Compare commits

..

3 Commits

Author SHA1 Message Date
dgtlmoon
8578cc3582 Fix tuple 2022-10-09 18:10:24 +02:00
dgtlmoon
b72d6f8dec use brotli package 2022-10-09 18:10:14 +02:00
dgtlmoon
5b3f240846 Dont use default Requests user-agent and accept headers in playwright+selenium requests, breaks sites such as united.com. 2022-10-09 17:54:13 +02:00
24 changed files with 103 additions and 308 deletions

View File

@@ -1,55 +0,0 @@
name: ChangeDetection.io Container Build Test
# Triggers the workflow on push or pull request events
# This line doesnt work, even tho it is the documented one
#on: [push, pull_request]
on:
push:
paths:
- requirements.txt
- Dockerfile
pull_request:
paths:
- requirements.txt
- Dockerfile
# Changes to requirements.txt packages and Dockerfile may or may not always be compatible with arm etc, so worth testing
# @todo: some kind of path filter for requirements.txt and Dockerfile
jobs:
test-container-build:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v2
- name: Set up Python 3.9
uses: actions/setup-python@v2
with:
python-version: 3.9
# Just test that the build works, some libraries won't compile on ARM/rPi etc
- name: Set up QEMU
uses: docker/setup-qemu-action@v1
with:
image: tonistiigi/binfmt:latest
platforms: all
- name: Set up Docker Buildx
id: buildx
uses: docker/setup-buildx-action@v1
with:
install: true
version: latest
driver-opts: image=moby/buildkit:master
- name: Test that the docker containers can build
id: docker_build
uses: docker/build-push-action@v2
# https://github.com/docker/build-push-action#customizing
with:
context: ./
file: ./Dockerfile
platforms: linux/arm/v7,linux/arm/v6,linux/amd64,linux/arm64,
cache-from: type=local,src=/tmp/.buildx-cache
cache-to: type=local,dest=/tmp/.buildx-cache

View File

@@ -1,25 +1,28 @@
name: ChangeDetection.io App Test
name: ChangeDetection.io Test
# Triggers the workflow on push or pull request events
on: [push, pull_request]
jobs:
test-application:
test-build:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v2
- name: Set up Python 3.9
uses: actions/setup-python@v2
with:
python-version: 3.9
- name: Show env vars
run: set
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install flake8 pytest
if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
if [ -f requirements-dev.txt ]; then pip install -r requirements-dev.txt; fi
- name: Lint with flake8
run: |
# stop the build if there are Python syntax errors or undefined names
@@ -36,4 +39,7 @@ jobs:
# Each test is totally isolated and performs its own cleanup/reset
cd changedetectionio; ./run_all_tests.sh
# https://github.com/docker/build-push-action/blob/master/docs/advanced/test-before-push.md ?
# https://github.com/docker/buildx/issues/59 ? Needs to be one platform?
# https://github.com/docker/buildx/issues/495#issuecomment-918925854

View File

@@ -6,7 +6,7 @@ Otherwise, it's always best to PR into the `dev` branch.
Please be sure that all new functionality has a matching test!
Use `pytest` to validate/test, you can run the existing tests as `pytest tests/test_notification.py` for example
Use `pytest` to validate/test, you can run the existing tests as `pytest tests/test_notifications.py` for example
```
pip3 install -r requirements-dev

View File

@@ -5,14 +5,13 @@ FROM python:3.8-slim as builder
ARG CRYPTOGRAPHY_DONT_BUILD_RUST=1
RUN apt-get update && apt-get install -y --no-install-recommends \
g++ \
libssl-dev \
libffi-dev \
gcc \
libc-dev \
libffi-dev \
libssl-dev \
libxslt-dev \
make \
zlib1g-dev
zlib1g-dev \
g++
RUN mkdir /install
WORKDIR /install
@@ -26,11 +25,6 @@ RUN pip install --target=/dependencies -r /requirements.txt
RUN pip install --target=/dependencies playwright~=1.26 \
|| echo "WARN: Failed to install Playwright. The application can still run, but the Playwright option will be disabled."
