
-
-  --color-link-new-version: #e07171;
-  --color-last-checked: #bbb;
-  --color-text-footer: #444;
-  --color-border-watch-table-cell: #eee;
-
-  --color-text-watch-tag-list: #e70069;
-  --color-background-new-watch-form: rgba(0, 0, 0, 0.05);
-  --color-background-new-watch-input: var(--color-white);
-  --color-text-new-watch-input: var(--color-text);
-
-  --color-border-input: var(--color-grey-500);
-  --color-shadow-input: var(--color-grey-400);
-  --color-background-input: var(--color-white);
-  --color-text-input: var(--color-text);
-  --color-text-input-description: var(--color-grey-500);
-  --color-text-input-placeholder: var(--color-grey-600);
-
-  --color-background-table-thead: var(--color-grey-800);
-  --color-border-table-cell: var(--color-grey-700);
-
-  --color-text-menu-heading: var(--color-grey-350);
-  --color-text-menu-link: var(--color-grey-500);
-  --color-background-menu-link-hover: var(--color-grey-850);
-  --color-text-menu-link-hover: var(--color-grey-300);
-
-  --color-shadow-jump: var(--color-grey-500);
-  --color-icon-github: var(--color-black);
-  --color-icon-github-hover: var(--color-grey-300);
-
-  --color-watch-table-error: var(--color-dark-red);
-  --color-watch-table-row-text: var(--color-grey-100);
-}
-
-html[data-darkmode="true"] {
-  --color-link: #59bdfb;
-  --color-text: var(--color-white);
-
-  --color-background-gradient-first: #3f90a5;
-  --color-background-gradient-second: #1e316c;
-  --color-background-gradient-third: #4d2c64;
-
-  --color-background-new-watch-input: var(--color-grey-100);
-  --color-text-new-watch-input: var(--color-text);
-  --color-background-table-thead: var(--color-grey-200);
-  --color-table-background: var(--color-grey-300);
-  --color-table-stripe: var(--color-grey-325);
-  --color-background: var(--color-grey-300);
-  --color-text-menu-heading: var(--color-grey-850);
-  --color-text-menu-link: var(--color-grey-800);
-  --color-border-table-cell: var(--color-grey-400);
-  --color-text-tab-active: var(--color-text);
-
-  --color-border-input: var(--color-grey-400);
-  --color-shadow-input: var(--color-grey-50);
-  --color-background-input: var(--color-grey-350);
-  --color-text-input-description: var(--color-grey-600);
-  --color-text-input-placeholder: var(--color-grey-600);
-  --color-text-watch-tag-list: #fa3e92;
-  --color-background-code: var(--color-grey-200);
-
-  --color-background-tab: rgba(0, 0, 0, 0.2);
-  --color-background-tab-hover: rgba(0, 0, 0, 0.5);
-
-  --color-background-snapshot-age: var(--color-grey-200);
-  --color-shadow-jump: var(--color-grey-200);
-  --color-icon-github: var(--color-white);
-  --color-icon-github-hover: var(--color-grey-700);
-  --color-watch-table-error: var(--color-light-red);
-  --color-watch-table-row-text: var(--color-grey-800);
-
-
-  .icon-spread {
-    filter: hue-rotate(-10deg) brightness(1.5);
-  }
-
-  .watch-table {
-
-    .title-col a[target="_blank"]::after,
-    .current-diff-url::after {
-      filter: invert(.5) hue-rotate(10deg) brightness(2);
-    }
-
-    .watch-controls {
-      .state-off {
-        img {
-          opacity: 0.3;
-        }
-      }
-      .state-on {
-        img {
-          opacity: 1.0;
-        }
-      }
-    }
-
-    .unviewed {
-      color: #fff;
-      &.error {
-        color: var(--color-watch-table-error);
-      }
-    }
-  }
-}

