Maybe this solves cryptography <-> rustc

* improving unique key fix

* also bump timestamp along 1 sec

.github/workflows/test-only.yml

@@ -4,17 +4,10 @@ name: ChangeDetection.io App Test
 on: [push, pull_request]
 
 jobs:
-  test-application:
+  lint-code:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-
-      # Mainly just for link/flake8
-      - name: Set up Python 3.11
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.11'
-
       - name: Lint with flake8
         run: |
           pip3 install flake8
@@ -23,202 +16,24 @@ jobs:
           # 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
-        run: |
-          
-          docker network create changedet-network
-          
-          # Selenium
-          docker run --network changedet-network -d --hostname selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome:4
-          
-          # SocketPuppetBrowser + Extra for custom browser test
-          docker run --network changedet-network -d -e "LOG_LEVEL=TRACE" --cap-add=SYS_ADMIN --name sockpuppetbrowser --hostname sockpuppetbrowser --rm -p 3000:3000 dgtlmoon/sockpuppetbrowser:latest                    
-          docker run --network changedet-network -d -e "LOG_LEVEL=TRACE" --cap-add=SYS_ADMIN --name sockpuppetbrowser-custom-url --hostname sockpuppetbrowser-custom-url  -p 3001:3000 --rm dgtlmoon/sockpuppetbrowser:latest
-
-      - name: Build changedetection.io container for testing
-        run: |         
-          # Build a changedetection.io container and start testing inside
-          docker build --build-arg LOGGER_LEVEL=TRACE -t test-changedetectionio .
-          # Debug info
-          docker run test-changedetectionio  bash -c 'pip list'
-
-      - name: Spin up ancillary SMTP+Echo message test server
-        run: |
-          # Debug SMTP server/echo message back server
-          docker run --network changedet-network -d -p 11025:11025 -p 11080:11080  --hostname mailserver test-changedetectionio  bash -c 'python changedetectionio/tests/smtp/smtp-test-server.py' 
-
-      - name: Show docker container state and other debug info
-        run: |
-          set -x
-          echo "Running processes in docker..."
-          docker ps
-
-      - name: Test built container with Pytest (generally as requests/plaintext fetching)
-        run: |
-          # Unit tests
-          echo "run test with unittest"
-          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_notification_diff'
-          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_watch_model'
-          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_jinja2_security'
-          
-          # All tests
-          echo "run test with pytest"
-          # The default pytest logger_level is TRACE
-          # To change logger_level for pytest(test/conftest.py),
-          # append the docker option. e.g. '-e LOGGER_LEVEL=DEBUG'
-          docker run --name test-cdio-basic-tests --network changedet-network  test-changedetectionio  bash -c 'cd changedetectionio && ./run_basic_tests.sh'
-
-# PLAYWRIGHT/NODE-> CDP
-      - name: Playwright and SocketPuppetBrowser - Specific tests in built container
-        run: |
-          # Playwright via Sockpuppetbrowser fetch
-          # tests/visualselector/test_fetch_data.py will do browser steps  
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_content.py'
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/test_errorhandling.py'
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/visualselector/test_fetch_data.py'
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_custom_js_before_content.py'
+  test-application-3-10:
+    needs: lint-code
+    uses: ./.github/workflows/test-stack-reusable-workflow.yml
+    with:
+      python-version: '3.10'
 
 
-      - name: Playwright and SocketPuppetBrowser - Headers and requests
-        run: |       
-          # Settings headers playwright tests - Call back in from Sockpuppetbrowser, check headers
-          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000?dumpio=true" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
+  test-application-3-11:
+    needs: lint-code
+    uses: ./.github/workflows/test-stack-reusable-workflow.yml
+    with:
+      python-version: '3.11'
+      skip-pypuppeteer: true
 
-      - name: Playwright and SocketPuppetBrowser - Restock detection
-        run: |                            
-          # restock detection via playwright - added name=changedet here so that playwright and sockpuppetbrowser can connect to it
-          docker run --rm --name "changedet" -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-port=5004 --live-server-host=0.0.0.0 tests/restock/test_restock.py'
+  test-application-3-12:
+    needs: lint-code
+    uses: ./.github/workflows/test-stack-reusable-workflow.yml
+    with:
+      python-version: '3.12'
+      skip-pypuppeteer: true
 
-# STRAIGHT TO CDP
-      - name: Pyppeteer and SocketPuppetBrowser - Specific tests in built container
-        run: |
-          # Playwright via Sockpuppetbrowser fetch 
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_content.py'
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/test_errorhandling.py'
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/visualselector/test_fetch_data.py'
-          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_custom_js_before_content.py'
-
-      - name: Pyppeteer and SocketPuppetBrowser - Headers and requests checks
-        run: |       
-          # Settings headers playwright tests - Call back in from Sockpuppetbrowser, check headers
-          docker run --name "changedet" --hostname changedet --rm  -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000?dumpio=true" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
-
-      - name: Pyppeteer and SocketPuppetBrowser - Restock detection
-        run: |                            
-          # restock detection via playwright - added name=changedet here so that playwright and sockpuppetbrowser can connect to it
-          docker run --rm --name "changedet" -e "FLASK_SERVER_NAME=changedet"  -e "FAST_PUPPETEER_CHROME_FETCHER=True"  -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-port=5004 --live-server-host=0.0.0.0 tests/restock/test_restock.py'
-
-# SELENIUM
-      - name: Specific tests in built container for Selenium
-        run: |
-          # Selenium fetch
-          docker run --rm -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'
-
-      - name: Specific tests in built container for headers and requests checks with Selenium
-        run: |
-          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "WEBDRIVER_URL=http://selenium:4444/wd/hub" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
-
-# OTHER STUFF
-      - name: Test SMTP notification mime types
-        run: |
-          # SMTP content types - needs the 'Debug SMTP server/echo message back server' container from above
-          docker run --rm  --network changedet-network test-changedetectionio bash -c 'cd changedetectionio;pytest tests/smtp/test_notification_smtp.py'
-
-      # @todo Add a test via playwright/puppeteer
-      # squid with auth is tested in run_proxy_tests.sh -> tests/proxy_list/test_select_custom_proxy.py
-      - name: Test proxy squid style interaction
-        run: |
-          cd changedetectionio
-          ./run_proxy_tests.sh
-          cd ..
-
-      - name: Test proxy SOCKS5 style interaction
-        run: |
-          cd changedetectionio
-          ./run_socks_proxy_tests.sh
-          cd ..
-
-      - name: Test custom browser URL
-        run: |
-          cd changedetectionio
-          ./run_custom_browser_url_tests.sh
-          cd ..
-
-      - name: Test changedetection.io container starts+runs basically without error
-        run: |
-          docker run --name test-changedetectionio -p 5556:5000  -d test-changedetectionio
-          sleep 3
-          # Should return 0 (no error) when grep finds it
-          curl --retry-connrefused --retry 6  -s http://localhost:5556 |grep -q checkbox-uuid
-          
-          # and IPv6
-          curl --retry-connrefused --retry 6  -s -g -6 "http://[::1]:5556"|grep -q checkbox-uuid
-
-          # Check whether TRACE log is enabled.
-          # Also, check whether TRACE is came from STDERR
-          docker logs test-changedetectionio 2>&1 1>/dev/null | grep 'TRACE log is enabled' || exit 1
-          # Check whether DEBUG is came from STDOUT
-          docker logs test-changedetectionio 2>/dev/null | grep 'DEBUG' || exit 1
-
-          docker kill test-changedetectionio
-
-      - name: Test changedetection.io SIGTERM and SIGINT signal shutdown
-        run: |
-          
-          echo SIGINT Shutdown request test
-          docker run --name sig-test -d test-changedetectionio
-          sleep 3
-          echo ">>> Sending SIGINT to sig-test container"
-          docker kill --signal=SIGINT sig-test
-          sleep 3
-          # invert the check (it should be not 0/not running)
-          docker ps
-          # check signal catch(STDERR) log. Because of
-          # changedetectionio/__init__.py: logger.add(sys.stderr, level=logger_level)
-          docker logs sig-test 2>&1 | grep 'Shutdown: Got Signal - SIGINT' || exit 1
-          test -z "`docker ps|grep sig-test`"
-          if [ $? -ne 0 ]
-          then
-            echo "Looks like container was running when it shouldnt be"
-            docker ps
-            exit 1
-          fi
-          
-          # @todo - scan the container log to see the right "graceful shutdown" text exists 
-          docker rm sig-test
-          
-          echo SIGTERM Shutdown request test
-          docker run --name sig-test -d test-changedetectionio
-          sleep 3
-          echo ">>> Sending SIGTERM to sig-test container"
-          docker kill --signal=SIGTERM sig-test
-          sleep 3
-          # invert the check (it should be not 0/not running)
-          docker ps
-          # check signal catch(STDERR) log. Because of
-          # changedetectionio/__init__.py: logger.add(sys.stderr, level=logger_level)
-          docker logs sig-test 2>&1 | grep 'Shutdown: Got Signal - SIGTERM' || exit 1
-          test -z "`docker ps|grep sig-test`"
-          if [ $? -ne 0 ]
-          then
-            echo "Looks like container was running when it shouldnt be"
-            docker ps
-            exit 1
-          fi
-          
-          # @todo - scan the container log to see the right "graceful shutdown" text exists           
-          docker rm sig-test
-
-      - name: Dump container log
-        if: always()
-        run: |
-          mkdir output-logs
-          docker logs test-cdio-basic-tests > output-logs/test-cdio-basic-tests-stdout.txt
-          docker logs test-cdio-basic-tests 2> output-logs/test-cdio-basic-tests-stderr.txt
-
-      - name: Store container log
-        if: always()
-        uses: actions/upload-artifact@v4
-        with:
-          name: test-cdio-basic-tests-output
-          path: output-logs

.github/workflows/test-stack-reusable-workflow.yml

@@ -0,0 +1,239 @@
+name: ChangeDetection.io App Test
+
+on:
+  workflow_call:
+    inputs:
+      python-version:
+        description: 'Python version to use'
+        required: true
+        type: string
+        default: '3.10'
+      skip-pypuppeteer:
+        description: 'Skip PyPuppeteer (not supported in 3.11/3.12)'
+        required: false
+        type: boolean
+        default: false
+
+jobs:
+  test-application:
+    runs-on: ubuntu-latest
+    env:
+      PYTHON_VERSION: ${{ inputs.python-version }}
+    steps:
+      - uses: actions/checkout@v4
+
+      # Mainly just for link/flake8
+      - name: Set up Python ${{ env.PYTHON_VERSION }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+
+      - name: Build changedetection.io container for testing under Python ${{ env.PYTHON_VERSION }}
+        run: |
+          echo "---- Building for Python ${{ env.PYTHON_VERSION }} -----"
+          # Build a changedetection.io container and start testing inside
+          docker build --build-arg PYTHON_VERSION=${{ env.PYTHON_VERSION }} --build-arg LOGGER_LEVEL=TRACE -t test-changedetectionio .
+          # Debug info
+          docker run test-changedetectionio  bash -c 'pip list'         
+
+      - name: We should be Python ${{ env.PYTHON_VERSION }} ...
+        run: |         
+          docker run test-changedetectionio  bash -c 'python3 --version'
+
+      - name: Spin up ancillary testable services
+        run: |
+          
+          docker network create changedet-network
+          
+          # Selenium
+          docker run --network changedet-network -d --hostname selenium  -p 4444:4444 --rm --shm-size="2g"  selenium/standalone-chrome:4
+          
+          # SocketPuppetBrowser + Extra for custom browser test
+          docker run --network changedet-network -d -e "LOG_LEVEL=TRACE" --cap-add=SYS_ADMIN --name sockpuppetbrowser --hostname sockpuppetbrowser --rm -p 3000:3000 dgtlmoon/sockpuppetbrowser:latest                    
+          docker run --network changedet-network -d -e "LOG_LEVEL=TRACE" --cap-add=SYS_ADMIN --name sockpuppetbrowser-custom-url --hostname sockpuppetbrowser-custom-url  -p 3001:3000 --rm dgtlmoon/sockpuppetbrowser:latest
+
+      - name: Spin up ancillary SMTP+Echo message test server
+        run: |
+          # Debug SMTP server/echo message back server
+          docker run --network changedet-network -d -p 11025:11025 -p 11080:11080  --hostname mailserver test-changedetectionio  bash -c 'pip3 install aiosmtpd && python changedetectionio/tests/smtp/smtp-test-server.py'
+          docker ps
+
+      - name: Show docker container state and other debug info
+        run: |
+          set -x
+          echo "Running processes in docker..."
+          docker ps
+
+      - name: Test built container with Pytest (generally as requests/plaintext fetching)
+        run: |
+          # Unit tests
+          echo "run test with unittest"
+          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_notification_diff'
+          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_watch_model'
+          docker run test-changedetectionio  bash -c 'python3 -m unittest changedetectionio.tests.unit.test_jinja2_security'
+          
+          # All tests
+          echo "run test with pytest"
+          # The default pytest logger_level is TRACE
+          # To change logger_level for pytest(test/conftest.py),
+          # append the docker option. e.g. '-e LOGGER_LEVEL=DEBUG'
+          docker run --name test-cdio-basic-tests --network changedet-network  test-changedetectionio  bash -c 'cd changedetectionio && ./run_basic_tests.sh'
+
+# PLAYWRIGHT/NODE-> CDP
+      - name: Playwright and SocketPuppetBrowser - Specific tests in built container
+        run: |
+          # Playwright via Sockpuppetbrowser fetch
+          # tests/visualselector/test_fetch_data.py will do browser steps  
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_content.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/test_errorhandling.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/visualselector/test_fetch_data.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_custom_js_before_content.py'
+
+
+      - name: Playwright and SocketPuppetBrowser - Headers and requests
+        run: |       
+          # Settings headers playwright tests - Call back in from Sockpuppetbrowser, check headers
+          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000?dumpio=true" --network changedet-network test-changedetectionio  bash -c 'find .; cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py; pwd;find .'
+
+      - name: Playwright and SocketPuppetBrowser - Restock detection
+        run: |                            
+          # restock detection via playwright - added name=changedet here so that playwright and sockpuppetbrowser can connect to it
+          docker run --rm --name "changedet" -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-port=5004 --live-server-host=0.0.0.0 tests/restock/test_restock.py'
+
+# STRAIGHT TO CDP
+      - name: Pyppeteer and SocketPuppetBrowser - Specific tests in built container
+        if: ${{ inputs.skip-pypuppeteer == false }}
+        run: |
+          # Playwright via Sockpuppetbrowser fetch 
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_content.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/test_errorhandling.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/visualselector/test_fetch_data.py'
+          docker run --rm -e "FLASK_SERVER_NAME=cdio" -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network --hostname=cdio test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-host=0.0.0.0 --live-server-port=5004 tests/fetchers/test_custom_js_before_content.py'
+
+      - name: Pyppeteer and SocketPuppetBrowser - Headers and requests checks
+        if: ${{ inputs.skip-pypuppeteer == false }}
+        run: |
+          # Settings headers playwright tests - Call back in from Sockpuppetbrowser, check headers
+          docker run --name "changedet" --hostname changedet --rm  -e "FAST_PUPPETEER_CHROME_FETCHER=True" -e "FLASK_SERVER_NAME=changedet" -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000?dumpio=true" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
+
+      - name: Pyppeteer and SocketPuppetBrowser - Restock detection
+        if: ${{ inputs.skip-pypuppeteer == false }}
+        run: |                            
+          # restock detection via playwright - added name=changedet here so that playwright and sockpuppetbrowser can connect to it
+          docker run --rm --name "changedet" -e "FLASK_SERVER_NAME=changedet"  -e "FAST_PUPPETEER_CHROME_FETCHER=True"  -e "PLAYWRIGHT_DRIVER_URL=ws://sockpuppetbrowser:3000" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio;pytest --live-server-port=5004 --live-server-host=0.0.0.0 tests/restock/test_restock.py'
+
+# SELENIUM
+      - name: Specific tests in built container for Selenium
+        run: |
+          # Selenium fetch
+          docker run --rm -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'
+
+      - name: Specific tests in built container for headers and requests checks with Selenium
+        run: |
+          docker run --name "changedet" --hostname changedet --rm -e "FLASK_SERVER_NAME=changedet" -e "WEBDRIVER_URL=http://selenium:4444/wd/hub" --network changedet-network test-changedetectionio  bash -c 'cd changedetectionio; pytest --live-server-host=0.0.0.0  --live-server-port=5004 tests/test_request.py'
+
+# OTHER STUFF
+      - name: Test SMTP notification mime types
+        run: |
+          # SMTP content types - needs the 'Debug SMTP server/echo message back server' container from above
+          # "mailserver" hostname defined above
+          docker run --rm --network changedet-network test-changedetectionio bash -c 'cd changedetectionio;pytest tests/smtp/test_notification_smtp.py'
+
+      # @todo Add a test via playwright/puppeteer
+      # squid with auth is tested in run_proxy_tests.sh -> tests/proxy_list/test_select_custom_proxy.py
+      - name: Test proxy squid style interaction
+        run: |
+          cd changedetectionio
+          ./run_proxy_tests.sh
+          cd ..
+
+      - name: Test proxy SOCKS5 style interaction
+        run: |
+          cd changedetectionio
+          ./run_socks_proxy_tests.sh
+          cd ..
+
+      - name: Test custom browser URL
+        run: |
+          cd changedetectionio
+          ./run_custom_browser_url_tests.sh
+          cd ..
+
+      - name: Test changedetection.io container starts+runs basically without error
+        run: |
+          docker run --name test-changedetectionio -p 5556:5000  -d test-changedetectionio
+          sleep 3
+          # Should return 0 (no error) when grep finds it
+          curl --retry-connrefused --retry 6  -s http://localhost:5556 |grep -q checkbox-uuid
+          
+          # and IPv6
+          curl --retry-connrefused --retry 6  -s -g -6 "http://[::1]:5556"|grep -q checkbox-uuid
+
+          # Check whether TRACE log is enabled.
+          # Also, check whether TRACE is came from STDERR
+          docker logs test-changedetectionio 2>&1 1>/dev/null | grep 'TRACE log is enabled' || exit 1
+          # Check whether DEBUG is came from STDOUT
+          docker logs test-changedetectionio 2>/dev/null | grep 'DEBUG' || exit 1
+
+          docker kill test-changedetectionio
+
+      - name: Test changedetection.io SIGTERM and SIGINT signal shutdown
+        run: |
+          
+          echo SIGINT Shutdown request test
+          docker run --name sig-test -d test-changedetectionio
+          sleep 3
+          echo ">>> Sending SIGINT to sig-test container"
+          docker kill --signal=SIGINT sig-test
+          sleep 3
+          # invert the check (it should be not 0/not running)
+          docker ps
+          # check signal catch(STDERR) log. Because of
+          # changedetectionio/__init__.py: logger.add(sys.stderr, level=logger_level)
+          docker logs sig-test 2>&1 | grep 'Shutdown: Got Signal - SIGINT' || exit 1
+          test -z "`docker ps|grep sig-test`"
+          if [ $? -ne 0 ]
+          then
+            echo "Looks like container was running when it shouldnt be"
+            docker ps
+            exit 1
+          fi
+          
+          # @todo - scan the container log to see the right "graceful shutdown" text exists 
+          docker rm sig-test
+          
+          echo SIGTERM Shutdown request test
+          docker run --name sig-test -d test-changedetectionio
+          sleep 3
+          echo ">>> Sending SIGTERM to sig-test container"
+          docker kill --signal=SIGTERM sig-test
+          sleep 3
+          # invert the check (it should be not 0/not running)
+          docker ps
+          # check signal catch(STDERR) log. Because of
+          # changedetectionio/__init__.py: logger.add(sys.stderr, level=logger_level)
+          docker logs sig-test 2>&1 | grep 'Shutdown: Got Signal - SIGTERM' || exit 1
+          test -z "`docker ps|grep sig-test`"
+          if [ $? -ne 0 ]
+          then
+            echo "Looks like container was running when it shouldnt be"
+            docker ps
+            exit 1
+          fi
+          
+          # @todo - scan the container log to see the right "graceful shutdown" text exists           
+          docker rm sig-test
+
+      - name: Dump container log
+        if: always()
+        run: |
+          mkdir output-logs
+          docker logs test-cdio-basic-tests > output-logs/test-cdio-basic-tests-stdout-${{ env.PYTHON_VERSION }}.txt
+          docker logs test-cdio-basic-tests 2> output-logs/test-cdio-basic-tests-stderr-${{ env.PYTHON_VERSION }}.txt
+
+      - name: Store everything including test-datastore
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: test-cdio-basic-tests-output-py${{ env.PYTHON_VERSION }}
+          path: .

