Compare commits

..

7 Commits

Author SHA1 Message Date
dgtlmoon
5db65bcafd not here 2023-09-26 13:40:13 +02:00
dgtlmoon
86832228ed fix punctuation 2023-09-26 13:33:24 +02:00
dgtlmoon
bd10a1f7c4 be more helpful 2023-09-26 13:31:31 +02:00
dgtlmoon
ccbfa1e20e more testing 2023-09-26 13:30:30 +02:00
dgtlmoon
29d34bcd22 better error 2023-09-26 13:26:50 +02:00
dgtlmoon
9b4fb80bef Add test 2023-09-26 13:18:12 +02:00
dgtlmoon
2ff65b53fb Try to be more helpful 2023-09-26 12:45:41 +02:00
53 changed files with 422 additions and 1151 deletions

View File

@@ -2,7 +2,7 @@
# Test that we can still build on Alpine (musl modified libc https://musl.libc.org/)
# Some packages wont install via pypi because they dont have a wheel available under this architecture.
FROM ghcr.io/linuxserver/baseimage-alpine:3.18
FROM ghcr.io/linuxserver/baseimage-alpine:3.16
ENV PYTHONUNBUFFERED=1
COPY requirements.txt /requirements.txt
@@ -26,6 +26,6 @@ RUN \
py3-pip && \
echo "**** pip3 install test of changedetection.io ****" && \
pip3 install -U pip wheel setuptools && \
pip3 install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.18/ -r /requirements.txt && \
pip3 install -U --no-cache-dir --find-links https://wheel-index.linuxserver.io/alpine-3.16/ -r /requirements.txt && \
apk del --purge \
build-dependencies

View File

@@ -30,11 +30,11 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@v4
uses: actions/checkout@v2
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@v2
uses: github/codeql-action/init@v1
with:
languages: ${{ matrix.language }}
# If you wish to specify custom queries, you can do so here or in a config file.
@@ -45,7 +45,7 @@ jobs:
# Autobuild attempts to build any compiled languages (C/C++, C#, or Java).
# If this step fails, then you should remove it and run the build manually (see below)
- name: Autobuild
uses: github/codeql-action/autobuild@v2
uses: github/codeql-action/autobuild@v1
# Command-line programs to run using the OS shell.
# 📚 https://git.io/JvXDl
@@ -59,4 +59,4 @@ jobs:
# make release
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@v2
uses: github/codeql-action/analyze@v1

View File

@@ -39,11 +39,11 @@ jobs:
# Or if we are in a tagged release scenario.
if: ${{ github.event.workflow_run.conclusion == 'success' }} || ${{ github.event.release.tag_name }} != ''
steps:
- uses: actions/checkout@v4
- name: Set up Python 3.11
uses: actions/setup-python@v4
- uses: actions/checkout@v2
- name: Set up Python 3.9
uses: actions/setup-python@v2
with:
python-version: 3.11
python-version: 3.9
- name: Install dependencies
run: |
@@ -58,27 +58,27 @@ jobs:
echo ${{ github.ref }} > changedetectionio/tag.txt
- name: Set up QEMU
uses: docker/setup-qemu-action@v3
uses: docker/setup-qemu-action@v1
with:
image: tonistiigi/binfmt:latest
platforms: all
- name: Login to GitHub Container Registry
uses: docker/login-action@v3
uses: docker/login-action@v1
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Login to Docker Hub Container Registry
uses: docker/login-action@v3
uses: docker/login-action@v1
with:
username: ${{ secrets.DOCKER_HUB_USERNAME }}
password: ${{ secrets.DOCKER_HUB_ACCESS_TOKEN }}
- name: Set up Docker Buildx
id: buildx
uses: docker/setup-buildx-action@v3
uses: docker/setup-buildx-action@v1
with:
install: true
version: latest
@@ -88,7 +88,7 @@ jobs:
- name: Build and push :dev
id: docker_build
if: ${{ github.ref }} == "refs/heads/master"
uses: docker/build-push-action@v5
uses: docker/build-push-action@v2
with:
context: ./
file: ./Dockerfile
@@ -105,7 +105,7 @@ jobs:
- 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@v5
uses: docker/build-push-action@v2
with:
context: ./
file: ./Dockerfile
@@ -125,7 +125,7 @@ jobs:
run: echo step SHA ${{ steps.vars.outputs.sha_short }} tag ${{steps.vars.outputs.tag}} branch ${{steps.vars.outputs.branch}} digest ${{ steps.docker_build.outputs.digest }}
- name: Cache Docker layers
uses: actions/cache@v3
uses: actions/cache@v2
with:
path: /tmp/.buildx-cache
key: ${{ runner.os }}-buildx-${{ github.sha }}

View File

@@ -24,22 +24,22 @@ jobs:
test-container-build:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Set up Python 3.11
uses: actions/setup-python@v4
- uses: actions/checkout@v2
- name: Set up Python 3.9
uses: actions/setup-python@v2
with:
python-version: 3.11
python-version: 3.9
# Just test that the build works, some libraries won't compile on ARM/rPi etc
- name: Set up QEMU
uses: docker/setup-qemu-action@v3
uses: docker/setup-qemu-action@v1
with:
image: tonistiigi/binfmt:latest
platforms: all
- name: Set up Docker Buildx
id: buildx
uses: docker/setup-buildx-action@v3
uses: docker/setup-buildx-action@v1
with:
install: true
version: latest
@@ -49,7 +49,7 @@ jobs:
# Check we can still build under alpine/musl
- name: Test that the docker containers can build (musl via alpine check)
id: docker_build_musl
uses: docker/build-push-action@v5
uses: docker/build-push-action@v2
with:
context: ./
file: ./.github/test/Dockerfile-alpine
@@ -57,7 +57,7 @@ jobs:
- name: Test that the docker containers can build
id: docker_build
uses: docker/build-push-action@v5
uses: docker/build-push-action@v2
# https://github.com/docker/build-push-action#customizing
with:
context: ./

View File

@@ -7,13 +7,13 @@ jobs:
test-application:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/checkout@v2
# Mainly just for link/flake8
- name: Set up Python 3.11
uses: actions/setup-python@v4
- name: Set up Python 3.10
uses: actions/setup-python@v2
with:
python-version: '3.11'
python-version: '3.10'
- name: Lint with flake8
run: |
@@ -83,7 +83,6 @@ jobs:
run: |
cd changedetectionio
./run_proxy_tests.sh
# And again with PLAYWRIGHT_DRIVER_URL=..
cd ..
- name: Test changedetection.io container starts+runs basically without error
@@ -99,4 +98,4 @@ jobs:
#export WEBDRIVER_URL=http://localhost:4444/wd/hub
#pytest tests/fetchers/test_content.py
#pytest tests/test_errorhandling.py
#pytest tests/test_errorhandling.py

View File

@@ -11,12 +11,12 @@ jobs:
test-pip-build-basics:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/checkout@v2
- name: Set up Python 3.11
uses: actions/setup-python@v4
- name: Set up Python 3.9
uses: actions/setup-python@v2
with:
python-version: 3.11
python-version: 3.9
- name: Test that the basic pip built package runs without error

View File

@@ -1,5 +1,5 @@
# pip dependencies install stage
FROM python:3.11-slim-bullseye as builder
FROM python:3.10-slim-bullseye as builder
# See `cryptography` pin comment in requirements.txt
ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
@@ -29,7 +29,7 @@ RUN pip install --target=/dependencies playwright~=1.27.1 \
|| echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
# Final image stage
FROM python:3.11-slim-bullseye
FROM python:3.10-slim-bullseye
RUN apt-get update && apt-get install -y --no-install-recommends \
libssl1.1 \

