Compare commits

..

4 Commits

Author SHA1 Message Date
dgtlmoon
ac1b5ee6f7 Update wiki link for 'More info' about sharing a watch and its configuration 2022-05-17 22:43:56 +02:00
dgtlmoon
aca6c753bf skip JSON 2022-05-17 22:12:37 +02:00
dgtlmoon
efae86c134 small cleanups 2022-05-17 22:06:20 +02:00
dgtlmoon
0f72471343 Option to control if pages with no renderable content are a change (like JS webapps that dont render any text sometimes etc) 2022-05-17 22:03:18 +02:00
53 changed files with 252 additions and 2838 deletions

View File

@@ -36,14 +36,11 @@ from flask import (
url_for,
)
from flask_login import login_required
from flask_restful import abort, Api
from flask_wtf import CSRFProtect
from changedetectionio import html_tools
from changedetectionio.api import api_v1
__version__ = '0.39.14'
__version__ = '0.39.13.1'
datastore = None
@@ -81,8 +78,6 @@ csrf.init_app(app)
notification_debug_log=[]
watch_api = Api(app, decorators=[csrf.exempt])
def init_app_secret(datastore_path):
secret = ""
@@ -184,25 +179,6 @@ def changedetection_app(config=None, datastore_o=None):
login_manager.login_view = 'login'
app.secret_key = init_app_secret(config['datastore_path'])
watch_api.add_resource(api_v1.WatchSingleHistory,
'/api/v1/watch/<string:uuid>/history/<string:timestamp>',
resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
watch_api.add_resource(api_v1.WatchHistory,
'/api/v1/watch/<string:uuid>/history',
resource_class_kwargs={'datastore': datastore})
watch_api.add_resource(api_v1.CreateWatch, '/api/v1/watch',
resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
watch_api.add_resource(api_v1.Watch, '/api/v1/watch/<string:uuid>',
resource_class_kwargs={'datastore': datastore, 'update_q': update_q})
# Setup cors headers to allow all domains
# https://flask-cors.readthedocs.io/en/latest/
# CORS(app)
@@ -391,8 +367,6 @@ def changedetection_app(config=None, datastore_o=None):
if limit_tag != None:
# Support for comma separated list of tags.
if watch['tag'] is None:
continue
for tag_in_watch in watch['tag'].split(','):
tag_in_watch = tag_in_watch.strip()
if tag_in_watch == limit_tag:
@@ -546,9 +520,16 @@ def changedetection_app(config=None, datastore_o=None):
# Defaults for proxy choice
if datastore.proxy_list is not None: # When enabled
# Radio needs '' not None, or incase that the chosen one no longer exists
if default['proxy'] is None or not any(default['proxy'] in tup for tup in datastore.proxy_list):
default['proxy'] = ''
system_proxy = datastore.data['settings']['requests']['proxy']
if default['proxy'] is None:
default['proxy'] = system_proxy
else:
# Does the chosen one exist?
if not any(default['proxy'] in tup for tup in datastore.proxy_list):
default['proxy'] = datastore.proxy_list[0][0]
# Used by the form handler to keep or remove the proxy settings
default['proxy_list'] = datastore.proxy_list
# proxy_override set to the json/text list of the items
form = forms.watchForm(formdata=request.form if request.method == 'POST' else None,
@@ -559,7 +540,9 @@ def changedetection_app(config=None, datastore_o=None):
# @todo - Couldn't get setattr() etc dynamic addition working, so remove it instead
del form.proxy
else:
form.proxy.choices = [('', 'Default')] + datastore.proxy_list
form.proxy.choices = datastore.proxy_list
if default['proxy'] is None:
form.proxy.default='http://hello'
if request.method == 'POST' and form.validate():
extra_update_obj = {}
@@ -596,10 +579,6 @@ def changedetection_app(config=None, datastore_o=None):
if len(datastore.data['watching'][uuid]['history']):
extra_update_obj['previous_md5'] = get_current_checksum_include_ignore_text(uuid=uuid)
# Be sure proxy value is None
if datastore.proxy_list is not None and form.data['proxy'] == '':
extra_update_obj['proxy'] = None
datastore.data['watching'][uuid].update(form.data)
datastore.data['watching'][uuid].update(extra_update_obj)
@@ -626,12 +605,6 @@ def changedetection_app(config=None, datastore_o=None):
if request.method == 'POST' and not form.validate():
flash("An error occurred, please see below.", "error")
visualselector_data_is_ready = datastore.visualselector_data_is_ready(uuid)
# Only works reliably with Playwright
visualselector_enabled = os.getenv('PLAYWRIGHT_DRIVER_URL', False) and default['fetch_backend'] == 'html_webdriver'
output = render_template("edit.html",
uuid=uuid,
watch=datastore.data['watching'][uuid],
@@ -639,9 +612,7 @@ def changedetection_app(config=None, datastore_o=None):