Dockerfile

@@ -2,7 +2,10 @@
 
 # @NOTE! I would love to move to 3.11 but it breaks the async handler in changedetectionio/content_fetchers/puppeteer.py
 #        If you know how to fix it, please do! and test it for both 3.10 and 3.11
-FROM python:3.10-slim-bookworm as builder
+
+ARG PYTHON_VERSION=3.10
+
+FROM python:${PYTHON_VERSION}-slim-bookworm as builder
 
 # See `cryptography` pin comment in requirements.txt
 ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
@@ -23,7 +26,8 @@ WORKDIR /install
 
 COPY requirements.txt /requirements.txt
 
-RUN pip install --target=/dependencies -r /requirements.txt
+# --extra-index-url https://www.piwheels.org/simple  is for cryptography module to be prebuilt (or rustc etc needs to be installed)
+RUN pip install --extra-index-url https://www.piwheels.org/simple  --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
@@ -32,7 +36,7 @@ RUN pip install --target=/dependencies playwright~=1.41.2 \
     || 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-bookworm
+FROM python:${PYTHON_VERSION}-slim-bookworm
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
     libxslt1.1 \

changedetectionio/__init__.py

@@ -2,7 +2,7 @@
 
 # Read more https://github.com/dgtlmoon/changedetection.io/wiki
 
-__version__ = '0.45.22'
+__version__ = '0.45.24'
 
 from changedetectionio.strtobool import strtobool
 from json.decoder import JSONDecodeError

changedetectionio/api/api_v1.py

@@ -12,9 +12,10 @@ import copy
 # See docs/README.md for rebuilding the docs/apidoc information
 
 from . import api_schema
+from ..model import watch_base
 
 # Build a JSON Schema atleast partially based on our Watch model
-from changedetectionio.model.Watch import base_config as watch_base_config
+watch_base_config = watch_base()
 schema = api_schema.build_watch_json_schema(watch_base_config)
 
 schema_create_watch = copy.deepcopy(schema)

changedetectionio/blueprint/browser_steps/browser_steps.py

@@ -255,8 +255,8 @@ class browsersteps_live_ui(steppable_browser_interface):
 
     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__, "../../content_fetchers/res/xpath_element_scraper.js").decode('utf-8')
+        import importlib.resources
+        xpath_element_js = importlib.resources.read_text("changedetectionio.content_fetchers.res", "xpath_element_scraper.js")
         now = time.time()
         self.page.wait_for_timeout(1 * 1000)
 
@@ -287,11 +287,9 @@ class browsersteps_live_ui(steppable_browser_interface):
         :param current_include_filters:
         :return:
         """
-
+        import importlib.resources
         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__, "../../content_fetchers/res/xpath_element_scraper.js").decode('utf-8')
+        xpath_element_js = importlib.resources.read_text("changedetectionio.content_fetchers.res", "xpath_element_scraper.js")
         from changedetectionio.content_fetchers import visualselector_xpath_selectors
         xpath_element_js = xpath_element_js.replace('%ELEMENTS%', visualselector_xpath_selectors)
         xpath_data = self.page.evaluate("async () => {" + xpath_element_js + "}")

changedetectionio/blueprint/price_data_follower/__init__.py

@@ -17,6 +17,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q: PriorityQueue
     @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
+        datastore.data['watching'][uuid]['processor'] = 'restock_diff'
         update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
         return redirect(url_for("index"))
 

changedetectionio/blueprint/tags/__init__.py

@@ -103,7 +103,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
         default = datastore.data['settings']['application']['tags'].get(uuid)
 
-        form = forms.watchForm(formdata=request.form if request.method == 'POST' else None,
+        form = forms.processor_text_json_diff_form(formdata=request.form if request.method == 'POST' else None,
                                data=default,
                                )
         form.datastore=datastore # needed?
@@ -126,7 +126,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
         default = datastore.data['settings']['application']['tags'].get(uuid)
 
-        form = forms.watchForm(formdata=request.form if request.method == 'POST' else None,
+        form = forms.processor_text_json_diff_form(formdata=request.form if request.method == 'POST' else None,
                                data=default,
                                )
         # @todo subclass form so validation works

changedetectionio/content_fetchers/base.py

@@ -28,7 +28,7 @@ def manage_user_agent(headers, current_ua=''):
     :return:
     """
     # Ask it what the user agent is, if its obviously ChromeHeadless, switch it to the default
-    ua_in_custom_headers = next((v for k, v in headers.items() if k.lower() == "user-agent"), None)
+    ua_in_custom_headers = headers.get('User-Agent')
     if ua_in_custom_headers:
         return ua_in_custom_headers
 
@@ -64,10 +64,9 @@ class Fetcher():
     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')
-        self.instock_data_js = resource_string(__name__, "res/stock-not-in-stock.js").decode('utf-8')
+        import importlib.resources
+        self.xpath_element_js = importlib.resources.read_text("changedetectionio.content_fetchers.res", 'xpath_element_scraper.js')
+        self.instock_data_js = importlib.resources.read_text("changedetectionio.content_fetchers.res", 'stock-not-in-stock.js')
 
     @abstractmethod
     def get_error(self):

changedetectionio/content_fetchers/puppeteer.py

@@ -9,7 +9,6 @@ from loguru import logger
 from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
 from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, BrowserFetchTimedOut, BrowserConnectError
 
-
 class fetcher(Fetcher):
     fetcher_description = "Puppeteer/direct {}/Javascript".format(
         os.getenv("PLAYWRIGHT_BROWSER_TYPE", 'chromium').capitalize()
@@ -93,15 +92,38 @@ class fetcher(Fetcher):
                                                        ignoreHTTPSErrors=True
                                                        )
         except websockets.exceptions.InvalidStatusCode as e:
-            raise BrowserConnectError(msg=f"Error while trying to connect the browser, Code {e.status_code} (check your access)")
+            raise BrowserConnectError(msg=f"Error while trying to connect the browser, Code {e.status_code} (check your access, whitelist IP, password etc)")
         except websockets.exceptions.InvalidURI:
             raise BrowserConnectError(msg=f"Error connecting to the browser, check your browser connection address (should be ws:// or wss://")
         except Exception as e:
             raise BrowserConnectError(msg=f"Error connecting to the browser {str(e)}")
-        else:
-            self.page = await browser.newPage()
 
-        await self.page.setUserAgent(manage_user_agent(headers=request_headers, current_ua=await self.page.evaluate('navigator.userAgent')))
+        # Better is to launch chrome with the URL as arg
+        # non-headless - newPage() will launch an extra tab/window, .browser should already contain 1 page/tab
+        # headless - ask a new page
+        self.page = (pages := await browser.pages) and len(pages) or await browser.newPage()
+
+        try:
+            from pyppeteerstealth import inject_evasions_into_page
+        except ImportError:
+            logger.debug("pyppeteerstealth module not available, skipping")
+            pass
+        else:
+            # I tried hooking events via self.page.on(Events.Page.DOMContentLoaded, inject_evasions_requiring_obj_to_page)
+            # But I could never get it to fire reliably, so we just inject it straight after
+            await inject_evasions_into_page(self.page)
+
+        # This user agent is similar to what was used when tweaking the evasions in inject_evasions_into_page(..)
+        user_agent = None
+        if request_headers and request_headers.get('User-Agent'):
+            # Request_headers should now be CaaseInsensitiveDict
+            # Remove it so it's not sent again with headers after
+            user_agent = request_headers.pop('User-Agent').strip()
+            await self.page.setUserAgent(user_agent)
+
+        if not user_agent:
+            # Attempt to strip 'HeadlessChrome' etc
+            await self.page.setUserAgent(manage_user_agent(headers=request_headers, current_ua=await self.page.evaluate('navigator.userAgent')))
 
         await self.page.setBypassCSP(True)
         if request_headers:

changedetectionio/content_fetchers/requests.py

@@ -30,11 +30,6 @@ class fetcher(Fetcher):
         if self.browser_steps_get_valid_steps():
             raise BrowserStepsInUnsupportedFetcher(url=url)
 
-        # Make requests use a more modern looking user-agent
-        if not {k.lower(): v for k, v in request_headers.items()}.get('user-agent', None):
-            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 = {}
 
         # Allows override the proxy on a per-request basis

changedetectionio/content_fetchers/res/__init__.py

@@ -0,0 +1 @@
+# resources for browser injection/scraping

changedetectionio/flask_app.py

@@ -5,6 +5,9 @@ import os
 import queue
 import threading
 import time
+
+from jinja2 import Template
+
 from .safe_jinja import render as jinja_render
 from changedetectionio.strtobool import strtobool
 from copy import deepcopy
@@ -124,10 +127,10 @@ def _jinja2_filter_datetime(watch_obj, format="%Y-%m-%d %H:%M:%S"):
 
 @app.template_filter('format_timestamp_timeago')
 def _jinja2_filter_datetimestamp(timestamp, format="%Y-%m-%d %H:%M:%S"):
-    if timestamp == False:
+    if not timestamp:
         return 'Not yet'
 
-    return timeago.format(timestamp, time.time())
+    return timeago.format(int(timestamp), time.time())
 
 
 @app.template_filter('pagination_slice')
@@ -338,8 +341,11 @@ def changedetection_app(config=None, datastore_o=None):
 
         # @todo needs a .itemsWithTag() or something - then we can use that in Jinaj2 and throw this away
         for uuid, watch in datastore.data['watching'].items():
+            # @todo tag notification_muted skip also (improve Watch model)
+            if datastore.data['settings']['application'].get('rss_hide_muted_watches') and watch.get('notification_muted'):
+                continue
             if limit_tag and not limit_tag in watch['tags']:
-                    continue
+                continue
             watch['uuid'] = uuid
             sorted_watches.append(watch)
 
@@ -469,7 +475,7 @@ def changedetection_app(config=None, datastore_o=None):
                                  # Don't link to hosting when we're on the hosting environment
                                  active_tag=active_tag,
                                  active_tag_uuid=active_tag_uuid,
-                                 app_rss_token=datastore.data['settings']['application']['rss_access_token'],
+                                 app_rss_token=datastore.data['settings']['application'].get('rss_access_token'),
                                  datastore=datastore,
                                  errored_count=errored_count,
                                  form=form,
@@ -613,7 +619,6 @@ def changedetection_app(config=None, datastore_o=None):
     @login_optionally_required
     # https://stackoverflow.com/questions/42984453/wtforms-populate-form-with-data-if-data-exists
     # https://wtforms.readthedocs.io/en/3.0.x/forms/#wtforms.form.Form.populate_obj ?
-
     def edit_page(uuid):
         from . import forms
         from .blueprint.browser_steps.browser_steps import browser_step_ui_config
@@ -649,9 +654,17 @@ def changedetection_app(config=None, datastore_o=None):
             # Radio needs '' not None, or incase that the chosen one no longer exists
             if default['proxy'] is None or not any(default['proxy'] in tup for tup in datastore.proxy_list):
                 default['proxy'] = ''
-
         # proxy_override set to the json/text list of the items
-        form = forms.watchForm(formdata=request.form if request.method == 'POST' else None,
+
+        processor = datastore.data['watching'][uuid].get('processor', '')
+        form_class_name = f"processor_{processor}_form"
+        try:
+            form_class = getattr(forms, form_class_name)
+        except AttributeError:
+            flash(f"Cannot load the edit form for processor/plugin '{processor}', plugin missing?", 'error')
+            return redirect(url_for('index'))
+
+        form = form_class(formdata=request.form if request.method == 'POST' else None,
                                data=default
                                )
 
@@ -676,7 +689,10 @@ def changedetection_app(config=None, datastore_o=None):
 
         if request.method == 'POST' and form.validate():
 
-            extra_update_obj = {}
+            extra_update_obj = {
+                'consecutive_filter_failures': 0,
+                'last_error' : False
+            }
 
             if request.args.get('unpause_on_save'):
                 extra_update_obj['paused'] = False
@@ -755,23 +771,38 @@ def changedetection_app(config=None, datastore_o=None):
 
