mirror of
https://github.com/dgtlmoon/changedetection.io.git
synced 2026-05-01 23:30:33 +00:00
Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 dgtlmoon
|
cdabdfeef1 |
@@ -1,33 +0,0 @@
|
||||
server {
|
||||
listen 80;
|
||||
server_name localhost;
|
||||
|
||||
# Test basic reverse proxy to changedetection.io
|
||||
location / {
|
||||
proxy_pass http://changedet-app:5000;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
|
||||
# WebSocket support
|
||||
proxy_http_version 1.1;
|
||||
proxy_set_header Upgrade $http_upgrade;
|
||||
proxy_set_header Connection "upgrade";
|
||||
}
|
||||
|
||||
# Test subpath deployment with X-Forwarded-Prefix
|
||||
location /changedet-sub/ {
|
||||
proxy_pass http://changedet-app:5000/;
|
||||
proxy_set_header X-Forwarded-Prefix /changedet-sub;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
|
||||
# WebSocket support
|
||||
proxy_http_version 1.1;
|
||||
proxy_set_header Upgrade $http_upgrade;
|
||||
proxy_set_header Connection "upgrade";
|
||||
}
|
||||
}
|
||||
@@ -66,27 +66,27 @@ jobs:
|
||||
echo ${{ github.ref }} > changedetectionio/tag.txt
|
||||
|
||||
- name: Set up QEMU
|
||||
uses: docker/setup-qemu-action@v4
|
||||
uses: docker/setup-qemu-action@v3
|
||||
with:
|
||||
image: tonistiigi/binfmt:latest
|
||||
platforms: all
|
||||
|
||||
- name: Login to GitHub Container Registry
|
||||
uses: docker/login-action@v4
|
||||
uses: docker/login-action@v3
|
||||
with:
|
||||
registry: ghcr.io
|
||||
username: ${{ github.actor }}
|
||||
password: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- name: Login to Docker Hub Container Registry
|
||||
uses: docker/login-action@v4
|
||||
uses: docker/login-action@v3
|
||||
with:
|
||||
username: ${{ secrets.DOCKER_HUB_USERNAME }}
|
||||
password: ${{ secrets.DOCKER_HUB_ACCESS_TOKEN }}
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
id: buildx
|
||||
uses: docker/setup-buildx-action@v4
|
||||
uses: docker/setup-buildx-action@v3
|
||||
with:
|
||||
install: true
|
||||
version: latest
|
||||
@@ -95,7 +95,7 @@ jobs:
|
||||
# master branch -> :dev container tag
|
||||
- name: Docker meta :dev
|
||||
if: ${{ github.ref == 'refs/heads/master' && github.event_name != 'release' }}
|
||||
uses: docker/metadata-action@v6
|
||||
uses: docker/metadata-action@v5
|
||||
id: meta_dev
|
||||
with:
|
||||
images: |
|
||||
@@ -103,19 +103,11 @@ jobs:
|
||||
ghcr.io/${{ github.repository }}
|
||||
tags: |
|
||||
type=raw,value=dev
|
||||
labels: |
|
||||
org.opencontainers.image.created=${{ github.event.release.published_at }}
|
||||
org.opencontainers.image.description=Website, webpage change detection, monitoring and notifications.
|
||||
org.opencontainers.image.documentation=https://changedetection.io
|
||||
org.opencontainers.image.revision=${{ github.sha }}
|
||||
org.opencontainers.image.source=https://github.com/dgtlmoon/changedetection.io
|
||||
org.opencontainers.image.title=changedetection.io
|
||||
org.opencontainers.image.url=https://changedetection.io
|
||||
|
||||
- name: Build and push :dev
|
||||
id: docker_build
|
||||
if: ${{ github.ref == 'refs/heads/master' && github.event_name != 'release' }}
|
||||
uses: docker/build-push-action@v7
|
||||
uses: docker/build-push-action@v6
|
||||
with:
|
||||
context: ./
|
||||
file: ./Dockerfile
|
||||
@@ -136,10 +128,10 @@ jobs:
|
||||
echo "Release tag: ${{ github.event.release.tag_name }}"
|
||||
echo "Github ref: ${{ github.ref }}"
|
||||
echo "Github ref name: ${{ github.ref_name }}"
|
||||
|
||||
|
||||
- name: Docker meta :tag
|
||||
if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
|
||||
uses: docker/metadata-action@v6
|
||||
uses: docker/metadata-action@v5
|
||||
id: meta
|
||||
with:
|
||||
images: |
|
||||
@@ -150,20 +142,11 @@ jobs:
|
||||
type=semver,pattern={{major}}.{{minor}},value=${{ github.event.release.tag_name }}
|
||||
type=semver,pattern={{major}},value=${{ github.event.release.tag_name }}
|
||||
type=raw,value=latest
|
||||
labels: |
|
||||
org.opencontainers.image.created=${{ github.event.release.published_at }}
|
||||
org.opencontainers.image.description=Website, webpage change detection, monitoring and notifications.
|
||||
org.opencontainers.image.documentation=https://changedetection.io
|
||||
org.opencontainers.image.revision=${{ github.sha }}
|
||||
org.opencontainers.image.source=https://github.com/dgtlmoon/changedetection.io
|
||||
org.opencontainers.image.title=changedetection.io
|
||||
org.opencontainers.image.url=https://changedetection.io
|
||||
org.opencontainers.image.version=${{ github.event.release.tag_name }}
|
||||
|
||||
- name: Build and push :tag
|
||||
id: docker_build_tag_release
|
||||
if: github.event_name == 'release' && startsWith(github.event.release.tag_name, '0.')
|
||||
uses: docker/build-push-action@v7
|
||||
uses: docker/build-push-action@v6
|
||||
with:
|
||||
context: ./
|
||||
file: ./Dockerfile
|
||||
|
||||
@@ -21,7 +21,7 @@ jobs:
|
||||
- name: Build a binary wheel and a source tarball
|
||||
run: python3 -m build
|
||||
- name: Store the distribution packages
|
||||
uses: actions/upload-artifact@v7
|
||||
uses: actions/upload-artifact@v6
|
||||
with:
|
||||
name: python-package-distributions
|
||||
path: dist/
|
||||
@@ -34,7 +34,7 @@ jobs:
|
||||
- build
|
||||
steps:
|
||||
- name: Download all the dists
|
||||
uses: actions/download-artifact@v8
|
||||
uses: actions/download-artifact@v7
|
||||
with:
|
||||
name: python-package-distributions
|
||||
path: dist/
|
||||
@@ -93,7 +93,7 @@ jobs:
|
||||
|
||||
steps:
|
||||
- name: Download all the dists
|
||||
uses: actions/download-artifact@v8
|
||||
uses: actions/download-artifact@v7
|
||||
with:
|
||||
name: python-package-distributions
|
||||
path: dist/
|
||||
|
||||
@@ -60,14 +60,14 @@ jobs:
|
||||
|
||||
# Just test that the build works, some libraries won't compile on ARM/rPi etc
|
||||
- name: Set up QEMU
|
||||
uses: docker/setup-qemu-action@v4
|
||||
uses: docker/setup-qemu-action@v3
|
||||
with:
|
||||
image: tonistiigi/binfmt:latest
|
||||
platforms: all
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
id: buildx
|
||||
uses: docker/setup-buildx-action@v4
|
||||
uses: docker/setup-buildx-action@v3
|
||||
with:
|
||||
install: true
|
||||
version: latest
|
||||
@@ -75,7 +75,7 @@ jobs:
|
||||
|
||||
- name: Test that the docker containers can build (${{ matrix.platform }} - ${{ matrix.dockerfile }})
|
||||
id: docker_build
|
||||
uses: docker/build-push-action@v7
|
||||
uses: docker/build-push-action@v6
|
||||
# https://github.com/docker/build-push-action#customizing
|
||||
with:
|
||||
context: ./
|
||||
|
||||
@@ -52,13 +52,4 @@ jobs:
|
||||
uses: ./.github/workflows/test-stack-reusable-workflow.yml
|
||||
with:
|
||||
python-version: '3.13'
|
||||
skip-pypuppeteer: true
|
||||
|
||||
|
||||
test-application-3-14:
|
||||
#if: github.event_name == 'push' && github.ref == 'refs/heads/master'
|
||||
needs: lint-code
|
||||
uses: ./.github/workflows/test-stack-reusable-workflow.yml
|
||||
with:
|
||||
python-version: '3.14'
|
||||
skip-pypuppeteer: false
|
||||
skip-pypuppeteer: true
|
||||
@@ -42,10 +42,10 @@ jobs:
|
||||
run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v4
|
||||
uses: docker/setup-buildx-action@v3
|
||||
|
||||
- name: Build changedetection.io container for testing under Python ${{ env.PYTHON_VERSION }}
|
||||
uses: docker/build-push-action@v7
|
||||
uses: docker/build-push-action@v6
|
||||
with:
|
||||
context: ./
|
||||
file: ./Dockerfile
|
||||
@@ -71,7 +71,7 @@ jobs:
|
||||
docker save test-changedetectionio -o /tmp/test-changedetectionio.tar
|
||||
|
||||
- name: Upload Docker image artifact
|
||||
uses: actions/upload-artifact@v7
|
||||
uses: actions/upload-artifact@v6
|
||||
with:
|
||||
name: test-changedetectionio-${{ env.PYTHON_VERSION }}
|
||||
path: /tmp/test-changedetectionio.tar
|
||||
@@ -88,7 +88,7 @@ jobs:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- name: Download Docker image artifact
|
||||
uses: actions/download-artifact@v8
|
||||
uses: actions/download-artifact@v7
|
||||
with:
|
||||
name: test-changedetectionio-${{ env.PYTHON_VERSION }}
|
||||
path: /tmp
|
||||
@@ -99,7 +99,11 @@ jobs:
|
||||
|
||||
- name: Run Unit Tests
|
||||
run: |
|
||||
docker run test-changedetectionio bash -c 'cd changedetectionio;pytest tests/unit/'
|
||||
docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_notification_diff'
|
||||
docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_watch_model'
|
||||
docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_jinja2_security'
|
||||
docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_semver'
|
||||
docker run test-changedetectionio bash -c 'python3 -m unittest changedetectionio.tests.unit.test_html_to_text'
|
||||
|
||||
# Basic pytest tests with ancillary services
|
||||
basic-tests:
|
||||
@@ -112,7 +116,7 @@ jobs:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- name: Download Docker image artifact
|
||||
uses: actions/download-artifact@v8
|
||||
uses: actions/download-artifact@v7
|
||||
with:
|
||||
name: test-changedetectionio-${{ env.PYTHON_VERSION }}
|
||||
path: /tmp
|
||||
@@ -161,14 +165,14 @@ jobs:
|
||||
|
||||
- name: Store test artifacts
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v7
|
||||
uses: actions/upload-artifact@v6
|
||||
with:
|
||||
name: test-cdio-basic-tests-output-py${{ env.PYTHON_VERSION }}
|
||||
path: output-logs
|
||||
|
||||
- name: Store CLI test output
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v7
|
||||
uses: actions/upload-artifact@v6
|
||||
with:
|
||||
name: test-cdio-cli-opts-output-py${{ env.PYTHON_VERSION }}
|
||||
path: cli-opts-output.txt
|
||||
@@ -184,7 +188,7 @@ jobs:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- name: Download Docker image artifact
|
||||
uses: actions/download-artifact@v8
|
||||
uses: actions/download-artifact@v7
|
||||
with:
|
||||
name: test-changedetectionio-${{ env.PYTHON_VERSION }}
|
||||
path: /tmp
|
||||
@@ -226,7 +230,7 @@ jobs:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- name: Download Docker image artifact
|
||||
uses: actions/download-artifact@v8
|
||||
uses: actions/download-artifact@v7
|
||||
with:
|
||||
name: test-changedetectionio-${{ env.PYTHON_VERSION }}
|
||||
path: /tmp
|
||||
@@ -266,7 +270,7 @@ jobs:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- name: Download Docker image artifact
|
||||
uses: actions/download-artifact@v8
|
||||
uses: actions/download-artifact@v7
|
||||
with:
|
||||
name: test-changedetectionio-${{ env.PYTHON_VERSION }}
|
||||
path: /tmp
|
||||
@@ -302,7 +306,7 @@ jobs:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- name: Download Docker image artifact
|
||||
uses: actions/download-artifact@v8
|
||||
uses: actions/download-artifact@v7
|
||||
with:
|
||||
name: test-changedetectionio-${{ env.PYTHON_VERSION }}
|
||||
path: /tmp
|
||||
@@ -320,175 +324,6 @@ jobs:
|
||||
run: |
|
||||
docker run --rm --network changedet-network test-changedetectionio bash -c 'cd changedetectionio;pytest tests/smtp/test_notification_smtp.py'
|
||||
|
||||
nginx-reverse-proxy:
|
||||
runs-on: ubuntu-latest
|
||||
needs: build
|
||||
timeout-minutes: 10
|
||||
env:
|
||||
PYTHON_VERSION: ${{ inputs.python-version }}
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- name: Download Docker image artifact
|
||||
uses: actions/download-artifact@v8
|
||||
with:
|
||||
name: test-changedetectionio-${{ env.PYTHON_VERSION }}
|
||||
path: /tmp
|
||||
|
||||
- name: Load Docker image
|
||||
run: |
|
||||
docker load -i /tmp/test-changedetectionio.tar
|
||||
|
||||
- name: Spin up services
|
||||
run: |
|
||||
docker network create changedet-network
|
||||
|
||||
# Start changedetection.io container with X-Forwarded headers support
|
||||
docker run --name changedet-app --hostname changedet-app --network changedet-network \
|
||||
-e USE_X_SETTINGS=true \
|
||||
-d test-changedetectionio
|
||||
sleep 3
|
||||
|
||||
- name: Start nginx reverse proxy
|
||||
run: |
|
||||
# Start nginx with our test configuration
|
||||
docker run --name nginx-proxy --network changedet-network -d -p 8080:80 --rm \
|
||||
-v ${{ github.workspace }}/.github/nginx-reverse-proxy-test.conf:/etc/nginx/conf.d/default.conf:ro \
|
||||
nginx:alpine
|
||||
sleep 2
|
||||
|
||||
- name: Test reverse proxy - root path
|
||||
run: |
|
||||
echo "=== Testing nginx reverse proxy at root path ==="
|
||||
curl --retry-connrefused --retry 6 -s http://localhost:8080/ > /tmp/nginx-test-root.html
|
||||
|
||||
# Check for changedetection.io UI elements
|
||||
if grep -q "checkbox-uuid" /tmp/nginx-test-root.html; then
|
||||
echo "✓ Found checkbox-uuid in response"
|
||||
else
|
||||
echo "ERROR: checkbox-uuid not found in response"
|
||||
cat /tmp/nginx-test-root.html
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Check for watchlist content
|
||||
if grep -q -i "watch" /tmp/nginx-test-root.html; then
|
||||
echo "✓ Found watch/watchlist content in response"
|
||||
else
|
||||
echo "ERROR: watchlist content not found"
|
||||
cat /tmp/nginx-test-root.html
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✓ Root path reverse proxy working correctly"
|
||||
|
||||
- name: Test reverse proxy - subpath with X-Forwarded-Prefix
|
||||
run: |
|
||||
echo "=== Testing nginx reverse proxy at subpath /changedet-sub/ ==="
|
||||
curl --retry-connrefused --retry 6 -s http://localhost:8080/changedet-sub/ > /tmp/nginx-test-subpath.html
|
||||
|
||||
# Check for changedetection.io UI elements
|
||||
if grep -q "checkbox-uuid" /tmp/nginx-test-subpath.html; then
|
||||
echo "✓ Found checkbox-uuid in subpath response"
|
||||
else
|
||||
echo "ERROR: checkbox-uuid not found in subpath response"
|
||||
cat /tmp/nginx-test-subpath.html
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✓ Subpath reverse proxy working correctly"
|
||||
|
||||
- name: Test API through reverse proxy subpath
|
||||
run: |
|
||||
echo "=== Testing API endpoints through nginx subpath /changedet-sub/ ==="
|
||||
|
||||
# Extract API key from the changedetection.io datastore
|
||||
API_KEY=$(docker exec changedet-app cat /datastore/changedetection.json | grep -o '"api_access_token": *"[^"]*"' | cut -d'"' -f4)
|
||||
|
||||
if [ -z "$API_KEY" ]; then
|
||||
echo "ERROR: Could not extract API key from datastore"
|
||||
docker exec changedet-app cat /datastore/changedetection.json
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✓ Extracted API key: ${API_KEY:0:8}..."
|
||||
|
||||
# Create a watch via API through nginx proxy subpath
|
||||
echo "Creating watch via POST to /changedet-sub/api/v1/watch"
|
||||
RESPONSE=$(curl -s -w "\n%{http_code}" -X POST "http://localhost:8080/changedet-sub/api/v1/watch" \
|
||||
-H "x-api-key: ${API_KEY}" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"url": "https://example.com/test-nginx-proxy",
|
||||
"tag": "nginx-test"
|
||||
}')
|
||||
|
||||
HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
|
||||
BODY=$(echo "$RESPONSE" | head -n-1)
|
||||
|
||||
if [ "$HTTP_CODE" != "201" ]; then
|
||||
echo "ERROR: Expected HTTP 201, got $HTTP_CODE"
|
||||
echo "Response: $BODY"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✓ Watch created successfully (HTTP 201)"
|
||||
|
||||
# Extract the watch UUID from response
|
||||
WATCH_UUID=$(echo "$BODY" | grep -o '"uuid": *"[^"]*"' | cut -d'"' -f4)
|
||||
echo "✓ Watch UUID: $WATCH_UUID"
|
||||
|
||||
# Update the watch via PUT through nginx proxy subpath
|
||||
echo "Updating watch via PUT to /changedet-sub/api/v1/watch/${WATCH_UUID}"
|
||||
RESPONSE=$(curl -s -w "\n%{http_code}" -X PUT "http://localhost:8080/changedet-sub/api/v1/watch/${WATCH_UUID}" \
|
||||
-H "x-api-key: ${API_KEY}" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"paused": true
|
||||
}')
|
||||
|
||||
HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
|
||||
BODY=$(echo "$RESPONSE" | head -n-1)
|
||||
|
||||
if [ "$HTTP_CODE" != "200" ]; then
|
||||
echo "ERROR: Expected HTTP 200, got $HTTP_CODE"
|
||||
echo "Response: $BODY"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if echo "$BODY" | grep -q 'OK'; then
|
||||
echo "✓ Watch updated successfully (HTTP 200, response: OK)"
|
||||
else
|
||||
echo "ERROR: Expected response 'OK', got: $BODY"
|
||||
echo "Response: $BODY"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Verify the watch is paused via GET
|
||||
echo "Verifying watch is paused via GET"
|
||||
RESPONSE=$(curl -s "http://localhost:8080/changedet-sub/api/v1/watch/${WATCH_UUID}" \
|
||||
-H "x-api-key: ${API_KEY}")
|
||||
|
||||
if echo "$RESPONSE" | grep -q '"paused": *true'; then
|
||||
echo "✓ Watch is paused as expected"
|
||||
else
|
||||
echo "ERROR: Watch paused state not confirmed"
|
||||
echo "Response: $RESPONSE"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✓ API tests through nginx subpath completed successfully"
|
||||
|
||||
- name: Cleanup nginx test
|
||||
if: always()
|
||||
run: |
|
||||
docker logs nginx-proxy || true
|
||||
docker logs changedet-app || true
|
||||
docker stop nginx-proxy changedet-app || true
|
||||
docker rm nginx-proxy changedet-app || true
|
||||
|
||||
|
||||
|
||||
# Proxy tests
|
||||
proxy-tests:
|
||||
runs-on: ubuntu-latest
|
||||
@@ -500,7 +335,7 @@ jobs:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- name: Download Docker image artifact
|
||||
uses: actions/download-artifact@v8
|
||||
uses: actions/download-artifact@v7
|
||||
with:
|
||||
name: test-changedetectionio-${{ env.PYTHON_VERSION }}
|
||||
path: /tmp
|
||||
@@ -540,7 +375,7 @@ jobs:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- name: Download Docker image artifact
|
||||
uses: actions/download-artifact@v8
|
||||
uses: actions/download-artifact@v7
|
||||
with:
|
||||
name: test-changedetectionio-${{ env.PYTHON_VERSION }}
|
||||
path: /tmp
|
||||
@@ -570,7 +405,7 @@ jobs:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- name: Download Docker image artifact
|
||||
uses: actions/download-artifact@v8
|
||||
uses: actions/download-artifact@v7
|
||||
with:
|
||||
name: test-changedetectionio-${{ env.PYTHON_VERSION }}
|
||||
path: /tmp
|
||||
@@ -583,10 +418,6 @@ jobs:
|
||||
run: |
|
||||
docker run -e EXTRA_PACKAGES=changedetection.io-osint-processor test-changedetectionio bash -c 'cd changedetectionio;pytest -vvv -s tests/plugins/test_processor.py::test_check_plugin_processor'
|
||||
|
||||
- name: Plugin get_html_head_extras hook injects into base.html
|
||||
run: |
|
||||
docker run test-changedetectionio bash -c 'cd changedetectionio;pytest -vvv -s tests/plugins/test_html_head_extras.py'
|
||||
|
||||
# Container startup tests
|
||||
container-tests:
|
||||
runs-on: ubuntu-latest
|
||||
@@ -598,7 +429,7 @@ jobs:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- name: Download Docker image artifact
|
||||
uses: actions/download-artifact@v8
|
||||
uses: actions/download-artifact@v7
|
||||
with:
|
||||
name: test-changedetectionio-${{ env.PYTHON_VERSION }}
|
||||
path: /tmp
|
||||
@@ -643,7 +474,7 @@ jobs:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- name: Download Docker image artifact
|
||||
uses: actions/download-artifact@v8
|
||||
uses: actions/download-artifact@v7
|
||||
with:
|
||||
name: test-changedetectionio-${{ env.PYTHON_VERSION }}
|
||||
path: /tmp
|
||||
@@ -706,19 +537,7 @@ jobs:
|
||||
- name: Check upgrade works without error
|
||||
run: |
|
||||
echo "=== Testing upgrade path from 0.49.1 to ${{ github.ref_name }} (${{ github.sha }}) ==="
|
||||
sudo apt-get update && sudo apt-get install -y --no-install-recommends \
|
||||
g++ \
|
||||
gcc \
|
||||
libc-dev \
|
||||
libffi-dev \
|
||||
libjpeg-dev \
|
||||
libssl-dev \
|
||||
libxslt-dev \
|
||||
make \
|
||||
patch \
|
||||
pkg-config \
|
||||
zlib1g-dev
|
||||
|
||||
|
||||
# Checkout old version and create datastore
|
||||
git checkout 0.49.1
|
||||
python3 -m venv .venv
|
||||
@@ -727,7 +546,7 @@ jobs:
|
||||
pip install 'pyOpenSSL>=23.2.0'
|
||||
|
||||
echo "=== Running version 0.49.1 to create datastore ==="
|
||||
ALLOW_IANA_RESTRICTED_ADDRESSES=true python3 ./changedetection.py -C -d /tmp/data &
|
||||
python3 ./changedetection.py -C -d /tmp/data &
|
||||
APP_PID=$!
|
||||
|
||||
# Wait for app to be ready
|
||||
@@ -775,7 +594,7 @@ jobs:
|
||||
pip install -r requirements.txt
|
||||
|
||||
echo "=== Running current version (commit ${{ github.sha }}) with old datastore (testing mode) ==="
|
||||
ALLOW_IANA_RESTRICTED_ADDRESSES=true TESTING_SHUTDOWN_AFTER_DATASTORE_LOAD=1 python3 ./changedetection.py -d /tmp/data > /tmp/upgrade-test.log 2>&1
|
||||
TESTING_SHUTDOWN_AFTER_DATASTORE_LOAD=1 python3 ./changedetection.py -d /tmp/data > /tmp/upgrade-test.log 2>&1
|
||||
|
||||
echo "=== Upgrade test output ==="
|
||||
cat /tmp/upgrade-test.log
|
||||
@@ -783,7 +602,7 @@ jobs:
|
||||
|
||||
# Now start the current version normally to verify the tag survived
|
||||
echo "=== Starting current version to verify tag exists after upgrade ==="
|
||||
ALLOW_IANA_RESTRICTED_ADDRESSES=true timeout 20 python3 ./changedetection.py -d /tmp/data > /tmp/ui-test.log 2>&1 &
|
||||
timeout 20 python3 ./changedetection.py -d /tmp/data > /tmp/ui-test.log 2>&1 &
|
||||
APP_PID=$!
|
||||
|
||||
# Wait for app to be ready and fetch UI
|
||||
@@ -832,7 +651,7 @@ jobs:
|
||||
|
||||
- name: Upload upgrade test logs
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v7
|
||||
uses: actions/upload-artifact@v6
|
||||
with:
|
||||
name: upgrade-test-logs-py${{ env.PYTHON_VERSION }}
|
||||
path: /tmp/upgrade-test.log
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
# Read more https://github.com/dgtlmoon/changedetection.io/wiki
|
||||
# Semver means never use .01, or 00. Should be .1.
|
||||
__version__ = '0.54.8'
|
||||
__version__ = '0.52.9'
|
||||
|
||||
from changedetectionio.strtobool import strtobool
|
||||
from json.decoder import JSONDecodeError
|
||||
@@ -61,22 +61,8 @@ import time
|
||||
# ==============================================================================
|
||||
|
||||
import multiprocessing
|
||||
import os
|
||||
import sys
|
||||
|
||||
# Limit glibc malloc arena count to prevent RSS growth from concurrent requests.
|
||||
# Default: glibc creates up to 8×CPU_cores arenas. Each concurrent thread/connection
|
||||
# can trigger a new arena, and freed memory stays mapped in those arenas as RSS forever.
|
||||
# With MALLOC_ARENA_MAX=2, at most 2 arenas are used; freed pages return to the OS faster.
|
||||
# Must be set before worker threads start; env var is read lazily by glibc on first arena creation.
|
||||
if 'MALLOC_ARENA_MAX' not in os.environ:
|
||||
os.environ['MALLOC_ARENA_MAX'] = '2'
|
||||
try:
|
||||
import ctypes as _ctypes
|
||||
_ctypes.CDLL('libc.so.6').mallopt(-8, 2) # M_ARENA_MAX = -8
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Set spawn as global default (safety net - all our code uses explicit contexts anyway)
|
||||
# Skip in tests to avoid breaking pytest-flask's LiveServer fixture (uses unpicklable local functions)
|
||||
if 'pytest' not in sys.modules:
|
||||
@@ -624,7 +610,7 @@ def main():
|
||||
|
||||
@app.context_processor
|
||||
def inject_template_globals():
|
||||
return dict(right_sticky="v"+__version__,
|
||||
return dict(right_sticky="v{}".format(datastore.data['version_tag']),
|
||||
new_version_available=app.config['NEW_VERSION_AVAILABLE'],
|
||||
has_password=datastore.data['settings']['application']['password'] != False,
|
||||
socket_io_enabled=datastore.data['settings']['application'].get('ui', {}).get('socket_io_enabled', True),
|
||||
|
||||
@@ -1,21 +0,0 @@
|
||||
import functools
|
||||
from flask import make_response
|
||||
from flask_restful import Resource
|
||||
|
||||
|
||||
@functools.cache
|
||||
def _get_spec_yaml():
|
||||
"""Build and cache the merged spec as a YAML string (only serialized once per process)."""
|
||||
import yaml
|
||||
from changedetectionio.api import build_merged_spec_dict
|
||||
return yaml.dump(build_merged_spec_dict(), default_flow_style=False, allow_unicode=True)
|
||||
|
||||
|
||||
class Spec(Resource):
|
||||
def get(self):
|
||||
"""Return the merged OpenAPI spec including all registered processor extensions."""
|
||||
return make_response(
|
||||
_get_spec_yaml(),
|
||||
200,
|
||||
{'Content-Type': 'application/yaml'}
|
||||
)
|
||||
@@ -17,7 +17,7 @@ class Tag(Resource):
|
||||
self.update_q = kwargs['update_q']
|
||||
|
||||
# Get information about a single tag
|
||||
# curl http://localhost:5000/api/v1/tag/<uuid_str:uuid>
|
||||
# curl http://localhost:5000/api/v1/tag/<string:uuid>
|
||||
@auth.check_token
|
||||
@validate_openapi_request('getTag')
|
||||
def get(self, uuid):
|
||||
@@ -97,6 +97,17 @@ class Tag(Resource):
|
||||
# Delete the tag, and any tag reference
|
||||
del self.datastore.data['settings']['application']['tags'][uuid]
|
||||
|
||||
# Delete tag.json file if it exists
|
||||
import os
|
||||
tag_dir = os.path.join(self.datastore.datastore_path, uuid)
|
||||
tag_json = os.path.join(tag_dir, "tag.json")
|
||||
if os.path.exists(tag_json):
|
||||
try:
|
||||
os.unlink(tag_json)
|
||||
logger.info(f"Deleted tag.json for tag {uuid}")
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to delete tag.json for tag {uuid}: {e}")
|
||||
|
||||
# Remove tag from all watches
|
||||
for watch_uuid, watch in self.datastore.data['watching'].items():
|
||||
if watch.get('tags') and uuid in watch['tags']:
|
||||
@@ -177,13 +188,6 @@ class Tag(Resource):
|
||||
|
||||
new_uuid = self.datastore.add_tag(title=title)
|
||||
if new_uuid:
|
||||
# Apply any extra fields (e.g. processor_config_restock_diff) beyond just title
|
||||
extra = {k: v for k, v in json_data.items() if k != 'title'}
|
||||
if extra:
|
||||
tag = self.datastore.data['settings']['application']['tags'].get(new_uuid)
|
||||
if tag:
|
||||
tag.update(extra)
|
||||
tag.commit()
|
||||
return {'uuid': new_uuid}, 201
|
||||
else:
|
||||
return "Invalid or unsupported tag", 400
|
||||
|
||||
@@ -57,7 +57,7 @@ class Watch(Resource):
|
||||
self.update_q = kwargs['update_q']
|
||||
|
||||
# Get information about a single watch, excluding the history list (can be large)
|
||||
# curl http://localhost:5000/api/v1/watch/<uuid_str:uuid>
|
||||
# curl http://localhost:5000/api/v1/watch/<string:uuid>
|
||||
# @todo - version2 - ?muted and ?paused should be able to be called together, return the watch struct not "OK"
|
||||
# ?recheck=true
|
||||
@auth.check_token
|
||||
@@ -217,7 +217,7 @@ class WatchHistory(Resource):
|
||||
self.datastore = kwargs['datastore']
|
||||
|
||||
# Get a list of available history for a watch by UUID
|
||||
# curl http://localhost:5000/api/v1/watch/<uuid_str:uuid>/history
|
||||
# curl http://localhost:5000/api/v1/watch/<string:uuid>/history
|
||||
@auth.check_token
|
||||
@validate_openapi_request('getWatchHistory')
|
||||
def get(self, uuid):
|
||||
@@ -338,7 +338,7 @@ class WatchHistoryDiff(Resource):
|
||||
word_diff = True
|
||||
|
||||
# Get boolean diff preferences with defaults from DIFF_PREFERENCES_CONFIG
|
||||
changes_only = strtobool(request.args.get('changesOnly', 'false'))
|
||||
changes_only = strtobool(request.args.get('changesOnly', 'true'))
|
||||
ignore_whitespace = strtobool(request.args.get('ignoreWhitespace', 'false'))
|
||||
include_removed = strtobool(request.args.get('removed', 'true'))
|
||||
include_added = strtobool(request.args.get('added', 'true'))
|
||||
@@ -349,7 +349,7 @@ class WatchHistoryDiff(Resource):
|
||||
previous_version_file_contents=from_version_file_contents,
|
||||
newest_version_file_contents=to_version_file_contents,
|
||||
ignore_junk=ignore_whitespace,
|
||||
include_equal=not changes_only,
|
||||
include_equal=changes_only,
|
||||
include_removed=include_removed,
|
||||
include_added=include_added,
|
||||
include_replaced=include_replaced,
|
||||
@@ -567,4 +567,4 @@ class CreateWatch(Resource):
|
||||
|
||||
return {'status': f'OK, queueing {len(watches_to_queue)} watches in background'}, 202
|
||||
|
||||
return list, 200
|
||||
return list, 200
|
||||
@@ -3,18 +3,29 @@ from flask import request, abort
|
||||
from loguru import logger
|
||||
|
||||
@functools.cache
|
||||
def build_merged_spec_dict():
|
||||
def get_openapi_spec():
|
||||
"""Lazy load OpenAPI spec and dependencies only when validation is needed."""
|
||||
import os
|
||||
import yaml # Lazy import - only loaded when API validation is actually used
|
||||
from openapi_core import OpenAPI # Lazy import - saves ~10.7 MB on startup
|
||||
|
||||
spec_path = os.path.join(os.path.dirname(__file__), '../../docs/api-spec.yaml')
|
||||
if not os.path.exists(spec_path):
|
||||
# Possibly for pip3 packages
|
||||
spec_path = os.path.join(os.path.dirname(__file__), '../docs/api-spec.yaml')
|
||||
|
||||
with open(spec_path, 'r', encoding='utf-8') as f:
|
||||
spec_dict = yaml.safe_load(f)
|
||||
_openapi_spec = OpenAPI.from_dict(spec_dict)
|
||||
return _openapi_spec
|
||||
|
||||
@functools.cache
|
||||
def get_openapi_schema_dict():
|
||||
"""
|
||||
Load the base OpenAPI spec and merge in any per-processor api.yaml extensions.
|
||||
Get the raw OpenAPI spec dictionary for schema access.
|
||||
|
||||
Each processor can provide an api.yaml file alongside its __init__.py that defines
|
||||
additional schemas (e.g., processor_config_restock_diff). These are merged into
|
||||
WatchBase.properties so the spec accurately reflects what the API accepts.
|
||||
|
||||
Plugin processors (via pluggy) are also supported - they just need an api.yaml
|
||||
next to their processor module.
|
||||
|
||||
Returns the merged dict (cached - do not mutate the returned value).
|
||||
Used by Import endpoint to validate and convert query parameters.
|
||||
Returns the YAML dict directly (not the OpenAPI object).
|
||||
"""
|
||||
import os
|
||||
import yaml
|
||||
@@ -24,59 +35,7 @@ def build_merged_spec_dict():
|
||||
spec_path = os.path.join(os.path.dirname(__file__), '../docs/api-spec.yaml')
|
||||
|
||||
with open(spec_path, 'r', encoding='utf-8') as f:
|
||||
spec_dict = yaml.safe_load(f)
|
||||
|
||||
try:
|
||||
from changedetectionio.processors import find_processors, get_parent_module
|
||||
for module, proc_name in find_processors():
|
||||
parent = get_parent_module(module)
|
||||
if not parent or not hasattr(parent, '__file__'):
|
||||
continue
|
||||
api_yaml_path = os.path.join(os.path.dirname(parent.__file__), 'api.yaml')
|
||||
if not os.path.exists(api_yaml_path):
|
||||
continue
|
||||
with open(api_yaml_path, 'r', encoding='utf-8') as f:
|
||||
proc_spec = yaml.safe_load(f)
|
||||
# Merge schemas
|
||||
proc_schemas = proc_spec.get('components', {}).get('schemas', {})
|
||||
spec_dict['components']['schemas'].update(proc_schemas)
|
||||
# Inject processor_config_{name} into WatchBase if the schema is defined
|
||||
schema_key = f'processor_config_{proc_name}'
|
||||
if schema_key in proc_schemas:
|
||||
spec_dict['components']['schemas']['WatchBase']['properties'][schema_key] = {
|
||||
'$ref': f'#/components/schemas/{schema_key}'
|
||||
}
|
||||
# Append x-code-samples from processor paths into existing path operations
|
||||
for path, path_item in proc_spec.get('paths', {}).items():
|
||||
if path not in spec_dict.get('paths', {}):
|
||||
continue
|
||||
for method, operation in path_item.items():
|
||||
if method not in spec_dict['paths'][path]:
|
||||
continue
|
||||
if 'x-code-samples' in operation:
|
||||
existing = spec_dict['paths'][path][method].get('x-code-samples', [])
|
||||
spec_dict['paths'][path][method]['x-code-samples'] = existing + operation['x-code-samples']
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to merge processor API specs: {e}")
|
||||
|
||||
return spec_dict
|
||||
|
||||
|
||||
@functools.cache
|
||||
def get_openapi_spec():
|
||||
"""Lazy load OpenAPI spec and dependencies only when validation is needed."""
|
||||
from openapi_core import OpenAPI # Lazy import - saves ~10.7 MB on startup
|
||||
return OpenAPI.from_dict(build_merged_spec_dict())
|
||||
|
||||
@functools.cache
|
||||
def get_openapi_schema_dict():
|
||||
"""
|
||||
Get the raw OpenAPI spec dictionary for schema access.
|
||||
|
||||
Used by Import endpoint to validate and convert query parameters.
|
||||
Returns the merged YAML dict (not the OpenAPI object).
|
||||
"""
|
||||
return build_merged_spec_dict()
|
||||
return yaml.safe_load(f)
|
||||
|
||||
@functools.cache
|
||||
def _resolve_schema_properties(schema_name):
|
||||
@@ -144,7 +103,6 @@ def validate_openapi_request(operation_id):
|
||||
if request.method.upper() != 'GET':
|
||||
# Lazy import - only loaded when actually validating a request
|
||||
from openapi_core.contrib.flask import FlaskOpenAPIRequest
|
||||
from openapi_core.templating.paths.exceptions import ServerNotFound, PathNotFound, PathError
|
||||
|
||||
spec = get_openapi_spec()
|
||||
openapi_request = FlaskOpenAPIRequest(request)
|
||||
@@ -152,16 +110,6 @@ def validate_openapi_request(operation_id):
|
||||
if result.errors:
|
||||
error_details = []
|
||||
for error in result.errors:
|
||||
# Skip path/server validation errors for reverse proxy compatibility
|
||||
# Flask routing already validates that endpoints exist (returns 404 if not).
|
||||
# OpenAPI validation here is primarily for request body schema validation.
|
||||
# When behind nginx/reverse proxy, URLs may have path prefixes that don't
|
||||
# match the OpenAPI server definitions, causing false positives.
|
||||
if isinstance(error, PathError):
|
||||
logger.debug(f"API Call - Skipping path/server validation (delegated to Flask): {error}")
|
||||
continue
|
||||
|
||||
error_str = str(error)
|
||||
# Extract detailed schema errors from __cause__
|
||||
if hasattr(error, '__cause__') and hasattr(error.__cause__, 'schema_errors'):
|
||||
for schema_error in error.__cause__.schema_errors:
|
||||
@@ -169,12 +117,9 @@ def validate_openapi_request(operation_id):
|
||||
msg = schema_error.message if hasattr(schema_error, 'message') else str(schema_error)
|
||||
error_details.append(f"{field}: {msg}")
|
||||
else:
|
||||
error_details.append(error_str)
|
||||
|
||||
# Only raise if we have actual validation errors (not path/server issues)
|
||||
if error_details:
|
||||
error_details.append(str(error))
|
||||
logger.error(f"API Call - Validation failed: {'; '.join(error_details)}")
|
||||
raise BadRequest(f"Validation failed: {'; '.join(error_details)}")
|
||||
raise BadRequest(f"Validation failed: {'; '.join(error_details)}")
|
||||
except BadRequest:
|
||||
# Re-raise BadRequest exceptions (validation failures)
|
||||
raise
|
||||
@@ -191,6 +136,5 @@ from .Watch import Watch, WatchHistory, WatchSingleHistory, WatchHistoryDiff, Cr
|
||||
from .Tags import Tags, Tag
|
||||
from .Import import Import
|
||||
from .SystemInfo import SystemInfo
|
||||
from .Spec import Spec
|
||||
from .Notifications import Notifications
|
||||
|
||||
|
||||
@@ -13,7 +13,7 @@ from loguru import logger
|
||||
BACKUP_FILENAME_FORMAT = "changedetection-backup-{}.zip"
|
||||
|
||||
|
||||
def create_backup(datastore_path, watches: dict, tags: dict = None):
|
||||
def create_backup(datastore_path, watches: dict):
|
||||
logger.debug("Creating backup...")
|
||||
import zipfile
|
||||
from pathlib import Path
|
||||
@@ -40,14 +40,10 @@ def create_backup(datastore_path, watches: dict, tags: dict = None):
|
||||
zipObj.write(url_watches_json, arcname="url-watches.json")
|
||||
logger.debug("Added url-watches.json to backup")
|
||||
|
||||
# Add tag data directories (each tag has its own {uuid}/tag.json)
|
||||
for uuid, tag in (tags or {}).items():
|
||||
for f in Path(tag.data_dir).glob('*'):
|
||||
zipObj.write(f,
|
||||
arcname=os.path.join(f.parts[-2], f.parts[-1]),
|
||||
compress_type=zipfile.ZIP_DEFLATED,
|
||||
compresslevel=8)
|
||||
logger.debug(f"Added tag '{tag.get('title')}' ({uuid}) to backup")
|
||||
# Add the flask app secret (if it exists)
|
||||
secret_file = os.path.join(datastore_path, "secret.txt")
|
||||
if os.path.isfile(secret_file):
|
||||
zipObj.write(secret_file, arcname="secret.txt")
|
||||
|
||||
# Add any data in the watch data directory.
|
||||
for uuid, w in watches.items():
|
||||
@@ -92,28 +88,24 @@ def create_backup(datastore_path, watches: dict, tags: dict = None):
|
||||
|
||||
|
||||
def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
from .restore import construct_restore_blueprint
|
||||
|
||||
backups_blueprint = Blueprint('backups', __name__, template_folder="templates")
|
||||
backups_blueprint.register_blueprint(construct_restore_blueprint(datastore))
|
||||
backup_threads = []
|
||||
|
||||
@backups_blueprint.route("/request-backup", methods=['GET'])
|
||||
@login_optionally_required
|
||||
@backups_blueprint.route("/request-backup", methods=['GET'])
|
||||
def request_backup():
|
||||
if any(thread.is_alive() for thread in backup_threads):
|
||||
flash(gettext("A backup is already running, check back in a few minutes"), "error")
|
||||
return redirect(url_for('backups.create'))
|
||||
return redirect(url_for('backups.index'))
|
||||
|
||||
if len(find_backups()) > int(os.getenv("MAX_NUMBER_BACKUPS", 100)):
|
||||
flash(gettext("Maximum number of backups reached, please remove some"), "error")
|
||||
return redirect(url_for('backups.create'))
|
||||
return redirect(url_for('backups.index'))
|
||||
|
||||
# With immediate persistence, all data is already saved
|
||||
zip_thread = threading.Thread(
|
||||
target=create_backup,
|
||||
args=(datastore.datastore_path, datastore.data.get("watching")),
|
||||
kwargs={'tags': datastore.data['settings']['application'].get('tags', {})},
|
||||
daemon=True,
|
||||
name="BackupCreator"
|
||||
)
|
||||
@@ -121,7 +113,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
backup_threads.append(zip_thread)
|
||||
flash(gettext("Backup building in background, check back in a few minutes."))