has_empty_checktime=using_default_check_time,
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),
visualselector_data_is_ready=visualselector_data_is_ready,
visualselector_enabled=visualselector_enabled
emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False)
)
return output
@@ -705,7 +676,6 @@ def changedetection_app(config=None, datastore_o=None):
form=form,
current_base_url = datastore.data['settings']['application']['base_url'],
hide_remove_pass=os.getenv("SALTED_PASS", False),
api_key=datastore.data['settings']['application'].get('api_access_token'),
emailprefix=os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False))
return output
@@ -904,6 +874,27 @@ def changedetection_app(config=None, datastore_o=None):
return output
@app.route("/api/<string:uuid>/snapshot/current", methods=['GET'])
@login_required
def api_snapshot(uuid):
# More for testing, possible to return the first/only
if uuid == 'first':
uuid = list(datastore.data['watching'].keys()).pop()
try:
watch = datastore.data['watching'][uuid]
except KeyError:
return abort(400, "No history found for the specified link, bad link?")
newest = list(watch['history'].keys())[-1]
with open(watch['history'][newest], 'r') as f:
content = f.read()
resp = make_response(content)
resp.headers['Content-Type'] = 'text/plain'
return resp
@app.route("/favicon.ico", methods=['GET'])
def favicon():
return send_from_directory("static/images", path="favicon.ico")
@@ -984,9 +975,10 @@ def changedetection_app(config=None, datastore_o=None):
@app.route("/static/<string:group>/<string:filename>", methods=['GET'])
def static_content(group, filename):
from flask import make_response
if group == 'screenshot':
from flask import make_response
# Could be sensitive, follow password requirements
if datastore.data['settings']['application']['password'] and not flask_login.current_user.is_authenticated:
abort(403)
@@ -1005,26 +997,6 @@ def changedetection_app(config=None, datastore_o=None):
except FileNotFoundError:
abort(404)
if group == 'visual_selector_data':
# Could be sensitive, follow password requirements
if datastore.data['settings']['application']['password'] and not flask_login.current_user.is_authenticated:
abort(403)
# These files should be in our subdirectory
try:
# set nocache, set content-type
watch_dir = datastore_o.datastore_path + "/" + filename
response = make_response(send_from_directory(filename="elements.json", directory=watch_dir, path=watch_dir + "/elements.json"))
response.headers['Content-type'] = 'application/json'
response.headers['Cache-Control'] = 'no-cache, no-store, must-revalidate'
response.headers['Pragma'] = 'no-cache'
response.headers['Expires'] = 0
return response
except FileNotFoundError:
abort(404)
# These files should be in our subdirectory
try:
return send_from_directory("static/{}".format(group), path=filename)
@@ -1033,7 +1005,7 @@ def changedetection_app(config=None, datastore_o=None):
@app.route("/api/add", methods=['POST'])
@login_required
def form_watch_add():
def api_watch_add():
from changedetectionio import forms
form = forms.quickWatchForm(request.form)
@@ -1059,7 +1031,7 @@ def changedetection_app(config=None, datastore_o=None):
@app.route("/api/delete", methods=['GET'])
@login_required
def form_delete():
def api_delete():
uuid = request.args.get('uuid')
if uuid != 'all' and not uuid in datastore.data['watching'].keys():
@@ -1076,7 +1048,7 @@ def changedetection_app(config=None, datastore_o=None):
@app.route("/api/clone", methods=['GET'])
@login_required
def form_clone():
def api_clone():
uuid = request.args.get('uuid')
# More for testing, possible to return the first/only
if uuid == 'first':
@@ -1090,7 +1062,7 @@ def changedetection_app(config=None, datastore_o=None):
@app.route("/api/checknow", methods=['GET'])
@login_required
def form_watch_checknow():
def api_watch_checknow():
tag = request.args.get('tag')
uuid = request.args.get('uuid')
@@ -1127,7 +1099,7 @@ def changedetection_app(config=None, datastore_o=None):
@app.route("/api/share-url", methods=['GET'])
@login_required
def form_share_put_watch():
def api_share_put_watch():
"""Given a watch UUID, upload the info and return a share-link
the share-link can be imported/added"""
import requests
@@ -1177,6 +1149,7 @@ def changedetection_app(config=None, datastore_o=None):
# paste in etc
return redirect(url_for('index'))
# @todo handle ctrl break
ticker_thread = threading.Thread(target=ticker_thread_check_time_launch_checks).start()