             # Only works reliably with Playwright
             visualselector_enabled = os.getenv('PLAYWRIGHT_DRIVER_URL', False) and is_html_webdriver
+            template_args = {
+                'available_processors': processors.available_processors(),
+                'browser_steps_config': browser_step_ui_config,
+                'emailprefix': os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
+                'extra_title': f" - Edit - {watch.label}",
+                'extra_processor_config': form.extra_tab_content(),
+                'form': form,
+                'has_default_notification_urls': True if len(datastore.data['settings']['application']['notification_urls']) else False,
+                'has_extra_headers_file': len(datastore.get_all_headers_in_textfile_for_watch(uuid=uuid)) > 0,
+                'has_special_tag_options': _watch_has_tag_options_set(watch=watch),
+                'is_html_webdriver': is_html_webdriver,
+                'jq_support': jq_support,
+                'playwright_enabled': os.getenv('PLAYWRIGHT_DRIVER_URL', False),
+                'settings_application': datastore.data['settings']['application'],
+                'using_global_webdriver_wait': not default['webdriver_delay'],
+                'uuid': uuid,
+                'visualselector_enabled': visualselector_enabled,
+                'watch': watch
+            }
+
+            included_content = None
+            if form.extra_form_content():
+                # So that the extra panels can access _helpers.html etc
+                from jinja2 import Environment, FileSystemLoader
+                env = Environment(loader=FileSystemLoader('changedetectionio/templates'))
+                template = env.from_string(form.extra_form_content())
+                included_content = template.render(**template_args)
+
             output = render_template("edit.html",
-                                     available_processors=processors.available_processors(),
-                                     browser_steps_config=browser_step_ui_config,
-                                     emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
-                                     extra_title=f" - Edit - {watch.label}",
-                                     form=form,
-                                     has_default_notification_urls=True if len(datastore.data['settings']['application']['notification_urls']) else False,
-                                     has_extra_headers_file=len(datastore.get_all_headers_in_textfile_for_watch(uuid=uuid)) > 0,
-                                     has_special_tag_options=_watch_has_tag_options_set(watch=watch),
-                                     is_html_webdriver=is_html_webdriver,
-                                     jq_support=jq_support,
-                                     playwright_enabled=os.getenv('PLAYWRIGHT_DRIVER_URL', False),
-                                     settings_application=datastore.data['settings']['application'],
-                                     using_global_webdriver_wait=default['webdriver_delay'] is None,
-                                     uuid=uuid,
-                                     visualselector_enabled=visualselector_enabled,
-                                     watch=watch
+                                     extra_tab_content=form.extra_tab_content() if form.extra_tab_content() else None,
+                                     extra_form_content=included_content,
+                                     **template_args
                                      )
 
         return output

changedetectionio/forms.py

@@ -1,5 +1,8 @@
 import os
 import re
+
+from wtforms.fields.numeric import FloatField
+
 from changedetectionio.strtobool import strtobool
 
 from wtforms import (
@@ -447,7 +450,7 @@ class SingleBrowserStep(Form):
 #    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):
+class processor_text_json_diff_form(commonSettingsForm):
 
     url = fields.URLField('URL', validators=[validateURL()])
     tags = StringTagUUID('Group tag', [validators.Optional()], default='')
@@ -475,9 +478,6 @@ class watchForm(commonSettingsForm):
     filter_text_replaced = BooleanField('Replaced/changed lines', default=True)
     filter_text_removed = BooleanField('Removed lines', default=True)
 
-    # @todo this class could be moved to its own text_json_diff_watchForm and this goes to restock_diff_Watchform perhaps
-    in_stock_only = BooleanField('Only trigger when product goes BACK to in-stock', default=True)
-
     trigger_text = StringListField('Trigger/wait for text', [validators.Optional(), ValidateListRegex()])
     if os.getenv("PLAYWRIGHT_DRIVER_URL"):
         browser_steps = FieldList(FormField(SingleBrowserStep), min_entries=10)
@@ -493,6 +493,12 @@ class watchForm(commonSettingsForm):
     notification_muted = BooleanField('Notifications Muted / Off', default=False)
     notification_screenshot = BooleanField('Attach screenshot to notification (where possible)', default=False)
 
+    def extra_tab_content(self):
+        return None
+
+    def extra_form_content(self):
+        return None
+
     def validate(self, **kwargs):
         if not super().validate():
             return False
@@ -514,6 +520,58 @@ class watchForm(commonSettingsForm):
         return result
 
 
+class processor_restock_diff_form(processor_text_json_diff_form):
+    in_stock_only = BooleanField('Only trigger when product goes BACK to in-stock', default=True)
+    price_change_min = FloatField('Minimum amount to trigger notification', [validators.Optional()], render_kw={"placeholder": "No limit", "size": "10"})
+    price_change_max = FloatField('Maximum amount to trigger notification', [validators.Optional()], render_kw={"placeholder": "No limit", "size": "10"})
+    price_change_threshold_percent = FloatField('Threshold in % for price changes', validators=[
+        validators.Optional(),
+        validators.NumberRange(min=0, max=100, message="Should be between 0 and 100"),
+    ], render_kw={"placeholder": "0%", "size": "5"})
+
+
+    follow_price_changes = BooleanField('Follow price changes', default=False)
+
+    def extra_tab_content(self):
+        return 'Restock & Price Detection'
+
+    def extra_form_content(self):
+        return """
+        {% from '_helpers.html' import render_field, render_checkbox_field, render_button %}
+        <script>        
+            $(document).ready(function () {
+                toggleOpacity('#follow_price_changes', '.price-change-minmax', true);
+            });
+        </script>
+        
+                
+        <fieldset>
+            <div class="pure-control-group">
+                <fieldset class="pure-group">
+                    {{ render_checkbox_field(form.in_stock_only) }}
+                    <span class="pure-form-message-inline">Only trigger notifications when page changes from <strong>out of stock</strong> to <strong>back in stock</strong></span>
+                </fieldset>
+                <fieldset class="pure-group">
+                    {{ render_checkbox_field(form.follow_price_changes) }}
+                    <span class="pure-form-message-inline">Changes in price should trigger a notification</span>
+                    <span class="pure-form-message-inline">When OFF - only care about restock detection</span>
+                </fieldset>
+                <fieldset class="pure-group price-change-minmax">               
+                    {{ render_field(form.price_change_min) }}
+                    <span class="pure-form-message-inline">Minimum amount, only trigger a change when the price is less than this amount.</span>
+                </fieldset>
+                <fieldset class="pure-group price-change-minmax">
+                    {{ render_field(form.price_change_max) }}
+                    <span class="pure-form-message-inline">Maximum amount, only trigger a change when the price is more than this amount.</span>
+                </fieldset>
+                <fieldset class="pure-group price-change-minmax">
+                    {{ render_field(form.price_change_threshold_percent) }}
+                    <span class="pure-form-message-inline">Price must change more than this % to trigger a change.</span><br>
+                    <span class="pure-form-message-inline">For example, If the product is $1,000 USD, <strong>2%</strong> would mean it has to change more than $20 since the last check.</span><br>
+                </fieldset>                
+            </div>
+        </fieldset>"""
+
 class SingleExtraProxy(Form):
 
     # maybe better to set some <script>var..
@@ -526,6 +584,10 @@ class SingleExtraBrowser(Form):
     browser_connection_url = StringField('Browser connection URL', [validators.Optional()], render_kw={"placeholder": "wss://brightdata... wss://oxylabs etc", "size":50})
     # @todo do the validation here instead
 
+class DefaultUAInputForm(Form):
+    html_requests = StringField('Plaintext requests', validators=[validators.Optional()], render_kw={"placeholder": "<default>"})
+    if os.getenv("PLAYWRIGHT_DRIVER_URL") or os.getenv("WEBDRIVER_URL"):
+        html_webdriver = StringField('Chrome requests', validators=[validators.Optional()], render_kw={"placeholder": "<default>"})
 
 # datastore.data['settings']['requests']..
 class globalSettingsRequestForm(Form):
@@ -537,6 +599,8 @@ class globalSettingsRequestForm(Form):
     extra_proxies = FieldList(FormField(SingleExtraProxy), min_entries=5)
     extra_browsers = FieldList(FormField(SingleExtraBrowser), min_entries=5)
 
+    default_ua = FormField(DefaultUAInputForm, label="Default User-Agent overrides")
+
     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'):
@@ -566,6 +630,8 @@ class globalSettingsApplicationForm(commonSettingsForm):
     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()])
+    rss_hide_muted_watches = BooleanField('Hide muted watches from RSS feed', default=True,
+                                      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,

changedetectionio/html_tools.py

@@ -240,7 +240,7 @@ def _get_stripped_text_from_json_match(match):
 # 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):
     stripped_text_from_html = False
-
+# https://github.com/dgtlmoon/changedetection.io/pull/2041#issuecomment-1848397161w
     # Try to parse/filter out the JSON, if we get some parser error, then maybe it's embedded within HTML tags
     try:
         stripped_text_from_html = _parse_json(json.loads(content), json_filter)
@@ -279,17 +279,19 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
                 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)
-                    # @type could also be a list (Product, SubType)
+                    # @type could also be a list although non-standard ("@type": ["Product", "SubType"],)
                     # LD_JSON auto-extract also requires some content PLUS the ldjson to be present
                     # 1833 - could be either str or dict, should not be anything else
-                    if json_data.get('@type') and stripped_text_from_html:
-                        try:
-                            if json_data.get('@type') == str or json_data.get('@type') == dict:
-                                types = [json_data.get('@type')] if isinstance(json_data.get('@type'), str) else json_data.get('@type')
-                                if ensure_is_ldjson_info_type.lower() in [x.lower().strip() for x in types]:
-                                    break
-                        except:
-                            continue
+
+                    t = json_data.get('@type')
+                    if t and stripped_text_from_html:
+
+                        if isinstance(t, str) and t.lower() == ensure_is_ldjson_info_type.lower():
+                            break
+                        # The non-standard part, some have a list
+                        elif isinstance(t, list):
+                            if ensure_is_ldjson_info_type.lower() in [x.lower().strip() for x in t]:
+                                break
 
             elif stripped_text_from_html:
                 break

changedetectionio/model/App.py

@@ -5,7 +5,9 @@ from changedetectionio.notification import (
     default_notification_title,
 )
 
+# Equal to or greater than this number of FilterNotFoundInResponse exceptions will trigger a filter-not-found notification
 _FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT = 6
+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'
 
 class model(dict):
     base_config = {
@@ -22,6 +24,10 @@ class model(dict):
                     '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
+                    'default_ua': {
+                        'html_requests': getenv("DEFAULT_SETTINGS_HEADERS_USERAGENT", DEFAULT_SETTINGS_HEADERS_USERAGENT),
+                        'html_webdriver': None,
+                    }
                 },
                 'application': {
                     # Custom notification content
@@ -41,6 +47,8 @@ class model(dict):
                     'pager_size': 50,
                     'password': False,
                     'render_anchor_tag_content': False,
+                    'rss_access_token': None,
+                    'rss_hide_muted_watches': True,
                     'schema_version' : 0,
                     'shared_diff_access': False,
                     'webdriver_delay': None , # Extra delay in seconds before extracting text

changedetectionio/model/Tag.py

@@ -1,19 +1,14 @@
-from .Watch import base_config
-import uuid
 
-class model(dict):
+from changedetectionio.model import watch_base
+
+class model(watch_base):
 
     def __init__(self, *arg, **kw):
 
-        self.update(base_config)
-
-        self['uuid'] = str(uuid.uuid4())
+        super(model, self).__init__(*arg, **kw)
 
         if kw.get('default'):
             self.update(kw['default'])
             del kw['default']
 
 
-        # Goes at the end so we update the default object with the initialiser
-        super(model, self).__init__(*arg, **kw)
-

changedetectionio/model/Watch.py

@@ -1,6 +1,6 @@
 from changedetectionio.strtobool import strtobool
 from changedetectionio.safe_jinja import render as jinja_render
-
+from . import watch_base
 import os
 import re
 import time
@@ -15,69 +15,6 @@ SAFE_PROTOCOL_REGEX='^(http|https|ftp|file):'
 minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 3))
 mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
 
-from changedetectionio.notification import (
-    default_notification_format_for_watch
-)
-
-base_config = {
-    'body': None,
-    'browser_steps': [],
-    'browser_steps_last_error_step': None,
-    'check_unique_lines': False,  # On change-detected, compare against all history if its something new
-    'check_count': 0,
-    'date_created': None,
-    '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', # plaintext, playwright etc
-    'fetch_time': 0.0,
-    'processor': 'text_json_diff', # could be restock_diff or others from .processors
-    'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
-    'filter_text_added': True,
-    'filter_text_replaced': True,
-    'filter_text_removed': 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
-    'in_stock' : None,
-    'in_stock_only' : True, # Only trigger change on going to instock from out-of-stock
-    'include_filters': [],
-    'last_checked': 0,
-    'last_error': False,
-    'last_viewed': 0,  # history key value of the last viewed via the [diff] link
-    'method': 'GET',
-    'notification_alert_count': 0,
-    # 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
-    'remote_server_reply': None, # From 'server' reply header
-    'sort_text_alphabetically': False,
-    'subtractive_selectors': [],
-    'tag': '', # Old system of text name for a tag, to be removed
-    'tags': [], # list of UUIDs to App.Tags
-    '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},
-    'time_between_check_use_default': True,
-    '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
@@ -94,20 +31,17 @@ def is_safe_url(test_url):
 
     return True
 
-class model(dict):
+
+class model(watch_base):
     __newest_history_key = None
     __history_n = 0
     jitter_seconds = 0
 
     def __init__(self, *arg, **kw):
-
-        self.update(base_config)
         self.__datastore_path = kw['datastore_path']
 
-        self['uuid'] = str(uuid.uuid4())
-
         del kw['datastore_path']
-
+        super(model, self).__init__(*arg, **kw)
         if kw.get('default'):
             self.update(kw['default'])
             del kw['default']
@@ -115,9 +49,6 @@ class model(dict):
         # Be sure the cached timestamp is ready
         bump = self.history
 
-        # Goes at the end so we update the default object with the initialiser
-        super(model, self).__init__(*arg, **kw)
-
     @property
     def viewed(self):
         # Don't return viewed when last_viewed is 0 and newest_key is 0
@@ -256,6 +187,17 @@ class model(dict):
 
         return has_browser_steps
 
+    @property
+    def has_restock_info(self):
+        # has either price or availability
+        if self.get('restock'):
+            if self['restock'].get('price') != None:
+                return True
+            if self['restock'].get('availability') != None:
+                return True
+
+        return False
+    
     # 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):
@@ -333,7 +275,9 @@ class model(dict):
         # 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)
+            logger.warning(f"Timestamp {timestamp} already exists, waiting 1 seconds so we have a unique key in history.txt")
+            timestamp = str(int(timestamp) + 1)
+            time.sleep(1)
 
         threshold = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD', 1024))
         skip_brotli = strtobool(os.getenv('DISABLE_BROTLI_TEXT_SNAPSHOT', 'False'))

changedetectionio/model/__init__.py

@@ -0,0 +1,80 @@
+import os
+import uuid
+
+from changedetectionio import strtobool
+from changedetectionio.notification import default_notification_format_for_watch
+
+
+class Restock(dict):
+    # @todo some setter to handle weird prices like "00,01" etc?
+    def __init__(self, *args, **kwargs):
+
+        default_values = {'in_stock': None, 'price': None, 'currency': None}
+        default_values.update(dict(*args, **kwargs))
+        super().__init__(default_values.copy())
+
+class watch_base(dict):
+
+    def __init__(self, *arg, **kw):
+        self.update({
+            # Custom notification content
+            # 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.
+            'body': None,
+            'browser_steps': [],
+            'browser_steps_last_error_step': None,
+            'check_count': 0,
+            'check_unique_lines': False,  # On change-detected, compare against all history if its something new
+            'consecutive_filter_failures': 0,  # Every time the CSS/xPath filter cannot be located, reset when all is fine.
+            'date_created': None,
+            'extract_text': [],  # Extract text by regex after filters
+            'extract_title_as_title': False,
+            'fetch_backend': 'system',  # plaintext, playwright etc
+            'fetch_time': 0.0,
+            'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
+            'filter_text_added': True,
+            'filter_text_removed': True,
+            'filter_text_replaced': True,
+            'follow_price_changes': True,
+            'has_ldjson_price_data': None,
+            'headers': {},  # Extra headers to send
+            'ignore_text': [],  # List of text to ignore when calculating the comparison checksum
+            'in_stock': None,
+            'in_stock_only': True,  # Only trigger change on going to instock from out-of-stock
+            'include_filters': [],
+            'last_checked': 0,
+            'last_error': False,
+            'last_viewed': 0,  # history key value of the last viewed via the [diff] link
+            'method': 'GET',
+            'notification_alert_count': 0,
+            'notification_body': None,
+            'notification_format': default_notification_format_for_watch,
+            'notification_muted': False,
+            'notification_screenshot': False,  # Include the latest screenshot if available and supported by the apprise URL
+            'notification_title': None,
+            '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
+            'processor': 'text_json_diff',  # could be restock_diff or others from .processors
+            'price_change_threshold_percent': None,
+            'proxy': None,  # Preferred proxy connection
+            'remote_server_reply': None,  # From 'server' reply header
+            'sort_text_alphabetically': False,
+            'subtractive_selectors': [],
+            'tag': '',  # Old system of text name for a tag, to be removed
+            'tags': [],  # list of UUIDs to App.Tags
+            'text_should_not_be_present': [],  # Text that should not present
+            'time_between_check': {'weeks': None, 'days': None, 'hours': None, 'minutes': None, 'seconds': None},
+            'time_between_check_use_default': True,
+            'title': None,
+            'track_ldjson_price_data': 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
+        })
+
+        super(watch_base, self).__init__(*arg, **kw)

changedetectionio/notification.py

@@ -122,10 +122,6 @@ 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
-    n_body = jinja_render(template_str=n_object.get('notification_body', ''), **notification_parameters)
-    n_title = jinja_render(template_str=n_object.get('notification_title', ''), **notification_parameters)
-
     n_format = valid_notification_formats.get(
         n_object.get('notification_format', default_notification_format),
         valid_notification_formats[default_notification_format],
@@ -151,6 +147,11 @@ def process_notification(n_object, datastore):
 
     with apprise.LogCapture(level=apprise.logging.DEBUG) as logs:
         for url in n_object['notification_urls']:
+
+            # Get the notification body from datastore
+            n_body = jinja_render(template_str=n_object.get('notification_body', ''), **notification_parameters)
+            n_title = jinja_render(template_str=n_object.get('notification_title', ''), **notification_parameters)
+
             url = url.strip()
             if not url:
                 logger.warning(f"Process Notification: skipping empty notification URL.")