|
||||
|
||||
return redirect(url_for('backups.create'))
|
||||
return redirect(url_for('backups.index'))
|
||||
|
||||
def find_backups():
|
||||
backup_filepath = os.path.join(datastore.datastore_path, BACKUP_FILENAME_FORMAT.format("*"))
|
||||
@@ -141,43 +133,40 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
|
||||
return backup_info
|
||||
|
||||
@backups_blueprint.route("/download/<string:filename>", methods=['GET'])
|
||||
@login_optionally_required
|
||||
@backups_blueprint.route("/download/<string:filename>", methods=['GET'])
|
||||
def download_backup(filename):
|
||||
import re
|
||||
filename = filename.strip()
|
||||
backup_filename_regex = BACKUP_FILENAME_FORMAT.format(r"\d+")
|
||||
backup_filename_regex = BACKUP_FILENAME_FORMAT.format("\d+")
|
||||
|
||||
full_path = os.path.join(os.path.abspath(datastore.datastore_path), filename)
|
||||
if not full_path.startswith(os.path.abspath(datastore.datastore_path)):
|
||||
abort(404)
|
||||
|
||||
# Resolve 'latest' before any validation so checks run against the real filename.
|
||||
if filename == 'latest':
|
||||
backups = find_backups()
|
||||
if not backups:
|
||||
abort(404)
|
||||
filename = backups[0]['filename']
|
||||
|
||||
if not re.match(r"^" + backup_filename_regex + "$", filename):
|
||||
abort(400) # Bad Request if the filename doesn't match the pattern
|
||||
|
||||
full_path = os.path.join(os.path.abspath(datastore.datastore_path), filename)
|
||||
if not full_path.startswith(os.path.abspath(datastore.datastore_path) + os.sep):
|
||||
abort(404)
|
||||
|
||||
logger.debug(f"Backup download request for '{full_path}'")
|
||||
return send_from_directory(os.path.abspath(datastore.datastore_path), filename, as_attachment=True)
|
||||
|
||||
@backups_blueprint.route("/", methods=['GET'])
|
||||
@backups_blueprint.route("/create", methods=['GET'])
|
||||
@login_optionally_required
|
||||
def create():
|
||||
@backups_blueprint.route("", methods=['GET'])
|
||||
def index():
|
||||
backups = find_backups()
|
||||
output = render_template("backup_create.html",
|
||||
output = render_template("overview.html",
|
||||
available_backups=backups,
|
||||
backup_running=any(thread.is_alive() for thread in backup_threads)
|
||||
)
|
||||
|
||||
return output
|
||||
|
||||
@backups_blueprint.route("/remove-backups", methods=['GET'])
|
||||
@login_optionally_required
|
||||
@backups_blueprint.route("/remove-backups", methods=['GET'])
|
||||
def remove_backups():
|
||||
|
||||
backup_filepath = os.path.join(datastore.datastore_path, BACKUP_FILENAME_FORMAT.format("*"))
|
||||
@@ -187,6 +176,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
|
||||
flash(gettext("Backups were deleted."))
|
||||
|
||||
return redirect(url_for('backups.create'))
|
||||
return redirect(url_for('backups.index'))
|
||||
|
||||
return backups_blueprint
|
||||
|
||||
@@ -1,248 +0,0 @@
|
||||
import io
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import shutil
|
||||
import tempfile
|
||||
import threading
|
||||
import zipfile
|
||||
|
||||
from flask import Blueprint, render_template, flash, url_for, redirect, request
|
||||
from flask_babel import gettext, lazy_gettext as _l
|
||||
from wtforms import Form, BooleanField, SubmitField
|
||||
from flask_wtf.file import FileField, FileAllowed
|
||||
from loguru import logger
|
||||
|
||||
from changedetectionio.flask_app import login_optionally_required
|
||||
|
||||
# Maximum size of the uploaded zip file. Override via env var MAX_RESTORE_UPLOAD_MB.
|
||||
_MAX_UPLOAD_BYTES = int(os.getenv("MAX_RESTORE_UPLOAD_MB", 256)) * 1024 * 1024
|
||||
# Maximum total uncompressed size of all entries (zip-bomb guard). Override via MAX_RESTORE_DECOMPRESSED_MB.
|
||||
_MAX_DECOMPRESSED_BYTES = int(os.getenv("MAX_RESTORE_DECOMPRESSED_MB", 1024)) * 1024 * 1024
|
||||
# Only top-level directories whose name is a valid UUID are treated as watch/tag entries.
|
||||
_UUID_RE = re.compile(
|
||||
r'^[0-9a-f]{8}-[0-9a-f]{4}-4[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$',
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
|
||||
class RestoreForm(Form):
|
||||
zip_file = FileField(_l('Backup zip file'), validators=[
|
||||
FileAllowed(['zip'], _l('Must be a .zip backup file!'))
|
||||
])
|
||||
include_groups = BooleanField(_l('Include groups'), default=True)
|
||||
include_groups_replace_existing = BooleanField(_l('Replace existing groups of the same UUID'), default=True)
|
||||
include_watches = BooleanField(_l('Include watches'), default=True)
|
||||
include_watches_replace_existing = BooleanField(_l('Replace existing watches of the same UUID'), default=True)
|
||||
submit = SubmitField(_l('Restore backup'))
|
||||
|
||||
|
||||
def import_from_zip(zip_stream, datastore, include_groups, include_groups_replace, include_watches, include_watches_replace):
|
||||
"""
|
||||
Extract and import watches and groups from a backup zip stream.
|
||||
|
||||
Mirrors the store's _load_watches / _load_tags loading pattern:
|
||||
- UUID dirs with tag.json → Tag.model + tag_obj.commit()
|
||||
- UUID dirs with watch.json → rehydrate_entity + watch_obj.commit()
|
||||
|
||||
Returns a dict with counts: restored_groups, skipped_groups, restored_watches, skipped_watches.
|
||||
Raises zipfile.BadZipFile if the stream is not a valid zip.
|
||||
"""
|
||||
from changedetectionio.model import Tag
|
||||
|
||||
restored_groups = 0
|
||||
skipped_groups = 0
|
||||
restored_watches = 0
|
||||
skipped_watches = 0
|
||||
|
||||
current_tags = datastore.data['settings']['application'].get('tags', {})
|
||||
current_watches = datastore.data['watching']
|
||||
|
||||
with tempfile.TemporaryDirectory() as tmpdir:
|
||||
logger.debug(f"Restore: extracting zip to {tmpdir}")
|
||||
with zipfile.ZipFile(zip_stream, 'r') as zf:
|
||||
total_uncompressed = sum(m.file_size for m in zf.infolist())
|
||||
if total_uncompressed > _MAX_DECOMPRESSED_BYTES:
|
||||
raise ValueError(
|
||||
f"Backup archive decompressed size ({total_uncompressed // (1024 * 1024)} MB) "
|
||||
f"exceeds the {_MAX_DECOMPRESSED_BYTES // (1024 * 1024)} MB limit"
|
||||
)
|
||||
resolved_dest = os.path.realpath(tmpdir)
|
||||
for member in zf.infolist():
|
||||
member_dest = os.path.realpath(os.path.join(resolved_dest, member.filename))
|
||||
if not member_dest.startswith(resolved_dest + os.sep) and member_dest != resolved_dest:
|
||||
raise ValueError(f"Zip Slip path traversal detected in backup archive: {member.filename!r}")
|
||||
zf.extract(member, tmpdir)
|
||||
logger.debug("Restore: zip extracted, scanning UUID directories")
|
||||
|
||||
for entry in os.scandir(tmpdir):
|
||||
if not entry.is_dir():
|
||||
continue
|
||||
|
||||
uuid = entry.name
|
||||
if not _UUID_RE.match(uuid):
|
||||
logger.warning(f"Restore: skipping non-UUID directory {uuid!r}")
|
||||
continue
|
||||
tag_json_path = os.path.join(entry.path, 'tag.json')
|
||||
watch_json_path = os.path.join(entry.path, 'watch.json')
|
||||
|
||||
# --- Tags (groups) ---
|
||||
if include_groups and os.path.exists(tag_json_path):
|
||||
if uuid in current_tags and not include_groups_replace:
|
||||
logger.debug(f"Restore: skipping existing group {uuid} (replace not requested)")
|
||||
skipped_groups += 1
|
||||
continue
|
||||
|
||||
try:
|
||||
with open(tag_json_path, 'r', encoding='utf-8') as f:
|
||||
tag_data = json.load(f)
|
||||
except (json.JSONDecodeError, IOError) as e:
|
||||
logger.error(f"Restore: failed to read tag.json for {uuid}: {e}")
|
||||
continue
|
||||
|
||||
title = tag_data.get('title', uuid)
|
||||
logger.debug(f"Restore: importing group '{title}' ({uuid})")
|
||||
|
||||
# Mirror _load_tags: set uuid and force processor
|
||||
tag_data['uuid'] = uuid
|
||||
tag_data['processor'] = 'restock_diff'
|
||||
|
||||
# Copy the UUID directory so data_dir exists for commit()
|
||||
dst_dir = os.path.join(datastore.datastore_path, uuid)
|
||||
if os.path.exists(dst_dir):
|
||||
shutil.rmtree(dst_dir)
|
||||
shutil.copytree(entry.path, dst_dir)
|
||||
|
||||
tag_obj = Tag.model(
|
||||
datastore_path=datastore.datastore_path,
|
||||
__datastore=datastore.data,
|
||||
default=tag_data
|
||||
)
|
||||
current_tags[uuid] = tag_obj
|
||||
tag_obj.commit()
|
||||
restored_groups += 1
|
||||
logger.success(f"Restore: group '{title}' ({uuid}) restored")
|
||||
|
||||
# --- Watches ---
|
||||
elif include_watches and os.path.exists(watch_json_path):
|
||||
if uuid in current_watches and not include_watches_replace:
|
||||
logger.debug(f"Restore: skipping existing watch {uuid} (replace not requested)")
|
||||
skipped_watches += 1
|
||||
continue
|
||||
|
||||
try:
|
||||
with open(watch_json_path, 'r', encoding='utf-8') as f:
|
||||
watch_data = json.load(f)
|
||||
except (json.JSONDecodeError, IOError) as e:
|
||||
logger.error(f"Restore: failed to read watch.json for {uuid}: {e}")
|
||||
continue
|
||||
|
||||
url = watch_data.get('url', uuid)
|
||||
logger.debug(f"Restore: importing watch '{url}' ({uuid})")
|
||||
|
||||
# Copy UUID directory first so data_dir and history files exist
|
||||
dst_dir = os.path.join(datastore.datastore_path, uuid)
|
||||
if os.path.exists(dst_dir):
|
||||
shutil.rmtree(dst_dir)
|
||||
shutil.copytree(entry.path, dst_dir)
|
||||
|
||||
# Mirror _load_watches / rehydrate_entity
|
||||
watch_data['uuid'] = uuid
|
||||
watch_obj = datastore.rehydrate_entity(uuid, watch_data)
|
||||
current_watches[uuid] = watch_obj
|
||||
watch_obj.commit()
|
||||
restored_watches += 1
|
||||
logger.success(f"Restore: watch '{url}' ({uuid}) restored")
|
||||
|
||||
logger.debug(f"Restore: scan complete - groups {restored_groups} restored / {skipped_groups} skipped, "
|
||||
f"watches {restored_watches} restored / {skipped_watches} skipped")
|
||||
|
||||
# Persist changedetection.json (includes the updated tags dict)
|
||||
logger.debug("Restore: committing datastore settings")
|
||||
datastore.commit()
|
||||
|
||||
return {
|
||||
'restored_groups': restored_groups,
|
||||
'skipped_groups': skipped_groups,
|
||||
'restored_watches': restored_watches,
|
||||
'skipped_watches': skipped_watches,
|
||||
}
|
||||
|
||||
|
||||
|
||||
def construct_restore_blueprint(datastore):
|
||||
restore_blueprint = Blueprint('restore', __name__, template_folder="templates")
|
||||
restore_threads = []
|
||||
|
||||
@restore_blueprint.route("/restore", methods=['GET'])
|
||||
@login_optionally_required
|
||||
def restore():
|
||||
form = RestoreForm()
|
||||
return render_template("backup_restore.html",
|
||||
form=form,
|
||||
restore_running=any(t.is_alive() for t in restore_threads),
|
||||
max_upload_mb=_MAX_UPLOAD_BYTES // (1024 * 1024),
|
||||
max_decompressed_mb=_MAX_DECOMPRESSED_BYTES // (1024 * 1024))
|
||||
|
||||
@restore_blueprint.route("/restore/start", methods=['POST'])
|
||||
@login_optionally_required
|
||||
def backups_restore_start():
|
||||
if any(t.is_alive() for t in restore_threads):
|
||||
flash(gettext("A restore is already running, check back in a few minutes"), "error")
|
||||
return redirect(url_for('backups.restore.restore'))
|
||||
|
||||
zip_file = request.files.get('zip_file')
|
||||
if not zip_file or not zip_file.filename:
|
||||
flash(gettext("No file uploaded"), "error")
|
||||
return redirect(url_for('backups.restore.restore'))
|
||||
|
||||
if not zip_file.filename.lower().endswith('.zip'):
|
||||
flash(gettext("File must be a .zip backup file"), "error")
|
||||
return redirect(url_for('backups.restore.restore'))
|
||||
|
||||
# Reject oversized uploads before reading the stream into memory.
|
||||
content_length = request.content_length
|
||||
if content_length and content_length > _MAX_UPLOAD_BYTES:
|
||||
flash(gettext("Backup file is too large (max %(mb)s MB)", mb=_MAX_UPLOAD_BYTES // (1024 * 1024)), "error")
|
||||
return redirect(url_for('backups.restore.restore'))
|
||||
|
||||
# Read into memory now — the request stream is gone once we return.
|
||||
# Read one byte beyond the limit so we can detect truncated-but-still-oversized streams.
|
||||
try:
|
||||
raw = zip_file.read(_MAX_UPLOAD_BYTES + 1)
|
||||
if len(raw) > _MAX_UPLOAD_BYTES:
|
||||
flash(gettext("Backup file is too large (max %(mb)s MB)", mb=_MAX_UPLOAD_BYTES // (1024 * 1024)), "error")
|
||||
return redirect(url_for('backups.restore.restore'))
|
||||
zip_bytes = io.BytesIO(raw)
|
||||
with zipfile.ZipFile(zip_bytes): # quick validity check before spawning
|
||||
pass
|
||||
zip_bytes.seek(0)
|
||||
except zipfile.BadZipFile:
|
||||
flash(gettext("Invalid or corrupted zip file"), "error")
|
||||
return redirect(url_for('backups.restore.restore'))
|
||||
|
||||
include_groups = request.form.get('include_groups') == 'y'
|
||||
include_groups_replace = request.form.get('include_groups_replace_existing') == 'y'
|
||||
include_watches = request.form.get('include_watches') == 'y'
|
||||
include_watches_replace = request.form.get('include_watches_replace_existing') == 'y'
|
||||
|
||||
restore_thread = threading.Thread(
|
||||
target=import_from_zip,
|
||||
kwargs={
|
||||
'zip_stream': zip_bytes,
|
||||
'datastore': datastore,
|
||||
'include_groups': include_groups,
|
||||
'include_groups_replace': include_groups_replace,
|
||||
'include_watches': include_watches,
|
||||
'include_watches_replace': include_watches_replace,
|
||||
},
|
||||
daemon=True,
|
||||
name="BackupRestore"
|
||||
)
|
||||
restore_thread.start()
|
||||
restore_threads[:] = [t for t in restore_threads if t.is_alive()]
|
||||
restore_threads.append(restore_thread)
|
||||
flash(gettext("Restore started in background, check back in a few minutes."))
|
||||
return redirect(url_for('backups.restore.restore'))
|
||||
|
||||
return restore_blueprint
|
||||
@@ -1,49 +0,0 @@
|
||||
{% extends 'base.html' %}
|
||||
{% block content %}
|
||||
{% from '_helpers.html' import render_simple_field, render_field %}
|
||||
|
||||
<div class="edit-form">
|
||||
<div class="tabs collapsable">
|
||||
<ul>
|
||||
<li class="tab active" id=""><a href="{{ url_for('backups.create') }}">{{ _('Create') }}</a></li>
|
||||
<li class="tab"><a href="{{ url_for('backups.restore.restore') }}">{{ _('Restore') }}</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="box-wrap inner">
|
||||
<div id="general">
|
||||
{% if backup_running %}
|
||||
<p>
|
||||
<span class="spinner"></span> <strong>{{ _('A backup is running!') }}</strong>
|
||||
</p>
|
||||
{% endif %}
|
||||
|
||||
<p>
|
||||
{{ _('Here you can download and request a new backup, when a backup is completed you will see it listed below.') }}
|
||||
</p>
|
||||
<br>
|
||||
{% if available_backups %}
|
||||
<ul>
|
||||
{% for backup in available_backups %}
|
||||
<li>
|
||||
<a href="{{ url_for('backups.download_backup', filename=backup["filename"]) }}">{{ backup["filename"] }}</a> {{ backup["filesize"] }} {{ _('Mb') }}
|
||||
</li>
|
||||
{% endfor %}
|
||||
</ul>
|
||||
{% else %}
|
||||
<p>
|
||||
<strong>{{ _('No backups found.') }}</strong>
|
||||
</p>
|
||||
{% endif %}
|
||||
|
||||
<a class="pure-button pure-button-primary"
|
||||
href="{{ url_for('backups.request_backup') }}">{{ _('Create backup') }}</a>
|
||||
{% if available_backups %}
|
||||
<a class="pure-button button-small button-error "
|
||||
href="{{ url_for('backups.remove_backups') }}">{{ _('Remove backups') }}</a>
|
||||
{% endif %}
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
{% endblock %}
|
||||
@@ -1,61 +0,0 @@
|
||||
{% extends 'base.html' %}
|
||||
{% block content %}
|
||||
{% from '_helpers.html' import render_field, render_checkbox_field %}
|
||||
|
||||
<div class="edit-form">
|
||||
<div class="tabs collapsable">
|
||||
<ul>
|
||||
<li class="tab"><a href="{{ url_for('backups.create') }}">{{ _('Create') }}</a></li>
|
||||
<li class="tab active"><a href="{{ url_for('backups.restore.restore') }}">{{ _('Restore') }}</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="box-wrap inner">
|
||||
<div id="general">
|
||||
{% if restore_running %}
|
||||
<p>
|
||||
<span class="spinner"></span> <strong>{{ _('A restore is running!') }}</strong>
|
||||
</p>
|
||||
{% endif %}
|
||||
|
||||
<p>{{ _('Restore a backup. Must be a .zip backup file created on/after v0.53.1 (new database layout).') }}</p>
|
||||
<p>{{ _('Note: This does not override the main application settings, only watches and groups.') }}</p>
|
||||
<p class="pure-form-message">
|
||||
{{ _('Max upload size: %(upload)s MB, Max decompressed size: %(decomp)s MB', upload=max_upload_mb, decomp=max_decompressed_mb) }}
|
||||
</p>
|
||||
|
||||
<form class="pure-form pure-form-stacked settings"
|
||||
action="{{ url_for('backups.restore.backups_restore_start') }}"
|
||||
method="POST"
|
||||
enctype="multipart/form-data">
|
||||
<input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
|
||||
|
||||
<div class="pure-control-group">
|
||||
{{ render_checkbox_field(form.include_groups) }}
|
||||
<span class="pure-form-message-inline">{{ _('Include all groups found in backup?') }}</span>
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
{{ render_checkbox_field(form.include_groups_replace_existing) }}
|
||||
<span class="pure-form-message-inline">{{ _('Replace any existing groups of the same UUID?') }}</span>
|
||||
</div>
|
||||
|
||||
<div class="pure-control-group">
|
||||
{{ render_checkbox_field(form.include_watches) }}
|
||||
<span class="pure-form-message-inline">{{ _('Include all watches found in backup?') }}</span>
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
{{ render_checkbox_field(form.include_watches_replace_existing) }}
|
||||
<span class="pure-form-message-inline">{{ _('Replace any existing watches of the same UUID?') }}</span>
|
||||
</div>
|
||||
|
||||
<div class="pure-control-group">
|
||||
{{ render_field(form.zip_file) }}
|
||||
</div>
|
||||
|
||||
<div class="pure-controls">
|
||||
<button type="submit" class="pure-button pure-button-primary">{{ _('Restore backup') }}</button>
|
||||
</div>
|
||||
</form>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
{% endblock %}
|
||||
@@ -0,0 +1,36 @@
|
||||
{% extends 'base.html' %}
|
||||
{% block content %}
|
||||
{% from '_helpers.html' import render_simple_field, render_field %}
|
||||
<div class="edit-form">
|
||||
<div class="box-wrap inner">
|
||||
<h2>{{ _('Backups') }}</h2>
|
||||
{% if backup_running %}
|
||||
<p>
|
||||
<span class="spinner"></span> <strong>{{ _('A backup is running!') }}</strong>
|
||||
</p>
|
||||
{% endif %}
|
||||
<p>
|
||||
{{ _('Here you can download and request a new backup, when a backup is completed you will see it listed below.') }}
|
||||
</p>
|
||||
<br>
|
||||
{% if available_backups %}
|
||||
<ul>
|
||||
{% for backup in available_backups %}
|
||||
<li><a href="{{ url_for('backups.download_backup', filename=backup["filename"]) }}">{{ backup["filename"] }}</a> {{ backup["filesize"] }} {{ _('Mb') }}</li>
|
||||
{% endfor %}
|
||||
</ul>
|
||||
{% else %}
|
||||
<p>
|
||||
<strong>{{ _('No backups found.') }}</strong>
|
||||
</p>
|
||||
{% endif %}
|
||||
|
||||
<a class="pure-button pure-button-primary" href="{{ url_for('backups.request_backup') }}">{{ _('Create backup') }}</a>
|
||||
{% if available_backups %}
|
||||
<a class="pure-button button-small button-error " href="{{ url_for('backups.remove_backups') }}">{{ _('Remove backups') }}</a>
|
||||
{% endif %}
|
||||
</div>
|
||||
</div>
|
||||
|
||||
|
||||
{% endblock %}
|
||||
@@ -102,35 +102,6 @@ def run_async_in_browser_loop(coro):
|
||||
else:
|
||||
raise RuntimeError("Browser steps event loop is not available")
|
||||
|
||||
async def _close_session_resources(session_data, label=''):
|
||||
"""Close all browser resources for a session in the correct order.
|
||||
|
||||
browserstepper.cleanup() closes page+context but not the browser itself.
|
||||
For CloakBrowser, browser.close() is what stops the local Chromium process via pw.stop().
|
||||
For the default CDP path, playwright_context.stop() shuts down the playwright instance.
|
||||
"""
|
||||
browserstepper = session_data.get('browserstepper')
|
||||
if browserstepper:
|
||||
try:
|
||||
await browserstepper.cleanup()
|
||||
except Exception as e:
|
||||
logger.error(f"Error cleaning up browserstepper{label}: {e}")
|
||||
|
||||
browser = session_data.get('browser')
|
||||
if browser:
|
||||
try:
|
||||
await asyncio.wait_for(browser.close(), timeout=5.0)
|
||||
except Exception as e:
|
||||
logger.warning(f"Error closing browser{label}: {e}")
|
||||
|
||||
playwright_context = session_data.get('playwright_context')
|
||||
if playwright_context:
|
||||
try:
|
||||
await playwright_context.stop()
|
||||
except Exception as e:
|
||||
logger.warning(f"Error stopping playwright context{label}: {e}")
|
||||
|
||||
|
||||
def cleanup_expired_sessions():
|
||||
"""Remove expired browsersteps sessions and cleanup their resources"""
|
||||
global browsersteps_sessions, browsersteps_watch_to_session
|
||||
@@ -148,10 +119,13 @@ def cleanup_expired_sessions():
|
||||
logger.debug(f"Cleaning up expired browsersteps session {session_id}")
|
||||
session_data = browsersteps_sessions[session_id]
|
||||
|
||||
try:
|
||||
run_async_in_browser_loop(_close_session_resources(session_data, label=f" for session {session_id}"))
|
||||
except Exception as e:
|
||||
logger.error(f"Error cleaning up session {session_id}: {e}")
|
||||
# Cleanup playwright resources asynchronously
|
||||
browserstepper = session_data.get('browserstepper')
|
||||
if browserstepper:
|
||||
try:
|
||||
run_async_in_browser_loop(browserstepper.cleanup())
|
||||
except Exception as e:
|
||||
logger.error(f"Error cleaning up session {session_id}: {e}")
|
||||
|
||||
# Remove from sessions dict
|
||||
del browsersteps_sessions[session_id]
|
||||
@@ -178,10 +152,12 @@ def cleanup_session_for_watch(watch_uuid):
|
||||
|
||||
session_data = browsersteps_sessions.get(session_id)
|
||||
if session_data:
|
||||
try:
|
||||
run_async_in_browser_loop(_close_session_resources(session_data, label=f" for watch {watch_uuid}"))
|
||||
except Exception as e:
|
||||
logger.error(f"Error cleaning up session {session_id} for watch {watch_uuid}: {e}")
|
||||
browserstepper = session_data.get('browserstepper')
|
||||
if browserstepper:
|
||||
try:
|
||||
run_async_in_browser_loop(browserstepper.cleanup())
|
||||
except Exception as e:
|
||||
logger.error(f"Error cleaning up session {session_id} for watch {watch_uuid}: {e}")
|
||||
|
||||
# Remove from sessions dict
|
||||
del browsersteps_sessions[session_id]
|
||||
@@ -198,80 +174,71 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
browser_steps_blueprint = Blueprint('browser_steps', __name__, template_folder="templates")
|
||||
|
||||
async def start_browsersteps_session(watch_uuid):
|
||||
from changedetectionio.browser_steps import browser_steps
|
||||
from . import browser_steps
|
||||
import time
|
||||
from playwright.async_api import async_playwright
|
||||
|
||||
# We keep the playwright session open for many minutes
|
||||
keepalive_seconds = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
|
||||
keepalive_ms = ((keepalive_seconds + 3) * 1000)
|
||||
|
||||
browsersteps_start_session = {'start_time': time.time()}
|
||||
|
||||
# Build proxy dict first — needed by both the CDP path and fetcher-specific launchers
|
||||
proxy_id = datastore.get_preferred_proxy_for_watch(uuid=watch_uuid)
|
||||
proxy = None
|
||||
if proxy_id:
|
||||
proxy_url = datastore.proxy_list.get(proxy_id, {}).get('url')
|
||||
if proxy_url:
|
||||
from urllib.parse import urlparse
|
||||
parsed = urlparse(proxy_url)
|
||||
proxy = {'server': proxy_url}
|
||||
if parsed.username:
|
||||
proxy['username'] = parsed.username
|
||||
if parsed.password:
|
||||
proxy['password'] = parsed.password
|
||||
logger.debug(f"Browser Steps: UUID {watch_uuid} selected proxy {proxy_url}")
|
||||
# Create a new async playwright instance for browser steps
|
||||
playwright_instance = async_playwright()
|
||||
playwright_context = await playwright_instance.start()
|
||||
|
||||
# Resolve the fetcher class for this watch so we can ask it to launch its own browser
|
||||
# if it supports that (e.g. CloakBrowser, which runs locally rather than via CDP)
|
||||
watch = datastore.data['watching'][watch_uuid]
|
||||
from changedetectionio import content_fetchers
|
||||
fetcher_name = watch.get_fetch_backend or 'system'
|
||||
if fetcher_name == 'system':
|
||||
fetcher_name = datastore.data['settings']['application'].get('fetch_backend', 'html_requests')
|
||||
fetcher_class = getattr(content_fetchers, fetcher_name, None)
|
||||
|
||||
browser = None
|
||||
playwright_context = None
|
||||
|
||||
# If the fetcher has its own browser launch for the live steps UI, use it.
|
||||
# get_browsersteps_browser(proxy, keepalive_ms) returns (browser, playwright_context_or_None)
|
||||
# or None to fall back to the default CDP path.
|
||||
if fetcher_class and hasattr(fetcher_class, 'get_browsersteps_browser'):
|
||||
result = await fetcher_class.get_browsersteps_browser(proxy=proxy, keepalive_ms=keepalive_ms)
|
||||
if result is not None:
|
||||
browser, playwright_context = result
|
||||
logger.debug(f"Browser Steps: using fetcher-specific browser for '{fetcher_name}'")
|
||||
|
||||
# Default: connect to the remote Playwright/sockpuppetbrowser via CDP
|
||||
if browser is None:
|
||||
playwright_instance = async_playwright()
|
||||
playwright_context = await playwright_instance.start()
|
||||
base_url = os.getenv('PLAYWRIGHT_DRIVER_URL', '').strip('"')
|
||||
a = "?" if '?' not in base_url else '&'
|
||||
base_url += a + f"timeout={keepalive_ms}"
|
||||
browser = await playwright_context.chromium.connect_over_cdp(base_url, timeout=keepalive_ms)
|
||||
logger.debug(f"Browser Steps: using CDP connection to {base_url}")
|
||||
keepalive_ms = ((keepalive_seconds + 3) * 1000)
|
||||
base_url = os.getenv('PLAYWRIGHT_DRIVER_URL', '').strip('"')
|
||||
a = "?" if not '?' in base_url else '&'
|
||||
base_url += a + f"timeout={keepalive_ms}"
|
||||
|
||||
browser = await playwright_context.chromium.connect_over_cdp(base_url, timeout=keepalive_ms)
|
||||
browsersteps_start_session['browser'] = browser
|
||||
browsersteps_start_session['playwright_context'] = playwright_context
|
||||
|
||||
proxy_id = datastore.get_preferred_proxy_for_watch(uuid=watch_uuid)
|
||||
proxy = None
|
||||
if proxy_id:
|
||||
proxy_url = datastore.proxy_list.get(proxy_id).get('url')
|
||||
if proxy_url:
|
||||
|
||||
# Playwright needs separate username and password values
|
||||
from urllib.parse import urlparse
|
||||
parsed = urlparse(proxy_url)
|
||||
proxy = {'server': proxy_url}
|
||||
|
||||
if parsed.username:
|
||||
proxy['username'] = parsed.username
|
||||
|
||||
if parsed.password:
|
||||
proxy['password'] = parsed.password
|
||||
|
||||
logger.debug(f"Browser Steps: UUID {watch_uuid} selected proxy {proxy_url}")
|
||||
|
||||
# Tell Playwright to connect to Chrome and setup a new session via our stepper interface
|
||||
browserstepper = browser_steps.browsersteps_live_ui(
|
||||
playwright_browser=browser,
|
||||
proxy=proxy,
|
||||
start_url=watch.link,
|
||||
headers=watch.get('headers')
|
||||
start_url=datastore.data['watching'][watch_uuid].link,
|
||||
headers=datastore.data['watching'][watch_uuid].get('headers')
|
||||
)
|
||||
|
||||
# Initialize the async connection
|
||||
await browserstepper.connect(proxy=proxy)
|
||||
|
||||
browsersteps_start_session['browserstepper'] = browserstepper
|
||||
|
||||
# For test
|
||||
#await browsersteps_start_session['browserstepper'].action_goto_url(value="http://example.com?time="+str(time.time()))
|
||||
|
||||
return browsersteps_start_session
|
||||
|
||||
|
||||
@browser_steps_blueprint.route("/browsersteps_start_session", methods=['GET'])
|
||||
@login_optionally_required
|
||||
@browser_steps_blueprint.route("/browsersteps_start_session", methods=['GET'])
|
||||
def browsersteps_start_session():
|
||||
# A new session was requested, return sessionID
|
||||
import asyncio
|
||||
import uuid
|
||||
browsersteps_session_id = str(uuid.uuid4())
|
||||
watch_uuid = request.args.get('uuid')
|
||||
@@ -304,8 +271,8 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
logger.debug("Starting connection with playwright - done")
|
||||
return {'browsersteps_session_id': browsersteps_session_id}
|
||||
|
||||
@browser_steps_blueprint.route("/browsersteps_image", methods=['GET'])
|
||||
@login_optionally_required
|
||||
@browser_steps_blueprint.route("/browsersteps_image", methods=['GET'])
|
||||
def browser_steps_fetch_screenshot_image():
|
||||
from flask import (
|
||||
make_response,
|
||||
@@ -330,14 +297,15 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
return make_response('Unable to fetch image, is the URL correct? does the watch exist? does the step_type-n.jpeg exist?', 401)
|
||||
|
||||
# A request for an action was received
|
||||
@browser_steps_blueprint.route("/browsersteps_update", methods=['POST'])
|
||||
@login_optionally_required
|
||||
@browser_steps_blueprint.route("/browsersteps_update", methods=['POST'])
|
||||
def browsersteps_ui_update():
|
||||
import base64
|
||||
import playwright._impl._errors
|
||||
from changedetectionio.blueprint.browser_steps import browser_steps
|
||||
|
||||
remaining = 0
|
||||
remaining =0
|
||||
uuid = request.args.get('uuid')
|
||||
goto_website_url_first_step = request.args.get('goto_website_url_first_step')
|
||||
|
||||
browsersteps_session_id = request.args.get('browsersteps_session_id')
|
||||
|
||||
@@ -348,33 +316,33 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
return make_response('No session exists under that ID', 500)
|
||||
|
||||
is_last_step = False
|
||||
|
||||
# @todo - should always be an existing session
|
||||
if goto_website_url_first_step:
|
||||
logger.debug("Going to site (requested automatically before stepping)..")
|
||||
step_operation = "Goto site"
|
||||
step_selector = None
|
||||
step_optional_value = None
|
||||
else:
|
||||
# Actions - step/apply/etc, do the thing and return state
|
||||
if request.method == 'POST':
|
||||
# @todo - should always be an existing session
|
||||
step_operation = request.form.get('operation')
|
||||
step_selector = request.form.get('selector')
|
||||
step_optional_value = request.form.get('optional_value')
|
||||
is_last_step = strtobool(request.form.get('is_last_step'))
|
||||
|
||||
try:
|
||||
# Run the async call_action method in the dedicated browser steps event loop
|
||||
run_async_in_browser_loop(
|
||||
browsersteps_sessions[browsersteps_session_id]['browserstepper'].call_action(
|
||||
action_name=step_operation,
|
||||
selector=step_selector,
|
||||
optional_value=step_optional_value
|
||||
try:
|
||||
# Run the async call_action method in the dedicated browser steps event loop
|
||||
run_async_in_browser_loop(
|
||||
browsersteps_sessions[browsersteps_session_id]['browserstepper'].call_action(
|
||||
action_name=step_operation,
|
||||
selector=step_selector,
|
||||
optional_value=step_optional_value
|
||||
)
|
||||
)
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Exception when calling step operation {step_operation} {str(e)}")
|
||||
# Try to find something of value to give back to the user
|
||||
return make_response(str(e).splitlines()[0], 401)
|
||||
except Exception as e:
|
||||
logger.error(f"Exception when calling step operation {step_operation} {str(e)}")
|
||||
# Try to find something of value to give back to the user
|
||||
return make_response(str(e).splitlines()[0], 401)
|
||||
|
||||
|
||||
# if not this_session.page:
|
||||
# cleanup_playwright_session()
|
||||
# return make_response('Browser session ran out of time :( Please reload this page.', 401)
|
||||
|
||||
# Screenshots and other info only needed on requesting a step (POST)
|
||||
try:
|
||||
@@ -382,7 +350,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
(screenshot, xpath_data) = run_async_in_browser_loop(
|
||||
browsersteps_sessions[browsersteps_session_id]['browserstepper'].get_current_state()
|
||||
)
|
||||
|
||||
|
||||
if is_last_step:
|
||||
watch = datastore.data['watching'].get(uuid)
|
||||
u = browsersteps_sessions[browsersteps_session_id]['browserstepper'].page.url
|
||||
|
||||
-11
@@ -8,17 +8,6 @@ from changedetectionio.content_fetchers import SCREENSHOT_MAX_HEIGHT_DEFAULT
|
||||
from changedetectionio.content_fetchers.base import manage_user_agent
|
||||
from changedetectionio.jinja2_custom import render as jinja_render
|
||||
|
||||
def browser_steps_get_valid_steps(browser_steps: list):
|
||||
if browser_steps is not None and len(browser_steps):
|
||||
valid_steps = list(filter(
|
||||
lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one'),browser_steps))
|
||||
|
||||
# Just incase they selected Goto site by accident with older JS
|
||||
if valid_steps and valid_steps[0]['operation'] == 'Goto site':
|
||||
del(valid_steps[0])
|
||||
|
||||
return valid_steps
|
||||
return []
|
||||
|
||||
|
||||
# Two flags, tell the JS which of the "Selector" or "Value" field should be enabled in the front end
|
||||
@@ -40,13 +40,12 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
contents = ''
|
||||
now = time.time()
|
||||
try:
|
||||
import asyncio
|
||||
processor_module = importlib.import_module("changedetectionio.processors.text_json_diff.processor")
|
||||
update_handler = processor_module.perform_site_check(datastore=datastore,
|
||||
watch_uuid=uuid
|
||||
)
|
||||
|
||||
asyncio.run(update_handler.call_browser(preferred_proxy_id=preferred_proxy))
|
||||
update_handler.call_browser(preferred_proxy_id=preferred_proxy)
|
||||
# title, size is len contents not len xfer
|
||||
except content_fetcher_exceptions.Non200ErrorCodeReceived as e:
|
||||
if e.status_code == 404:
|
||||
@@ -95,13 +94,13 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
return results
|
||||
|
||||
@login_required
|
||||
@check_proxies_blueprint.route("/<uuid_str:uuid>/status", methods=['GET'])
|
||||
@check_proxies_blueprint.route("/<string:uuid>/status", methods=['GET'])
|
||||
def get_recheck_status(uuid):
|
||||
results = _recalc_check_status(uuid=uuid)
|
||||
return results
|
||||
|
||||
@login_required
|
||||
@check_proxies_blueprint.route("/<uuid_str:uuid>/start", methods=['GET'])
|
||||
@check_proxies_blueprint.route("/<string:uuid>/start", methods=['GET'])
|
||||
def start_check(uuid):
|
||||
|
||||
if not datastore.proxy_list:
|
||||
|
||||
@@ -9,7 +9,6 @@
|
||||
<li class="tab" id=""><a href="#url-list">{{ _('URL List') }}</a></li>
|
||||
<li class="tab"><a href="#distill-io">{{ _('Distill.io') }}</a></li>
|
||||
<li class="tab"><a href="#xlsx">{{ _('.XLSX & Wachete') }}</a></li>
|
||||
<li class="tab"><a href="{{url_for('backups.restore.restore')}}">{{ _('Backup Restore') }}</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
@@ -17,11 +16,6 @@
|
||||
<form class="pure-form" action="{{url_for('imports.import_page')}}" method="POST" enctype="multipart/form-data">
|
||||
<input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
|
||||
<div class="tab-pane-inner" id="url-list">
|
||||
|
||||
<p>
|
||||
{{ _('Restoring changedetection.io backups is in the') }}<a href="{{ url_for('backups.restore.restore') }}"> {{ _('backups section') }}</a>.