RUN pip install --target=/dependencies jq~=1.3 \
|| echo "WARN: Failed to install JQ. The application can still run, but the Jq: filter option will be disabled."
# Final image stage
FROM python:3.8-slim
@@ -64,7 +58,6 @@ EXPOSE 5000
# The actual flask app
COPY changedetectionio /app/changedetectionio
# The eventlet server wrapper
COPY changedetection.py /app/changedetection.py

View File

@@ -2,7 +2,6 @@ recursive-include changedetectionio/api *
recursive-include changedetectionio/templates *
recursive-include changedetectionio/static *
recursive-include changedetectionio/model *
recursive-include changedetectionio/tests *
include changedetection.py
global-exclude *.pyc
global-exclude node_modules

View File

@@ -121,8 +121,8 @@ See the wiki for more information https://github.com/dgtlmoon/changedetection.io
## Filters
XPath, JSONPath, jq, and CSS support comes baked in! You can be as specific as you need, use XPath exported from various XPath element query creation tools.
(We support LXML `re:test`, `re:math` and `re:replace`.)
## Notifications
@@ -161,14 +161,46 @@ This will re-parse the JSON and apply formatting to the text, making it super ea
### JSONPath or jq?
For more complex parsing, filtering, and modifying of JSON data, jq is recommended due to the built-in operators and functions. Refer to the [documentation](https://stedolan.github.io/jq/manual/) for more specifc information on jq.
For more complex parsing, filtering, and modifying of JSON data, jq is recommended due to the built-in operators and functions. Refer to the [documentation](https://stedolan.github.io/jq/manual/) for more information on jq.
One big advantage of `jq` is that you can use logic in your JSON filter, such as filters to only show items that have a value greater than/less than etc.
The example below adds the price in dollars to each item in the JSON data, and then filters to only show items that are greater than 10.
See the wiki https://github.com/dgtlmoon/changedetection.io/wiki/JSON-Selector-Filter-help for more information and examples
#### Sample input data from API
```
{
"items": [
{
"name": "Product A",
"priceInCents": 2500
},
{
"name": "Product B",
"priceInCents": 500
},
{
"name": "Product C",
"priceInCents": 2000
}
]
}
```
Note: `jq` library must be added separately (`pip3 install jq`)
#### Sample jq
`jq:.items[] | . + { "priceInDollars": (.priceInCents / 100) } | select(.priceInDollars > 10)`
#### Sample output data
```
{
"name": "Product A",
"priceInCents": 2500,
"priceInDollars": 25
}
{
"name": "Product C",
"priceInCents": 2000,
"priceInDollars": 20
}
```
### Parse JSON embedded in HTML!

View File

@@ -33,7 +33,7 @@ from flask_wtf import CSRFProtect
from changedetectionio import html_tools
from changedetectionio.api import api_v1
__version__ = '0.39.20.4'
__version__ = '0.39.20'
datastore = None
@@ -194,9 +194,6 @@ def changedetection_app(config=None, datastore_o=None):
watch_api.add_resource(api_v1.Watch, '/api/v1/watch/<string:uuid>',
resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
watch_api.add_resource(api_v1.SystemInfo, '/api/v1/systeminfo',
resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
@@ -639,27 +636,20 @@ def changedetection_app(config=None, datastore_o=None):
# Only works reliably with Playwright
visualselector_enabled = os.getenv('PLAYWRIGHT_DRIVER_URL', False) and default['fetch_backend'] == 'html_webdriver'
# JQ is difficult to install on windows and must be manually added (outside requirements.txt)
jq_support = True
try:
import jq
except ModuleNotFoundError:
jq_support = False
output = render_template("edit.html",
uuid=uuid,
watch=datastore.data['watching'][uuid],
form=form,
has_empty_checktime=using_default_check_time,
has_default_notification_urls=True if len(datastore.data['settings']['application']['notification_urls']) else False,
using_global_webdriver_wait=default['webdriver_delay'] is None,
current_base_url=datastore.data['settings']['application']['base_url'],
emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
form=form,
has_default_notification_urls=True if len(datastore.data['settings']['application']['notification_urls']) else False,