changedetectionio/processors/__init__.py

@@ -1,10 +1,10 @@
 from abc import abstractmethod
-import os
-import hashlib
-import re
-from copy import deepcopy
 from changedetectionio.strtobool import strtobool
+from copy import deepcopy
 from loguru import logger
+import hashlib
+import os
+import re
 
 class difference_detection_processor():
 
@@ -21,7 +21,7 @@ class difference_detection_processor():
         self.watch = deepcopy(self.datastore.data['watching'].get(watch_uuid))
 
     def call_browser(self):
-
+        from requests.structures import CaseInsensitiveDict
         # Protect against file:// access
         if re.search(r'^file://', self.watch.get('url', '').strip(), re.IGNORECASE):
             if not strtobool(os.getenv('ALLOW_FILE_URI', 'false')):
@@ -93,7 +93,13 @@ class difference_detection_processor():
             self.fetcher.browser_steps_screenshot_path = os.path.join(self.datastore.datastore_path, self.watch.get('uuid'))
 
         # Tweak the base config with the per-watch ones
-        request_headers = self.watch.get('headers', [])
+        request_headers = CaseInsensitiveDict()
+
+        ua = self.datastore.data['settings']['requests'].get('default_ua')
+        if ua and ua.get(prefer_fetch_backend):
+            request_headers.update({'User-Agent': ua.get(prefer_fetch_backend)})
+
+        request_headers.update(self.watch.get('headers', {}))
         request_headers.update(self.datastore.get_all_base_headers())
         request_headers.update(self.datastore.get_all_headers_in_textfile_for_watch(uuid=self.watch.get('uuid')))
 

changedetectionio/processors/restock_diff.py

@@ -1,25 +1,113 @@
-
 from . import difference_detection_processor
+from ..model import Restock
 from copy import deepcopy
 from loguru import logger
 import hashlib
+import re
 import urllib3
+import time
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
-name = 'Re-stock detection for single product pages'
+name = 'Re-stock & Price detection for single product pages'
 description = 'Detects if the product goes back to in-stock'
 
+
 class UnableToExtractRestockData(Exception):
     def __init__(self, status_code):
         # Set this so we can use it in other parts of the app
         self.status_code = status_code
         return
 
+def _search_prop_by_value(matches, value):
+    for properties in matches:
+        for prop in properties:
+            if value in prop[0]:
+                return prop[1]  # Yield the desired value and exit the function
+
+# should return Restock()
+# add casting?
+def get_itemprop_availability(html_content) -> Restock:
+    """
+    Kind of funny/cool way to find price/availability in one many different possibilities.
+    Use 'extruct' to find any possible RDFa/microdata/json-ld data, make a JSON string from the output then search it.
+    """
+    from jsonpath_ng import parse
+
+    now = time.time()
+    import extruct
+    logger.trace(f"Imported extruct module in {time.time() - now:.3f}s")
+
+    value = {}
+    now = time.time()
+    # Extruct is very slow, I'm wondering if some ML is going to be faster (800ms on my i7), 'rdfa' seems to be the heaviest.
+
+    syntaxes = ['dublincore', 'json-ld', 'microdata', 'microformat', 'opengraph']
+
+    data = extruct.extract(html_content, syntaxes=syntaxes)
+    logger.trace(f"Extruct basic extract of all metadata done in {time.time() - now:.3f}s")
+
+    # First phase, dead simple scanning of anything that looks useful
+    if data:
+        logger.debug(f"Using jsonpath to find price/availability/etc")
+        price_parse = parse('$..(price|Price)')
+        pricecurrency_parse = parse('$..(pricecurrency|currency| priceCurrency )')
+        availability_parse = parse('$..(availability|Availability)')
+
+        price_result = price_parse.find(data)
+        if price_result:
+            value['price'] = price_result[0].value
+
+        pricecurrency_result = pricecurrency_parse.find(data)
+        if pricecurrency_result:
+            value['currency'] = pricecurrency_result[0].value
+
+        availability_result = availability_parse.find(data)
+        if availability_result:
+            value['availability'] = availability_result[0].value
+
+        if value.get('availability'):
+            value['availability'] = re.sub(r'(?i)^(https|http)://schema.org/', '',
+                                           value.get('availability').strip(' "\'').lower()) if value.get('availability') else None
+
+        # Second, go dig OpenGraph which is something that jsonpath_ng cant do because of the tuples and double-dots (:)
+        if not value.get('price') or value.get('availability'):
+            logger.debug(f"Alternatively digging through OpenGraph properties for restock/price info..")
+            jsonpath_expr = parse('$..properties')
+
+            for match in jsonpath_expr.find(data):
+                if not value.get('price'):
+                    value['price'] = _search_prop_by_value([match.value], "price:amount")
+                if not value.get('availability'):
+                    value['availability'] = _search_prop_by_value([match.value], "product:availability")
+                if not value.get('currency'):
+                    value['currency'] = _search_prop_by_value([match.value], "price:currency")
+
+    logger.trace(f"Processed with Extruct in {time.time()-now:.3f}s")
+
+    return Restock(value)
+
+
+def is_between(number, lower=None, upper=None):
+    """
+    Check if a number is between two values.
+
+    Parameters:
+    number (float): The number to check.
+    lower (float or None): The lower bound (inclusive). If None, no lower bound.
+    upper (float or None): The upper bound (inclusive). If None, no upper bound.
+
+    Returns:
+    bool: True if the number is between the lower and upper bounds, False otherwise.
+    """
+    return (lower is None or lower <= number) and (upper is None or number <= upper)
+
+
 class perform_site_check(difference_detection_processor):
     screenshot = None
     xpath_data = None
 
+
     def run_changedetection(self, uuid, skip_when_checksum_same=True):
 
         # DeepCopy so we can be sure we don't accidently change anything by reference
@@ -29,7 +117,7 @@ class perform_site_check(difference_detection_processor):
             raise Exception("Watch no longer exists.")
 
         # Unset any existing notification error
-        update_obj = {'last_notification_error': False, 'last_error': False}
+        update_obj = {'last_notification_error': False, 'last_error': False, 'restock':  None}
 
         self.screenshot = self.fetcher.screenshot
         self.xpath_data = self.fetcher.xpath_data
@@ -38,29 +126,91 @@ class perform_site_check(difference_detection_processor):
         update_obj['content_type'] = self.fetcher.headers.get('Content-Type', '')
         update_obj["last_check_status"] = self.fetcher.get_last_status_code()
 
-        # Main detection method
-        fetched_md5 = None
-        if self.fetcher.instock_data:
-            fetched_md5 = hashlib.md5(self.fetcher.instock_data.encode('utf-8')).hexdigest()
-            # 'Possibly in stock' comes from stock-not-in-stock.js when no string found above the fold.
-            update_obj["in_stock"] = True if self.fetcher.instock_data == 'Possibly in stock' else False
-            logger.debug(f"Watch UUID {uuid} restock check returned '{self.fetcher.instock_data}' from JS scraper.")
-        else:
+        itemprop_availability = get_itemprop_availability(html_content=self.fetcher.content)
+        # Something valid in get_itemprop_availability() by scraping metadata ?
+        if itemprop_availability.get('price') or itemprop_availability.get('availability'):
+            # Store for other usage
+            update_obj['restock'] = itemprop_availability
+
+            if itemprop_availability.get('availability'):
+                # @todo: Configurable?
+                if any(substring.lower() in itemprop_availability['availability'].lower() for substring in [
+                    'instock',
+                    'instoreonly',
+                    'limitedavailability',
+                    'onlineonly',
+                    'presale']
+                       ):
+                    update_obj['restock']['in_stock'] = True
+                else:
+                    update_obj['restock']['in_stock'] = False
+
+            # Used for the change detection, we store the real data separately, in the future this can implement some min,max threshold
+            # @todo if price is None?
+            self.fetcher.instock_data = f"{itemprop_availability.get('availability')} - {itemprop_availability.get('price')}"
+
+        elif self.fetcher.instock_data:
+            # 'Possibly in stock' comes from stock-not-in-stock.js when no string found above in the metadata of the HTML
+            update_obj['restock'] = Restock({'in_stock': True if self.fetcher.instock_data == 'Possibly in stock' else False})
+
+            # @todo scrape price somehow
+            logger.debug(
+                f"Restock - using scraped browserdata - Watch UUID {uuid} restock check returned '{self.fetcher.instock_data}' from JS scraper.")
+
+        if not self.fetcher.instock_data:
             raise UnableToExtractRestockData(status_code=self.fetcher.status_code)
 
+        # Main detection method
+        fetched_md5 = hashlib.md5(self.fetcher.instock_data.encode('utf-8')).hexdigest()
+
         # The main thing that all this at the moment comes down to :)
         changed_detected = False
         logger.debug(f"Watch UUID {uuid} restock check - Previous MD5: {watch.get('previous_md5')}, Fetched MD5 {fetched_md5}")
 
-        if watch.get('previous_md5') and watch.get('previous_md5') != fetched_md5:
+        # out of stock -> back in stock only?
+        if watch.get('restock') and watch['restock'].get('in_stock') != update_obj['restock'].get('in_stock'):
             # Yes if we only care about it going to instock, AND we are in stock
-            if watch.get('in_stock_only') and update_obj["in_stock"]:
+            if watch.get('in_stock_only') and update_obj['restock']['in_stock']:
                 changed_detected = True
 
             if not watch.get('in_stock_only'):
                 # All cases
                 changed_detected = True
 
+        if watch.get('follow_price_changes') and watch.get('restock') and update_obj.get('restock') and update_obj['restock'].get('price'):
+            price = float(update_obj['restock'].get('price'))
+            # Default to current price if no previous price found
+            previous_price = float(watch['restock'].get('price', price))
+
+            # It was different, but negate it further down
+            if price != previous_price:
+                changed_detected = True
+
+            # Minimum/maximum price limit
+            if update_obj.get('restock') and update_obj['restock'].get('price'):
+                logger.debug(
+                    f"{uuid} - Change was detected, 'price_change_max' is '{watch.get('price_change_max', '')}' 'price_change_min' is '{watch.get('price_change_min', '')}', price from website is '{update_obj['restock'].get('price', '')}'.")
+                if update_obj['restock'].get('price'):
+                    min_limit = float(watch.get('price_change_min')) if watch.get('price_change_min') else None
+                    max_limit = float(watch.get('price_change_max')) if watch.get('price_change_max') else None
+
+                    price = float(update_obj['restock'].get('price'))
+                    logger.debug(f"{uuid} after float conversion - Min limit: '{min_limit}' Max limit: '{max_limit}' Price: '{price}'")
+                    if min_limit or max_limit:
+                        if is_between(number=price, lower=min_limit, upper=max_limit):
+                            if changed_detected:
+                                logger.debug(f"{uuid} Override change-detected to FALSE because price was inside threshold")
+                                changed_detected = False
+
+                    if changed_detected and watch.get('price_change_threshold_percent'):
+                        pc = float(watch.get('price_change_threshold_percent'))
+                        change = abs((price - previous_price) / previous_price * 100)
+                        if change and change <= pc:
+                            logger.debug(f"{uuid} Override change-detected to FALSE because % threshold ({pc}%) was {change:.3f}%")
+                            changed_detected = False
+                        else:
+                            logger.debug(f"{uuid} Price change was {change:.3f}% , (threshold {pc}%)")
+
         # Always record the new checksum
         update_obj["previous_md5"] = fetched_md5
         return changed_detected, update_obj, self.fetcher.instock_data.encode('utf-8').strip()

changedetectionio/static/js/preview.js

@@ -40,9 +40,13 @@ if (selectElement) {
     if (selectedOption) {
         if (selectedOption.previousElementSibling) {
             document.getElementById('btn-previous').href = "?version=" + selectedOption.previousElementSibling.value;
+        } else {
+            document.getElementById('btn-previous').remove()
         }
         if (selectedOption.nextElementSibling) {
             document.getElementById('btn-next').href = "?version=" + selectedOption.nextElementSibling.value;
+        } else {
+            document.getElementById('btn-next').remove()
         }
 
     }

changedetectionio/static/js/watch-settings.js

@@ -1,8 +1,8 @@
-function toggleOpacity(checkboxSelector, fieldSelector) {
+function toggleOpacity(checkboxSelector, fieldSelector, inverted) {
     const checkbox = document.querySelector(checkboxSelector);
     const fields = document.querySelectorAll(fieldSelector);
     function updateOpacity() {
-        const opacityValue = checkbox.checked ? 0.6 : 1;
+        const opacityValue = !checkbox.checked ? (inverted ? 0.6 : 1) : (inverted ? 1 : 0.6);
         fields.forEach(field => {
             field.style.opacity = opacityValue;
         });
@@ -25,6 +25,8 @@ $(document).ready(function () {
         $('#notification-tokens-info').toggle();
     });
 
-    toggleOpacity('#time_between_check_use_default', '#time_between_check');
+    toggleOpacity('#time_between_check_use_default', '#time_between_check', false);
+
+
 });
 

changedetectionio/static/styles/scss/styles.scss

@@ -186,12 +186,17 @@ code {
   }
 }
 
-.watch-tag-list {
-  color: var(--color-white);
+.inline-tag {
   white-space: nowrap;
-  background: var(--color-text-watch-tag-list);
   border-radius: 5px;
   padding: 2px 5px;
+  margin-right: 4px;
+}
+
+.watch-tag-list {
+  color: var(--color-white);
+  background: var(--color-text-watch-tag-list);
+  @extend .inline-tag;
 }
 
 .box {
@@ -243,7 +248,6 @@ body::after {
 body::before {
   // background-image set in base.html so it works with reverse proxies etc
   content: "";
-  background-size: cover
 }
 
 body:after,
@@ -1022,6 +1026,11 @@ ul {
   border-radius: 10px;
   margin-bottom: 1em;
   display: none;
+  button {
+    /* some space if they wrap the page */
+    margin-bottom: 3px;
+    margin-top: 3px;
+  }
 }
 
 .checkbox-uuid {
@@ -1052,9 +1061,8 @@ ul {
 .tracking-ldjson-price-data {
   background-color: var(--color-background-button-green);
   color: #000;
-  padding: 3px;
-  border-radius: 3px;
-  white-space: nowrap;
+  opacity: 0.6;
+  @extend .inline-tag;
 }
 
 .ldjson-price-track-offer {
@@ -1083,6 +1091,9 @@ ul {
     li {
       list-style: none;
       font-size: 0.8rem;
+      > * {
+        display: inline-block;
+      }
     }
   }
 
@@ -1097,9 +1108,12 @@ ul {
     background-color: var(--color-background-button-cancel);
     color: #777;
   }
-  padding: 3px;
-  border-radius: 3px;
-  white-space: nowrap;
+  &.error {
+    background-color: var(--color-background-button-error);
+    color: #fff;
+    opacity: 0.7;
+  }
+  @extend .inline-tag;
 }
 
 #chrome-extension-link {

changedetectionio/static/styles/styles.css

@@ -531,12 +531,15 @@ code {
     content: url(data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAoAAAAKCAYAAACNMs+9AAAAQElEQVR42qXKwQkAIAxDUUdxtO6/RBQkQZvSi8I/pL4BoGw/XPkh4XigPmsUgh0626AjRsgxHTkUThsG2T/sIlzdTsp52kSS1wAAAABJRU5ErkJggg==);
     margin: 0 3px 0 5px; }
 