changedetectionio/static/styles/styles.scss

@@ -0,0 +1,643 @@
+/*
+ * -- BASE STYLES --
+ * Most of these are inherited from Base, but I want to change a few.
+ * nvm use v14.18.1
+ * npm install
+ * npm run build
+ * or npm run watch
+ */
+body {
+  color: #333;
+  background: #262626;
+}
+.pure-table-even {
+  background: #fff;
+}
+
+/* Some styles from https://css-tricks.com/ */
+a {
+  text-decoration: none;
+  color: #1b98f8;
+}
+
+a.github-link {
+  color: #fff;
+}
+
+.pure-menu-horizontal {
+  background: #fff;
+  padding: 5px;
+  display: flex;
+  justify-content: space-between;
+  border-bottom: 2px solid #ed5900;
+  align-items: center;
+}
+
+section.content {
+  padding-top: 5em;
+  padding-bottom: 1em;
+  flex-direction: column;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+}
+
+code {
+  background: #eee;
+}
+
+/* table related */
+.watch-table {
+  width: 100%;
+  font-size: 80%;
+
+  tr.unviewed {
+    font-weight: bold;
+  }
+
+  .error {
+    color: #a00;
+  }
+
+  td {
+    white-space: nowrap;
+  }
+
+  td.title-col {
+    word-break: break-all;
+    white-space: normal;
+  }
+
+  th {
+    white-space: nowrap;
+  }
+
+  .title-col a[target="_blank"]::after, .current-diff-url::after {
+    content: url(data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAQElEQVR42qXKwQkAIAxDUUdxtO6/RBQkQZvSi8I/pL4BoGw/XPkh4XigPmsUgh0626AjRsgxHTkUThsG2T/sIlzdTsp52kSS1wAAAABJRU5ErkJggg==);
+    margin: 0 3px 0 5px;
+  }
+}
+
+.watch-tag-list {
+  color: #e70069;
+  white-space: nowrap;
+}
+
+.box {
+  max-width: 80%;
+  flex-direction: column;
+  display: flex;
+  justify-content: center;
+}
+
+
+#post-list-buttons {
+  text-align: right;
+  padding: 0px;
+  margin: 0px;
+
+  li {
+    display: inline-block;
+  }
+
+  a {
+    border-top-left-radius: initial;
+    border-top-right-radius: initial;
+    border-bottom-left-radius: 5px;
+    border-bottom-right-radius: 5px;
+  }
+}
+
+
+body:after {
+  content: "";
+  background: linear-gradient(130deg, #5ad8f7, #2f50af 41.07%, #9150bf 84.05%);
+}
+
+body:after, body:before {
+  display: block;
+  height: 650px;
+  position: absolute;
+  top: 0;
+  left: 0;
+  width: 100%;
+  z-index: -1;
+}
+
+body::after {
+  opacity: 0.91;
+}
+
+body::before {
+  // background-image set in base.html so it works with reverse proxies etc
+  content: "";
+  background-size: cover
+}
+
+body:after, body:before {
+  -webkit-clip-path: polygon(100% 0, 0 0, 0 77.5%, 1% 77.4%, 2% 77.1%, 3% 76.6%, 4% 75.9%, 5% 75.05%, 6% 74.05%, 7% 72.95%, 8% 71.75%, 9% 70.55%, 10% 69.3%, 11% 68.05%, 12% 66.9%, 13% 65.8%, 14% 64.8%, 15% 64%, 16% 63.35%, 17% 62.85%, 18% 62.6%, 19% 62.5%, 20% 62.65%, 21% 63%, 22% 63.5%, 23% 64.2%, 24% 65.1%, 25% 66.1%, 26% 67.2%, 27% 68.4%, 28% 69.65%, 29% 70.9%, 30% 72.15%, 31% 73.3%, 32% 74.35%, 33% 75.3%, 34% 76.1%, 35% 76.75%, 36% 77.2%, 37% 77.45%, 38% 77.5%, 39% 77.3%, 40% 76.95%, 41% 76.4%, 42% 75.65%, 43% 74.75%, 44% 73.75%, 45% 72.6%, 46% 71.4%, 47% 70.15%, 48% 68.9%, 49% 67.7%, 50% 66.55%, 51% 65.5%, 52% 64.55%, 53% 63.75%, 54% 63.15%, 55% 62.75%, 56% 62.55%, 57% 62.5%, 58% 62.7%, 59% 63.1%, 60% 63.7%, 61% 64.45%, 62% 65.4%, 63% 66.45%, 64% 67.6%, 65% 68.8%, 66% 70.05%, 67% 71.3%, 68% 72.5%, 69% 73.6%, 70% 74.65%, 71% 75.55%, 72% 76.35%, 73% 76.9%, 74% 77.3%, 75% 77.5%, 76% 77.45%, 77% 77.25%, 78% 76.8%, 79% 76.2%, 80% 75.4%, 81% 74.45%, 82% 73.4%, 83% 72.25%, 84% 71.05%, 85% 69.8%, 86% 68.55%, 87% 67.35%, 88% 66.2%, 89% 65.2%, 90% 64.3%, 91% 63.55%, 92% 63%, 93% 62.65%, 94% 62.5%, 95% 62.55%, 96% 62.8%, 97% 63.3%, 98% 63.9%, 99% 64.75%, 100% 65.7%);
+  clip-path: polygon(100% 0, 0 0, 0 77.5%, 1% 77.4%, 2% 77.1%, 3% 76.6%, 4% 75.9%, 5% 75.05%, 6% 74.05%, 7% 72.95%, 8% 71.75%, 9% 70.55%, 10% 69.3%, 11% 68.05%, 12% 66.9%, 13% 65.8%, 14% 64.8%, 15% 64%, 16% 63.35%, 17% 62.85%, 18% 62.6%, 19% 62.5%, 20% 62.65%, 21% 63%, 22% 63.5%, 23% 64.2%, 24% 65.1%, 25% 66.1%, 26% 67.2%, 27% 68.4%, 28% 69.65%, 29% 70.9%, 30% 72.15%, 31% 73.3%, 32% 74.35%, 33% 75.3%, 34% 76.1%, 35% 76.75%, 36% 77.2%, 37% 77.45%, 38% 77.5%, 39% 77.3%, 40% 76.95%, 41% 76.4%, 42% 75.65%, 43% 74.75%, 44% 73.75%, 45% 72.6%, 46% 71.4%, 47% 70.15%, 48% 68.9%, 49% 67.7%, 50% 66.55%, 51% 65.5%, 52% 64.55%, 53% 63.75%, 54% 63.15%, 55% 62.75%, 56% 62.55%, 57% 62.5%, 58% 62.7%, 59% 63.1%, 60% 63.7%, 61% 64.45%, 62% 65.4%, 63% 66.45%, 64% 67.6%, 65% 68.8%, 66% 70.05%, 67% 71.3%, 68% 72.5%, 69% 73.6%, 70% 74.65%, 71% 75.55%, 72% 76.35%, 73% 76.9%, 74% 77.3%, 75% 77.5%, 76% 77.45%, 77% 77.25%, 78% 76.8%, 79% 76.2%, 80% 75.4%, 81% 74.45%, 82% 73.4%, 83% 72.25%, 84% 71.05%, 85% 69.8%, 86% 68.55%, 87% 67.35%, 88% 66.2%, 89% 65.2%, 90% 64.3%, 91% 63.55%, 92% 63%, 93% 62.65%, 94% 62.5%, 95% 62.55%, 96% 62.8%, 97% 63.3%, 98% 63.9%, 99% 64.75%, 100% 65.7%)
+}
+
+.arrow {
+  border: solid black;
+  border-width: 0 3px 3px 0;
+  display: inline-block;
+  padding: 3px;
+    &.right {
+      transform: rotate(-45deg);
+      -webkit-transform: rotate(-45deg);
+    }
+    &.left {
+      transform: rotate(135deg);
+      -webkit-transform: rotate(135deg);
+    }
+    &.up {
+      transform: rotate(-135deg);
+      -webkit-transform: rotate(-135deg);
+    }
+    &.down {
+      transform: rotate(45deg);
+      -webkit-transform: rotate(45deg);
+    }
+}
+
+.button-small {
+  font-size: 85%;
+}
+
+.fetch-error {
+  padding-top: 1em;
+  font-size: 60%;
+  max-width: 400px;
+  display: block;
+}
+
+
+.button-secondary {
+  color: white;
+  border-radius: 4px;
+  text-shadow: 0 1px 1px rgba(0, 0, 0, 0.2);
+}
+
+.button-success {
+  background: rgb(28, 184, 65);
+  /* this is a green */
+}
+
+.button-tag {
+  background: rgb(99, 99, 99);
+  color: #fff;
+  font-size: 65%;
+  border-bottom-left-radius: initial;
+  border-bottom-right-radius: initial;
+
+  &.active {
+    background: #9c9c9c;
+    font-weight: bold;
+  }
+
+}
+
+.button-error {
+  background: rgb(202, 60, 60);
+  /* this is a maroon */
+}
+
+.button-warning {
+  background: rgb(223, 117, 20);
+  /* this is an orange */
+}
+
+.button-secondary {
+  background: rgb(66, 184, 221);
+  /* this is a light blue */
+}
+
+
+.button-cancel {
+  background: rgb(200, 200, 200);
+  /* this is a green */
+}
+
+.messages {
+    li {
+        list-style: none;
+        padding: 1em;
+        border-radius: 10px;
+        color: #fff;
+        font-weight: bold;
+        &.message {
+            background: rgba(255, 255, 255, .2);
+        }
+        &.error {
+            background: rgba(255, 1, 1, .5);
+        }
+        &.notice {
+            background: rgba(255, 255, 255, .5);
+        }
+    }
+    &.with-share-link {
+     > *:hover {
+       cursor:pointer;
+     }
+    }
+}
+
+#notification-customisation {
+    border: 1px solid #ccc;
+    padding: 0.5rem;
+    border-radius: 5px;
+}
+
+#notification-error-log {
+    border: 1px solid #ccc;
+    padding: 1rem;
+    border-radius: 5px;
+    overflow-wrap: break-word;
+}
+
+#token-table {
+    &.pure-table td, &.pure-table th {
+        font-size: 80%;
+    }
+}
+
+#new-watch-form {
+  background: rgba(0, 0, 0, .05);
+  padding: 1em;
+  border-radius: 10px;
+  margin-bottom: 1em;
+  input {
+    width: auto !important;
+    display: inline-block;
+  }
+  .label {
+    display: none;
+  }
+  legend {
+    color: #fff;
+    font-weight: bold;
+  }
+}
+
+
+
+
+#diff-col {
+  padding-left: 40px;
+}
+
+#diff-jump {
+  position: fixed;
+  left: 0px;
+  top: 120px;
+  background: #fff;
+  padding: 10px;
+  border-top-right-radius: 5px;
+  border-bottom-right-radius: 5px;
+  box-shadow: 5px 0 5px -2px #888;
+     a {
+      color: #1b98f8;
+      cursor: grabbing;
+      -moz-user-select: none;
+      -webkit-user-select: none;
+      -ms-user-select: none;
+      user-select: none;
+      -o-user-select: none;
+    }
+}
+
+footer {
+  padding: 10px;
+  background: #fff;
+  color: #444;
+  text-align: center;
+}
+
+#feed-icon {
+  vertical-align: middle;
+}
+
+#top-right-menu {
+// Just let flex overflow the x axis for now
+/*
+    position: absolute;
+    right: 0px;
+    background: linear-gradient(to right, #fff0, #fff 10%);
+    padding-left: 20px;
+    padding-right: 10px;
+    */
+}
+
+.sticky-tab {
+  position: absolute;
+  top: 60px;
+  font-size: 65%;
+  background: #fff;
+  padding: 10px;
+  &#left-sticky {
+    left: 0px;
+  }
+  &#right-sticky {
+    right: 0px;
+  }
+  &#hosted-sticky {
+    right: 0px;
+    top: 100px;
+    font-weight: bold;
+  }
+}
+
+#new-version-text a {
+  color: #e07171;
+}
+
+.paused-state {
+  &.state-False img {
+    opacity: 0.2;
+  }
+
+  &.state-False:hover img {
+    opacity: 0.8;
+  }
+}
+
+.monospaced-textarea {
+    textarea {
+        width: 100%;
+        font-family: monospace;
+        white-space: pre;
+        overflow-wrap: normal;
+        overflow-x: scroll;
+    }
+}
+
+
+.pure-form {
+    .pure-control-group, .pure-group, .pure-controls {
+        padding-bottom: 1em;
+        div {
+            margin: 0px;
+        }
+        .checkbox {
+            > * {
+              display: inline;
+              vertical-align: middle;
+            }
+            > label {
+               padding-left: 5px;
+            }
+        }
+    }
+  /* The input fields with errors */
+  .error {
+    input {
+        background-color: #ffebeb;
+    }
+  }
+
+  /* The list of errors */
+  ul.errors {
+    padding: .5em .6em;
+    border: 1px solid #dd0000;
+    border-radius: 4px;
+    vertical-align: middle;
+    -webkit-box-sizing: border-box;
+    box-sizing: border-box;
+    li {
+        margin-left: 1em;
+        color: #dd0000;
+    }
+  }
+
+  label {
+    font-weight: bold;
+  }
+
+  textarea {
+    width: 100%;
+  }
+  .inline-radio {
+      ul {
+        margin: 0px;
+        list-style: none;
+        li {
+            > * {
+                display: inline-block;
+            }
+        }
+      }
+  }
+}
+
+@media only screen and (max-width: 760px), (min-device-width: 768px) and (max-device-width: 1024px) {
+  .box {
+    max-width: 95%
+  }
+  .edit-form {
+    padding: 0.5em;
+    margin: 0;
+  }
+  #nav-menu {
+    overflow-x: scroll;
+  }
+}
+
+
+
+@media only screen and (max-width: 760px), (min-device-width: 768px) and (max-device-width: 800px) {
+
+  div.sticky-tab#hosted-sticky {
+    top: 60px;
+    left: 0px;
+    right: auto;
+  }
+
+  section.content {
+    padding-top: 110px;
+  }
+
+  // Make the tabs easier to hit, they will be all nice and horizontal
+  div.tabs.collapsable ul li {
+    display: block;
+    border-radius: 0px;
+  }
+
+  input[type='text'] {
+    width: 100%;
+  }
+
+/*
+Max width before this PARTICULAR table gets nasty
+This query will take effect for any screen smaller than 760px
+and also iPads specifically.
+*/
+  .watch-table {
+    /* Force table to not be like tables anymore */
+    thead, tbody, th, td, tr {
+      display: block;
+    }
+
+    .last-checked::before {
+      color: #555;
+      content: "Last Checked ";
+    }
+
+    .last-changed::before {
+      color: #555;
+      content: "Last Changed ";
+    }
+
+    /* Force table to not be like tables anymore */
+    td.inline {
+      display: inline-block;
+    }
+
+    /* Hide table headers (but not display: none;, for accessibility) */
+    thead tr {
+      position: absolute;
+      top: -9999px;
+      left: -9999px;
+    }
+
+    .pure-table td, .pure-table th {
+      border: none;
+    }
+
+    td {
+      /* Behave  like a "row" */
+      border: none;
+      border-bottom: 1px solid #eee;
+
+      &:before {
+        /* Top/left values mimic padding */
+        top: 6px;
+        left: 6px;
+        width: 45%;
+        padding-right: 10px;
+        white-space: nowrap;
+      }
+    }
+
+    &.pure-table-striped {
+      tr {
+        background-color: #fff;
+      }
+
+      tr:nth-child(2n-1) {
+        background-color: #eee;
+      }
+
+      tr:nth-child(2n-1) td {
+        background-color: inherit;
+      }
+    }
+
+  }
+}
+
+
+/** Desktop vs mobile input field strategy
+- We dont use 'size' with <input> because `size` is too unreliable to override, and will often push-out
+- Rely always on width in CSS
+*/
+@media only screen and (min-width: 761px) {
+/* m-d is medium-desktop */
+    .m-d {
+        min-width: 80%;
+    }
+}
+
+
+
+.tabs {
+  ul {
+    margin: 0px;
+    padding: 0px;
+    display:block;
+    li {
+      margin-right: 3px;
+      display: inline-block;
+      color: #fff;
+      border-top-left-radius: 5px;
+      border-top-right-radius: 5px;
+      background-color: rgba(255, 255, 255, 0.2);
+
+      &.active,:target {
+        background-color: #fff;
+        a {
+          color: #222;
+          font-weight: bold;
+        }
+      }
+      a {
+        display: block;
+        padding: 0.8em;
+        color: #fff;
+      }
+    }
+  }
+}
+
+$form-edge-padding: 20px;
+.pure-form-stacked {
+  >div:first-child {
+    display: block;
+  }
+}
+
+.login-form {
+  .inner {
+    background: #fff;;
+    padding: $form-edge-padding;
+    border-radius: 5px;
+  }
+}
+
+.tab-pane-inner {
+    &:not(:target) {
+        display: none;
+    }
+    &:target {
+      display: block;
+    }
+    // doesnt need padding because theres another row of buttons/activity
+    padding: 0px;
+}
+
+.edit-form {
+  min-width: 70%;
+  /* so it cant overflow */
+  max-width: 95%;
+  .box-wrap {
+    position: relative;
+  }
+  .inner {
+    background: #fff;;
+    padding: $form-edge-padding;
+  }
+  #actions {
+    display: block;
+    background: #fff;
+  }
+
+  .pure-form-message-inline {
+    padding-left: 0;
+  }
+}
+
+ul {
+    padding-left: 1em;
+    padding-top: 0px;
+    margin-top: 4px;
+}
+
+.time-check-widget {
+    tr {
+        display: inline;
+        input[type="number"] {
+            width: 4em;
+        }
+    }
+}

changedetectionio/store.py

@@ -1,20 +1,21 @@
 from flask import (
     flash
 )
-
-from . model import App, Watch
-from copy import deepcopy
-from os import path, unlink
-from threading import Lock
 import json
 import logging
 import os
-import re
-import requests
-import secrets
 import threading
 import time
 import uuid as uuid_builder
+from copy import deepcopy
+from os import mkdir, path, unlink
+from threading import Lock
+import re
+import requests
+import sqlite3
+
+from . model import App, Watch
+
 
 # Is there an existing library to ensure some data store (JSON etc) is in sync with CRUD methods?
 # Open a github issue if you know something :)
@@ -27,20 +28,25 @@ class ChangeDetectionStore:
     # For when we edit, we should write to disk
     needs_write_urgent = False
 
-    __version_check = True
-
     def __init__(self, datastore_path="/datastore", include_default_watches=True, version_tag="0.0.0"):
         # Should only be active for docker
         # logging.basicConfig(filename='/dev/stdout', level=logging.INFO)
-        self.__data = App.model()
+        self.needs_write = False
         self.datastore_path = datastore_path
         self.json_store_path = "{}/url-watches.json".format(self.datastore_path)
-        self.needs_write = False
-        self.start_time = time.time()
+        self.datastore_path = datastore_path
+
+        #@todo - check for better options
+        self.__history_db_connection = sqlite3.connect("{}/watch.db".format(self.datastore_path))
+
+        self.proxy_list = None
         self.stop_thread = False
+
+        self.__data = App.model()
+
         # Base definition for all watchers
         # deepcopy part of #569 - not sure why its needed exactly
-        self.generic_definition = deepcopy(Watch.model(datastore_path = datastore_path, default={}))
+        self.generic_definition = deepcopy(Watch.model())
 
         if path.isfile('changedetectionio/source.txt'):
             with open('changedetectionio/source.txt') as f:
@@ -71,28 +77,31 @@ class ChangeDetectionStore:
                     if 'application' in from_disk['settings']:
                         self.__data['settings']['application'].update(from_disk['settings']['application'])
 