has_empty_checktime=using_default_check_time,
jq_support=jq_support,
playwright_enabled=os.getenv('PLAYWRIGHT_DRIVER_URL', False),
settings_application=datastore.data['settings']['application'],
using_global_webdriver_wait=default['webdriver_delay'] is None,
uuid=uuid,
visualselector_data_is_ready=visualselector_data_is_ready,
visualselector_enabled=visualselector_enabled,
watch=datastore.data['watching'][uuid],
playwright_enabled=os.getenv('PLAYWRIGHT_DRIVER_URL', False)
)
return output
@@ -819,10 +809,8 @@ def changedetection_app(config=None, datastore_o=None):
newest_file = history[dates[-1]]
# Read as binary and force decode as UTF-8
# Windows may fail decode in python if we just use 'r' mode (chardet decode exception)
try:
with open(newest_file, 'r', encoding='utf-8', errors='ignore') as f:
with open(newest_file, 'r') as f:
newest_version_file_contents = f.read()
except Exception as e:
newest_version_file_contents = "Unable to read {}.\n".format(newest_file)
@@ -835,7 +823,7 @@ def changedetection_app(config=None, datastore_o=None):
previous_file = history[dates[-2]]
try:
with open(previous_file, 'r', encoding='utf-8', errors='ignore') as f:
with open(previous_file, 'r') as f:
previous_version_file_contents = f.read()
except Exception as e:
previous_version_file_contents = "Unable to read {}.\n".format(previous_file)
@@ -912,7 +900,7 @@ def changedetection_app(config=None, datastore_o=None):
timestamp = list(watch.history.keys())[-1]
filename = watch.history[timestamp]
try:
with open(filename, 'r', encoding='utf-8', errors='ignore') as f:
with open(filename, 'r') as f:
tmp = f.readlines()
# Get what needs to be highlighted

View File

@@ -122,37 +122,3 @@ class CreateWatch(Resource):
return {'status': "OK"}, 200
return list, 200
class SystemInfo(Resource):
def __init__(self, **kwargs):
# datastore is a black box dependency
self.datastore = kwargs['datastore']
self.update_q = kwargs['update_q']
@auth.check_token
def get(self):
import time
overdue_watches = []
# Check all watches and report which have not been checked but should have been
for uuid, watch in self.datastore.data.get('watching', {}).items():
# see if now - last_checked is greater than the time that should have been
# this is not super accurate (maybe they just edited it) but better than nothing
t = watch.threshold_seconds()
if not t:
# Use the system wide default
t = self.datastore.threshold_seconds
time_since_check = time.time() - watch.get('last_checked')
# Allow 5 minutes of grace time before we decide it's overdue
if time_since_check - (5 * 60) > t:
overdue_watches.append(uuid)
return {
'queue_size': self.update_q.qsize(),
'overdue_watches': overdue_watches,
'uptime': round(time.time() - self.datastore.start_time, 2),
'watch_count': len(self.datastore.data.get('watching', {}))
}, 200

View File

@@ -102,14 +102,6 @@ def main():
has_password=datastore.data['settings']['application']['password'] != False
)
# Monitored websites will not receive a Referer header
# when a user clicks on an outgoing link.
@app.after_request
def hide_referrer(response):
if os.getenv("HIDE_REFERER", False):
response.headers["Referrer-Policy"] = "no-referrer"
return response
# Proxy sub-directory support
# Set environment var USE_X_SETTINGS=1 on this script
# And then in your proxy_pass settings

View File

@@ -65,9 +65,7 @@ class perform_site_check():
request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
timeout = self.datastore.data['settings']['requests'].get('timeout')
url = watch.link
url = watch.get('url')
request_body = self.datastore.data['watching'][uuid].get('body')
request_method = self.datastore.data['watching'][uuid].get('method')
ignore_status_codes = self.datastore.data['watching'][uuid].get('ignore_status_codes', False)

View File

@@ -303,16 +303,12 @@ class ValidateCSSJSONXPATHInput(object):
# Re #265 - maybe in the future fetch the page and offer a
# warning/notice that its possible the rule doesnt yet match anything?
if 'jq:' in line:
if not self.allow_json:
raise ValidationError("jq not permitted in this field!")