+.inline-tag, .watch-tag-list, .tracking-ldjson-price-data, .restock-label {
+  white-space: nowrap;
+  border-radius: 5px;
+  padding: 2px 5px;
+  margin-right: 4px; }
+
 .watch-tag-list {
   color: var(--color-white);
-  white-space: nowrap;
-  background: var(--color-text-watch-tag-list);
-  border-radius: 5px;
-  padding: 2px 5px; }
+  background: var(--color-text-watch-tag-list); }
 
 .box {
   max-width: 80%;
@@ -574,8 +577,7 @@ body::after {
   opacity: 0.91; }
 
 body::before {
-  content: "";
-  background-size: cover; }
+  content: ""; }
 
 body:after,
 body:before {
@@ -1128,6 +1130,10 @@ ul {
   border-radius: 10px;
   margin-bottom: 1em;
   display: none; }
+  #checkbox-operations button {
+    /* some space if they wrap the page */
+    margin-bottom: 3px;
+    margin-top: 3px; }
 
 .checkbox-uuid > * {
   vertical-align: middle; }
@@ -1149,9 +1155,7 @@ ul {
 .tracking-ldjson-price-data {
   background-color: var(--color-background-button-green);
   color: #000;
-  padding: 3px;
-  border-radius: 3px;
-  white-space: nowrap; }
+  opacity: 0.6; }
 
 .ldjson-price-track-offer {
   font-weight: bold;
@@ -1173,17 +1177,21 @@ ul {
     #quick-watch-processor-type ul li {
       list-style: none;
       font-size: 0.8rem; }
+      #quick-watch-processor-type ul li > * {
+        display: inline-block; }
 
-.restock-label {
-  padding: 3px;
-  border-radius: 3px;
-  white-space: nowrap; }
-  .restock-label.in-stock {
-    background-color: var(--color-background-button-green);
-    color: #fff; }
-  .restock-label.not-in-stock {
-    background-color: var(--color-background-button-cancel);
-    color: #777; }
+.restock-label.in-stock {
+  background-color: var(--color-background-button-green);
+  color: #fff; }
+
+.restock-label.not-in-stock {
+  background-color: var(--color-background-button-cancel);
+  color: #777; }
+
+.restock-label.error {
+  background-color: var(--color-background-button-error);
+  color: #fff;
+  opacity: 0.7; }
 
 #chrome-extension-link {
   padding: 9px;

changedetectionio/store.py

@@ -124,12 +124,12 @@ class ChangeDetectionStore:
                 self.__data['app_guid'] = str(uuid_builder.uuid4())
 
         # Generate the URL access token for RSS feeds
-        if not 'rss_access_token' in self.__data['settings']['application']:
+        if not self.__data['settings']['application'].get('rss_access_token'):
             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']:
+        if not self.__data['settings']['application'].get('api_access_token'):
             secret = secrets.token_hex(16)
             self.__data['settings']['application']['api_access_token'] = secret
 
@@ -178,7 +178,7 @@ class ChangeDetectionStore:
     @property
     def has_unviewed(self):
         for uuid, watch in self.__data['watching'].items():
-            if watch.viewed == False:
+            if watch.history_n >= 2 and watch.viewed == False:
                 return True
         return False
 
@@ -242,7 +242,7 @@ class ChangeDetectionStore:
     # Remove a watchs data but keep the entry (URL etc)
     def clear_watch_history(self, uuid):
         import pathlib
-
+        from .model import Restock
         self.__data['watching'][uuid].update({
                 'browser_steps_last_error_step' : None,
                 'check_count': 0,
@@ -257,6 +257,7 @@ class ChangeDetectionStore:
                 'previous_md5_before_filters': False,
                 'remote_server_reply': None,
                 'track_ldjson_price_data': None,
+                'restock': Restock()
             })
 
         # JSON Data, Screenshots, Textfiles (history index and snapshots), HTML in the future etc
@@ -554,7 +555,6 @@ class ChangeDetectionStore:
         return os.path.isfile(filepath)
 
     def get_all_base_headers(self):
-        from .model.App import parse_headers_from_text_file
         headers = {}
         # Global app settings
         headers.update(self.data['settings'].get('headers', {}))
@@ -623,7 +623,8 @@ class ChangeDetectionStore:
         # Eventually almost everything todo with a watch will apply as a Tag
         # So we use the same model as a Watch
         with self.lock:
-            new_tag = Watch.model(datastore_path=self.datastore_path, default={
+            from .model import Tag
+            new_tag = Tag.model(datastore_path=self.datastore_path, default={
                 'title': name.strip(),
                 'date_created': int(time.time())
             })
@@ -662,6 +663,12 @@ class ChangeDetectionStore:
         return next((v for v in tags if v.get('title', '').lower() == tag_name.lower()),
                     None)
 
+    def any_watches_have_processor_by_name(self, processor_name):
+        for watch in self.data['watching'].values():
+            if watch.get('processor') == processor_name:
+                return True
+        return False
+
     def get_updates_available(self):
         import inspect
         updates_available = []

changedetectionio/templates/base.html

@@ -6,7 +6,9 @@
     <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)}}" >
+    {% if app_rss_token %}
+      <link rel="alternate" type="application/rss+xml" title="Changedetection.io » Feed{% if active_tag_uuid %}- {{active_tag.title}}{% endif %}" href="{{ url_for('rss', tag=active_tag_uuid , token=app_rss_token)}}" >
+    {% endif %}
     <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')}}?v={{ get_css_version() }}" >
     {% if extra_stylesheets %}
@@ -24,12 +26,6 @@
     <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') }});
-      }
-    </style>
     <script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
   </head>
 
@@ -89,8 +85,8 @@
           <li class="pure-menu-item pure-form" id="search-menu-item">
             <!-- We use GET here so it offers people a chance to set bookmarks etc -->
             <form name="searchForm" action="" method="GET">
-              <input id="search-q" class="" name="q" placeholder="URL or Title {% if active_tag %}in '{{ active_tag }}'{% endif %}" required="" type="text" value="">
-              <input name="tags" type="hidden" value="{% if active_tag %}{{active_tag}}{% endif %}">
+              <input id="search-q" class="" name="q" placeholder="URL or Title {% if active_tag_uuid %}in '{{ active_tag.title }}'{% endif %}" required="" type="text" value="">
+              <input name="tags" type="hidden" value="{% if active_tag_uuid %}{{active_tag_uuid}}{% endif %}">
               <button class="toggle-button " id="toggle-search" type="button" title="Search, or Use Alt+S Key" >
                 {% include "svgs/search-icon.svg" %}
               </button>

changedetectionio/templates/edit.html

@@ -16,7 +16,7 @@
     const email_notification_prefix=JSON.parse('{{ emailprefix|tojson }}');
 {% endif %}
     const notification_base_url="{{url_for('ajax_callback_send_notification_test', watch_uuid=uuid)}}";
-    const playwright_enabled={% if playwright_enabled %} true {% else %} false {% endif %};
+    const playwright_enabled={% if playwright_enabled %}true{% else %}false{% endif %};
     const recheck_proxy_start_url="{{url_for('check_proxies.start_check', uuid=uuid)}}";
     const proxy_recheck_status_url="{{url_for('check_proxies.get_recheck_status', uuid=uuid)}}";
     const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
@@ -41,18 +41,16 @@
         <ul>
             <li class="tab" id=""><a href="#general">General</a></li>
             <li class="tab"><a href="#request">Request</a></li>
+            {% if extra_tab_content %}
+            <li class="tab"><a href="#extras_tab">{{ extra_tab_content }}</a></li>
+            {% endif %}
             {% if playwright_enabled %}
             <li class="tab"><a id="browsersteps-tab" href="#browser-steps">Browser Steps</a></li>
             {% endif %}
-
             {% if watch['processor'] == 'text_json_diff' %}
             <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>
             {% endif %}
-
-            {% if watch['processor'] == 'restock_diff' %}
-            <li class="tab"><a href="#restock">Restock Detection</a></li>
-            {% endif %}
             <li class="tab"><a href="#notifications">Notifications</a></li>
             <li class="tab"><a href="#stats">Stats</a></li>
         </ul>
@@ -72,7 +70,7 @@
                         <span class="pure-form-message-inline">
                         {% if watch['processor'] == 'text_json_diff' %}
                             Current mode: <strong>Webpage Text/HTML, JSON and PDF changes.</strong><br>
-                          <a href="{{url_for('edit_page', uuid=uuid)}}?switch_processor=restock_diff" class="pure-button button-xsmall">Switch to re-stock detection mode.</a>
+                          <a href="{{url_for('edit_page', uuid=uuid)}}?switch_processor=restock_diff" class="pure-button button-xsmall">Switch to re-stock & Price detection mode for single product pages</a>
                         {% else %}
                         Current mode: <strong>Re-stock detection.</strong><br>
                           <a href="{{url_for('edit_page', uuid=uuid)}}?switch_processor=text_json_diff" class="pure-button button-xsmall">Switch to Webpage Text/HTML, JSON and PDF changes mode.</a>
@@ -413,18 +411,12 @@ Unavailable") }}
                 </div>
             </div>
             {% endif %}
-
-            {% if watch['processor'] == 'restock_diff' %}
-            <div class="tab-pane-inner" id="restock">
-                    <fieldset>
-                        <div class="pure-control-group">
-                            {{ render_checkbox_field(form.in_stock_only) }}
-                            <span class="pure-form-message-inline">Only trigger notifications when page changes from <strong>out of stock</strong> to <strong>back in stock</strong></span>
-                        </div>
-                    </fieldset>
+        {# rendered sub Template #}
+        {% if extra_form_content %}
+            <div class="tab-pane-inner" id="extras_tab">
+            {{ extra_form_content|safe }}
             </div>
-            {% endif %}
-
+        {% endif %}
             {% if watch['processor'] == 'text_json_diff' %}
             <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')}}" alt="New beta functionality">
@@ -433,7 +425,8 @@ Unavailable") }}
                     <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, this tool is a helper to manage filters in the  "CSS/JSONPath/JQ/XPath Filters" box of the <a href="#filters-and-triggers">Filters & Triggers</a> tab.
+                                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>
+                                This tool is a helper to manage filters in the  "CSS/JSONPath/JQ/XPath Filters" box of the <a href="#filters-and-triggers">Filters & Triggers</a> tab.
                             </span>
 
                             <div id="selector-header">

changedetectionio/templates/preview.html

@@ -66,7 +66,7 @@
         </div>
 
         <div class="tab-pane-inner" id="text">
-            <div class="snapshot-age">{{ watch.snapshot_text_ctime|format_timestamp_timeago }}</div>
+            <div class="snapshot-age">{{ current_version|format_timestamp_timeago }}</div>
             <span class="ignored">Grey lines are ignored</span> <span class="triggered">Blue lines are triggers</span>
             <span class="tip"><strong>Pro-tip</strong>: Highlight text to add to ignore filters</span>
 

changedetectionio/templates/settings.html

@@ -62,6 +62,9 @@
                         <span class="pure-form-message-inline">Allow access to view watch diff page when password is enabled (Good for sharing the diff page)
                         </span>
                     </div>
+                    <div class="pure-control-group">
+                        {{ render_checkbox_field(form.application.form.rss_hide_muted_watches) }}
+                    </div>
                     <div class="pure-control-group">
                         {{ render_field(form.application.form.pager_size) }}
                         <span class="pure-form-message-inline">Number of items per page in the watch overview list, 0 to disable.</span>
@@ -108,8 +111,6 @@
                         <p>Use the <strong>Basic</strong> method (default) where your watched sites don't need Javascript to render.</p>
                         <p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
                     </span>
-                    <br>
-                    Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using Bright Data and Oxylabs Proxies, find out more here.</a>
                 </div>
                 <fieldset class="pure-group" id="webdriver-override-options" data-visible-for="application-fetch_backend=html_webdriver">
                     <div class="pure-form-message-inline">
@@ -121,6 +122,18 @@
                         {{ render_field(form.application.form.webdriver_delay) }}
                     </div>
                 </fieldset>
+                <div class="pure-control-group inline-radio">
+                    {{ render_field(form.requests.form.default_ua) }}
+                    <span class="pure-form-message-inline">
+                        Applied to all requests.<br><br>
+                        Note: Simply changing the User-Agent often does not defeat anti-robot technologies, it's important to consider <a href="https://changedetection.io/tutorial/what-are-main-types-anti-robot-mechanisms">all of the ways that the browser is detected</a>.
+                    </span>
+                </div>
+                <div class="pure-control-group">
+                                        <br>
+                    Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using Bright Data and Oxylabs Proxies, find out more here.</a>
+
+                </div>
             </div>
 
             <div class="tab-pane-inner" id="filters">
@@ -190,7 +203,7 @@ nav
                         <a id="chrome-extension-link"
                            title="Try our new Chrome Extension!"
                            href="https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop">
-                            <img src="{{ url_for('static_content', group='images', filename='Google-Chrome-icon.png') }}">
+                            <img src="{{ url_for('static_content', group='images', filename='Google-Chrome-icon.png') }}" alt="Chrome">
                             Chrome Webstore
                         </a>
                     </p>

changedetectionio/templates/watch-overview.html

@@ -13,7 +13,7 @@
             <div id="watch-add-wrapper-zone">
 
                     {{ render_nolabel_field(form.url, placeholder="https://...", required=true) }}
-                    {{ render_nolabel_field(form.tags, value=active_tag.title if active_tag else '', placeholder="watch label / tag") }}
+                    {{ render_nolabel_field(form.tags, value=active_tag.title if active_tag_uuid else '', placeholder="watch label / tag") }}
                     {{ render_nolabel_field(form.watch_submit_button, title="Watch this URL!" ) }}
                     {{ render_nolabel_field(form.edit_and_watch_submit_button, title="Edit first then Watch") }}
             </div>
@@ -46,7 +46,7 @@
     {% endif %}
     {% if search_q %}<div id="search-result-info">Searching "<strong><i>{{search_q}}</i></strong>"</div>{% endif %}
     <div>
-        <a href="{{url_for('index')}}" class="pure-button button-tag {{'active' if not active_tag }}">All</a>
+        <a href="{{url_for('index')}}" class="pure-button button-tag {{'active' if not active_tag_uuid }}">All</a>
 
     <!-- tag list -->
     {% for uuid, tag in tags %}
@@ -59,6 +59,11 @@
     {% set sort_order = sort_order or 'asc' %}
     {% set sort_attribute = sort_attribute or 'last_changed'  %}
     {% set pagination_page = request.args.get('page', 0) %}
+    {% set cols_required = 6 %}
+    {% set any_has_restock_price_processor = datastore.any_watches_have_processor_by_name("restock_diff") %}
+    {% if any_has_restock_price_processor %}
+        {% set cols_required = cols_required + 1 %}
+    {% endif %}
 