-                # Convert each existing watch back to the Watch.model object
+                # Bump the update version by running updates
+                self.run_updates()
+
+                # Reinitialise each `watching` with our generic_definition in the case that we add a new var in the future.
+                # @todo pretty sure theres a python we todo this with an abstracted(?) object!
                 for uuid, watch in self.__data['watching'].items():
-                    watch['uuid']=uuid
-                    self.__data['watching'][uuid] = Watch.model(datastore_path=self.datastore_path, default=watch)
+                    _blank = deepcopy(self.generic_definition)
+                    _blank.update(watch)
+                    self.__data['watching'].update({uuid: _blank})
+                    self.__data['watching'][uuid]['newest_history_key'] = self.get_newest_history_key(uuid)
                     print("Watching:", uuid, self.__data['watching'][uuid]['url'])
 
-        # First time ran, Create the datastore.
-        except (FileNotFoundError):
+
+        # First time ran, doesnt exist.
+        except (FileNotFoundError, json.decoder.JSONDecodeError):
             if include_default_watches:
-                print("No JSON DB found at {}, creating JSON store at {}".format(self.json_store_path, self.datastore_path))
-                self.add_watch(url='https://news.ycombinator.com/',
-                               tag='Tech news',
-                               extras={'fetch_backend': 'html_requests'})
+                print("Creating JSON store at", self.datastore_path)
+
+                self.add_watch(url='http://www.quotationspage.com/random.php', tag='test')
+                self.add_watch(url='https://news.ycombinator.com/', tag='Tech news')
+                self.add_watch(url='https://www.gov.uk/coronavirus', tag='Covid')
+                self.add_watch(url='https://changedetection.io/CHANGELOG.txt')
 
-                self.add_watch(url='https://changedetection.io/CHANGELOG.txt',
-                               tag='changedetection.io',
-                               extras={'fetch_backend': 'html_requests'})
         self.__data['version_tag'] = version_tag
 
-        # Just to test that proxies.json if it exists, doesnt throw a parsing error on startup
-        test_list = self.proxy_list
-
         # Helper to remove password protection
         password_reset_lockfile = "{}/removepassword.lock".format(self.datastore_path)
         if path.isfile(password_reset_lockfile):
@@ -109,24 +118,41 @@ class ChangeDetectionStore:
 
         # Generate the URL access token for RSS feeds
         if not 'rss_access_token' in self.__data['settings']['application']:
+            import secrets
             secret = secrets.token_hex(16)
             self.__data['settings']['application']['rss_access_token'] = secret
 
-        # Generate the API access token
-        if not 'api_access_token' in self.__data['settings']['application']:
-            secret = secrets.token_hex(16)
-            self.__data['settings']['application']['api_access_token'] = secret
+        # Proxy list support - available as a selection in settings when text file is imported
+        # CSV list
+        # "name, address", or just "name"
+        proxy_list_file = "{}/proxies.txt".format(self.datastore_path)
+        if path.isfile(proxy_list_file):
+            self.import_proxy_list(proxy_list_file)
 
-        # Bump the update version by running updates
-        self.run_updates()
 
         self.needs_write = True
 
         # Finally start the thread that will manage periodic data saves to JSON
         save_data_thread = threading.Thread(target=self.save_datastore).start()
 
+    # Returns the newest key, but if theres only 1 record, then it's counted as not being new, so return 0.
+    def get_newest_history_key(self, uuid):
+
+        cur = self.__history_db_connection.cursor()
+
+        c = cur.execute("SELECT COUNT(*) FROM watch_history WHERE watch_uuid = :uuid", {"uuid": uuid}).fetchone()
+        if c and c[0] <= 1:
+            return 0
+
+        max = cur.execute("SELECT MAX(timestamp) FROM watch_history WHERE  watch_uuid  = :uuid", {"uuid": uuid}).fetchone()
+        return max[0]
+
+    def __refresh_history_max_timestamp(self):
+        # select watch_uuid, max(timestamp) from watch_history group by watch_uuid;
+        # could be way faster
+        x=1
+
     def set_last_viewed(self, uuid, timestamp):
-        logging.debug("Setting watch UUID: {} last viewed to {}".format(uuid, int(timestamp)))
         self.data['watching'][uuid].update({'last_viewed': int(timestamp)})
         self.needs_write = True
 
@@ -150,39 +176,51 @@ class ChangeDetectionStore:
                         del (update_obj[dict_key])
 
             self.__data['watching'][uuid].update(update_obj)
+            self.__data['watching'][uuid]['newest_history_key'] = self.get_newest_history_key(uuid)
 
         self.needs_write = True
 
     @property
     def threshold_seconds(self):
         seconds = 0
-        for m, n in Watch.mtable.items():
+        mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
+        minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 60))
+        for m, n in mtable.items():
             x = self.__data['settings']['requests']['time_between_check'].get(m)
             if x:
                 seconds += x * n
-        return seconds
-
-    @property
-    def has_unviewed(self):
-        for uuid, watch in self.__data['watching'].items():
-            if watch.viewed == False:
-                return True
-        return False
+        return max(seconds, minimum_seconds_recheck_time)
 
     @property
     def data(self):
+        has_unviewed = False
+        for uuid, v in self.__data['watching'].items():
+#            self.__data['watching'][uuid]['newest_history_key'] = self.get_newest_history_key(uuid)
+#            if int(v['newest_history_key']) <= int(v['last_viewed']):
+#                self.__data['watching'][uuid]['viewed'] = True
+
+#            else:
+#                self.__data['watching'][uuid]['viewed'] = False
+#                has_unviewed = True
+
+            # #106 - Be sure this is None on empty string, False, None, etc
+            # Default var for fetch_backend
+            if not self.__data['watching'][uuid]['fetch_backend']:
+                self.__data['watching'][uuid]['fetch_backend'] = self.__data['settings']['application']['fetch_backend']
+
         # Re #152, Return env base_url if not overriden, @todo also prefer the proxy pass url
         env_base_url = os.getenv('BASE_URL','')
         if not self.__data['settings']['application']['base_url']:
           self.__data['settings']['application']['base_url'] = env_base_url.strip('" ')
 
+        self.__data['has_unviewed'] = has_unviewed
+
         return self.__data
 
     def get_all_tags(self):
         tags = []
         for uuid, watch in self.data['watching'].items():
-            if watch['tag'] is None:
-                continue
+
             # Support for comma separated list of tags.
             for tag in watch['tag'].split(','):
                 tag = tag.strip()
@@ -192,24 +230,27 @@ class ChangeDetectionStore:
         tags.sort()
         return tags
 
+    def unlink_history_file(self, path):
+        try:
+            unlink(path)
+        except (FileNotFoundError, IOError):
+            pass
+
     # Delete a single watch by UUID
     def delete(self, uuid):
-        import pathlib
-        import shutil
-
         with self.lock:
             if uuid == 'all':
                 self.__data['watching'] = {}
 
                 # GitHub #30 also delete history records
                 for uuid in self.data['watching']:
-                    path = pathlib.Path(os.path.join(self.datastore_path, uuid))
-                    shutil.rmtree(path)
-                    self.needs_write_urgent = True
+                    for path in self.data['watching'][uuid]['history'].values():
+                        self.unlink_history_file(path)
 
             else:
-                path = pathlib.Path(os.path.join(self.datastore_path, uuid))
-                shutil.rmtree(path)
+                for path in self.data['watching'][uuid]['history'].values():
+                    self.unlink_history_file(path)
+
                 del self.data['watching'][uuid]
 
             self.needs_write_urgent = True
@@ -231,37 +272,23 @@ class ChangeDetectionStore:
 
         return False
 
+    def get_val(self, uuid, val):
+        # Probably their should be dict...
+        return self.data['watching'][uuid].get(val)
+
     # Remove a watchs data but keep the entry (URL etc)
-    def clear_watch_history(self, uuid):
+    def scrub_watch(self, uuid):
         import pathlib
 
-        self.__data['watching'][uuid].update({
-                'last_checked': 0,
-                'has_ldjson_price_data': None,
-                'last_error': False,
-                'last_notification_error': False,
-                'last_viewed': 0,
-                'previous_md5': False,
-                'track_ldjson_price_data': None,
-            })
-
-        # JSON Data, Screenshots, Textfiles (history index and snapshots), HTML in the future etc
-        for item in pathlib.Path(os.path.join(self.datastore_path, uuid)).rglob("*.*"):
-            unlink(item)
-
-        # Force the attr to recalculate
-        bump = self.__data['watching'][uuid].history
-
+        self.__data['watching'][uuid].update({'history': {}, 'last_checked': 0, 'last_changed': 0, 'newest_history_key': 0, 'previous_md5': False})
         self.needs_write_urgent = True
 
-    def add_watch(self, url, tag="", extras=None, write_to_disk_now=True):
+        for item in pathlib.Path(self.datastore_path).rglob(uuid+"/*.txt"):
+            unlink(item)
 
+    def add_watch(self, url, tag="", extras=None, write_to_disk_now=True):
         if extras is None:
             extras = {}
-        # should always be str
-        if tag is None or not tag:
-            tag = ''
-
         # Incase these are copied across, assume it's a reference and deepcopy()
         apply_extras = deepcopy(extras)
 
@@ -274,119 +301,85 @@ class ChangeDetectionStore:
                                      headers={'App-Guid': self.__data['app_guid']})
                 res = r.json()
 
-                # List of permissible attributes we accept from the wild internet
-                for k in [
-                    'body',
-                    'browser_steps',
-                    'css_filter',
-                    'extract_text',
-                    'extract_title_as_title',
-                    'headers',
-                    'ignore_text',
-                    'include_filters',
-                    'method',
-                    'paused',
-                    'previous_md5',
-                    'subtractive_selectors',
-                    'tag',
-                    'text_should_not_be_present',
-                    'title',
-                    'trigger_text',
-                    'url',
-                    'webdriver_js_execute_code',
-                ]:
+                # List of permisable stuff we accept from the wild internet
+                for k in ['url', 'tag',
+                                   'paused', 'title',
+                                   'previous_md5', 'headers',
+                                   'body', 'method',
+                                   'ignore_text', 'css_filter',
+                                   'subtractive_selectors', 'trigger_text',
+                                   'extract_title_as_title']:
                     if res.get(k):
-                        if k != 'css_filter':
-                            apply_extras[k] = res[k]
-                        else:
-                            # We renamed the field and made it a list
-                            apply_extras['include_filters'] = [res['css_filter']]
+                        apply_extras[k] = res[k]
 
             except Exception as e:
                 logging.error("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
-        if not is_safe_url(url):
-            flash('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX', 'error')
-            return None
 
         with self.lock:
+            # @todo use a common generic version of this
+            new_uuid = str(uuid_builder.uuid4())
             # #Re 569
-            new_watch = Watch.model(datastore_path=self.datastore_path, default={
+            # Not sure why deepcopy was needed here, sometimes new watches would appear to already have 'history' set
+            # I assumed this would instantiate a new object but somehow an existing dict was getting used
+            new_watch = deepcopy(Watch.model({
                 'url': url,
                 'tag': tag
-            })
+            }))
 
-            new_uuid = new_watch['uuid']
-            logging.debug("Added URL {} - {}".format(url, new_uuid))
 
             for k in ['uuid', 'history', 'last_checked', 'last_changed', 'newest_history_key', 'previous_md5', 'viewed']:
                 if k in apply_extras:
                     del apply_extras[k]
 
             new_watch.update(apply_extras)
-            self.__data['watching'][new_uuid] = new_watch
+            self.__data['watching'][new_uuid]=new_watch
 
-        self.__data['watching'][new_uuid].ensure_data_dir_exists()
+        # Get the directory ready
+        output_path = "{}/{}".format(self.datastore_path, new_uuid)
+        try:
+            mkdir(output_path)
+        except FileExistsError:
+            print(output_path, "already exists.")
 