if 'jq:' in line:
try:
import jq
except ModuleNotFoundError:
# `jq` requires full compilation in windows and so isn't generally available
raise ValidationError("jq not support not found")
input = line.replace('jq:', '')
try:

View File

@@ -1,11 +1,12 @@
import json
from typing import List
from bs4 import BeautifulSoup
from jsonpath_ng.ext import parse
import jq
import re
from inscriptis import get_text
from inscriptis.model.config import ParserConfig
from jsonpath_ng.ext import parse
from typing import List
import json
import re
class FilterNotFoundInResponse(ValueError):
def __init__(self, msg):
@@ -84,18 +85,9 @@ def _parse_json(json_data, json_filter):
jsonpath_expression = parse(json_filter.replace('json:', ''))
match = jsonpath_expression.find(json_data)
return _get_stripped_text_from_json_match(match)
if 'jq:' in json_filter:
try:
import jq
except ModuleNotFoundError:
# `jq` requires full compilation in windows and so isn't generally available
raise Exception("jq not support not found")
jq_expression = jq.compile(json_filter.replace('jq:', ''))
match = jq_expression.input(json_data).all()
return _get_stripped_text_from_json_match(match)
def _get_stripped_text_from_json_match(match):

View File

@@ -87,16 +87,6 @@ class model(dict):
print ("> Creating data dir {}".format(target_path))
os.mkdir(target_path)
@property
def link(self):
url = self.get('url', '')
if '{%' in url or '{{' in url:
from jinja2 import Environment
# Jinja2 available in URLs along with https://pypi.org/project/jinja2-time/
jinja2_env = Environment(extensions=['jinja2_time.TimeExtension'])
return str(jinja2_env.from_string(url).render())
return url
@property
def label(self):
# Used for sorting
@@ -128,10 +118,7 @@ class model(dict):
if os.path.isfile(fname):
logging.debug("Reading history index " + str(time.time()))
with open(fname, "r") as f:
for i in f.readlines():
if ',' in i:
k, v = i.strip().split(',', 2)
tmp_history[k] = v
tmp_history = dict(i.strip().split(',', 2) for i in f.readlines())
if len(tmp_history):
self.__newest_history_key = list(tmp_history.keys())[-1]
@@ -164,30 +151,28 @@ class model(dict):
import uuid
import logging
output_path = os.path.join(self.__datastore_path, self['uuid'])
output_path = "{}/{}".format(self.__datastore_path, self['uuid'])
self.ensure_data_dir_exists()
snapshot_fname = os.path.join(output_path, str(uuid.uuid4()))
snapshot_fname = "{}/{}.stripped.txt".format(output_path, uuid.uuid4())
logging.debug("Saving history text {}".format(snapshot_fname))
# in /diff/ and /preview/ we are going to assume for now that it's UTF-8 when reading
# most sites are utf-8 and some are even broken utf-8
with open(snapshot_fname, 'wb') as f:
f.write(contents)
f.close()
# Append to index
# @todo check last char was \n
index_fname = os.path.join(output_path, "history.txt")
index_fname = "{}/history.txt".format(output_path)
with open(index_fname, 'a') as f:
f.write("{},{}\n".format(timestamp, snapshot_fname))
f.close()
self.__newest_history_key = timestamp
self.__history_n += 1
self.__history_n+=1
# @todo bump static cache of the last timestamp so we dont need to examine the file to set a proper ''viewed'' status
#@todo bump static cache of the last timestamp so we dont need to examine the file to set a proper ''viewed'' status
return snapshot_fname
@property

View File

@@ -9,8 +9,6 @@
# exit when any command fails
set -e
SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
find tests/test_*py -type f|while read test_name
do
echo "TEST RUNNING $test_name"
@@ -25,13 +23,6 @@ export BASE_URL="https://really-unique-domain.io"
pytest tests/test_notification.py
## JQ + JSON: filter test
# jq is not available on windows and we should just test it when the package is installed
# this will re-test with jq support
pip3 install jq~=1.3
pytest tests/test_jsonpath_jq_selector.py
# Now for the selenium and playwright/browserless fetchers
# Note - this is not UI functional tests - just checking that each one can fetch the content
@@ -47,9 +38,7 @@ docker kill $$-test_selenium
echo "TESTING WEBDRIVER FETCH > PLAYWRIGHT/BROWSERLESS..."