View File

@@ -2,44 +2,19 @@
Live your data-life pro-actively, track website content changes and receive notifications via Discord, Email, Slack, Telegram and 70+ more
[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring, list of websites with changes" title="Self-hosted web page change monitoring, list of websites with changes" />](https://changedetection.io)
[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring" title="Self-hosted web page change monitoring" />](https://changedetection.io)
[**Don't have time? Let us host it for you! try our extremely affordable subscription use our proxies and support!**](https://changedetection.io)
### Target specific parts of the webpage using the Visual Selector tool.
Available when connected to a <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Playwright-content-fetcher">playwright content fetcher</a> (included as part of our subscription service)
[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/visualselector-anim.gif" style="max-width:100%;" alt="Select parts and elements of a web page to monitor for changes" title="Select parts and elements of a web page to monitor for changes" />](https://changedetection.io?src=pip)
### Easily see what changed, examine by word, line, or individual character.
[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot-diff.png" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference " title="Self-hosted web page change monitoring context difference " />](https://changedetection.io?src=pip)
### Perform interactive browser steps
Fill in text boxes, click buttons and more, setup your changedetection scenario.
Using the **Browser Steps** configuration, add basic steps before performing change detection, such as logging into websites, adding a product to a cart, accept cookie logins, entering dates and refining searches.
[<img src="docs/browsersteps-anim.gif" style="max-width:100%;" alt="Website change detection with interactive browser steps, detect changes behind login and password, search queries and more" title="Website change detection with interactive browser steps, detect changes behind login and password, search queries and more" />](https://changedetection.io?src=pip)
After **Browser Steps** have been run, then visit the **Visual Selector** tab to refine the content you're interested in.
Requires Playwright to be enabled.
### Example use cases
#### Example use cases
- Products and services have a change in pricing
- _Out of stock notification_ and _Back In stock notification_
- Monitor and track PDF file changes, know when a PDF file has text changes.
- Governmental department updates (changes are often only on their websites)
- New software releases, security advisories when you're not on their mailing list.
- Festivals with changes
- Discogs restock alerts and monitoring
- Realestate listing changes
- Know when your favourite whiskey is on sale, or other special deals are announced before anyone else
- COVID related news from government websites
@@ -52,34 +27,18 @@ Requires Playwright to be enabled.
- Create RSS feeds based on changes in web content
- Monitor HTML source code for unexpected changes, strengthen your PCI compliance
- You have a very sensitive list of URLs to watch and you do _not_ want to use the paid alternatives. (Remember, _you_ are the product)
- Get notified when certain keywords appear in Twitter search results
- Proactively search for jobs, get notified when companies update their careers page, search job portals for keywords.
- Get alerts when new job positions are open on Bamboo HR and other job platforms
- Website defacement monitoring
- Pokémon Card Restock Tracker / Pokémon TCG Tracker
- RegTech - stay ahead of regulatory changes, regulatory compliance
_Need an actual Chrome runner with Javascript support? We support fetching via WebDriver and Playwright!</a>_
#### Key Features
- Lots of trigger filters, such as "Trigger on text", "Remove text by selector", "Ignore text", "Extract text", also using regular-expressions!
- Target elements with xPath(1.0) and CSS Selectors, Easily monitor complex JSON with JSONPath or jq
- Target elements with xPath and CSS Selectors, Easily monitor complex JSON with JSONPath or jq
- Switch between fast non-JS and Chrome JS based "fetchers"
- Track changes in PDF files (Monitor text changed in the PDF, Also monitor PDF filesize and checksums)
- Easily specify how often a site should be checked
- Execute JS before extracting text (Good for logging in, see examples in the UI!)
- Override Request Headers, Specify `POST` or `GET` and other methods
- Use the "Visual Selector" to help target specific elements
- Configurable [proxy per watch](https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration)
- Send a screenshot with the notification when a change is detected in the web page
We [recommend and use Bright Data](https://brightdata.grsm.io/n0r16zf7eivq) global proxy services, Bright Data will match any first deposit up to $100 using our signup link.
[Oxylabs](https://oxylabs.go2cloud.org/SH2d) is also an excellent proxy provider and well worth using, they offer Residental, ISP, Rotating and many other proxy types to suit your project.
Please :star: star :star: this project and help it grow! https://github.com/dgtlmoon/changedetection.io/
```bash

View File

@@ -5,7 +5,7 @@
_Live your data-life pro-actively._
[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web site page change monitoring" title="Self-hosted web site page change monitoring" />](https://changedetection.io?src=github)
[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/screenshot.png" style="max-width:100%;" alt="Self-hosted web page change monitoring" title="Self-hosted web page change monitoring" />](https://changedetection.io?src=github)
[![Release Version][release-shield]][release-link] [![Docker Pulls][docker-pulls]][docker-link] [![License][license-shield]](LICENSE.md)
@@ -22,7 +22,7 @@ _Live your data-life pro-actively._
Available when connected to a <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Playwright-content-fetcher">playwright content fetcher</a> (included as part of our subscription service)
[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/visualselector-anim.gif" style="max-width:100%;" alt="Select parts and elements of a web page to monitor for changes" title="Select parts and elements of a web page to monitor for changes" />](https://changedetection.io?src=github)
[<img src="https://raw.githubusercontent.com/dgtlmoon/changedetection.io/master/docs/visualselector-anim.gif" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference " title="Self-hosted web page change monitoring context difference " />](https://changedetection.io?src=github)
### Easily see what changed, examine by word, line, or individual character.
@@ -35,7 +35,7 @@ Fill in text boxes, click buttons and more, setup your changedetection scenario.
Using the **Browser Steps** configuration, add basic steps before performing change detection, such as logging into websites, adding a product to a cart, accept cookie logins, entering dates and refining searches.
[<img src="docs/browsersteps-anim.gif" style="max-width:100%;" alt="Website change detection with interactive browser steps, detect changes behind login and password, search queries and more" title="Website change detection with interactive browser steps, detect changes behind login and password, search queries and more" />](https://changedetection.io?src=github)
[<img src="docs/browsersteps-anim.gif" style="max-width:100%;" alt="Self-hosted web page change monitoring context difference " title="Website change detection with interactive browser steps, login, cookies etc" />](https://changedetection.io?src=github)
After **Browser Steps** have been run, then visit the **Visual Selector** tab to refine the content you're interested in.
Requires Playwright to be enabled.
@@ -226,7 +226,7 @@ The application also supports notifying you that it can follow this information
## Proxy Configuration
See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration , we also support using [Bright Data proxy services where possible](https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support) and [Oxylabs](https://oxylabs.go2cloud.org/SH2d) proxy services.
See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration , we also support using [Bright Data proxy services where possible]( https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support)
## Raspberry Pi support?

View File

@@ -38,7 +38,7 @@ from flask_paginate import Pagination, get_page_parameter
from changedetectionio import html_tools
from changedetectionio.api import api_v1
__version__ = '0.45.3'
__version__ = '0.45.2'
from changedetectionio.store import BASE_URL_NOT_SET_TEXT
@@ -186,6 +186,7 @@ class User(flask_login.UserMixin):
pass
def login_optionally_required(func):
@wraps(func)
def decorated_view(*args, **kwargs):
@@ -198,6 +199,7 @@ def login_optionally_required(func):
# Permitted
elif request.endpoint == 'diff_history_page' and datastore.data['settings']['application'].get('shared_diff_access'):
return func(*args, **kwargs)
elif request.method in flask_login.config.EXEMPT_METHODS:
return func(*args, **kwargs)
elif app.config.get('LOGIN_DISABLED'):
@@ -416,14 +418,8 @@ def changedetection_app(config=None, datastore_o=None):
# Sort by last_changed and add the uuid which is usually the key..
sorted_watches = []
with_errors = request.args.get('with_errors') == "1"
errored_count = 0
search_q = request.args.get('q').strip().lower() if request.args.get('q') else False
for uuid, watch in datastore.data['watching'].items():
if with_errors and not watch.get('last_error'):
continue
if watch.get('last_error'):
errored_count += 1
if limit_tag and not limit_tag in watch['tags']:
continue
@@ -448,7 +444,6 @@ def changedetection_app(config=None, datastore_o=None):
active_tag=limit_tag,
app_rss_token=datastore.data['settings']['application']['rss_access_token'],
datastore=datastore,
errored_count=errored_count,
form=form,
guid=datastore.data['app_guid'],
has_proxies=datastore.proxy_list,
@@ -629,6 +624,7 @@ def changedetection_app(config=None, datastore_o=None):
if request.args.get('unpause_on_save'):
extra_update_obj['paused'] = False
# Re #110, if they submit the same as the default value, set it to None, so we continue to follow the default
# Assume we use the default value, unless something relevant is different, then use the form value
# values could be None, 0 etc.
@@ -714,11 +710,11 @@ def changedetection_app(config=None, datastore_o=None):
# Only works reliably with Playwright
visualselector_enabled = os.getenv('PLAYWRIGHT_DRIVER_URL', False) and is_html_webdriver
output = render_template("edit.html",
available_processors=processors.available_processors(),
browser_steps_config=browser_step_ui_config,
emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
extra_title=f" - Edit - {watch.label}",
form=form,
has_default_notification_urls=True if len(datastore.data['settings']['application']['notification_urls']) else False,
has_empty_checktime=using_default_check_time,
@@ -862,10 +858,7 @@ def changedetection_app(config=None, datastore_o=None):
def mark_all_viewed():
# Save the current newest history as the most recently viewed
with_errors = request.args.get('with_errors') == "1"
for watch_uuid, watch in datastore.data['watching'].items():
if with_errors and not watch.get('last_error'):
continue
datastore.set_last_viewed(watch_uuid, int(time.time()))
return redirect(url_for('index'))
@@ -921,29 +914,21 @@ def changedetection_app(config=None, datastore_o=None):
# Read as binary and force decode as UTF-8
# Windows may fail decode in python if we just use 'r' mode (chardet decode exception)
from_version = request.args.get('from_version')
from_version_index = -2 # second newest
if from_version and from_version in dates:
from_version_index = dates.index(from_version)
else:
from_version = dates[from_version_index]
try:
newest_version_file_contents = watch.get_history_snapshot(dates[-1])
except Exception as e:
newest_version_file_contents = "Unable to read {}.\n".format(dates[-1])
previous_version = request.args.get('previous_version')
previous_timestamp = dates[-2]
if previous_version:
previous_timestamp = previous_version
try:
from_version_file_contents = watch.get_history_snapshot(dates[from_version_index])
previous_version_file_contents = watch.get_history_snapshot(previous_timestamp)
except Exception as e:
from_version_file_contents = "Unable to read to-version at index{}.\n".format(dates[from_version_index])
previous_version_file_contents = "Unable to read {}.\n".format(previous_timestamp)
to_version = request.args.get('to_version')
to_version_index = -1
if to_version and to_version in dates:
to_version_index = dates.index(to_version)
else:
to_version = dates[to_version_index]
try:
to_version_file_contents = watch.get_history_snapshot(dates[to_version_index])
except Exception as e:
to_version_file_contents = "Unable to read to-version at index{}.\n".format(dates[to_version_index])
screenshot_url = watch.get_screenshot()
@@ -959,24 +944,22 @@ def changedetection_app(config=None, datastore_o=None):
output = render_template("diff.html",
current_diff_url=watch['url'],
from_version=str(from_version),
to_version=str(to_version),
current_previous_version=str(previous_version),
extra_stylesheets=extra_stylesheets,
extra_title=f" - Diff - {watch.label}",
extra_title=" - Diff - {}".format(watch['title'] if watch['title'] else watch['url']),
extract_form=extract_form,
is_html_webdriver=is_html_webdriver,
last_error=watch['last_error'],
last_error_screenshot=watch.get_error_snapshot(),
last_error_text=watch.get_error_text(),
left_sticky=True,
newest=to_version_file_contents,
newest=newest_version_file_contents,
newest_version_timestamp=dates[-1],