|
||||
<br>
|
||||
</p>
|
||||
<div class="pure-control-group">
|
||||
{{ _('Enter one URL per line, and optionally add tags for each URL after a space, delineated by comma (,):') }}
|
||||
<br>
|
||||
@@ -43,6 +37,9 @@
|
||||
</div>
|
||||
|
||||
<div class="tab-pane-inner" id="distill-io">
|
||||
|
||||
|
||||
|
||||
<div class="pure-control-group">
|
||||
{{ _('Copy and Paste your Distill.io watch \'export\' file, this should be a JSON file.') }}<br>
|
||||
{{ _('This is') }} <i>{{ _('experimental') }}</i>, {{ _('supported fields are') }} <code>name</code>, <code>uri</code>, <code>tags</code>, <code>config:selections</code>, {{ _('the rest (including') }} <code>schedule</code>) {{ _('are ignored.') }}
|
||||
@@ -52,6 +49,8 @@
|
||||
{{ _('Be sure to set your default fetcher to Chrome if required.') }}<br>
|
||||
</p>
|
||||
</div>
|
||||
|
||||
|
||||
<textarea name="distill-io" class="pure-input-1-2" style="width: 100%;
|
||||
font-family:monospace;
|
||||
white-space: pre;
|
||||
@@ -115,7 +114,6 @@
|
||||
</div>
|
||||
</div>
|
||||
<button type="submit" class="pure-button pure-input-1-2 pure-button-primary">{{ _('Import') }}</button>
|
||||
|
||||
</form>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -15,7 +15,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q: PriorityQueue
|
||||
price_data_follower_blueprint = Blueprint('price_data_follower', __name__)
|
||||
|
||||
@login_required
|
||||
@price_data_follower_blueprint.route("/<uuid_str:uuid>/accept", methods=['GET'])
|
||||
@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'
|
||||
@@ -25,7 +25,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q: PriorityQueue
|
||||
return redirect(url_for("watchlist.index"))
|
||||
|
||||
@login_required
|
||||
@price_data_follower_blueprint.route("/<uuid_str:uuid>/reject", methods=['GET'])
|
||||
@price_data_follower_blueprint.route("/<string:uuid>/reject", methods=['GET'])
|
||||
def reject(uuid):
|
||||
datastore.data['watching'][uuid]['track_ldjson_price_data'] = PRICE_DATA_TRACK_REJECT
|
||||
datastore.data['watching'][uuid].commit()
|
||||
|
||||
@@ -9,12 +9,11 @@ def construct_single_watch_routes(rss_blueprint, datastore):
|
||||
datastore: The ChangeDetectionStore instance
|
||||
"""
|
||||
|
||||
@rss_blueprint.route("/watch/<uuid_str:uuid>", methods=['GET'])
|
||||
@rss_blueprint.route("/watch/<string:uuid>", methods=['GET'])
|
||||
def rss_single_watch(uuid):
|
||||
import time
|
||||
|
||||
from flask import make_response, request, Response
|
||||
from flask_babel import lazy_gettext as _l
|
||||
from flask import make_response, request
|
||||
from feedgen.feed import FeedGenerator
|
||||
from loguru import logger
|
||||
|
||||
@@ -43,12 +42,12 @@ def construct_single_watch_routes(rss_blueprint, datastore):
|
||||
# Get the watch by UUID
|
||||
watch = datastore.data['watching'].get(uuid)
|
||||
if not watch:
|
||||
return Response(_l("Watch with UUID %(uuid)s not found", uuid=uuid), status=404, mimetype='text/plain')
|
||||
return f"Watch with UUID {uuid} not found", 404
|
||||
|
||||
# Check if watch has at least 2 history snapshots
|
||||
dates = list(watch.history.keys())
|
||||
if len(dates) < 2:
|
||||
return Response(_l("Watch %(uuid)s does not have enough history snapshots to show changes (need at least 2)", uuid=uuid), status=400, mimetype='text/plain')
|
||||
return f"Watch {uuid} does not have enough history snapshots to show changes (need at least 2)", 400
|
||||
|
||||
# Get the number of diffs to include (default: 5)
|
||||
rss_diff_length = datastore.data['settings']['application'].get('rss_diff_length', 5)
|
||||
|
||||
@@ -7,7 +7,7 @@ def construct_tag_routes(rss_blueprint, datastore):
|
||||
datastore: The ChangeDetectionStore instance
|
||||
"""
|
||||
|
||||
@rss_blueprint.route("/tag/<uuid_str:tag_uuid>", methods=['GET'])
|
||||
@rss_blueprint.route("/tag/<string:tag_uuid>", methods=['GET'])
|
||||
def rss_tag_feed(tag_uuid):
|
||||
|
||||
from flask import make_response, request, url_for
|
||||
|
||||
@@ -25,7 +25,7 @@
|
||||
<li class="tab"><a href="#ui-options">{{ _('UI Options') }}</a></li>
|
||||
<li class="tab"><a href="#api">{{ _('API') }}</a></li>
|
||||
<li class="tab"><a href="#rss">{{ _('RSS') }}</a></li>
|
||||
<li class="tab"><a href="{{ url_for('backups.create') }}">{{ _('Backups') }}</a></li>
|
||||
<li class="tab"><a href="{{ url_for('backups.index') }}">{{ _('Backups') }}</a></li>
|
||||
<li class="tab"><a href="#timedate">{{ _('Time & Date') }}</a></li>
|
||||
<li class="tab"><a href="#proxies">{{ _('CAPTCHA & Proxies') }}</a></li>
|
||||
{% if plugin_tabs %}
|
||||
@@ -154,8 +154,9 @@
|
||||
</span>
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
<br>
|
||||
{{ _('Tip:') }} <a href="{{ url_for('settings.settings_page')}}#proxies">{{ _('Connect using Bright Data proxies, find out more here.') }}</a>
|
||||
<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>
|
||||
|
||||
@@ -351,7 +352,7 @@ nav
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<p><strong>{{ _('Tip') }}</strong>: {{ _('"Residential" and "Mobile" proxy type can be more successful than "Data Center" for blocked websites.') }}</p>
|
||||
<p><strong>{{ _('Tip') }}</strong>: {{ _('"Residential" and "Mobile" proxy type can be more successfull than "Data Center" for blocked websites.') }}</p>
|
||||
|
||||
<div class="pure-control-group" id="extra-proxies-setting">
|
||||
{{ render_fieldlist_with_inline_errors(form.requests.form.extra_proxies) }}
|
||||
|
||||
@@ -22,14 +22,11 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
|
||||
tag_count = Counter(tag for watch in datastore.data['watching'].values() if watch.get('tags') for tag in watch['tags'])
|
||||
|
||||
from changedetectionio import processors
|
||||
output = render_template("groups-overview.html",
|
||||
app_rss_token=datastore.data['settings']['application'].get('rss_access_token'),
|
||||
available_tags=sorted_tags,
|
||||
form=add_form,
|
||||
generate_tag_colors=processors.generate_processor_badge_colors,
|
||||
tag_count=tag_count,
|
||||
wcag_text_color=processors.wcag_text_color,
|
||||
)
|
||||
|
||||
return output
|
||||
@@ -57,7 +54,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
|
||||
return redirect(url_for('tags.tags_overview_page'))
|
||||
|
||||
@tags_blueprint.route("/mute/<uuid_str:uuid>", methods=['GET'])
|
||||
@tags_blueprint.route("/mute/<string:uuid>", methods=['GET'])
|
||||
@login_optionally_required
|
||||
def mute(uuid):
|
||||
tag = datastore.data['settings']['application']['tags'].get(uuid)
|
||||
@@ -66,13 +63,24 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
tag.commit()
|
||||
return redirect(url_for('tags.tags_overview_page'))
|
||||
|
||||
@tags_blueprint.route("/delete/<uuid_str:uuid>", methods=['GET'])
|
||||
@tags_blueprint.route("/delete/<string:uuid>", methods=['GET'])
|
||||
@login_optionally_required
|
||||
def delete(uuid):
|
||||
# Delete the tag from settings immediately
|
||||
if datastore.data['settings']['application']['tags'].get(uuid):
|
||||
del datastore.data['settings']['application']['tags'][uuid]
|
||||
|
||||
# Delete tag.json file if it exists
|
||||
import os
|
||||
tag_dir = os.path.join(datastore.datastore_path, uuid)
|
||||
tag_json = os.path.join(tag_dir, "tag.json")
|
||||
if os.path.exists(tag_json):
|
||||
try:
|
||||
os.unlink(tag_json)
|
||||
logger.info(f"Deleted tag.json for tag {uuid}")
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to delete tag.json for tag {uuid}: {e}")
|
||||
|
||||
# Remove tag from all watches in background thread to avoid blocking
|
||||
def remove_tag_background(tag_uuid):
|
||||
"""Background thread to remove tag from watches - discarded after completion."""
|
||||
@@ -93,7 +101,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
flash(gettext("Tag deleted, removing from watches in background"))
|
||||
return redirect(url_for('tags.tags_overview_page'))
|
||||
|
||||
@tags_blueprint.route("/unlink/<uuid_str:uuid>", methods=['GET'])
|
||||
@tags_blueprint.route("/unlink/<string:uuid>", methods=['GET'])
|
||||
@login_optionally_required
|
||||
def unlink(uuid):
|
||||
# Unlink tag from all watches in background thread to avoid blocking
|
||||
@@ -119,11 +127,19 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
@tags_blueprint.route("/delete_all", methods=['GET'])
|
||||
@login_optionally_required
|
||||
def delete_all():
|
||||
|
||||
# Delete all tag.json files
|
||||
import os
|
||||
for tag_uuid in list(datastore.data['settings']['application']['tags'].keys()):
|
||||
# TagsDict 'del' handler will remove the dir
|
||||
del datastore.data['settings']['application']['tags'][tag_uuid]
|
||||
tag_dir = os.path.join(datastore.datastore_path, tag_uuid)
|
||||
tag_json = os.path.join(tag_dir, "tag.json")
|
||||
if os.path.exists(tag_json):
|
||||
try:
|
||||
os.unlink(tag_json)
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to delete tag.json for tag {tag_uuid}: {e}")
|
||||
|
||||
# Clear all tags from settings immediately
|
||||
datastore.data['settings']['application']['tags'] = {}
|
||||
|
||||
# Clear tags from all watches in background thread to avoid blocking
|
||||
def clear_all_tags_background():
|
||||
@@ -144,7 +160,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
flash(gettext("All tags deleted, clearing from watches in background"))
|
||||
return redirect(url_for('tags.tags_overview_page'))
|
||||
|
||||
@tags_blueprint.route("/edit/<uuid_str:uuid>", methods=['GET'])
|
||||
@tags_blueprint.route("/edit/<string:uuid>", methods=['GET'])
|
||||
@login_optionally_required
|
||||
def form_tag_edit(uuid):
|
||||
from changedetectionio.blueprint.tags.form import group_restock_settings_form
|
||||
@@ -163,21 +179,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
default_system_settings = datastore.data['settings'],
|
||||
)
|
||||
|
||||
# Bridge API-stored processor_config_* values into the form's FormField sub-forms.
|
||||
# The API stores processor_config_restock_diff in the tag dict; find the matching
|
||||
# FormField by checking which one's sub-fields cover the config keys.
|
||||
from wtforms.fields.form import FormField as WTFormField
|
||||
for key, value in default.items():
|
||||
if not key.startswith('processor_config_') or not isinstance(value, dict):
|
||||
continue
|
||||
for form_field in form:
|
||||
if isinstance(form_field, WTFormField) and all(k in form_field.form._fields for k in value):
|
||||
for sub_key, sub_value in value.items():
|
||||
sub_field = form_field.form._fields.get(sub_key)
|
||||
if sub_field is not None:
|
||||
sub_field.data = sub_value
|
||||
break
|
||||
|
||||
template_args = {
|
||||
'data': default,
|
||||
'form': form,
|
||||
@@ -211,17 +212,9 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
template = env.from_string(template_str)
|
||||
included_content = template.render(**template_args)
|
||||
|
||||
# Watches whose URL currently matches this tag's pattern
|
||||
matching_watches = {
|
||||
w_uuid: watch
|
||||
for w_uuid, watch in datastore.data['watching'].items()
|
||||
if default.matches_url(watch.get('url', ''))
|
||||
}
|
||||
|
||||
output = render_template("edit-tag.html",
|
||||
extra_form_content=included_content,
|
||||
extra_tab_content=form.extra_tab_content() if form.extra_tab_content() else None,
|
||||
matching_watches=matching_watches,
|
||||
settings_application=datastore.data['settings']['application'],
|
||||
**template_args
|
||||
)
|
||||
@@ -229,7 +222,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
return output
|
||||
|
||||
|
||||
@tags_blueprint.route("/edit/<uuid_str:uuid>", methods=['POST'])
|
||||
@tags_blueprint.route("/edit/<string:uuid>", methods=['POST'])
|
||||
@login_optionally_required
|
||||
def form_tag_edit_submit(uuid):
|
||||
from changedetectionio.blueprint.tags.form import group_restock_settings_form
|
||||
@@ -262,4 +255,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
return redirect(url_for('tags.tags_overview_page'))
|
||||
|
||||
|
||||
@tags_blueprint.route("/delete/<string:uuid>", methods=['GET'])
|
||||
def form_tag_delete(uuid):
|
||||
return redirect(url_for('tags.tags_overview_page'))
|
||||
return tags_blueprint
|
||||
|
||||
@@ -10,11 +10,12 @@ from changedetectionio.processors.restock_diff.forms import processor_settings_f
|
||||
|
||||
class group_restock_settings_form(restock_settings_form):
|
||||
overrides_watch = BooleanField('Activate for individual watches in this tag/group?', default=False)
|
||||
url_match_pattern = StringField('Auto-apply to watches with URLs matching',
|
||||
render_kw={"placeholder": "e.g. *://example.com/* or github.com/myorg"})
|
||||
tag_colour = StringField('Tag colour', default='')
|
||||
|
||||
class SingleTag(Form):
|
||||
|
||||
name = StringField('Tag name', [validators.InputRequired()], render_kw={"placeholder": "Name"})
|
||||
save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -43,46 +43,6 @@
|
||||
<div class="pure-control-group">
|
||||
{{ render_field(form.title, placeholder="https://...", required=true, class="m-d") }}
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
{{ render_field(form.url_match_pattern, class="m-d") }}
|
||||
<span class="pure-form-message-inline">{{ _('Automatically applies this tag to any watch whose URL matches. Supports wildcards: <code>*example.com*</code> or plain substring: <code>github.com/myorg</code>')|safe }}</span>
|
||||
</div>
|
||||
{% if matching_watches %}
|
||||
<div class="pure-control-group">
|
||||
<label>{{ _('Currently matching watches') }} ({{ matching_watches|length }})</label>
|
||||
<ul class="tag-url-match-list">
|
||||
{% for w_uuid, w in matching_watches.items() %}
|
||||
<li><a href="{{ url_for('ui.ui_edit.edit_page', uuid=w_uuid) }}">{{ w.label }}</a></li>
|
||||
{% endfor %}
|
||||
</ul>
|
||||
</div>
|
||||
{% endif %}
|
||||
<div class="pure-control-group">
|
||||
<label>{{ _('Tag colour') }}</label>
|
||||
<div style="display:flex; align-items:center; gap:0.75em;">
|
||||
<input type="checkbox" id="use_custom_colour"
|
||||
{% if data.get('tag_colour') %}checked{% endif %}>
|
||||
<label for="use_custom_colour" style="margin:0">{{ _('Custom colour') }}</label>
|
||||
<input type="color" id="tag_colour_picker"
|
||||
value="{{ data.get('tag_colour') or '#4f8ef7' }}"
|
||||
{% if not data.get('tag_colour') %}disabled{% endif %}>
|
||||
<input type="hidden" name="tag_colour" id="tag_colour_hidden"
|
||||
value="{{ data.get('tag_colour', '') }}">
|
||||
</div>
|
||||
<span class="pure-form-message-inline">{{ _('Leave unchecked to use the auto-generated colour based on the tag name.') }}</span>
|
||||
</div>
|
||||
<script>
|
||||
(function () {
|
||||
var cb = document.getElementById('use_custom_colour');
|
||||
var picker = document.getElementById('tag_colour_picker');
|
||||
var hidden = document.getElementById('tag_colour_hidden');
|
||||
picker.addEventListener('input', function () { hidden.value = this.value; });
|
||||
cb.addEventListener('change', function () {
|
||||
picker.disabled = !this.checked;
|
||||
hidden.value = this.checked ? picker.value : '';
|
||||
});
|
||||
})();
|
||||
</script>
|
||||
</fieldset>
|
||||
</div>
|
||||
|
||||
|
||||
@@ -3,26 +3,6 @@
|
||||
{% from '_helpers.html' import render_simple_field, render_field %}
|
||||
<script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
|
||||
<script src="{{url_for('static_content', group='js', filename='modal.js')}}"></script>
|
||||
<style>
|
||||
{%- for uuid, tag in available_tags -%}
|
||||
{%- if tag and tag.title -%}
|
||||
{%- set class_name = tag.title|sanitize_tag_class -%}
|
||||
{%- if tag.get('tag_colour') -%}
|
||||
.watch-tag-list.tag-{{ class_name }} { background-color: {{ tag.tag_colour }}; color: {{ wcag_text_color(tag.tag_colour) }}; }
|
||||
{%- else -%}
|
||||
{%- set colors = generate_tag_colors(tag.title) -%}
|
||||
.watch-tag-list.tag-{{ class_name }} {
|
||||
background-color: {{ colors['light']['bg'] }};
|
||||
color: {{ colors['light']['color'] }};
|
||||
}
|
||||
html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
|
||||
background-color: {{ colors['dark']['bg'] }};
|
||||
color: {{ colors['dark']['color'] }};
|
||||
}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
</style>
|
||||
|
||||
<div class="box">
|
||||
<form class="pure-form" action="{{ url_for('tags.form_tag_add') }}" method="POST" id="new-watch-form">
|
||||
@@ -68,7 +48,7 @@ html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
|
||||
<a class="link-mute state-{{'on' if tag.notification_muted else 'off'}}" href="{{url_for('tags.mute', uuid=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>{{ "{:,}".format(tag_count[uuid]) if uuid in tag_count else 0 }}</td>
|
||||
<td class="title-col inline"> <a href="{{url_for('watchlist.index', tag=uuid) }}" class="watch-tag-list tag-{{ tag.title|sanitize_tag_class }}">{{ tag.title }}</a></td>
|
||||
<td class="title-col inline"> <a href="{{url_for('watchlist.index', tag=uuid) }}">{{ tag.title }}</a></td>
|
||||
<td>
|
||||
<a class="pure-button pure-button-primary" href="{{ url_for('tags.form_tag_edit', uuid=uuid) }}">{{ _('Edit') }}</a>
|
||||
<a href="{{ url_for('ui.form_watch_checknow', tag=uuid) }}" class="pure-button pure-button-primary" >{{ _('Recheck') }}</a>
|
||||
|
||||
@@ -141,7 +141,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_pool,
|
||||
# Import the login decorator
|
||||
from changedetectionio.auth_decorator import login_optionally_required
|
||||
|
||||
@ui_blueprint.route("/clear_history/<uuid_str:uuid>", methods=['GET'])
|
||||
@ui_blueprint.route("/clear_history/<string:uuid>", methods=['GET'])
|
||||
@login_optionally_required
|
||||
def clear_watch_history(uuid):
|
||||
try:
|
||||
@@ -156,9 +156,9 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_pool,
|
||||
@login_optionally_required
|
||||
def clear_all_history():
|
||||
if request.method == 'POST':
|
||||
confirmtext = request.form.get('confirmtext', '')
|
||||
confirmtext = request.form.get('confirmtext')
|
||||
|
||||
if confirmtext.strip().lower() == gettext('clear').strip().lower():
|
||||
if confirmtext == 'clear':
|
||||
# Run in background thread to avoid blocking
|
||||
def clear_history_background():
|
||||
# Capture UUIDs first to avoid race conditions
|
||||
@@ -194,9 +194,9 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_pool,
|
||||
tag_limit = request.args.get('tag')
|
||||
now = int(time.time())
|
||||
|
||||
# Mark watches as viewed - use background thread only for large watch counts
|
||||
def mark_viewed_impl():
|
||||
"""Mark watches as viewed - can run synchronously or in background thread."""
|
||||
# Mark watches as viewed in background thread to avoid blocking
|
||||
def mark_viewed_background():
|
||||
"""Background thread to mark watches as viewed - discarded after completion."""
|
||||
marked_count = 0
|
||||
try:
|
||||
for watch_uuid, watch in datastore.data['watching'].items():
|
||||
@@ -209,21 +209,15 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_pool,
|
||||
datastore.set_last_viewed(watch_uuid, now)
|
||||
marked_count += 1
|
||||
|
||||
logger.info(f"Marking complete: {marked_count} watches marked as viewed")
|
||||
logger.info(f"Background marking complete: {marked_count} watches marked as viewed")
|
||||
except Exception as e:
|
||||
logger.error(f"Error marking as viewed: {e}")
|
||||
logger.error(f"Error in background mark as viewed: {e}")
|
||||
|
||||
# For small watch counts (< 10), run synchronously to avoid race conditions in tests
|
||||
# For larger counts, use background thread to avoid blocking the UI
|
||||
watch_count = len(datastore.data['watching'])
|
||||
if watch_count < 10:
|
||||
# Run synchronously for small watch counts
|
||||
mark_viewed_impl()
|
||||
else:
|
||||
# Start background thread for large watch counts
|
||||
thread = threading.Thread(target=mark_viewed_impl, daemon=True)
|
||||
thread.start()
|
||||
# Start background thread and return immediately
|
||||
thread = threading.Thread(target=mark_viewed_background, daemon=True)
|
||||
thread.start()
|
||||
|
||||
flash(gettext("Marking watches as viewed in background..."))
|
||||
return redirect(url_for('watchlist.index', tag=tag_limit))
|
||||
|
||||
@ui_blueprint.route("/delete", methods=['GET'])
|
||||
@@ -366,7 +360,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_pool,
|
||||
return redirect(url_for('watchlist.index'))
|
||||
|
||||
|
||||
@ui_blueprint.route("/share-url/<uuid_str:uuid>", methods=['GET'])
|
||||
@ui_blueprint.route("/share-url/<string:uuid>", methods=['GET'])
|
||||
@login_optionally_required
|
||||
def form_share_put_watch(uuid):
|
||||
"""Given a watch UUID, upload the info and return a share-link
|
||||
|
||||
@@ -66,7 +66,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
|
||||
return Markup(result)
|
||||
|
||||
@diff_blueprint.route("/diff/<uuid_str:uuid>", methods=['GET'])
|
||||
@diff_blueprint.route("/diff/<string:uuid>", methods=['GET'])
|
||||
@login_optionally_required
|
||||
def diff_history_page(uuid):
|
||||
"""
|
||||
@@ -128,7 +128,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
redirect=redirect
|
||||
)
|
||||
|
||||
@diff_blueprint.route("/diff/<uuid_str:uuid>/extract", methods=['GET'])
|
||||
@diff_blueprint.route("/diff/<string:uuid>/extract", methods=['GET'])
|
||||
@login_optionally_required
|
||||
def diff_history_page_extract_GET(uuid):
|
||||
"""
|
||||
@@ -182,7 +182,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
redirect=redirect
|
||||
)
|
||||
|
||||
@diff_blueprint.route("/diff/<uuid_str:uuid>/extract", methods=['POST'])
|
||||
@diff_blueprint.route("/diff/<string:uuid>/extract", methods=['POST'])
|
||||
@login_optionally_required
|
||||
def diff_history_page_extract_POST(uuid):
|
||||
"""
|
||||
@@ -238,7 +238,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
redirect=redirect
|
||||
)
|
||||
|
||||
@diff_blueprint.route("/diff/<uuid_str:uuid>/processor-asset/<string:asset_name>", methods=['GET'])
|
||||
@diff_blueprint.route("/diff/<string:uuid>/processor-asset/<string:asset_name>", methods=['GET'])
|
||||
@login_optionally_required
|
||||
def processor_asset(uuid, asset_name):
|
||||
"""
|
||||
|
||||
@@ -20,13 +20,13 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
|
||||
if tag_uuid in watch.get('tags', []) and (tag.get('include_filters') or tag.get('subtractive_selectors')):
|
||||
return True
|
||||
|
||||
@edit_blueprint.route("/edit/<uuid_str:uuid>", methods=['GET', 'POST'])
|
||||
@edit_blueprint.route("/edit/<string:uuid>", methods=['GET', 'POST'])
|
||||
@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 changedetectionio import forms
|
||||
from changedetectionio.browser_steps.browser_steps import browser_step_ui_config
|
||||
from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
|
||||
from changedetectionio import processors
|
||||
import importlib
|
||||
|
||||
@@ -117,25 +117,12 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
|
||||
processor_config = processor_instance.get_extra_watch_config(config_filename)
|
||||
|
||||
if processor_config:
|
||||
from wtforms.fields.form import FormField
|
||||
# Populate processor-config-* fields from JSON
|
||||
for config_key, config_value in processor_config.items():
|
||||
if not isinstance(config_value, dict):
|
||||
continue
|
||||
# Try exact API-named field first (e.g., processor_config_restock_diff)
|
||||
target_field = getattr(form, f'processor_config_{config_key}', None)
|
||||
# Fallback: find any FormField sub-form whose fields cover config_value keys
|
||||
if target_field is None:
|
||||
for form_field in form:
|
||||
if isinstance(form_field, FormField) and all(k in form_field.form._fields for k in config_value):
|
||||
target_field = form_field
|
||||
break
|
||||
if target_field is not None:
|
||||
for sub_key, sub_value in config_value.items():
|
||||
sub_field = target_field.form._fields.get(sub_key)
|
||||
if sub_field is not None:
|
||||
sub_field.data = sub_value
|
||||
logger.debug(f"Loaded processor config from {config_filename}: {sub_key} = {sub_value}")
|
||||
field_name = f'processor_config_{config_key}'
|
||||
if hasattr(form, field_name):
|
||||
getattr(form, field_name).data = config_value
|
||||
logger.debug(f"Loaded processor config from {config_filename}: {field_name} = {config_value}")
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to load processor config: {e}")
|
||||
|
||||
@@ -320,12 +307,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
|
||||
'using_global_webdriver_wait': not default['webdriver_delay'],
|
||||
'uuid': uuid,
|
||||
'watch': watch,
|
||||
'capabilities': capabilities,
|
||||
'auto_applied_tags': {
|
||||
tag_uuid: tag
|
||||
for tag_uuid, tag in datastore.data['settings']['application']['tags'].items()
|
||||
if tag_uuid not in watch.get('tags', []) and tag.matches_url(watch.get('url', ''))
|
||||
},
|
||||
'capabilities': capabilities
|
||||
}
|
||||
|
||||
included_content = None
|
||||
@@ -345,7 +327,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
|
||||
|
||||
return output
|
||||
|
||||
@edit_blueprint.route("/edit/<uuid_str:uuid>/get-html", methods=['GET'])
|
||||
@edit_blueprint.route("/edit/<string:uuid>/get-html", methods=['GET'])
|
||||
@login_optionally_required
|
||||
def watch_get_latest_html(uuid):
|
||||
from io import BytesIO
|
||||
@@ -372,7 +354,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
|
||||
# Return a 500 error
|
||||
abort(500)
|
||||
|
||||
@edit_blueprint.route("/edit/<uuid_str:uuid>/get-data-package", methods=['GET'])
|
||||
@edit_blueprint.route("/edit/<string:uuid>/get-data-package", methods=['GET'])
|
||||
@login_optionally_required
|
||||
def watch_get_data_package(uuid):
|
||||
"""Download all data for a single watch as a zip file"""
|
||||
@@ -382,6 +364,9 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
|
||||
from pathlib import Path
|
||||
import datetime
|
||||
|
||||
if uuid == 'first':
|
||||
uuid = list(datastore.data['watching'].keys()).pop()
|
||||
|
||||
watch = datastore.data['watching'].get(uuid)
|
||||
if not watch:
|
||||
abort(404)
|
||||
@@ -423,7 +408,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
|
||||
mimetype='application/zip')
|
||||
|
||||
# Ajax callback
|
||||
@edit_blueprint.route("/edit/<uuid_str:uuid>/preview-rendered", methods=['POST'])
|
||||
@edit_blueprint.route("/edit/<string:uuid>/preview-rendered", methods=['POST'])
|
||||
@login_optionally_required
|
||||
def watch_get_preview_rendered(uuid):
|
||||
'''For when viewing the "preview" of the rendered text from inside of Edit'''
|
||||
|
||||
@@ -10,8 +10,7 @@ from changedetectionio import html_tools
|
||||
def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
preview_blueprint = Blueprint('ui_preview', __name__, template_folder="../ui/templates")
|
||||
|
||||
|
||||
@preview_blueprint.route("/preview/<uuid_str:uuid>", methods=['GET', 'POST'])
|
||||
@preview_blueprint.route("/preview/<string:uuid>", methods=['GET'])
|
||||
@login_optionally_required
|
||||
def preview_page(uuid):
|
||||
"""
|
||||
@@ -60,8 +59,12 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
versions = []
|
||||
timestamp = None
|
||||
|
||||
system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
|
||||
extra_stylesheets = [url_for('static_content', group='styles', filename='diff.css')]
|
||||
is_html_webdriver = watch.fetcher_supports_screenshots
|
||||
|
||||
is_html_webdriver = False
|
||||
if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
|
||||
is_html_webdriver = True
|
||||
|
||||
triggered_line_numbers = []
|
||||
ignored_line_numbers = []
|
||||
@@ -71,9 +74,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
flash(gettext("Preview unavailable - No fetch/check completed or triggers not reached"), "error")
|
||||
else:
|
||||
# So prepare the latest preview or not
|
||||
preferred_version = request.values.get('version') if request.method == 'POST' else request.args.get('version')
|
||||
|
||||
|
||||
preferred_version = request.args.get('version')
|
||||
versions = list(watch.history.keys())
|
||||
timestamp = versions[-1]
|
||||
if preferred_version and preferred_version in versions:
|
||||
@@ -124,7 +125,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
|
||||
|
||||
return output
|
||||
|
||||
@preview_blueprint.route("/preview/<uuid_str:uuid>/processor-asset/<string:asset_name>", methods=['GET'])
|
||||
@preview_blueprint.route("/preview/<string:uuid>/processor-asset/<string:asset_name>", methods=['GET'])
|
||||
@login_optionally_required
|
||||
def processor_asset(uuid, asset_name):
|
||||
"""
|
||||
|
||||
@@ -81,14 +81,6 @@
|
||||
<div class="pure-control-group">
|
||||
{{ render_field(form.tags) }}
|
||||
<span class="pure-form-message-inline">{{ _('Organisational tag/group name used in the main listing page') }}</span>
|
||||
{% if auto_applied_tags %}
|
||||
<span class="pure-form-message-inline">
|
||||
{{ _('Also automatically applied by URL pattern:') }}
|
||||
{% for tag_uuid, tag in auto_applied_tags.items() %}
|
||||
<a href="{{ url_for('tags.form_tag_edit', uuid=tag_uuid) }}" class="watch-tag-list tag-{{ tag.title|sanitize_tag_class }}">{{ tag.title }}</a>
|
||||
{% endfor %}
|
||||
</span>
|
||||
{% endif %}
|
||||
</div>
|
||||
<div class="pure-control-group inline-radio">
|
||||
{{ render_field(form.processor) }}
|
||||
@@ -496,7 +488,7 @@ Math: {{ 1 + 1 }}") }}
|
||||
{% if watch.history_n %}
|
||||
<p>
|
||||
<a href="{{url_for('ui.ui_edit.watch_get_latest_html', uuid=uuid)}}" class="pure-button button-small">{{ _('Download latest HTML snapshot') }}</a>
|
||||
<a href="{{url_for('ui.ui_edit.watch_get_data_package', uuid=uuid)}}" class="pure-button button-small">{{ _('Download watch data package') }}</a>
|
||||
<a href="{{url_for('ui.ui_edit.watch_get_data_package', uuid=uuid)}}" class="pure-button button-small">{{ _('Export watch data') }}</a>
|
||||
</p>
|
||||
{% endif %}
|
||||
|
||||
|
||||
@@ -17,7 +17,7 @@
|
||||
<script src="{{ url_for('static_content', group='js', filename='tabs.js') }}" defer></script>
|
||||
{% if versions|length >= 2 %}
|
||||
<div id="diff-form" style="text-align: center;">
|
||||
<form class="pure-form " action="{{url_for('ui.ui_preview.preview_page', uuid=uuid)}}" method="POST">
|
||||
<form class="pure-form " action="" method="POST">
|
||||
<fieldset>
|
||||
<label for="preview-version">{{ _('Select timestamp') }}</label> <select id="preview-version"
|
||||
name="from_version"
|
||||
@@ -28,7 +28,6 @@
|
||||
</option>
|
||||
{% endfor %}
|
||||
</select>
|
||||
<input type="hidden" name="csrf_token" value="{{ csrf_token() }}">
|
||||
<button type="submit" class="pure-button pure-button-primary">{{ _('Go') }}</button>
|
||||
|
||||
</fieldset>
|
||||
|
||||
@@ -81,7 +81,6 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
|
||||
|
||||
sorted_tags = sorted(datastore.data['settings']['application'].get('tags').items(), key=lambda x: x[1]['title'])
|
||||
|
||||
proxy_list = datastore.proxy_list
|
||||
output = render_template(
|
||||
"watch-overview.html",
|
||||
active_tag=active_tag,
|
||||
@@ -92,9 +91,8 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
|
||||
extra_classes='has-queue' if not update_q.empty() else '',
|
||||
form=form,
|
||||
generate_tag_colors=processors.generate_processor_badge_colors,
|
||||
wcag_text_color=processors.wcag_text_color,
|
||||
guid=datastore.data['app_guid'],
|
||||
has_proxies=proxy_list,
|
||||
has_proxies=datastore.proxy_list,
|
||||
hosted_sticky=os.getenv("SALTED_PASS", False) == False,
|
||||
now_time_server=round(time.time()),
|
||||
pagination=pagination,
|
||||
@@ -112,16 +110,6 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
|
||||
watches=sorted_watches
|
||||
)
|
||||
|
||||
# Return freed template-building memory to the OS immediately.
|
||||
# render_template allocates ~20MB of intermediate strings that are freed on return,
|
||||
# but glibc keeps those pages mapped in its arenas as RSS. malloc_trim() forces
|
||||
# glibc to release them, preventing RSS growth from concurrent Chrome connections.
|
||||
try:
|
||||
import ctypes
|
||||
ctypes.CDLL('libc.so.6').malloc_trim(0)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
if session.get('share-link'):
|
||||
del (session['share-link'])
|
||||
|
||||
|
||||
@@ -71,13 +71,6 @@ document.addEventListener('DOMContentLoaded', function() {
|
||||
{%- for uuid, tag in tags -%}
|
||||
{%- if tag and tag.title -%}
|
||||
{%- set class_name = tag.title|sanitize_tag_class -%}
|
||||
{%- if tag.get('tag_colour') -%}
|
||||
.button-tag.tag-{{ class_name }},
|
||||
.watch-tag-list.tag-{{ class_name }} {
|
||||
background-color: {{ tag.tag_colour }};
|
||||
color: {{ wcag_text_color(tag.tag_colour) }};
|
||||
}
|
||||
{%- else -%}
|
||||
{%- set colors = generate_tag_colors(tag.title) -%}
|
||||
.button-tag.tag-{{ class_name }} {
|
||||
background-color: {{ colors['light']['bg'] }};
|
||||
@@ -99,7 +92,6 @@ html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
|
||||
color: {{ colors['dark']['color'] }};
|
||||
}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
</style>
|
||||
<div class="box" id="form-quick-watch-add">
|
||||
@@ -221,13 +213,12 @@ html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
|
||||
{%- set checking_now = is_checking_now(watch) -%}
|
||||
{%- set history_n = watch.history_n -%}
|
||||
{%- set favicon = watch.get_favicon_filename() -%}
|
||||
{%- set error_texts = watch.compile_error_texts(has_proxies=has_proxies) -%}
|
||||
{%- set system_use_url_watchlist = datastore.data['settings']['application']['ui'].get('use_page_title_in_list') -%}
|
||||
{# Class settings mirrored in changedetectionio/static/js/realtime.js for the frontend #}
|
||||
{%- set row_classes = [
|
||||
loop.cycle('pure-table-odd', 'pure-table-even'),
|
||||
'processor-' ~ watch['processor'],
|
||||
'has-error' if error_texts|length > 2 else '',
|
||||
'has-error' if watch.compile_error_texts()|length > 2 else '',
|
||||
'paused' if watch.paused is defined and watch.paused != False else '',
|
||||
'unviewed' if watch.has_unviewed else '',
|
||||
'has-restock-info' if watch.has_restock_info else 'no-restock-info',
|
||||
@@ -280,7 +271,7 @@ html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
|
||||
{% endif %}
|
||||
<a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}"> </a>
|
||||
</span>
|
||||
<div class="error-text" style="display:none;">{{ error_texts|safe }}</div>
|
||||
<div class="error-text" style="display:none;">{{ watch.compile_error_texts(has_proxies=datastore.proxy_list)|safe }}</div>
|
||||
{%- 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">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>
|
||||
@@ -313,20 +304,11 @@ html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
|
||||
</span>
|
||||
{%- endif -%}
|
||||
|
||||
{%- if watch.get('restock') and watch['restock'].get('price') -%}
|
||||
{%- set restock = watch['restock'] -%}
|
||||
{%- set price = restock.get('price') -%}
|
||||
{%- set cur = restock.get('currency','') -%}
|
||||
|
||||
{%- if price is not none and (price|string)|regex_search('\d') -%}
|
||||
<span class="restock-label price" title="{{ _('Price') }}">
|
||||
{# @todo: make parse_currency/parse_decimal aware of the locale of the actual web page and use that instead changedetectionio/processors/restock_diff/__init__.py #}
|
||||
{%- if price is number -%}{# It's a number so we can convert it to their locale' #}
|
||||
{{ price|format_number_locale }} {{ cur }}<!-- as number -->
|
||||
{%- else -%}{# It's totally fine if it arrives as something else, the website might be something weird in this field #}
|
||||
{{ price }} {{ cur }}<!-- as string -->
|
||||
{%- endif -%}
|
||||
</span>
|
||||
{%- if watch.get('restock') and watch['restock']['price'] != None -%}
|
||||
{%- if watch['restock']['price'] != None -%}
|
||||
<span class="restock-label price" title="{{ _('Price') }}">
|
||||
{{ watch['restock']['price']|format_number_locale if watch['restock'].get('price') else '' }} {{ watch['restock'].get('currency','') }}
|
||||
</span>
|
||||
{%- endif -%}
|
||||
{%- elif not watch.has_restock_info -%}
|
||||
<span class="restock-label error">{{ _('No information') }}</span>
|
||||
|
||||
@@ -38,6 +38,7 @@ def manage_user_agent(headers, current_ua=''):
|
||||
|
||||
return None
|
||||
|
||||
|
||||
class Fetcher():
|
||||
browser_connection_is_custom = None
|
||||
browser_connection_url = None
|
||||
@@ -162,16 +163,30 @@ class Fetcher():
|
||||
"""
|
||||
return {k.lower(): v for k, v in self.headers.items()}
|
||||
|
||||
def browser_steps_get_valid_steps(self):
|
||||
if self.browser_steps is not None and len(self.browser_steps):
|
||||
valid_steps = list(filter(
|
||||
lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one'),
|
||||
self.browser_steps))
|
||||
|
||||
# Just incase they selected Goto site by accident with older JS
|
||||
if valid_steps and valid_steps[0]['operation'] == 'Goto site':
|
||||
del(valid_steps[0])
|
||||
|
||||
return valid_steps
|
||||
|
||||
return None
|
||||
|
||||
async def iterate_browser_steps(self, start_url=None):
|
||||
from changedetectionio.browser_steps.browser_steps import steppable_browser_interface, browser_steps_get_valid_steps
|
||||
from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
|
||||
from playwright._impl._errors import TimeoutError, Error
|
||||
from changedetectionio.jinja2_custom import render as jinja_render
|
||||
step_n = 0
|
||||
|
||||
if self.browser_steps:
|
||||
if self.browser_steps is not None and len(self.browser_steps):
|
||||
interface = steppable_browser_interface(start_url=start_url)
|
||||
interface.page = self.page
|
||||
valid_steps = browser_steps_get_valid_steps(self.browser_steps)
|
||||
valid_steps = self.browser_steps_get_valid_steps()
|
||||
|
||||
for step in valid_steps:
|
||||
step_n += 1
|
||||
|
||||
@@ -49,9 +49,6 @@ async def capture_full_page_async(page, screenshot_format='JPEG', watch_uuid=Non
|
||||
if page_height > page.viewport_size['height']:
|
||||
if page_height < step_size:
|
||||
step_size = page_height # Incase page is bigger than default viewport but smaller than proposed step size
|
||||
# Never set viewport taller than our max capture height - otherwise one screenshot chunk
|
||||
# captures the whole (e.g. 8098px) page even when SCREENSHOT_MAX_HEIGHT=1000
|
||||
step_size = min(step_size, SCREENSHOT_MAX_TOTAL_HEIGHT)
|
||||
viewport_start = time.time()
|
||||
logger.debug(f"{watch_info}Setting bigger viewport to step through large page width W{page.viewport_size['width']}xH{step_size} because page_height > viewport_size")
|
||||
# Set viewport to a larger size to capture more content at once
|
||||
@@ -298,7 +295,7 @@ class fetcher(Fetcher):
|
||||
self.page.on("console", lambda msg: logger.debug(f"Playwright console: Watch URL: {url} {msg.type}: {msg.text} {msg.args}"))
|
||||
|
||||
# Re-use as much code from browser steps as possible so its the same
|
||||
from changedetectionio.browser_steps.browser_steps import steppable_browser_interface
|
||||
from changedetectionio.blueprint.browser_steps.browser_steps import steppable_browser_interface
|
||||
browsersteps_interface = steppable_browser_interface(start_url=url)
|
||||
browsersteps_interface.page = self.page
|
||||
|
||||
@@ -365,7 +362,7 @@ class fetcher(Fetcher):
|
||||
# Wrap remaining operations in try/finally to ensure cleanup
|
||||
try:
|
||||
# Run Browser Steps here
|
||||
if self.browser_steps:
|
||||
if self.browser_steps_get_valid_steps():
|
||||
try:
|
||||
await self.iterate_browser_steps(start_url=url)
|
||||
except BrowserStepsStepException:
|
||||
|
||||
@@ -75,9 +75,6 @@ async def capture_full_page(page, screenshot_format='JPEG', watch_uuid=None, loc
|
||||
if page_height > page.viewport['height']:
|
||||
if page_height < step_size:
|
||||
step_size = page_height # Incase page is bigger than default viewport but smaller than proposed step size
|
||||
# Never set viewport taller than our max capture height - otherwise one screenshot chunk
|
||||
# captures the whole page even when SCREENSHOT_MAX_HEIGHT is set smaller
|
||||
step_size = min(step_size, SCREENSHOT_MAX_TOTAL_HEIGHT)
|
||||
viewport_start = time.time()
|
||||
await page.setViewport({'width': page.viewport['width'], 'height': step_size})
|
||||
viewport_time = time.time() - viewport_start
|
||||
@@ -89,8 +86,8 @@ async def capture_full_page(page, screenshot_format='JPEG', watch_uuid=None, loc
|
||||
# better than scrollTo incase they override it in the page
|
||||
await page.evaluate(
|
||||
"""(y) => {
|
||||
const el = document.scrollingElement;
|
||||
if (el) el.scrollTop = y;
|
||||
document.documentElement.scrollTop = y;
|
||||
document.body.scrollTop = y;
|
||||
}""",
|
||||
y
|
||||
)
|
||||
@@ -308,8 +305,6 @@ class fetcher(Fetcher):
|
||||
await asyncio.wait_for(self.browser.close(), timeout=3.0)
|
||||
except Exception as cleanup_error:
|
||||
logger.error(f"[{watch_uuid}] Failed to cleanup browser after page creation failure: {cleanup_error}")
|
||||
finally:
|
||||
self.browser = None
|
||||
raise
|
||||
|
||||
# Add console handler to capture console.log from favicon fetcher
|
||||
@@ -461,7 +456,7 @@ class fetcher(Fetcher):
|
||||
|
||||
# Run Browser Steps here
|
||||
# @todo not yet supported, we switch to playwright in this case
|
||||
# if self.browser_steps:
|
||||
# if self.browser_steps_get_valid_steps():
|
||||
# self.iterate_browser_steps()
|
||||
|
||||
|
||||
@@ -537,14 +532,6 @@ class fetcher(Fetcher):
|
||||
)
|
||||
except asyncio.TimeoutError:
|
||||
raise (BrowserFetchTimedOut(msg=f"Browser connected but was unable to process the page in {max_time} seconds."))