# Not all platforms support playwright (not ARM/rPI), so it's not packaged in requirements.txt
PLAYWRIGHT_VERSION=$(grep -i -E "RUN pip install.+" "$SCRIPT_DIR/../Dockerfile" | grep --only-matching -i -E "playwright[=><~+]+[0-9\.]+")
echo "using $PLAYWRIGHT_VERSION"
pip3 install "$PLAYWRIGHT_VERSION"
pip3 install playwright~=1.24
docker run -d --name $$-test_browserless -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm -p 3000:3000 --shm-size="2g" browserless/chrome:1.53-chrome-stable
# takes a while to spin up
sleep 5

View File

@@ -30,14 +30,14 @@ class ChangeDetectionStore:
def __init__(self, datastore_path="/datastore", include_default_watches=True, version_tag="0.0.0"):
# Should only be active for docker
# logging.basicConfig(filename='/dev/stdout', level=logging.INFO)
self.__data = App.model()
self.needs_write = False
self.datastore_path = datastore_path
self.json_store_path = "{}/url-watches.json".format(self.datastore_path)
self.needs_write = False
self.proxy_list = None
self.start_time = time.time()
self.stop_thread = False
self.__data = App.model()
# Base definition for all watchers
# deepcopy part of #569 - not sure why its needed exactly
self.generic_definition = deepcopy(Watch.model(datastore_path = datastore_path, default={}))

View File

@@ -40,8 +40,7 @@
<fieldset>
<div class="pure-control-group">
{{ render_field(form.url, placeholder="https://...", required=true, class="m-d") }}
<span class="pure-form-message-inline">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></span><br/>
<span class="pure-form-message-inline">You can use variables in the URL, perfect for inserting the current date and other logic, <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a></span><br/>
<span class="pure-form-message-inline">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></span>
</div>
<div class="pure-control-group">
{{ render_field(form.title, class="m-d") }}
@@ -185,14 +184,10 @@ User-Agent: wonderbra 1.0") }}
<span class="pure-form-message-inline">
<ul>
<li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
<li>JSON - Limit text to this JSON rule, using either <a href="https://pypi.org/project/jsonpath-ng/" target="new">JSONPath</a> or <a href="https://stedolan.github.io/jq/" target="new">jq</a> (if installed).
<li>JSON - Limit text to this JSON rule, using either <a href="https://pypi.org/project/jsonpath-ng/" target="new">JSONPath</a> or <a href="https://stedolan.github.io/jq/" target="new">jq</a>.
<ul>
<li>JSONPath: Prefix with <code>json:</code>, use <code>json:$</code> to force re-formatting if required, <a href="https://jsonpath.com/" target="new">test your JSONPath here</a>.</li>
{% if jq_support %}
<li>jq: Prefix with <code>jq:</code> and <a href="https://jqplay.org/" target="new">test your jq here</a>. Using <a href="https://stedolan.github.io/jq/" target="new">jq</a> allows for complex filtering and processing of JSON data with built-in functions, regex, filtering, and more. See examples and documentation <a href="https://stedolan.github.io/jq/manual/" target="new">here</a>.</li>
{% else %}
<li>jq support not installed</li>
{% endif %}
</ul>
</li>
<li>XPath - Limit text to this XPath rule, simply start with a forward-slash,
@@ -203,7 +198,7 @@ User-Agent: wonderbra 1.0") }}
</ul>
</li>
</ul>
Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath{% if jq_support %}, or jq selector{%endif%} rules before filing an issue on GitHub! <a
Please be sure that you thoroughly understand how to write CSS, JSONPath, XPath, or jq selector rules before filing an issue on GitHub! <a
href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br/>
</span>
</div>

View File

@@ -87,7 +87,7 @@
<a class="state-{{'on' if watch.notification_muted}}" href="{{url_for('index', op='mute', uuid=watch.uuid, tag=active_tag)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications"/></a>
</td>
<td class="title-col inline">{{watch.title if watch.title is not none and watch.title|length > 0 else watch.url}}
<a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}"></a>
<a class="external" target="_blank" rel="noopener" href="{{ watch.url.replace('source:','') }}"></a>
<a href="{{url_for('form_share_put_watch', uuid=watch.uuid)}}"><img style="height: 1em;display:inline-block;" src="{{url_for('static_content', group='images', filename='spread.svg')}}" /></a>
{%if watch.fetch_backend == "html_webdriver" %}<img style="height: 1em; display:inline-block;" src="{{url_for('static_content', group='images', filename='Google-Chrome-icon.png')}}" />{% endif %}

View File

@@ -147,16 +147,6 @@ def test_api_simple(client, live_server):