     <div id="watch-table-wrapper">
 
@@ -67,18 +72,21 @@
             <tr>
                 {% set link_order = "desc" if sort_order  == 'asc' else "asc" %}
                 {% set arrow_span = "" %}
-                <th><input style="vertical-align: middle" type="checkbox" id="check-all" > <a class="{{ 'active '+link_order if sort_attribute == 'date_created' else 'inactive' }}"  href="{{url_for('index', sort='date_created', order=link_order, tag=active_tag)}}"># <span class='arrow {{link_order}}'></span></a></th>
+                <th><input style="vertical-align: middle" type="checkbox" id="check-all" > <a class="{{ 'active '+link_order if sort_attribute == 'date_created' else 'inactive' }}"  href="{{url_for('index', sort='date_created', order=link_order, tag=active_tag_uuid)}}"># <span class='arrow {{link_order}}'></span></a></th>
                 <th></th>
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'label' else 'inactive' }}" href="{{url_for('index', sort='label', order=link_order, tag=active_tag)}}">Website <span class='arrow {{link_order}}'></span></a></th>
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_checked' else 'inactive' }}" href="{{url_for('index', sort='last_checked', order=link_order, tag=active_tag)}}">Last Checked <span class='arrow {{link_order}}'></span></a></th>
-                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_changed' else 'inactive' }}" href="{{url_for('index', sort='last_changed', order=link_order, tag=active_tag)}}">Last Changed <span class='arrow {{link_order}}'></span></a></th>
+                <th><a class="{{ 'active '+link_order if sort_attribute == 'label' else 'inactive' }}" href="{{url_for('index', sort='label', order=link_order, tag=active_tag_uuid)}}">Website <span class='arrow {{link_order}}'></span></a></th>
+             {% if any_has_restock_price_processor %}
+                <th>Restock &amp; Price</th>
+             {% endif %}
+                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_checked' else 'inactive' }}" href="{{url_for('index', sort='last_checked', order=link_order, tag=active_tag_uuid)}}">Last Checked <span class='arrow {{link_order}}'></span></a></th>
+                <th><a class="{{ 'active '+link_order if sort_attribute == 'last_changed' else 'inactive' }}" href="{{url_for('index', sort='last_changed', order=link_order, tag=active_tag_uuid)}}">Last Changed <span class='arrow {{link_order}}'></span></a></th>
                 <th></th>
             </tr>
             </thead>
             <tbody>
             {% if not watches|length %}
             <tr>
-                <td colspan="6">No website watches configured, please add a URL in the box above, or <a href="{{ url_for('import_page')}}" >import a list</a>.</td>
+                <td colspan="{{ cols_required }}" style="text-wrap: wrap;">No website watches configured, please add a URL in the box above, or <a href="{{ url_for('import_page')}}" >import a list</a>.</td>
             </tr>
             {% endif %}
             {% for watch in (watches|sort(attribute=sort_attribute, reverse=sort_order == 'asc'))|pagination_slice(skip=pagination.skip) %}
@@ -91,15 +99,16 @@
                 {% if watch.last_notification_error is defined and watch.last_notification_error != False %}error{% endif %}
                 {% if watch.paused is defined and watch.paused != False %}paused{% endif %}
                 {% if is_unviewed %}unviewed{% endif %}
+                {% if watch.has_restock_info %}has-restock-info {% if watch['restock']['in_stock'] %}in-stock{% else %}not-in-stock{% endif %}{% endif %}
                 {% if watch.uuid in queued_uuids %}queued{% endif %}">
                 <td class="inline checkbox-uuid" ><input name="uuids"  type="checkbox" value="{{ watch.uuid}} " > <span>{{ loop.index+pagination.skip }}</span></td>
                 <td class="inline watch-controls">
                     {% if not watch.paused %}
-                    <a class="state-off" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="Pause checks" title="Pause checks" class="icon icon-pause" ></a>
+                    <a class="state-off" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="Pause checks" title="Pause checks" class="icon icon-pause" ></a>
                     {% else %}
-                    <a class="state-on" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='play.svg')}}" alt="UnPause checks" title="UnPause checks" class="icon icon-unpause" ></a>
+                    <a class="state-on" href="{{url_for('index', op='pause', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='play.svg')}}" alt="UnPause checks" title="UnPause checks" class="icon icon-unpause" ></a>
                     {% endif %}
-                    <a class="link-mute state-{{'on' if watch.notification_muted else 'off'}}" href="{{url_for('index', op='mute', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications" class="icon icon-mute" ></a>
+                    <a class="link-mute state-{{'on' if watch.notification_muted else 'off'}}" href="{{url_for('index', op='mute', uuid=watch.uuid, tag=active_tag_uuid)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications" class="icon icon-mute" ></a>
                 </td>
                 <td class="title-col inline">{{watch.title if watch.title is not none and watch.title|length > 0 else watch.url}}
                     <a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}"></a>
@@ -135,30 +144,40 @@
 
                     {% if watch['processor'] == 'text_json_diff'  %}
                         {% if watch['has_ldjson_price_data'] and not watch['track_ldjson_price_data']  %}
-                        <div class="ldjson-price-track-offer">Embedded price data detected, follow only price data? <a href="{{url_for('price_data_follower.accept', uuid=watch.uuid)}}" class="pure-button button-xsmall">Yes</a> <a href="{{url_for('price_data_follower.reject', uuid=watch.uuid)}}" class="">No</a></div>
+                        <div class="ldjson-price-track-offer">Switch to Restock & Price watch mode? <a href="{{url_for('price_data_follower.accept', uuid=watch.uuid)}}" class="pure-button button-xsmall">Yes</a> <a href="{{url_for('price_data_follower.reject', uuid=watch.uuid)}}" class="">No</a></div>
                         {% endif %}
-                        {% if watch['track_ldjson_price_data'] == 'accepted' %}
+                    {% endif %}
+                    {% if watch['processor'] == 'restock_diff' %}
                         <span class="tracking-ldjson-price-data" title="Automatically following embedded price information"><img src="{{url_for('static_content', group='images', filename='price-tag-icon.svg')}}"  class="status-icon price-follow-tag-icon" > Price</span>
-                        {% endif %}
                     {% endif %}
-
-                    {% if watch['processor'] == 'restock_diff'  %}
-                    <span class="restock-label {{'in-stock' if watch['in_stock'] else 'not-in-stock' }}" title="detecting restock conditions">
-                        <!-- maybe some object watch['processor'][restock_diff] or.. -->
-                        {% if watch['last_checked'] and watch['in_stock'] != None %}
-                            {% if watch['in_stock'] %} In stock {% else %} Not in stock {% endif %}
-                        {% else %}
-                            Not yet checked
-                        {% endif %}
-                    </span>
-                    {% endif %}
-
-
                     {% for watch_tag_uuid, watch_tag in datastore.get_all_tags_for_watch(watch['uuid']).items() %}
                       <span class="watch-tag-list">{{ watch_tag.title }}</span>
                     {% endfor %}
-
                 </td>
+{% if any_has_restock_price_processor %}
+                <td class="restock-and-price">
+                    {% if watch['processor'] == 'restock_diff'  %}
+                        {% if watch.get('restock') and watch['restock']['in_stock'] != None %}
+                            <span class="restock-label {{'in-stock' if watch['restock']['in_stock'] else 'not-in-stock' }}" title="Detecting restock and price">
+                                <!-- maybe some object watch['processor'][restock_diff] or.. -->
+                                 {% if watch['restock']['in_stock'] %} In stock {% else %} Not in stock {% endif %}
+                            </span>
+                        {% endif %}
+
+                        {% if watch.get('restock') and watch['restock']['price'] != None %}
+                            {% if watch['restock']['price'] != None %}
+                                <span class="restock-label price {{'in-stock' if watch['restock']['in_stock'] else 'not-in-stock' }}" title="Price">
+                                {{ watch['restock']['price'] }} {{ watch['restock']['currency'] }}
+                                </span>
+                            {% endif %}
+                        {% elif not watch.has_restock_info %}
+                            <span class="restock-label error">No information</span>
+                        {% endif %}
+
+
+                    {% endif %}
+                </td>
+{% endif %}
                 <td class="last-checked" data-timestamp="{{ watch.last_checked }}">{{watch|format_last_checked_time|safe}}</td>
                 <td class="last-changed" data-timestamp="{{ watch.last_changed }}">{% if watch.history_n >=2 and watch.last_changed >0 %}
                     {{watch.last_changed|format_timestamp_timeago}}
@@ -204,7 +223,7 @@
                 all {% if active_tag_uuid %} in "{{active_tag.title}}"{%endif%}</a>
             </li>
             <li>
-                <a href="{{ url_for('rss', tag=active_tag , token=app_rss_token)}}"><img alt="RSS Feed" id="feed-icon" src="{{url_for('static_content', group='images', filename='Generic_Feed-icon.svg')}}" height="15"></a>
+                <a href="{{ url_for('rss', tag=active_tag_uuid, token=app_rss_token)}}"><img alt="RSS Feed" id="feed-icon" src="{{url_for('static_content', group='images', filename='Generic_Feed-icon.svg')}}" height="15"></a>
             </li>
         </ul>
         {{ pagination.links }}

changedetectionio/tests/smtp/smtp-test-server.py

@@ -1,42 +1,51 @@
 #!/usr/bin/python3
-import smtpd
-import asyncore
+import asyncio
+from aiosmtpd.controller import Controller
+from aiosmtpd.smtp import SMTP
 
 # Accept a SMTP message and offer a way to retrieve the last message via TCP Socket
 
 last_received_message = b"Nothing"
 
 
-class CustomSMTPServer(smtpd.SMTPServer):
-
-    def process_message(self, peer, mailfrom, rcpttos, data, **kwargs):
+class CustomSMTPHandler:
+    async def handle_DATA(self, server, session, envelope):
         global last_received_message
-        last_received_message = data
-        print('Receiving message from:', peer)
-        print('Message addressed from:', mailfrom)
-        print('Message addressed to  :', rcpttos)
-        print('Message length        :', len(data))
-        print(data.decode('utf8'))
-        return
+        last_received_message = envelope.content
+        print('Receiving message from:', session.peer)
+        print('Message addressed from:', envelope.mail_from)
+        print('Message addressed to  :', envelope.rcpt_tos)
+        print('Message length        :', len(envelope.content))
+        print(envelope.content.decode('utf8'))
+        return '250 Message accepted for delivery'
 
 
-# Just print out the last message received on plain TCP socket server
-class EchoServer(asyncore.dispatcher):
-
-    def __init__(self, host, port):
-        asyncore.dispatcher.__init__(self)
-        self.create_socket()
-        self.set_reuse_addr()
-        self.bind((host, port))
-        self.listen(5)
-
-    def handle_accepted(self, sock, addr):
+class EchoServerProtocol(asyncio.Protocol):
+    def connection_made(self, transport):
         global last_received_message
-        print('Incoming connection from %s' % repr(addr))
-        sock.send(last_received_message)
+        self.transport = transport
+        peername = transport.get_extra_info('peername')
+        print('Incoming connection from {}'.format(peername))
+        self.transport.write(last_received_message)
+
         last_received_message = b''
+        self.transport.close()
 
 
-server = CustomSMTPServer(('0.0.0.0', 11025), None)  # SMTP mail goes here
-server2 = EchoServer('0.0.0.0', 11080)  # Echo back last message received
-asyncore.loop()
+async def main():
+    # Start the SMTP server
+    controller = Controller(CustomSMTPHandler(), hostname='0.0.0.0', port=11025)
+    controller.start()
+
+    # Start the TCP Echo server
+    loop = asyncio.get_running_loop()
+    server = await loop.create_server(
+        lambda: EchoServerProtocol(),
+        '0.0.0.0', 11080
+    )
+    async with server:
+        await server.serve_forever()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

changedetectionio/tests/smtp/test_notification_smtp.py

@@ -32,6 +32,8 @@ def get_last_message_from_smtp_server():
     client_socket.connect((smtp_test_server, port))  # connect to the server
 
     data = client_socket.recv(50024).decode()  # receive response
+    logging.info("get_last_message_from_smtp_server..")
+    logging.info(data)
     client_socket.close()  # close the connection
     return data
 
@@ -71,6 +73,8 @@ def test_check_notification_email_formats_default_HTML(client, live_server):
 
     wait_for_all_checks(client)
     set_longer_modified_response()
+    time.sleep(2)
+
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
 
@@ -81,7 +85,7 @@ def test_check_notification_email_formats_default_HTML(client, live_server):
 
     # The email should have two bodies, and the text/html part should be <br>
     assert 'Content-Type: text/plain' in msg
-    assert '(added) So let\'s see what happens.\n' in msg  # The plaintext part with \n
+    assert '(added) So let\'s see what happens.\r\n' in msg  # The plaintext part with \r\n
     assert 'Content-Type: text/html' in msg
     assert '(added) So let\'s see what happens.<br>' in msg  # the html part
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
@@ -135,6 +139,7 @@ def test_check_notification_email_formats_default_Text_override_HTML(client, liv
 
     wait_for_all_checks(client)
     set_longer_modified_response()
+    time.sleep(2)
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
 
@@ -147,7 +152,7 @@ def test_check_notification_email_formats_default_Text_override_HTML(client, liv
     # The email should not have two bodies, should be TEXT only
 
     assert 'Content-Type: text/plain' in msg
-    assert '(added) So let\'s see what happens.\n' in msg  # The plaintext part with \n
+    assert '(added) So let\'s see what happens.\r\n' in msg  # The plaintext part with \r\n
 
     set_original_response()
     # Now override as HTML format
@@ -168,7 +173,7 @@ def test_check_notification_email_formats_default_Text_override_HTML(client, liv
 
     # The email should have two bodies, and the text/html part should be <br>
     assert 'Content-Type: text/plain' in msg
-    assert '(removed) So let\'s see what happens.\n' in msg  # The plaintext part with \n
+    assert '(removed) So let\'s see what happens.\r\n' in msg  # The plaintext part with \n
     assert 'Content-Type: text/html' in msg
     assert '(removed) So let\'s see what happens.<br>' in msg  # the html part
 

changedetectionio/tests/test_auth.py

@@ -2,13 +2,12 @@
 
 import time
 from flask import url_for
-from . util import live_server_setup
+from .util import live_server_setup, wait_for_all_checks
+
 
 def test_basic_auth(client, live_server):
 
     live_server_setup(live_server)
-    # Give the endpoint time to spin up
-    time.sleep(1)
 
     # Add our URL to the import page
     test_url = url_for('test_basicauth_method', _external=True).replace("//","//myuser:mypass@")
@@ -19,8 +18,8 @@ def test_basic_auth(client, live_server):
         follow_redirects=True
     )
     assert b"1 Imported" in res.data
+    wait_for_all_checks(client)
     time.sleep(1)
-
     # Check form validation
     res = client.post(
         url_for("edit_page", uuid="first"),
@@ -29,7 +28,7 @@ def test_basic_auth(client, live_server):
     )
     assert b"Updated watch." in res.data
 
-    time.sleep(1)
+    wait_for_all_checks(client)
     res = client.get(
         url_for("preview_page", uuid="first"),
         follow_redirects=True

changedetectionio/tests/test_automatic_follow_ldjson_price.py

@@ -1,234 +0,0 @@
-#!/usr/bin/python3
-
-import time
-from flask import url_for
-from .util import live_server_setup, extract_UUID_from_client, extract_api_key_from_UI, wait_for_all_checks
-
-
-def set_response_with_ldjson():
-    test_return_data = """<html>
-       <body>
-     Some initial text<br>
-     <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
-     <div class="sametext">Some text thats the same</div>
-     <div class="changetext">Some text that will change</div>
-     <script type="application/ld+json">
-        {
-           "@context":"https://schema.org/",
-           "@type":"Product",
-           "@id":"https://www.some-virtual-phone-shop.com/celular-iphone-14/p",
-           "name":"Celular Iphone 14 Pro Max 256Gb E Sim A16 Bionic",
-           "brand":{
-              "@type":"Brand",
-              "name":"APPLE"
-           },
-           "image":"https://www.some-virtual-phone-shop.com/15509426/image.jpg",
-           "description":"You dont need it",
-           "mpn":"111111",
-           "sku":"22222",
-           "Offers":{
-              "@type":"AggregateOffer",
-              "lowPrice":8097000,
-              "highPrice":8099900,
-              "priceCurrency":"COP",
-              "offers":[
-                 {
-                    "@type":"Offer",
-                    "price":8097000,
-                    "priceCurrency":"COP",
-                    "availability":"http://schema.org/InStock",
-                    "sku":"102375961",
-                    "itemCondition":"http://schema.org/NewCondition",
-                    "seller":{
-                       "@type":"Organization",
-                       "name":"ajax"
-                    }
-                 }
-              ],
-              "offerCount":1
-           }
-        }
-       </script>
-     </body>
-     </html>
-"""
-
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write(test_return_data)
-    return None
-
-def set_response_without_ldjson():
-    test_return_data = """<html>
-       <body>
-     Some initial text<br>
-     <p>Which is across multiple lines</p>
-     <br>
-     So let's see what happens.  <br>
-     <div class="sametext">Some text thats the same</div>
-     <div class="changetext">Some text that will change</div>     
-     </body>
-     </html>
-"""
-
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write(test_return_data)
-    return None
-
-def test_setup(client, live_server):
-    live_server_setup(live_server)
-
-# actually only really used by the distll.io importer, but could be handy too
-def test_check_ldjson_price_autodetect(client, live_server):
-
-    set_response_with_ldjson()
-
-    # Add our URL to the import page
-    test_url = url_for('test_endpoint', _external=True)
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-    assert b"1 Imported" in res.data
-    wait_for_all_checks(client)
-
-    # Should get a notice that it's available
-    res = client.get(url_for("index"))
-    assert b'ldjson-price-track-offer' in res.data
-
-    # Accept it
-    uuid = extract_UUID_from_client(client)
-
-    client.get(url_for('price_data_follower.accept', uuid=uuid, follow_redirects=True))
-    wait_for_all_checks(client)
-
-    # Trigger a check
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    wait_for_all_checks(client)
-    # Offer should be gone
-    res = client.get(url_for("index"))
-    assert b'Embedded price data' not in res.data
-    assert b'tracking-ldjson-price-data' in res.data
-
-    # and last snapshop (via API) should be just the price
-    api_key = extract_api_key_from_UI(client)
-    res = client.get(
-        url_for("watchsinglehistory", uuid=uuid, timestamp='latest'),
-        headers={'x-api-key': api_key},
-    )
-
-    # Should see this (dont know where the whitespace came from)
-    assert b'"highPrice": 8099900' in res.data
-    # And not this cause its not the ld-json
-    assert b"So let's see what happens" not in res.data
-
-    client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-
-    ##########################################################################################
-    # And we shouldnt see the offer
-    set_response_without_ldjson()
-
-    # Add our URL to the import page
-    test_url = url_for('test_endpoint', _external=True)
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-    assert b"1 Imported" in res.data
-    wait_for_all_checks(client)
-    res = client.get(url_for("index"))
-    assert b'ldjson-price-track-offer' not in res.data
-    
-    ##########################################################################################
-    client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-
-
-def _test_runner_check_bad_format_ignored(live_server, client, has_ldjson_price_data):
-
-    test_url = url_for('test_endpoint', _external=True)
-    res = client.post(
-        url_for("import_page"),
-        data={"urls": test_url},
-        follow_redirects=True
-    )
-    assert b"1 Imported" in res.data
-    wait_for_all_checks(client)
-
-    for k,v in client.application.config.get('DATASTORE').data['watching'].items():
-        assert v.get('last_error') == False
-        assert v.get('has_ldjson_price_data') == has_ldjson_price_data
-
-
-    ##########################################################################################
-    client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-
-
-def test_bad_ldjson_is_correctly_ignored(client, live_server):
-    #live_server_setup(live_server)
-    test_return_data = """
-            <html>
-            <head>
-                <script type="application/ld+json">
-                    {
-                        "@context": "http://schema.org",
-                        "@type": ["Product", "SubType"],
-                        "name": "My test product",
-                        "description": "",
-                        "offers": {
-                            "note" : "You can see the case-insensitive OffERS key, it should work",
-                            "@type": "Offer",
-                            "offeredBy": {
-                                "@type": "Organization",
-                                "name":"Person",
-                                "telephone":"+1 999 999 999"
-                            },
-                            "price": "1",
-                            "priceCurrency": "EUR",
-                            "url": "/some/url"
-                        }
-                    }
-                </script>
-            </head>
-            <body>
-            <div class="yes">Some extra stuff</div>
-            </body></html>
-     """
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write(test_return_data)
-
-    _test_runner_check_bad_format_ignored(live_server=live_server, client=client, has_ldjson_price_data=True)
-    test_return_data = """
-            <html>
-            <head>
-                <script type="application/ld+json">
-                    {
-                        "@context": "http://schema.org",
-                        "@type": ["Product", "SubType"],
-                        "name": "My test product",
-                        "description": "",
-                        "BrokenOffers": {
-                            "@type": "Offer",
-                            "offeredBy": {
-                                "@type": "Organization",
-                                "name":"Person",
-                                "telephone":"+1 999 999 999"
-                            },
-                            "price": "1",
-                            "priceCurrency": "EUR",
-                            "url": "/some/url"
-                        }
-                    }
-                </script>
-            </head>
-            <body>
-            <div class="yes">Some extra stuff</div>
-            </body></html>
-     """
-    with open("test-datastore/endpoint-content.txt", "w") as f:
-        f.write(test_return_data)
-
-    _test_runner_check_bad_format_ignored(live_server=live_server, client=client, has_ldjson_price_data=False)
-