|
||||
finally:
|
||||
# Internal cleanup on any exception/timeout - call quit() immediately
|
||||
# This prevents connection leaks during exception bursts
|
||||
# Worker.py's quit() call becomes a redundant safety net (idempotent)
|
||||
try:
|
||||
await self.quit(watch={'uuid': watch_uuid} if watch_uuid else None)
|
||||
except Exception as cleanup_error:
|
||||
logger.error(f"[{watch_uuid}] Error during internal quit() cleanup: {cleanup_error}")
|
||||
|
||||
|
||||
# Plugin registration for built-in fetcher
|
||||
|
||||
@@ -1,14 +1,12 @@
|
||||
from loguru import logger
|
||||
from urllib.parse import urljoin, urlparse
|
||||
import hashlib
|
||||
import os
|
||||
import re
|
||||
import asyncio
|
||||
|
||||
from functools import partial
|
||||
from changedetectionio import strtobool
|
||||
from changedetectionio.content_fetchers.exceptions import BrowserStepsInUnsupportedFetcher, EmptyReply, Non200ErrorCodeReceived
|
||||
from changedetectionio.content_fetchers.base import Fetcher
|
||||
from changedetectionio.validate_url import is_private_hostname
|
||||
|
||||
|
||||
# "html_requests" is listed as the default fetcher in store.py!
|
||||
@@ -38,7 +36,7 @@ class fetcher(Fetcher):
|
||||
import requests
|
||||
from requests.exceptions import ProxyError, ConnectionError, RequestException
|
||||
|
||||
if self.browser_steps:
|
||||
if self.browser_steps_get_valid_steps():
|
||||
raise BrowserStepsInUnsupportedFetcher(url=url)
|
||||
|
||||
proxies = {}
|
||||
@@ -81,48 +79,14 @@ class fetcher(Fetcher):
|
||||
if strtobool(os.getenv('ALLOW_FILE_URI', 'false')) and url.startswith('file://'):
|
||||
from requests_file import FileAdapter
|
||||
session.mount('file://', FileAdapter())
|
||||
|
||||
allow_iana_restricted = strtobool(os.getenv('ALLOW_IANA_RESTRICTED_ADDRESSES', 'false'))
|
||||
|
||||
try:
|
||||
# Fresh DNS check at fetch time — catches DNS rebinding regardless of add-time cache.
|
||||
if not allow_iana_restricted:
|
||||
parsed_initial = urlparse(url)
|
||||
if parsed_initial.hostname and is_private_hostname(parsed_initial.hostname):
|
||||
raise Exception(f"Fetch blocked: '{url}' resolves to a private/reserved IP address. "
|
||||
f"Set ALLOW_IANA_RESTRICTED_ADDRESSES=true to allow.")
|
||||
|
||||
r = session.request(method=request_method,
|
||||
data=request_body.encode('utf-8') if type(request_body) is str else request_body,
|
||||
url=url,
|
||||
headers=request_headers,
|
||||
timeout=timeout,
|
||||
proxies=proxies,
|
||||
verify=False,
|
||||
allow_redirects=False)
|
||||
|
||||
# Manually follow redirects so each hop's resolved IP can be validated,
|
||||
# preventing SSRF via an open redirect on a public host.
|
||||
current_url = url
|
||||
for _ in range(10):
|
||||
if not r.is_redirect:
|
||||
break
|
||||
location = r.headers.get('Location', '')
|
||||
redirect_url = urljoin(current_url, location)
|
||||
if not allow_iana_restricted:
|
||||
parsed_redirect = urlparse(redirect_url)
|
||||
if parsed_redirect.hostname and is_private_hostname(parsed_redirect.hostname):
|
||||
raise Exception(f"Redirect blocked: '{redirect_url}' resolves to a private/reserved IP address.")
|
||||
current_url = redirect_url
|
||||
r = session.request('GET', redirect_url,
|
||||
headers=request_headers,
|
||||
timeout=timeout,
|
||||
proxies=proxies,
|
||||
verify=False,
|
||||
allow_redirects=False)
|
||||
else:
|
||||
raise Exception("Too many redirects")
|
||||
|
||||
verify=False)
|
||||
except Exception as e:
|
||||
msg = str(e)
|
||||
if proxies and 'SOCKSHTTPSConnectionPool' in msg:
|
||||
@@ -148,32 +112,10 @@ class fetcher(Fetcher):
|
||||
# Default to UTF-8 for XML if no encoding found
|
||||
r.encoding = 'utf-8'
|
||||
else:
|
||||
# No charset in HTTP header - sniff encoding in priority order matching browsers
|
||||
# (WHATWG encoding sniffing algorithm):
|
||||
# 1. BOM - highest confidence, check before anything else
|
||||
# 2. <meta charset> in first 2kb
|
||||
# 3. chardet statistical detection - last resort
|
||||
# See: https://github.com/dgtlmoon/changedetection.io/issues/3952
|
||||
boms = [
|
||||
(b'\xef\xbb\xbf', 'utf-8-sig'),
|
||||
(b'\xff\xfe', 'utf-16-le'),
|
||||
(b'\xfe\xff', 'utf-16-be'),
|
||||
]
|
||||
bom_encoding = next((enc for bom, enc in boms if r.content.startswith(bom)), None)
|
||||
if bom_encoding:
|
||||
logger.info(f"URL: {url} Using encoding '{bom_encoding}' detected from BOM")
|
||||
r.encoding = bom_encoding
|
||||
else:
|
||||
meta_charset_match = re.search(rb'<meta[^>]+charset\s*=\s*["\']?\s*([^"\'\s;>]+)', r.content[:2000], re.IGNORECASE)
|
||||
if meta_charset_match:
|
||||
encoding = meta_charset_match.group(1).decode('ascii', errors='ignore')
|
||||
logger.info(f"URL: {url} No content-type encoding in HTTP headers - Using encoding '{encoding}' from HTML meta charset tag")
|
||||
r.encoding = encoding
|
||||
else:
|
||||
encoding = chardet.detect(r.content)['encoding']
|
||||
logger.warning(f"URL: {url} No charset in headers or meta tag, guessed encoding as '{encoding}' via chardet")
|
||||
if encoding:
|
||||
r.encoding = encoding
|
||||
# For other content types, use chardet
|
||||
encoding = chardet.detect(r.content)['encoding']
|
||||
if encoding:
|
||||
r.encoding = encoding
|
||||
|
||||
self.headers = r.headers
|
||||
|
||||
@@ -242,6 +184,7 @@ class fetcher(Fetcher):
|
||||
)
|
||||
|
||||
async def quit(self, watch=None):
|
||||
|
||||
# In case they switched to `requests` fetcher from something else
|
||||
# Then the screenshot could be old, in any case, it's not used here.
|
||||
# REMOVE_REQUESTS_OLD_SCREENSHOTS - Mainly used for testing
|
||||
|
||||
@@ -56,10 +56,6 @@ def stitch_images_worker_raw_bytes(pipe_conn, original_page_height, capture_heig
|
||||
im.close()
|
||||
del images
|
||||
|
||||
# Clip stitched image to capture_height (chunks may overshoot by up to step_size-1 px)
|
||||
if total_height > capture_height:
|
||||
stitched = stitched.crop((0, 0, max_width, capture_height))
|
||||
|
||||
# Draw caption only if page was trimmed
|
||||
if original_page_height > capture_height:
|
||||
draw = ImageDraw.Draw(stitched)
|
||||
|
||||
@@ -104,17 +104,15 @@ class fetcher(Fetcher):
|
||||
|
||||
from selenium.webdriver.remote.remote_connection import RemoteConnection
|
||||
from selenium.webdriver.remote.webdriver import WebDriver as RemoteWebDriver
|
||||
from selenium.webdriver.remote.client_config import ClientConfig
|
||||
from urllib3.util import Timeout
|
||||
driver = None
|
||||
try:
|
||||
connection_timeout = int(os.getenv("WEBDRIVER_CONNECTION_TIMEOUT", 90))
|
||||
client_config = ClientConfig(
|
||||
remote_server_addr=self.browser_connection_url,
|
||||
timeout=Timeout(connect=connection_timeout, total=connection_timeout)
|
||||
# Create the RemoteConnection and set timeout (e.g., 30 seconds)
|
||||
remote_connection = RemoteConnection(
|
||||
self.browser_connection_url,
|
||||
)
|
||||
remote_connection = RemoteConnection(client_config=client_config)
|
||||
remote_connection.set_timeout(30) # seconds
|
||||
|
||||
# Now create the driver with the RemoteConnection
|
||||
driver = RemoteWebDriver(
|
||||
command_executor=remote_connection,
|
||||
options=options
|
||||
|
||||
@@ -45,36 +45,6 @@ CHANGED_INTO_PLACEMARKER_CLOSED = '@changed_into_PLACEMARKER_CLOSED'
|
||||
# Compiled regex patterns for performance
|
||||
WHITESPACE_NORMALIZE_RE = re.compile(r'\s+')
|
||||
|
||||
# Regexes built from the constants above — no brittle hardcoded strings
|
||||
_EXTRACT_REMOVED_RE = re.compile(
|
||||
re.escape(REMOVED_PLACEMARKER_OPEN) + r'(.*?)' + re.escape(REMOVED_PLACEMARKER_CLOSED)
|
||||
+ r'|' +
|
||||
re.escape(CHANGED_PLACEMARKER_OPEN) + r'(.*?)' + re.escape(CHANGED_PLACEMARKER_CLOSED)
|
||||
)
|
||||
_EXTRACT_ADDED_RE = re.compile(
|
||||
re.escape(ADDED_PLACEMARKER_OPEN) + r'(.*?)' + re.escape(ADDED_PLACEMARKER_CLOSED)
|
||||
+ r'|' +
|
||||
re.escape(CHANGED_INTO_PLACEMARKER_OPEN) + r'(.*?)' + re.escape(CHANGED_INTO_PLACEMARKER_CLOSED)
|
||||
)
|
||||
|
||||
|
||||
def extract_changed_from(raw_diff: str) -> str:
|
||||
"""Extract only the removed/changed-from fragments from a raw diff string.
|
||||
|
||||
Useful for {{diff_changed_from}} — gives just the old value (e.g. old price),
|
||||
not the full surrounding line. Multiple fragments joined with newlines.
|
||||
"""
|
||||
return '\n'.join(m.group(1) or m.group(2) for m in _EXTRACT_REMOVED_RE.finditer(raw_diff))
|
||||
|
||||
|
||||
def extract_changed_to(raw_diff: str) -> str:
|
||||
"""Extract only the added/changed-into fragments from a raw diff string.
|
||||
|
||||
Useful for {{diff_changed_to}} — gives just the new value (e.g. new price),
|
||||
not the full surrounding line. Multiple fragments joined with newlines.
|
||||
"""
|
||||
return '\n'.join(m.group(1) or m.group(2) for m in _EXTRACT_ADDED_RE.finditer(raw_diff))
|
||||
|
||||
|
||||
def render_inline_word_diff(before_line: str, after_line: str, ignore_junk: bool = False, markdown_style: str = None, tokenizer: str = 'words_and_html') -> tuple[str, bool]:
|
||||
"""
|
||||
|
||||
@@ -4,7 +4,6 @@ import flask_login
|
||||
import locale
|
||||
import os
|
||||
import queue
|
||||
import re
|
||||
import sys
|
||||
import threading
|
||||
import time
|
||||
@@ -28,6 +27,7 @@ from flask import (
|
||||
session,
|
||||
url_for,
|
||||
)
|
||||
from flask_compress import Compress as FlaskCompress
|
||||
from flask_restful import abort, Api
|
||||
from flask_cors import CORS
|
||||
|
||||
@@ -40,7 +40,7 @@ from loguru import logger
|
||||
|
||||
from changedetectionio import __version__
|
||||
from changedetectionio import queuedWatchMetaData
|
||||
from changedetectionio.api import Watch, WatchHistory, WatchSingleHistory, WatchHistoryDiff, CreateWatch, Import, SystemInfo, Tag, Tags, Notifications, WatchFavicon, Spec
|
||||
from changedetectionio.api import Watch, WatchHistory, WatchSingleHistory, WatchHistoryDiff, CreateWatch, Import, SystemInfo, Tag, Tags, Notifications, WatchFavicon
|
||||
from changedetectionio.api.Search import Search
|
||||
from .time_handler import is_within_schedule
|
||||
from changedetectionio.languages import get_available_languages, get_language_codes, get_flag_for_locale, get_timeago_locale
|
||||
@@ -69,43 +69,19 @@ socketio_server = None
|
||||
|
||||
# Enable CORS, especially useful for the Chrome extension to operate from anywhere
|
||||
CORS(app)
|
||||
from werkzeug.routing import BaseConverter, ValidationError
|
||||
from uuid import UUID
|
||||
|
||||
class StrictUUIDConverter(BaseConverter):
|
||||
# Special sentinel values allowed in addition to strict UUIDs
|
||||
_ALLOWED_SENTINELS = frozenset({'first'})
|
||||
|
||||
def to_python(self, value: str) -> str:
|
||||
if value in self._ALLOWED_SENTINELS:
|
||||
return value
|
||||
try:
|
||||
u = UUID(value)
|
||||
except ValueError as e:
|
||||
raise ValidationError() from e
|
||||
# Reject non-standard formats (braces, URNs, no-hyphens)
|
||||
if str(u) != value.lower():
|
||||
raise ValidationError()
|
||||
return str(u)
|
||||
|
||||
def to_url(self, value) -> str:
|
||||
return str(value)
|
||||
|
||||
# app setup (once)
|
||||
app.url_map.converters["uuid_str"] = StrictUUIDConverter
|
||||
|
||||
# Flask-Compress handles HTTP compression, Socket.IO compression disabled to prevent memory leak.
|
||||
# There's also a bug between flask compress and socketio that causes some kind of slow memory leak
|
||||
# It's better to use compression on your reverse proxy (nginx etc) instead.
|
||||
if strtobool(os.getenv("FLASK_ENABLE_COMPRESSION")):
|
||||
from flask_compress import Compress as FlaskCompress
|
||||
app.config['COMPRESS_MIN_SIZE'] = 2096
|
||||
app.config['COMPRESS_MIMETYPES'] = ['text/html', 'text/css', 'text/javascript', 'application/json', 'application/javascript', 'image/svg+xml']
|
||||
# Use gzip only - smaller memory footprint than zstd/brotli (4-8KB vs 200-500KB contexts)
|
||||
app.config['COMPRESS_ALGORITHM'] = ['gzip']
|
||||
compress = FlaskCompress()
|
||||
compress.init_app(app)
|
||||
|
||||
compress = FlaskCompress()
|
||||
|
||||
compress.init_app(app)
|
||||
app.config['TEMPLATES_AUTO_RELOAD'] = False
|
||||
|
||||
|
||||
@@ -212,23 +188,14 @@ def _is_safe_valid_url(test_url):
|
||||
from .validate_url import is_safe_valid_url
|
||||
return is_safe_valid_url(test_url)
|
||||
|
||||
@app.template_global('get_html_head_extras')
|
||||
def _get_html_head_extras():
|
||||
from .pluggy_interface import collect_html_head_extras
|
||||
return collect_html_head_extras()
|
||||
|
||||
|
||||
@app.template_filter('format_number_locale')
|
||||
def _jinja2_filter_format_number_locale(value: float) -> str:
|
||||
"Formats for example 4000.10 to the local locale default of 4,000.10"
|
||||
# Format the number with two decimal places (locale format string will return 6 decimal)
|
||||
formatted_value = locale.format_string("%.2f", value, grouping=True)
|
||||
return formatted_value
|
||||
|
||||
@app.template_filter('regex_search')
|
||||
def _jinja2_filter_regex_search(value, pattern):
|
||||
import re
|
||||
return re.search(pattern, str(value)) is not None
|
||||
return formatted_value
|
||||
|
||||
@app.template_global('is_checking_now')
|
||||
def _watch_is_checking_now(watch_obj, format="%Y-%m-%d %H:%M:%S"):
|
||||
@@ -393,8 +360,6 @@ def _jinja2_filter_fetcher_status_icons(fetcher_name):
|
||||
|
||||
return ''
|
||||
|
||||
_RE_SANITIZE_TAG = re.compile(r'[^a-zA-Z0-9]')
|
||||
|
||||
@app.template_filter('sanitize_tag_class')
|
||||
def _jinja2_filter_sanitize_tag_class(tag_title):
|
||||
"""Sanitize a tag title to create a valid CSS class name.
|
||||
@@ -406,8 +371,9 @@ def _jinja2_filter_sanitize_tag_class(tag_title):
|
||||
Returns:
|
||||
str: A sanitized string suitable for use as a CSS class name
|
||||
"""
|
||||
import re
|
||||
# Remove all non-alphanumeric characters and convert to lowercase
|
||||
sanitized = _RE_SANITIZE_TAG.sub('', tag_title).lower()
|
||||
sanitized = re.sub(r'[^a-zA-Z0-9]', '', tag_title).lower()
|
||||
# Ensure it starts with a letter (CSS requirement)
|
||||
if sanitized and not sanitized[0].isalpha():
|
||||
sanitized = 'tag' + sanitized
|
||||
@@ -495,21 +461,28 @@ def changedetection_app(config=None, datastore_o=None):
|
||||
available_languages = get_available_languages()
|
||||
language_codes = get_language_codes()
|
||||
|
||||
_locale_aliases = {
|
||||
'zh-TW': 'zh_Hant_TW', # Traditional Chinese: browser sends zh-TW, we use zh_Hant_TW
|
||||
'zh_TW': 'zh_Hant_TW', # Also handle underscore variant
|
||||
}
|
||||
_locale_match_list = language_codes + list(_locale_aliases.keys())
|
||||
|
||||
def get_locale():
|
||||
# Locale aliases: map browser language codes to translation directory names
|
||||
# This handles cases where browsers send standard codes (e.g., zh-TW)
|
||||
# but our translations use more specific codes (e.g., zh_Hant_TW)
|
||||
locale_aliases = {
|
||||
'zh-TW': 'zh_Hant_TW', # Traditional Chinese: browser sends zh-TW, we use zh_Hant_TW
|
||||
'zh_TW': 'zh_Hant_TW', # Also handle underscore variant
|
||||
}
|
||||
|
||||
# 1. Try to get locale from session (user explicitly selected)
|
||||
if 'locale' in session:
|
||||
return session['locale']
|
||||
|
||||
# 2. Fall back to Accept-Language header
|
||||
browser_locale = request.accept_languages.best_match(_locale_match_list)
|
||||
# 3. Map browser locale to our internal locale if needed
|
||||
return _locale_aliases.get(browser_locale, browser_locale)
|
||||
# Get the best match from browser's Accept-Language header
|
||||
browser_locale = request.accept_languages.best_match(language_codes + list(locale_aliases.keys()))
|
||||
|
||||
# 3. Check if we need to map the browser locale to our internal locale
|
||||
if browser_locale in locale_aliases:
|
||||
return locale_aliases[browser_locale]
|
||||
|
||||
return browser_locale
|
||||
|
||||
# Initialize Babel with locale selector
|
||||
babel = Babel(app, locale_selector=get_locale)
|
||||
@@ -561,22 +534,22 @@ def changedetection_app(config=None, datastore_o=None):
|
||||
|
||||
|
||||
watch_api.add_resource(WatchHistoryDiff,
|
||||
'/api/v1/watch/<uuid_str:uuid>/difference/<string:from_timestamp>/<string:to_timestamp>',
|
||||
'/api/v1/watch/<string:uuid>/difference/<string:from_timestamp>/<string:to_timestamp>',
|
||||
resource_class_kwargs={'datastore': datastore})
|
||||
watch_api.add_resource(WatchSingleHistory,
|
||||
'/api/v1/watch/<uuid_str:uuid>/history/<string:timestamp>',
|
||||
'/api/v1/watch/<string:uuid>/history/<string:timestamp>',
|
||||
resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
|
||||
watch_api.add_resource(WatchFavicon,
|
||||
'/api/v1/watch/<uuid_str:uuid>/favicon',
|
||||
'/api/v1/watch/<string:uuid>/favicon',
|
||||
resource_class_kwargs={'datastore': datastore})
|
||||
watch_api.add_resource(WatchHistory,
|
||||
'/api/v1/watch/<uuid_str:uuid>/history',
|
||||
'/api/v1/watch/<string:uuid>/history',
|
||||
resource_class_kwargs={'datastore': datastore})
|
||||
|
||||
watch_api.add_resource(CreateWatch, '/api/v1/watch',
|
||||
resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
|
||||
|
||||
watch_api.add_resource(Watch, '/api/v1/watch/<uuid_str:uuid>',
|
||||
watch_api.add_resource(Watch, '/api/v1/watch/<string:uuid>',
|
||||
resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
|
||||
|
||||
watch_api.add_resource(SystemInfo, '/api/v1/systeminfo',
|
||||
@@ -589,7 +562,7 @@ def changedetection_app(config=None, datastore_o=None):
|
||||
watch_api.add_resource(Tags, '/api/v1/tags',
|
||||
resource_class_kwargs={'datastore': datastore})
|
||||
|
||||
watch_api.add_resource(Tag, '/api/v1/tag', '/api/v1/tag/<uuid_str:uuid>',
|
||||
watch_api.add_resource(Tag, '/api/v1/tag', '/api/v1/tag/<string:uuid>',
|
||||
resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
|
||||
|
||||
watch_api.add_resource(Search, '/api/v1/search',
|
||||
@@ -598,8 +571,6 @@ def changedetection_app(config=None, datastore_o=None):
|
||||
watch_api.add_resource(Notifications, '/api/v1/notifications',
|
||||
resource_class_kwargs={'datastore': datastore})
|
||||
|
||||
watch_api.add_resource(Spec, '/api/v1/full-spec')
|
||||
|
||||
@login_manager.user_loader
|
||||
def user_loader(email):
|
||||
user = User()
|
||||
@@ -741,14 +712,8 @@ def changedetection_app(config=None, datastore_o=None):
|
||||
def static_content(group, filename):
|
||||
from flask import make_response
|
||||
import re
|
||||
|
||||
# Strict sanitization: only allow a-z, 0-9, and underscore (blocks .. and other traversal)
|
||||
group = re.sub(r'[^a-z0-9_-]+', '', group.lower())
|
||||
filename = filename
|
||||
|
||||
# Additional safety: reject if sanitization resulted in empty strings
|
||||
if not group or not filename:
|
||||
abort(404)
|
||||
group = re.sub(r'[^\w.-]+', '', group.lower())
|
||||
filename = re.sub(r'[^\w.-]+', '', filename.lower())
|
||||
|
||||
if group == 'screenshot':
|
||||
# Could be sensitive, follow password requirements
|
||||
@@ -1022,16 +987,15 @@ def check_for_new_version():
|
||||
import urllib3
|
||||
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
|
||||
|
||||
session = requests.Session()
|
||||
session.verify = False
|
||||
|
||||
while not app.config.exit.is_set():
|
||||
try:
|
||||
r = session.post("https://changedetection.io/check-ver.php",
|
||||
r = requests.post("https://changedetection.io/check-ver.php",
|
||||
data={'version': __version__,
|
||||
'app_guid': datastore.data['app_guid'],
|
||||
'watch_count': len(datastore.data['watching'])
|
||||
})
|
||||
},
|
||||
|
||||
verify=False)
|
||||
except:
|
||||
pass
|
||||
|
||||
|
||||
@@ -7,6 +7,8 @@ from flask_babel import lazy_gettext as _l, gettext
|
||||
from changedetectionio.blueprint.rss import RSS_FORMAT_TYPES, RSS_TEMPLATE_TYPE_OPTIONS, RSS_TEMPLATE_HTML_DEFAULT
|
||||
from changedetectionio.conditions.form import ConditionFormRow
|
||||
from changedetectionio.notification_service import NotificationContextData
|
||||
from changedetectionio.processors.image_ssim_diff import SCREENSHOT_COMPARISON_THRESHOLD_OPTIONS, \
|
||||
SCREENSHOT_COMPARISON_THRESHOLD_OPTIONS_DEFAULT
|
||||
from changedetectionio.strtobool import strtobool
|
||||
from changedetectionio import processors
|
||||
|
||||
@@ -35,7 +37,7 @@ from changedetectionio.widgets import TernaryNoneBooleanField
|
||||
|
||||
# default
|
||||
# each select <option data-enabled="enabled-0-0"
|
||||
from changedetectionio.browser_steps.browser_steps import browser_step_ui_config
|
||||
from changedetectionio.blueprint.browser_steps.browser_steps import browser_step_ui_config
|
||||
|
||||
from changedetectionio import html_tools, content_fetchers
|
||||
|
||||
@@ -492,6 +494,7 @@ class ValidateJinja2Template(object):
|
||||
Validates that a {token} is from a valid set
|
||||
"""
|
||||
def __call__(self, form, field):
|
||||
from changedetectionio import notification
|
||||
from changedetectionio.jinja2_custom import create_jinja_env
|
||||
from jinja2 import BaseLoader, TemplateSyntaxError, UndefinedError
|
||||
from jinja2.meta import find_undeclared_variables
|
||||
@@ -608,12 +611,13 @@ class ValidateCSSJSONXPATHInput(object):
|
||||
raise ValidationError("XPath not permitted in this field!")
|
||||
from lxml import etree, html
|
||||
import elementpath
|
||||
from changedetectionio.html_tools import SafeXPath3Parser
|
||||
# xpath 2.0-3.1
|
||||
from elementpath.xpath3 import XPath3Parser
|
||||
tree = html.fromstring("<html></html>")
|
||||
line = line.replace('xpath:', '')
|
||||
|
||||
try:
|
||||
elementpath.select(tree, line.strip(), parser=SafeXPath3Parser)
|
||||
elementpath.select(tree, line.strip(), parser=XPath3Parser)
|
||||
except elementpath.ElementPathError as e:
|
||||
message = field.gettext('\'%s\' is not a valid XPath expression. (%s)')
|
||||
raise ValidationError(message % (line, str(e)))
|
||||
@@ -667,11 +671,9 @@ class ValidateCSSJSONXPATHInput(object):
|
||||
# `jq` requires full compilation in windows and so isn't generally available
|
||||
raise ValidationError("jq not support not found")
|
||||
|
||||
from changedetectionio.html_tools import validate_jq_expression
|
||||
input = line.replace('jq:', '')
|
||||
|
||||
try:
|
||||
validate_jq_expression(input)
|
||||
jq.compile(input)
|
||||
except (ValueError) as e:
|
||||
message = field.gettext('\'%s\' is not a valid jq expression. (%s)')
|
||||
@@ -818,7 +820,8 @@ class processor_text_json_diff_form(commonSettingsForm):
|
||||
filter_text_removed = BooleanField(_l('Removed lines'), default=True)
|
||||
|
||||
trigger_text = StringListField(_l('Keyword triggers - Trigger/wait for text'), [validators.Optional(), ValidateListRegex()])
|
||||
browser_steps = FieldList(FormField(SingleBrowserStep), min_entries=10)
|
||||
if os.getenv("PLAYWRIGHT_DRIVER_URL"):
|
||||
browser_steps = FieldList(FormField(SingleBrowserStep), min_entries=10)
|
||||
text_should_not_be_present = StringListField(_l('Block change-detection while text matches'), [validators.Optional(), ValidateListRegex()])
|
||||
webdriver_js_execute_code = TextAreaField(_l('Execute JavaScript before change detection'), render_kw={"rows": "5"}, validators=[validators.Optional()])
|
||||
|
||||
@@ -1007,7 +1010,7 @@ class globalSettingsApplicationForm(commonSettingsForm):
|
||||
render_kw={"placeholder": "0.1", "style": "width: 8em;"}
|
||||
)
|
||||
|
||||
password = SaltyPasswordField(_l('Password'), render_kw={"autocomplete": "new-password"})
|
||||
password = SaltyPasswordField(_l('Password'))
|
||||
pager_size = IntegerField(_l('Pager size'),
|
||||
render_kw={"style": "width: 5em;"},
|
||||
validators=[validators.NumberRange(min=0,
|
||||
|
||||
+13
-146
@@ -4,7 +4,6 @@ from loguru import logger
|
||||
from typing import List
|
||||
import html
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
|
||||
# HTML added to be sure each result matching a filter (.example) gets converted to a new line by Inscriptis
|
||||
@@ -14,45 +13,6 @@ PERL_STYLE_REGEX = r'^/(.*?)/([a-z]*)?$'
|
||||
|
||||
TITLE_RE = re.compile(r"<title[^>]*>(.*?)</title>", re.I | re.S)
|
||||
META_CS = re.compile(r'<meta[^>]+charset=["\']?\s*([a-z0-9_\-:+.]+)', re.I)
|
||||
|
||||
# jq builtins that can leak sensitive data or cause harm when user-supplied expressions are executed.
|
||||
# env/$ENV reads all process environment variables (passwords, API keys, etc.)
|
||||
# include/import can read arbitrary files from disk
|
||||
# input/inputs reads beyond the supplied JSON data
|
||||
# debug/stderr leaks data to stderr
|
||||
# halt/halt_error terminates the process (DoS)
|
||||
_JQ_BLOCKED_PATTERNS = [
|
||||
(re.compile(r'\benv\b'), 'env (reads environment variables)'),
|
||||
(re.compile(r'\$ENV\b'), '$ENV (reads environment variables)'),
|
||||
(re.compile(r'\binclude\b'), 'include (reads files from disk)'),
|
||||
(re.compile(r'\bimport\b'), 'import (reads files from disk)'),
|
||||
(re.compile(r'\binputs?\b'), 'input/inputs (reads beyond provided data)'),
|
||||
(re.compile(r'\bdebug\b'), 'debug (leaks data to stderr)'),
|
||||
(re.compile(r'\bstderr\b'), 'stderr (leaks data to stderr)'),
|
||||
(re.compile(r'\bhalt(?:_error)?\b'), 'halt/halt_error (terminates the process)'),
|
||||
(re.compile(r'\$__loc__\b'), '$__loc__ (leaks file path information)'),
|
||||
(re.compile(r'\bbuiltins\b'), 'builtins (enumerates available functions)'),
|
||||
(re.compile(r'\bmodulemeta\b'), 'modulemeta (leaks module information)'),
|
||||
(re.compile(r'\$JQ_BUILD_CONFIGURATION\b'), '$JQ_BUILD_CONFIGURATION (leaks build information)'),
|
||||
]
|
||||
|
||||
def validate_jq_expression(expression: str) -> None:
|
||||
"""Raise ValueError if the jq expression uses any dangerous builtin.
|
||||
|
||||
User-supplied jq expressions are executed server-side. Without this check,
|
||||
builtins like `env` expose every process environment variable (SALTED_PASS,
|
||||
proxy credentials, API keys, etc.) as watch output.
|
||||
"""
|
||||
from changedetectionio.strtobool import strtobool
|
||||
if strtobool(os.getenv('JQ_ALLOW_RISKY_EXPRESSIONS', 'false')):
|
||||
return
|
||||
|
||||
for pattern, description in _JQ_BLOCKED_PATTERNS:
|
||||
if pattern.search(expression):
|
||||
msg = f"jq expression uses disallowed builtin: {description}"
|
||||
logger.critical(f"Security: blocked jq expression containing '{description}' - expression: {expression!r}")
|
||||
raise ValueError(msg)
|
||||
|
||||
META_CT = re.compile(r'<meta[^>]+http-equiv=["\']?content-type["\']?[^>]*content=["\'][^>]*charset=([a-z0-9_\-:+.]+)', re.I)
|
||||
|
||||
# 'price' , 'lowPrice', 'highPrice' are usually under here
|
||||
@@ -63,59 +23,6 @@ class JSONNotFound(ValueError):
|
||||
def __init__(self, msg):
|
||||
ValueError.__init__(self, msg)
|
||||
|
||||
|
||||
_DEFAULT_UNSAFE_XPATH3_FUNCTIONS = [
|
||||
'unparsed-text',
|
||||
'unparsed-text-lines',
|
||||
'unparsed-text-available',
|
||||
'doc',
|
||||
'doc-available',
|
||||
'json-doc',
|
||||
'json-doc-available',
|
||||
'collection', # XPath 2.0+: loads XML node collections from arbitrary URIs
|
||||
'uri-collection', # XPath 3.0+: enumerates URIs from resource collections
|
||||
'transform', # XPath 3.1: XSLT transformation (currently raises, block proactively)
|
||||
'load-xquery-module', # XPath 3.1: loads XQuery modules (currently raises, block proactively)
|
||||
'environment-variable',
|
||||
'available-environment-variables',
|
||||
]
|
||||
|
||||
|
||||
def _build_safe_xpath3_parser():
|
||||
"""Return an XPath3Parser subclass with filesystem/environment access functions removed.
|
||||
|
||||
XPath 3.0 includes functions that can read arbitrary files or environment variables:
|
||||
- unparsed-text / unparsed-text-lines / unparsed-text-available (file read)
|
||||
- doc / doc-available (XML fetch from URI)
|
||||
- environment-variable / available-environment-variables (env var leakage)
|
||||
|
||||
Subclassing gives us an independent symbol_table copy (not shared with the parent class),
|
||||
so removing entries here does not affect XPath3Parser itself.
|
||||
|
||||
Override the blocked list via the XPATH_BLOCKED_FUNCTIONS environment variable
|
||||
(comma-separated, e.g. "unparsed-text,doc,environment-variable").
|
||||
"""
|
||||
import os
|
||||
from elementpath.xpath3 import XPath3Parser
|
||||
|
||||
class SafeXPath3Parser(XPath3Parser):
|
||||
pass
|
||||
|
||||
env_override = os.getenv('XPATH_BLOCKED_FUNCTIONS')
|
||||
if env_override is not None:
|
||||
blocked = [f.strip() for f in env_override.split(',') if f.strip()]
|
||||
else:
|
||||
blocked = _DEFAULT_UNSAFE_XPATH3_FUNCTIONS
|
||||
|
||||
for _fn in blocked:
|
||||
SafeXPath3Parser.symbol_table.pop(_fn, None)
|
||||
|
||||
return SafeXPath3Parser
|
||||
|
||||
|
||||
# Module-level singleton — built once, reused everywhere.
|
||||
SafeXPath3Parser = _build_safe_xpath3_parser()
|
||||
|
||||
# Doesn't look like python supports forward slash auto enclosure in re.findall
|
||||
# So convert it to inline flag "(?i)foobar" type configuration
|
||||
@lru_cache(maxsize=100)
|
||||
@@ -276,6 +183,8 @@ def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False
|
||||
"""
|
||||
from lxml import etree, html
|
||||
import elementpath
|
||||
# xpath 2.0-3.1
|
||||
from elementpath.xpath3 import XPath3Parser
|
||||
|
||||
parser = etree.HTMLParser()
|
||||
tree = None
|
||||
@@ -301,7 +210,7 @@ def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False
|
||||
# This allows //title to match elements in the default namespace
|
||||
namespaces[''] = tree.nsmap[None]
|
||||
|
||||
r = elementpath.select(tree, xpath_filter.strip(), namespaces=namespaces, parser=SafeXPath3Parser)
|
||||
r = elementpath.select(tree, xpath_filter.strip(), namespaces=namespaces, parser=XPath3Parser)
|
||||
#@note: //title/text() now works with default namespaces (fixed by registering '' prefix)
|
||||
#@note: //title/text() wont work where <title>CDATA.. (use cdata_in_document_to_text first)
|
||||
|
||||
@@ -326,9 +235,6 @@ def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False
|
||||
else:
|
||||
html_block += elementpath_tostring(element)
|
||||
|
||||
# Drop element references before the finally block so tree.clear() can release
|
||||
# the libxml2 document immediately (elements pin the C-level doc via refcount).
|
||||
del r
|
||||
return html_block
|
||||
finally:
|
||||
# Explicitly clear the tree to free memory
|
||||
@@ -424,16 +330,12 @@ def _parse_json(json_data, json_filter):
|
||||
raise Exception("jq not support not found")
|
||||
|
||||
if json_filter.startswith("jq:"):
|
||||
expr = json_filter.removeprefix("jq:")
|
||||
validate_jq_expression(expr)
|
||||
jq_expression = jq.compile(expr)
|
||||
jq_expression = jq.compile(json_filter.removeprefix("jq:"))
|
||||
match = jq_expression.input(json_data).all()
|
||||
return _get_stripped_text_from_json_match(match)
|
||||
|
||||
if json_filter.startswith("jqraw:"):
|
||||
expr = json_filter.removeprefix("jqraw:")
|
||||
validate_jq_expression(expr)
|
||||
jq_expression = jq.compile(expr)
|
||||
jq_expression = jq.compile(json_filter.removeprefix("jqraw:"))
|
||||
match = jq_expression.input(json_data).all()
|
||||
return '\n'.join(str(item) for item in match)
|
||||
|
||||
@@ -537,25 +439,13 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
|
||||
except json.JSONDecodeError as e:
|
||||
logger.warning(f"Error processing JSON {content[:20]}...{str(e)})")
|
||||
else:
|
||||
# Check for JSONP wrapper: someCallback({...}) or some.namespace({...})
|
||||
# Server may claim application/json but actually return JSONP
|
||||
jsonp_match = re.match(r'^\w[\w.]*\s*\((.+)\)\s*;?\s*$', content.lstrip("\ufeff").strip(), re.DOTALL)
|
||||
if jsonp_match:
|
||||
try:
|
||||
inner = jsonp_match.group(1).strip()
|
||||
logger.warning(f"Content looks like JSONP, attempting to extract inner JSON for filter '{json_filter}'")
|
||||
stripped_text_from_html = _parse_json(json.loads(inner), json_filter)
|
||||
except json.JSONDecodeError as e:
|
||||
logger.warning(f"Error processing JSONP inner content {content[:20]}...{str(e)})")
|
||||
|
||||
if not stripped_text_from_html:
|
||||
# Probably something else, go fish inside for it
|
||||
try:
|
||||
stripped_text_from_html = extract_json_blob_from_html(content=content,
|
||||
ensure_is_ldjson_info_type=ensure_is_ldjson_info_type,
|
||||
json_filter=json_filter)
|
||||
except json.JSONDecodeError as e:
|
||||
logger.warning(f"Error processing JSON while extracting JSON from HTML blob {content[:20]}...{str(e)})")
|
||||
# Probably something else, go fish inside for it
|
||||
try:
|
||||
stripped_text_from_html = extract_json_blob_from_html(content=content,
|
||||
ensure_is_ldjson_info_type=ensure_is_ldjson_info_type,
|
||||
json_filter=json_filter )
|
||||
except json.JSONDecodeError as e:
|
||||
logger.warning(f"Error processing JSON while extracting JSON from HTML blob {content[:20]}...{str(e)})")
|
||||
|
||||
if not stripped_text_from_html:
|
||||
# Re 265 - Just return an empty string when filter not found
|
||||
@@ -671,33 +561,10 @@ def html_to_text(html_content: str, render_anchor_tag_content=False, is_rss=Fals
|
||||
)
|
||||
else:
|
||||
parser_config = None
|
||||
|
||||
if is_rss:
|
||||
html_content = re.sub(r'<title([\s>])', r'<h1\1', html_content)
|
||||
html_content = re.sub(r'</title>', r'</h1>', html_content)
|
||||
else:
|
||||
# Use BS4 html.parser to strip bloat — SPA's often dump 10MB+ of CSS/JS into <head>,
|
||||
# causing inscriptis to silently give up. Regex-based stripping is unsafe because tags
|
||||
# can appear inside JSON data attributes with JS-escaped closing tags (e.g. <\/script>),
|
||||
# causing the regex to scan past the intended close and eat real page content.
|
||||
from bs4 import BeautifulSoup
|
||||
soup = BeautifulSoup(html_content, 'html.parser')
|
||||
# Strip tags that inscriptis cannot render as meaningful text and which can be very large.
|
||||
# svg/math: produce path-data/MathML garbage; canvas/iframe/template: no inscriptis handlers.
|
||||
# video/audio/picture are kept — they may contain meaningful fallback text or captions.
|
||||
for tag in soup.find_all(['head', 'script', 'style', 'noscript', 'svg',
|
||||
'math', 'canvas', 'iframe', 'template']):
|
||||
tag.decompose()
|
||||
|
||||
# SPAs often use <body style="display:none"> to hide content until JS loads.
|
||||
# inscriptis respects CSS display rules, so strip hiding styles from the body tag.
|
||||
body_tag = soup.find('body')
|
||||
if body_tag and body_tag.get('style'):
|
||||
style = body_tag['style']
|
||||
if re.search(r'\b(?:display\s*:\s*none|visibility\s*:\s*hidden)\b', style, re.IGNORECASE):
|
||||
logger.debug(f"html_to_text: Removing hiding styles from body tag (found: '{style}')")
|
||||
del body_tag['style']
|
||||
|
||||
html_content = str(soup)
|
||||
|
||||
text_content = get_text(html_content, config=parser_config)
|
||||
return text_content
|
||||
|
||||
@@ -28,20 +28,17 @@ def get_timeago_locale(flask_locale):
|
||||
str: timeago library locale code (e.g., 'en', 'zh_CN', 'pt_PT')
|
||||
"""
|
||||
locale_map = {
|
||||
'zh': 'zh_CN', # Chinese Simplified
|
||||
'zh': 'zh_CN', # Chinese Simplified
|
||||
# timeago library just hasn't been updated to use the more modern locale naming convention, before BCP 47 / RFC 5646.
|
||||
'zh_TW': 'zh_TW', # Chinese Traditional (timeago uses zh_TW)
|
||||
'zh_TW': 'zh_TW', # Chinese Traditional (timeago uses zh_TW)
|
||||
'zh_Hant_TW': 'zh_TW', # Flask-Babel normalizes zh_TW to zh_Hant_TW, map back to timeago's zh_TW
|
||||
'pt': 'pt_PT', # Portuguese (Portugal)
|
||||
'pt_BR': 'pt_BR', # Portuguese (Brasil)
|
||||
'sv': 'sv_SE', # Swedish
|
||||
'no': 'nb_NO', # Norwegian Bokmål
|
||||
'hi': 'in_HI', # Hindi
|
||||
'cs': 'en', # Czech not supported by timeago, fallback to English
|
||||
'ja': 'ja', # Japanese
|
||||
'uk': 'uk', # Ukrainian
|
||||
'en_GB': 'en', # British English - timeago uses 'en'
|
||||
'en_US': 'en', # American English - timeago uses 'en'
|
||||
'pt': 'pt_PT', # Portuguese (Portugal)
|
||||
'sv': 'sv_SE', # Swedish
|
||||
'no': 'nb_NO', # Norwegian Bokmål
|
||||
'hi': 'in_HI', # Hindi
|
||||
'cs': 'en', # Czech not supported by timeago, fallback to English
|
||||
'en_GB': 'en', # British English - timeago uses 'en'
|
||||
'en_US': 'en', # American English - timeago uses 'en'
|
||||
}
|
||||
return locale_map.get(flask_locale, flask_locale)
|
||||
|
||||
@@ -55,8 +52,7 @@ LANGUAGE_DATA = {
|
||||
'ko': {'flag': 'fi fi-kr fis', 'name': '한국어'},
|
||||
'cs': {'flag': 'fi fi-cz fis', 'name': 'Čeština'},
|
||||
'es': {'flag': 'fi fi-es fis', 'name': 'Español'},
|
||||
'pt': {'flag': 'fi fi-pt fis', 'name': 'Português (Portugal)'},
|
||||
'pt_BR': {'flag': 'fi fi-br fis', 'name': 'Português (Brasil)'},
|
||||
'pt': {'flag': 'fi fi-pt fis', 'name': 'Português'},
|
||||
'it': {'flag': 'fi fi-it fis', 'name': 'Italiano'},
|
||||
'ja': {'flag': 'fi fi-jp fis', 'name': '日本語'},
|
||||
'zh': {'flag': 'fi fi-cn fis', 'name': '中文 (简体)'},
|
||||
@@ -71,7 +67,6 @@ LANGUAGE_DATA = {
|
||||
'tr': {'flag': 'fi fi-tr fis', 'name': 'Türkçe'},
|
||||
'ar': {'flag': 'fi fi-sa fis', 'name': 'العربية'},
|
||||
'hi': {'flag': 'fi fi-in fis', 'name': 'हिन्दी'},
|
||||
'uk': {'flag': 'fi fi-ua fis', 'name': 'Українська'},
|
||||
}
|
||||
|
||||
|
||||
|
||||
@@ -2,7 +2,6 @@ from os import getenv
|
||||
from copy import deepcopy
|
||||
|
||||
from changedetectionio.blueprint.rss import RSS_FORMAT_TYPES, RSS_CONTENT_FORMAT_DEFAULT
|
||||
from changedetectionio.model.Tags import TagsDict
|
||||
|
||||
from changedetectionio.notification import (
|
||||
default_notification_body,
|
||||
@@ -69,7 +68,7 @@ class model(dict):
|
||||
'schema_version' : 0,
|
||||
'shared_diff_access': False,
|
||||
'strip_ignored_lines': False,
|
||||
'tags': None, # Initialized in __init__ with real datastore_path
|
||||
'tags': {}, #@todo use Tag.model initialisers
|
||||
'webdriver_delay': None , # Extra delay in seconds before extracting text
|
||||
'ui': {
|
||||
'use_page_title_in_list': True,
|
||||
@@ -81,16 +80,10 @@ class model(dict):
|
||||
}
|
||||
}
|
||||
|
||||
def __init__(self, *arg, datastore_path=None, **kw):
|
||||
def __init__(self, *arg, **kw):
|
||||
super(model, self).__init__(*arg, **kw)
|
||||
# Capture any tags data passed in before base_config overwrites the structure
|
||||
existing_tags = self.get('settings', {}).get('application', {}).get('tags') or {}
|
||||
# CRITICAL: deepcopy to avoid sharing mutable objects between instances
|
||||
self.update(deepcopy(self.base_config))
|
||||
# TagsDict requires the real datastore_path at runtime (cannot be set at class-definition time)
|
||||
if datastore_path is None:
|
||||
raise ValueError("App.model() requires 'datastore_path' keyword argument")
|
||||
self['settings']['application']['tags'] = TagsDict(existing_tags, datastore_path=datastore_path)
|
||||
|
||||
|
||||
def parse_headers_from_text_file(filepath):
|
||||
|
||||
@@ -46,26 +46,11 @@ class model(EntityPersistenceMixin, watch_base):
|
||||
super(model, self).__init__(*arg, **kw)
|
||||
|
||||
self['overrides_watch'] = kw.get('default', {}).get('overrides_watch')
|
||||
self['url_match_pattern'] = kw.get('default', {}).get('url_match_pattern', '')
|
||||
|
||||
if kw.get('default'):
|
||||
self.update(kw['default'])
|
||||
del kw['default']
|
||||
|
||||
def matches_url(self, url: str) -> bool:
|
||||
"""Return True if this tag should be auto-applied to the given watch URL.