password_enabled_and_share_is_off=password_enabled_and_share_is_off,
from_version_file_contents=from_version_file_contents,
to_version_file_contents=to_version_file_contents,
previous=previous_version_file_contents,
screenshot=screenshot_url,
uuid=uuid,
versions=dates, # All except current/last
versions=dates[:-1], # All except current/last
watch_a=watch
)
@@ -1274,8 +1257,6 @@ def changedetection_app(config=None, datastore_o=None):
# Forced recheck will skip the 'skip if content is the same' rule (, 'reprocess_existing_data': True})))
tag = request.args.get('tag')
uuid = request.args.get('uuid')
with_errors = request.args.get('with_errors') == "1"
i = 0
running_uuids = []
@@ -1291,8 +1272,6 @@ def changedetection_app(config=None, datastore_o=None):
# Items that have this current tag
for watch_uuid, watch in datastore.data['watching'].items():
if tag in watch.get('tags', {}):
if with_errors and not watch.get('last_error'):
continue
if watch_uuid not in running_uuids and not datastore.data['watching'][watch_uuid]['paused']:
update_q.put(
queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False})
@@ -1303,11 +1282,8 @@ def changedetection_app(config=None, datastore_o=None):
# No tag, no uuid, add everything.
for watch_uuid, watch in datastore.data['watching'].items():
if watch_uuid not in running_uuids and not datastore.data['watching'][watch_uuid]['paused']:
if with_errors and not watch.get('last_error'):
continue
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False}))
i += 1
flash("{} watches queued for rechecking.".format(i))
return redirect(url_for('index', tag=tag))
@@ -1455,7 +1431,6 @@ def changedetection_app(config=None, datastore_o=None):
return redirect(url_for('index'))
@app.route("/highlight_submit_ignore_url", methods=['POST'])
@login_optionally_required
def highlight_submit_ignore_url():
import re
mode = request.form.get('mode')

View File

@@ -23,10 +23,8 @@
from distutils.util import strtobool
from flask import Blueprint, request, make_response
import logging
import os
import re
import logging
from changedetectionio.store import ChangeDetectionStore
from changedetectionio import login_optionally_required
@@ -46,7 +44,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
# We keep the playwright session open for many minutes
keepalive_seconds = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
seconds_keepalive = int(os.getenv('BROWSERSTEPS_MINUTES_KEEPALIVE', 10)) * 60
browsersteps_start_session = {'start_time': time.time()}
@@ -58,18 +56,16 @@ def construct_blueprint(datastore: ChangeDetectionStore):
# Start the Playwright context, which is actually a nodejs sub-process and communicates over STDIN/STDOUT pipes
io_interface_context = io_interface_context.start()
keepalive_ms = ((keepalive_seconds + 3) * 1000)
base_url = os.getenv('PLAYWRIGHT_DRIVER_URL', '')
a = "?" if not '?' in base_url else '&'
base_url += a + f"timeout={keepalive_ms}"
# keep it alive for 10 seconds more than we advertise, sometimes it helps to keep it shutting down cleanly
keepalive = "&timeout={}".format(((seconds_keepalive + 3) * 1000))
try:
browsersteps_start_session['browser'] = io_interface_context.chromium.connect_over_cdp(base_url)
browsersteps_start_session['browser'] = io_interface_context.chromium.connect_over_cdp(
os.getenv('PLAYWRIGHT_DRIVER_URL', '') + keepalive)
except Exception as e:
if 'ECONNREFUSED' in str(e):
return make_response('Unable to start the Playwright Browser session, is it running?', 401)
else:
# Other errors, bad URL syntax, bad reply etc
return make_response(str(e), 401)
proxy_id = datastore.get_preferred_proxy_for_watch(uuid=watch_uuid)
@@ -122,31 +118,6 @@ def construct_blueprint(datastore: ChangeDetectionStore):
print("Starting connection with playwright - done")
return {'browsersteps_session_id': browsersteps_session_id}
@login_optionally_required
@browser_steps_blueprint.route("/browsersteps_image", methods=['GET'])
def browser_steps_fetch_screenshot_image():
from flask import (
make_response,
request,
send_from_directory,
)
uuid = request.args.get('uuid')
step_n = int(request.args.get('step_n'))
watch = datastore.data['watching'].get(uuid)
filename = f"step_before-{step_n}.jpeg" if request.args.get('type', '') == 'before' else f"step_{step_n}.jpeg"
if step_n and watch and os.path.isfile(os.path.join(watch.watch_data_dir, filename)):
response = make_response(send_from_directory(directory=watch.watch_data_dir, path=filename))
response.headers['Content-type'] = 'image/jpeg'
response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
response.headers['Pragma'] = 'no-cache'
response.headers['Expires'] = 0
return response
else:
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
@login_optionally_required
@browser_steps_blueprint.route("/browsersteps_update", methods=['POST'])

View File

@@ -138,13 +138,13 @@ class steppable_browser_interface():
def action_wait_for_text(self, selector, value):
import json
v = json.dumps(value)
self.page.wait_for_function(f'document.querySelector("body").innerText.includes({v});', timeout=30000)
self.page.wait_for_function(f'document.querySelector("body").innerText.includes({v});', timeout=90000)
def action_wait_for_text_in_element(self, selector, value):
import json
s = json.dumps(selector)
v = json.dumps(value)
self.page.wait_for_function(f'document.querySelector({s}).innerText.includes({v});', timeout=30000)
self.page.wait_for_function(f'document.querySelector({s}).innerText.includes({v});', timeout=90000)
# @todo - in the future make some popout interface to capture what needs to be set
# https://playwright.dev/python/docs/api/class-keyboard

View File

@@ -57,11 +57,9 @@ def construct_blueprint(datastore: ChangeDetectionStore):
status.update({'status': 'ERROR OTHER', 'length': len(contents), 'text': f"Got empty reply with code {e.status_code} - Access denied"})
else:
status.update({'status': 'ERROR OTHER', 'length': len(contents) if contents else 0, 'text': f"Empty reply with code {e.status_code}, needs chrome?"})
except content_fetcher.ReplyWithContentButNoText as e:
txt = f"Got reply but with no content - Status code {e.status_code} - It's possible that the filters were found, but contained no usable text (or contained only an image)."
status.update({'status': 'ERROR', 'text': txt})
except Exception as e:
status.update({'status': 'ERROR OTHER', 'length': len(contents) if contents else 0, 'text': 'Error: '+type(e).__name__+str(e)})
status.update({'status': 'ERROR OTHER', 'length': len(contents) if contents else 0, 'text': 'Error: '+str(e)})
else:
status.update({'status': 'OK', 'length': len(contents), 'text': ''})

View File

@@ -1,15 +1,12 @@
from abc import abstractmethod
from distutils.util import strtobool
from urllib.parse import urlparse
import chardet
import hashlib
from abc import abstractmethod
import chardet
import json
import logging
import os
import requests
import sys
import time
import urllib.parse
visualselector_xpath_selectors = 'div,span,form,table,tbody,tr,td,a,p,ul,li,h1,h2,h3,h4, header, footer, section, article, aside, details, main, nav, section, summary'
@@ -269,6 +266,7 @@ class base_html_playwright(Fetcher):
if self.proxy:
# Playwright needs separate username and password values
from urllib.parse import urlparse
parsed = urlparse(self.proxy.get('server'))
if parsed.username:
self.proxy['username'] = parsed.username
@@ -323,13 +321,14 @@ class base_html_playwright(Fetcher):
# Append proxy connect string
if self.proxy:
import urllib.parse
# Remove username/password if it exists in the URL or you will receive "ERR_NO_SUPPORTED_PROXIES" error
# Actual authentication handled by Puppeteer/node
o = urlparse(self.proxy.get('server'))
# Remove scheme, socks5:// doesnt always work and it will autodetect anyway
proxy_url = urllib.parse.quote(o._replace(netloc="{}:{}".format(o.hostname, o.port)).geturl().replace(f"{o.scheme}://", '', 1))
proxy_url = urllib.parse.quote(o._replace(netloc="{}:{}".format(o.hostname, o.port)).geturl())
browserless_function_url = f"{browserless_function_url}&--proxy-server={proxy_url}&dumpio=true"
try:
amp = '&' if '?' in browserless_function_url else '?'
response = requests.request(
@@ -348,7 +347,7 @@ class base_html_playwright(Fetcher):
'url': url,
'user_agent': {k.lower(): v for k, v in request_headers.items()}.get('user-agent', None),
'proxy_username': self.proxy.get('username', '') if self.proxy else False,
'proxy_password': self.proxy.get('password', '') if self.proxy and self.proxy.get('username') else False,
'proxy_password': self.proxy.get('password', '') if self.proxy else False,
'no_cache_list': [
'twitter',
'.pdf'
@@ -417,8 +416,8 @@ class base_html_playwright(Fetcher):
lambda s: (s['operation'] and len(s['operation']) and s['operation'] != 'Choose one' and s['operation'] != 'Goto site'),
self.browser_steps))
if not has_browser_steps and os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH'):
if strtobool(os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH')):
if not has_browser_steps:
if os.getenv('USE_EXPERIMENTAL_PUPPETEER_FETCH'):
# Temporary backup solution until we rewrite the playwright code
return self.run_fetch_browserless_puppeteer(
url,
@@ -435,7 +434,6 @@ class base_html_playwright(Fetcher):
self.delete_browser_steps_screenshots()
response = None
with sync_playwright() as p:
browser_type = getattr(p, self.browser_type)
@@ -444,9 +442,6 @@ class base_html_playwright(Fetcher):
# 60,000 connection timeout only
browser = browser_type.connect_over_cdp(self.command_executor, timeout=60000)
# SOCKS5 with authentication is not supported (yet)
# https://github.com/microsoft/playwright/issues/10567
# Set user agent to prevent Cloudflare from blocking the browser
# Use the default one configured in the App.py model that's passed from fetch_site_status.py
context = browser.new_context(
@@ -483,6 +478,7 @@ class base_html_playwright(Fetcher):
print("Content Fetcher > retrying request got error - ", str(e))
time.sleep(1)
response = self.page.goto(url, wait_until='commit')
except Exception as e:
print("Content Fetcher > Other exception when page.goto", str(e))
context.close()
@@ -618,6 +614,7 @@ class base_html_webdriver(Fetcher):
from selenium.common.exceptions import WebDriverException
# request_body, request_method unused for now, until some magic in the future happens.
# check env for WEBDRIVER_URL
self.driver = webdriver.Remote(
command_executor=self.command_executor,
desired_capabilities=DesiredCapabilities.CHROME,
@@ -696,10 +693,6 @@ class html_requests(Fetcher):
proxies = {}
# Allows override the proxy on a per-request basis
# https://requests.readthedocs.io/en/latest/user/advanced/#socks
# Should also work with `socks5://user:pass@host:port` type syntax.
if self.proxy_override:
proxies = {'http': self.proxy_override, 'https': self.proxy_override, 'ftp': self.proxy_override}
else:

View File

@@ -481,7 +481,7 @@ class SingleExtraProxy(Form):
# maybe better to set some <script>var..
proxy_name = StringField('Name', [validators.Optional()], render_kw={"placeholder": "Name"})
proxy_url = StringField('Proxy URL', [validators.Optional()], render_kw={"placeholder": "socks5:// or regular proxy http://user:pass@...:3128", "size":50})
proxy_url = StringField('Proxy URL', [validators.Optional()], render_kw={"placeholder": "http://user:pass@...:3128", "size":50})
# @todo do the validation here instead
# datastore.data['settings']['requests']..

View File

@@ -1,44 +1,23 @@
from bs4 import BeautifulSoup
from inscriptis import get_text
from inscriptis.model.config import ParserConfig
from jsonpath_ng.ext import parse
from typing import List
from inscriptis.css_profiles import CSS_PROFILES, HtmlElement
from inscriptis.html_properties import Display
from inscriptis.model.config import ParserConfig
from xml.sax.saxutils import escape as xml_escape
import json
import re
# HTML added to be sure each result matching a filter (.example) gets converted to a new line by Inscriptis
TEXT_FILTER_LIST_LINE_SUFFIX = "<br>"
PERL_STYLE_REGEX = r'^/(.*?)/([a-z]*)?$'
# 'price' , 'lowPrice', 'highPrice' are usually under here
# All of those may or may not appear on different websites - I didnt find a way todo case-insensitive searching here
LD_JSON_PRODUCT_OFFER_SELECTORS = ["json:$..offers", "json:$..Offers"]
# all of those may or may not appear on different websites
LD_JSON_PRODUCT_OFFER_SELECTOR = "json:$..offers"
class JSONNotFound(ValueError):
def __init__(self, msg):
ValueError.__init__(self, msg)
# Doesn't look like python supports forward slash auto enclosure in re.findall
# So convert it to inline flag "(?i)foobar" type configuration
def perl_style_slash_enclosed_regex_to_options(regex):
res = re.search(PERL_STYLE_REGEX, regex, re.IGNORECASE)
if res:
flags = res.group(2) if res.group(2) else 'i'
regex = f"(?{flags}){res.group(1)}"
else:
# Fall back to just ignorecase as an option
regex = f"(?i){regex}"
return regex
# Given a CSS Rule, and a blob of HTML, return the blob of HTML that matches
def include_filters(include_filters, html_content, append_pretty_line_formatting=False):
soup = BeautifulSoup(html_content, "html.parser")
@@ -71,15 +50,10 @@ def element_removal(selectors: List[str], html_content):
# Return str Utf-8 of matched rules
def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False, is_rss=False):
def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False):
from lxml import etree, html
parser = None
if is_rss:
# So that we can keep CDATA for cdata_in_document_to_text() to process
parser = etree.XMLParser(strip_cdata=False)
tree = html.fromstring(bytes(html_content, encoding='utf-8'), parser=parser)
tree = html.fromstring(bytes(html_content, encoding='utf-8'))
html_block = ""
r = tree.xpath(xpath_filter.strip(), namespaces={'re': 'http://exslt.org/regular-expressions'})
@@ -102,6 +76,7 @@ def xpath_filter(xpath_filter, html_content, append_pretty_line_formatting=False
return html_block