changedetectionio/tests/test_backend.py

@@ -62,9 +62,6 @@ def test_check_basic_change_detection_functionality(client, live_server):
     # Make a change
     set_modified_response()
 
-    res = urlopen(url_for('test_endpoint', _external=True))
-    assert b'which has this one new line' in res.read()
-
     # Force recheck
     res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
     assert b'1 watches queued for rechecking.' in res.data
@@ -135,6 +132,9 @@ def test_check_basic_change_detection_functionality(client, live_server):
     # It should have picked up the <title>
     assert b'head title' in res.data
 
+    # Be sure the last_viewed is going to be greater than the last snapshot
+    time.sleep(1)
+
     # hit the mark all viewed link
     res = client.get(url_for("mark_all_viewed"), follow_redirects=True)
 

changedetectionio/tests/test_encoding.py

@@ -3,7 +3,7 @@
 
 import time
 from flask import url_for
-from .util import live_server_setup
+from .util import live_server_setup, wait_for_all_checks
 import pytest
 
 
@@ -27,9 +27,6 @@ def set_html_response():
 def test_check_encoding_detection(client, live_server):
     set_html_response()
 
-    # Give the endpoint time to spin up
-    time.sleep(1)
-
     # Add our URL to the import page
     test_url = url_for('test_endpoint', content_type="text/html", _external=True)
     client.post(
@@ -39,7 +36,7 @@ def test_check_encoding_detection(client, live_server):
     )
 
     # Give the thread time to pick it up
-    time.sleep(2)
+    wait_for_all_checks(client)
 
     res = client.get(
         url_for("preview_page", uuid="first"),
@@ -56,9 +53,6 @@ def test_check_encoding_detection(client, live_server):
 def test_check_encoding_detection_missing_content_type_header(client, live_server):
     set_html_response()
 
-    # Give the endpoint time to spin up
-    time.sleep(1)
-
     # Add our URL to the import page
     test_url = url_for('test_endpoint', _external=True)
     client.post(
@@ -67,8 +61,7 @@ def test_check_encoding_detection_missing_content_type_header(client, live_serve
         follow_redirects=True
     )
 
-    # Give the thread time to pick it up
-    time.sleep(2)
+    wait_for_all_checks(client)
 
     res = client.get(
         url_for("preview_page", uuid="first"),

changedetectionio/tests/test_extract_csv.py

@@ -29,6 +29,7 @@ def test_check_extract_text_from_diff(client, live_server):
     # Load in 5 different numbers/changes
     last_date=""
     for n in range(5):
+        time.sleep(1)
         # Give the thread time to pick it up
         print("Bumping snapshot and checking.. ", n)
         last_date = str(time.time())

changedetectionio/tests/test_filter_failure_notification.py

@@ -21,10 +21,11 @@ def set_response_with_filter():
         f.write(test_return_data)
     return None
 
-def run_filter_test(client, content_filter):
+def run_filter_test(client, live_server, content_filter):
+
+    # Response WITHOUT the filter ID element
+    set_original_response()
 
-    # Give the endpoint time to spin up
-    time.sleep(1)
     # cleanup for the next
     client.get(
         url_for("form_delete", uuid="all"),
@@ -79,6 +80,7 @@ def run_filter_test(client, content_filter):
         "include_filters": content_filter,
         "fetch_backend": "html_requests"})
 
+    # A POST here will also reset the filter failure counter (filter_failure_notification_threshold_attempts)
     res = client.post(
         url_for("edit_page", uuid="first"),
         data=notification_form_data,
@@ -91,20 +93,21 @@ def run_filter_test(client, content_filter):
     # Now the notification should not exist, because we didnt reach the threshold
     assert not os.path.isfile("test-datastore/notification.txt")
 
-    # -2 because we would have checked twice above (on adding and on edit)
+    # recheck it up to just before the threshold, including the fact that in the previous POST it would have rechecked (and incremented)
     for i in range(0, App._FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT-2):
-        res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+        client.get(url_for("form_watch_checknow"), follow_redirects=True)
         wait_for_all_checks(client)
-        assert not os.path.isfile("test-datastore/notification.txt"), f"test-datastore/notification.txt should not exist - Attempt {i}"
+        time.sleep(2) # delay for apprise to fire
+        assert not os.path.isfile("test-datastore/notification.txt"), f"test-datastore/notification.txt should not exist - Attempt {i} when threshold is {App._FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT}"
 
     # We should see something in the frontend
+    res = client.get(url_for("index"))
     assert b'Warning, no filters were found' in res.data
 
-    # One more check should trigger it (see -2 above)
-    client.get(url_for("form_watch_checknow"), follow_redirects=True)
-    wait_for_all_checks(client)
+    # One more check should trigger the _FILTER_FAILURE_THRESHOLD_ATTEMPTS_DEFAULT threshold
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
+    time.sleep(2)  # delay for apprise to fire
     # Now it should exist and contain our "filter not found" alert
     assert os.path.isfile("test-datastore/notification.txt")
 
@@ -149,13 +152,9 @@ def test_setup(live_server):
     live_server_setup(live_server)
 
 def test_check_include_filters_failure_notification(client, live_server):
-    set_original_response()
-    wait_for_all_checks(client)
-    run_filter_test(client, '#nope-doesnt-exist')
+    run_filter_test(client, live_server,'#nope-doesnt-exist')
 
 def test_check_xpath_filter_failure_notification(client, live_server):
-    set_original_response()
-    time.sleep(1)
-    run_filter_test(client, '//*[@id="nope-doesnt-exist"]')
+    run_filter_test(client, live_server, '//*[@id="nope-doesnt-exist"]')
 
 # Test that notification is never sent

changedetectionio/tests/test_jsonpath_jq_selector.py

@@ -479,8 +479,9 @@ def test_correct_header_detect(client, live_server):
         url_for("preview_page", uuid="first"),
         follow_redirects=True
     )
-    assert b'"world":' in res.data
-    assert res.data.count(b'{') >= 2
+
+    assert b'"hello": 123,' in res.data
+    assert b'&#34;world&#34;: 123</div>' in res.data
 
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data

changedetectionio/tests/test_notification_errors.py

@@ -9,9 +9,6 @@ def test_check_notification_error_handling(client, live_server):
     live_server_setup(live_server)
     set_original_response()
 
-    # Give the endpoint time to spin up
-    time.sleep(1)
-
     # Set a URL and fetch it, then set a notification URL which is going to give errors
     test_url = url_for('test_endpoint', _external=True)
     res = client.post(

changedetectionio/tests/test_request.py

@@ -10,6 +10,7 @@ def test_setup(live_server):
 # Hard to just add more live server URLs when one test is already running (I think)
 # So we add our test here (was in a different file)
 def test_headers_in_request(client, live_server):
+
     #ve_server_setup(live_server)
     # Add our URL to the import page
     test_url = url_for('test_headers', _external=True)
@@ -253,15 +254,99 @@ def test_method_in_request(client, live_server):
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
     assert b'Deleted' in res.data
 
+# Re #2408 - user-agent override test, also should handle case-insensitive header deduplication
+def test_ua_global_override(client, live_server):
+    # live_server_setup(live_server)
+    test_url = url_for('test_headers', _external=True)
+
+    res = client.post(
+        url_for("settings_page"),
+        data={
+            "application-fetch_backend": "html_requests",
+            "application-minutes_between_check": 180,
+            "requests-default_ua-html_requests": "html-requests-user-agent"
+        },
+        follow_redirects=True
+    )
+    assert b'Settings updated' in res.data
+
+    res = client.post(
+        url_for("import_page"),
+        data={"urls": test_url},
+        follow_redirects=True
+    )
+    assert b"1 Imported" in res.data
+
+    wait_for_all_checks(client)
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+
+    assert b"html-requests-user-agent" in res.data
+    # default user-agent should have shown by now
+    # now add a custom one in the headers
+
+
+    # Add some headers to a request
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={
+            "url": test_url,
+            "tags": "testtag",
+            "fetch_backend": 'html_requests',
+            # Important - also test case-insensitive
+            "headers": "User-AGent: agent-from-watch"},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    wait_for_all_checks(client)
+    res = client.get(
+        url_for("preview_page", uuid="first"),
+        follow_redirects=True
+    )
+    assert b"agent-from-watch" in res.data
+    assert b"html-requests-user-agent" not in res.data
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
 def test_headers_textfile_in_request(client, live_server):
     #live_server_setup(live_server)
     # Add our URL to the import page
+
+    webdriver_ua = "Hello fancy webdriver UA 1.0"
+    requests_ua = "Hello basic requests UA 1.1"
+
     test_url = url_for('test_headers', _external=True)
     if os.getenv('PLAYWRIGHT_DRIVER_URL'):
         # Because its no longer calling back to localhost but from the browser container, set in test-only.yml
         test_url = test_url.replace('localhost', 'cdio')
 
-    print ("TEST URL IS ",test_url)
+    form_data = {
+        "application-fetch_backend": "html_requests",
+        "application-minutes_between_check": 180,
+        "requests-default_ua-html_requests": requests_ua
+    }
+
+    if os.getenv('PLAYWRIGHT_DRIVER_URL'):
+        form_data["requests-default_ua-html_webdriver"] = webdriver_ua
+
+    res = client.post(
+        url_for("settings_page"),
+        data=form_data,
+        follow_redirects=True
+    )
+    assert b'Settings updated' in res.data
+
+    res = client.get(url_for("settings_page"))
+
+    # Only when some kind of real browser is setup
+    if os.getenv('PLAYWRIGHT_DRIVER_URL'):
+        assert b'requests-default_ua-html_webdriver' in res.data
+
+    # Field should always be there
+    assert b"requests-default_ua-html_requests" in res.data
+
     # Add the test URL twice, we will check
     res = client.post(
         url_for("import_page"),
@@ -272,15 +357,14 @@ def test_headers_textfile_in_request(client, live_server):
 
     wait_for_all_checks(client)
 
-
     # Add some headers to a request
     res = client.post(
         url_for("edit_page", uuid="first"),
         data={
-              "url": test_url,
-              "tags": "testtag",
-              "fetch_backend": 'html_webdriver' if os.getenv('PLAYWRIGHT_DRIVER_URL') else 'html_requests',
-              "headers": "xxx:ooo\ncool:yeah\r\n"},
+            "url": test_url,
+            "tags": "testtag",
+            "fetch_backend": 'html_webdriver' if os.getenv('PLAYWRIGHT_DRIVER_URL') else 'html_requests',
+            "headers": "xxx:ooo\ncool:yeah\r\n"},
         follow_redirects=True
     )
     assert b"Updated watch." in res.data
@@ -292,21 +376,27 @@ def test_headers_textfile_in_request(client, live_server):
     with open('test-datastore/headers.txt', 'w') as f:
         f.write("global-header: nice\r\nnext-global-header: nice")
 
-    with open('test-datastore/'+extract_UUID_from_client(client)+'/headers.txt', 'w') as f:
+    with open('test-datastore/' + extract_UUID_from_client(client) + '/headers.txt', 'w') as f:
         f.write("watch-header: nice")
 
+    wait_for_all_checks(client)
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
 
-    # Give the thread time to pick it up
+    # Give the thread time to pick it up, this actually is not super reliable and pytest can terminate before the check is ran
     wait_for_all_checks(client)
 
+    # WARNING - pytest and 'wait_for_all_checks' shuts down before it has actually stopped processing when using pyppeteer fetcher
+    # so adding more time here
+    if os.getenv('FAST_PUPPETEER_CHROME_FETCHER'):
+        time.sleep(6)
+
     res = client.get(url_for("edit_page", uuid="first"))
     assert b"Extra headers file found and will be added to this watch" in res.data
 
     # Not needed anymore
     os.unlink('test-datastore/headers.txt')
     os.unlink('test-datastore/headers-testtag.txt')
-    os.unlink('test-datastore/'+extract_UUID_from_client(client)+'/headers.txt')
+
     # The service should echo back the request verb
     res = client.get(
         url_for("preview_page", uuid="first"),
@@ -319,7 +409,12 @@ def test_headers_textfile_in_request(client, live_server):
     assert b"Watch-Header:nice" in res.data
     assert b"Tag-Header:test" in res.data
 
+    # Check the custom UA from system settings page made it through
+    if os.getenv('PLAYWRIGHT_DRIVER_URL'):
+        assert "User-Agent:".encode('utf-8') + webdriver_ua.encode('utf-8') in res.data
+    else:
+        assert "User-Agent:".encode('utf-8') + requests_ua.encode('utf-8') in res.data
 