|
||||
|
||||
Wildcard patterns (*,?,[ ) use fnmatch; anything else is a case-insensitive
|
||||
substring match. Returns False if no pattern is configured.
|
||||
"""
|
||||
import fnmatch
|
||||
pattern = self.get('url_match_pattern', '').strip()
|
||||
if not pattern or not url:
|
||||
return False
|
||||
if any(c in pattern for c in ('*', '?', '[')):
|
||||
return fnmatch.fnmatch(url.lower(), pattern.lower())
|
||||
return pattern.lower() in url.lower()
|
||||
|
||||
# _save_to_disk() method provided by EntityPersistenceMixin
|
||||
# commit() and _get_commit_data() methods inherited from watch_base
|
||||
# Tag uses default _get_commit_data() (includes all keys)
|
||||
|
||||
@@ -1,39 +0,0 @@
|
||||
import os
|
||||
import shutil
|
||||
from pathlib import Path
|
||||
from loguru import logger
|
||||
|
||||
_SENTINEL = object()
|
||||
|
||||
|
||||
class TagsDict(dict):
|
||||
"""Dict subclass that removes the corresponding tag.json file when a tag is deleted."""
|
||||
|
||||
def __init__(self, *args, datastore_path: str | os.PathLike, **kwargs) -> None:
|
||||
self._datastore_path = Path(datastore_path)
|
||||
super().__init__(*args, **kwargs)
|
||||
|
||||
def __delitem__(self, key: str) -> None:
|
||||
super().__delitem__(key)
|
||||
tag_dir = self._datastore_path / key
|
||||
tag_json_file = tag_dir / "tag.json"
|
||||
if not os.path.exists(tag_json_file):
|
||||
logger.critical(f"Aborting deletion of directory '{tag_dir}' because '{tag_json_file}' does not exist.")
|
||||
return
|
||||
try:
|
||||
shutil.rmtree(tag_dir)
|
||||
logger.info(f"Deleted tag directory for tag {key!r}")
|
||||
except FileNotFoundError:
|
||||
pass
|
||||
except OSError as e:
|
||||
logger.error(f"Failed to delete tag directory for tag {key!r}: {e}")
|
||||
|
||||
def pop(self, key: str, default=_SENTINEL):
|
||||
"""Remove and return tag, deleting its tag.json file. Raises KeyError if missing and no default given."""
|
||||
if key in self:
|
||||
value = self[key]
|
||||
del self[key]
|
||||
return value
|
||||
if default is _SENTINEL:
|
||||
raise KeyError(key)
|
||||
return default
|
||||
@@ -43,11 +43,6 @@ from ..html_tools import TRANSLATE_WHITESPACE_TABLE
|
||||
FAVICON_RESAVE_THRESHOLD_SECONDS=86400
|
||||
BROTLI_COMPRESS_SIZE_THRESHOLD = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD', 1024*20))
|
||||
|
||||
# Module-level favicon filename cache: data_dir → basename (or None)
|
||||
# Keyed by data_dir so it survives Watch object recreation, deepcopy, and concurrent requests.
|
||||
# Invalidated explicitly in bump_favicon() when a new favicon is saved.
|
||||
_FAVICON_FILENAME_CACHE: dict = {}
|
||||
|
||||
minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 3))
|
||||
mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
|
||||
|
||||
@@ -388,25 +383,6 @@ class model(EntityPersistenceMixin, watch_base):
|
||||
|
||||
return self.get('fetch_backend')
|
||||
|
||||
@property
|
||||
def fetcher_supports_screenshots(self):
|
||||
"""Return True if the fetcher configured for this watch supports screenshots.
|
||||
|
||||
Resolves 'system' via self._datastore, then checks supports_screenshots on
|
||||
the actual fetcher class. Works for built-in and plugin fetchers alike.
|
||||
"""
|
||||
from changedetectionio import content_fetchers
|
||||
|
||||
fetcher_name = self.get_fetch_backend # already handles is_pdf → html_requests
|
||||
if not fetcher_name or fetcher_name == 'system':
|
||||
fetcher_name = self._datastore['settings']['application'].get('fetch_backend', 'html_requests')
|
||||
|
||||
fetcher_class = getattr(content_fetchers, fetcher_name, None)
|
||||
if fetcher_class is None:
|
||||
return False
|
||||
|
||||
return bool(getattr(fetcher_class, 'supports_screenshots', False))
|
||||
|
||||
@property
|
||||
def is_pdf(self):
|
||||
url = str(self.get("url") or "").lower()
|
||||
@@ -830,8 +806,9 @@ class model(EntityPersistenceMixin, watch_base):
|
||||
with open(fname, 'wb') as f:
|
||||
f.write(decoded)
|
||||
|
||||
# Invalidate module-level favicon filename cache for this watch
|
||||
_FAVICON_FILENAME_CACHE.pop(self.data_dir, None)
|
||||
# Invalidate favicon filename cache
|
||||
if hasattr(self, '_favicon_filename_cache'):
|
||||
delattr(self, '_favicon_filename_cache')
|
||||
|
||||
# A signal that could trigger the socket server to update the browser also
|
||||
watch_check_update = signal('watch_favicon_bump')
|
||||
@@ -846,23 +823,35 @@ class model(EntityPersistenceMixin, watch_base):
|
||||
|
||||
def get_favicon_filename(self) -> str | None:
|
||||
"""
|
||||
Find any favicon.* file in the watch data directory.
|
||||
Find any favicon.* file in the current working directory
|
||||
and return the contents of the newest one.
|
||||
|
||||
Uses a module-level cache keyed by data_dir to survive Watch object recreation,
|
||||
deepcopy (which drops instance attrs), and concurrent request races.
|
||||
Invalidated by bump_favicon() when a new favicon is saved.
|
||||
MEMORY LEAK FIX: Cache the result to avoid repeated glob.glob() operations.
|
||||
glob.glob() causes millions of fnmatch allocations when called for every watch on page load.
|
||||
|
||||
Returns:
|
||||
str: Basename of the favicon file, or None if not found.
|
||||
str: Basename of the newest favicon file, or None if not found.
|
||||
"""
|
||||
if self.data_dir in _FAVICON_FILENAME_CACHE:
|
||||
return _FAVICON_FILENAME_CACHE[self.data_dir]
|
||||
# Check cache first (prevents 26M+ allocations from repeated glob operations)
|
||||
cache_key = '_favicon_filename_cache'
|
||||
if hasattr(self, cache_key):
|
||||
return getattr(self, cache_key)
|
||||
|
||||
import glob
|
||||
|
||||
# Search for all favicon.* files
|
||||
files = glob.glob(os.path.join(self.data_dir, "favicon.*"))
|
||||
fname = os.path.basename(files[0]) if files else None
|
||||
_FAVICON_FILENAME_CACHE[self.data_dir] = fname
|
||||
return fname
|
||||
|
||||
if not files:
|
||||
result = None
|
||||
else:
|
||||
# Find the newest by modification time
|
||||
newest_file = max(files, key=os.path.getmtime)
|
||||
result = os.path.basename(newest_file)
|
||||
|
||||
# Cache the result
|
||||
setattr(self, cache_key, result)
|
||||
return result
|
||||
|
||||
def get_screenshot_as_thumbnail(self, max_age=3200):
|
||||
"""Return path to a square thumbnail of the most recent screenshot.
|
||||
@@ -1193,13 +1182,18 @@ class model(EntityPersistenceMixin, watch_base):
|
||||
def compile_error_texts(self, has_proxies=None):
|
||||
"""Compile error texts for this watch.
|
||||
Accepts has_proxies parameter to ensure it works even outside app context"""
|
||||
from flask import url_for, has_request_context
|
||||
from flask import url_for
|
||||
from markupsafe import Markup
|
||||
|
||||
output = [] # Initialize as list since we're using append
|
||||
last_error = self.get('last_error','')
|
||||
|
||||
has_app_context = has_request_context()
|
||||
try:
|
||||
url_for('settings.settings_page')
|
||||
except Exception as e:
|
||||
has_app_context = False
|
||||
else:
|
||||
has_app_context = True
|
||||
|
||||
# has app+request context, we can use url_for()
|
||||
if has_app_context:
|
||||
|
||||
@@ -6,8 +6,6 @@ from .persistence import EntityPersistenceMixin, _determine_entity_type
|
||||
|
||||
__all__ = ['EntityPersistenceMixin', 'watch_base']
|
||||
|
||||
from ..browser_steps.browser_steps import browser_steps_get_valid_steps
|
||||
|
||||
USE_SYSTEM_DEFAULT_NOTIFICATION_FORMAT_FOR_WATCH = 'System default'
|
||||
CONDITIONS_MATCH_LOGIC_DEFAULT = 'ALL'
|
||||
|
||||
@@ -366,10 +364,6 @@ class watch_base(dict):
|
||||
self._mark_field_as_edited(key)
|
||||
|
||||
def update(self, *args, **kwargs):
|
||||
|
||||
if args and args[0].get('browser_steps'):
|
||||
args[0]['browser_steps'] = browser_steps_get_valid_steps(args[0].get('browser_steps'))
|
||||
|
||||
"""Override dict.update() to track modifications to writable fields."""
|
||||
# Call parent update first
|
||||
super().update(*args, **kwargs)
|
||||
@@ -382,7 +376,6 @@ class watch_base(dict):
|
||||
for key in kwargs.keys():
|
||||
self._mark_field_as_edited(key)
|
||||
|
||||
|
||||
def pop(self, key, *args):
|
||||
"""Override dict.pop() to track removal of writable fields."""
|
||||
result = super().pop(key, *args)
|
||||
|
||||
@@ -54,152 +54,34 @@ def _check_cascading_vars(datastore, var_name, watch):
|
||||
return None
|
||||
|
||||
|
||||
class FormattableTimestamp(str):
|
||||
"""
|
||||
A str subclass representing a formatted datetime. As a plain string it renders
|
||||
with the default format, but can also be called with a custom format argument
|
||||
in Jinja2 templates:
|
||||
|
||||
{{ change_datetime }} → '2024-01-15 10:30:00 UTC'
|
||||
{{ change_datetime(format='%Y') }} → '2024'
|
||||
{{ change_datetime(format='%A') }} → 'Monday'
|
||||
{{ change_datetime(format='%Y-%m-%d') }} → '2024-01-15'
|
||||
|
||||
Being a str subclass means it is natively JSON serializable.
|
||||
"""
|
||||
_DEFAULT_FORMAT = '%Y-%m-%d %H:%M:%S %Z'
|
||||
|
||||
def __new__(cls, timestamp):
|
||||
dt = datetime.datetime.fromtimestamp(int(timestamp), tz=pytz.UTC)
|
||||
local_tz = datetime.datetime.now().astimezone().tzinfo
|
||||
dt_local = dt.astimezone(local_tz)
|
||||
try:
|
||||
formatted = dt_local.strftime(cls._DEFAULT_FORMAT)
|
||||
except Exception:
|
||||
formatted = dt_local.isoformat()
|
||||
instance = super().__new__(cls, formatted)
|
||||
instance._dt = dt_local
|
||||
return instance
|
||||
|
||||
def __call__(self, format=_DEFAULT_FORMAT):
|
||||
try:
|
||||
return self._dt.strftime(format)
|
||||
except Exception:
|
||||
return self._dt.isoformat()
|
||||
|
||||
|
||||
class FormattableExtract(str):
|
||||
"""
|
||||
A str subclass that holds only the extracted changed fragments from a diff.
|
||||
Used for {{diff_changed_from}} and {{diff_changed_to}} tokens.
|
||||
|
||||
{{ diff_changed_from }} → old value(s) only, e.g. "$99.99"
|
||||
{{ diff_changed_to }} → new value(s) only, e.g. "$109.99"
|
||||
|
||||
Multiple changed fragments are joined with newlines.
|
||||
Being a str subclass means it is natively JSON serializable.
|
||||
"""
|
||||
def __new__(cls, prev_snapshot, current_snapshot, extract_fn):
|
||||
if prev_snapshot or current_snapshot:
|
||||
from changedetectionio import diff as diff_module
|
||||
raw = diff_module.render_diff(prev_snapshot, current_snapshot, word_diff=True)
|
||||
extracted = extract_fn(raw)
|
||||
else:
|
||||
extracted = ''
|
||||
instance = super().__new__(cls, extracted)
|
||||
return instance
|
||||
|
||||
|
||||
class FormattableDiff(str):
|
||||
"""
|
||||
A str subclass representing a rendered diff. As a plain string it renders
|
||||
with the default options for that variant, but can be called with custom
|
||||
arguments in Jinja2 templates:
|
||||
|
||||
{{ diff }} → default diff output
|
||||
{{ diff(lines=5) }} → truncate to 5 lines
|
||||
{{ diff(added_only=true) }} → only show added lines
|
||||
{{ diff(removed_only=true) }} → only show removed lines
|
||||
{{ diff(context=3) }} → 3 lines of context around changes
|
||||
{{ diff(word_diff=false) }} → line-level diff instead of word-level
|
||||
{{ diff(lines=10, added_only=true) }} → combine args
|
||||
{{ diff_added(lines=5) }} → works on any diff_* variant too
|
||||
|
||||
Being a str subclass means it is natively JSON serializable.
|
||||
"""
|
||||
def __new__(cls, prev_snapshot, current_snapshot, **base_kwargs):
|
||||
if prev_snapshot or current_snapshot:
|
||||
from changedetectionio import diff as diff_module
|
||||
rendered = diff_module.render_diff(prev_snapshot, current_snapshot, **base_kwargs)
|
||||
else:
|
||||
rendered = ''
|
||||
instance = super().__new__(cls, rendered)
|
||||
instance._prev = prev_snapshot
|
||||
instance._current = current_snapshot
|
||||
instance._base_kwargs = base_kwargs
|
||||
return instance
|
||||
|
||||
def __call__(self, lines=None, added_only=False, removed_only=False, context=0,
|
||||
word_diff=None, case_insensitive=False, ignore_junk=False):
|
||||
from changedetectionio import diff as diff_module
|
||||
kwargs = dict(self._base_kwargs)
|
||||
|
||||
if added_only:
|
||||
kwargs['include_removed'] = False
|
||||
if removed_only:
|
||||
kwargs['include_added'] = False
|
||||
if context:
|
||||
kwargs['context_lines'] = int(context)
|
||||
if word_diff is not None:
|
||||
kwargs['word_diff'] = bool(word_diff)
|
||||
if case_insensitive:
|
||||
kwargs['case_insensitive'] = True
|
||||
if ignore_junk:
|
||||
kwargs['ignore_junk'] = True
|
||||
|
||||
result = diff_module.render_diff(self._prev or '', self._current or '', **kwargs)
|
||||
|
||||
if lines is not None:
|
||||
result = '\n'.join(result.splitlines()[:int(lines)])
|
||||
|
||||
return result
|
||||
|
||||
|
||||
|
||||
# What is passed around as notification context, also used as the complete list of valid {{ tokens }}
|
||||
class NotificationContextData(dict):
|
||||
def __init__(self, initial_data=None, **kwargs):
|
||||
# ValidateJinja2Template() validates against the keynames of this dict to check for valid tokens in the body (user submission)
|
||||
super().__init__({
|
||||
'base_url': None,
|
||||
'change_datetime': FormattableTimestamp(time.time()),
|
||||
'current_snapshot': None,
|
||||
'diff': FormattableDiff('', ''),
|
||||
'diff_clean': FormattableDiff('', '', include_change_type_prefix=False),
|
||||
'diff_added': FormattableDiff('', '', include_removed=False),
|
||||
'diff_added_clean': FormattableDiff('', '', include_removed=False, include_change_type_prefix=False),
|
||||
'diff_full': FormattableDiff('', '', include_equal=True),
|
||||
'diff_full_clean': FormattableDiff('', '', include_equal=True, include_change_type_prefix=False),
|
||||
'diff_patch': FormattableDiff('', '', patch_format=True),
|
||||
'diff_removed': FormattableDiff('', '', include_added=False),
|
||||
'diff_removed_clean': FormattableDiff('', '', include_added=False, include_change_type_prefix=False),
|
||||
'diff_changed_from': FormattableExtract('', '', extract_fn=lambda x: x),
|
||||
'diff_changed_to': FormattableExtract('', '', extract_fn=lambda x: x),
|
||||
'diff': None,
|
||||
'diff_clean': None,
|
||||
'diff_added': None,
|
||||
'diff_added_clean': None,
|
||||
'diff_full': None,
|
||||
'diff_full_clean': None,
|
||||
'diff_patch': None,
|
||||
'diff_removed': None,
|
||||
'diff_removed_clean': None,
|
||||
'diff_url': None,
|
||||
'markup_text_links_to_html_links': False, # If automatic conversion of plaintext to HTML should happen
|
||||
'notification_timestamp': time.time(),
|
||||
'prev_snapshot': None,
|
||||
'preview_url': None,
|
||||
'screenshot': None,
|
||||
'triggered_text': None,
|
||||
'timestamp_from': None,
|
||||
'timestamp_to': None,
|
||||
'triggered_text': None,
|
||||
'uuid': 'XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX', # Converted to 'watch_uuid' in create_notification_parameters
|
||||
'watch_mime_type': None,
|
||||
'watch_tag': None,
|
||||
'watch_title': None,
|
||||
'watch_url': 'https://WATCH-PLACE-HOLDER/',
|
||||
'watch_uuid': 'XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX', # Converted to 'watch_uuid' in create_notification_parameters
|
||||
})
|
||||
|
||||
# Apply any initial data passed in
|
||||
@@ -221,7 +103,7 @@ class NotificationContextData(dict):
|
||||
So we can test the output in the notification body
|
||||
"""
|
||||
for key in self.keys():
|
||||
if key in ['uuid', 'time', 'watch_uuid', 'change_datetime'] or key.startswith('diff'):
|
||||
if key in ['uuid', 'time', 'watch_uuid']:
|
||||
continue
|
||||
rand_str = 'RANDOM-PLACEHOLDER-'+''.join(random.choices(string.ascii_letters + string.digits, k=12))
|
||||
self[key] = rand_str
|
||||
@@ -233,6 +115,24 @@ class NotificationContextData(dict):
|
||||
|
||||
super().__setitem__(key, value)
|
||||
|
||||
def timestamp_to_localtime(timestamp):
|
||||
# Format the date using locale-aware formatting with timezone
|
||||
dt = datetime.datetime.fromtimestamp(int(timestamp))
|
||||
dt = dt.replace(tzinfo=pytz.UTC)
|
||||
|
||||
# Get local timezone-aware datetime
|
||||
local_tz = datetime.datetime.now().astimezone().tzinfo
|
||||
local_dt = dt.astimezone(local_tz)
|
||||
|
||||
# Format date with timezone - using strftime for locale awareness
|
||||
try:
|
||||
formatted_date = local_dt.strftime('%Y-%m-%d %H:%M:%S %Z')
|
||||
except:
|
||||
# Fallback if locale issues
|
||||
formatted_date = local_dt.isoformat()
|
||||
|
||||
return formatted_date
|
||||
|
||||
def add_rendered_diff_to_notification_vars(notification_scan_text:str, prev_snapshot:str, current_snapshot:str, word_diff:bool):
|
||||
"""
|
||||
Efficiently renders only the diff placeholders that are actually used in the notification text.
|
||||
@@ -250,12 +150,13 @@ def add_rendered_diff_to_notification_vars(notification_scan_text:str, prev_snap
|
||||
Returns:
|
||||
dict: Only the diff placeholders that were found in notification_scan_text, with rendered content
|
||||
"""
|
||||
from changedetectionio import diff
|
||||
import re
|
||||
from functools import lru_cache
|
||||
|
||||
now = time.time()
|
||||
|
||||
# Define base kwargs for each diff variant — these become the stored defaults
|
||||
# on the FormattableDiff object, so {{ diff(lines=5) }} overrides on top of them
|
||||
# Define specifications for each diff variant
|
||||
diff_specs = {
|
||||
'diff': {'word_diff': word_diff},
|
||||
'diff_clean': {'word_diff': word_diff, 'include_change_type_prefix': False},
|
||||
@@ -268,27 +169,23 @@ def add_rendered_diff_to_notification_vars(notification_scan_text:str, prev_snap
|
||||
'diff_removed_clean': {'word_diff': word_diff, 'include_added': False, 'include_change_type_prefix': False},
|
||||
}
|
||||
|
||||
from changedetectionio.diff import extract_changed_from, extract_changed_to
|
||||
extract_specs = {
|
||||
'diff_changed_from': extract_changed_from,
|
||||
'diff_changed_to': extract_changed_to,
|
||||
}
|
||||
# Memoize render_diff to avoid duplicate renders with same kwargs
|
||||
@lru_cache(maxsize=4)
|
||||
def cached_render(kwargs_tuple):
|
||||
return diff.render_diff(prev_snapshot, current_snapshot, **dict(kwargs_tuple))
|
||||
|
||||
ret = {}
|
||||
rendered_count = 0
|
||||
# Only create FormattableDiff/FormattableExtract objects for diff keys actually used in the notification text
|
||||
# Only check and render diff keys that exist in NotificationContextData
|
||||
for key in NotificationContextData().keys():
|
||||
if not key.startswith('diff'):
|
||||
continue
|
||||
pattern = rf"(?<![A-Za-z0-9_]){re.escape(key)}(?![A-Za-z0-9_])"
|
||||
if not re.search(pattern, notification_scan_text, re.IGNORECASE):
|
||||
continue
|
||||
if key in diff_specs:
|
||||
ret[key] = FormattableDiff(prev_snapshot, current_snapshot, **diff_specs[key])
|
||||
rendered_count += 1
|
||||
elif key in extract_specs:
|
||||
ret[key] = FormattableExtract(prev_snapshot, current_snapshot, extract_fn=extract_specs[key])
|
||||
rendered_count += 1
|
||||
if key.startswith('diff') and key in diff_specs:
|
||||
# Check if this placeholder is actually used in the notification text
|
||||
pattern = rf"(?<![A-Za-z0-9_]){re.escape(key)}(?![A-Za-z0-9_])"
|
||||
if re.search(pattern, notification_scan_text, re.IGNORECASE):
|
||||
kwargs = diff_specs[key]
|
||||
# Convert dict to sorted tuple for cache key (handles duplicate kwarg combinations)
|
||||
ret[key] = cached_render(tuple(sorted(kwargs.items())))
|
||||
rendered_count += 1
|
||||
|
||||
if rendered_count:
|
||||
logger.trace(f"Rendered {rendered_count} diff placeholder(s) {sorted(ret.keys())} in {time.time() - now:.3f}s")
|
||||
@@ -301,7 +198,7 @@ def set_basic_notification_vars(current_snapshot, prev_snapshot, watch, triggere
|
||||
'current_snapshot': current_snapshot,
|
||||
'prev_snapshot': prev_snapshot,
|
||||
'screenshot': watch.get_screenshot() if watch and watch.get('notification_screenshot') else None,
|
||||
'change_datetime': FormattableTimestamp(timestamp_changed) if timestamp_changed else None,
|
||||
'change_datetime': timestamp_to_localtime(timestamp_changed) if timestamp_changed else None,
|
||||
'triggered_text': triggered_text,
|
||||
'uuid': watch.get('uuid') if watch else None,
|
||||
'watch_url': watch.get('url') if watch else None,
|
||||
|
||||
@@ -129,109 +129,6 @@ class ChangeDetectionSpec:
|
||||
"""
|
||||
pass
|
||||
|
||||
@hookspec
|
||||
def update_handler_alter(update_handler, watch, datastore):
|
||||
"""Modify or wrap the update_handler before it processes a watch.
|
||||
|
||||
This hook is called after the update_handler (perform_site_check instance) is created
|
||||
but before it calls call_browser() and run_changedetection(). Plugins can use this to:
|
||||
- Wrap the handler to add logging/metrics
|
||||
- Modify handler configuration
|
||||
- Add custom preprocessing logic
|
||||
|
||||
Args:
|
||||
update_handler: The perform_site_check instance that will process the watch
|
||||
watch: The watch dict being processed
|
||||
datastore: The application datastore
|
||||
|
||||
Returns:
|
||||
object or None: Return a modified/wrapped handler, or None to keep the original.
|
||||
If multiple plugins return handlers, they are chained in registration order.
|
||||
"""
|
||||
pass
|
||||
|
||||
@hookspec
|
||||
def update_finalize(update_handler, watch, datastore, processing_exception):
|
||||
"""Called after watch processing completes (success or failure).
|
||||
|
||||
This hook is called in the finally block after all processing is complete,
|
||||
allowing plugins to perform cleanup, update metrics, or log final status.
|
||||
|
||||
The plugin can access update_handler.last_logging_insert_id if it was stored
|
||||
during update_handler_alter, and use processing_exception to determine if
|
||||
the processing succeeded or failed.
|
||||
|
||||
Args:
|
||||
update_handler: The perform_site_check instance (may be None if creation failed)
|
||||
watch: The watch dict that was processed (may be None if not loaded)
|
||||
datastore: The application datastore
|
||||
processing_exception: The exception from the main processing block, or None if successful.
|
||||
This does NOT include cleanup exceptions - only exceptions from
|
||||
the actual watch processing (fetch, diff, etc).
|
||||
|
||||
Returns:
|
||||
None: This hook doesn't return a value
|
||||
"""
|
||||
pass
|
||||
|
||||
@hookspec
|
||||
def get_html_head_extras():
|
||||
"""Return HTML to inject into the <head> of every page via base.html.
|
||||
|
||||
Plugins can use this to add <script>, <style>, or <link> tags that should
|
||||
be present on all pages. Return a raw HTML string or None.
|
||||
|
||||
IMPORTANT: Always use Flask's url_for() for any src/href URLs so that
|
||||
sub-path deployments (nginx reverse proxy with USE_X_SETTINGS / X-Forwarded-Prefix)
|
||||
work correctly. This hook is called inside a request context so url_for() is
|
||||
always available.
|
||||
|
||||
For small amounts of CSS/JS, return them inline — no file-serving needed::
|
||||
|
||||
from changedetectionio.pluggy_interface import hookimpl
|
||||
|
||||
@hookimpl
|
||||
def get_html_head_extras(self):
|
||||
return (
|
||||
'<style>.my-module-banner { color: red; }</style>\\n'
|
||||
'<script>console.log("my_module_content loaded");</script>'
|
||||
)
|
||||
|
||||
For larger assets, register your own lightweight Flask routes in the plugin
|
||||
module and point to them with url_for() so the sub-path prefix is handled
|
||||
automatically::
|
||||
|
||||
from flask import url_for, Response
|
||||
from changedetectionio.pluggy_interface import hookimpl
|
||||
from changedetectionio.flask_app import app as _app
|
||||
|
||||
MY_CSS = ".my-module-example { color: red; }"
|
||||
MY_JS = "console.log('my_module_content loaded');"
|
||||
|
||||
@_app.route('/my_module_content/css')
|
||||
def my_module_content_css():
|
||||
return Response(MY_CSS, mimetype='text/css',
|
||||
headers={'Cache-Control': 'max-age=3600'})
|
||||
|
||||
@_app.route('/my_module_content/js')
|
||||
def my_module_content_js():
|
||||
return Response(MY_JS, mimetype='application/javascript',
|
||||
headers={'Cache-Control': 'max-age=3600'})
|
||||
|
||||
@hookimpl
|
||||
def get_html_head_extras(self):
|
||||
css = url_for('my_module_content_css')
|
||||
js = url_for('my_module_content_js')
|
||||
return (
|
||||
f'<link rel="stylesheet" href="{css}">\\n'
|
||||
f'<script src="{js}" defer></script>'
|
||||
)
|
||||
|
||||
Returns:
|
||||
str or None: Raw HTML string to inject inside <head>, or None
|
||||
"""
|
||||
pass
|
||||
|
||||
|
||||
# Set up Plugin Manager
|
||||
plugin_manager = pluggy.PluginManager(PLUGIN_NAMESPACE)
|
||||
@@ -602,82 +499,4 @@ def get_plugin_template_paths():
|
||||
template_paths.append(templates_dir)
|
||||
logger.debug(f"Added plugin template path: {templates_dir}")
|
||||
|
||||
return template_paths
|
||||
|
||||
|
||||
def apply_update_handler_alter(update_handler, watch, datastore):
|
||||
"""Apply update_handler_alter hooks from all plugins.
|
||||
|
||||
Allows plugins to wrap or modify the update_handler before it processes a watch.
|
||||
Multiple plugins can chain modifications - each plugin receives the result from
|
||||
the previous plugin.
|
||||
|
||||
Args:
|
||||
update_handler: The perform_site_check instance to potentially modify
|
||||
watch: The watch dict being processed
|
||||
datastore: The application datastore
|
||||
|
||||
Returns:
|
||||
object: The (potentially modified/wrapped) update_handler
|
||||
"""
|
||||
# Get all plugins that implement the update_handler_alter hook
|
||||
results = plugin_manager.hook.update_handler_alter(
|
||||
update_handler=update_handler,
|
||||
watch=watch,
|
||||
datastore=datastore
|
||||
)
|
||||
|
||||
# Chain results - each plugin gets the result from the previous one
|
||||
current_handler = update_handler
|
||||
if results:
|
||||
for result in results:
|
||||
if result is not None:
|
||||
logger.debug(f"Plugin modified update_handler for watch {watch.get('uuid')}")
|
||||
current_handler = result
|
||||
|
||||
return current_handler
|
||||
|
||||
|
||||
def apply_update_finalize(update_handler, watch, datastore, processing_exception):
|
||||
"""Apply update_finalize hooks from all plugins.
|
||||
|
||||
Called in the finally block after watch processing completes, allowing plugins
|
||||
to perform cleanup, update metrics, or log final status.
|
||||
|
||||
Args:
|
||||
update_handler: The perform_site_check instance (may be None)
|
||||
watch: The watch dict that was processed (may be None)
|
||||
datastore: The application datastore
|
||||
processing_exception: The exception from processing, or None if successful
|
||||
|
||||
Returns:
|
||||
None
|
||||
"""
|
||||
try:
|
||||
# Call all plugins that implement the update_finalize hook
|
||||
plugin_manager.hook.update_finalize(
|
||||
update_handler=update_handler,
|
||||
watch=watch,
|
||||
datastore=datastore,
|
||||
processing_exception=processing_exception
|
||||
)
|
||||
except Exception as e:
|
||||
# Don't let plugin errors crash the worker
|
||||
logger.error(f"Error in update_finalize hook: {e}")
|
||||
logger.exception(f"update_finalize hook exception details:")
|
||||
|
||||
|
||||
def collect_html_head_extras():
|
||||
"""Collect and combine HTML head extras from all plugins.
|
||||
|
||||
Called from a Flask template global so it always runs inside a request context.
|
||||
This means url_for() works correctly in plugin implementations, including when the
|
||||
app is deployed under a sub-path via USE_X_SETTINGS / X-Forwarded-Prefix (ProxyFix
|
||||
sets SCRIPT_NAME so url_for() automatically prepends the prefix).
|
||||
|
||||
Returns:
|
||||
str: Combined HTML string to inject inside <head>, or empty string
|
||||
"""
|
||||
results = plugin_manager.hook.get_html_head_extras()
|
||||
parts = [r for r in results if r]
|
||||
return "\n".join(parts) if parts else ""
|
||||
return template_paths
|
||||
@@ -9,15 +9,6 @@ Some suggestions for the future
|
||||
|
||||
- `graphical`
|
||||
|
||||
## API schema extension (`api.yaml`)
|
||||
|
||||
A processor can extend the Watch/Tag API schema by placing an `api.yaml` alongside its `__init__.py`.
|
||||
Define a `components.schemas.processor_config_<name>` entry and it will be merged into `WatchBase` at startup,
|
||||
making `processor_config_<name>` a valid field on all watch create/update API calls.
|
||||
The fully merged spec is served live at `/api/v1/full-spec`.
|
||||
|
||||
See `restock_diff/api.yaml` for a working example.
|
||||
|
||||
## Todo
|
||||
|
||||
- Make each processor return a extra list of sub-processed (so you could configure a single processor in different ways)
|
||||
|
||||
@@ -341,18 +341,6 @@ def get_processor_descriptions():
|
||||
return descriptions
|
||||
|
||||
|
||||
def wcag_text_color(hex_bg: str) -> str:
|
||||
"""Return #000000 or #ffffff for maximum WCAG contrast against hex_bg."""
|
||||
hex_bg = hex_bg.lstrip('#')
|
||||
if len(hex_bg) != 6:
|
||||
return '#000000'
|
||||
r, g, b = (int(hex_bg[i:i+2], 16) / 255 for i in (0, 2, 4))
|
||||
def lin(c):
|
||||
return c / 12.92 if c <= 0.04045 else ((c + 0.055) / 1.055) ** 2.4
|
||||
L = 0.2126 * lin(r) + 0.7152 * lin(g) + 0.0722 * lin(b)
|
||||
return '#000000' if L > 0.179 else '#ffffff'
|
||||
|
||||
|
||||
def generate_processor_badge_colors(processor_name):
|
||||
"""
|
||||
Generate consistent colors for a processor badge based on its name.
|
||||
|
||||
@@ -1,15 +1,10 @@
|
||||
import asyncio
|
||||
import re
|
||||
import hashlib
|
||||
|
||||
from changedetectionio.browser_steps.browser_steps import browser_steps_get_valid_steps
|
||||
from changedetectionio.content_fetchers.base import Fetcher
|
||||
from changedetectionio.strtobool import strtobool
|
||||
from changedetectionio.validate_url import is_private_hostname
|
||||
from copy import deepcopy
|
||||
from abc import abstractmethod
|
||||
import os
|
||||
from urllib.parse import urlparse
|
||||
from loguru import logger
|
||||
|
||||
SCREENSHOT_FORMAT_JPEG = 'JPEG'
|
||||
@@ -98,23 +93,6 @@ class difference_detection_processor():
|
||||
self.last_raw_content_checksum = None
|
||||
|
||||
|
||||
async def validate_iana_url(self):
|
||||
"""Pre-flight SSRF check — runs DNS lookup in executor to avoid blocking the event loop.
|
||||
Covers all fetchers (requests, playwright, puppeteer, plugins) since every fetch goes
|
||||
through call_browser().
|
||||
"""
|
||||
if strtobool(os.getenv('ALLOW_IANA_RESTRICTED_ADDRESSES', 'false')):
|
||||
return
|
||||
parsed = urlparse(self.watch.link)
|
||||
if not parsed.hostname:
|
||||
return
|
||||
loop = asyncio.get_running_loop()
|
||||
if await loop.run_in_executor(None, is_private_hostname, parsed.hostname):
|
||||
raise Exception(
|
||||
f"Fetch blocked: '{self.watch.link}' resolves to a private/reserved IP address. "
|
||||
f"Set ALLOW_IANA_RESTRICTED_ADDRESSES=true to allow."
|
||||
)
|
||||
|
||||
async def call_browser(self, preferred_proxy_id=None):
|
||||
|
||||
from requests.structures import CaseInsensitiveDict
|
||||
@@ -128,8 +106,6 @@ class difference_detection_processor():
|
||||
"file:// type access is denied for security reasons."
|
||||
)
|
||||
|
||||
await self.validate_iana_url()
|
||||
|
||||
# Requests, playwright, other browser via wss:// etc, fetch_extra_something
|
||||
prefer_fetch_backend = self.watch.get('fetch_backend', 'system')
|
||||
|
||||
@@ -193,7 +169,7 @@ class difference_detection_processor():
|
||||
)
|
||||
|
||||
if self.watch.has_browser_steps:
|
||||
self.fetcher.browser_steps = browser_steps_get_valid_steps(self.watch.get('browser_steps', []))
|
||||
self.fetcher.browser_steps = self.watch.get('browser_steps', [])
|
||||
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
|
||||
@@ -260,16 +236,6 @@ class difference_detection_processor():
|
||||
# @todo .quit here could go on close object, so we can run JS if change-detected
|
||||
await self.fetcher.quit(watch=self.watch)
|
||||
|
||||
# Sanitize lone surrogates - these can appear when servers return malformed/mixed-encoding
|
||||
# content that gets decoded into surrogate characters (e.g. \udcad). Without this,
|
||||
# encode('utf-8') raises UnicodeEncodeError downstream in checksums, diffs, file writes, etc.
|
||||
# Covers all fetchers (requests, playwright, puppeteer, selenium) in one place.
|
||||
# Also note: By this point we SHOULD know the original encoding so it can safely convert to utf-8 for the rest of the app.