View File

@@ -1,125 +0,0 @@
from flask_restful import abort, Resource
from flask import request, make_response
import validators
from . import auth
# https://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html
class Watch(Resource):
def __init__(self, **kwargs):
# datastore is a black box dependency
self.datastore = kwargs['datastore']
self.update_q = kwargs['update_q']
# Get information about a single watch, excluding the history list (can be large)
# curl http://localhost:4000/api/v1/watch/<string:uuid>
# ?recheck=true
@auth.check_token
def get(self, uuid):
from copy import deepcopy
watch = deepcopy(self.datastore.data['watching'].get(uuid))
if not watch:
abort(404, message='No watch exists with the UUID of {}'.format(uuid))
if request.args.get('recheck'):
self.update_q.put(uuid)
return "OK", 200
# Return without history, get that via another API call
watch['history_n'] = len(watch['history'])
del (watch['history'])
return watch
@auth.check_token
def delete(self, uuid):
if not self.datastore.data['watching'].get(uuid):
abort(400, message='No watch exists with the UUID of {}'.format(uuid))
self.datastore.delete(uuid)
return 'OK', 204
class WatchHistory(Resource):
def __init__(self, **kwargs):
# datastore is a black box dependency
self.datastore = kwargs['datastore']
# Get a list of available history for a watch by UUID
# curl http://localhost:4000/api/v1/watch/<string:uuid>/history
def get(self, uuid):
watch = self.datastore.data['watching'].get(uuid)
if not watch:
abort(404, message='No watch exists with the UUID of {}'.format(uuid))
return watch['history'], 200
class WatchSingleHistory(Resource):
def __init__(self, **kwargs):
# datastore is a black box dependency
self.datastore = kwargs['datastore']
# Read a given history snapshot and return its content
# <string:timestamp> or "latest"
# curl http://localhost:4000/api/v1/watch/<string:uuid>/history/<int:timestamp>
@auth.check_token
def get(self, uuid, timestamp):
watch = self.datastore.data['watching'].get(uuid)
if not watch:
abort(404, message='No watch exists with the UUID of {}'.format(uuid))
if not len(watch['history']):
abort(404, message='Watch found but no history exists for the UUID {}'.format(uuid))
if timestamp == 'latest':
timestamp = list(watch['history'].keys())[-1]
with open(watch['history'][timestamp], 'r') as f:
content = f.read()
response = make_response(content, 200)
response.mimetype = "text/plain"
return response
class CreateWatch(Resource):
def __init__(self, **kwargs):
# datastore is a black box dependency
self.datastore = kwargs['datastore']
self.update_q = kwargs['update_q']
@auth.check_token
def post(self):
# curl http://localhost:4000/api/v1/watch -H "Content-Type: application/json" -d '{"url": "https://my-nice.com", "tag": "one, two" }'
json_data = request.get_json()
tag = json_data['tag'].strip() if json_data.get('tag') else ''
if not validators.url(json_data['url'].strip()):
return "Invalid or unsupported URL", 400
extras = {'title': json_data['title'].strip()} if json_data.get('title') else {}
new_uuid = self.datastore.add_watch(url=json_data['url'].strip(), tag=tag, extras=extras)
self.update_q.put(new_uuid)
return {'uuid': new_uuid}, 201
# Return concise list of available watches and some very basic info
# curl http://localhost:4000/api/v1/watch|python -mjson.tool
# ?recheck_all=1 to recheck all
@auth.check_token
def get(self):
list = {}
for k, v in self.datastore.data['watching'].items():
list[k] = {'url': v['url'],
'title': v['title'],
'last_checked': v['last_checked'],
'last_changed': v['last_changed'],
'last_error': v['last_error']}
if request.args.get('recheck_all'):
for uuid in self.datastore.data['watching'].keys():
self.update_q.put(uuid)
return {'status': "OK"}, 200
return list, 200