# @todo how to handle None/default global values?
assert watch['history_n'] == 2, "Found replacement history section, which is in its own API"
# basic systeminfo check
res = client.get(
url_for("systeminfo"),
headers={'x-api-key': api_key},
)
info = json.loads(res.data)
assert info.get('watch_count') == 1
assert info.get('uptime') > 0.5
# Finally delete the watch
res = client.delete(
url_for("watch", uuid=watch_uuid),

View File

@@ -1,33 +0,0 @@
#!/usr/bin/python3
import time
from flask import url_for
from .util import live_server_setup
# If there was only a change in the whitespacing, then we shouldnt have a change detected
def test_jinja2_in_url_query(client, live_server):
live_server_setup(live_server)
# Give the endpoint time to spin up
time.sleep(1)
# Add our URL to the import page
test_url = url_for('test_return_query', _external=True)
# because url_for() will URL-encode the var, but we dont here
full_url = "{}?{}".format(test_url,
"date={% now 'Europe/Berlin', '%Y' %}.{% now 'Europe/Berlin', '%m' %}.{% now 'Europe/Berlin', '%d' %}", )
res = client.post(
url_for("form_quick_watch_add"),
data={"url": full_url, "tag": "test"},
follow_redirects=True
)
assert b"Watch added" in res.data
time.sleep(3)
# It should report nothing found (no new 'unviewed' class)
res = client.get(
url_for("preview_page", uuid="first"),
follow_redirects=True
)
assert b'date=2' in res.data

View File

@@ -5,12 +5,7 @@ import time
from flask import url_for, escape
from . util import live_server_setup
import pytest
jq_support = True
try:
import jq
except ModuleNotFoundError:
jq_support = False
def test_setup(live_server):
live_server_setup(live_server)
@@ -45,14 +40,13 @@ and it can also be repeated
assert text == "23.5"
# also check for jq
if jq_support:
text = html_tools.extract_json_as_string(content, "jq:.offers.price")
assert text == "23.5"
text = html_tools.extract_json_as_string('{"id":5}', "jq:.id")
text = html_tools.extract_json_as_string('{"id":5}', "json:$.id")
assert text == "5"
text = html_tools.extract_json_as_string('{"id":5}', "json:$.id")
text = html_tools.extract_json_as_string('{"id":5}', "jq:.id")
assert text == "5"
# When nothing at all is found, it should throw JSONNOTFound
@@ -60,7 +54,6 @@ and it can also be repeated
with pytest.raises(html_tools.JSONNotFound) as e_info:
html_tools.extract_json_as_string('COMPLETE GIBBERISH, NO JSON!', "json:$.id")
if jq_support:
with pytest.raises(html_tools.JSONNotFound) as e_info:
html_tools.extract_json_as_string('COMPLETE GIBBERISH, NO JSON!', "jq:.id")
@@ -278,7 +271,6 @@ def test_check_jsonpath_filter(client, live_server):
check_json_filter('json:boss.name', client, live_server)
def test_check_jq_filter(client, live_server):
if jq_support:
check_json_filter('jq:.boss.name', client, live_server)
def check_json_filter_bool_val(json_filter, client, live_server):
@@ -337,7 +329,6 @@ def test_check_jsonpath_filter_bool_val(client, live_server):
check_json_filter_bool_val("json:$['available']", client, live_server)
def test_check_jq_filter_bool_val(client, live_server):
if jq_support:
check_json_filter_bool_val("jq:.available", client, live_server)
# Re #265 - Extended JSON selector test
@@ -417,5 +408,4 @@ def test_check_jsonpath_ext_filter(client, live_server):
check_json_ext_filter('json:$[?(@.status==Sold)]', client, live_server)