|
||||
# See: https://github.com/dgtlmoon/changedetection.io/issues/3952
|
||||
|
||||
if self.fetcher.content and isinstance(self.fetcher.content, str):
|
||||
self.fetcher.content = self.fetcher.content.encode('utf-8', errors='replace').decode('utf-8')
|
||||
|
||||
# After init, call run_changedetection() which will do the actual change-detection
|
||||
|
||||
def get_extra_watch_config(self, filename):
|
||||
|
||||
@@ -42,7 +42,10 @@ def render_form(watch, datastore, request, url_for, render_template, flash, redi
|
||||
# Get error information for the template
|
||||
screenshot_url = watch.get_screenshot()
|
||||
|
||||
is_html_webdriver = watch.fetcher_supports_screenshots
|
||||
system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
|
||||
is_html_webdriver = False
|
||||
if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
|
||||
is_html_webdriver = True
|
||||
|
||||
password_enabled_and_share_is_off = False
|
||||
if datastore.data['settings']['application'].get('password') or os.getenv("SALTED_PASS", False):
|
||||
|
||||
@@ -100,13 +100,7 @@ class guess_stream_type():
|
||||
if any(s in http_content_header for s in RSS_XML_CONTENT_TYPES):
|
||||
self.is_rss = True
|
||||
elif any(s in http_content_header for s in JSON_CONTENT_TYPES):
|
||||
# JSONP detection: server claims application/json but content is actually JSONP (e.g. cb({...}))
|
||||
# A JSONP response starts with an identifier followed by '(' - not valid JSON
|
||||
if re.match(r'^\w[\w.]*\s*\(', test_content):
|
||||
logger.warning(f"Content-Type header claims JSON but content looks like JSONP (starts with identifier+parenthesis) - treating as plaintext")
|
||||
self.is_plaintext = True
|
||||
else:
|
||||
self.is_json = True
|
||||
self.is_json = True
|
||||
elif 'pdf' in magic_content_header:
|
||||
self.is_pdf = True
|
||||
# magic will call a rss document 'xml'
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
|
||||
from babel.numbers import parse_decimal
|
||||
from changedetectionio.model.Watch import model as BaseWatch
|
||||
from decimal import Decimal, InvalidOperation
|
||||
from typing import Union
|
||||
import re
|
||||
|
||||
@@ -11,8 +10,6 @@ supports_browser_steps = True
|
||||
supports_text_filters_and_triggers = True
|
||||
supports_text_filters_and_triggers_elements = True
|
||||
supports_request_type = True
|
||||
_price_re = re.compile(r"Price:\s*(\d+(?:\.\d+)?)", re.IGNORECASE)
|
||||
|
||||
|
||||
class Restock(dict):
|
||||
|
||||
@@ -34,7 +31,6 @@ class Restock(dict):
|
||||
|
||||
if standardized_value:
|
||||
# Convert to float
|
||||
# @todo locale needs to be the locale of the webpage
|
||||
return float(parse_decimal(standardized_value, locale='en'))
|
||||
|
||||
return None
|
||||
@@ -66,22 +62,15 @@ class Restock(dict):
|
||||
|
||||
super().__setitem__(key, value)
|
||||
|
||||
def get_price_from_history_str(history_str):
|
||||
m = _price_re.search(history_str)
|
||||
if not m:
|
||||
return None
|
||||
|
||||
try:
|
||||
return str(Decimal(m.group(1)))
|
||||
except InvalidOperation:
|
||||
return None
|
||||
|
||||
|
||||
class Watch(BaseWatch):
|
||||
def __init__(self, *arg, **kw):
|
||||
super().__init__(*arg, **kw)
|
||||
self['restock'] = Restock(kw['default']['restock']) if kw.get('default') and kw['default'].get('restock') else Restock()
|
||||
|
||||
self['restock_settings'] = kw['default']['restock_settings'] if kw.get('default',{}).get('restock_settings') else {
|
||||
'follow_price_changes': True,
|
||||
'in_stock_processing' : 'in_stock_only'
|
||||
} #@todo update
|
||||
|
||||
def clear_watch(self):
|
||||
super().clear_watch()
|
||||
@@ -90,27 +79,13 @@ class Watch(BaseWatch):
|
||||
def extra_notification_token_values(self):
|
||||
values = super().extra_notification_token_values()
|
||||
values['restock'] = self.get('restock', {})
|
||||
|
||||
values['restock']['previous_price'] = None
|
||||
if self.history_n >= 2:
|
||||
history = self.history
|
||||
if history and len(history) >=2:
|
||||
"""Unfortunately for now timestamp is stored as string key"""
|
||||
sorted_keys = sorted(list(history), key=lambda x: int(x))
|
||||
sorted_keys.reverse()
|
||||
|
||||
price_str = self.get_history_snapshot(timestamp=sorted_keys[-1])
|
||||
if price_str:
|
||||
values['restock']['previous_price'] = get_price_from_history_str(price_str)
|
||||
return values
|
||||
|
||||
def extra_notification_token_placeholder_info(self):
|
||||
values = super().extra_notification_token_placeholder_info()
|
||||
|
||||
values.append(('restock.price', "Price detected"))
|
||||
values.append(('restock.in_stock', "In stock status"))
|
||||
values.append(('restock.original_price', "Original price at first check"))
|
||||
values.append(('restock.previous_price', "Previous price in history"))
|
||||
|
||||
return values
|
||||
|
||||
|
||||
@@ -1,149 +0,0 @@
|
||||
components:
|
||||
schemas:
|
||||
processor_config_restock_diff:
|
||||
type: object
|
||||
description: Configuration for the restock_diff processor (restock and price tracking)
|
||||
properties:
|
||||
in_stock_processing:
|
||||
type: string
|
||||
enum: [in_stock_only, all_changes, 'off']
|
||||
default: in_stock_only
|
||||
description: |
|
||||
When to trigger on stock changes:
|
||||
- `in_stock_only`: Only trigger on Out Of Stock -> In Stock transitions
|
||||
- `all_changes`: Trigger on any availability change
|
||||
- `off`: Disable stock/availability tracking
|
||||
follow_price_changes:
|
||||
type: boolean
|
||||
default: true
|
||||
description: Monitor and track price changes
|
||||
price_change_min:
|
||||
type: [number, 'null']
|
||||
description: Trigger a notification when the price drops below this value
|
||||
price_change_max:
|
||||
type: [number, 'null']
|
||||
description: Trigger a notification when the price rises above this value
|
||||
price_change_threshold_percent:
|
||||
type: [number, 'null']
|
||||
minimum: 0
|
||||
maximum: 100
|
||||
description: Minimum price change percentage since the original price to trigger a notification
|
||||
|
||||
paths:
|
||||
/watch:
|
||||
post:
|
||||
x-code-samples:
|
||||
- lang: 'curl'
|
||||
label: 'Restock & price tracking'
|
||||
source: |
|
||||
curl -X POST "http://localhost:5000/api/v1/watch" \
|
||||
-H "x-api-key: YOUR_API_KEY" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"url": "https://example.com/product",
|
||||
"processor": "restock_diff",
|
||||
"processor_config_restock_diff": {
|
||||
"in_stock_processing": "in_stock_only",
|
||||
"follow_price_changes": true,
|
||||
"price_change_threshold_percent": 5
|
||||
}
|
||||
}'
|
||||
- lang: 'Python'
|
||||
label: 'Restock & price tracking'
|
||||
source: |
|
||||
import requests
|
||||
|
||||
headers = {
|
||||
'x-api-key': 'YOUR_API_KEY',
|
||||
'Content-Type': 'application/json'
|
||||
}
|
||||
data = {
|
||||
'url': 'https://example.com/product',
|
||||
'processor': 'restock_diff',
|
||||
'processor_config_restock_diff': {
|
||||
'in_stock_processing': 'in_stock_only',
|
||||
'follow_price_changes': True,
|
||||
'price_change_threshold_percent': 5,
|
||||
}
|
||||
}
|
||||
response = requests.post('http://localhost:5000/api/v1/watch',
|
||||
headers=headers, json=data)
|
||||
print(response.json())
|
||||
|
||||
/watch/{uuid}:
|
||||
put:
|
||||
x-code-samples:
|
||||
- lang: 'curl'
|
||||
label: 'Update restock config'
|
||||
source: |
|
||||
curl -X PUT "http://localhost:5000/api/v1/watch/YOUR-UUID" \
|
||||
-H "x-api-key: YOUR_API_KEY" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"processor_config_restock_diff": {
|
||||
"in_stock_processing": "all_changes",
|
||||
"follow_price_changes": true,
|
||||
"price_change_min": 10.00,
|
||||
"price_change_max": 500.00
|
||||
}
|
||||
}'
|
||||
- lang: 'Python'
|
||||
label: 'Update restock config'
|
||||
source: |
|
||||
import requests
|
||||
|
||||
headers = {
|
||||
'x-api-key': 'YOUR_API_KEY',
|
||||
'Content-Type': 'application/json'
|
||||
}
|
||||
uuid = 'YOUR-UUID'
|
||||
data = {
|
||||
'processor_config_restock_diff': {
|
||||
'in_stock_processing': 'all_changes',
|
||||
'follow_price_changes': True,
|
||||
'price_change_min': 10.00,
|
||||
'price_change_max': 500.00,
|
||||
}
|
||||
}
|
||||
response = requests.put(f'http://localhost:5000/api/v1/watch/{uuid}',
|
||||
headers=headers, json=data)
|
||||
print(response.text)
|
||||
|
||||
/tag/{uuid}:
|
||||
put:
|
||||
x-code-samples:
|
||||
- lang: 'curl'
|
||||
label: 'Set restock config on group/tag'
|
||||
source: |
|
||||
curl -X PUT "http://localhost:5000/api/v1/tag/YOUR-TAG-UUID" \
|
||||
-H "x-api-key: YOUR_API_KEY" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"overrides_watch": true,
|
||||
"processor_config_restock_diff": {
|
||||
"in_stock_processing": "in_stock_only",
|
||||
"follow_price_changes": true,
|
||||
"price_change_threshold_percent": 10
|
||||
}
|
||||
}'
|
||||
- lang: 'Python'
|
||||
label: 'Set restock config on group/tag'
|
||||
source: |
|
||||
import requests
|
||||
|
||||
headers = {
|
||||
'x-api-key': 'YOUR_API_KEY',
|
||||
'Content-Type': 'application/json'
|
||||
}
|
||||
tag_uuid = 'YOUR-TAG-UUID'
|
||||
data = {
|
||||
'overrides_watch': True,
|
||||
'processor_config_restock_diff': {
|
||||
'in_stock_processing': 'in_stock_only',
|
||||
'follow_price_changes': True,
|
||||
'price_change_threshold_percent': 10,
|
||||
}
|
||||
}
|
||||
response = requests.put(f'http://localhost:5000/api/v1/tag/{tag_uuid}',
|
||||
headers=headers, json=data)
|
||||
print(response.text)
|
||||
@@ -31,7 +31,7 @@ class RestockSettingsForm(Form):
|
||||
follow_price_changes = BooleanField(_l('Follow price changes'), default=True)
|
||||
|
||||
class processor_settings_form(processor_text_json_diff_form):
|
||||
processor_config_restock_diff = FormField(RestockSettingsForm)
|
||||
restock_settings = FormField(RestockSettingsForm)
|
||||
|
||||
def extra_tab_content(self):
|
||||
return _l('Restock & Price Detection')
|
||||
@@ -48,34 +48,34 @@ class processor_settings_form(processor_text_json_diff_form):
|
||||
|
||||
output += """
|
||||
{% from '_helpers.html' import render_field, render_checkbox_field, render_button %}
|
||||
<script>
|
||||
<script>
|
||||
$(document).ready(function () {
|
||||
toggleOpacity('#processor_config_restock_diff-follow_price_changes', '.price-change-minmax', true);
|
||||
toggleOpacity('#restock_settings-follow_price_changes', '.price-change-minmax', true);
|
||||
});
|
||||
</script>
|
||||
|
||||
<fieldset id="restock-fieldset-price-group">
|
||||
<div class="pure-control-group">
|
||||
<fieldset class="pure-group inline-radio">
|
||||
{{ render_field(form.processor_config_restock_diff.in_stock_processing) }}
|
||||
{{ render_field(form.restock_settings.in_stock_processing) }}
|
||||
</fieldset>
|
||||
<fieldset class="pure-group">
|
||||
{{ render_checkbox_field(form.processor_config_restock_diff.follow_price_changes) }}
|
||||
{{ render_checkbox_field(form.restock_settings.follow_price_changes) }}
|
||||
<span class="pure-form-message-inline">Changes in price should trigger a notification</span>
|
||||
</fieldset>
|
||||
<fieldset class="pure-group price-change-minmax">
|
||||
{{ render_field(form.processor_config_restock_diff.price_change_min, placeholder=watch.get('restock', {}).get('price')) }}
|
||||
<fieldset class="pure-group price-change-minmax">
|
||||
{{ render_field(form.restock_settings.price_change_min, placeholder=watch.get('restock', {}).get('price')) }}
|
||||
<span class="pure-form-message-inline">Minimum amount, Trigger a change/notification when the price drops <i>below</i> this value.</span>
|
||||
</fieldset>
|
||||
<fieldset class="pure-group price-change-minmax">
|
||||
{{ render_field(form.processor_config_restock_diff.price_change_max, placeholder=watch.get('restock', {}).get('price')) }}
|
||||
{{ render_field(form.restock_settings.price_change_max, placeholder=watch.get('restock', {}).get('price')) }}
|
||||
<span class="pure-form-message-inline">Maximum amount, Trigger a change/notification when the price rises <i>above</i> this value.</span>
|
||||
</fieldset>
|
||||
<fieldset class="pure-group price-change-minmax">
|
||||
{{ render_field(form.processor_config_restock_diff.price_change_threshold_percent) }}
|
||||
{{ render_field(form.restock_settings.price_change_threshold_percent) }}
|
||||
<span class="pure-form-message-inline">Price must change more than this % to trigger a change since the first check.</span><br>
|
||||
<span class="pure-form-message-inline">For example, If the product is $1,000 USD originally, <strong>2%</strong> would mean it has to change more than $20 since the first check.</span><br>
|
||||
</fieldset>
|
||||
</fieldset>
|
||||
</div>
|
||||
</fieldset>
|
||||
"""
|
||||
|
||||
@@ -437,32 +437,26 @@ class perform_site_check(difference_detection_processor):
|
||||
|
||||
# Only try to process restock information (like scraping for keywords) if the page was actually rendered correctly.
|
||||
# Otherwise it will assume "in stock" because nothing suggesting the opposite was found
|
||||
#useless
|
||||
# from ...html_tools import html_to_text
|
||||
# text = html_to_text(self.fetcher.content)
|
||||
# logger.debug(f"Length of text after conversion: {len(text)}")
|
||||
# if not len(text):
|
||||
# from ...content_fetchers.exceptions import ReplyWithContentButNoText
|
||||
# raise ReplyWithContentButNoText(url=watch.link,
|
||||
# status_code=self.fetcher.get_last_status_code(),
|
||||
# screenshot=self.fetcher.screenshot,
|
||||
# html_content=self.fetcher.content,
|
||||
# xpath_data=self.fetcher.xpath_data
|
||||
# )
|
||||
from ...html_tools import html_to_text
|
||||
text = html_to_text(self.fetcher.content)
|
||||
logger.debug(f"Length of text after conversion: {len(text)}")
|
||||
if not len(text):
|
||||
from ...content_fetchers.exceptions import ReplyWithContentButNoText
|
||||
raise ReplyWithContentButNoText(url=watch.link,
|
||||
status_code=self.fetcher.get_last_status_code(),
|
||||
screenshot=self.fetcher.screenshot,
|
||||
html_content=self.fetcher.content,
|
||||
xpath_data=self.fetcher.xpath_data
|
||||
)
|
||||
|
||||
# Which restock settings to compare against?
|
||||
# Settings are stored in restock_diff.json (migrated from watch.json by update_30).
|
||||
_extra_config = self.get_extra_watch_config('restock_diff.json')
|
||||
restock_settings = _extra_config.get('restock_diff') or {
|
||||
'follow_price_changes': True,
|
||||
'in_stock_processing': 'in_stock_only',
|
||||
}
|
||||
restock_settings = watch.get('restock_settings', {})
|
||||
|
||||
# See if any tags have 'activate for individual watches in this tag/group?' enabled and use the first we find
|
||||
for tag_uuid in watch.get('tags'):
|
||||
tag = self.datastore.data['settings']['application']['tags'].get(tag_uuid, {})
|
||||
if tag.get('overrides_watch'):
|
||||
restock_settings = tag.get('processor_config_restock_diff') or {}
|
||||
restock_settings = tag.get('restock_settings', {})
|
||||
logger.info(f"Watch {watch.get('uuid')} - Tag '{tag.get('title')}' selected for restock settings override")
|
||||
break
|
||||
|
||||
|
||||
@@ -283,7 +283,4 @@ def query_price_availability(extracted_data):
|
||||
if not result.get('availability') and 'availability' in microdata:
|
||||
result['availability'] = microdata['availability']
|
||||
|
||||
# result['price'] could be float or str here, depending on the website, for example it might contain "1,00" commas, etc.
|
||||
# using something like babel you need to know the locale of the website and even then it can be problematic
|
||||
# we dont really do anything with the price data so far.. so just accept it the way it comes.
|
||||
return result
|
||||
|
||||
@@ -36,7 +36,7 @@ def _task(watch, update_handler):
|
||||
|
||||
|
||||
def prepare_filter_prevew(datastore, watch_uuid, form_data):
|
||||
'''Used by @app.route("/edit/<uuid_str:uuid>/preview-rendered", methods=['POST'])'''
|
||||
'''Used by @app.route("/edit/<string:uuid>/preview-rendered", methods=['POST'])'''
|
||||
from changedetectionio import forms, html_tools
|
||||
from changedetectionio.model.Watch import model as watch_model
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
|
||||
@@ -154,7 +154,11 @@ def render(watch, datastore, request, url_for, render_template, flash, redirect,
|
||||
|
||||
screenshot_url = watch.get_screenshot()
|
||||
|
||||
is_html_webdriver = watch.fetcher_supports_screenshots
|
||||
system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
|
||||
|
||||
is_html_webdriver = False
|
||||
if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver' or watch.get('fetch_backend', '').startswith('extra_browser_'):
|
||||
is_html_webdriver = True
|
||||
|
||||
password_enabled_and_share_is_off = False
|
||||
if datastore.data['settings']['application'].get('password') or os.getenv("SALTED_PASS", False):
|
||||
|
||||
@@ -347,7 +347,6 @@ class ContentProcessor:
|
||||
def extract_text_from_html(self, html_content, stream_content_type):
|
||||
"""Convert HTML to plain text."""
|
||||
do_anchor = self.datastore.data["settings"]["application"].get("render_anchor_tag_content", False)
|
||||
|
||||
return html_tools.html_to_text(
|
||||
html_content=html_content,
|
||||
render_anchor_tag_content=do_anchor,
|
||||
|
||||
@@ -29,11 +29,9 @@ def register_watch_operation_handlers(socketio, datastore):
|
||||
# Perform the operation
|
||||
if op == 'pause':
|
||||
watch.toggle_pause()
|
||||
watch.commit()
|
||||
logger.info(f"Socket.IO: Toggled pause for watch {uuid}")
|
||||
elif op == 'mute':
|
||||
watch.toggle_mute()
|
||||
watch.commit()
|
||||
logger.info(f"Socket.IO: Toggled mute for watch {uuid}")
|
||||
elif op == 'recheck':
|
||||
# Import here to avoid circular imports
|
||||
|
||||
@@ -199,31 +199,8 @@ def handle_watch_update(socketio, **kwargs):
|
||||
logger.error(f"Socket.IO error in handle_watch_update: {str(e)}")
|
||||
|
||||
|
||||
def _suppress_werkzeug_ws_abrupt_disconnect_noise():
|
||||
"""Patch BaseWSGIServer.log to suppress the AssertionError traceback that fires when
|
||||
a browser closes a WebSocket connection mid-handshake (e.g. closing a tab).
|
||||
The exception is caught inside run_wsgi and routed to self.server.log() — it never
|
||||
propagates out, so wrapping run_wsgi doesn't help. Patching the log method is the
|
||||
only reliable intercept point. The error is cosmetic: Socket.IO already handles the
|
||||
disconnect correctly via its own disconnect handler and timeout logic."""
|
||||
try:
|
||||
from werkzeug.serving import BaseWSGIServer
|
||||
_original_log = BaseWSGIServer.log
|
||||
|
||||
def _filtered_log(self, type, message, *args):
|
||||
if type == 'error' and 'write() before start_response' in message:
|
||||
return
|
||||
_original_log(self, type, message, *args)
|
||||
|
||||
BaseWSGIServer.log = _filtered_log
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
|
||||
def init_socketio(app, datastore):
|
||||
"""Initialize SocketIO with the main Flask app"""
|
||||
_suppress_werkzeug_ws_abrupt_disconnect_noise()
|
||||
|
||||
import platform
|
||||
import sys
|
||||
|
||||
@@ -368,4 +345,4 @@ def init_socketio(app, datastore):
|
||||
|
||||
logger.info("Socket.IO initialized and attached to main Flask app")
|
||||
logger.info(f"Socket.IO: Registered event handlers: {socketio.handlers if hasattr(socketio, 'handlers') else 'No handlers found'}")
|
||||
return socketio
|
||||
return socketio
|
||||
@@ -44,12 +44,12 @@ data_sanity_test () {
|
||||
cd ..
|
||||
TMPDIR=$(mktemp -d)
|
||||
PORT_N=$((5000 + RANDOM % (6501 - 5000)))
|
||||
ALLOW_IANA_RESTRICTED_ADDRESSES=true ./changedetection.py -p $PORT_N -d $TMPDIR -u "https://localhost?test-url-is-sanity=1" &
|
||||
./changedetection.py -p $PORT_N -d $TMPDIR -u "https://localhost?test-url-is-sanity=1" &
|
||||
PID=$!
|
||||
sleep 5
|
||||
kill $PID
|
||||
sleep 2
|
||||
ALLOW_IANA_RESTRICTED_ADDRESSES=true ./changedetection.py -p $PORT_N -d $TMPDIR &
|
||||
./changedetection.py -p $PORT_N -d $TMPDIR &
|
||||
PID=$!
|
||||
sleep 5
|
||||
# On a restart the URL should still be there
|
||||
|
||||
@@ -17,6 +17,8 @@ $(document).ready(function () {
|
||||
set_scale();
|
||||
});
|
||||
// Should always be disabled
|
||||
$('#browser_steps-0-operation option[value="Goto site"]').prop("selected", "selected");
|
||||
$('#browser_steps-0-operation').attr('disabled', 'disabled');
|
||||
|
||||
$('#browsersteps-click-start').click(function () {
|
||||
$("#browsersteps-click-start").fadeOut();
|
||||
@@ -43,6 +45,12 @@ $(document).ready(function () {
|
||||
browsersteps_session_id = false;
|
||||
apply_buttons_disabled = false;
|
||||
ctx.clearRect(0, 0, c.width, c.height);
|
||||
set_first_gotosite_disabled();
|
||||
}
|
||||
|
||||
function set_first_gotosite_disabled() {
|
||||
$('#browser_steps >li:first-child select').val('Goto site').attr('disabled', 'disabled');
|
||||
$('#browser_steps >li:first-child').css('opacity', '0.5');
|
||||
}
|
||||
|
||||
// Show seconds remaining until the browser interface needs to restart the session
|
||||
@@ -235,54 +243,14 @@ $(document).ready(function () {
|
||||
ctx.fill();
|
||||
}
|
||||
|
||||
// Reusable AJAX function for browser step operations
|
||||
function executeBrowserStep(url, data = {}) {
|
||||
$('#browser-steps-ui .loader .spinner').fadeIn();
|
||||
apply_buttons_disabled = true;
|
||||
$('ul#browser_steps li .control .apply').css('opacity', 0.5);
|
||||
$("#browsersteps-img").css('opacity', 0.65);
|
||||
|
||||
return $.ajax({
|
||||
method: "POST",
|
||||
url: url,
|
||||
data: data,
|
||||
statusCode: {
|
||||
400: function () {
|
||||
alert("There was a problem processing the request, please reload the page.");
|
||||
$("#loading-status-text").hide();
|
||||
$('#browser-steps-ui .loader .spinner').fadeOut();
|
||||
},
|
||||
401: function (data) {
|
||||
alert(data.responseText);
|
||||
$("#loading-status-text").hide();
|
||||
$('#browser-steps-ui .loader .spinner').fadeOut();
|
||||
}
|
||||
}
|
||||
}).done(function (data) {
|
||||
xpath_data = data.xpath_data;
|
||||
$('#browsersteps-img').attr('src', data.screenshot);
|
||||
$('#browser-steps-ui .loader .spinner').fadeOut();
|
||||
apply_buttons_disabled = false;
|
||||
$("#browsersteps-img").css('opacity', 1);
|
||||
$('ul#browser_steps li .control .apply').css('opacity', 1);
|
||||
$("#loading-status-text").hide();
|
||||
}).fail(function (data) {
|
||||
console.log(data);
|
||||
if (data.responseText && data.responseText.includes("Browser session expired")) {
|
||||
disable_browsersteps_ui();
|
||||
}
|
||||
apply_buttons_disabled = false;
|
||||
$("#loading-status-text").hide();
|
||||
$('ul#browser_steps li .control .apply').css('opacity', 1);
|
||||
$("#browsersteps-img").css('opacity', 1);
|
||||
});
|
||||
}
|
||||
|
||||
function start() {
|
||||
console.log("Starting browser-steps UI");
|
||||
browsersteps_session_id = false;
|
||||
// @todo This setting of the first one should be done at the datalayer but wtforms doesnt wanna play nice
|
||||
$('#browser_steps >li:first-child').removeClass('empty');
|
||||
set_first_gotosite_disabled();
|
||||
$('#browser-steps-ui .loader .spinner').show();
|
||||
// Request a new session
|
||||
$('.clear,.remove', $('#browser_steps >li:first-child')).hide();
|
||||
$.ajax({
|
||||
type: "GET",
|
||||
url: browser_steps_start_url,
|
||||
@@ -299,12 +267,11 @@ $(document).ready(function () {
|
||||
}).done(function (data) {
|
||||
$("#loading-status-text").fadeIn();
|
||||
browsersteps_session_id = data.browsersteps_session_id;
|
||||
// This should trigger 'Goto site'
|
||||
console.log("Got startup response, requesting Goto-Site (first) step fake click");
|
||||
$('#browser_steps >li:first-child .apply').click();
|
||||
browser_interface_seconds_remaining = 500;
|
||||
// Request goto_site operation
|
||||
executeBrowserStep(
|
||||
browser_steps_sync_url + "&browsersteps_session_id=" + browsersteps_session_id + "&goto_website_url_first_step=true"
|
||||
);
|
||||
|
||||
set_first_gotosite_disabled();
|
||||
}).fail(function (data) {
|
||||
console.log(data);
|
||||
alert('There was an error communicating with the server.');
|
||||
@@ -313,6 +280,7 @@ $(document).ready(function () {
|
||||
}
|
||||
|
||||
function disable_browsersteps_ui() {
|
||||
set_first_gotosite_disabled();
|
||||
$("#browser-steps-ui").css('opacity', '0.3');
|
||||
$('#browsersteps-selector-canvas').off("mousemove mousedown click");
|
||||
}
|
||||
@@ -360,13 +328,16 @@ $(document).ready(function () {
|
||||
// Add the extra buttons to the steps
|
||||
$('ul#browser_steps li').each(function (i) {
|
||||
var s = '<div class="control">' + '<a data-step-index=' + i + ' class="pure-button button-secondary button-green button-xsmall apply" >Apply</a> ';
|
||||
s += `<a data-step-index="${i}" class="pure-button button-secondary button-xsmall clear" >Clear</a> ` +
|
||||
`<a data-step-index="${i}" class="pure-button button-secondary button-red button-xsmall remove" >Remove</a>`;
|
||||
if (i > 0) {
|
||||
// The first step never gets these (Goto-site)
|
||||
s += `<a data-step-index="${i}" class="pure-button button-secondary button-xsmall clear" >Clear</a> ` +
|
||||
`<a data-step-index="${i}" class="pure-button button-secondary button-red button-xsmall remove" >Remove</a>`;
|
||||
|
||||
// if a screenshot is available
|
||||
if (browser_steps_available_screenshots.includes(i.toString())) {
|
||||
var d = (browser_steps_last_error_step === i+1) ? 'before' : 'after';
|
||||
s += ` <a data-step-index="${i}" class="pure-button button-secondary button-xsmall show-screenshot" title="Show screenshot from last run" data-type="${d}">Pic</a> `;
|
||||
// if a screenshot is available
|
||||
if (browser_steps_available_screenshots.includes(i.toString())) {
|
||||
var d = (browser_steps_last_error_step === i+1) ? 'before' : 'after';
|
||||
s += ` <a data-step-index="${i}" class="pure-button button-secondary button-xsmall show-screenshot" title="Show screenshot from last run" data-type="${d}">Pic</a> `;
|
||||
}
|
||||
}
|
||||
s += '</div>';
|
||||
$(this).append(s)
|
||||
@@ -405,35 +376,80 @@ $(document).ready(function () {
|
||||
});
|
||||
|
||||
$('ul#browser_steps li .control .apply').click(function (event) {
|
||||
// sequential requests @todo refactor
|
||||
if (apply_buttons_disabled) {
|
||||
return;
|
||||
}
|
||||
|
||||
var current_data = $(event.currentTarget).closest('li');
|
||||
$('#browser-steps-ui .loader .spinner').fadeIn();
|
||||
apply_buttons_disabled = true;
|
||||
$('ul#browser_steps li .control .apply').css('opacity', 0.5);
|
||||
$("#browsersteps-img").css('opacity', 0.65);
|
||||
|
||||
var is_last_step = 0;
|
||||
var step_n = $(event.currentTarget).data('step-index');
|
||||
|
||||
// Determine if this is the last configured step
|
||||
var is_last_step = 0;
|
||||
// On the last step, we should also be getting data ready for the visual selector
|
||||
$('ul#browser_steps li select').each(function (i) {
|
||||
if ($(this).val() !== 'Choose one') {
|
||||
is_last_step += 1;
|
||||
}
|
||||
});
|
||||
is_last_step = (is_last_step == (step_n + 1));
|
||||
|
||||
if (is_last_step == (step_n + 1)) {
|
||||
is_last_step = true;
|
||||
} else {
|
||||
is_last_step = false;
|
||||
}
|
||||
|
||||
console.log("Requesting step via POST " + $("select[id$='operation']", current_data).first().val());
|
||||
|
||||
// Execute the browser step
|
||||
executeBrowserStep(
|
||||
browser_steps_sync_url + "&browsersteps_session_id=" + browsersteps_session_id,
|
||||
{
|
||||
// POST the currently clicked step form widget back and await response, redraw
|
||||
$.ajax({
|
||||
method: "POST",
|
||||
url: browser_steps_sync_url + "&browsersteps_session_id=" + browsersteps_session_id,
|
||||
data: {
|
||||
'operation': $("select[id$='operation']", current_data).first().val(),
|
||||
'selector': $("input[id$='selector']", current_data).first().val(),
|
||||
'optional_value': $("input[id$='optional_value']", current_data).first().val(),
|
||||
'step_n': step_n,
|
||||
'is_last_step': is_last_step
|
||||
},
|
||||
statusCode: {
|
||||
400: function () {
|
||||
// More than likely the CSRF token was lost when the server restarted
|
||||
alert("There was a problem processing the request, please reload the page.");
|
||||
$("#loading-status-text").hide();
|
||||
$('#browser-steps-ui .loader .spinner').fadeOut();
|
||||
},
|
||||
401: function (data) {
|
||||
// More than likely the CSRF token was lost when the server restarted
|
||||
alert(data.responseText);
|
||||
$("#loading-status-text").hide();
|
||||
$('#browser-steps-ui .loader .spinner').fadeOut();
|
||||
}
|
||||
}
|
||||
);
|
||||
}).done(function (data) {
|
||||
// it should return the new state (selectors available and screenshot)
|
||||
xpath_data = data.xpath_data;
|
||||
$('#browsersteps-img').attr('src', data.screenshot);
|
||||
$('#browser-steps-ui .loader .spinner').fadeOut();
|
||||
apply_buttons_disabled = false;
|
||||
$("#browsersteps-img").css('opacity', 1);
|
||||
$('ul#browser_steps li .control .apply').css('opacity', 1);
|
||||
$("#loading-status-text").hide();
|
||||
set_first_gotosite_disabled();
|
||||
}).fail(function (data) {
|
||||
console.log(data);
|
||||
if (data.responseText.includes("Browser session expired")) {
|
||||
disable_browsersteps_ui();
|
||||
}
|
||||
apply_buttons_disabled = false;
|
||||
$("#loading-status-text").hide();
|
||||
$('ul#browser_steps li .control .apply').css('opacity', 1);
|
||||
$("#browsersteps-img").css('opacity', 1);
|
||||
});
|
||||
|
||||
});
|
||||
|
||||
$('ul#browser_steps li .control .show-screenshot').click(function (element) {
|
||||
|
||||
@@ -116,14 +116,6 @@ $(document).ready(function () {
|
||||
$('#realtime-conn-error').show();
|
||||
});
|
||||
|
||||
// Tell the server we're leaving cleanly so it can release the connection
|
||||
// immediately rather than waiting for a timeout.
|
||||
// Note: this only fires for voluntary closes (tab/window close, navigation away).
|
||||
// Hard kills, crashes and network drops will still timeout normally on the server.
|
||||
window.addEventListener('beforeunload', function () {
|
||||
socket.disconnect();
|
||||
});
|
||||
|
||||
socket.on('queue_size', function (data) {
|
||||
console.log(`${data.event_timestamp} - Queue size update: ${data.q_length}`);
|
||||
if(queueSizePagerInfoText) {
|
||||
|
||||
@@ -102,9 +102,7 @@
|
||||
}
|
||||
|
||||
// Navigate to search results (always redirect to watchlist home)
|
||||
// Use base_path if available (for sub-path deployments like /enlighten-richerx)
|
||||
const basePath = typeof base_path !== 'undefined' ? base_path : '';
|
||||
window.location.href = basePath + '/?' + params.toString();
|
||||
window.location.href = '/?' + params.toString();
|
||||
});
|
||||
}
|
||||
});
|
||||
|
||||
@@ -1 +1 @@
|
||||
#diff-form{background:rgba(0,0,0,.05);padding:1em;border-radius:10px;margin-bottom:1em;color:#fff;font-size:.9rem;text-align:center}#diff-form label.from-to-label{width:4rem;text-decoration:none;padding:.5rem}#diff-form label.from-to-label#change-from{color:#b30000;background:#fadad7}#diff-form label.from-to-label#change-to{background:#eaf2c2;color:#406619}#diff-form #diff-style>span{display:inline-block;padding:.3em}#diff-form #diff-style>span label{font-weight:normal}#diff-form *{vertical-align:middle}body.difference-page section.content{padding-top:40px}#diff-ui{background:var(--color-background);padding:1rem;border-radius:5px}@media(min-width: 767px){#diff-ui{min-width:50%}}#diff-ui #text{font-size:11px}#diff-ui pre{white-space:break-spaces;overflow-wrap:anywhere}#diff-ui h1{display:inline;font-size:100%}#diff-ui #result{white-space:pre-wrap;word-break:break-word;overflow-wrap:break-word}#diff-ui .source{position:absolute;right:1%;top:.2em}@-moz-document url-prefix(){#diff-ui body{height:99%}}#diff-ui td#diff-col div{text-align:justify;white-space:pre-wrap}#diff-ui .ignored{background-color:#ccc;opacity:.7}#diff-ui .triggered{background-color:#1b98f8}#diff-ui .ignored.triggered{background-color:red}#diff-ui .tab-pane-inner#screenshot{text-align:center}#diff-ui .tab-pane-inner#screenshot img{max-width:99%}#diff-ui .pure-form button.reset-margin{margin:0px}#diff-ui .diff-fieldset{display:flex;align-items:center;gap:4px;flex-wrap:wrap}#diff-ui ul#highlightSnippetActions{list-style-type:none;display:flex;align-items:center;justify-content:center;gap:1.5rem;flex-wrap:wrap;padding:0;margin:0}#diff-ui ul#highlightSnippetActions li{display:flex;flex-direction:column;align-items:center;text-align:center;padding:.5rem;gap:.3rem}#diff-ui ul#highlightSnippetActions li button,#diff-ui ul#highlightSnippetActions li a{white-space:nowrap}#diff-ui ul#highlightSnippetActions span{font-size:.8rem;color:var(--color-text-input-description)}#diff-ui #cell-diff-jump-visualiser{display:flex;flex-direction:row;gap:1px;background:var(--color-background);border-radius:3px;overflow-x:hidden;position:sticky;top:0;z-index:10;padding-top:1rem;padding-bottom:1rem;justify-content:center}#diff-ui #cell-diff-jump-visualiser>div{flex:1;min-width:1px;max-width:10px;height:10px;background:var(--color-background-button-cancel);opacity:.3;border-radius:1px;transition:opacity .2s;position:relative}#diff-ui #cell-diff-jump-visualiser>div.deletion{background:#b30000;opacity:1}#diff-ui #cell-diff-jump-visualiser>div.insertion{background:#406619;opacity:1}#diff-ui #cell-diff-jump-visualiser>div.note{background:#406619;opacity:1}#diff-ui #cell-diff-jump-visualiser>div.mixed{background:linear-gradient(to right, #b30000 50%, #406619 50%);opacity:1}#diff-ui #cell-diff-jump-visualiser>div.current-position::after{content:"";position:absolute;bottom:-6px;left:50%;transform:translateX(-50%);width:0;height:0;border-left:4px solid rgba(0,0,0,0);border-right:4px solid rgba(0,0,0,0);border-bottom:4px solid var(--color-text)}#diff-ui #cell-diff-jump-visualiser>div:hover{opacity:.8;cursor:pointer}#text-diff-heading-area .snapshot-age{padding:4px;margin:.5rem 0;background-color:var(--color-background-snapshot-age);border-radius:3px;font-weight:bold;margin-bottom:4px}#text-diff-heading-area .snapshot-age.error{background-color:var(--color-error-background-snapshot-age);color:var(--color-error-text-snapshot-age)}#text-diff-heading-area .snapshot-age>*{padding-right:1rem}
|
||||
#diff-form{background:rgba(0,0,0,.05);padding:1em;border-radius:10px;margin-bottom:1em;color:#fff;font-size:.9rem;text-align:center}#diff-form label.from-to-label{width:4rem;text-decoration:none;padding:.5rem}#diff-form label.from-to-label#change-from{color:#b30000;background:#fadad7}#diff-form label.from-to-label#change-to{background:#eaf2c2;color:#406619}#diff-form #diff-style>span{display:inline-block;padding:.3em}#diff-form #diff-style>span label{font-weight:normal}#diff-form *{vertical-align:middle}body.difference-page section.content{padding-top:40px}#diff-ui{background:var(--color-background);padding:1rem;border-radius:5px}@media(min-width: 767px){#diff-ui{min-width:50%}}#diff-ui #text{font-size:11px}#diff-ui pre{white-space:break-spaces}#diff-ui h1{display:inline;font-size:100%}#diff-ui #result{white-space:pre-wrap;word-break:break-word;overflow-wrap:break-word}#diff-ui .source{position:absolute;right:1%;top:.2em}@-moz-document url-prefix(){#diff-ui body{height:99%}}#diff-ui td#diff-col div{text-align:justify;white-space:pre-wrap}#diff-ui .ignored{background-color:#ccc;opacity:.7}#diff-ui .triggered{background-color:#1b98f8}#diff-ui .ignored.triggered{background-color:red}#diff-ui .tab-pane-inner#screenshot{text-align:center}#diff-ui .tab-pane-inner#screenshot img{max-width:99%}#diff-ui .pure-form button.reset-margin{margin:0px}#diff-ui .diff-fieldset{display:flex;align-items:center;gap:4px;flex-wrap:wrap}#diff-ui ul#highlightSnippetActions{list-style-type:none;display:flex;align-items:center;justify-content:center;gap:1.5rem;flex-wrap:wrap;padding:0;margin:0}#diff-ui ul#highlightSnippetActions li{display:flex;flex-direction:column;align-items:center;text-align:center;padding:.5rem;gap:.3rem}#diff-ui ul#highlightSnippetActions li button,#diff-ui ul#highlightSnippetActions li a{white-space:nowrap}#diff-ui ul#highlightSnippetActions span{font-size:.8rem;color:var(--color-text-input-description)}#diff-ui #cell-diff-jump-visualiser{display:flex;flex-direction:row;gap:1px;background:var(--color-background);border-radius:3px;overflow-x:hidden;position:sticky;top:0;z-index:10;padding-top:1rem;padding-bottom:1rem;justify-content:center}#diff-ui #cell-diff-jump-visualiser>div{flex:1;min-width:1px;max-width:10px;height:10px;background:var(--color-background-button-cancel);opacity:.3;border-radius:1px;transition:opacity .2s;position:relative}#diff-ui #cell-diff-jump-visualiser>div.deletion{background:#b30000;opacity:1}#diff-ui #cell-diff-jump-visualiser>div.insertion{background:#406619;opacity:1}#diff-ui #cell-diff-jump-visualiser>div.note{background:#406619;opacity:1}#diff-ui #cell-diff-jump-visualiser>div.mixed{background:linear-gradient(to right, #b30000 50%, #406619 50%);opacity:1}#diff-ui #cell-diff-jump-visualiser>div.current-position::after{content:"";position:absolute;bottom:-6px;left:50%;transform:translateX(-50%);width:0;height:0;border-left:4px solid rgba(0,0,0,0);border-right:4px solid rgba(0,0,0,0);border-bottom:4px solid var(--color-text)}#diff-ui #cell-diff-jump-visualiser>div:hover{opacity:.8;cursor:pointer}#text-diff-heading-area .snapshot-age{padding:4px;margin:.5rem 0;background-color:var(--color-background-snapshot-age);border-radius:3px;font-weight:bold;margin-bottom:4px}#text-diff-heading-area .snapshot-age.error{background-color:var(--color-error-background-snapshot-age);color:var(--color-error-text-snapshot-age)}#text-diff-heading-area .snapshot-age>*{padding-right:1rem}
|
||||
|
||||
@@ -62,7 +62,6 @@ body.difference-page {
|
||||
|
||||
pre {
|
||||
white-space: break-spaces;
|
||||
overflow-wrap: anywhere;
|
||||
}
|
||||
|
||||
|
||||
|
||||
File diff suppressed because one or more lines are too long
@@ -22,8 +22,6 @@ import uuid as uuid_builder
|
||||
from loguru import logger
|
||||
from blinker import signal
|
||||
|
||||
from ..model.Tags import TagsDict
|
||||
|
||||
# Try to import orjson for faster JSON serialization
|
||||
try:
|
||||
import orjson
|
||||
@@ -123,11 +121,6 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
|
||||
if 'application' in settings_data['settings']:
|
||||
self.__data['settings']['application'].update(settings_data['settings']['application'])
|
||||
|
||||
# Use our Tags dict with cleanup helpers etc
|
||||
# @todo Same for Watches
|
||||
existing_tags = settings_data.get('settings', {}).get('application', {}).get('tags') or {}
|
||||
self.__data['settings']['application']['tags'] = TagsDict(existing_tags, datastore_path=self.datastore_path)
|
||||
|
||||
# More or less for the old format which had this data in the one url-watches.json
|
||||
# cant hurt to leave it here,
|
||||
if 'watching' in settings_data:
|
||||
@@ -203,7 +196,7 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
|
||||
self.datastore_path = datastore_path
|
||||
|
||||
# Initialize data structure
|
||||
self.__data = App.model(datastore_path=datastore_path)
|
||||
self.__data = App.model()
|
||||
self.json_store_path = os.path.join(self.datastore_path, "changedetection.json")
|
||||
|
||||
# Base definition for all watchers (deepcopy part of #569)
|
||||
@@ -242,8 +235,6 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
|
||||
# No datastore yet - check if this is a fresh install or legacy migration
|
||||
self.init_fresh_install(include_default_watches=include_default_watches,
|
||||
version_tag=version_tag)
|
||||
# Maybe they copied a bunch of watch subdirs across too
|
||||
self._load_state()
|
||||
|
||||
def init_fresh_install(self, include_default_watches, version_tag):
|
||||
# Generate app_guid FIRST (required for all operations)
|
||||
@@ -362,9 +353,6 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
|
||||
# Deep copy settings to avoid modifying the original
|
||||
settings_copy = copy.deepcopy(self.__data['settings'])
|
||||
|
||||
# Is saved as {uuid}/tag.json
|
||||
settings_copy['application']['tags'] = {}
|
||||
|
||||
return {
|
||||
'note': 'Settings file - watches are in {uuid}/watch.json, tags are in {uuid}/tag.json',
|
||||
'app_guid': self.__data.get('app_guid'),
|
||||
@@ -728,11 +716,8 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
|
||||
return False
|
||||
|
||||
if not is_safe_valid_url(url):
|
||||
from flask import has_request_context
|
||||
if has_request_context():
|
||||
flash(gettext('Watch protocol is not permitted or invalid URL format'), 'error')
|
||||
else:
|
||||
logger.error(f"add_watch: URL '{url}' is not permitted or invalid, skipping.")