View File

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

View File

@@ -27,117 +27,6 @@ class Fetcher():
status_code = None
content = None
headers = None
fetcher_description = "No description"
xpath_element_js = """
// Include the getXpath script directly, easier than fetching
!function(e,n){"object"==typeof exports&&"undefined"!=typeof module?module.exports=n():"function"==typeof define&&define.amd?define(n):(e=e||self).getXPath=n()}(this,function(){return function(e){var n=e;if(n&&n.id)return'//*[@id="'+n.id+'"]';for(var o=[];n&&Node.ELEMENT_NODE===n.nodeType;){for(var i=0,r=!1,d=n.previousSibling;d;)d.nodeType!==Node.DOCUMENT_TYPE_NODE&&d.nodeName===n.nodeName&&i++,d=d.previousSibling;for(d=n.nextSibling;d;){if(d.nodeName===n.nodeName){r=!0;break}d=d.nextSibling}o.push((n.prefix?n.prefix+":":"")+n.localName+(i||r?"["+(i+1)+"]":"")),n=n.parentNode}return o.length?"/"+o.reverse().join("/"):""}});
const findUpTag = (el) => {
let r = el
chained_css = [];
depth=0;
// Strategy 1: Keep going up until we hit an ID tag, imagine it's like #list-widget div h4
while (r.parentNode) {
if(depth==5) {
break;
}
if('' !==r.id) {
chained_css.unshift("#"+r.id);
final_selector= chained_css.join('>');
// Be sure theres only one, some sites have multiples of the same ID tag :-(
if (window.document.querySelectorAll(final_selector).length ==1 ) {
return final_selector;
}
return null;
} else {
chained_css.unshift(r.tagName.toLowerCase());
}
r=r.parentNode;
depth+=1;
}
return null;
}
// @todo - if it's SVG or IMG, go into image diff mode
var elements = window.document.querySelectorAll("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");
var size_pos=[];
// after page fetch, inject this JS
// build a map of all elements and their positions (maybe that only include text?)
var bbox;
for (var i = 0; i < elements.length; i++) {
bbox = elements[i].getBoundingClientRect();
// forget really small ones
if (bbox['width'] <20 && bbox['height'] < 20 ) {
continue;
}
// @todo the getXpath kind of sucks, it doesnt know when there is for example just one ID sometimes
// it should not traverse when we know we can anchor off just an ID one level up etc..
// maybe, get current class or id, keep traversing up looking for only class or id until there is just one match
// 1st primitive - if it has class, try joining it all and select, if theres only one.. well thats us.
xpath_result=false;
try {
var d= findUpTag(elements[i]);
if (d) {
xpath_result =d;
}
} catch (e) {
var x=1;
}
// You could swap it and default to getXpath and then try the smarter one
// default back to the less intelligent one
if (!xpath_result) {
xpath_result = getXPath(elements[i]);
}
if(window.getComputedStyle(elements[i]).visibility === "hidden") {
continue;
}
size_pos.push({
xpath: xpath_result,
width: Math.round(bbox['width']),
height: Math.round(bbox['height']),
left: Math.floor(bbox['left']),
top: Math.floor(bbox['top']),
childCount: elements[i].childElementCount