         if write_to_disk_now:
             self.sync_to_json()
-
         return new_uuid
 
-    def visualselector_data_is_ready(self, watch_uuid):
+    # Save some text file to the appropriate path and bump the history
+    # result_obj from fetch_site_status.run()
+    def save_history_text(self, watch_uuid, contents):
+        import uuid
+
         output_path = "{}/{}".format(self.datastore_path, watch_uuid)
-        screenshot_filename = "{}/last-screenshot.png".format(output_path)
-        elements_index_filename = "{}/elements.json".format(output_path)
-        if path.isfile(screenshot_filename) and  path.isfile(elements_index_filename) :
-            return True
+        # Incase the operator deleted it, check and create.
+        if not os.path.isdir(output_path):
+            mkdir(output_path)
+
+        fname = "{}/{}.stripped.txt".format(output_path, uuid.uuid4())
+        with open(fname, 'wb') as f:
+            f.write(contents)
+            f.close()
+
+        return fname
+
+    def get_screenshot(self, watch_uuid):
+        output_path = "{}/{}".format(self.datastore_path, watch_uuid)
+        fname = "{}/last-screenshot.png".format(output_path)
+        if path.isfile(fname):
+            return fname
 
         return False
 
     # Save as PNG, PNG is larger but better for doing visual diff in the future
-    def save_screenshot(self, watch_uuid, screenshot: bytes, as_error=False):
-        if not self.data['watching'].get(watch_uuid):
-            return
-
-        if as_error:
-            target_path = os.path.join(self.datastore_path, watch_uuid, "last-error-screenshot.png")
-        else:
-            target_path = os.path.join(self.datastore_path, watch_uuid, "last-screenshot.png")
-
-        self.data['watching'][watch_uuid].ensure_data_dir_exists()
-
-        with open(target_path, 'wb') as f:
+    def save_screenshot(self, watch_uuid, screenshot: bytes):
+        output_path = "{}/{}".format(self.datastore_path, watch_uuid)
+        fname = "{}/last-screenshot.png".format(output_path)
+        with open(fname, 'wb') as f:
             f.write(screenshot)
             f.close()
 
-        # Make a JPEG that's used in notifications (due to being a smaller size) available
-        from PIL import Image
-        im1 = Image.open(target_path)
-        im1.convert('RGB').save(target_path.replace('.png','.jpg'), quality=int(os.getenv("NOTIFICATION_SCREENSHOT_JPG_QUALITY", 75)))
-
-
-    def save_error_text(self, watch_uuid, contents):
-        if not self.data['watching'].get(watch_uuid):
-            return
-        target_path = os.path.join(self.datastore_path, watch_uuid, "last-error.txt")
-
-        with open(target_path, 'w') as f:
-            f.write(contents)
-
-    def save_xpath_data(self, watch_uuid, data, as_error=False):
-        if not self.data['watching'].get(watch_uuid):
-            return
-        if as_error:
-            target_path = os.path.join(self.datastore_path, watch_uuid, "elements-error.json")
-        else:
-            target_path = os.path.join(self.datastore_path, watch_uuid, "elements.json")
-
-        with open(target_path, 'w') as f:
-            f.write(json.dumps(data))
-            f.close()
-
-
     def sync_to_json(self):
         logging.info("Saving JSON..")
         print("Saving JSON..")
@@ -439,8 +432,8 @@ class ChangeDetectionStore:
 
         index=[]
         for uuid in self.data['watching']:
-            for id in self.data['watching'][uuid].history:
-                index.append(self.data['watching'][uuid].history[str(id)])
+            for id in self.data['watching'][uuid]['history']:
+                index.append(self.data['watching'][uuid]['history'][str(id)])
 
         import pathlib
 
@@ -451,62 +444,20 @@ class ChangeDetectionStore:
                     print ("Removing",item)
                     unlink(item)
 
-    @property
-    def proxy_list(self):
-        proxy_list = {}
-        proxy_list_file = os.path.join(self.datastore_path, 'proxies.json')
+    def import_proxy_list(self, filename):
+        import csv
+        with open(filename, newline='') as f:
+            reader = csv.reader(f, skipinitialspace=True)
+            # @todo This loop can could be improved
+            l = []
+            for row in reader:
+                if len(row):
+                    if len(row)>=2:
+                        l.append(tuple(row[:2]))
+                    else:
+                        l.append(tuple([row[0], row[0]]))
+            self.proxy_list = l if len(l) else None
 
-        # Load from external config file
-        if path.isfile(proxy_list_file):
-            with open("{}/proxies.json".format(self.datastore_path)) as f:
-                proxy_list = json.load(f)
-
-        # Mapping from UI config if available
-        extras = self.data['settings']['requests'].get('extra_proxies')
-        if extras:
-            i=0
-            for proxy in extras:
-                i += 0
-                if proxy.get('proxy_name') and proxy.get('proxy_url'):
-                    k = "ui-" + str(i) + proxy.get('proxy_name')
-                    proxy_list[k] = {'label': proxy.get('proxy_name'), 'url': proxy.get('proxy_url')}
-
-
-        return proxy_list if len(proxy_list) else None
-
-
-
-
-    def get_preferred_proxy_for_watch(self, uuid):
-        """
-        Returns the preferred proxy by ID key
-        :param uuid: UUID
-        :return: proxy "key" id
-        """
-
-        if self.proxy_list is None:
-            return None
-
-        # If it's a valid one
-        watch = self.data['watching'].get(uuid)
-
-        if watch.get('proxy') and watch.get('proxy') in list(self.proxy_list.keys()):
-            return watch.get('proxy')
-
-        # not valid (including None), try the system one
-        else:
-            system_proxy_id = self.data['settings']['requests'].get('proxy')
-            # Is not None and exists
-            if self.proxy_list.get(system_proxy_id):
-                return system_proxy_id
-
-
-        # Fallback - Did not resolve anything, or doesnt exist, use the first available
-        if system_proxy_id is None or not self.proxy_list.get(system_proxy_id):
-            first_default = list(self.proxy_list)[0]
-            return first_default
-
-        return None
 
     # Run all updates
     # IMPORTANT - Each update could be run even when they have a new install and the schema is correct
@@ -554,132 +505,30 @@ class ChangeDetectionStore:
                 if watch.get('minutes_between_check', False):
                     self.data['watching'][uuid]['time_between_check']['minutes'] = watch['minutes_between_check']
 
-    # Move the history list to a flat text file index
-    # Better than SQLite because this list is only appended to, and works across NAS / NFS type setups
-    def update_2(self):
-        # @todo test running this on a newly updated one (when this already ran)
-        for uuid, watch in self.data['watching'].items():
-            history = []
-
-            if watch.get('history', False):
-                for d, p in watch['history'].items():
-                    d = int(d)  # Used to be keyed as str, we'll fix this now too
-                    history.append("{},{}\n".format(d,p))
-
-                if len(history):
-                    target_path = os.path.join(self.datastore_path, uuid)
-                    if os.path.exists(target_path):
-                        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))
-
-                # 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.
-                # In the distant future we can remove this entirely
-                self.data['watching'][uuid]['history'] = {}
-
-    # We incorrectly stored last_changed when there was not a change, and then confused the output list table
     def update_3(self):
-        # see https://github.com/dgtlmoon/changedetection.io/pull/835
-        return
+        """Migrate storage of history data to SQLite
+        - No need to store the history list in memory and re-write it everytime
+        - I've seen memory usage grow exponentially due to having large lists of watches with long histories
+        - Data about 'last changed' still stored in the main JSON struct which is fine
+        - We don't really need this data until we query against it (like for listing other available snapshots in the diff page etc)
+        """
 
-    # `last_changed` not needed, we pull that information from the history.txt index
-    def update_4(self):
-        for uuid, watch in self.data['watching'].items():
-            try:
-                # Remove it from the struct
-                del(watch['last_changed'])
-            except:
-                continue
-        return
+        if self.__history_db_connection:
+            # Create the table
+            self.__history_db_connection.execute("CREATE TABLE IF NOT EXISTS  watch_history(id INTEGER PRIMARY KEY, watch_uuid VARCHAR(36), timestamp INT, path TEXT, snapshot_type VARCHAR(10))")
+            self.__history_db_connection.execute("CREATE INDEX IF NOT EXISTS `uuid` ON `watch_history` (`watch_uuid`)")
+            self.__history_db_connection.execute("CREATE INDEX IF NOT EXISTS `uuid_timestamp` ON `watch_history` (`watch_uuid`, `timestamp`)")
 
-    def update_5(self):
-        # If the watch notification body, title look the same as the global one, unset it, so the watch defaults back to using the main settings
-        # In other words - the watch notification_title and notification_body are not needed if they are the same as the default one
-        current_system_body = self.data['settings']['application']['notification_body'].translate(str.maketrans('', '', "\r\n "))
-        current_system_title = self.data['settings']['application']['notification_body'].translate(str.maketrans('', '', "\r\n "))
-        for uuid, watch in self.data['watching'].items():
-            try:
-                watch_body = watch.get('notification_body', '')
-                if watch_body and watch_body.translate(str.maketrans('', '', "\r\n ")) == current_system_body:
-                    # Looks the same as the default one, so unset it
-                    watch['notification_body'] = None
+            # Insert each watch history list as executemany() for faster migration
+            for uuid, watch in self.data['watching'].items():
+                history = []
 
-                watch_title = watch.get('notification_title', '')
-                if watch_title and watch_title.translate(str.maketrans('', '', "\r\n ")) == current_system_title:
-                    # Looks the same as the default one, so unset it
-                    watch['notification_title'] = None
-            except Exception as e:
-                continue
-        return
+                if watch.get('history', False):
+                    for d, p in watch['history'].items():
+                        d = int(d) # Used to be keyed as str, we'll fix this now too
+                        history.append((uuid, d, p, 'text'))
 
-
-    # We incorrectly used common header overrides that should only apply to Requests
-    # These are now handled in content_fetcher::html_requests and shouldnt be passed to Playwright/Selenium
-    def update_7(self):
-        # These were hard-coded in early versions
-        for v in ['User-Agent', 'Accept', 'Accept-Encoding', 'Accept-Language']:
-            if self.data['settings']['headers'].get(v):
-                del self.data['settings']['headers'][v]
-
-    # Convert filters to a list of filters css_filter -> include_filters
-    def update_8(self):
-        for uuid, watch in self.data['watching'].items():
-            try:
-                existing_filter = watch.get('css_filter', '')
-                if existing_filter:
-                    watch['include_filters'] = [existing_filter]
-            except:
-                continue
-        return
-
-    # Convert old static notification tokens to jinja2 tokens
-    def update_9(self):
-        # Each watch
-        import re
-        # only { } not {{ or }}
-        r = r'(?<!{){(?!{)(\w+)(?<!})}(?!})'
-        for uuid, watch in self.data['watching'].items():
-            try:
-                n_body = watch.get('notification_body', '')
-                if n_body:
-                    watch['notification_body'] = re.sub(r, r'{{\1}}', n_body)
-
-                n_title = watch.get('notification_title')
-                if n_title:
-                    watch['notification_title'] = re.sub(r, r'{{\1}}', n_title)
-
-                n_urls = watch.get('notification_urls')
-                if n_urls:
-                    for i, url in enumerate(n_urls):
-                        watch['notification_urls'][i] = re.sub(r, r'{{\1}}', url)
-
-            except:
-                continue
-
-        # System wide
-        n_body = self.data['settings']['application'].get('notification_body')
-        if n_body:
-            self.data['settings']['application']['notification_body'] = re.sub(r, r'{{\1}}', n_body)
-
-        n_title = self.data['settings']['application'].get('notification_title')
-        if n_body:
-            self.data['settings']['application']['notification_title'] = re.sub(r, r'{{\1}}', n_title)
-
-        n_urls =  self.data['settings']['application'].get('notification_urls')
-        if n_urls:
-            for i, url in enumerate(n_urls):
-                self.data['settings']['application']['notification_urls'][i] = re.sub(r, r'{{\1}}', url)
-
-        return
-
-    # Some setups may have missed the correct default, so it shows the wrong config in the UI, although it will default to system-wide
-    def update_10(self):
-        for uuid, watch in self.data['watching'].items():
-            try:
-                if not watch.get('fetch_backend', ''):
-                    watch['fetch_backend'] = 'system'
-            except:
-                continue
-        return
+                    if len(history):
+                        self.__history_db_connection.executemany("INSERT INTO watch_history (watch_uuid, timestamp, path, snapshot_type) VALUES (?,?,?,?)", history)
+                        self.__history_db_connection.commit()
+                        del(self.data['watching'][uuid]['history'])