|
||||
flash(gettext('Watch protocol is not permitted or invalid URL format'), 'error')
|
||||
|
||||
return None
|
||||
|
||||
# Check PAGE_WATCH_LIMIT if set
|
||||
@@ -980,20 +965,12 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
|
||||
def get_all_tags_for_watch(self, uuid):
|
||||
"""This should be in Watch model but Watch doesn't have access to datastore, not sure how to solve that yet"""
|
||||
watch = self.data['watching'].get(uuid)
|
||||
if not watch:
|
||||
return {}
|
||||
|
||||
# Start with manually assigned tags
|
||||
result = dictfilt(self.__data['settings']['application']['tags'], watch.get('tags', []))
|
||||
# Should return a dict of full tag info linked by UUID
|
||||
if watch:
|
||||
return dictfilt(self.__data['settings']['application']['tags'], watch.get('tags', []))
|
||||
|
||||
# Additionally include any tag whose url_match_pattern matches this watch's URL
|
||||
watch_url = watch.get('url', '')
|
||||
if watch_url:
|
||||
for tag_uuid, tag in self.__data['settings']['application']['tags'].items():
|
||||
if tag_uuid not in result and tag.matches_url(watch_url):
|
||||
result[tag_uuid] = tag
|
||||
|
||||
return result
|
||||
return {}
|
||||
|
||||
@property
|
||||
def extra_browsers(self):
|
||||
|
||||
@@ -669,9 +669,7 @@ class DatastoreUpdatesMixin:
|
||||
def update_26(self):
|
||||
self.migrate_legacy_db_format()
|
||||
|
||||
# Re-run tag to JSON migration
|
||||
def update_29(self):
|
||||
|
||||
def update_28(self):
|
||||
"""
|
||||
Migrate tags to individual tag.json files.
|
||||
|
||||
@@ -684,6 +682,8 @@ class DatastoreUpdatesMixin:
|
||||
- Enables independent tag versioning/backup
|
||||
- Maintains backwards compatibility (tags stay in settings too)
|
||||
"""
|
||||
# Force save as tag.json (not watch.json) even if object is corrupted
|
||||
|
||||
logger.critical("=" * 80)
|
||||
logger.critical("Running migration: Individual tag persistence (update_28)")
|
||||
logger.critical("Creating individual tag.json files")
|
||||
@@ -702,9 +702,6 @@ class DatastoreUpdatesMixin:
|
||||
failed_count = 0
|
||||
|
||||
for uuid, tag_data in tags.items():
|
||||
if os.path.isfile(os.path.join(self.datastore_path, uuid, "tag.json")):
|
||||
logger.debug(f"Tag {uuid} tag.json exists, skipping")
|
||||
continue
|
||||
try:
|
||||
tag_data.commit()
|
||||
saved_count += 1
|
||||
@@ -726,52 +723,3 @@ class DatastoreUpdatesMixin:
|
||||
logger.info("Future tag edits will update both locations (dual storage)")
|
||||
logger.critical("=" * 80)
|
||||
|
||||
# write it to disk, it will be saved without ['tags'] in the JSON db because we find it from disk glob
|
||||
# (left this out by accident in previous update, added tags={} in the changedetection.json save_to_disk)
|
||||
self._save_settings()
|
||||
|
||||
def update_30(self):
|
||||
"""Migrate restock_settings out of watch.json into restock_diff.json processor config file.
|
||||
|
||||
Previously, restock_diff processor settings (in_stock_processing, follow_price_changes, etc.)
|
||||
were stored directly in the watch dict (watch.json). They now belong in a separate per-watch
|
||||
processor config file (restock_diff.json) consistent with the processor_config_* API system.
|
||||
|
||||
For tags: restock_settings key is renamed to processor_config_restock_diff in the tag dict,
|
||||
matching what the API writes when updating a tag.
|
||||
|
||||
Safe to re-run: skips watches that already have a restock_diff.json, skips tags that already
|
||||
have processor_config_restock_diff set.
|
||||
"""
|
||||
import json
|
||||
|
||||
# --- Watches ---
|
||||
for uuid, watch in self.data['watching'].items():
|
||||
if watch.get('processor') != 'restock_diff':
|
||||
continue
|
||||
restock_settings = watch.get('restock_settings')
|
||||
if not restock_settings:
|
||||
continue
|
||||
|
||||
data_dir = watch.data_dir
|
||||
if data_dir:
|
||||
watch.ensure_data_dir_exists()
|
||||
filepath = os.path.join(data_dir, 'restock_diff.json')
|
||||
if not os.path.isfile(filepath):
|
||||
with open(filepath, 'w', encoding='utf-8') as f:
|
||||
json.dump({'restock_diff': restock_settings}, f, indent=2)
|
||||
logger.info(f"update_30: migrated restock_settings → {filepath}")
|
||||
|
||||
del self.data['watching'][uuid]['restock_settings']
|
||||
watch.commit()
|
||||
|
||||
# --- Tags ---
|
||||
for tag_uuid, tag in self.data['settings']['application']['tags'].items():
|
||||
restock_settings = tag.get('restock_settings')
|
||||
if not restock_settings or tag.get('processor_config_restock_diff'):
|
||||
continue
|
||||
tag['processor_config_restock_diff'] = restock_settings
|
||||
del tag['restock_settings']
|
||||
tag.commit()
|
||||
logger.info(f"update_30: migrated tag {tag_uuid} restock_settings → processor_config_restock_diff")
|
||||
|
||||
|
||||
@@ -44,26 +44,13 @@
|
||||
<td><code>{{ '{{preview_url}}' }}</code></td>
|
||||
<td>{{ _('The URL of the preview page generated by changedetection.io.') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{change_datetime}}' }}</code></td>
|
||||
<td>{{ _('Date/time of the change, accepts format=, change_datetime(format=\'%A\')\', default is \'%Y-%m-%d %H:%M:%S %Z\'') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{diff_url}}' }}</code></td>
|
||||
<td>{{ _('The URL of the diff output for the watch.') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{diff_url}}' }}</code></td>
|
||||
<td>{{ _('The URL of the diff output for the watch.') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{diff}}' }}</code></td>
|
||||
<td>{{ _('The diff output - only changes, additions, and removals') }}<br>
|
||||
<small>
|
||||
{{ _('All diff variants accept') }} <code>lines=</code>, <code>context=</code>, <code>word_diff=</code>, <code>ignore_junk=</code> {{ _('args, e.g.') }}
|
||||
<code>{{ '{{diff(lines=10)}}' }}</code>, <code>{{ '{{diff_added(lines=5, context=2)}}' }}</code>
|
||||
</small>
|
||||
</td>
|
||||
<td>{{ _('The diff output - only changes, additions, and removals') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{diff_clean}}' }}</code></td>
|
||||
@@ -98,14 +85,6 @@
|
||||
<td><code>{{ '{{diff_patch}}' }}</code></td>
|
||||
<td>{{ _('The diff output - patch in unified format') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{diff_changed_from}}' }}</code></td>
|
||||
<td>{{ _('Only the changed words/values from the previous version — e.g. the old price. Best when a single value changes per line; multiple changed fragments are joined by newline.') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{diff_changed_to}}' }}</code></td>
|
||||
<td>{{ _('Only the changed words/values from the new version — e.g. the new price. Best when a single value changes per line; multiple changed fragments are joined by newline.') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{current_snapshot}}' }}</code></td>
|
||||
<td>{{ _('The current snapshot text contents value, useful when combined with JSON or CSS filters') }}
|
||||
|
||||
@@ -45,10 +45,6 @@
|
||||
<script src="{{url_for('static_content', group='js', filename='socket.io.min.js')}}"></script>
|
||||
<script src="{{url_for('static_content', group='js', filename='realtime.js')}}" defer></script>
|
||||
{% endif %}
|
||||
{%- set _html_head_extras = get_html_head_extras() -%}
|
||||
{%- if _html_head_extras %}
|
||||
{{ _html_head_extras | safe }}
|
||||
{%- endif %}
|
||||
</head>
|
||||
|
||||
<body class="{{extra_classes}}">
|
||||
|
||||
@@ -10,7 +10,6 @@
|
||||
<li>{{ _('Trigger text is processed from the result-text that comes out of any CSS/JSON Filters for this monitor') }}</li>
|
||||
<li>{{ _('Each line is processed separately (think of each line as "OR")') }}</li>
|
||||
<li>{{ _('Note: Wrap in forward slash / to use regex example:') }} <code>/foo\d/</code></li>
|
||||
<li>{{ _('You can also use')}} <a href="#conditions">{{ _('conditions')}}</a> - {{ _('"Page text" - with Contains, Starts With, Not Contains and many more' ) }} <code>/foo\d/</code></li>
|
||||
</ul>
|
||||
</span>
|
||||
</div>
|
||||
|
||||
@@ -2,7 +2,6 @@
|
||||
import psutil
|
||||
import time
|
||||
from threading import Thread
|
||||
import multiprocessing
|
||||
|
||||
import pytest
|
||||
import arrow
|
||||
@@ -14,10 +13,6 @@ import sys
|
||||
# When test server is slow/unresponsive, workers fail fast instead of holding UUIDs for 45s
|
||||
# This prevents exponential priority growth from repeated deferrals (priority × 10 each defer)
|
||||
os.environ['DEFAULT_SETTINGS_REQUESTS_TIMEOUT'] = '5'
|
||||
# Test server runs on localhost (127.0.0.1) which is a private IP.
|
||||
# Allow it globally so all existing tests keep working; test_ssrf_protection
|
||||
# uses monkeypatch to temporarily override this for its own assertions.
|
||||
os.environ['ALLOW_IANA_RESTRICTED_ADDRESSES'] = 'true'
|
||||
|
||||
from changedetectionio.flask_app import init_app_secret, changedetection_app
|
||||
from changedetectionio.tests.util import live_server_setup, new_live_server_setup
|
||||
@@ -192,34 +187,6 @@ def cleanup(datastore_path):
|
||||
if os.path.isfile(f):
|
||||
os.unlink(f)
|
||||
|
||||
def pytest_configure(config):
|
||||
"""Configure pytest environment before tests run.
|
||||
|
||||
CRITICAL: Set multiprocessing start method to 'fork' for Python 3.14+ compatibility.
|
||||
|
||||
Python 3.14 changed the default start method from 'fork' to 'forkserver' on Linux.
|
||||
The forkserver method requires all objects to be picklable, but pytest-flask's
|
||||
LiveServer uses nested functions that can't be pickled.
|
||||
|
||||
Setting 'fork' explicitly:
|
||||
- Maintains compatibility with Python 3.10-3.13 (where 'fork' was already default)
|
||||
- Fixes Python 3.14 pickling errors
|
||||
- Only affects Unix-like systems (Windows uses 'spawn' regardless)
|
||||
|
||||
See: https://github.com/python/cpython/issues/126831
|
||||
See: https://docs.python.org/3/whatsnew/3.14.html
|
||||
"""
|
||||
# Only set if not already set (respects existing configuration)
|
||||
if multiprocessing.get_start_method(allow_none=True) is None:
|
||||
try:
|
||||
# 'fork' is available on Unix-like systems (Linux, macOS)
|
||||
# On Windows, this will have no effect as 'spawn' is the only option
|
||||
multiprocessing.set_start_method('fork', force=False)
|
||||
logger.debug("Set multiprocessing start method to 'fork' for Python 3.14+ compatibility")
|
||||
except (ValueError, RuntimeError):
|
||||
# Already set, not available on this platform, or context already created
|
||||
pass
|
||||
|
||||
def pytest_addoption(parser):
|
||||
"""Add custom command-line options for pytest.
|
||||
|
||||
@@ -364,7 +331,6 @@ def prepare_test_function(live_server, datastore_path):
|
||||
# Cleanup: Clear watches and queue after test
|
||||
try:
|
||||
from changedetectionio.flask_app import update_q
|
||||
from pathlib import Path
|
||||
|
||||
# Clear the queue to prevent leakage to next test
|
||||
while not update_q.empty():
|
||||
@@ -374,18 +340,6 @@ def prepare_test_function(live_server, datastore_path):
|
||||
break
|
||||
|
||||
datastore.data['watching'] = {}
|
||||
|
||||
# Delete any old watch metadata JSON files
|
||||
base_path = Path(datastore.datastore_path).resolve()
|
||||
max_depth = 2
|
||||
|
||||
for file in base_path.rglob("*.json"):
|
||||
# Calculate depth relative to base path
|
||||
depth = len(file.relative_to(base_path).parts) - 1
|
||||
|
||||
if depth <= max_depth and file.is_file():
|
||||
file.unlink()
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"Error during datastore cleanup: {e}")
|
||||
|
||||
|
||||
@@ -1,83 +0,0 @@
|
||||
"""Test that plugins can inject HTML into base.html <head> via get_html_head_extras hookimpl."""
|
||||
import pytest
|
||||
from flask import url_for, Response
|
||||
|
||||
from changedetectionio.pluggy_interface import hookimpl, plugin_manager
|
||||
|
||||
_MY_JS = "console.log('my_module_content loaded');"
|
||||
_MY_CSS = ".my-module-example { color: red; }"
|
||||
|
||||
|
||||
class _HeadExtrasPlugin:
|
||||
"""Test plugin that injects tags pointing at its own Flask routes."""
|
||||
|
||||
@hookimpl
|
||||
def get_html_head_extras(self):
|
||||
css_url = url_for('test_plugin_my_module_content_css')
|
||||
js_url = url_for('test_plugin_my_module_content_js')
|
||||
return (
|
||||
f'<link rel="stylesheet" id="test-head-extra-css" href="{css_url}">\n'
|
||||
f'<script id="test-head-extra-js" src="{js_url}" defer></script>'
|
||||
)
|
||||
|
||||
|
||||
@pytest.fixture(scope='module')
|
||||
def plugin_routes(live_server):
|
||||
"""Register plugin asset routes once per module (Flask routes can't be added twice)."""
|
||||
app = live_server.app
|
||||
|
||||
@app.route('/test-plugin/my_module_content/css')
|
||||
def test_plugin_my_module_content_css():
|
||||
return Response(_MY_CSS, mimetype='text/css',
|
||||
headers={'Cache-Control': 'max-age=3600'})
|
||||
|
||||
@app.route('/test-plugin/my_module_content/js')
|
||||
def test_plugin_my_module_content_js():
|
||||
return Response(_MY_JS, mimetype='application/javascript',
|
||||
headers={'Cache-Control': 'max-age=3600'})
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def head_extras_plugin(plugin_routes):
|
||||
"""Register the hookimpl for one test then unregister it — function-scoped for clean isolation."""
|
||||
plugin = _HeadExtrasPlugin()
|
||||
plugin_manager.register(plugin, name="test_head_extras")
|
||||
yield plugin
|
||||
plugin_manager.unregister(name="test_head_extras")
|
||||
|
||||
|
||||
def test_plugin_html_injected_into_head(client, live_server, measure_memory_usage, datastore_path, head_extras_plugin):
|
||||
"""get_html_head_extras output must appear inside <head> in the rendered page."""
|
||||
res = client.get(url_for("watchlist.index"), follow_redirects=True)
|
||||
assert res.status_code == 200
|
||||
assert b'id="test-head-extra-css"' in res.data, "Plugin <link> tag missing from rendered page"
|
||||
assert b'id="test-head-extra-js"' in res.data, "Plugin <script> tag missing from rendered page"
|
||||
|
||||
head_end = res.data.find(b'</head>')
|
||||
assert head_end != -1
|
||||
for marker in (b'id="test-head-extra-css"', b'id="test-head-extra-js"'):
|
||||
pos = res.data.find(marker)
|
||||
assert pos != -1 and pos < head_end, f"{marker} must appear before </head>"
|
||||
|
||||
|
||||
def test_plugin_js_route_returns_correct_content(client, live_server, measure_memory_usage, datastore_path, plugin_routes):
|
||||
"""The plugin-registered JS route must return JS with the right Content-Type."""
|
||||
res = client.get(url_for('test_plugin_my_module_content_js'))
|
||||
assert res.status_code == 200
|
||||
assert 'javascript' in res.content_type
|
||||
assert _MY_JS.encode() in res.data
|
||||
|
||||
|
||||
def test_plugin_css_route_returns_correct_content(client, live_server, measure_memory_usage, datastore_path, plugin_routes):
|
||||
"""The plugin-registered CSS route must return CSS with the right Content-Type."""
|
||||
res = client.get(url_for('test_plugin_my_module_content_css'))
|
||||
assert res.status_code == 200
|
||||
assert 'css' in res.content_type
|
||||
assert _MY_CSS.encode() in res.data
|
||||
|
||||
|
||||
def test_no_extras_without_plugin(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""With no hookimpl registered the markers must not appear (isolation check)."""
|
||||
res = client.get(url_for("watchlist.index"), follow_redirects=True)
|
||||
assert b'id="test-head-extra-css"' not in res.data
|
||||
assert b'id="test-head-extra-js"' not in res.data
|
||||
@@ -11,10 +11,10 @@ from changedetectionio.tests.util import set_original_response, set_modified_res
|
||||
set_longer_modified_response, delete_all_watches
|
||||
|
||||
import logging
|
||||
import os
|
||||
|
||||
|
||||
# NOTE - RELIES ON mailserver as hostname running, see github build recipes
|
||||
smtp_test_server = os.getenv('SMTP_TEST_MAILSERVER', 'mailserver')
|
||||
smtp_test_server = 'mailserver'
|
||||
|
||||
ALL_MARKUP_TOKENS = ''.join(f"TOKEN: '{t}'\n{{{{{t}}}}}\n" for t in NotificationContextData().keys())
|
||||
|
||||
|
||||
@@ -170,14 +170,6 @@ def test_api_simple(client, live_server, measure_memory_usage, datastore_path):
|
||||
headers={'x-api-key': api_key},
|
||||
)
|
||||
assert b'(changed) Which is across' in res.data
|
||||
assert b'Some text thats the same' in res.data
|
||||
|
||||
# Fetch the difference between two versions (default text format)
|
||||
res = client.get(
|
||||
url_for("watchhistorydiff", uuid=watch_uuid, from_timestamp='previous', to_timestamp='latest')+"?changesOnly=true",
|
||||
headers={'x-api-key': api_key},
|
||||
)
|
||||
assert b'Some text thats the same' not in res.data
|
||||
|
||||
# Test htmlcolor format
|
||||
res = client.get(
|
||||
@@ -815,88 +807,6 @@ def test_api_import_large_background(client, live_server, measure_memory_usage,
|
||||
print(f"\n✓ Successfully created {num_urls} watches in background (took {elapsed}s)")
|
||||
|
||||
|
||||
def test_api_restock_processor_config(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test that processor_config_restock_diff is accepted by the API for watches using
|
||||
restock_diff processor, that its schema is validated (enum values, types), and that
|
||||
genuinely unknown fields are rejected with an error that originates from the
|
||||
OpenAPI spec validation layer.
|
||||
"""
|
||||
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
|
||||
test_url = url_for('test_endpoint', _external=True)
|
||||
|
||||
# Create a watch in restock_diff mode WITH processor_config in the POST body (matches the API docs example)
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"processor": "restock_diff",
|
||||
"title": "Restock test",
|
||||
"processor_config_restock_diff": {
|
||||
"in_stock_processing": "in_stock_only",
|
||||
"follow_price_changes": True,
|
||||
"price_change_min": 8888888.0,
|
||||
}
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert res.status_code == 201
|
||||
watch_uuid = res.json.get('uuid')
|
||||
assert is_valid_uuid(watch_uuid)
|
||||
|
||||
# Verify the value set on POST is reflected in the UI edit page (not just via PUT)
|
||||
res = client.get(url_for("ui.ui_edit.edit_page", uuid=watch_uuid))
|
||||
assert res.status_code == 200
|
||||
assert b'8888888' in res.data, "price_change_min set via POST should appear in the UI edit form"
|
||||
|
||||
# Valid processor_config_restock_diff update via PUT should also be accepted
|
||||
res = client.put(
|
||||
url_for("watch", uuid=watch_uuid),
|
||||
headers={'x-api-key': api_key, 'content-type': 'application/json'},
|
||||
data=json.dumps({
|
||||
"processor_config_restock_diff": {
|
||||
"in_stock_processing": "all_changes",
|
||||
"follow_price_changes": False,
|
||||
"price_change_min": 8888888.0,
|
||||
"price_change_max": 9999999.0,
|
||||
}
|
||||
}),
|
||||
)
|
||||
assert res.status_code == 200, f"Valid processor_config_restock_diff should be accepted, got: {res.data}"
|
||||
|
||||
# Verify the updated value is still reflected in the UI edit page
|
||||
res = client.get(url_for("ui.ui_edit.edit_page", uuid=watch_uuid))
|
||||
assert res.status_code == 200
|
||||
assert b'8888888' in res.data, "price_change_min set via PUT should appear in the UI edit form"
|
||||
|
||||
# An invalid enum value inside processor_config_restock_diff should be rejected by the spec
|
||||
res = client.put(
|
||||
url_for("watch", uuid=watch_uuid),
|
||||
headers={'x-api-key': api_key, 'content-type': 'application/json'},
|
||||
data=json.dumps({
|
||||
"processor_config_restock_diff": {
|
||||
"in_stock_processing": "not_a_valid_enum_value"
|
||||
}
|
||||
}),
|
||||
)
|
||||
assert res.status_code == 400, "Invalid enum value in processor config should be rejected"
|
||||
assert b'Validation failed' in res.data, "Rejection should come from OpenAPI spec validation layer"
|
||||
|
||||
# A completely unknown field should be rejected (either by OpenAPI spec validation or
|
||||
# the application-level field filter — both are acceptable gatekeepers)
|
||||
res = client.put(
|
||||
url_for("watch", uuid=watch_uuid),
|
||||
headers={'x-api-key': api_key, 'content-type': 'application/json'},
|
||||
data=json.dumps({"field_that_is_not_in_the_spec_at_all": "some value"}),
|
||||
)
|
||||
assert res.status_code == 400, "Unknown fields should be rejected"
|
||||
assert (b'Validation failed' in res.data or b'Unknown field' in res.data), \
|
||||
"Rejection should come from either the OpenAPI spec validation layer or application field filter"
|
||||
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
def test_api_conflict_UI_password(client, live_server, measure_memory_usage, datastore_path):
|
||||
|
||||
|
||||
|
||||
@@ -9,51 +9,7 @@ by testing various scenarios that should trigger validation errors.
|
||||
import time
|
||||
import json
|
||||
from flask import url_for
|
||||
from .util import live_server_setup, wait_for_all_checks, delete_all_watches
|
||||
|
||||
|
||||
def test_openapi_merged_spec_contains_restock_fields():
|
||||
"""
|
||||
Unit test: verify that build_merged_spec_dict() correctly merges the
|
||||
restock_diff processor api.yaml into the base spec so that
|
||||
WatchBase.properties includes processor_config_restock_diff with all
|
||||
expected sub-fields. No live server required.
|
||||
"""
|
||||
from changedetectionio.api import build_merged_spec_dict
|
||||
|
||||
spec = build_merged_spec_dict()
|
||||
schemas = spec['components']['schemas']
|
||||
|
||||
# The merged schema for processor_config_restock_diff should exist
|
||||
assert 'processor_config_restock_diff' in schemas, \
|
||||
"processor_config_restock_diff schema missing from merged spec"
|
||||
|
||||
restock_schema = schemas['processor_config_restock_diff']
|
||||
props = restock_schema.get('properties', {})
|
||||
|
||||
expected_fields = {
|
||||
'in_stock_processing',
|
||||
'follow_price_changes',
|
||||
'price_change_min',
|
||||
'price_change_max',
|
||||
'price_change_threshold_percent',
|
||||
}
|
||||
missing = expected_fields - set(props.keys())
|
||||
assert not missing, f"Missing fields in processor_config_restock_diff schema: {missing}"
|
||||
|
||||
# in_stock_processing must be an enum with the three valid values
|
||||
enum_values = set(props['in_stock_processing'].get('enum', []))
|
||||
assert enum_values == {'in_stock_only', 'all_changes', 'off'}, \
|
||||
f"Unexpected enum values for in_stock_processing: {enum_values}"
|
||||
|
||||
# WatchBase.properties must carry a $ref to the restock schema so the
|
||||
# validation middleware can enforce it on every POST/PUT to /watch
|
||||
watchbase_props = schemas['WatchBase']['properties']
|
||||
assert 'processor_config_restock_diff' in watchbase_props, \
|
||||
"processor_config_restock_diff not wired into WatchBase.properties"
|
||||
ref = watchbase_props['processor_config_restock_diff'].get('$ref', '')
|
||||
assert 'processor_config_restock_diff' in ref, \
|
||||
f"WatchBase.processor_config_restock_diff should $ref the schema, got: {ref}"
|
||||
from .util import live_server_setup, wait_for_all_checks
|
||||
|
||||
|
||||
def test_openapi_validation_invalid_content_type_on_create_watch(client, live_server, measure_memory_usage, datastore_path):
|
||||
@@ -71,7 +27,6 @@ def test_openapi_validation_invalid_content_type_on_create_watch(client, live_se
|
||||
# Should get 400 error due to OpenAPI validation failure
|
||||
assert res.status_code == 400, f"Expected 400 but got {res.status_code}"
|
||||
assert b"Validation failed" in res.data, "Should contain validation error message"
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
def test_openapi_validation_missing_required_field_create_watch(client, live_server, measure_memory_usage, datastore_path):
|
||||
@@ -89,7 +44,6 @@ def test_openapi_validation_missing_required_field_create_watch(client, live_ser
|
||||
# Should get 400 error due to missing required field
|
||||
assert res.status_code == 400, f"Expected 400 but got {res.status_code}"
|
||||
assert b"Validation failed" in res.data, "Should contain validation error message"
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
def test_openapi_validation_invalid_field_in_request_body(client, live_server, measure_memory_usage, datastore_path):
|
||||
@@ -129,7 +83,6 @@ def test_openapi_validation_invalid_field_in_request_body(client, live_server, m
|
||||
# Backend validation now returns "Unknown field(s):" message
|
||||
assert b"Unknown field" in res.data, \
|
||||
"Should contain validation error about unknown fields"
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
def test_openapi_validation_import_wrong_content_type(client, live_server, measure_memory_usage, datastore_path):
|
||||
@@ -147,7 +100,6 @@ def test_openapi_validation_import_wrong_content_type(client, live_server, measu
|
||||
# Should get 400 error due to content-type mismatch
|
||||
assert res.status_code == 400, f"Expected 400 but got {res.status_code}"
|
||||
assert b"Validation failed" in res.data, "Should contain validation error message"
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
def test_openapi_validation_import_correct_content_type_succeeds(client, live_server, measure_memory_usage, datastore_path):
|
||||
@@ -165,7 +117,6 @@ def test_openapi_validation_import_correct_content_type_succeeds(client, live_se
|
||||
# Should succeed
|
||||
assert res.status_code == 200, f"Expected 200 but got {res.status_code}"
|
||||
assert len(res.json) == 2, "Should import 2 URLs"
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
def test_openapi_validation_get_requests_bypass_validation(client, live_server, measure_memory_usage, datastore_path):
|
||||
@@ -190,7 +141,6 @@ def test_openapi_validation_get_requests_bypass_validation(client, live_server,
|
||||
|
||||
# Should return JSON with watch list (empty in this case)
|
||||
assert isinstance(res.json, dict), "Should return JSON dictionary for watch list"
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
def test_openapi_validation_create_tag_missing_required_title(client, live_server, measure_memory_usage, datastore_path):
|
||||
@@ -208,13 +158,10 @@ def test_openapi_validation_create_tag_missing_required_title(client, live_serve
|
||||
# Should get 400 error due to missing required field
|
||||
assert res.status_code == 400, f"Expected 400 but got {res.status_code}"
|
||||
assert b"Validation failed" in res.data, "Should contain validation error message"
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
def test_openapi_validation_watch_update_allows_partial_updates(client, live_server, measure_memory_usage, datastore_path):
|
||||
|
||||
"""Test that watch updates allow partial updates without requiring all fields (positive test)."""
|
||||
#xxx
|
||||
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
|
||||
|
||||
# First create a valid watch
|
||||
@@ -251,5 +198,4 @@ def test_openapi_validation_watch_update_allows_partial_updates(client, live_ser
|
||||
)
|
||||
assert res.status_code == 200
|
||||
assert res.json.get('title') == 'Updated Title Only', "Title should be updated"
|
||||
assert res.json.get('url') == 'https://example.com', "URL should remain unchanged"
|
||||
delete_all_watches(client)
|
||||
assert res.json.get('url') == 'https://example.com', "URL should remain unchanged"
|
||||
@@ -176,97 +176,6 @@ def test_api_tags_listing(client, live_server, measure_memory_usage, datastore_p
|
||||
assert res.status_code == 204
|
||||
|
||||
|
||||
def test_api_tag_restock_processor_config(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test that a tag/group can be created and updated with processor_config_restock_diff via the API.
|
||||
Since Tag extends WatchBase, processor config fields injected into WatchBase are also valid for tags.
|
||||
"""
|
||||
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
|
||||
|
||||
set_original_response(datastore_path=datastore_path)
|
||||
|
||||
# Create a tag with processor_config_restock_diff in a single POST (issue #3966)
|
||||
res = client.post(
|
||||
url_for("tag"),
|
||||
data=json.dumps({
|
||||
"title": "Restock Group",
|
||||
"overrides_watch": True,
|
||||
"processor_config_restock_diff": {
|
||||
"in_stock_processing": "in_stock_only",
|
||||
"follow_price_changes": True,
|
||||
"price_change_min": 7777777
|
||||
}
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key}
|
||||
)
|
||||
assert res.status_code == 201, f"POST tag with restock config failed: {res.data}"
|
||||
tag_uuid = res.json.get('uuid')
|
||||
|
||||
# Verify processor config was saved during creation (the bug: these were discarded)
|
||||
res = client.get(
|
||||
url_for("tag", uuid=tag_uuid),
|
||||
headers={'x-api-key': api_key}
|
||||
)
|
||||
assert res.status_code == 200
|
||||
tag_data = res.json
|
||||
assert tag_data.get('overrides_watch') == True, "overrides_watch should be saved on POST"
|
||||
assert tag_data.get('processor_config_restock_diff', {}).get('in_stock_processing') == 'in_stock_only', \
|
||||
"processor_config_restock_diff should be saved on POST"
|
||||
assert tag_data.get('processor_config_restock_diff', {}).get('price_change_min') == 7777777, \
|
||||
"price_change_min should be saved on POST"
|
||||
|
||||
# Update tag with valid processor_config_restock_diff via PUT
|
||||
res = client.put(
|
||||
url_for("tag", uuid=tag_uuid),
|
||||
headers={'x-api-key': api_key, 'content-type': 'application/json'},
|
||||
data=json.dumps({
|
||||
"overrides_watch": True,
|
||||
"processor_config_restock_diff": {
|
||||
"in_stock_processing": "in_stock_only",
|
||||
"follow_price_changes": True,
|
||||
"price_change_min": 8888888
|
||||
}
|
||||
})
|
||||
)
|
||||
assert res.status_code == 200, f"PUT tag with restock config failed: {res.data}"
|
||||
|
||||
# Verify the config was stored via API
|
||||
res = client.get(
|
||||
url_for("tag", uuid=tag_uuid),
|
||||
headers={'x-api-key': api_key}
|
||||
)
|
||||
assert res.status_code == 200
|
||||
tag_data = res.json
|
||||
assert tag_data.get('overrides_watch') == True
|
||||
assert tag_data.get('processor_config_restock_diff', {}).get('in_stock_processing') == 'in_stock_only'
|
||||
assert tag_data.get('processor_config_restock_diff', {}).get('price_change_min') == 8888888
|
||||
|
||||
# Verify the value is also reflected in the UI tag edit page
|
||||
res = client.get(url_for("tags.form_tag_edit", uuid=tag_uuid))
|
||||
assert res.status_code == 200
|
||||
assert b'8888888' in res.data, "price_change_min set via API should appear in the UI tag edit form"
|
||||
|
||||
# Invalid enum value should be rejected by OpenAPI spec validation
|
||||
res = client.put(
|
||||
url_for("tag", uuid=tag_uuid),
|
||||
headers={'x-api-key': api_key, 'content-type': 'application/json'},
|
||||
data=json.dumps({
|
||||
"processor_config_restock_diff": {
|
||||
"in_stock_processing": "not_a_valid_value"
|
||||
}
|
||||
})
|
||||
)
|
||||
assert res.status_code == 400
|
||||
assert b'Validation failed' in res.data
|
||||
|
||||
# Clean up
|
||||
res = client.delete(
|
||||
url_for("tag", uuid=tag_uuid),
|
||||
headers={'x-api-key': api_key}
|
||||
)
|
||||
assert res.status_code == 204
|
||||
|
||||
|
||||
def test_roundtrip_API(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test the full round trip, this way we test the default Model fits back into OpenAPI spec
|
||||
|
||||
@@ -6,6 +6,8 @@ from flask import url_for
|
||||
from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, extract_rss_token_from_UI, \
|
||||
extract_UUID_from_client, delete_all_watches
|
||||
|
||||
sleep_time_for_fetch_thread = 3
|
||||
|
||||
|
||||
# Basic test to check inscriptus is not adding return line chars, basically works etc
|
||||
def test_inscriptus():
|
||||
@@ -48,15 +50,6 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
|
||||
# Check this class does not appear (that we didnt see the actual source)
|
||||
assert b'foobar-detection' not in res.data
|
||||
|
||||
# Check POST preview
|
||||
res = client.post(
|
||||
url_for("ui.ui_preview.preview_page", uuid="first"),
|
||||
follow_redirects=True
|
||||
)
|
||||
# Check this class does not appear (that we didnt see the actual source)
|
||||
assert b'foobar-detection' not in res.data
|
||||
|
||||
|
||||
# Make a change
|
||||
set_modified_response(datastore_path=datastore_path)
|
||||
|
||||
@@ -422,28 +415,3 @@ def test_plaintext_even_if_xml_content_and_can_apply_filters(client, live_server
|
||||
assert b'<foobar' not in res.data
|
||||
|
||||
res = delete_all_watches(client)
|
||||
|
||||
|
||||
def test_last_error_cleared_on_same_checksum(client, live_server, datastore_path):
|
||||
"""last_error should be cleared even when content is unchanged (checksumFromPreviousCheckWasTheSame path)"""
|
||||
set_original_response(datastore_path=datastore_path)
|
||||
|
||||
uuid = client.application.config.get('DATASTORE').add_watch(url=url_for('test_endpoint', _external=True))
|
||||
|
||||
# First check - establishes baseline checksum
|
||||
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
|
||||
wait_for_all_checks(client)
|
||||
|
||||
# Inject a stale last_error directly (simulates a prior failed check)
|
||||
datastore = client.application.config.get('DATASTORE')
|
||||
datastore.update_watch(uuid=uuid, update_obj={'last_error': 'Some previous error'})
|
||||
assert datastore.data['watching'][uuid].get('last_error') == 'Some previous error'
|
||||
|
||||
# Second check - same content, so checksumFromPreviousCheckWasTheSame will fire
|
||||
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
|
||||
wait_for_all_checks(client)
|
||||
|
||||
# last_error must be cleared even though no change was detected
|
||||
assert datastore.data['watching'][uuid].get('last_error') == False
|
||||
|
||||
delete_all_watches(client)
|
||||
|
||||
@@ -3,13 +3,14 @@
|
||||
from .util import set_original_response, live_server_setup, wait_for_all_checks
|
||||
from flask import url_for
|
||||
import io
|
||||
from zipfile import ZipFile, ZIP_DEFLATED
|
||||
from zipfile import ZipFile
|
||||
import re
|
||||
import time
|
||||
from changedetectionio.model import Watch, Tag
|
||||
|
||||
|
||||
def test_backup(client, live_server, measure_memory_usage, datastore_path):
|
||||
# live_server_setup(live_server) # Setup on conftest per function
|
||||
|
||||
set_original_response(datastore_path=datastore_path)
|
||||
|
||||
|
||||
@@ -31,7 +32,7 @@ def test_backup(client, live_server, measure_memory_usage, datastore_path):
|
||||
time.sleep(4)
|
||||
|
||||
res = client.get(
|
||||
url_for("backups.create"),
|
||||
url_for("backups.index"),
|
||||
follow_redirects=True
|
||||
)
|
||||
# Can see the download link to the backup
|
||||
@@ -68,9 +69,6 @@ def test_backup(client, live_server, measure_memory_usage, datastore_path):
|
||||
# Check for changedetection.json (settings file)
|
||||
assert 'changedetection.json' in l, "changedetection.json should be in backup"
|
||||
|
||||
# secret.txt must never be included — it contains the Flask session key
|
||||
assert 'secret.txt' not in l, "secret.txt (Flask session key) must not be included in backup"
|
||||
|
||||
# Get the latest one
|
||||
res = client.get(
|
||||
url_for("backups.remove_backups"),
|
||||
@@ -82,18 +80,37 @@ def test_backup(client, live_server, measure_memory_usage, datastore_path):
|
||||
|
||||
def test_watch_data_package_download(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""Test downloading a single watch's data as a zip package"""
|
||||
import os
|
||||
import json
|
||||
|
||||
set_original_response(datastore_path=datastore_path)
|
||||
|
||||
uuid = client.application.config.get('DATASTORE').add_watch(url=url_for('test_endpoint', _external=True))
|
||||
tag_uuid = client.application.config.get('DATASTORE').add_tag(title="Tasty backup tag")
|
||||
tag_uuid2 = client.application.config.get('DATASTORE').add_tag(title="Tasty backup tag number two")
|
||||
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
|
||||
# Add a watch
|
||||
res = client.post(
|
||||
url_for("imports.import_page"),
|
||||
data={"urls": url_for('test_endpoint', _external=True)},
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
assert b"1 Imported" in res.data
|
||||
wait_for_all_checks(client)
|
||||
|
||||
# Get the UUID directly from the datastore
|
||||
# Find the watch directories
|
||||
uuid = None
|
||||
for item in os.listdir(datastore_path):
|
||||
item_path = os.path.join(datastore_path, item)
|
||||
if os.path.isdir(item_path) and len(item) == 36: # UUID format
|
||||
uuid = item
|
||||
break
|
||||
|
||||
assert uuid is not None, "Could not find watch UUID in datastore"
|
||||
|
||||
# Download the watch data package
|
||||
res = client.get(url_for("ui.ui_edit.watch_get_data_package", uuid=uuid))
|
||||
res = client.get(
|
||||
url_for("ui.ui_edit.watch_get_data_package", uuid=uuid),
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
# Should get the right zip content type
|
||||
assert res.content_type == "application/zip"
|
||||
@@ -116,146 +133,4 @@ def test_watch_data_package_download(client, live_server, measure_memory_usage,
|
||||
# Should contain history/snapshot files
|
||||
uuid4hex_txt = re.compile(f'^{re.escape(uuid)}/.*\\.txt', re.I)
|
||||
txt_files = list(filter(uuid4hex_txt.match, files))
|
||||
assert len(txt_files) > 0, f"Should have at least one .txt file (history/snapshot), got: {files}"
|
||||
|
||||
|
||||
def test_backup_restore(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""Test that a full backup zip can be restored — watches and tags survive a round-trip."""