# Extract/find element
def extract_element(find='title', html_content=''):
@@ -169,6 +144,7 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
# Foreach <script json></script> blob.. just return the first that matches json_filter
# As a last resort, try to parse the whole <body>
s = []
soup = BeautifulSoup(content, 'html.parser')
if ensure_is_ldjson_info_type:
@@ -194,24 +170,13 @@ def extract_json_as_string(content, json_filter, ensure_is_ldjson_info_type=None
for json_data in bs_jsons:
stripped_text_from_html = _parse_json(json_data, json_filter)
if ensure_is_ldjson_info_type:
# Could sometimes be list, string or something else random
if isinstance(json_data, dict):
# If it has LD JSON 'key' @type, and @type is 'product', and something was found for the search
# (Some sites have multiple of the same ld+json @type='product', but some have the review part, some have the 'price' part)
# @type could also be a list (Product, SubType)
# LD_JSON auto-extract also requires some content PLUS the ldjson to be present
# 1833 - could be either str or dict, should not be anything else
if json_data.get('@type') and stripped_text_from_html:
try:
if json_data.get('@type') == str or json_data.get('@type') == dict:
types = [json_data.get('@type')] if isinstance(json_data.get('@type'), str) else json_data.get('@type')
if ensure_is_ldjson_info_type.lower() in [x.lower().strip() for x in types]:
break
except:
continue
if json_data.get('@type', False) and json_data.get('@type','').lower() == ensure_is_ldjson_info_type.lower() and stripped_text_from_html:
break
elif stripped_text_from_html:
break
@@ -230,14 +195,23 @@ def strip_ignore_text(content, wordlist, mode="content"):
output = []
ignore_text = []
ignore_regex = []
ignored_line_numbers = []
for k in wordlist:
# Is it a regex?
res = re.search(PERL_STYLE_REGEX, k, re.IGNORECASE)
if res:
ignore_regex.append(re.compile(perl_style_slash_enclosed_regex_to_options(k)))
x = re.search('^\/(.*)\/(.*)', k.strip())
if x:
# Starts with / but doesn't look like a regex
p = x.group(1)
try:
# @Todo python regex options can go before the regex str, but not really many of the options apply on a per-line basis
ignore_regex.append(re.compile(rf"{p}", re.IGNORECASE))
except Exception as e:
# Badly formed regex, treat as text
ignore_text.append(k.strip())
else:
# Had a / but doesn't work as regex
ignore_text.append(k.strip())
for line in content.splitlines():
@@ -267,15 +241,8 @@ def strip_ignore_text(content, wordlist, mode="content"):
return "\n".encode('utf8').join(output)
def cdata_in_document_to_text(html_content: str, render_anchor_tag_content=False) -> str:
pattern = '<!\[CDATA\[(\s*(?:.(?<!\]\]>)\s*)*)\]\]>'
def repl(m):
text = m.group(1)
return xml_escape(html_to_text(html_content=text)).strip()
return re.sub(pattern, repl, html_content)
def html_to_text(html_content: str, render_anchor_tag_content=False, is_rss=False) -> str:
def html_to_text(html_content: str, render_anchor_tag_content=False) -> str:
"""Converts html string to a string with just the text. If ignoring
rendering anchor tag content is enable, anchor tag content are also
included in the text
@@ -291,21 +258,16 @@ def html_to_text(html_content: str, render_anchor_tag_content=False, is_rss=Fals
# if anchor tag content flag is set to True define a config for
# extracting this content
if render_anchor_tag_content:
parser_config = ParserConfig(
annotation_rules={"a": ["hyperlink"]},
display_links=True
annotation_rules={"a": ["hyperlink"]}, display_links=True
)
# otherwise set config to None/default
# otherwise set config to None
else:
parser_config = None
# RSS Mode - Inscriptis will treat `title` as something else.
# Make it as a regular block display element (//item/title)
# This is a bit of a hack - the real way it to use XSLT to convert it to HTML #1874
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)
# get text and annotations via inscriptis
text_content = get_text(html_content, config=parser_config)
return text_content
@@ -313,18 +275,9 @@ def html_to_text(html_content: str, render_anchor_tag_content=False, is_rss=Fals
# Does LD+JSON exist with a @type=='product' and a .price set anywhere?
def has_ldjson_product_info(content):
pricing_data = ''
try:
if not 'application/ld+json' in content:
return False
for filter in LD_JSON_PRODUCT_OFFER_SELECTORS:
pricing_data += extract_json_as_string(content=content,
json_filter=filter,
ensure_is_ldjson_info_type="product")
except Exception as e:
pricing_data = extract_json_as_string(content=content, json_filter=LD_JSON_PRODUCT_OFFER_SELECTOR, ensure_is_ldjson_info_type="product")
except JSONNotFound as e:
# Totally fine
return False
x=bool(pricing_data)

View File

@@ -4,7 +4,6 @@ import os
import re
import time
import uuid
from pathlib import Path
# Allowable protocols, protects against javascript: etc
# file:// is further checked by ALLOW_FILE_URI
@@ -19,7 +18,6 @@ from changedetectionio.notification import (
base_config = {
'body': None,
'browser_steps_last_error_step': None,
'check_unique_lines': False, # On change-detected, compare against all history if its something new
'check_count': 0,
'date_created': None,
@@ -27,7 +25,6 @@ base_config = {
'extract_text': [], # Extract text by regex after filters
'extract_title_as_title': False,
'fetch_backend': 'system', # plaintext, playwright etc
'fetch_time': 0.0,
'processor': 'text_json_diff', # could be restock_diff or others from .processors
'filter_failure_notification_send': strtobool(os.getenv('FILTER_FAILURE_NOTIFICATION_SEND_DEFAULT', 'True')),
'filter_text_added': True,
@@ -170,7 +167,9 @@ class model(dict):
@property
def label(self):
# Used for sorting
return self.get('title') if self.get('title') else self.get('url')
if self['title']:
return self['title']
return self['url']
@property
def last_changed(self):
@@ -492,13 +491,3 @@ class model(dict):
filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
with open(filepath, 'wb') as f:
f.write(brotli.compress(contents, mode=brotli.MODE_TEXT))
@property
def get_browsersteps_available_screenshots(self):
"For knowing which screenshots are available to show the user in BrowserSteps UI"
available = []
for f in Path(self.watch_data_dir).glob('step_before-*.jpeg'):
step_n=re.search(r'step_before-(\d+)', f.name)
if step_n:
available.append(step_n.group(1))
return available

View File

@@ -11,19 +11,17 @@ from changedetectionio import content_fetcher, html_tools
from changedetectionio.blueprint.price_data_follower import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
from copy import deepcopy
from . import difference_detection_processor
from ..html_tools import PERL_STYLE_REGEX, cdata_in_document_to_text
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
name = 'Webpage Text/HTML, JSON and PDF changes'
name = 'Webpage Text/HTML, JSON and PDF changes'
description = 'Detects all text changes where possible'
json_filter_prefixes = ['json:', 'jq:']
class FilterNotFoundInResponse(ValueError):
def __init__(self, msg):
ValueError.__init__(self, msg)
class PDFToHTMLToolNotFound(ValueError):
def __init__(self, msg):
ValueError.__init__(self, msg)
@@ -39,6 +37,19 @@ class perform_site_check(difference_detection_processor):
super().__init__(*args, **kwargs)
self.datastore = datastore
# Doesn't look like python supports forward slash auto enclosure in re.findall
# So convert it to inline flag "foobar(?i)" type configuration
def forward_slash_enclosed_regex_to_options(self, regex):
res = re.search(r'^/(.*?)/(\w+)$', regex, re.IGNORECASE)
if res:
regex = res.group(1)
regex += '(?{})'.format(res.group(2))
else:
regex += '(?{})'.format('i')
return regex
def run(self, uuid, skip_when_checksum_same=True, preferred_proxy=None):
changed_detected = False
screenshot = False # as bytes
@@ -124,8 +135,7 @@ class perform_site_check(difference_detection_processor):
# requests for PDF's, images etc should be passwd the is_binary flag
is_binary = watch.is_pdf
fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch.get('include_filters'),
is_binary=is_binary)
fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_codes, watch.get('include_filters'), is_binary=is_binary)
fetcher.quit()
self.screenshot = fetcher.screenshot
@@ -141,6 +151,7 @@ class perform_site_check(difference_detection_processor):
if update_obj['previous_md5_before_filters'] == watch.get('previous_md5_before_filters'):
raise content_fetcher.checksumFromPreviousCheckWasTheSame()
# Fetching complete, now filters
# @todo move to class / maybe inside of fetcher abstract base?
@@ -153,22 +164,13 @@ class perform_site_check(difference_detection_processor):
is_json = 'application/json' in fetcher.get_all_headers().get('content-type', '').lower()
is_html = not is_json
is_rss = False
ctype_header = fetcher.get_all_headers().get('content-type', '').lower()
# Go into RSS preprocess for converting CDATA/comment to usable text
if any(substring in ctype_header for substring in ['application/xml', 'application/rss', 'text/xml']):
if '<rss' in fetcher.content[:100].lower():
fetcher.content = cdata_in_document_to_text(html_content=fetcher.content)
is_rss = True
# source: support, basically treat it as plaintext
if is_source:
is_html = False
is_json = False
inline_pdf = fetcher.get_all_headers().get('content-disposition', '') and '%PDF-1' in fetcher.content[:10]
if watch.is_pdf or 'application/pdf' in fetcher.get_all_headers().get('content-type', '').lower() or inline_pdf:
if watch.is_pdf or 'application/pdf' in fetcher.get_all_headers().get('content-type', '').lower():
from shutil import which
tool = os.getenv("PDF_TO_HTML_TOOL", "pdftohtml")
if not which(tool):
@@ -205,7 +207,7 @@ class perform_site_check(difference_detection_processor):
# Inject a virtual LD+JSON price tracker rule
if watch.get('track_ldjson_price_data', '') == PRICE_DATA_TRACK_ACCEPT:
include_filters_rule += html_tools.LD_JSON_PRODUCT_OFFER_SELECTORS
include_filters_rule.append(html_tools.LD_JSON_PRODUCT_OFFER_SELECTOR)
has_filter_rule = len(include_filters_rule) and len(include_filters_rule[0].strip())
has_subtractive_selectors = len(subtractive_selectors) and len(subtractive_selectors[0].strip())
@@ -223,11 +225,14 @@ class perform_site_check(difference_detection_processor):
pass
if has_filter_rule:
json_filter_prefixes = ['json:', 'jq:']
for filter in include_filters_rule:
if any(prefix in filter for prefix in json_filter_prefixes):
stripped_text_from_html += html_tools.extract_json_as_string(content=fetcher.content, json_filter=filter)
is_html = False
if is_html or is_source:
# CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
@@ -251,8 +256,7 @@ class perform_site_check(difference_detection_processor):
if filter_rule[0] == '/' or filter_rule.startswith('xpath:'):
html_content += html_tools.xpath_filter(xpath_filter=filter_rule.replace('xpath:', ''),
html_content=fetcher.content,
append_pretty_line_formatting=not is_source,
is_rss=is_rss)
append_pretty_line_formatting=not is_source)
else:
# CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
html_content += html_tools.include_filters(include_filters=filter_rule,
@@ -272,14 +276,14 @@ class perform_site_check(difference_detection_processor):
do_anchor = self.datastore.data["settings"]["application"].get("render_anchor_tag_content", False)
stripped_text_from_html = \
html_tools.html_to_text(
html_content=html_content,
render_anchor_tag_content=do_anchor,
is_rss=is_rss # #1874 activate the <title workaround hack
html_content,
render_anchor_tag_content=do_anchor
)
# Re #340 - return the content before the 'ignore text' was applied
text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
# @todo whitespace coming from missing rtrim()?
# stripped_text_from_html could be based on their preferences, replace the processed text with only that which they want to know about.
# Rewrite's the processing text based on only what diff result they want to see
@@ -289,13 +293,13 @@ class perform_site_check(difference_detection_processor):
# needs to not include (added) etc or it may get used twice
# Replace the processed text with the preferred result
rendered_diff = diff.render_diff(previous_version_file_contents=watch.get_last_fetched_before_filters(),
newest_version_file_contents=stripped_text_from_html,
include_equal=False, # not the same lines
include_added=watch.get('filter_text_added', True),
include_removed=watch.get('filter_text_removed', True),
include_replaced=watch.get('filter_text_replaced', True),
line_feed_sep="\n",
include_change_type_prefix=False)
newest_version_file_contents=stripped_text_from_html,
include_equal=False, # not the same lines
include_added=watch.get('filter_text_added', True),
include_removed=watch.get('filter_text_removed', True),
include_replaced=watch.get('filter_text_replaced', True),
line_feed_sep="\n",
include_change_type_prefix=False)
watch.save_last_fetched_before_filters(text_content_before_ignored_filter)
@@ -336,25 +340,16 @@ class perform_site_check(difference_detection_processor):
regex_matched_output = []
for s_re in extract_text:
# incase they specified something in '/.../x'
if re.search(PERL_STYLE_REGEX, s_re, re.IGNORECASE):
regex = html_tools.perl_style_slash_enclosed_regex_to_options(s_re)
result = re.findall(regex.encode('utf-8'), stripped_text_from_html)
regex = self.forward_slash_enclosed_regex_to_options(s_re)
result = re.findall(regex.encode('utf-8'), stripped_text_from_html)
for l in result:
if type(l) is tuple:
# @todo - some formatter option default (between groups)
regex_matched_output += list(l) + [b'\n']
else:
# @todo - some formatter option default (between each ungrouped result)
regex_matched_output += [l] + [b'\n']
else:
# Doesnt look like regex, just hunt for plaintext and return that which matches
# `stripped_text_from_html` will be bytes, so we must encode s_re also to bytes
r = re.compile(re.escape(s_re.encode('utf-8')), re.IGNORECASE)
res = r.findall(stripped_text_from_html)