changedetectionio/templates/_common_fields.jinja

@@ -1,50 +1,44 @@
 
 {% from '_helpers.jinja' import render_field %}
 
-{% macro render_common_settings_form(form, emailprefix, settings_application) %}
+{% macro render_common_settings_form(form, current_base_url, emailprefix) %}
                         <div class="pure-control-group">
                             {{ render_field(form.notification_urls, rows=5, placeholder="Examples:
     Gitter - gitter://token/room
     Office365 - o365://TenantID:AccountEmail/ClientID/ClientSecret/TargetEmail
     AWS SNS - sns://AccessKeyID/AccessSecretKey/RegionName/+PhoneNo
-    SMTPS - mailtos://user:pass@mail.domain.com?to=receivingAddress@example.com",
-    class="notification-urls" )
+    SMTPS - mailtos://user:pass@mail.domain.com?to=receivingAddress@example.com", class="notification-urls")
                             }}
                             <div class="pure-form-message-inline">
                               <ul>
                                 <li>Use <a target=_new href="https://github.com/caronc/apprise">AppRise URLs</a> for notification to just about any service! <i><a target=_new href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes">Please read the notification services wiki here for important configuration notes</a></i>.</li>
                                 <li><code>discord://</code> only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
                                 <li><code>tgram://</code> bots cant send messages to other bots, so you should specify chat ID of non-bot user.</li>
-                                <li><code>tgram://</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>Go here for <a href="{{url_for('notification_logs')}}">notification debug logs</a></li>
                               </ul>
                             </div>
-                            <div class="notifications-wrapper">
-                              <a id="send-test-notification" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Send test notification</a>
-                            {% if emailprefix %}
-                              <a id="add-email-helper" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Add email</a>
-                            {% endif %}
-                              <a href="{{url_for('notification_logs')}}" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Notification debug logs</a>
-                            </div>
+                            <br/>
+                            <a id="send-test-notification" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Send test notification</a>
+{% if emailprefix %}
+                            <a id="add-email-helper" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Add email</a>
+{% endif %}
                         </div>
                         <div id="notification-customisation" class="pure-control-group">
                             <div class="pure-control-group">
-                                {{ render_field(form.notification_title, class="m-d notification-title", placeholder=settings_application['notification_title']) }}
+                                {{ render_field(form.notification_title, class="m-d notification-title") }}
                                 <span class="pure-form-message-inline">Title for all notifications</span>
                             </div>
                             <div class="pure-control-group">
-                                {{ render_field(form.notification_body , rows=5, class="notification-body", placeholder=settings_application['notification_body']) }}
+                                {{ render_field(form.notification_body , rows=5, class="notification-body") }}
                                 <span class="pure-form-message-inline">Body for all notifications</span>
                             </div>
                             <div class="pure-control-group">
-                            <!-- unsure -->
-                                {{ render_field(form.notification_format , class="notification-format") }}
+                                {{ render_field(form.notification_format , rows=5, class="notification-format") }}
                                 <span class="pure-form-message-inline">Format for all notifications</span>
                             </div>
                             <div class="pure-controls">
-                            <p class="pure-form-message-inline">
-                                You can use <a target="_new" href="https://jinja.palletsprojects.com/en/3.0.x/templates/">Jinja2</a> templating in the notification title, body and URL.
-                            </p>
+                            <span class="pure-form-message-inline">
+                                These tokens can be used in the notification body and title to customise the notification text.
 
                                 <table class="pure-table" id="token-table">
                                     <thead>
@@ -55,49 +49,52 @@
                                     </thead>
                                     <tbody>
                                     <tr>
-                                        <td><code>{{ '{{ base_url }}' }}</code></td>
+                                        <td><code>{base_url}</code></td>
                                         <td>The URL of the changedetection.io instance you are running.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{ watch_url }}' }}</code></td>
+                                        <td><code>{watch_url}</code></td>
                                         <td>The URL being watched.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{ watch_uuid }}' }}</code></td>
+                                        <td><code>{watch_uuid}</code></td>
                                         <td>The UUID of the watch.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{ watch_title }}' }}</code></td>
+                                        <td><code>{watch_title}</code></td>
                                         <td>The title of the watch.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{ watch_tag }}' }}</code></td>
-                                        <td>The watch label / tag</td>
+                                        <td><code>{watch_tag}</code></td>
+                                        <td>The tag of the watch.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{ preview_url }}' }}</code></td>
+                                        <td><code>{preview_url}</code></td>
                                         <td>The URL of the preview page generated by changedetection.io.</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{ diff_url }}' }}</code></td>
+                                        <td><code>{diff}</code></td>
                                         <td>The diff output - differences only</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{ diff_full }}' }}</code></td>
+                                        <td><code>{diff_full}</code></td>
                                         <td>The diff output - full difference output</td>
                                     </tr>
                                     <tr>
-                                        <td><code>{{ '{{ current_snapshot }}' }}</code></td>
+                                        <td><code>{diff_url}</code></td>
+                                        <td>The URL of the diff page generated by changedetection.io.</td>
+                                    </tr>
+                                    <tr>
+                                        <td><code>{current_snapshot}</code></td>
                                         <td>The current snapshot value, useful when combined with JSON or CSS filters
                                         </td>
                                     </tr>
                                     </tbody>
                                 </table>
-                                <div class="pure-form-message-inline">
-                                    <br>
-                                    URLs generated by changedetection.io (such as <code>{{ '{{ diff_url }}' }}</code>) require the <code>BASE_URL</code> environment variable set.<br/>
-                                    Your <code>BASE_URL</code> var is currently "{{settings_application['current_base_url']}}"
-                                </div>
+                                <br/>
+                                URLs generated by changedetection.io (such as <code>{diff_url}</code>) require the <code>BASE_URL</code> environment variable set.<br/>
+                                Your <code>BASE_URL</code> var is currently "{{current_base_url}}"
+                            </span>
                             </div>
                         </div>
 {% endmacro %}

changedetectionio/templates/_pagination.jinja

@@ -1,7 +0,0 @@
-{% macro pagination(sorted_watches, total_per_page, current_page) %}
-  {{ sorted_watches|length }}
-
-  {% for row in sorted_watches|batch(total_per_page, ' ') %}
-    {{ loop.index}}
-  {% endfor %}
-{% endmacro %}

changedetectionio/templates/base.html

@@ -1,152 +1,110 @@
-<!DOCTYPE html>
-<html lang="en" data-darkmode="{{ get_darkmode_state() }}">
-
-  <head>
-    <meta charset="utf-8"/>
-    <meta name="viewport" content="width=device-width, initial-scale=1.0"/>
-    <meta name="description" content="Self hosted website change detection."/>
+<!doctype html>
+<html lang="en">
+<head>
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <meta name="description" content="Self hosted website change detection.">
     <title>Change Detection{{extra_title}}</title>
-    <link rel="alternate" type="application/rss+xml" title="Changedetection.io » Feed{% if active_tag %}- {{active_tag}}{% endif %}" href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}"/>
-    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='pure-min.css')}}"/>
-    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='styles.css')}}"/>
+    <link rel="alternate" type="application/rss+xml" title="Changedetection.io » Feed{% if active_tag %}- {{active_tag}}{% endif %}" href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}" />
+    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='pure-min.css')}}">
+    <link rel="stylesheet" href="{{url_for('static_content', group='styles', filename='styles.css')}}">
     {% if extra_stylesheets %}
-      {% for m in extra_stylesheets %}
-        <link rel="stylesheet" href="{{ m }}?ver=1000"/>
-      {% endfor %}
+        {% for m in extra_stylesheets %}
+        <link rel="stylesheet" href="{{ m }}?ver=1000">
+        {% endfor %}
     {% endif %}
-
-    <link rel="apple-touch-icon" sizes="180x180" href="{{url_for('static_content', group='favicons', filename='apple-touch-icon.png')}}"/>
-    <link rel="icon" type="image/png" sizes="32x32" href="{{url_for('static_content', group='favicons', filename='favicon-32x32.png')}}"/>
-    <link rel="icon" type="image/png" sizes="16x16" href="{{url_for('static_content', group='favicons', filename='favicon-16x16.png')}}"/>
-    <link rel="manifest" href="{{url_for('static_content', group='favicons', filename='site.webmanifest')}}"/>
-    <link rel="mask-icon" href="{{url_for('static_content', group='favicons', filename='safari-pinned-tab.svg')}}" color="#5bbad5"/>
-    <link rel="shortcut icon" href="{{url_for('static_content', group='favicons', filename='favicon.ico')}}"/>
-    <meta name="msapplication-TileColor" content="#da532c"/>
-    <meta name="msapplication-config" content="favicons/browserconfig.xml"/>
-    <meta name="theme-color" content="#ffffff"/>
-
     <style>
-      body::before {
-        background-image: url({{url_for('static_content', group='images', filename='gradient-border.png') }});
-      }
+    body::before {
+        background-image: url({{url_for('static_content', group='images', filename='gradient-border.png')}});
+    }
     </style>
     <script type="text/javascript" src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
-  </head>
 
-  <body>
-    <div class="header">
-      <div class="home-menu pure-menu pure-menu-horizontal pure-menu-fixed" id="nav-menu">
+</head>
+
+<body>
+
+<div class="header">
+
+    <div class="home-menu pure-menu pure-menu-horizontal pure-menu-fixed" id="nav-menu">
         {% if has_password and not current_user.is_authenticated %}
-          <a class="pure-menu-heading" href="https://github.com/dgtlmoon/changedetection.io" rel="noopener">
-            <strong>Change</strong>Detection.io</a>
+            <a class="pure-menu-heading" href="https://github.com/dgtlmoon/changedetection.io" rel="noopener"><strong>Change</strong>Detection.io</a>
         {% else %}
-          <a class="pure-menu-heading" href="{{url_for('index')}}">
-            <strong>Change</strong>Detection.io</a>
+            <a class="pure-menu-heading" href="{{url_for('index')}}"><strong>Change</strong>Detection.io</a>
         {% endif %}
         {% if current_diff_url %}
-          <a class="current-diff-url" href="{{ current_diff_url }}">
-            <span style="max-width: 30%; overflow: hidden">{{ current_diff_url }}</span></a>
+        <a class=current-diff-url href="{{ current_diff_url }}"><span style="max-width: 30%; overflow: hidden;">{{ current_diff_url }}</span></a>
         {% else %}
-          {% if new_version_available and not(has_password and not current_user.is_authenticated) %}
-            <span id="new-version-text" class="pure-menu-heading">
-              <a href="https://github.com/dgtlmoon/changedetection.io">A new version is available</a>
-            </span>
-          {% endif %}
+        {% if new_version_available and not (has_password and not current_user.is_authenticated) %}
+        <span id="new-version-text" class="pure-menu-heading"><a href="https://github.com/dgtlmoon/changedetection.io">A new version is available</a></span>
+        {% endif %}
         {% endif %}
 