|
||||
|
||||
set_original_response(datastore_path=datastore_path)
|
||||
|
||||
datastore = live_server.app.config['DATASTORE']
|
||||
watch_url = url_for('test_endpoint', _external=True)
|
||||
|
||||
# Set up: one watch and two tags
|
||||
uuid = datastore.add_watch(url=watch_url)
|
||||
tag_uuid = datastore.add_tag(title="Tasty backup tag")
|
||||
tag_uuid2 = datastore.add_tag(title="Tasty backup tag number two")
|
||||
|
||||
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
|
||||
wait_for_all_checks(client)
|
||||
|
||||
# Create a full backup
|
||||
client.get(url_for("backups.request_backup"), follow_redirects=True)
|
||||
time.sleep(4)
|
||||
|
||||
# Download the latest backup zip
|
||||
res = client.get(url_for("backups.download_backup", filename="latest"), follow_redirects=True)
|
||||
assert res.content_type == "application/zip"
|
||||
zip_data = res.data
|
||||
|
||||
# Confirm the zip contains both watch.json and tag.json entries
|
||||
backup = ZipFile(io.BytesIO(zip_data))
|
||||
names = backup.namelist()
|
||||
assert f"{uuid}/watch.json" in names, f"watch.json missing from backup: {names}"
|
||||
assert f"{tag_uuid}/tag.json" in names, f"tag.json for tag 1 missing from backup: {names}"
|
||||
assert f"{tag_uuid2}/tag.json" in names, f"tag.json for tag 2 missing from backup: {names}"
|
||||
|
||||
# --- Wipe everything ---
|
||||
datastore.delete('all')
|
||||
client.get(url_for("tags.delete_all"), follow_redirects=True)
|
||||
|
||||
assert uuid not in datastore.data['watching'], "Watch should be gone after delete"
|
||||
assert tag_uuid not in datastore.data['settings']['application']['tags'], "Tag 1 should be gone after delete"
|
||||
assert tag_uuid2 not in datastore.data['settings']['application']['tags'], "Tag 2 should be gone after delete"
|
||||
|
||||
# --- Restore from the backup zip ---
|
||||
res = client.post(
|
||||
url_for("backups.restore.backups_restore_start"),
|
||||
data={
|
||||
'zip_file': (io.BytesIO(zip_data), 'backup.zip'),
|
||||
'include_groups': 'y',
|
||||
'include_groups_replace_existing': 'y',
|
||||
'include_watches': 'y',
|
||||
'include_watches_replace_existing': 'y',
|
||||
},
|
||||
content_type='multipart/form-data',
|
||||
follow_redirects=True
|
||||
)
|
||||
assert res.status_code == 200
|
||||
|
||||
# Wait for the thread to finish
|
||||
time.sleep(2)
|
||||
|
||||
# --- Watch checks ---
|
||||
restored_watch = datastore.data['watching'].get(uuid)
|
||||
assert restored_watch is not None, f"Watch {uuid} not found after restore"
|
||||
assert restored_watch['url'] == watch_url, "Restored watch URL does not match"
|
||||
assert isinstance(restored_watch, Watch.model), \
|
||||
f"Watch not properly rehydrated, got {type(restored_watch)}"
|
||||
assert restored_watch.history_n >= 1, \
|
||||
f"Restored watch should have at least 1 history entry, got {restored_watch.history_n}"
|
||||
|
||||
# --- Tag checks ---
|
||||
restored_tags = datastore.data['settings']['application']['tags']
|
||||
|
||||
restored_tag = restored_tags.get(tag_uuid)
|
||||
assert restored_tag is not None, f"Tag {tag_uuid} not found after restore"
|
||||
assert restored_tag['title'] == "Tasty backup tag", "Restored tag 1 title does not match"
|
||||
assert isinstance(restored_tag, Tag.model), \
|
||||
f"Tag 1 not properly rehydrated, got {type(restored_tag)}"
|
||||
|
||||
restored_tag2 = restored_tags.get(tag_uuid2)
|
||||
assert restored_tag2 is not None, f"Tag {tag_uuid2} not found after restore"
|
||||
assert restored_tag2['title'] == "Tasty backup tag number two", "Restored tag 2 title does not match"
|
||||
assert isinstance(restored_tag2, Tag.model), \
|
||||
f"Tag 2 not properly rehydrated, got {type(restored_tag2)}"
|
||||
|
||||
|
||||
def test_backup_restore_zip_slip_rejected(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""Zip Slip path traversal entries in a restore zip must be rejected."""
|
||||
import pytest
|
||||
from changedetectionio.blueprint.backups.restore import import_from_zip
|
||||
|
||||
# Build a zip with a path traversal entry that would escape the extraction dir
|
||||
malicious_zip = io.BytesIO()
|
||||
with ZipFile(malicious_zip, 'w') as zf:
|
||||
zf.writestr("../escaped.txt", "ATTACKER-CONTROLLED")
|
||||
malicious_zip.seek(0)
|
||||
|
||||
datastore = live_server.app.config['DATASTORE']
|
||||
|
||||
with pytest.raises(ValueError, match="Zip Slip"):
|
||||
import_from_zip(
|
||||
zip_stream=malicious_zip,
|
||||
datastore=datastore,
|
||||
include_groups=True,
|
||||
include_groups_replace=True,
|
||||
include_watches=True,
|
||||
include_watches_replace=True,
|
||||
)
|
||||
|
||||
|
||||
def test_backup_restore_zip_bomb_rejected(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""A zip whose total uncompressed size exceeds the limit must be rejected.
|
||||
|
||||
The guard reads file_size from the zip central-directory metadata — no
|
||||
actual decompression happens, so this test is fast and uses minimal RAM.
|
||||
100 KB of zeros compresses to ~100 bytes; monkeypatching the limit to
|
||||
50 KB is enough to trigger the check without creating any large files.
|
||||
"""
|
||||
import pytest
|
||||
import changedetectionio.blueprint.backups.restore as restore_mod
|
||||
from changedetectionio.blueprint.backups.restore import import_from_zip
|
||||
|
||||
# ~100 KB of zeros → deflate compresses to ~100 bytes, but file_size metadata = 100 KB
|
||||
bomb_zip = io.BytesIO()
|
||||
with ZipFile(bomb_zip, 'w', compression=ZIP_DEFLATED) as zf:
|
||||
zf.writestr("data.txt", b"\x00" * (100 * 1024))
|
||||
bomb_zip.seek(0)
|
||||
|
||||
datastore = live_server.app.config['DATASTORE']
|
||||
original_limit = restore_mod._MAX_DECOMPRESSED_BYTES
|
||||
try:
|
||||
restore_mod._MAX_DECOMPRESSED_BYTES = 50 * 1024 # 50 KB limit for this test
|
||||
with pytest.raises(ValueError, match="decompressed size"):
|
||||
import_from_zip(
|
||||
zip_stream=bomb_zip,
|
||||
datastore=datastore,
|
||||
include_groups=True,
|
||||
include_groups_replace=True,
|
||||
include_watches=True,
|
||||
include_watches_replace=True,
|
||||
)
|
||||
finally:
|
||||
restore_mod._MAX_DECOMPRESSED_BYTES = original_limit
|
||||
assert len(txt_files) > 0, f"Should have at least one .txt file (history/snapshot), got: {files}"
|
||||
@@ -1,7 +1,6 @@
|
||||
#!/usr/bin/env python3
|
||||
# coding=utf-8
|
||||
|
||||
import hashlib
|
||||
import time
|
||||
from flask import url_for
|
||||
from .util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
|
||||
@@ -12,69 +11,6 @@ import os
|
||||
|
||||
|
||||
|
||||
def test_surrogate_characters_in_content_are_sanitized():
|
||||
"""Lone surrogates can appear in requests' r.text when a server returns malformed/mixed-encoding
|
||||
content. Without sanitization, encoding to UTF-8 raises UnicodeEncodeError.
|
||||
See: https://github.com/dgtlmoon/changedetection.io/issues/3952
|
||||
"""
|
||||
content_with_surrogate = '<html><body>Hello \udcad World</body></html>'
|
||||
|
||||
# Confirm the raw problem exists
|
||||
with pytest.raises(UnicodeEncodeError):
|
||||
content_with_surrogate.encode('utf-8')
|
||||
|
||||
# Our fix: sanitize after fetcher.run() in processors/base.py call_browser()
|
||||
sanitized = content_with_surrogate.encode('utf-8', errors='replace').decode('utf-8')
|
||||
assert 'Hello' in sanitized
|
||||
assert 'World' in sanitized
|
||||
assert '\udcad' not in sanitized
|
||||
|
||||
# Checksum computation (processors/base.py get_raw_document_checksum) must not crash
|
||||
hashlib.md5(sanitized.encode('utf-8')).hexdigest()
|
||||
|
||||
|
||||
def test_utf8_content_without_charset_header(client, live_server, datastore_path):
|
||||
"""Server returns UTF-8 content but no charset in Content-Type header.
|
||||
chardet can misdetect such pages as UTF-7 (Python 3.14 then produces surrogates).
|
||||
Our fix tries UTF-8 first before falling back to chardet.
|
||||
See: https://github.com/dgtlmoon/changedetection.io/issues/3952
|
||||
"""
|
||||
from .util import write_test_file_and_sync
|
||||
# UTF-8 encoded content with non-ASCII chars - no charset will be in the header
|
||||
html = '<html><body><p>Español</p><p>Français</p><p>日本語</p></body></html>'
|
||||
write_test_file_and_sync(os.path.join(datastore_path, "endpoint-content.txt"), html.encode('utf-8'), mode='wb')
|
||||
|
||||
test_url = url_for('test_endpoint', content_type="text/html", _external=True)
|
||||
client.application.config.get('DATASTORE').add_watch(url=test_url)
|
||||
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
|
||||
wait_for_all_checks(client)
|
||||
|
||||
res = client.get(url_for("ui.ui_preview.preview_page", uuid="first"), follow_redirects=True)
|
||||
# Should decode correctly as UTF-8, not produce mojibake (Español) or replacement chars
|
||||
assert 'Español'.encode('utf-8') in res.data
|
||||
assert 'Français'.encode('utf-8') in res.data
|
||||
assert '日本語'.encode('utf-8') in res.data
|
||||
|
||||
|
||||
def test_shiftjis_with_meta_charset(client, live_server, datastore_path):
|
||||
"""Server returns Shift-JIS content with no charset in HTTP header, but the HTML
|
||||
declares <meta charset="Shift-JIS">. We should use the meta tag, not chardet.
|
||||
Real-world case: https://github.com/dgtlmoon/changedetection.io/issues/3952
|
||||
"""
|
||||
from .util import write_test_file_and_sync
|
||||
japanese_text = '日本語のページ'
|
||||
html = f'<html><head><meta http-equiv="Content-Type" content="text/html;charset=Shift-JIS"></head><body><p>{japanese_text}</p></body></html>'
|
||||
write_test_file_and_sync(os.path.join(datastore_path, "endpoint-content.txt"), html.encode('shift_jis'), mode='wb')
|
||||
|
||||
test_url = url_for('test_endpoint', content_type="text/html", _external=True)
|
||||
client.application.config.get('DATASTORE').add_watch(url=test_url)
|
||||
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
|
||||
wait_for_all_checks(client)
|
||||
|
||||
res = client.get(url_for("ui.ui_preview.preview_page", uuid="first"), follow_redirects=True)
|
||||
assert japanese_text.encode('utf-8') in res.data
|
||||
|
||||
|
||||
def set_html_response(datastore_path):
|
||||
test_return_data = """
|
||||
<html><body><span class="nav_second_img_text">
|
||||
|
||||
@@ -6,6 +6,10 @@ from urllib.request import urlopen
|
||||
from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
|
||||
import os
|
||||
|
||||
sleep_time_for_fetch_thread = 3
|
||||
|
||||
|
||||
|
||||
def test_check_extract_text_from_diff(client, live_server, measure_memory_usage, datastore_path):
|
||||
import time
|
||||
with open(os.path.join(datastore_path, "endpoint-content.txt"), "w") as f:
|
||||
|
||||
@@ -624,76 +624,3 @@ def test_session_locale_overrides_accept_language(client, live_server, measure_m
|
||||
assert "분".encode() in res.data, "Expected Korean '분' for Minutes"
|
||||
assert "小時".encode() not in res.data, "Should not have Traditional Chinese '小時' when Korean is set"
|
||||
assert "分鐘".encode() not in res.data, "Should not have Traditional Chinese '分鐘' when Korean is set"
|
||||
|
||||
|
||||
def test_clear_history_translated_confirmation(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test that clearing snapshot history works with translated confirmation text.
|
||||
|
||||
Issue #3865: When the app language is set to German, the clear history
|
||||
confirmation dialog shows the translated word (e.g. 'loschen') but the
|
||||
backend only accepted the English word 'clear', making it impossible
|
||||
to clear snapshots in non-English languages.
|
||||
"""
|
||||
from flask import url_for
|
||||
|
||||
test_url = url_for('test_endpoint', _external=True)
|
||||
|
||||
# Add a watch so there is history to clear
|
||||
res = client.post(
|
||||
url_for("imports.import_page"),
|
||||
data={"urls": test_url},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert b"1 Imported" in res.data
|
||||
wait_for_all_checks(client)
|
||||
|
||||
# Set language to German
|
||||
res = client.get(
|
||||
url_for("set_language", locale="de"),
|
||||
follow_redirects=True
|
||||
)
|
||||
assert res.status_code == 200
|
||||
|
||||
# Verify the clear history page shows the German confirmation word
|
||||
res = client.get(
|
||||
url_for("ui.clear_all_history"),
|
||||
follow_redirects=True
|
||||
)
|
||||
assert res.status_code == 200
|
||||
assert "löschen".encode() in res.data, "Expected German word 'loschen' on clear history page"
|
||||
|
||||
# Submit the form with the German translated word
|
||||
res = client.post(
|
||||
url_for("ui.clear_all_history"),
|
||||
data={"confirmtext": "löschen"},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert res.status_code == 200
|
||||
# Should NOT show error message
|
||||
assert b"Incorrect confirmation text" not in res.data, \
|
||||
"German confirmation word 'loschen' should be accepted (issue #3865)"
|
||||
|
||||
# Switch back to English and verify English word still works
|
||||
res = client.get(
|
||||
url_for("set_language", locale="en_US"),
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
res = client.post(
|
||||
url_for("ui.clear_all_history"),
|
||||
data={"confirmtext": "clear"},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert res.status_code == 200
|
||||
assert b"Incorrect confirmation text" not in res.data, \
|
||||
"English confirmation word 'clear' should still be accepted"
|
||||
|
||||
# Verify that missing/empty confirmtext does not crash the server
|
||||
res = client.post(
|
||||
url_for("ui.clear_all_history"),
|
||||
data={},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert res.status_code == 200, \
|
||||
"Missing confirmtext should not crash the server"
|
||||
|
||||
@@ -41,6 +41,7 @@ def set_modified_ignore_response(datastore_path):
|
||||
def test_render_anchor_tag_content_true(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""Testing that the link changes are detected when
|
||||
render_anchor_tag_content setting is set to true"""
|
||||
sleep_time_for_fetch_thread = 3
|
||||
|
||||
# Give the endpoint time to spin up
|
||||
time.sleep(1)
|
||||
|
||||
@@ -100,6 +100,7 @@ def test_normal_page_check_works_with_ignore_status_code(client, live_server, me
|
||||
|
||||
# Tests the whole stack works with staus codes ignored
|
||||
def test_403_page_check_works_with_ignore_status_code(client, live_server, measure_memory_usage, datastore_path):
|
||||
sleep_time_for_fetch_thread = 3
|
||||
|
||||
set_original_response(datastore_path=datastore_path)
|
||||
|
||||
@@ -111,7 +112,8 @@ def test_403_page_check_works_with_ignore_status_code(client, live_server, measu
|
||||
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
|
||||
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
|
||||
|
||||
wait_for_all_checks(client)
|
||||
# Give the thread time to pick it up
|
||||
time.sleep(sleep_time_for_fetch_thread)
|
||||
|
||||
# Goto the edit page, check our ignore option
|
||||
# Add our URL to the import page
|
||||
|
||||
@@ -2,9 +2,10 @@
|
||||
|
||||
import time
|
||||
from flask import url_for
|
||||
from . util import live_server_setup
|
||||
import os
|
||||
|
||||
from .util import live_server_setup, delete_all_watches, wait_for_all_checks
|
||||
|
||||
|
||||
|
||||
# Should be the same as set_original_ignore_response(datastore_path=datastore_path) but with a little more whitespacing
|
||||
@@ -49,7 +50,10 @@ def set_original_ignore_response(datastore_path):
|
||||
|
||||
# If there was only a change in the whitespacing, then we shouldnt have a change detected
|
||||
def test_check_ignore_whitespace(client, live_server, measure_memory_usage, datastore_path):
|
||||
sleep_time_for_fetch_thread = 3
|
||||
|
||||
# Give the endpoint time to spin up
|
||||
time.sleep(1)
|
||||
|
||||
set_original_ignore_response(datastore_path=datastore_path)
|
||||
|
||||
@@ -70,17 +74,17 @@ def test_check_ignore_whitespace(client, live_server, measure_memory_usage, data
|
||||
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
|
||||
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
|
||||
|
||||
wait_for_all_checks(client)
|
||||
time.sleep(sleep_time_for_fetch_thread)
|
||||
# Trigger a check
|
||||
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
|
||||
|
||||
set_original_ignore_response_but_with_whitespace(datastore_path)
|
||||
wait_for_all_checks(client)
|
||||
time.sleep(sleep_time_for_fetch_thread)
|
||||
# Trigger a check
|
||||
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
|
||||
|
||||
# Give the thread time to pick it up
|
||||
wait_for_all_checks(client)
|
||||
time.sleep(sleep_time_for_fetch_thread)
|
||||
|
||||
# It should report nothing found (no new 'has-unread-changes' class)
|
||||
res = client.get(url_for("watchlist.index"))
|
||||
|
||||
@@ -16,51 +16,6 @@ except ModuleNotFoundError:
|
||||
|
||||
|
||||
|
||||
def test_jsonp_treated_as_plaintext():
|
||||
from ..processors.magic import guess_stream_type
|
||||
|
||||
# JSONP content (server wrongly claims application/json) should be detected as plaintext
|
||||
# Callback names are arbitrary identifiers, not always 'cb'
|
||||
jsonp_content = 'jQuery123456({ "version": "8.0.41", "url": "https://example.com/app.apk" })'
|
||||
result = guess_stream_type(http_content_header="application/json", content=jsonp_content)
|
||||
assert result.is_json is False
|
||||
assert result.is_plaintext is True
|
||||
|
||||
# Variation with dotted callback name e.g. jQuery.cb(...)
|
||||
jsonp_dotted = 'some.callback({ "version": "1.0" })'
|
||||
result = guess_stream_type(http_content_header="application/json", content=jsonp_dotted)
|
||||
assert result.is_json is False
|
||||
assert result.is_plaintext is True
|
||||
|
||||
# Real JSON should still be detected as JSON
|
||||
json_content = '{ "version": "8.0.41", "url": "https://example.com/app.apk" }'
|
||||
result = guess_stream_type(http_content_header="application/json", content=json_content)
|
||||
assert result.is_json is True
|
||||
assert result.is_plaintext is False
|
||||
|
||||
|
||||
def test_jsonp_json_filter_extraction():
|
||||
from .. import html_tools
|
||||
|
||||
# Tough case: dotted namespace callback, trailing semicolon, deeply nested content with arrays
|
||||
jsonp_content = 'weixin.update.callback({"platforms": {"android": {"variants": [{"arch": "arm64", "versionName": "8.0.68", "url": "https://example.com/app-arm64.apk"}, {"arch": "arm32", "versionName": "8.0.41", "url": "https://example.com/app-arm32.apk"}]}}});'
|
||||
|
||||
# Deep nested jsonpath filter into array element
|
||||
text = html_tools.extract_json_as_string(jsonp_content, "json:$.platforms.android.variants[0].versionName")
|
||||
assert text == '"8.0.68"'
|
||||
|
||||
# Filter that selects the second array element
|
||||
text = html_tools.extract_json_as_string(jsonp_content, "json:$.platforms.android.variants[1].arch")
|
||||
assert text == '"arm32"'
|
||||
|
||||
if jq_support:
|
||||
text = html_tools.extract_json_as_string(jsonp_content, "jq:.platforms.android.variants[0].versionName")
|
||||
assert text == '"8.0.68"'
|
||||
|
||||
text = html_tools.extract_json_as_string(jsonp_content, "jqraw:.platforms.android.variants[1].url")
|
||||
assert text == "https://example.com/app-arm32.apk"
|
||||
|
||||
|
||||
def test_unittest_inline_html_extract():
|
||||
# So lets pretend that the JSON we want is inside some HTML
|
||||
content="""
|
||||
|
||||
@@ -17,7 +17,6 @@ from changedetectionio.notification import (
|
||||
)
|
||||
from ..diff import HTML_CHANGED_STYLE
|
||||
from ..model import USE_SYSTEM_DEFAULT_NOTIFICATION_FORMAT_FOR_WATCH
|
||||
from ..notification_service import FormattableTimestamp
|
||||
|
||||
|
||||
# Hard to just add more live server URLs when one test is already running (I think)
|
||||
@@ -108,11 +107,7 @@ def test_check_notification(client, live_server, measure_memory_usage, datastore
|
||||
"Diff Added: {{diff_added}}\n"
|
||||
"Diff Removed: {{diff_removed}}\n"
|
||||
"Diff Full: {{diff_full}}\n"
|
||||
"Diff with args: {{diff(context=3)}}"
|
||||
"Diff as Patch: {{diff_patch}}\n"
|
||||
"Change datetime: {{change_datetime}}\n"
|
||||
"Change datetime format: Weekday {{change_datetime(format='%A')}}\n"
|
||||
"Change datetime format: {{change_datetime(format='%Y-%m-%dT%H:%M:%S%z')}}\n"
|
||||
":-)",
|
||||
"notification_screenshot": True,
|
||||
"notification_format": 'text'}
|
||||
@@ -140,6 +135,8 @@ def test_check_notification(client, live_server, measure_memory_usage, datastore
|
||||
assert bytes(notification_url.encode('utf-8')) in res.data
|
||||
assert bytes("New ChangeDetection.io Notification".encode('utf-8')) in res.data
|
||||
|
||||
|
||||
|
||||
## Now recheck, and it should have sent the notification
|
||||
wait_for_all_checks(client)
|
||||
set_modified_response(datastore_path=datastore_path)
|
||||
@@ -175,23 +172,11 @@ def test_check_notification(client, live_server, measure_memory_usage, datastore
|
||||
assert ":-)" in notification_submission
|
||||
assert "New ChangeDetection.io Notification - {}".format(test_url) in notification_submission
|
||||
assert test_url in notification_submission
|
||||
|
||||
assert ':-)' in notification_submission
|
||||
# Check the attachment was added, and that it is a JPEG from the original PNG
|
||||
notification_submission_object = json.loads(notification_submission)
|
||||
assert notification_submission_object
|
||||
|
||||
import time
|
||||
# Could be from a few seconds ago (when the notification was fired vs in this test checking), so check for any
|
||||
times_possible = [str(FormattableTimestamp(int(time.time()) - i)) for i in range(15)]
|
||||
assert any(t in notification_submission for t in times_possible)
|
||||
|
||||
txt = f"Weekday {FormattableTimestamp(int(time.time()))(format='%A')}"
|
||||
assert txt in notification_submission
|
||||
|
||||
|
||||
|
||||
|
||||
# We keep PNG screenshots for now
|
||||
# IF THIS FAILS YOU SHOULD BE TESTING WITH ENV VAR REMOVE_REQUESTS_OLD_SCREENSHOTS=False
|
||||
assert notification_submission_object['attachments'][0]['filename'] == 'last-screenshot.png'
|
||||
|
||||
@@ -109,7 +109,7 @@ def test_itemprop_price_change(client, live_server, measure_memory_usage, datast
|
||||
set_original_response(props_markup=instock_props[0], price='120.45', datastore_path=datastore_path)
|
||||
res = client.post(
|
||||
url_for("ui.ui_edit.edit_page", uuid="first"),
|
||||
data={"processor_config_restock_diff-follow_price_changes": "", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
|
||||
data={"restock_settings-follow_price_changes": "", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert b"Updated watch." in res.data
|
||||
@@ -204,9 +204,9 @@ def _run_test_minmax_limit(client, extra_watch_edit_form, datastore_path):
|
||||
def test_restock_itemprop_minmax(client, live_server, measure_memory_usage, datastore_path):
|
||||
|
||||
extras = {
|
||||
"processor_config_restock_diff-follow_price_changes": "y",
|
||||
"processor_config_restock_diff-price_change_min": 900.0,
|
||||
"processor_config_restock_diff-price_change_max": 1100.10
|
||||
"restock_settings-follow_price_changes": "y",
|
||||
"restock_settings-price_change_min": 900.0,
|
||||
"restock_settings-price_change_max": 1100.10
|
||||
}
|
||||
_run_test_minmax_limit(client, extra_watch_edit_form=extras, datastore_path=datastore_path)
|
||||
|
||||
@@ -223,9 +223,9 @@ def test_restock_itemprop_with_tag(client, live_server, measure_memory_usage, da
|
||||
res = client.post(
|
||||
url_for("tags.form_tag_edit_submit", uuid="first"),
|
||||
data={"name": "test-tag",
|
||||
"processor_config_restock_diff-follow_price_changes": "y",
|
||||
"processor_config_restock_diff-price_change_min": 900.0,
|
||||
"processor_config_restock_diff-price_change_max": 1100.10,
|
||||
"restock_settings-follow_price_changes": "y",
|
||||
"restock_settings-price_change_min": 900.0,
|
||||
"restock_settings-price_change_max": 1100.10,
|
||||
"overrides_watch": "y", #overrides_watch should be restock_overrides_watch
|
||||
},
|
||||
follow_redirects=True
|
||||
@@ -258,8 +258,8 @@ def test_itemprop_percent_threshold(client, live_server, measure_memory_usage, d
|
||||
|
||||
res = client.post(
|
||||
url_for("ui.ui_edit.edit_page", uuid="first"),
|
||||
data={"processor_config_restock_diff-follow_price_changes": "y",
|
||||
"processor_config_restock_diff-price_change_threshold_percent": 5.0,
|
||||
data={"restock_settings-follow_price_changes": "y",
|
||||
"restock_settings-price_change_threshold_percent": 5.0,
|
||||
"url": test_url,
|
||||
"tags": "",
|
||||
"headers": "",
|
||||
@@ -305,8 +305,8 @@ def test_itemprop_percent_threshold(client, live_server, measure_memory_usage, d
|
||||
|
||||
res = client.post(
|
||||
url_for("ui.ui_edit.edit_page", uuid=uuid),
|
||||
data={"processor_config_restock_diff-follow_price_changes": "y",
|
||||
"processor_config_restock_diff-price_change_threshold_percent": 5.05,
|
||||
data={"restock_settings-follow_price_changes": "y",
|
||||
"restock_settings-price_change_threshold_percent": 5.05,
|
||||
"processor": "text_json_diff",
|
||||
"url": test_url,
|
||||
'fetch_backend': "html_requests",
|
||||
@@ -350,7 +350,6 @@ def test_change_with_notification_values(client, live_server, measure_memory_usa
|
||||
res = client.get(url_for("settings.settings_page"))
|
||||
|
||||
assert b'{{restock.original_price}}' in res.data
|
||||
assert b'{{restock.previous_price}}' in res.data
|
||||
assert b'Original price at first check' in res.data
|
||||
|
||||
#####################
|
||||
@@ -359,7 +358,7 @@ def test_change_with_notification_values(client, live_server, measure_memory_usa
|
||||
url_for("settings.settings_page"),
|
||||
data={"application-notification_urls": notification_url,
|
||||
"application-notification_title": "title new price {{restock.price}}",
|
||||
"application-notification_body": "new price {{restock.price}} previous price {{restock.previous_price}} instock {{restock.in_stock}}",
|
||||
"application-notification_body": "new price {{restock.price}}",
|
||||
"application-notification_format": default_notification_format,
|
||||
"requests-time_between_check-minutes": 180,
|
||||
'application-fetch_backend': "html_requests"},
|
||||
@@ -373,6 +372,8 @@ def test_change_with_notification_values(client, live_server, measure_memory_usa
|
||||
|
||||
assert b"Settings updated." in res.data
|
||||
|
||||
|
||||
set_original_response(props_markup=instock_props[0], price='960.45', datastore_path=datastore_path)
|
||||
# A change in price, should trigger a change by default
|
||||
set_original_response(props_markup=instock_props[0], price='1950.45', datastore_path=datastore_path)
|
||||
client.get(url_for("ui.form_watch_checknow"))
|
||||
@@ -383,7 +384,6 @@ def test_change_with_notification_values(client, live_server, measure_memory_usa
|
||||
notification = f.read()
|
||||
assert "new price 1950.45" in notification
|
||||
assert "title new price 1950.45" in notification
|
||||
assert "previous price 960.45" in notification
|
||||
|
||||
## Now test the "SEND TEST NOTIFICATION" is working
|
||||
os.unlink(os.path.join(datastore_path, "notification.txt"))
|
||||
@@ -467,38 +467,3 @@ def test_special_prop_examples(client, live_server, measure_memory_usage, datast
|
||||
assert b'155.55' in res.data
|
||||
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
def test_itemprop_as_str(client, live_server, measure_memory_usage, datastore_path):
|
||||
|
||||
test_return_data = f"""<html>
|
||||
<body>
|
||||
Some initial text<br>
|
||||
<p>Which is across multiple lines</p>
|
||||
<span itemprop="offers" itemscope itemtype="http://schema.org/Offer">
|
||||
<meta content="767.55" itemprop="price"/>
|
||||
<meta content="EUR" itemprop="priceCurrency"/>
|
||||
<meta content="InStock" itemprop="availability"/>
|
||||
<meta content="https://www.123-test.dk" itemprop="url"/>
|
||||
</span>
|
||||
</body>
|
||||
</html>
|
||||
"""
|
||||
|
||||
with open(os.path.join(datastore_path, "endpoint-content.txt"), "w") as f:
|
||||
f.write(test_return_data)
|
||||
|
||||
|
||||
test_url = url_for('test_endpoint', _external=True)
|
||||
|
||||
client.post(
|
||||
url_for("ui.ui_views.form_quick_watch_add"),
|
||||
data={"url": test_url, "tags": 'restock tests', 'processor': 'restock_diff'},
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
client.get(url_for("ui.form_watch_checknow"))
|
||||
wait_for_all_checks(client)
|
||||
|
||||
res = client.get(url_for("watchlist.index"))
|
||||
assert b'767.55' in res.data
|
||||
@@ -1,5 +1,4 @@
|
||||
import os
|
||||
import pytest
|
||||
|
||||
from flask import url_for
|
||||
|
||||
@@ -25,31 +24,6 @@ def set_original_response(datastore_path):
|
||||
f.write(test_return_data)
|
||||
return None
|
||||
|
||||
|
||||
def test_favicon(client, live_server, measure_memory_usage, datastore_path):
|
||||
# Attempt to fetch it, make sure that works
|
||||
SVG_BASE64 = 'PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAxIDEiLz4='
|
||||
uuid = client.application.config.get('DATASTORE').add_watch(url='https://localhost')
|
||||
live_server.app.config['DATASTORE'].data['watching'][uuid].bump_favicon(url="favicon-set-type.svg",
|
||||
favicon_base_64=SVG_BASE64
|
||||
)
|
||||
|
||||
|
||||
res = client.get(url_for('static_content', group='favicon', filename=uuid))
|
||||
assert res.status_code == 200
|
||||
assert len(res.data) > 10
|
||||
|
||||
res = client.get(url_for('static_content', group='..', filename='__init__.py'))
|
||||
assert res.status_code != 200
|
||||
|
||||
|
||||
res = client.get(url_for('static_content', group='.', filename='../__init__.py'))
|
||||
assert res.status_code != 200
|
||||
|
||||
# Traverse by filename protection
|
||||
res = client.get(url_for('static_content', group='js', filename='../styles/styles.css'))
|
||||
assert res.status_code != 200
|
||||
|
||||
def test_bad_access(client, live_server, measure_memory_usage, datastore_path):
|
||||
|
||||
res = client.post(
|
||||
@@ -504,243 +478,3 @@ def test_logout_with_redirect(client, live_server, measure_memory_usage, datasto
|
||||
# Cleanup
|
||||
del client.application.config['DATASTORE'].data['settings']['application']['password']
|
||||
|
||||
|
||||
def test_static_directory_traversal(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test that the static file serving route properly blocks directory traversal attempts.
|
||||
This tests the fix for GHSA-9jj8-v89v-xjvw (CVE pending).
|
||||
|
||||
The vulnerability was in /static/<group>/<filename> where the sanitization regex
|
||||
allowed dots, enabling "../" traversal to read application source files.
|
||||
|
||||
The fix changed the regex from r'[^\w.-]+' to r'[^a-z0-9_]+' which blocks dots.
|
||||
"""
|
||||
|
||||
# Test 1: Direct .. traversal attempt (URL-encoded)
|
||||
res = client.get(
|
||||
"/static/%2e%2e/flask_app.py",
|
||||
follow_redirects=False
|
||||
)
|
||||
# Should be blocked (404 or 403)
|
||||
assert res.status_code in [404, 403], f"Expected 404/403, got {res.status_code}"
|
||||
# Should NOT contain application source code
|
||||
assert b"def static_content" not in res.data
|
||||
assert b"changedetection_app" not in res.data
|
||||
|
||||
# Test 2: Direct .. traversal attempt (unencoded)
|
||||
res = client.get(
|
||||
"/static/../flask_app.py",
|
||||
follow_redirects=False
|
||||
)
|
||||
assert res.status_code in [404, 403], f"Expected 404/403, got {res.status_code}"
|
||||
assert b"def static_content" not in res.data
|
||||
|
||||
# Test 3: Multiple dots traversal
|
||||
res = client.get(
|
||||
"/static/..../flask_app.py",
|
||||
follow_redirects=False
|
||||
)
|
||||
assert res.status_code in [404, 403], f"Expected 404/403, got {res.status_code}"
|
||||
assert b"def static_content" not in res.data
|
||||
|
||||
# Test 4: Try to access other application files
|
||||
for filename in ["__init__.py", "datastore.py", "store.py"]:
|
||||
res = client.get(
|
||||
f"/static/%2e%2e/{filename}",
|
||||
follow_redirects=False
|
||||
)
|
||||
assert res.status_code in [404, 403], f"File {filename} should be blocked"
|
||||
# Should not contain Python code indicators
|
||||
assert b"import" not in res.data or b"# Test" in res.data # Allow "1 Imported" etc
|
||||
|
||||
# Test 5: Verify legitimate static files still work
|
||||
# Note: We can't test actual files without knowing what exists,
|
||||
# but we can verify the sanitization doesn't break valid groups
|
||||
res = client.get(
|
||||
"/static/images/test.png", # Will 404 if file doesn't exist, but won't traverse
|
||||
follow_redirects=False
|
||||
)
|
||||
# Should get 404 (file not found) not 403 (blocked)
|
||||
# This confirms the group name "images" is valid
|
||||
assert res.status_code == 404
|
||||
|
||||
# Test 6: Ensure hyphens and dots are blocked in group names
|
||||
res = client.get(
|
||||
"/static/../../../etc/passwd",
|
||||
follow_redirects=False
|
||||
)
|
||||
assert res.status_code in [404, 403]
|
||||
assert b"root:" not in res.data
|
||||
|
||||
# Test 7: Test that underscores still work (they're allowed)
|
||||
res = client.get(
|
||||
"/static/visual_selector_data/test.json",
|
||||
follow_redirects=False
|
||||
)
|
||||
# visual_selector_data is a real group, but requires auth
|
||||
# Should get 403 (not authenticated) or 404 (file not found), not a path traversal
|
||||
assert res.status_code in [403, 404]
|
||||
|
||||
|
||||
def test_ssrf_private_ip_blocked(client, live_server, monkeypatch, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
SSRF protection: IANA-reserved/private IP addresses are blocked at fetch-time, not add-time.
|
||||
|
||||
Watches targeting private/reserved IPs can be *added* freely; the block happens when the
|
||||
fetcher actually tries to reach the URL (via validate_iana_url() in call_browser()).
|
||||
|
||||
Covers:
|
||||
1. is_private_hostname() correctly classifies all reserved ranges
|
||||
2. is_safe_valid_url() ALLOWS private-IP URLs at add-time (IANA check moved to fetch-time)
|
||||
3. ALLOW_IANA_RESTRICTED_ADDRESSES has no effect on add-time; it only controls fetch-time
|
||||
4. UI form accepts private-IP URLs at add-time without error
|
||||
5. Requests fetcher blocks fetch-time DNS rebinding (fresh check on every fetch)
|
||||
6. Requests fetcher blocks redirects that lead to a private IP (open-redirect bypass)
|
||||
|
||||
conftest.py sets ALLOW_IANA_RESTRICTED_ADDRESSES=true globally so the test
|
||||
server (localhost) keeps working for all other tests. monkeypatch temporarily
|
||||
overrides it to 'false' here, and is automatically restored after the test.
|
||||
"""
|
||||
from unittest.mock import patch, MagicMock
|
||||
from changedetectionio.validate_url import is_safe_valid_url, is_private_hostname
|
||||
|
||||
monkeypatch.setenv('ALLOW_IANA_RESTRICTED_ADDRESSES', 'false')
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# 1. is_private_hostname() — unit tests across all reserved ranges
|
||||
# ------------------------------------------------------------------
|
||||
private_hosts = [
|
||||
'127.0.0.1', # loopback
|
||||
'10.0.0.1', # RFC 1918
|
||||
'172.16.0.1', # RFC 1918
|
||||
'192.168.1.1', # RFC 1918
|
||||
'169.254.169.254', # link-local / AWS metadata endpoint
|
||||
'::1', # IPv6 loopback
|
||||
'fc00::1', # IPv6 unique local
|
||||
'fe80::1', # IPv6 link-local
|
||||
]
|
||||
for host in private_hosts:
|
||||
assert is_private_hostname(host), f"{host} should be identified as private/reserved"
|
||||
|
||||
for host in ['8.8.8.8', '1.1.1.1']:
|
||||
assert not is_private_hostname(host), f"{host} should be identified as public"
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# 2. is_safe_valid_url() ALLOWS private-IP URLs at add-time
|
||||
# IANA check is no longer done here — it moved to fetch-time validate_iana_url()
|
||||
# ------------------------------------------------------------------
|
||||
private_ip_urls = [
|
||||
'http://127.0.0.1/',
|
||||
'http://10.0.0.1/',
|
||||
'http://172.16.0.1/',
|
||||
'http://192.168.1.1/',
|
||||
'http://169.254.169.254/',
|
||||
'http://169.254.169.254/latest/meta-data/iam/security-credentials/',
|
||||
'http://[::1]/',
|
||||
'http://[fc00::1]/',
|
||||
'http://[fe80::1]/',
|
||||
]
|
||||
for url in private_ip_urls:
|
||||
assert is_safe_valid_url(url), f"{url} should be allowed by is_safe_valid_url (IANA check is at fetch-time)"
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# 3. ALLOW_IANA_RESTRICTED_ADDRESSES does not affect add-time validation
|
||||
# It only controls fetch-time blocking inside validate_iana_url()
|
||||
# ------------------------------------------------------------------
|
||||
monkeypatch.setenv('ALLOW_IANA_RESTRICTED_ADDRESSES', 'true')
|
||||
assert is_safe_valid_url('http://127.0.0.1/'), \
|
||||
"Private IP should be allowed at add-time regardless of ALLOW_IANA_RESTRICTED_ADDRESSES"
|
||||
|
||||
monkeypatch.setenv('ALLOW_IANA_RESTRICTED_ADDRESSES', 'false')
|
||||
assert is_safe_valid_url('http://127.0.0.1/'), \
|
||||
"Private IP should be allowed at add-time regardless of ALLOW_IANA_RESTRICTED_ADDRESSES"
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# 4. UI form accepts private-IP URLs at add-time
|
||||
# The watch is created; the SSRF block fires later at fetch-time
|
||||
# ------------------------------------------------------------------
|
||||
for url in ['http://127.0.0.1/', 'http://169.254.169.254/latest/meta-data/']:
|
||||
res = client.post(
|
||||
url_for('ui.ui_views.form_quick_watch_add'),
|
||||
data={'url': url, 'tags': ''},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert b'Watch protocol is not permitted or invalid URL format' not in res.data, \
|
||||
f"UI should accept {url} at add-time (SSRF is blocked at fetch-time)"
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# 5. Fetch-time DNS-rebinding check in the requests fetcher
|
||||
# Simulates: URL passed add-time validation with a public IP, but
|
||||
# by fetch time DNS has been rebound to a private IP.
|
||||
# ------------------------------------------------------------------
|
||||
from changedetectionio.content_fetchers.requests import fetcher as RequestsFetcher
|
||||
|
||||
f = RequestsFetcher()
|
||||
|
||||
with patch('changedetectionio.content_fetchers.requests.is_private_hostname', return_value=True):
|
||||
with pytest.raises(Exception, match='private/reserved'):
|
||||
f._run_sync(
|
||||
url='http://example.com/',
|
||||
timeout=5,
|
||||
request_headers={},
|
||||
request_body=None,
|
||||
request_method='GET',
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# 6. Redirect-to-private-IP blocked (open-redirect SSRF bypass)
|
||||
# Public host returns a 302 pointing at an IANA-reserved address.
|
||||
# ------------------------------------------------------------------
|
||||
mock_redirect = MagicMock()
|
||||
mock_redirect.is_redirect = True
|
||||
mock_redirect.status_code = 302
|
||||
mock_redirect.headers = {'Location': 'http://169.254.169.254/latest/meta-data/'}
|
||||
|
||||
def _private_only_for_redirect(hostname):
|
||||
# Initial host is "public"; the redirect target is private
|
||||
return hostname in {'169.254.169.254', '10.0.0.1', '172.16.0.1',
|
||||
'192.168.0.1', '127.0.0.1', '::1'}
|
||||
|
||||
with patch('changedetectionio.content_fetchers.requests.is_private_hostname',
|
||||
side_effect=_private_only_for_redirect):
|
||||
with patch('requests.Session.request', return_value=mock_redirect):
|
||||
with pytest.raises(Exception, match='Redirect blocked'):
|
||||
f._run_sync(
|
||||
url='http://example.com/',
|
||||
timeout=5,
|
||||
request_headers={},
|
||||
request_body=None,
|
||||
request_method='GET',
|
||||
)
|
||||
|
||||
|
||||
def test_unresolvable_hostname_is_allowed(client, live_server, monkeypatch):
|
||||
"""
|
||||
Unresolvable hostnames must NOT be blocked at add-time when ALLOW_IANA_RESTRICTED_ADDRESSES=false.
|
||||
|
||||
DNS failure (gaierror) at add-time does not mean the URL resolves to a private IP —
|
||||
the domain may simply be offline or not yet live. Blocking it would be a false positive.
|
||||
The real DNS-rebinding protection happens at fetch-time in call_browser().
|
||||
"""
|
||||
from changedetectionio.validate_url import is_safe_valid_url
|
||||
|
||||
monkeypatch.setenv('ALLOW_IANA_RESTRICTED_ADDRESSES', 'false')
|
||||
|
||||
url = 'http://this-host-does-not-exist-xyz987.invalid/some/path'
|
||||
|
||||
# Should pass URL validation despite being unresolvable
|
||||
assert is_safe_valid_url(url), \
|
||||
"Unresolvable hostname should pass is_safe_valid_url — DNS failure is not a private-IP signal"
|
||||
|
||||
# Should be accepted via the UI form and appear in the watch list
|
||||
res = client.post(
|
||||
url_for('ui.ui_views.form_quick_watch_add'),
|
||||
data={'url': url, 'tags': ''},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert b'Watch protocol is not permitted or invalid URL format' not in res.data, \
|
||||
"UI should not reject a URL just because its hostname is unresolvable"
|
||||
|
||||
res = client.get(url_for('watchlist.index'))
|
||||
assert b'this-host-does-not-exist-xyz987.invalid' in res.data, \
|
||||
"Unresolvable hostname watch should appear in the watch overview list"
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user