if res:
for match in res:
regex_matched_output += [match] + [b'\n']
for l in result:
if type(l) is tuple:
# @todo - some formatter option default (between groups)
regex_matched_output += list(l) + [b'\n']
else:
# @todo - some formatter option default (between each ungrouped result)
regex_matched_output += [l] + [b'\n']
# Now we will only show what the regex matched
stripped_text_from_html = b''

View File

@@ -18,7 +18,6 @@ module.exports = async ({page, context}) => {
await page.setBypassCSP(true)
await page.setExtraHTTPHeaders(req_headers);
if (user_agent) {
await page.setUserAgent(user_agent);
}
@@ -27,10 +26,6 @@ module.exports = async ({page, context}) => {
await page.setDefaultNavigationTimeout(0);
if (proxy_username) {
// Setting Proxy-Authentication header is deprecated, and doing so can trigger header change errors from Puppeteer
// https://github.com/puppeteer/puppeteer/issues/676 ?
// https://help.brightdata.com/hc/en-us/articles/12632549957649-Proxy-Manager-How-to-Guides#h_01HAKWR4Q0AFS8RZTNYWRDFJC2
// https://cri.dev/posts/2020-03-30-How-to-solve-Puppeteer-Chrome-Error-ERR_INVALID_ARGUMENT/
await page.authenticate({
username: proxy_username,
password: proxy_password

View File

@@ -5,19 +5,14 @@ function isItemInStock() {
'agotado',
'artikel zurzeit vergriffen',
'as soon as stock is available',
'ausverkauft', // sold out
'available for back order',
'back-order or out of stock',
'backordered',
'benachrichtigt mich', // notify me
'brak na stanie',
'brak w magazynie',
'coming soon',
'currently have any tickets for this',
'currently unavailable',
'dostępne wkrótce',
'en rupture de stock',
'ist derzeit nicht auf lager',
'item is no longer available',
'message if back in stock',
'nachricht bei',
@@ -42,7 +37,6 @@ function isItemInStock() {
'unavailable tickets',
'we do not currently have an estimate of when this product will be back in stock.',
'zur zeit nicht an lager',
'已售完',
];

View File

@@ -10,40 +10,6 @@ set -x
docker run --network changedet-network -d --name squid-one --hostname squid-one --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf ubuntu/squid:4.13-21.10_edge
docker run --network changedet-network -d --name squid-two --hostname squid-two --rm -v `pwd`/tests/proxy_list/squid.conf:/etc/squid/conf.d/debian.conf ubuntu/squid:4.13-21.10_edge
# SOCKS5 related - start simple Socks5 proxy server
# SOCKSTEST=xyz should show in the logs of this service to confirm it fetched
docker run --network changedet-network -d --hostname socks5proxy --name socks5proxy -p 1080:1080 -e PROXY_USER=proxy_user123 -e PROXY_PASSWORD=proxy_pass123 serjs/go-socks5-proxy
docker run --network changedet-network -d --hostname socks5proxy-noauth -p 1081:1080 --name socks5proxy-noauth serjs/go-socks5-proxy
echo "---------------------------------- SOCKS5 -------------------"
# SOCKS5 related - test from proxies.json
docker run --network changedet-network \
-v `pwd`/tests/proxy_socks5/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json \
--rm \
-e "SOCKSTEST=proxiesjson" \
test-changedetectionio \
bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'
# SOCKS5 related - by manually entering in UI
docker run --network changedet-network \
--rm \
-e "SOCKSTEST=manual" \
test-changedetectionio \
bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy.py'
# SOCKS5 related - test from proxies.json via playwright - NOTE- PLAYWRIGHT DOESNT SUPPORT AUTHENTICATING PROXY
docker run --network changedet-network \
-e "SOCKSTEST=manual-playwright" \
-v `pwd`/tests/proxy_socks5/proxies.json-example-noauth:/app/changedetectionio/test-datastore/proxies.json \
-e "PLAYWRIGHT_DRIVER_URL=ws://browserless:3000" \
--rm \
test-changedetectionio \
bash -c 'cd changedetectionio && pytest tests/proxy_socks5/test_socks5_proxy_sources.py'
echo "socks5 server logs"
docker logs socks5proxy
echo "----------------------------------"
# Used for configuring a custom proxy URL via the UI
docker run --network changedet-network -d \
--name squid-custom \

View File

@@ -208,7 +208,7 @@ $(document).ready(function () {
console.log(x);
if (x && first_available.length) {
// @todo will it let you click shit that has a layer ontop? probably not.
if (x['tagtype'] === 'text' || x['tagtype'] === 'number' || x['tagtype'] === 'email' || x['tagName'] === 'textarea' || x['tagtype'] === 'password' || x['tagtype'] === 'search') {
if (x['tagtype'] === 'text' || x['tagtype'] === 'email' || x['tagName'] === 'textarea' || x['tagtype'] === 'password' || x['tagtype'] === 'search') {
$('select', first_available).val('Enter text in field').change();
$('input[type=text]', first_available).first().val(x['xpath']);
$('input[placeholder="Value"]', first_available).addClass('ok').click().focus();
@@ -321,14 +321,8 @@ $(document).ready(function () {
var s = '<div class="control">' + '<a data-step-index=' + i + ' class="pure-button button-secondary button-green button-xsmall apply" >Apply</a>&nbsp;';
if (i > 0) {
// The first step never gets these (Goto-site)
s += `<a data-step-index="${i}" class="pure-button button-secondary button-xsmall clear" >Clear</a>&nbsp;` +
`<a data-step-index="${i}" class="pure-button button-secondary button-red button-xsmall remove" >Remove</a>`;
// if a screenshot is available
if (browser_steps_available_screenshots.includes(i.toString())) {
var d = (browser_steps_last_error_step === i+1) ? 'before' : 'after';
s += `&nbsp;<a data-step-index="${i}" class="pure-button button-secondary button-xsmall show-screenshot" title="Show screenshot from last run" data-type="${d}">Pic</a>&nbsp;`;
}
s += '<a data-step-index=' + i + ' class="pure-button button-secondary button-xsmall clear" >Clear</a>&nbsp;' +
'<a data-step-index=' + i + ' class="pure-button button-secondary button-red button-xsmall remove" >Remove</a>';
}
s += '</div>';
$(this).append(s)
@@ -443,24 +437,6 @@ $(document).ready(function () {
});
$('ul#browser_steps li .control .show-screenshot').click(function (element) {
var step_n = $(event.currentTarget).data('step-index');
w = window.open(this.href, "_blank", "width=640,height=480");
const t = $(event.currentTarget).data('type');
const url = browser_steps_fetch_screenshot_image_url + `&step_n=${step_n}&type=${t}`;
w.document.body.innerHTML = `<!DOCTYPE html>
<html lang="en">
<body>
<img src="${url}" style="width: 100%" alt="Browser Step at step ${step_n} from last run." title="Browser Step at step ${step_n} from last run."/>
</body>
</html>`;
w.document.title = `Browser Step at step ${step_n} from last run.`;
});
if (browser_steps_last_error_step) {
$("ul#browser_steps>li:nth-child("+browser_steps_last_error_step+")").addClass("browser-step-with-error");
}
$("ul#browser_steps select").change(function () {
set_greyed_state();

View File

@@ -1,120 +1,110 @@
$(document).ready(function () {
var a = document.getElementById("a");
var b = document.getElementById("b");
var result = document.getElementById("result");
var inputs;
var a = document.getElementById("a");
var b = document.getElementById("b");
var result = document.getElementById("result");
$('#jump-next-diff').click(function () {
function changed() {
// https://github.com/kpdecker/jsdiff/issues/389
// I would love to use `{ignoreWhitespace: true}` here but it breaks the formatting
options = {
ignoreWhitespace: document.getElementById("ignoreWhitespace").checked,
};
var element = inputs[inputs.current];
var headerOffset = 80;
var elementPosition = element.getBoundingClientRect().top;
var offsetPosition = elementPosition - headerOffset + window.scrollY;
window.scrollTo({
top: offsetPosition,
behavior: "smooth",
});
inputs.current++;
if (inputs.current >= inputs.length) {
inputs.current = 0;
}
});
function changed() {
// https://github.com/kpdecker/jsdiff/issues/389
// I would love to use `{ignoreWhitespace: true}` here but it breaks the formatting
options = {
ignoreWhitespace: document.getElementById("ignoreWhitespace").checked,
};
var diff = Diff[window.diffType](a.textContent, b.textContent, options);
var fragment = document.createDocumentFragment();
for (var i = 0; i < diff.length; i++) {
if (diff[i].added && diff[i + 1] && diff[i + 1].removed) {
var swap = diff[i];
diff[i] = diff[i + 1];
diff[i + 1] = swap;
}
var node;
if (diff[i].removed) {
node = document.createElement("del");
node.classList.add("change");
const wrapper = node.appendChild(document.createElement("span"));
wrapper.appendChild(document.createTextNode(diff[i].value));
} else if (diff[i].added) {
node = document.createElement("ins");
node.classList.add("change");
const wrapper = node.appendChild(document.createElement("span"));
wrapper.appendChild(document.createTextNode(diff[i].value));
} else {
node = document.createTextNode(diff[i].value);
}
fragment.appendChild(node);
}
result.textContent = "";
result.appendChild(fragment);
// For nice mouse-over hover/title information
const removed_current_option = $('#diff-version option:selected')
if (removed_current_option) {
$('del').each(function () {
$(this).prop('title', 'Removed '+removed_current_option[0].label);
});
}
const inserted_current_option = $('#current-version option:selected')
if (removed_current_option) {
$('ins').each(function () {
$(this).prop('title', 'Inserted '+inserted_current_option[0].label);
});
}
// Set the list of possible differences to jump to
inputs = document.querySelectorAll('#diff-ui .change')
// Set the "current" diff pointer
inputs.current = 0;
// Goto diff
$('#jump-next-diff').click();
var diff = Diff[window.diffType](a.textContent, b.textContent, options);
var fragment = document.createDocumentFragment();
for (var i = 0; i < diff.length; i++) {
if (diff[i].added && diff[i + 1] && diff[i + 1].removed) {
var swap = diff[i];
diff[i] = diff[i + 1];
diff[i + 1] = swap;
}
$('.needs-localtime').each(function () {
for (var option of this.options) {
var dateObject = new Date(option.value * 1000);
option.label = dateObject.toLocaleString(undefined, {dateStyle: "full", timeStyle: "medium"});
}
})
onDiffTypeChange(
document.querySelector('#settings [name="diff_type"]:checked'),
);
changed();
a.onpaste = a.onchange = b.onpaste = b.onchange = changed;
if ("oninput" in a) {
a.oninput = b.oninput = changed;
var node;
if (diff[i].removed) {
node = document.createElement("del");
node.classList.add("change");
const wrapper = node.appendChild(document.createElement("span"));
wrapper.appendChild(document.createTextNode(diff[i].value));
} else if (diff[i].added) {
node = document.createElement("ins");
node.classList.add("change");
const wrapper = node.appendChild(document.createElement("span"));
wrapper.appendChild(document.createTextNode(diff[i].value));
} else {
a.onkeyup = b.onkeyup = changed;
node = document.createTextNode(diff[i].value);
}
fragment.appendChild(node);
}
function onDiffTypeChange(radio) {
window.diffType = radio.value;
// Not necessary
// document.title = "Diff " + radio.value.slice(4);
result.textContent = "";
result.appendChild(fragment);
// Jump at start
inputs.current = 0;
next_diff();
}
window.onload = function () {
/* Convert what is options from UTC time.time() to local browser time */
var diffList = document.getElementById("diff-version");
if (typeof diffList != "undefined" && diffList != null) {
for (var option of diffList.options) {
var dateObject = new Date(option.value * 1000);
option.label = dateObject.toLocaleString();
}
}
var radio = document.getElementsByName("diff_type");
for (var i = 0; i < radio.length; i++) {
radio[i].onchange = function (e) {
onDiffTypeChange(e.target);
changed();
};
}
/* Set current version date as local time in the browser also */
var current_v = document.getElementById("current-v-date");
var dateObject = new Date(newest_version_timestamp * 1000);
current_v.innerHTML = dateObject.toLocaleString();
onDiffTypeChange(
document.querySelector('#settings [name="diff_type"]:checked'),
);
changed();
};
document.getElementById("ignoreWhitespace").onchange = function (e) {
changed();
};
a.onpaste = a.onchange = b.onpaste = b.onchange = changed;
});
if ("oninput" in a) {
a.oninput = b.oninput = changed;
} else {
a.onkeyup = b.onkeyup = changed;
}
function onDiffTypeChange(radio) {
window.diffType = radio.value;
// Not necessary
// document.title = "Diff " + radio.value.slice(4);
}
var radio = document.getElementsByName("diff_type");
for (var i = 0; i < radio.length; i++) {
radio[i].onchange = function (e) {
onDiffTypeChange(e.target);
changed();
};
}
document.getElementById("ignoreWhitespace").onchange = function (e) {
changed();
};
var inputs = document.getElementsByClassName("change");
inputs.current = 0;
function next_diff() {
var element = inputs[inputs.current];
var headerOffset = 80;
var elementPosition = element.getBoundingClientRect().top;
var offsetPosition = elementPosition - headerOffset + window.scrollY;
window.scrollTo({
top: offsetPosition,
behavior: "smooth",
});
inputs.current++;
if (inputs.current >= inputs.length) {
inputs.current = 0;
}
}

View File

@@ -4,14 +4,6 @@ $(function () {
$(this).closest('.unviewed').removeClass('unviewed');
});
$('td[data-timestamp]').each(function () {
$(this).prop('title', new Intl.DateTimeFormat(undefined,
{
dateStyle: 'full',
timeStyle: 'long'
}).format($(this).data('timestamp') * 1000));
})
$("#checkbox-assign-tag").click(function (e) {
$('#op_extradata').val(prompt("Enter a tag name"));
});

View File

@@ -187,10 +187,6 @@ ins {
padding: 0.5em; }
#settings ins {
padding: 0.5em; }
#settings option:checked {
font-weight: bold; }
#settings [type=radio], #settings [type=checkbox] {
vertical-align: middle; }
.source {
position: absolute;

View File

@@ -77,13 +77,6 @@ ins {
ins {
padding: 0.5em;
}
option:checked {
font-weight: bold;
}
[type=radio],[type=checkbox] {
vertical-align: middle;
}
}
.source {

View File

@@ -6,10 +6,6 @@
}
li {
&.browser-step-with-error {
background-color: #ffd6d6;
border-radius: 4px;
}
&:not(:first-child) {
&:hover {
opacity: 1.0;
@@ -48,7 +44,7 @@