-        <ul class="pure-menu-list" id="top-right-menu">
-          {% if current_user.is_authenticated or not has_password %}
-            {% if not
-            current_diff_url %}
-              <li class="pure-menu-item">
+        <ul class="pure-menu-list"  id="top-right-menu">
+        {% if current_user.is_authenticated or not has_password %}
+            {% if not current_diff_url %}
+            <li class="pure-menu-item">
                 <a href="{{ url_for('settings_page')}}" class="pure-menu-link">SETTINGS</a>
-              </li>
-              <li class="pure-menu-item">
+            </li>
+            <li class="pure-menu-item">
                 <a href="{{ url_for('import_page')}}" class="pure-menu-link">IMPORT</a>
-              </li>
-              <li class="pure-menu-item">
+            </li>
+            <li class="pure-menu-item">
                 <a href="{{ url_for('get_backup')}}" class="pure-menu-link">BACKUP</a>
-              </li>
+            </li>
             {% else %}
-              <li class="pure-menu-item">
+            <li class="pure-menu-item">
                 <a href="{{ url_for('edit_page', uuid=uuid, next='diff') }}" class="pure-menu-link">EDIT</a>
-              </li>
-            {% endif %}
-          {% else %}
-            <li class="pure-menu-item">
-              <a class="pure-menu-link" href="https://github.com/dgtlmoon/changedetection.io">Website Change Detection and Notification.</a>
             </li>
-          {% endif %}
-          {% if current_user.is_authenticated %}
-            <li class="pure-menu-item">
-              <a href="{{url_for('logout')}}" class="pure-menu-link">LOG OUT</a>
-            </li>
-          {% endif %}
-          <li class="pure-menu-item">
-            {% if dark_mode %}
-            {% set darkClass = 'dark' %}
             {% endif %}
-            <button class="toggle-theme {{darkClass}}" type="button" title="Toggle Light/Dark Mode">
-              <span class="visually-hidden">Toggle light/dark mode</span>
-              <span class="icon-light">
-                {% include "svgs/light-mode-toggle-icon.svg" %}
-              </span>
-              <span class="icon-dark">
-                {% include "svgs/dark-mode-toggle-icon.svg" %}
-              </span>
-            </button>
-          </li>
-          <li class="pure-menu-item">
-            <a class="github-link" href="https://github.com/dgtlmoon/changedetection.io">
-              {% include "svgs/github.svg" %}
-            </a>
-          </li>
+        {% else %}
+            <li class="pure-menu-item">
+                <a class="pure-menu-link" href="https://github.com/dgtlmoon/changedetection.io">Website Change Detection and Notification.</a>
+            </li>
+        {% endif %}
+
+        {% if current_user.is_authenticated %}
+            <li class="pure-menu-item"><a href="{{url_for('logout')}}" class="pure-menu-link">LOG OUT</a></li>
+        {% endif %}
+            <li class="pure-menu-item"><a class="github-link" href="https://github.com/dgtlmoon/changedetection.io">
+                <svg class="octicon octicon-mark-github v-align-middle" height="32" viewBox="0 0 16 16"
+                     version="1.1"
+                     width="32" aria-hidden="true">
+                    <path fill-rule="evenodd"
+                          d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.013 8.013 0 0016 8c0-4.42-3.58-8-8-8z"></path>
+                </svg>
+            </a></li>
         </ul>
-      </div>
     </div>
-    {% if hosted_sticky %}
-      <div class="sticky-tab" id="hosted-sticky">
-        <a href="https://lemonade.changedetection.io/start?ref={{guid}}">Let us host your instance!</a>
-      </div>
-    {% endif %}
-    {% if left_sticky %}
-      <div class="sticky-tab" id="left-sticky">
-        <a href="{{url_for('preview_page', uuid=uuid)}}">Show current snapshot</a>
-      </div>
-    {% endif %}
-    {% if right_sticky %}
-      <div class="sticky-tab" id="right-sticky">{{ right_sticky }}</div>
-    {% endif %}
-    <section class="content">
-      <header>
+</div>
+{% if hosted_sticky %}<div class="sticky-tab" id="hosted-sticky"><a href="https://lemonade.changedetection.io/start?ref={{guid}}">Let us host your instance!</a></div>{% endif %}
+{% if left_sticky %}<div class="sticky-tab" id="left-sticky"><a href="{{url_for('preview_page', uuid=uuid)}}">Show current snapshot</a></div> {% endif %}
+{% if right_sticky %}<div class="sticky-tab" id="right-sticky">{{ right_sticky }}</div> {% endif %}
+<section class="content">
+    <header>
         {% block header %}{% endblock %}
-      </header>
+    </header>
 
-      {% with messages = get_flashed_messages(with_categories = true) %}
-      {% if
-      messages %}
-        <ul class="messages">
-          {% for category, message in messages %}
-            <li class="{{ category }}">{{ message }}</li>
-          {% endfor %}
+    {% with messages = get_flashed_messages(with_categories=true) %}
+      {% if messages %}
+        <ul class=messages>
+        {% for category, message in messages %}
+          <li class="{{ category }}">{{ message }}</li>
+        {% endfor %}
         </ul>
       {% endif %}
-      {% endwith %}
-      {% if session['share-link'] %}
+    {% endwith %}
+
+    {% if session['share-link'] %}
         <ul class="messages with-share-link">
-          <li class="message">
-            Share this link:
-            <span id="share-link">{{ session['share-link'] }}</span>
-            <img style="height: 1em; display: inline-block" src="{{url_for('static_content', group='images', filename='copy.svg')}}"/>
-          </li>
+          <li class="message">Share this link: <span id="share-link">{{ session['share-link'] }}</span> <img style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='copy.svg')}}" /></li>
         </ul>
-      {% endif %}
-      {% block content %}{% endblock %}
-    </section>
-    <script
-      type="text/javascript"
-      src="{{url_for('static_content', group='js', filename='toggle-theme.js')}}"
-      defer></script>
-  </body>
+    {% endif %}
 
+    {% block content %}
+
+    {% endblock %}
+</section>
+
+</body>
 </html>

changedetectionio/templates/clear_all_history.html

@@ -1,49 +0,0 @@
-{% extends 'base.html' %} {% block content %}
-<div class="edit-form">
-  <div class="box-wrap inner">
-    <form
-      class="pure-form pure-form-stacked"
-      action="{{url_for('clear_all_history')}}"
-      method="POST"
-    >
-      <input type="hidden" name="csrf_token" value="{{ csrf_token() }}" />
-      <fieldset>
-        <div class="pure-control-group">
-          This will remove version history (snapshots) for ALL watches, but keep
-          your list of URLs! <br />
-          You may like to use the <strong>BACKUP</strong> link first.<br />
-        </div>
-        <br />
-        <div class="pure-control-group">
-          <label for="confirmtext">Confirmation text</label>
-          <input
-            type="text"
-            id="confirmtext"
-            required=""
-            name="confirmtext"
-            value=""
-            size="10"
-          />
-          <span class="pure-form-message-inline"
-            >Type in the word <strong>clear</strong> to confirm that you
-            understand.</span
-          >
-        </div>
-        <br />
-        <div class="pure-control-group">
-          <button type="submit" class="pure-button pure-button-primary">
-            Clear History!
-          </button>
-        </div>
-        <br />
-        <div class="pure-control-group">
-          <a href="{{url_for('index')}}" class="pure-button button-cancel"
-            >Cancel</a
-          >
-        </div>
-      </fieldset>
-    </form>
-  </div>
-</div>
-
-{% endblock %}

changedetectionio/templates/diff.html

@@ -1,14 +1,6 @@
 {% extends 'base.html' %}
-{% from '_helpers.jinja' import render_field, render_checkbox_field, render_button %}
-{% block content %}
-<script>
-    const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
-    {% if last_error_screenshot %}
-    const error_screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid, error_screenshot=1) }}";
-    {% endif %}
-</script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
 
+{% block content %}
 <div id="settings">
     <h1>Differences</h1>
     <form class="pure-form " action="" method="GET">
@@ -21,14 +13,11 @@
 
             <label for="diffChars" class="pure-checkbox">
                 <input type="radio" name="diff_type" id="diffChars" value="diffChars"/> Chars</label>
-            <!-- @todo - when mimetype is JSON, select this by default? -->
-            <label for="diffJson" class="pure-checkbox">
-                <input type="radio" name="diff_type" id="diffJson" value="diffJson" /> JSON</label>
 
             {% if versions|length >= 1 %}
             <label for="diff-version">Compare newest (<span id="current-v-date"></span>) with</label>
             <select id="diff-version" name="previous_version">
-                {% for version in versions|reverse %}
+                {% for version in versions %}
                 <option value="{{version}}" {% if version== current_previous_version %} selected="" {% endif %}>
                     {{version}}
                 </option>
@@ -40,11 +29,6 @@
     </form>
     <del>Removed text</del>
     <ins>Inserted Text</ins>
-    <span>
-        <!-- https://github.com/kpdecker/jsdiff/issues/389 ? -->
-        <label for="ignoreWhitespace" class="pure-checkbox" id="label-diff-ignorewhitespace">
-            <input type="checkbox" id="ignoreWhitespace" name="ignoreWhitespace"/> Ignore Whitespace</label>
-    </span>
 </div>
 
 <div id="diff-jump">
@@ -54,36 +38,17 @@
 <script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <div class="tabs">
     <ul>
-        {% if last_error_text %}<li class="tab" id="error-text-tab"><a href="#error-text">Error Text</a></li> {% endif %}
-        {% if last_error_screenshot %}<li class="tab" id="error-screenshot-tab"><a href="#error-screenshot">Error Screenshot</a></li> {% endif %}
-        <li class="tab" id=""><a href="#text">Text</a></li>
-        <li class="tab" id="screenshot-tab"><a href="#screenshot">Screenshot</a></li>
-        <li class="tab" id="extract-tab"><a href="#extract">Extract Data</a></li>
+        <li class="tab" id="default-tab"><a href="#text">Text</a></li>
+{% if screenshot %}
+        <li class="tab"><a href="#screenshot">Current screenshot</a></li>
+{% endif %}
     </ul>
 </div>
 
 <div id="diff-ui">
-    <div class="tab-pane-inner" id="error-text">
-        <div class="snapshot-age error">{{watch_a.error_text_ctime|format_seconds_ago}} seconds ago</div>
-        <pre>
-            {{ last_error_text }}
-        </pre>
-    </div>
-
-    <div class="tab-pane-inner" id="error-screenshot">
-        <div class="snapshot-age error">{{watch_a.snapshot_error_screenshot_ctime|format_seconds_ago}} seconds ago</div>
-        <img id="error-screenshot-img"  style="max-width: 80%" alt="Current error-ing screenshot from most recent request"/>
-    </div>
-
      <div class="tab-pane-inner" id="text">
-         <div class="tip">Pro-tip: Use <strong>show current snapshot</strong> tab to visualise what will be ignored.</div>
-
-         {% if password_enabled_and_share_is_off %}
-           <div class="tip">Pro-tip: You can enable <strong>"share access when password is enabled"</strong> from settings</div>
-         {% endif %}
-
-         <div class="snapshot-age">{{watch_a.snapshot_text_ctime|format_timestamp_timeago}}</div>
-
+         <div class="tip">Pro-tip: Use <strong>show current snapshot</strong> tab to visualise what will be ignored.
+         </div>
          <table>
              <tbody>
              <tr>
@@ -98,60 +63,136 @@
          </table>
          Diff algorithm from the amazing <a href="https://github.com/kpdecker/jsdiff">github.com/kpdecker/jsdiff</a>
      </div>
+
+{% if screenshot %}
      <div class="tab-pane-inner" id="screenshot">
-         <div class="tip">
-             For now, Differences are performed on text, not graphically, only the latest screenshot is available.
-         </div>
-         {% if is_html_webdriver %}
-           {% if screenshot %}
-            <div class="snapshot-age">{{watch_a.snapshot_screenshot_ctime|format_timestamp_timeago}}</div>
-            <img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request"/>
-           {% else %}
-              No screenshot available just yet! Try rechecking the page.
-           {% endif %}
-         {% else %}
-           <strong>Screenshot requires Playwright/WebDriver enabled</strong>
-         {% endif %}
+         <p>
+         <i>For now, only the most recent screenshot is saved and displayed.</i>
+             </p>
+
+        <img src="{{url_for('static_content', group='screenshot', filename=uuid)}}">
      </div>
-    <div class="tab-pane-inner" id="extract">
-        <form id="extract-data-form" class="pure-form pure-form-stacked edit-form"
-              action="{{ url_for('diff_history_page', uuid=uuid) }}#extract"
-              method="POST">
-            <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
+{% endif %}
 