-    #unlink headers.txt on start/stop
+    # unlink headers.txt on start/stop
     res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
-    assert b'Deleted' in res.data
+    assert b'Deleted' in res.data

changedetectionio/tests/test_restock_itemprop.py

@@ -0,0 +1,258 @@
+#!/usr/bin/python3
+from flask import url_for
+from .util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
+
+instock_props = [
+    # LD+JSON with non-standard list of 'type' https://github.com/dgtlmoon/changedetection.io/issues/1833
+    '<script type=\'application/ld+json\'>{"@context": "http://schema.org","@type": ["Product", "SubType"],"name": "My test product","description":"","Offers": {    "@type": "Offer",    "offeredBy": {        "@type": "Organization",        "name":"Person",       "telephone":"+1 999 999 999"    },    "price": $$PRICE$$,    "priceCurrency": "EUR",    "url": "/some/url", "availability": "http://schema.org/InStock"}        }</script>',
+    # LD JSON
+    '<script type=\'application/ld+json\'>[{"@context":"http://schema.org","@type":"WebSite","name":"partsDíly.cz","description":"Nejlevnější autodlíly.","url":"https://parts.com/?id=3038915","potentialAction":{"@type":"SearchAction","target":"https://parts.com/vyhledavani?search={query}","query-input":{"@type":"PropertyValueSpecification","valueRequired":"http://schema.org/True","valueName":"query"}},"publisher":{"@context":"http://schema.org","@type":"Organization","name":"Car Díly.cz","url":"https://carparts.com/","logo":"https://parts.com/77026_3195959275.png","sameAs":["https://twitter.com/parts","https://www.instagram.com/parts/?hl=cs"]},"sameAs":["https://twitter.com/parts","https://www.instagram.com/parts/"]},{"@context":"http://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":0,"item":{"@id":"/autodily","name":"Autodíly pro osobní vozy"}},{"@type":"ListItem","position":1,"item":{"@id":"/autodily/dodge","name":"DODGE"}},{"@type":"ListItem","position":2,"item":{"@id":"https://parts.com/280kw","name":"parts parts  • 100 kW"}}]},{"@context":"http://schema.org","@type":"Product","name":"Olejový filtr K&N Filters","description":"","mpn":"xxx11","brand":"K&N Filters","image":"https://parts.com/images/1600/c8fe1f1428021f4fe17a39297686178b04cba885.jpg","offers":{"@context":"http://schema.org","@type":"Offer","price":$$PRICE$$,"priceCurrency":"CZK","url":"https://parts.com/filters/hp","availability":"http://schema.org/InStock"}}]</script>',
+    '<script id="product-jsonld" type="application/ld+json">{"@context":"https://schema.org","@type":"Product","brand":{"@type":"Brand","name":"Ubiquiti"},"name":"UniFi Express","sku":"UX","description":"Impressively compact UniFi Cloud Gateway and WiFi 6 access point that runs UniFi Network. Powers an entire network or simply meshes as an access point.","url":"https://store.ui.com/us/en/products/ux","image":{"@type":"ImageObject","url":"https://cdn.ecomm.ui.com/products/4ed25b4c-db92-4b98-bbf3-b0989f007c0e/123417a2-895e-49c7-ba04-b6cd8f6acc03.png","width":"1500","height":"1500"},"offers":{"@type":"Offer","availability":"https://schema.org/InStock","priceSpecification":{"@type":"PriceSpecification","price":$$PRICE$$,"priceCurrency":"USD","valueAddedTaxIncluded":false}}}</script>',
+    '<script id="product-schema" type="application/ld+json">{"@context": "https://schema.org","@type": "Product","itemCondition": "https://schema.org/NewCondition","image": "//1.com/hmgo","name": "Polo MuscleFit","color": "Beige","description": "Polo","sku": "0957102010","brand": {"@type": "Brand","name": "H&M"},"category": {"@type": "Thing","name": "Polo"},"offers": [{"@type": "Offer","url": "https:/www2.xxxxxx.com/fr_fr/productpage.0957102010.html","priceCurrency": "EUR","price": $$PRICE$$,"availability": "http://schema.org/InStock","seller": {  "@type": "Organization", "name": "H&amp;M"}}]}</script>'
+    # Microdata
+    '<div itemscope itemtype="https://schema.org/Product"><h1 itemprop="name">Example Product</h1><p itemprop="description">This is a sample product description.</p><div itemprop="offers" itemscope itemtype="https://schema.org/Offer"><p>Price: <span itemprop="price">$$$PRICE$$</span></p><link itemprop="availability" href="https://schema.org/InStock" /></div></div>'
+]
+
+out_of_stock_props = [
+    # out of stock AND contains multiples
+    '<script type="application/ld+json">{"@context":"http://schema.org","@type":"WebSite","url":"https://www.medimops.de/","potentialAction":{"@type":"SearchAction","target":"https://www.medimops.de/produkte-C0/?fcIsSearch=1&searchparam={searchparam}","query-input":"required name=searchparam"}}</script><script type="application/ld+json">{"@context":"http://schema.org","@type":"Product","name":"Horsetrader: Robert Sangster and the Rise and Fall of the Sport of Kings","image":"https://images2.medimops.eu/product/43a982/M00002551322-large.jpg","productID":"isbn:9780002551328","gtin13":"9780002551328","category":"Livres en langue étrangère","offers":{"@type":"Offer","priceCurrency":"EUR","price":$$PRICE$$,"itemCondition":"UsedCondition","availability":"OutOfStock"},"brand":{"@type":"Thing","name":"Patrick Robinson","url":"https://www.momox-shop.fr/,patrick-robinson/"}}</script>'
+]
+
+def set_original_response(props_markup='', price="121.95"):
+
+    props_markup=props_markup.replace('$$PRICE$$', price)
+    test_return_data = f"""<html>
+       <body>
+     Some initial text<br>
+     <p>Which is across multiple lines</p>
+     <br>
+     So let's see what happens.  <br>
+     <div>price: ${price}</div>
+     {props_markup}
+     </body>
+     </html>
+    """
+
+    with open("test-datastore/endpoint-content.txt", "w") as f:
+        f.write(test_return_data)
+    return None
+
+
+
+
+def test_setup(client, live_server):
+
+    live_server_setup(live_server)
+
+def test_restock_itemprop_basic(client, live_server):
+
+    #live_server_setup(live_server)
+
+    test_url = url_for('test_endpoint', _external=True)
+
+    for p in instock_props:
+        set_original_response(props_markup=p)
+        client.post(
+            url_for("form_quick_watch_add"),
+            data={"url": test_url, "tags": 'restock tests', 'processor': 'restock_diff'},
+            follow_redirects=True
+        )
+        wait_for_all_checks(client)
+        res = client.get(url_for("index"))
+        assert b'has-restock-info in-stock' in res.data
+        assert b'has-restock-info not-in-stock' not in res.data
+        res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+        assert b'Deleted' in res.data
+
+
+    for p in out_of_stock_props:
+        set_original_response(props_markup=p)
+        client.post(
+            url_for("form_quick_watch_add"),
+            data={"url": test_url, "tags": '', 'processor': 'restock_diff'},
+            follow_redirects=True
+        )
+        wait_for_all_checks(client)
+        res = client.get(url_for("index"))
+        assert b'has-restock-info not-in-stock' in res.data
+
+        res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+        assert b'Deleted' in res.data
+
+def test_itemprop_price_change(client, live_server):
+    #live_server_setup(live_server)
+
+    test_url = url_for('test_endpoint', _external=True)
+
+    set_original_response(props_markup=instock_props[0], price="190.95")
+    client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": 'restock tests', 'processor': 'restock_diff'},
+        follow_redirects=True
+    )
+
+    # A change in price, should trigger a change by default
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'190.95' in res.data
+
+    # basic price change, look for notification
+    set_original_response(props_markup=instock_props[0], price='180.45')
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'180.45' in res.data
+    assert b'unviewed' in res.data
+    client.get(url_for("mark_all_viewed"), follow_redirects=True)
+
+    # turning off price change trigger, but it should show the new price, with no change notification
+    set_original_response(props_markup=instock_props[0], price='120.45')
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"follow_price_changes": "", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'120.45' in res.data
+    assert b'unviewed' not in res.data
+
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+def test_itemprop_price_minmax_limit(client, live_server):
+    #live_server_setup(live_server)
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+    test_url = url_for('test_endpoint', _external=True)
+
+    set_original_response(props_markup=instock_props[0], price="950.95")
+    client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": 'restock tests', 'processor': 'restock_diff'},
+        follow_redirects=True
+    )
+
+    # A change in price, should trigger a change by default
+    wait_for_all_checks(client)
+
+
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"follow_price_changes": "y",
+              "price_change_min": 900.0,
+              "price_change_max": 1100.10,
+              "url": test_url,
+              "tags": "",
+              "headers": "",
+              'fetch_backend': "html_requests"
+              },
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    wait_for_all_checks(client)
+
+    client.get(url_for("mark_all_viewed"))
+
+    # price changed to something greater than min (900), and less than max (1100).. should be no change
+    set_original_response(props_markup=instock_props[0], price='1000.45')
+    client.get(url_for("form_watch_checknow"))
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'1000.45' in res.data
+    assert b'unviewed' not in res.data
+
+
+    # price changed to something LESS than min (900), SHOULD be a change
+    set_original_response(props_markup=instock_props[0], price='890.45')
+    res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    assert b'1 watches queued for rechecking.' in res.data
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'890.45' in res.data
+    assert b'unviewed' in res.data
+
+    client.get(url_for("mark_all_viewed"))
+
+    # price changed to something MORE than max (1100.10), SHOULD be a change
+    set_original_response(props_markup=instock_props[0], price='1890.45')
+    client.get(url_for("form_watch_checknow"), follow_redirects=True)
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'1890.45' in res.data
+    assert b'unviewed' in res.data
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+
+def test_itemprop_percent_threshold(client, live_server):
+    #live_server_setup(live_server)
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+
+    test_url = url_for('test_endpoint', _external=True)
+
+    set_original_response(props_markup=instock_props[0], price="950.95")
+    client.post(
+        url_for("form_quick_watch_add"),
+        data={"url": test_url, "tags": 'restock tests', 'processor': 'restock_diff'},
+        follow_redirects=True
+    )
+
+    # A change in price, should trigger a change by default
+    wait_for_all_checks(client)
+
+    res = client.post(
+        url_for("edit_page", uuid="first"),
+        data={"follow_price_changes": "y",
+              "price_change_threshold_percent": 5.0,
+              "url": test_url,
+              "tags": "",
+              "headers": "",
+              'fetch_backend': "html_requests"
+              },
+        follow_redirects=True
+    )
+    assert b"Updated watch." in res.data
+    wait_for_all_checks(client)
+
+
+    # Basic change should not trigger
+    set_original_response(props_markup=instock_props[0], price='960.45')
+    client.get(url_for("form_watch_checknow"))
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'960.45' in res.data
+    assert b'unviewed' not in res.data
+
+    # Bigger INCREASE change than the threshold should trigger
+    set_original_response(props_markup=instock_props[0], price='1960.45')
+    client.get(url_for("form_watch_checknow"))
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'1960.45' in res.data
+    assert b'unviewed' in res.data
+
+
+    # Small decrease should NOT trigger
+    client.get(url_for("mark_all_viewed"))
+    set_original_response(props_markup=instock_props[0], price='1950.45')
+    client.get(url_for("form_watch_checknow"))
+    wait_for_all_checks(client)
+    res = client.get(url_for("index"))
+    assert b'1950.45' in res.data
+    assert b'unviewed' not in res.data
+
+
+
+
+    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    assert b'Deleted' in res.data
+

changedetectionio/tests/test_rss.py

@@ -69,6 +69,7 @@ def test_rss_and_token(client, live_server):
 
     wait_for_all_checks(client)
     set_modified_response()
+    time.sleep(1)
     client.get(url_for("form_watch_checknow"), follow_redirects=True)
     wait_for_all_checks(client)
 
@@ -87,7 +88,7 @@ def test_rss_and_token(client, live_server):
     assert b"Access denied, bad token" not in res.data
     assert b"Random content" in res.data
 
-    res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
+    client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
 
 def test_basic_cdata_rss_markup(client, live_server):
     #live_server_setup(live_server)

changedetectionio/tests/unit/test_restock_logic.py

@@ -0,0 +1,21 @@
+#!/usr/bin/python3
+
+# run from dir above changedetectionio/ dir
+# python3 -m unittest changedetectionio.tests.unit.test_restock_logic
+
+import unittest
+import os
+
+from changedetectionio.processors import restock_diff
+
+# mostly
+class TestDiffBuilder(unittest.TestCase):
+
+    def test_logic(self):
+        assert restock_diff.is_between(number=10, lower=9, upper=11) == True, "Between 9 and 11"
+        assert restock_diff.is_between(number=10, lower=0, upper=11) == True, "Between 9 and 11"
+        assert restock_diff.is_between(number=10, lower=None, upper=11) == True, "Between None and 11"
+        assert not restock_diff.is_between(number=12, lower=None, upper=11) == True, "12 is not between None and 11"
+
+if __name__ == '__main__':
+    unittest.main()

changedetectionio/tests/util.py

@@ -121,18 +121,21 @@ def extract_UUID_from_client(client):
     return uuid.strip()
 
 def wait_for_all_checks(client):
+    # actually this is not entirely true, it can still be 'processing' but not in the queue
     # Loop waiting until done..
     attempt=0
-    time.sleep(0.1)
+    # because sub-second rechecks are problematic in testing, use lots of delays
+    time.sleep(1)
     while attempt < 60:
-        time.sleep(1)
         res = client.get(url_for("index"))
         if not b'Checking now' in res.data:
             break
         logging.getLogger().info("Waiting for watch-list to not say 'Checking now'.. {}".format(attempt))
-
+        time.sleep(1)
         attempt += 1
 
+    time.sleep(1)
+
 def live_server_setup(live_server):
 
     @live_server.app.route('/test-random-content-endpoint')

changedetectionio/update_worker.py

@@ -348,7 +348,7 @@ class update_worker(threading.Thread):
                             # Send notification if we reached the threshold?
                             threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts',
                                                                                            0)
-                            logger.error(f"Filter for {uuid} not found, consecutive_filter_failures: {c}")
+                            logger.warning(f"Filter for {uuid} not found, consecutive_filter_failures: {c}")
                             if threshold > 0 and c >= threshold:
                                 if not self.datastore.data['watching'][uuid].get('notification_muted'):
                                     self.send_filter_failure_notification(uuid)
@@ -362,7 +362,6 @@ class update_worker(threading.Thread):
                         # Yes fine, so nothing todo, don't continue to process.
                         process_changedetection_results = False
                         changed_detected = False
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': False})
                     except content_fetchers.exceptions.BrowserConnectError as e:
                         self.datastore.update_watch(uuid=uuid,
                                                     update_obj={'last_error': e.msg
@@ -455,9 +454,12 @@ class update_worker(threading.Thread):
 
                     except UnableToExtractRestockData as e:
                         # Usually when fetcher.instock_data returns empty
-                        logger.error(f"Exception (UnableToExtractRestockData) reached processing watch UUID: {uuid}")
-                        logger.error(str(e))
-                        self.datastore.update_watch(uuid=uuid, update_obj={'last_error': f"Unable to extract restock data for this page unfortunately. (Got code {e.status_code} from server)"})
+                        self.app.logger.error("Exception reached processing watch UUID: %s - %s", uuid, str(e))
+                        self.datastore.update_watch(uuid=uuid,
+                                                    update_obj={
+                                                        'last_error': f"Unable to extract restock data for this page unfortunately. (Got code {e.status_code} from server), no embedded stock information was found and nothing interesting in the text, try using this watch with Chrome.",
+                                                    }
+                                                    )
                         process_changedetection_results = False
                     except Exception as e:
                         logger.error(f"Exception reached processing watch UUID: {uuid}")

requirements.txt

@@ -1,7 +1,7 @@
 # Used by Pyppeteer
 pyee
 
-eventlet==0.33.3 # related to dnspython fixes
+eventlet>=0.36.1 # fixes SSL error on Python 3.12
 feedgen~=0.9
 flask-compress
 # 0.6.3 included compatibility fix for werkzeug 3.x (2.x had deprecation of url handlers)
@@ -23,15 +23,13 @@ validators~=0.21
 brotli~=1.0
 requests[socks]
 
-urllib3==1.26.18
+urllib3==1.26.19
 chardet>2.3.0
 
 wtforms~=3.0
 jsonpath-ng~=1.5.3
 
-# Pinned: module 'eventlet.green.select' has no attribute 'epoll'
-# https://github.com/eventlet/eventlet/issues/805#issuecomment-1640463482
-dnspython==2.3.0 # related to eventlet fixes
+dnspython==2.6.1 # related to eventlet fixes
 
 # jq not available on Windows so must be installed manually
 
@@ -43,10 +41,8 @@ apprise~=1.8.0
 # use v1.x due to https://github.com/eclipse/paho.mqtt.python/issues/814
 paho-mqtt>=1.6.1,<2.0.0
 
-# This mainly affects some ARM builds, which unlike the other builds ignores "ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1"
-# so without this pinning, the newer versions on ARM will forcefully try to build rust, which results in "rust compiler not found"
-# (introduced once apprise became a dep)
-cryptography~=3.4
+# Requires extra wheel for rPi
+cryptography~=42.0.8
 
 # Used for CSS filtering
 beautifulsoup4
@@ -73,12 +69,10 @@ openpyxl
 jq~=1.3; python_version >= "3.8" and sys_platform == "darwin"
 jq~=1.3; python_version >= "3.8" and sys_platform == "linux"
 
-# Any current modern version, required so far for screenshot PNG->JPEG conversion but will be used more in the future
-pillow
 # playwright is installed at Dockerfile build time because it's not available on all platforms
 
-# experimental release
 pyppeteer-ng==2.0.0rc5
+pyppeteerstealth>=0.0.4
 
 # Include pytest, so if theres a support issue we can ask them to run these tests on their setup
 pytest ~=7.2
@@ -88,3 +82,9 @@ pytest-flask ~=1.2
 jsonschema==4.17.3
 
 loguru
+
+# For scraping all possible metadata relating to products so we can do better restock detection
+extruct
+
+# Needed for > 3.10, https://github.com/microsoft/playwright-python/issues/2096
+greenlet >= 3.0.3