#browser-steps .flex-wrapper {
display: flex;
flex-flow: row;
height: 70vh;
height: 600px; /*@todo make this dynamic */
}
/* this is duplicate :( */

View File

@@ -1,28 +0,0 @@
#selector-wrapper {
height: 100%;
max-height: 70vh;
overflow-y: scroll;
position: relative;
//width: 100%;
>img {
position: absolute;
z-index: 4;
max-width: 100%;
}
>canvas {
position: relative;
z-index: 5;
max-width: 100%;
&:hover {
cursor: pointer;
}
}
}
#selector-current-xpath {
font-size: 80%;
}

View File

@@ -471,11 +471,7 @@ footer {
padding: 10px;
&#left-sticky {
left: 0;
position: fixed;
border-top-right-radius: 5px;
border-bottom-right-radius: 5px;
box-shadow: 1px 1px 4px var(--color-shadow-jump);
left: 0px;
}
&#right-sticky {
@@ -943,7 +939,32 @@ ul {
}
}
@import "parts/_visualselector";
#selector-wrapper {
height: 100%;
overflow-y: scroll;
position: relative;
//width: 100%;
>img {
position: absolute;
z-index: 4;
max-width: 100%;
}
>canvas {
position: relative;
z-index: 5;
max-width: 100%;
&:hover {
cursor: pointer;
}
}
}
#selector-current-xpath {
font-size: 80%;
}
#webdriver-override-options {
input[type="number"] {

View File

@@ -26,9 +26,6 @@
#browser_steps li {
list-style: decimal;
padding: 5px; }
#browser_steps li.browser-step-with-error {
background-color: #ffd6d6;
border-radius: 4px; }
#browser_steps li:not(:first-child):hover {
opacity: 1.0; }
#browser_steps li .control {
@@ -53,7 +50,8 @@
#browser-steps .flex-wrapper {
display: flex;
flex-flow: row;
height: 70vh; }
height: 600px;
/*@todo make this dynamic */ }
/* this is duplicate :( */
#browsersteps-selector-wrapper {
@@ -670,11 +668,7 @@ footer {
background: var(--color-background);
padding: 10px; }
.sticky-tab#left-sticky {
left: 0;
position: fixed;
border-top-right-radius: 5px;
border-bottom-right-radius: 5px;
box-shadow: 1px 1px 4px var(--color-shadow-jump); }
left: 0px; }
.sticky-tab#right-sticky {
right: 0px; }
.sticky-tab#hosted-sticky {
@@ -983,7 +977,6 @@ ul {
#selector-wrapper {
height: 100%;
max-height: 70vh;
overflow-y: scroll;
position: relative; }
#selector-wrapper > img {

View File

@@ -42,7 +42,6 @@ class ChangeDetectionStore:
self.__data = App.model()
self.datastore_path = datastore_path
self.json_store_path = "{}/url-watches.json".format(self.datastore_path)
print(">>> Datastore path is ", self.json_store_path)
self.needs_write = False
self.start_time = time.time()
self.stop_thread = False
@@ -96,14 +95,6 @@ class ChangeDetectionStore:
self.add_watch(url='https://changedetection.io/CHANGELOG.txt',
tag='changedetection.io',
extras={'fetch_backend': 'html_requests'})
updates_available = self.get_updates_available()
self.__data['settings']['application']['schema_version'] = updates_available.pop()
else:
# Bump the update version by running updates
self.run_updates()
self.__data['version_tag'] = version_tag
# Just to test that proxies.json if it exists, doesnt throw a parsing error on startup
@@ -133,6 +124,9 @@ class ChangeDetectionStore:
secret = secrets.token_hex(16)
self.__data['settings']['application']['api_access_token'] = secret
# Bump the update version by running updates
self.run_updates()
self.needs_write = True
# Finally start the thread that will manage periodic data saves to JSON
@@ -244,16 +238,12 @@ class ChangeDetectionStore:
import pathlib
self.__data['watching'][uuid].update({
'browser_steps_last_error_step' : None,
'check_count': 0,
'fetch_time' : 0.0,
'has_ldjson_price_data': None,
'last_checked': 0,
'has_ldjson_price_data': None,
'last_error': False,
'last_notification_error': False,
'last_viewed': 0,
'previous_md5': False,
'previous_md5_before_filters': False,
'track_ldjson_price_data': None,
})
@@ -634,8 +624,14 @@ class ChangeDetectionStore:
def tag_exists_by_name(self, tag_name):
return any(v.get('title', '').lower() == tag_name.lower() for k, v in self.__data['settings']['application']['tags'].items())
def get_updates_available(self):
# Run all updates
# IMPORTANT - Each update could be run even when they have a new install and the schema is correct
# So therefor - each `update_n` should be very careful about checking if it needs to actually run
# Probably we should bump the current update schema version with each tag release version?
def run_updates(self):
import inspect
import shutil
updates_available = []
for i, o in inspect.getmembers(self, predicate=inspect.ismethod):
m = re.search(r'update_(\d+)$', i)
@@ -643,15 +639,6 @@ class ChangeDetectionStore:
updates_available.append(int(m.group(1)))
updates_available.sort()
return updates_available
# Run all updates
# IMPORTANT - Each update could be run even when they have a new install and the schema is correct
# So therefor - each `update_n` should be very careful about checking if it needs to actually run
# Probably we should bump the current update schema version with each tag release version?
def run_updates(self):
import shutil
updates_available = self.get_updates_available()
for update_n in updates_available:
if update_n > self.__data['settings']['application']['schema_version']:
print ("Applying update_{}".format((update_n)))

View File

@@ -121,8 +121,7 @@
{% endif %}
{% if left_sticky %}
<div class="sticky-tab" id="left-sticky">
<a href="{{url_for('preview_page', uuid=uuid)}}">Show current snapshot</a><br>
Visualise <strong>triggers</strong> and <strong>ignored text</strong>
<a href="{{url_for('preview_page', uuid=uuid)}}">Show current snapshot</a>
</div>
{% endif %}
{% if right_sticky %}

View File

@@ -13,31 +13,10 @@
<script src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
<div id="settings">
<h1>Differences</h1>
<form class="pure-form " action="" method="GET">
<fieldset>
{% if versions|length >= 1 %}
<strong>Compare</strong>
<del class="change"><span>from</span></del>
<select id="diff-version" name="from_version" class="needs-localtime">
{% for version in versions|reverse %}
<option value="{{ version }}" {% if version== from_version %} selected="" {% endif %}>
{{ version }}
</option>
{% endfor %}
</select>
<ins class="change"><span>to</span></ins>
<select id="current-version" name="to_version" class="needs-localtime">
{% for version in versions|reverse %}
<option value="{{ version }}" {% if version== to_version %} selected="" {% endif %}>
{{ version }}
</option>
{% endfor %}
</select>
<button type="submit" class="pure-button pure-button-primary">Go</button>
{% endif %}
</fieldset>
<fieldset>
<strong>Style</strong>
<label for="diffWords" class="pure-checkbox">
<input type="radio" name="diff_type" id="diffWords" value="diffWords"> Words</label>
<label for="diffLines" class="pure-checkbox">
@@ -47,20 +26,32 @@
<input type="radio" name="diff_type" id="diffChars" value="diffChars"> Chars</label>
<!-- @todo - when mimetype is JSON, select this by default? -->
<label for="diffJson" class="pure-checkbox">
<input type="radio" name="diff_type" id="diffJson" value="diffJson"> JSON</label>
<input type="radio" name="diff_type" id="diffJson" value="diffJson" > JSON</label>
<span>
<!-- https://github.com/kpdecker/jsdiff/issues/389 ? -->
<label for="ignoreWhitespace" class="pure-checkbox" id="label-diff-ignorewhitespace">
<input type="checkbox" id="ignoreWhitespace" name="ignoreWhitespace"> Ignore Whitespace</label>
</span>
{% if versions|length >= 1 %}
<label for="diff-version">Compare newest (<span id="current-v-date"></span>) with</label>
<select id="diff-version" name="previous_version">
{% for version in versions|reverse %}
<option value="{{version}}" {% if version== current_previous_version %} selected="" {% endif %}>
{{version}}
</option>
{% endfor %}
</select>
<button type="submit" class="pure-button pure-button-primary">Go</button>
{% endif %}
</fieldset>
</form>
<del>Removed text</del>
<ins>Inserted Text</ins>
<span>
<!-- https://github.com/kpdecker/jsdiff/issues/389 ? -->
<label for="ignoreWhitespace" class="pure-checkbox" id="label-diff-ignorewhitespace">
<input type="checkbox" id="ignoreWhitespace" name="ignoreWhitespace" > Ignore Whitespace</label>
</span>
</div>
<div id="diff-jump">
<a id="jump-next-diff" title="Jump to next difference">Jump</a>
<a onclick="next_diff();">Jump</a>
</div>
<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
@@ -88,6 +79,8 @@
</div>
<div class="tab-pane-inner" id="text">
<div class="tip">Pro-tip: Use <strong>show current snapshot</strong> tab to visualise what will be ignored, highlight text to add to ignore filters</div>
{% if password_enabled_and_share_is_off %}
<div class="tip">Pro-tip: You can enable <strong>"share access when password is enabled"</strong> from settings</div>
{% endif %}
@@ -98,8 +91,8 @@
<tbody>
<tr>
<!-- just proof of concept copied straight from github.com/kpdecker/jsdiff -->
<td id="a" style="display: none;">{{from_version_file_contents}}</td>
<td id="b" style="display: none;">{{to_version_file_contents}}</td>
<td id="a" style="display: none;">{{previous}}</td>
<td id="b" style="display: none;">{{newest}}</td>
<td id="diff-col">
<span id="result" class="highlightable-filter"></span>
</td>

View File

@@ -4,10 +4,8 @@
{% from '_common_fields.jinja' import render_common_settings_form %}
<script src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
<script>
const browser_steps_available_screenshots=JSON.parse('{{ watch.get_browsersteps_available_screenshots|tojson }}');
const browser_steps_config=JSON.parse('{{ browser_steps_config|tojson }}');
const browser_steps_fetch_screenshot_image_url="{{url_for('browser_steps.browser_steps_fetch_screenshot_image', uuid=uuid)}}";
const browser_steps_last_error_step={{ watch.browser_steps_last_error_step|tojson }};
const browser_steps_start_url="{{url_for('browser_steps.browsersteps_start_session', uuid=uuid)}}";
const browser_steps_sync_url="{{url_for('browser_steps.browsersteps_ui_update', uuid=uuid)}}";
{% if emailprefix %}
@@ -51,7 +49,6 @@
<li class="tab"><a href="#restock">Restock Detection</a></li>
{% endif %}
<li class="tab"><a href="#notifications">Notifications</a></li>
<li class="tab"><a href="#stats">Stats</a></li>
</ul>
</div>
@@ -112,7 +109,7 @@
<span class="pure-form-message-inline">
<p>Use the <strong>Basic</strong> method (default) where your watched site doesn't need Javascript to render.</p>
<p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using Bright Data and Oxylabs Proxies, find out more here.</a>
Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using BrightData Proxies, find out more here.</a>
</span>
</div>
{% if form.proxy %}
@@ -381,16 +378,15 @@ Unavailable") }}
{{ render_field(form.extract_text, rows=5, placeholder="\d+ online") }}
<span class="pure-form-message-inline">
<ul>
<li>Extracts text in the final output (line by line) after other filters using regular expressions or string match;
<li>Extracts text in the final output (line by line) after other filters using regular expressions;
<ul>
<li>Regular expression &dash; example <code>/reports.+?2022/i</code></li>
<li>Don't forget to consider the white-space at the start of a line <code>/.+?reports.+?2022/i</code></li>
<li>Use <code>//(?aiLmsux))</code> type flags (more <a href="https://docs.python.org/3/library/re.html#index-15">information here</a>)<br></li>
<li>Keyword example &dash; example <code>Out of stock</code></li>
<li>Use groups to extract just that text &dash; example <code>/reports.+?(\d+)/i</code> returns a list of years only</li>
</ul>
</li>
<li>One line per regular-expression/string match</li>
<li>One line per regular-expression/ string match</li>
</ul>
</span>
</div>
@@ -444,35 +440,7 @@ Unavailable") }}
</fieldset>
</div>
{% endif %}
<div class="tab-pane-inner" id="stats">
<div class="pure-control-group">
<style>
#stats-table tr > td:first-child {
font-weight: bold;
}
</style>
<table class="pure-table" id="stats-table">
<tbody>
<tr>
<td>Check count</td>
<td>{{ watch.check_count }}</td>
</tr>
<tr>
<td>Consecutive filter failures</td>
<td>{{ watch.consecutive_filter_failures }}</td>
</tr>
<tr>
<td>History length</td>
<td>{{ watch.history|length }}</td>
</tr>
<tr>
<td>Last fetch time</td>
<td>{{ watch.fetch_time }}s</td>
</tr>
</tbody>
</table>
</div>
</div>
<div id="actions">
<div class="pure-control-group">
{{ render_button(form.save_button) }}

View File

@@ -109,7 +109,7 @@
<p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
</span>
<br>
Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using Bright Data and Oxylabs Proxies, find out more here.</a>
Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using BrightData Proxies, find out more here.</a>
</div>
<fieldset class="pure-group" id="webdriver-override-options">
<div class="pure-form-message-inline">
@@ -229,8 +229,7 @@ nav
<div class="pure-control-group">
{{ render_field(form.requests.form.extra_proxies) }}
<span class="pure-form-message-inline">"Name" will be used for selecting the proxy in the Watch Edit settings</span><br>
<span class="pure-form-message-inline">SOCKS5 proxies with authentication are only supported with 'plain requests' fetcher, for other fetchers you should whitelist the IP access instead</span>
<span class="pure-form-message-inline">"Name" will be used for selecting the proxy in the Watch Edit settings</span>
</div>
</div>
<div id="actions">

View File

@@ -119,9 +119,6 @@
<a href="{{ url_for('settings_page', uuid=watch.uuid) }}#proxies">Try adding external proxies/locations</a>
{% endif %}
{% if 'empty result or contain only an image' in watch.last_error %}
<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Detecting-changes-in-images">more help here</a>.
{% endif %}
</div>
{% endif %}
{% if watch.last_notification_error is defined and watch.last_notification_error != False %}
@@ -154,8 +151,8 @@
{% endfor %}
</td>
<td class="last-checked" data-timestamp="{{ watch.last_checked }}">{{watch|format_last_checked_time|safe}}</td>
<td class="last-changed" data-timestamp="{{ watch.last_changed }}">{% if watch.history_n >=2 and watch.last_changed >0 %}