-            <p>This tool will extract text data from all of the watch history.</p>
-
-            <div class="pure-control-group">
-                {{ render_field(extract_form.extract_regex) }}
-                <span class="pure-form-message-inline">
-                    A <strong>RegEx</strong> is a pattern that identifies exactly which part inside of the text that you want to extract.<br/>
-
-                    <p>
-                        For example, to extract only the numbers from text &dash;</br>
-                        <strong>Raw text</strong>: <code>Temperature <span style="color: red">5.5</span>°C in Sydney</code></br>
-                        <strong>RegEx to extract:</strong> <code>Temperature <span style="color: red">([0-9\.]+)</span></code><br/>
-                    </p>
-                    <p>
-                        <a href="https://RegExr.com/">Be sure to test your RegEx here.</a>
-                    </p>
-                    <p>
-                        Each RegEx group bracket <code>()</code> will be in its own column, the first column value is always the date.
-                    </p>
-                </span>
-            </div>
-            <div class="pure-control-group">
-                {{ render_button(extract_form.extract_submit_button) }}
-            </div>
-        </form>
-    </div>
 </div>
 
-<script>
-    const newest_version_timestamp = {{newest_version_timestamp}};
-</script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff.min.js')}}"></script>
 
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-render.js')}}"></script>
+<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff.js')}}"></script>
+
+<script defer="">
+
+
+var a = document.getElementById('a');
+var b = document.getElementById('b');
+var result = document.getElementById('result');
+
+function changed() {
+	var diff = JsDiff[window.diffType](a.textContent, b.textContent);
+	var fragment = document.createDocumentFragment();
+	for (var i=0; i < diff.length; i++) {
+
+		if (diff[i].added && diff[i + 1] && diff[i + 1].removed) {
+			var swap = diff[i];
+			diff[i] = diff[i + 1];
+			diff[i + 1] = swap;
+		}
+
+		var node;
+		if (diff[i].removed) {
+			node = document.createElement('del');
+			node.classList.add("change");
+			node.appendChild(document.createTextNode(diff[i].value));
+
+		} else if (diff[i].added) {
+			node = document.createElement('ins');
+			node.classList.add("change");
+			node.appendChild(document.createTextNode(diff[i].value));
+		} else {
+			node = document.createTextNode(diff[i].value);
+		}
+		fragment.appendChild(node);
+	}
+
+	result.textContent = '';
+	result.appendChild(fragment);
+
+	// Jump at start
+	inputs.current=0;
+    next_diff();
+}
+
+window.onload = function() {
+
+
+    /* Convert what is options from UTC time.time() to local browser time */
+    var diffList=document.getElementById("diff-version");
+    if (typeof(diffList) != 'undefined' && diffList != null) {
+        for (var option of diffList.options) {
+          var dateObject = new Date(option.value*1000);
+          option.label=dateObject.toLocaleString();
+        }
+    }
+
+    /* Set current version date as local time in the browser also */
+    var current_v = document.getElementById("current-v-date");
+    var dateObject = new Date({{ newest_version_timestamp }}*1000);
+    current_v.innerHTML=dateObject.toLocaleString();
+
+
+	onDiffTypeChange(document.querySelector('#settings [name="diff_type"]:checked'));
+	changed();
+
+};
+
+a.onpaste = a.onchange =
+b.onpaste = b.onchange = changed;
+
+if ('oninput' in a) {
+	a.oninput = b.oninput = changed;
+} else {
+	a.onkeyup = b.onkeyup = changed;
+}
+
+function onDiffTypeChange(radio) {
+	window.diffType = radio.value;
+// Not necessary 
+//	document.title = "Diff " + radio.value.slice(4);
+}
+
+var radio = document.getElementsByName('diff_type');
+for (var i = 0; i < radio.length; i++) {
+	radio[i].onchange = function(e) {
+		onDiffTypeChange(e.target);
+		changed();
+	}
+}
+
+
+var inputs = document.getElementsByClassName('change');
+inputs.current=0;
+
+
+function next_diff() {
+
+    var element = inputs[inputs.current];
+    var headerOffset = 80;
+    var elementPosition = element.getBoundingClientRect().top;
+    var offsetPosition = elementPosition - headerOffset +  window.scrollY;
+
+    window.scrollTo({
+         top: offsetPosition,
+         behavior: "smooth"
+    });
+
+    inputs.current++;
+    if(inputs.current >= inputs.length) {
+      inputs.current=0;
+    }
+}
+
+
+
+</script>
 
 
 {% endblock %}

changedetectionio/templates/edit.html

@@ -5,36 +5,19 @@
 <script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
 <script>
     const notification_base_url="{{url_for('ajax_callback_send_notification_test')}}";
-    const watch_visual_selector_data_url="{{url_for('static_content', group='visual_selector_data', filename=uuid)}}";
-    const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
-    const playwright_enabled={% if playwright_enabled %} true {% else %} false {% endif %};
-
 {% if emailprefix %}
     const email_notification_prefix=JSON.parse('{{ emailprefix|tojson }}');
 {% endif %}
-
-    const browser_steps_config=JSON.parse('{{ browser_steps_config|tojson }}');
-    const browser_steps_sync_url="{{url_for('browser_steps.browsersteps_ui_update', uuid=uuid)}}";
 </script>
-
 <script type="text/javascript" src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>
 <script type="text/javascript" src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='visual-selector.js')}}" defer></script>
-{% if playwright_enabled %}
-<script type="text/javascript" src="{{url_for('static_content', group='js', filename='browser-steps.js')}}" defer></script>
-{% endif %}
 
 <div class="edit-form monospaced-textarea">
 
     <div class="tabs collapsable">
         <ul>
-            <li class="tab" id=""><a href="#general">General</a></li>
+            <li class="tab" id="default-tab"><a href="#general">General</a></li>
             <li class="tab"><a href="#request">Request</a></li>
-            {% if playwright_enabled %}
-            <li class="tab"><a id="browsersteps-tab" href="#browser-steps">Browser Steps</a></li>
-            {% endif %}
-            <li class="tab"><a id="visualselector-tab" href="#visualselector">Visual Filter Selector</a></li>
             <li class="tab"><a href="#filters-and-triggers">Filters &amp; Triggers</a></li>
             <li class="tab"><a href="#notifications">Notifications</a></li>
         </ul>
@@ -42,15 +25,14 @@
 
     <div class="box-wrap inner">
         <form class="pure-form pure-form-stacked"
-              action="{{ url_for('edit_page', uuid=uuid, next = request.args.get('next'), unpause_on_save = request.args.get('unpause_on_save')) }}" method="POST">
+              action="{{ url_for('edit_page', uuid=uuid, next = request.args.get('next') ) }}" method="POST">
              <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
 
             <div class="tab-pane-inner" id="general">
                 <fieldset>
                     <div class="pure-control-group">
                         {{ render_field(form.url, placeholder="https://...", required=true, class="m-d") }}
-                        <span class="pure-form-message-inline">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></span><br/>
-                        <span class="pure-form-message-inline">You can use variables in the URL, perfect for inserting the current date and other logic, <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a></span><br/>
+                        <span class="pure-form-message-inline">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></span>
                     </div>
                     <div class="pure-control-group">
                         {{ render_field(form.title, class="m-d") }}
@@ -72,12 +54,6 @@
                     <div class="pure-control-group">
                         {{ render_checkbox_field(form.extract_title_as_title) }}
                     </div>
-                    <div class="pure-control-group">
-                        {{ render_checkbox_field(form.filter_failure_notification_send) }}
-                        <span class="pure-form-message-inline">
-                         Sends a notification when the filter can no longer be seen on the page, good for knowing when the page changed and your filter will not work anymore.
-                        </span>
-                    </div>
                 </fieldset>
             </div>
 
@@ -87,7 +63,6 @@
                         <span class="pure-form-message-inline">
                             <p>Use the <strong>Basic</strong> method (default) where your watched site doesn't need Javascript to render.</p>
                             <p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
-                            Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using BrightData Proxies, find out more here.</a>
                         </span>
                     </div>
                 {% if form.proxy %}
@@ -98,43 +73,19 @@
                         </span>
                     </div>
                 {% endif %}
-                    <div  class="pure-control-group inline-radio">
-                        {{ render_checkbox_field(form.ignore_status_codes) }}
-                    </div>
-                <fieldset id="webdriver-override-options">
-                    <div class="pure-control-group">
-                        {{ render_field(form.webdriver_delay) }}
-                        <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/>
-                            This will wait <i>n</i> seconds before extracting the text.
-                            {% if using_global_webdriver_wait %}
-                            <br/><strong>Using the current global default settings</strong>
-                            {% endif %}
-                        </div>
-                    </div>
-                    <div class="pure-control-group">
-                        {{ 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>
-                        </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">
+                    <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>
+                    <div class="pure-control-group">
                         {{ render_field(form.method) }}
                     </div>
-                    <div class="pure-control-group" id="request-headers">
+                    <div class="pure-control-group">
 {{ render_field(form.headers, rows=5, placeholder="Example
 Cookie: foobar
 User-Agent: wonderbra 1.0") }}
                     </div>
-                    <div class="pure-control-group" id="request-body">
+                    <div class="pure-control-group">
                                         {{ render_field(form.body, rows=5, placeholder="Example
 {
    \"name\":\"John\",
@@ -142,80 +93,25 @@ User-Agent: wonderbra 1.0") }}
    \"car\":null
 }") }}
                     </div>
-                </fieldset>
-            </div>
-            {% if playwright_enabled %}
-            <div class="tab-pane-inner" id="browser-steps">
-                <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}">
-                <fieldset>
-                    <div class="pure-control-group">
-                        <!--
-                        Too hard right now, better to just send the events to the fetcher for now and leave it in the final screenshot
-                        and/or report an error
-                        <a id="play-steps" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Play steps  ▶</a>
-                        -->
-
-                        <!---  Do this later -->
-                        <div class="checkbox" style="display: none;">
-                            <input type=checkbox id="include_text_elements" > <label for="include_text_elements">Turn on text finder</label>
-                        </div>
-
-                        <div id="loading-status-text" style="display: none;">Please wait, first browser step can take a little time to load..<div class="spinner"></div></div>
-                        <div class="flex-wrapper" >
-
-                            <div id="browser-steps-ui" class="noselect"  style="width: 100%; background-color: #eee; border-radius: 5px;">
-
-                                <div class="noselect"  id="browsersteps-selector-wrapper" style="width: 100%">
-                                    <span class="loader" >
-                                        <span id="browsersteps-click-start">
-                                            <h2 >Click here to Start</h2>
-                                            Please allow 10-15 seconds for the browser to connect.
-                                        </span>
-                                        <div class="spinner"  style="display: none;"></div>
-                                    </span>
-                                    <img  class="noselect" id="browsersteps-img" src="" style="max-width: 100%; width: 100%;" />
-                                    <canvas  class="noselect" id="browsersteps-selector-canvas" style="max-width: 100%; width: 100%;"></canvas>
-                                </div>
-                            </div>
-                            <div id="browser-steps-fieldlist" style="padding-left: 1em;  width: 350px; font-size: 80%;" >
-                                <span id="browserless-seconds-remaining">Loading</span> <span style="font-size: 80%;"> (<a target=_new href="https://github.com/dgtlmoon/changedetection.io/pull/478/files#diff-1a79d924d1840c485238e66772391268a89c95b781d69091384cf1ea1ac146c9R4">?</a>) </span>
-                                {{ render_field(form.browser_steps) }}
-                            </div>
-                        </div>
+                    <div>
+                        {{ render_checkbox_field(form.ignore_status_codes) }}
                     </div>
                 </fieldset>
+                <br/>
             </div>
-            {% endif %}
 