def test_check_jq_ext_filter(client, live_server):
if jq_support:
check_json_ext_filter('jq:.[] | select(.status | contains("Sold"))', client, live_server)

View File

@@ -159,10 +159,5 @@ def live_server_setup(live_server):
ret = " ".join([auth.username, auth.password, auth.type])
return ret
# Just return some GET var
@live_server.app.route('/test-return-query', methods=['GET'])
def test_return_query():
return request.query_string
live_server.start()

View File

@@ -13,9 +13,9 @@ def test_visual_selector_content_ready(client, live_server):
live_server_setup(live_server)
time.sleep(1)
# Add our URL to the import page, because the docker container (playwright/selenium) wont be able to connect to our usual test url
test_url = "https://changedetection.io/ci-test/test-runjs.html"
# Add our URL to the import page, maybe better to use something we control?
# We use an external URL because the docker container is too difficult to setup to connect back to the pytest socket
test_url = 'https://news.ycombinator.com'
res = client.post(
url_for("form_quick_watch_add"),
data={"url": test_url, "tag": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
@@ -25,27 +25,13 @@ def test_visual_selector_content_ready(client, live_server):
res = client.post(
url_for("edit_page", uuid="first", unpause_on_save=1),
data={
"url": test_url,
"tag": "",
"headers": "",
'fetch_backend': "html_webdriver",
'webdriver_js_execute_code': 'document.querySelector("button[name=test-button]").click();'
},
data={"css_filter": ".does-not-exist", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_webdriver"},
follow_redirects=True
)
assert b"unpaused" in res.data
time.sleep(1)
wait_for_all_checks(client)
uuid = extract_UUID_from_client(client)
# Check the JS execute code before extract worked
res = client.get(
url_for("preview_page", uuid="first"),
follow_redirects=True
)
assert b'I smell JavaScript' in res.data
assert os.path.isfile(os.path.join('test-datastore', uuid, 'last-screenshot.png')), "last-screenshot.png should exist"
assert os.path.isfile(os.path.join('test-datastore', uuid, 'elements.json')), "xpath elements.json data should exist"

View File

@@ -45,9 +45,6 @@ services:
# Respect proxy_pass type settings, `proxy_set_header Host "localhost";` and `proxy_set_header X-Forwarded-Prefix /app;`
# More here https://github.com/dgtlmoon/changedetection.io/wiki/Running-changedetection.io-behind-a-reverse-proxy-sub-directory
# - USE_X_SETTINGS=1
#
# Hides the `Referer` header so that monitored websites can't see the changedetection.io hostname.
# - HIDE_REFERER=true
# Comment out ports: when using behind a reverse proxy , enable networks: etc.
ports:

View File

@@ -1,8 +1,8 @@
flask ~= 2.0
flask~= 2.0
flask_wtf
eventlet >= 0.31.0
eventlet>=0.31.0
validators
timeago ~= 1.0
timeago ~=1.0
inscriptis ~= 2.2
feedgen ~= 0.9
flask-login ~= 0.5
@@ -19,8 +19,7 @@ chardet > 2.3.0
wtforms ~= 3.0
jsonpath-ng ~= 1.5.3
# jq not available on Windows so must be installed manually
jq ~= 1.3.0
# Notification library
apprise ~= 1.1.0
@@ -46,9 +45,4 @@ selenium ~= 4.1.0
# need to revisit flask login versions
werkzeug ~= 2.0.0
# Templating, so far just in the URLs but in the future can be for the notifications also
jinja2 ~= 3.1
jinja2-time
# playwright is installed at Dockerfile build time because it's not available on all platforms