<td class="last-checked">{{watch|format_last_checked_time|safe}}</td>
<td class="last-changed">{% if watch.history_n >=2 and watch.last_changed >0 %}
{{watch.last_changed|format_timestamp_timeago}}
{% else %}
Not yet
@@ -178,18 +175,13 @@
</tbody>
</table>
<ul id="post-list-buttons">
{% if errored_count %}
<li>
<a href="{{url_for('index', with_errors=1, tag=request.args.get('tag')) }}" class="pure-button button-tag button-error ">With errors ({{ errored_count }})</a>
</li>
{% endif %}
{% if has_unviewed %}
<li>
<a href="{{url_for('mark_all_viewed',with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag ">Mark all viewed</a>
<a href="{{url_for('mark_all_viewed', tag=request.args.get('tag')) }}" class="pure-button button-tag ">Mark all viewed</a>
</li>
{% endif %}
<li>
<a href="{{ url_for('form_watch_checknow', tag=active_tag, with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag ">Recheck
<a href="{{ url_for('form_watch_checknow', tag=active_tag) }}" class="pure-button button-tag ">Recheck
all {% if active_tag%} in "{{tags[active_tag].title}}"{%endif%}</a>
</li>
<li>

View File

@@ -28,6 +28,8 @@ def test_fetch_webdriver_content(client, live_server):
)
assert b"1 Imported" in res.data
time.sleep(3)
wait_for_all_checks(client)

View File

@@ -2,11 +2,12 @@
import time
from flask import url_for
from ..util import live_server_setup, wait_for_all_checks
from ..util import live_server_setup
def test_preferred_proxy(client, live_server):
time.sleep(1)
live_server_setup(live_server)
time.sleep(1)
url = "http://chosen.changedetection.io"
res = client.post(
@@ -19,7 +20,7 @@ def test_preferred_proxy(client, live_server):
assert b"1 Imported" in res.data
wait_for_all_checks(client)
time.sleep(2)
res = client.post(
url_for("edit_page", uuid="first"),
data={
@@ -33,5 +34,5 @@ def test_preferred_proxy(client, live_server):
follow_redirects=True
)
assert b"Updated watch." in res.data
wait_for_all_checks(client)
time.sleep(2)
# Now the request should appear in the second-squid logs

View File

@@ -1,6 +0,0 @@
{
"socks5proxy": {
"label": "socks5proxy",
"url": "socks5://proxy_user123:proxy_pass123@socks5proxy:1080"
}
}

View File

@@ -1,6 +0,0 @@
{
"socks5proxy": {
"label": "socks5proxy",
"url": "socks5://socks5proxy-noauth:1080"
}
}

View File

@@ -1,63 +0,0 @@
#!/usr/bin/python3
import os
import time
from flask import url_for
from changedetectionio.tests.util import live_server_setup, wait_for_all_checks
def test_socks5(client, live_server):
live_server_setup(live_server)
# Setup a proxy
res = client.post(
url_for("settings_page"),
data={
"requests-time_between_check-minutes": 180,
"application-ignore_whitespace": "y",
"application-fetch_backend": "html_requests",
# set in .github/workflows/test-only.yml
"requests-extra_proxies-0-proxy_url": "socks5://proxy_user123:proxy_pass123@socks5proxy:1080",
"requests-extra_proxies-0-proxy_name": "socks5proxy",
},
follow_redirects=True
)
assert b"Settings updated." in res.data
test_url = "https://changedetection.io/CHANGELOG.txt?socks-test-tag=" + os.getenv('SOCKSTEST', '')
res = client.post(
url_for("form_quick_watch_add"),
data={"url": test_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
follow_redirects=True
)
assert b"Watch added in Paused state, saving will unpause" in res.data
res = client.get(
url_for("edit_page", uuid="first", unpause_on_save=1),
)
# check the proxy is offered as expected
assert b'ui-0socks5proxy' in res.data
res = client.post(
url_for("edit_page", uuid="first", unpause_on_save=1),
data={
"include_filters": "",
"fetch_backend": 'html_webdriver' if os.getenv('PLAYWRIGHT_DRIVER_URL') else 'html_requests',
"headers": "",
"proxy": "ui-0socks5proxy",
"tags": "",
"url": test_url,
},
follow_redirects=True
)
assert b"unpaused" in res.data
wait_for_all_checks(client)
res = client.get(
url_for("preview_page", uuid="first"),
follow_redirects=True
)
# Should see the proper string
assert "+0200:".encode('utf-8') in res.data

View File

@@ -1,52 +0,0 @@
#!/usr/bin/python3
import os
import time
from flask import url_for
from changedetectionio.tests.util import live_server_setup, wait_for_all_checks
# should be proxies.json mounted from run_proxy_tests.sh already
# -v `pwd`/tests/proxy_socks5/proxies.json-example:/app/changedetectionio/test-datastore/proxies.json
def test_socks5_from_proxiesjson_file(client, live_server):
live_server_setup(live_server)
test_url = "https://changedetection.io/CHANGELOG.txt?socks-test-tag=" + os.getenv('SOCKSTEST', '')
res = client.get(url_for("settings_page"))
assert b'name="requests-proxy" type="radio" value="socks5proxy"' in res.data
res = client.post(
url_for("form_quick_watch_add"),
data={"url": test_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
follow_redirects=True
)
assert b"Watch added in Paused state, saving will unpause" in res.data
res = client.get(
url_for("edit_page", uuid="first", unpause_on_save=1),
)
# check the proxy is offered as expected
assert b'name="proxy" type="radio" value="socks5proxy"' in res.data
res = client.post(
url_for("edit_page", uuid="first", unpause_on_save=1),
data={
"include_filters": "",
"fetch_backend": 'html_webdriver' if os.getenv('PLAYWRIGHT_DRIVER_URL') else 'html_requests',
"headers": "",
"proxy": "socks5proxy",
"tags": "",
"url": test_url,
},
follow_redirects=True
)
assert b"unpaused" in res.data
wait_for_all_checks(client)
res = client.get(
url_for("preview_page", uuid="first"),
follow_redirects=True
)
# Should see the proper string
assert "+0200:".encode('utf-8') in res.data

View File

@@ -2,8 +2,7 @@
import time
from flask import url_for
from .util import live_server_setup, extract_UUID_from_client, extract_api_key_from_UI, wait_for_all_checks
from .util import live_server_setup, extract_UUID_from_client, extract_api_key_from_UI
def set_response_with_ldjson():
test_return_data = """<html>
@@ -28,7 +27,7 @@ def set_response_with_ldjson():
"description":"You dont need it",
"mpn":"111111",
"sku":"22222",
"Offers":{
"offers":{
"@type":"AggregateOffer",
"lowPrice":8097000,
"highPrice":8099900,
@@ -76,11 +75,12 @@ def set_response_without_ldjson():
f.write(test_return_data)
return None
def test_setup(client, live_server):
live_server_setup(live_server)
# actually only really used by the distll.io importer, but could be handy too
def test_check_ldjson_price_autodetect(client, live_server):
live_server_setup(live_server)
# Give the endpoint time to spin up
time.sleep(1)
set_response_with_ldjson()
@@ -92,7 +92,7 @@ def test_check_ldjson_price_autodetect(client, live_server):
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
time.sleep(3)
# Should get a notice that it's available
res = client.get(url_for("index"))
@@ -102,11 +102,11 @@ def test_check_ldjson_price_autodetect(client, live_server):
uuid = extract_UUID_from_client(client)
client.get(url_for('price_data_follower.accept', uuid=uuid, follow_redirects=True))
wait_for_all_checks(client)
time.sleep(2)
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
time.sleep(2)
# Offer should be gone
res = client.get(url_for("index"))
assert b'Embedded price data' not in res.data
@@ -138,97 +138,9 @@ def test_check_ldjson_price_autodetect(client, live_server):
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
time.sleep(3)
res = client.get(url_for("index"))
assert b'ldjson-price-track-offer' not in res.data
##########################################################################################
client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
def _test_runner_check_bad_format_ignored(live_server, client, has_ldjson_price_data):
test_url = url_for('test_endpoint', _external=True)
res = client.post(
url_for("import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
for k,v in client.application.config.get('DATASTORE').data['watching'].items():
assert v.get('last_error') == False
assert v.get('has_ldjson_price_data') == has_ldjson_price_data
##########################################################################################
client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
def test_bad_ldjson_is_correctly_ignored(client, live_server):
#live_server_setup(live_server)
test_return_data = """
<html>
<head>
<script type="application/ld+json">
{
"@context": "http://schema.org",
"@type": ["Product", "SubType"],
"name": "My test product",
"description": "",
"offers": {
"note" : "You can see the case-insensitive OffERS key, it should work",
"@type": "Offer",
"offeredBy": {
"@type": "Organization",
"name":"Person",
"telephone":"+1 999 999 999"
},
"price": "1",
"priceCurrency": "EUR",
"url": "/some/url"
}
}
</script>
</head>
<body>
<div class="yes">Some extra stuff</div>
</body></html>
"""
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write(test_return_data)
_test_runner_check_bad_format_ignored(live_server=live_server, client=client, has_ldjson_price_data=True)
test_return_data = """
<html>
<head>
<script type="application/ld+json">
{
"@context": "http://schema.org",
"@type": ["Product", "SubType"],
"name": "My test product",
"description": "",
"BrokenOffers": {
"@type": "Offer",
"offeredBy": {
"@type": "Organization",
"name":"Person",
"telephone":"+1 999 999 999"
},
"price": "1",
"priceCurrency": "EUR",
"url": "/some/url"
}
}
</script>
</head>
<body>
<div class="yes">Some extra stuff</div>
</body></html>
"""
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write(test_return_data)
_test_runner_check_bad_format_ignored(live_server=live_server, client=client, has_ldjson_price_data=False)

View File

@@ -89,7 +89,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
# Following the 'diff' link, it should no longer display as 'unviewed' even after we recheck it a few times
res = client.get(url_for("diff_history_page", uuid="first"))
assert b'selected=""' in res.data, "Confirm diff history page loaded"
assert b'Compare newest' in res.data
# Check the [preview] pulls the right one
res = client.get(

View File

@@ -2,7 +2,7 @@
import time
from flask import url_for
from .util import live_server_setup, wait_for_all_checks
from .util import live_server_setup
from ..html_tools import *
@@ -55,8 +55,6 @@ def set_multiline_response():
</p>
<div>aaand something lines</div>
<br>
<div>and this should be</div>
</body>
</html>
"""
@@ -68,10 +66,11 @@ def set_multiline_response():
def test_setup(client, live_server):
live_server_setup(live_server)
def test_check_filter_multiline(client, live_server):
#live_server_setup(live_server)
set_multiline_response()
# Add our URL to the import page
@@ -83,15 +82,14 @@ def test_check_filter_multiline(client, live_server):
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
time.sleep(3)
# Goto the edit page, add our ignore text
# Add our URL to the import page
res = client.post(
url_for("edit_page", uuid="first"),
data={"include_filters": '',
# Test a regex and a plaintext
'extract_text': '/something.+?6 billion.+?lines/si\r\nand this should be',
'extract_text': '/something.+?6 billion.+?lines/si',
"url": test_url,
"tags": "",
"headers": "",
@@ -101,19 +99,13 @@ def test_check_filter_multiline(client, live_server):
)
assert b"Updated watch." in res.data
wait_for_all_checks(client)
res = client.get(url_for("index"))
# Issue 1828
assert b'not at the start of the expression' not in res.data
time.sleep(3)
res = client.get(
url_for("preview_page", uuid="first"),
follow_redirects=True
)
# Plaintext that doesnt look like a regex should match also
assert b'and this should be' in res.data
assert b'<div class="">Something' in res.data
assert b'<div class="">across 6 billion multiple' in res.data
@@ -123,11 +115,14 @@ def test_check_filter_multiline(client, live_server):
assert b'aaand something lines' not in res.data
def test_check_filter_and_regex_extract(client, live_server):
sleep_time_for_fetch_thread = 3
include_filters = ".changetext"
set_original_response()
# Give the endpoint time to spin up
time.sleep(1)
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
res = client.post(
@@ -137,15 +132,19 @@ def test_check_filter_and_regex_extract(client, live_server):
)
assert b"1 Imported" in res.data
time.sleep(1)
# Trigger a check
client.get(url_for("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)
# Goto the edit page, add our ignore text
# Add our URL to the import page
res = client.post(
url_for("edit_page", uuid="first"),
data={"include_filters": include_filters,
'extract_text': '/\d+ online/\r\n/\d+ guests/\r\n/somecase insensitive \d+/i\r\n/somecase insensitive (345\d)/i\r\n/issue1828.+?2022/i',
'extract_text': '\d+ online\r\n\d+ guests\r\n/somecase insensitive \d+/i\r\n/somecase insensitive (345\d)/i',
"url": test_url,
"tags": "",
"headers": "",
@@ -156,13 +155,8 @@ def test_check_filter_and_regex_extract(client, live_server):
assert b"Updated watch." in res.data
# Give the thread time to pick it up
wait_for_all_checks(client)
res = client.get(url_for("index"))
#issue 1828
assert b'not at the start of the expression' not in res.data
time.sleep(sleep_time_for_fetch_thread)
# Make a change
set_modified_response()
@@ -170,7 +164,7 @@ def test_check_filter_and_regex_extract(client, live_server):
# Trigger a check
client.get(url_for("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 have 'unviewed' still
# Because it should be looking at only that 'sametext' id

View File

@@ -2,61 +2,12 @@
import time
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
from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, extract_rss_token_from_UI
def set_original_cdata_xml():
test_return_data = """<rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:media="http://search.yahoo.com/mrss/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
<channel>
<title>Gizi</title>
<link>https://test.com</link>
<atom:link href="https://testsite.com" rel="self" type="application/rss+xml"/>
<description>
<![CDATA[ The Future Could Be Here ]]>
</description>
<language>en</language>
<item>
<title>