             <div class="tab-pane-inner" id="notifications">
+                <strong>Note: <i>These settings override the global settings for this watch.</i></strong>
                 <fieldset>
-                    <div  class="pure-control-group inline-radio">
-                      {{ render_checkbox_field(form.notification_muted) }}
-                    </div>
-                    {% if is_html_webdriver %}
-                    <div class="pure-control-group inline-radio">
-                      {{ render_checkbox_field(form.notification_screenshot) }}
-                        <span class="pure-form-message-inline">
-                            <strong>Use with caution!</strong> This will easily fill up your email storage quota or flood other storages.
-                        </span>
-                    </div>
-                    {% endif %}
-                    <div class="field-group" id="notification-field-group">
-                        {% if has_default_notification_urls %}
-                        <div class="inline-warning">
-                            <img class="inline-warning-icon" src="{{url_for('static_content', group='images', filename='notice.svg')}}" alt="Look out!" title="Lookout!"/>
-                            There are <a href="{{ url_for('settings_page')}}#notifications">system-wide notification URLs enabled</a>, this form will override notification settings for this watch only &dash; an empty Notification URL list here will still send notifications.
-                        </div>
-                        {% endif %}
-                        <a href="#notifications" id="notification-setting-reset-to-default" class="pure-button button-xsmall" style="right: 20px; top: 20px; position: absolute; background-color: #5f42dd; border-radius: 4px; font-size: 70%; color: #fff">Use system defaults</a>
-
-                        {{ render_common_settings_form(form, emailprefix, settings_application) }}
+                    <div class="field-group">
+                        {{ render_common_settings_form(form, current_base_url, emailprefix) }}
                     </div>
                 </fieldset>
             </div>
 
             <div class="tab-pane-inner" id="filters-and-triggers">
-                    <div class="pure-control-group">
+                <fieldset>
+                        <div class="pure-control-group">
                             <strong>Pro-tips:</strong><br/>
                             <ul>
                                 <li>
@@ -226,50 +122,23 @@ User-Agent: wonderbra 1.0") }}
                                 </li>
                             </ul>
                     </div>
-                    <fieldset>
-                        <div class="pure-control-group">
-                            {{ render_checkbox_field(form.check_unique_lines) }}
-                            <span class="pure-form-message-inline">Good for websites that just move the content around, and you want to know when NEW content is added, compares new lines against all history for this watch.</span>
-                        </div>
-                    </fieldset>
-                    <div class="pure-control-group">
-                        {% set field = render_field(form.include_filters,
-                            rows=5,
-                            placeholder="#example
-xpath://body/div/span[contains(@class, 'example-class')]",
-                            class="m-d")
-                        %}
-                        {{ field }}
-                        {% if '/text()' in  field %}
-                          <span class="pure-form-message-inline"><strong>Note!: //text() function does not work where the &lt;element&gt; contains &lt;![CDATA[]]&gt;</strong></span><br/>
-                        {% endif %}
-                        <span class="pure-form-message-inline">One rule per line, <i>any</i> rules that matches will be used.<br/>
 
+                    <div class="pure-control-group">
+                        {{ render_field(form.css_filter, placeholder=".class-name or #some-id, or other CSS selector rule.",
+                        class="m-d") }}
+                        <span class="pure-form-message-inline">
                     <ul>
                         <li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
-                        <li>JSON - Limit text to this JSON rule, using either <a href="https://pypi.org/project/jsonpath-ng/" target="new">JSONPath</a> or <a href="https://stedolan.github.io/jq/" target="new">jq</a> (if installed).
-                            <ul>
-                                <li>JSONPath: Prefix with <code>json:</code>, use <code>json:$</code> to force re-formatting if required,  <a href="https://jsonpath.com/" target="new">test your JSONPath here</a>.</li>
-                                {% if jq_support %}
-                                <li>jq: Prefix with <code>jq:</code> and <a href="https://jqplay.org/" target="new">test your jq here</a>. Using <a href="https://stedolan.github.io/jq/" target="new">jq</a> allows for complex filtering and processing of JSON data with built-in functions, regex, filtering, and more. See examples and documentation <a href="https://stedolan.github.io/jq/manual/" target="new">here</a>.</li>
-                                {% else %}
-                                <li>jq support not installed</li>
-                                {% endif %}
-                            </ul>
-                        </li>
-                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash,
-                            <ul>
-                                <li>Example:  <code>//*[contains(@class, 'sametext')]</code> or <code>xpath://*[contains(@class, 'sametext')]</code>, <a
+                        <li>JSON - Limit text to this JSON rule, using <a href="https://pypi.org/project/jsonpath-ng/">JSONPath</a>, prefix with <code>"json:"</code>, use <code>json:$</code> to force re-formatting if required,  <a
+                                href="https://jsonpath.com/" target="new">test your JSONPath here</a></li>
+                        <li>XPath - Limit text to this XPath rule, simply start with a forward-slash, example  <code>//*[contains(@class, 'sametext')]</code> or <code>xpath://*[contains(@class, 'sametext')]</code>, <a
                                 href="http://xpather.com/" target="new">test your XPath here</a></li>
-                                <li>Example: Get all titles from an RSS feed <code>//title/text()</code></li>
-                            </ul>
-                            </li>
                     </ul>
-                    Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath{% if jq_support %}, or jq selector{%endif%} rules before filing an issue on GitHub! <a
+                    Please be sure that you thoroughly understand how to write CSS or JSONPath, XPath selector rules before filing an issue on GitHub! <a
                                 href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br/>
                 </span>
                     </div>
-                    <div class="pure-control-group">
+                    <fieldset class="pure-group">
                       {{ render_field(form.subtractive_selectors, rows=5, placeholder="header
 footer
 nav
@@ -280,7 +149,8 @@ nav
                           <li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
                         </ul>
                       </span>
-                    </div>
+                    </fieldset>
+                </fieldset>
                 <fieldset class="pure-group">
                     {{ render_field(form.ignore_text, rows=5, placeholder="Some text to ignore in a line
 /some.regex\d{2}/ for case-INsensitive regex
@@ -288,7 +158,7 @@ nav
                     <span class="pure-form-message-inline">
                         <ul>
                             <li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
-                            <li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
+                            <li>Regular Expression support, wrap the line in forward slash <code>/regex/</code></li>
                             <li>Changing this will affect the comparison checksum which may trigger an alert</li>
                             <li>Use the preview/show current tab to see ignores</li>
                         </ul>
@@ -310,83 +180,16 @@ nav
                         </span>
                     </div>
                 </fieldset>
-                <fieldset>
-                    <div class="pure-control-group">
-                        {{ render_field(form.text_should_not_be_present, rows=5, placeholder="For example: Out of stock
-Sold out
-Not in stock
-Unavailable") }}
-                        <span class="pure-form-message-inline">
-                            <ul>
-                                <li>Block change-detection while this text is on the page, all text and regex are tested <i>case-insensitive</i>, good for waiting for when a product is available again</li>
-                                <li>Block text is processed from the result-text that comes out of any CSS/JSON Filters for this watch</li>
-                                <li>All lines here must not exist (think of each line as "OR")</li>
-                                <li>Note: Wrap in forward slash / to use regex  example: <code>/foo\d/</code></li>
-                            </ul>
-                        </span>
-                    </div>
-                </fieldset>
-                <fieldset>
-                    <div class="pure-control-group">
-                        {{ render_field(form.extract_text, rows=5, placeholder="\d+ online") }}
-                        <span class="pure-form-message-inline">
-                    <ul>
-                        <li>Extracts text in the final output (line by line) after other filters using regular expressions;
-                            <ul>
-                                <li>Regular expression &dash; example <code>/reports.+?2022/i</code></li>
-                                <li>Use <code>//(?aiLmsux))</code> type flags (more <a href="https://docs.python.org/3/library/re.html#index-15">information here</a>)<br/></li>
-                                <li>Keyword example &dash; example <code>Out of stock</code></li>
-                                <li>Use groups to extract just that text &dash; example <code>/reports.+?(\d+)/i</code> returns a list of years only</li>
-                            </ul>
-                        </li>
-                        <li>One line per regular-expression/ string match</li>
-                    </ul>
-                        </span>
-                    </div>
-                </fieldset>
-            </div>
-
-            <div class="tab-pane-inner visual-selector-ui" id="visualselector">
-                <img class="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}">
-
-                <fieldset>
-                    <div class="pure-control-group">
-                        {% if visualselector_enabled %}
-                            <span class="pure-form-message-inline">
-                                The Visual Selector tool lets you select the <i>text</i> elements that will be used for the change detection &dash; after the <i>Browser Steps</i> has completed.<br/><br/>
-                            </span>
-
-                            <div id="selector-header">
-                                <a id="clear-selector" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Clear selection</a>
-                                <i class="fetching-update-notice" style="font-size: 80%;">One moment, fetching screenshot and element information..</i>
-                            </div>
-                            <div id="selector-wrapper" style="display: none">
-                                <!-- request the screenshot and get the element offset info ready -->
-                                <!-- use img src ready load to know everything is ready to map out -->
-                                <!-- @todo: maybe something interesting like a field to select 'elements that contain text... and their parents n' -->
-                                <img id="selector-background" />
-                                <canvas id="selector-canvas"></canvas>
-                            </div>
-                            <div id="selector-current-xpath" style="overflow-x: hidden"><strong>Currently:</strong>&nbsp;<span class="text">Loading...</span></div>
-                        {% else %}
-                            <span class="pure-form-message-inline">
-                                <p>Sorry, this functionality only works with Playwright/Chrome enabled watches.</p>
-                                <p>Enable the Playwright Chrome fetcher, or alternatively try our <a href="https://lemonade.changedetection.io/start">very affordable subscription based service</a>.</p>
-                                <p>This is because Selenium/WebDriver can not extract full page screenshots reliably.</p>
-                            </span>
-                        {% endif %}
-                    </div>
-                </fieldset>
             </div>
 
             <div id="actions">
                 <div class="pure-control-group">
-                    {{ render_button(form.save_button) }}
-                    <a href="{{url_for('form_delete', uuid=uuid)}}"
+
+                      {{ render_button(form.save_button) }} {{ render_button(form.save_and_preview_button) }}
+
+                    <a href="{{url_for('api_delete', uuid=uuid)}}"
                        class="pure-button button-small button-error ">Delete</a>
-                    <a href="{{url_for('clear_watch_history', uuid=uuid)}}"
-                       class="pure-button button-small button-error ">Clear History</a>
-                    <a href="{{url_for('form_clone', uuid=uuid)}}"
+                    <a href="{{url_for('api_clone', uuid=uuid)}}"
                        class="pure-button button-small ">Create Copy</a>
                 </div>
             </div>

changedetectionio/templates/import.html

@@ -5,7 +5,7 @@
 
     <div class="tabs collapsable">
         <ul>
-            <li class="tab" id=""><a href="#url-list">URL List</a></li>
+            <li class="tab" id="default-tab"><a href="#url-list">URL List</a></li>
             <li class="tab"><a href="#distill-io">Distill.io</a></li>
         </ul>
     </div>