<![CDATA[ <img src="https://testsite.com/hacked.jpg"> Hackers can access your computer ]]>
</title>
<link>https://testsite.com/news/12341234234</link>
<description>
<![CDATA[ <img class="type:primaryImage" src="https://testsite.com/701c981da04869e.jpg"/><p>The days of Terminator and The Matrix could be closer. But be positive.</p><p><a href="https://testsite.com">Read more link...</a></p> ]]>
</description>
<category>cybernetics</category>
<category>rand corporation</category>
<pubDate>Tue, 17 Oct 2023 15:10:00 GMT</pubDate>
<guid isPermaLink="false">1850933241</guid>
<dc:creator>
<![CDATA[ Mr Hacker News ]]>
</dc:creator>
<media:thumbnail url="https://testsite.com/thumbnail-c224e10d81488e818701c981da04869e.jpg"/>
</item>
<item>
<title> Some other title </title>
<link>https://testsite.com/news/12341234236</link>
<description>
Some other description
</description>
</item>
</channel>
</rss>
"""
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write(test_return_data)
def test_setup(client, live_server):
live_server_setup(live_server)
def test_rss_and_token(client, live_server):
# live_server_setup(live_server)
set_original_response()
rss_token = extract_rss_token_from_UI(client)
live_server_setup(live_server)
# Add our URL to the import page
res = client.post(
@@ -66,11 +17,11 @@ def test_rss_and_token(client, live_server):
)
assert b"1 Imported" in res.data
rss_token = extract_rss_token_from_UI(client)
wait_for_all_checks(client)
set_modified_response()
time.sleep(2)
client.get(url_for("form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
time.sleep(2)
# Add our URL to the import page
res = client.get(
@@ -86,80 +37,3 @@ def test_rss_and_token(client, live_server):
)
assert b"Access denied, bad token" not in res.data
assert b"Random content" in res.data
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
def test_basic_cdata_rss_markup(client, live_server):
#live_server_setup(live_server)
set_original_cdata_xml()
test_url = url_for('test_endpoint', content_type="application/xml", _external=True)
# Add our URL to the import page
res = client.post(
url_for("import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
res = client.get(
url_for("preview_page", uuid="first"),
follow_redirects=True
)
assert b'CDATA' not in res.data
assert b'<![' not in res.data
assert b'Hackers can access your computer' in res.data
assert b'The days of Terminator' in res.data
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
def test_rss_xpath_filtering(client, live_server):
#live_server_setup(live_server)
set_original_cdata_xml()
test_url = url_for('test_endpoint', content_type="application/xml", _external=True)
res = client.post(
url_for("form_quick_watch_add"),
data={"url": test_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
follow_redirects=True
)
assert b"Watch added in Paused state, saving will unpause" in res.data
uuid = extract_UUID_from_client(client)
res = client.post(
url_for("edit_page", uuid=uuid, unpause_on_save=1),
data={
"include_filters": "//item/title",
"fetch_backend": "html_requests",
"headers": "",
"proxy": "no-proxy",
"tags": "",
"url": test_url,
},
follow_redirects=True
)
assert b"unpaused" in res.data
wait_for_all_checks(client)
res = client.get(
url_for("preview_page", uuid="first"),
follow_redirects=True
)
assert b'CDATA' not in res.data
assert b'<![' not in res.data
# #1874 All but the first <title was getting selected
# Convert any HTML with just a top level <title> to <h1> to be sure title renders
assert b'Hackers can access your computer' in res.data # Should ONLY be selected by the xpath
assert b'Some other title' in res.data # Should ONLY be selected by the xpath
assert b'The days of Terminator' not in res.data # Should NOT be selected by the xpath
assert b'Some other description' not in res.data # Should NOT be selected by the xpath
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)

View File

@@ -2,7 +2,7 @@
import time
from flask import url_for
from .util import live_server_setup, wait_for_all_checks
from . util import live_server_setup
def set_original_ignore_response():
@@ -26,8 +26,13 @@ def test_trigger_regex_functionality(client, live_server):
live_server_setup(live_server)
sleep_time_for_fetch_thread = 3
set_original_ignore_response()
# Give the endpoint time to spin up
time.sleep(1)
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
res = client.post(
@@ -38,7 +43,7 @@ def test_trigger_regex_functionality(client, live_server):
assert b"1 Imported" in res.data
# 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 (just a new one shouldnt have anything)
res = client.get(url_for("index"))
@@ -52,7 +57,7 @@ def test_trigger_regex_functionality(client, live_server):
"fetch_backend": "html_requests"},
follow_redirects=True
)
wait_for_all_checks(client)
time.sleep(sleep_time_for_fetch_thread)
# so that we set the state to 'unviewed' after all the edits
client.get(url_for("diff_history_page", uuid="first"))
@@ -60,7 +65,7 @@ def test_trigger_regex_functionality(client, live_server):
f.write("some new noise")
client.get(url_for("form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
time.sleep(sleep_time_for_fetch_thread)
# It should report nothing found (nothing should match the regex)
res = client.get(url_for("index"))
@@ -70,7 +75,7 @@ def test_trigger_regex_functionality(client, live_server):
f.write("regex test123<br>\nsomething 123")
client.get(url_for("form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
time.sleep(sleep_time_for_fetch_thread)
res = client.get(url_for("index"))
assert b'unviewed' in res.data

View File

@@ -2,7 +2,7 @@
import time
from flask import url_for
from .util import live_server_setup, wait_for_all_checks
from . util import live_server_setup
from ..html_tools import *
@@ -86,14 +86,14 @@ def test_check_xpath_filter_utf8(client, live_server):
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
time.sleep(1)
res = client.post(
url_for("edit_page", uuid="first"),
data={"include_filters": filter, "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
wait_for_all_checks(client)
time.sleep(3)
res = client.get(url_for("index"))
assert b'Unicode strings with encoding declaration are not supported.' not in res.data
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
@@ -140,14 +140,14 @@ def test_check_xpath_text_function_utf8(client, live_server):
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
time.sleep(1)
res = client.post(
url_for("edit_page", uuid="first"),
data={"include_filters": filter, "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
wait_for_all_checks(client)
time.sleep(3)
res = client.get(url_for("index"))
assert b'Unicode strings with encoding declaration are not supported.' not in res.data
@@ -164,6 +164,7 @@ def test_check_xpath_text_function_utf8(client, live_server):
assert b'Deleted' in res.data
def test_check_markup_xpath_filter_restriction(client, live_server):
sleep_time_for_fetch_thread = 3
xpath_filter = "//*[contains(@class, 'sametext')]"
@@ -182,7 +183,7 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
assert b"1 Imported" in res.data
# Give the thread time to pick it up
wait_for_all_checks(client)
time.sleep(sleep_time_for_fetch_thread)
# Goto the edit page, add our ignore text
# Add our URL to the import page
@@ -194,7 +195,7 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
assert b"Updated watch." in res.data
# Give the thread time to pick it up
wait_for_all_checks(client)
time.sleep(sleep_time_for_fetch_thread)
# view it/reset state back to viewed
client.get(url_for("diff_history_page", uuid="first"), follow_redirects=True)
@@ -205,7 +206,7 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
# Trigger a check
client.get(url_for("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)
res = client.get(url_for("index"))
assert b'unviewed' not in res.data
@@ -215,6 +216,9 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
def test_xpath_validation(client, live_server):
# Give the endpoint time to spin up
time.sleep(1)
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
res = client.post(
@@ -223,7 +227,7 @@ def test_xpath_validation(client, live_server):
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
time.sleep(2)
res = client.post(
url_for("edit_page", uuid="first"),
@@ -240,8 +244,11 @@ def test_check_with_prefix_include_filters(client, live_server):
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
# Give the endpoint time to spin up
time.sleep(1)
set_original_response()
wait_for_all_checks(client)
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
res = client.post(
@@ -250,7 +257,7 @@ def test_check_with_prefix_include_filters(client, live_server):
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
time.sleep(3)
res = client.post(
url_for("edit_page", uuid="first"),
@@ -259,7 +266,7 @@ def test_check_with_prefix_include_filters(client, live_server):
)
assert b"Updated watch." in res.data
wait_for_all_checks(client)
time.sleep(3)
res = client.get(
url_for("preview_page", uuid="first"),
@@ -270,46 +277,3 @@ def test_check_with_prefix_include_filters(client, live_server):
assert b"Some text that will change" not in res.data #not in selector
client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
def test_various_rules(client, live_server):
# Just check these don't error
#live_server_setup(live_server)
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write("""<html>
<body>
Some initial text<br>
<p>Which is across multiple lines</p>
<br>
So let's see what happens. <br>
<div class="sametext">Some text thats the same</div>
<div class="changetext">Some text that will change</div>
<a href=''>some linky </a>
<a href=''>another some linky </a>
<!-- related to https://github.com/dgtlmoon/changedetection.io/pull/1774 -->
<input type="email" id="email" />
</body>
</html>
""")
test_url = url_for('test_endpoint', _external=True)
res = client.post(
url_for("import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
for r in ['//div', '//a', 'xpath://div', 'xpath://a']:
res = client.post(
url_for("edit_page", uuid="first"),
data={"include_filters": r,
"url": test_url,
"tags": "",
"headers": "",
'fetch_backend': "html_requests"},
follow_redirects=True
)
wait_for_all_checks(client)
assert b"Updated watch." in res.data
res = client.get(url_for("index"))
assert b'fetch-error' not in res.data, f"Should not see errors after '{r} filter"

View File

@@ -238,9 +238,7 @@ class update_worker(threading.Thread):
# Used as a default and also by some tests
update_handler = text_json_diff.perform_site_check(datastore=self.datastore)
self.datastore.data['watching'][uuid]['browser_steps_last_error_step'] = None
changed_detected, update_obj, contents = update_handler.run(uuid, skip_when_checksum_same=queued_item_data.item.get('skip_when_checksum_same'))
# Re #342
# In Python 3, all strings are sequences of Unicode characters. There is a bytes type that holds raw bytes.
# We then convert/.decode('utf-8') for the notification etc
@@ -259,7 +257,7 @@ class update_worker(threading.Thread):
has_img = html_tools.include_filters(include_filters='img',
html_content=e.html_content)
if has_img:
extra_help = ", it's possible that the filters you have give an empty result or contain only an image."
extra_help = ", it's possible that the filters you have give an empty result or contain only an image <a href=\"https://github.com/dgtlmoon/changedetection.io/wiki/Detecting-changes-in-images\">more help here</a>."
else:
extra_help = ", it's possible that the filters were found, but contained no usable text."
@@ -326,13 +324,8 @@ class update_worker(threading.Thread):
if not self.datastore.data['watching'].get(uuid):
continue
error_step = e.step_n + 1
err_text = f"Warning, browser step at position {error_step} could not run, target not found, check the watch, add a delay if necessary, view Browser Steps to see screenshot at that step"
self.datastore.update_watch(uuid=uuid,
update_obj={'last_error': err_text,
'browser_steps_last_error_step': error_step
}
)
err_text = "Warning, browser step at position {} could not run, target not found, check the watch, add a delay if necessary.".format(e.step_n+1)
self.datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text})
if self.datastore.data['watching'][uuid].get('filter_failure_notification_send', False):

View File

@@ -81,7 +81,7 @@ services:
# restart: unless-stopped
# Used for fetching pages via Playwright+Chrome where you need Javascript support.
# Note: Playwright/browserless not supported on ARM type devices (rPi etc)
# playwright-chrome:
# hostname: playwright-chrome
# image: browserless/chrome

View File

@@ -16,7 +16,7 @@ validators~=0.21
# Set these versions together to avoid a RequestsDependencyWarning
# >= 2.26 also adds Brotli support if brotli is installed
brotli~=1.0
requests[socks]
requests[socks] ~=2.28
urllib3>1.26
chardet>2.3.0
@@ -33,7 +33,7 @@ dnspython<2.3.0
# jq not available on Windows so must be installed manually
# Notification library
apprise~=1.6.0
apprise~=1.5.0
# apprise mqtt https://github.com/dgtlmoon/changedetection.io/issues/315
paho-mqtt
@@ -63,8 +63,7 @@ jinja2-time
# https://peps.python.org/pep-0508/#environment-markers
# https://github.com/dgtlmoon/changedetection.io/pull/1009
jq~=1.3; python_version >= "3.8" and sys_platform == "darwin"
jq~=1.3; python_version >= "3.8" and sys_platform == "linux"
jq~=1.3 ;python_version >= "3.8" and sys_platform == "linux"
# Any current modern version, required so far for screenshot PNG->JPEG conversion but will be used more in the future
pillow

View File

@@ -1 +1 @@
python-3.11.5
python-3.9.15

View File

@@ -41,7 +41,7 @@ setup(
include_package_data=True,
install_requires=install_requires,
license="Apache License 2.0",
python_requires=">= 3.7",
python_requires=">= 3.6",
classifiers=['Intended Audience :: Customer Service',
'Intended Audience :: Developers',
'Intended Audience :: Education',