});
}
// inject the current one set in the css_filter, which may be a CSS rule
// used for displaying the current one in VisualSelector, where its not one we generated.
if (css_filter.length) {
// is it xpath?
if (css_filter.startsWith('/') ) {
q=document.evaluate(css_filter, document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;
} else {
q=document.querySelector(css_filter);
}
bbox = q.getBoundingClientRect();
if (bbox && bbox['width'] >0 && bbox['height']>0) {
size_pos.push({
xpath: css_filter,
width: bbox['width'],
height: bbox['height'],
left: bbox['left'],
top: bbox['top'],
childCount: q.childElementCount
});
}
}
// https://stackoverflow.com/questions/1145850/how-to-get-height-of-entire-document-with-javascript
return {'size_pos':size_pos, 'browser_width': window.innerWidth, 'browser_height':document.body.scrollHeight};
"""
xpath_data = None
# Will be needed in the future by the VisualSelector, always get this where possible.
screenshot = False
fetcher_description = "No description"
@@ -158,8 +47,7 @@ class Fetcher():
request_headers,
request_body,
request_method,
ignore_status_codes=False,
current_css_filter=None):
ignore_status_codes=False):
# Should set self.error, self.status_code and self.content
pass
@@ -240,8 +128,7 @@ class base_html_playwright(Fetcher):
request_headers,
request_body,
request_method,
ignore_status_codes=False,
current_css_filter=None):
ignore_status_codes=False):
from playwright.sync_api import sync_playwright
import playwright._impl._api_types
@@ -261,8 +148,8 @@ class base_html_playwright(Fetcher):
proxy=self.proxy
)
page = context.new_page()
page.set_viewport_size({"width": 1280, "height": 1024})
try:
# Bug - never set viewport size BEFORE page.goto
response = page.goto(url, timeout=timeout * 1000, wait_until='commit')
# Wait_until = commit
# - `'commit'` - consider operation to be finished when network response is received and the document started loading.
@@ -279,27 +166,14 @@ class base_html_playwright(Fetcher):
if len(page.content().strip()) == 0:
raise EmptyReply(url=url, status_code=None)
# Bug 2(?) Set the viewport size AFTER loading the page
page.set_viewport_size({"width": 1280, "height": 1024})
# Bugish - Let the page redraw/reflow
page.set_viewport_size({"width": 1280, "height": 1024})
self.status_code = response.status
self.content = page.content()
self.headers = response.all_headers()
if current_css_filter is not None:
page.evaluate("var css_filter='{}'".format(current_css_filter))
else:
page.evaluate("var css_filter=''")
self.xpath_data = page.evaluate("async () => {" + self.xpath_element_js + "}")
# Bug 3 in Playwright screenshot handling
# Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
# JPEG is better here because the screenshots can be very very large
page.screenshot(type='jpeg', clip={'x': 1.0, 'y': 1.0, 'width': 1280, 'height': 1024})
self.screenshot = page.screenshot(type='jpeg', full_page=True, quality=92)
self.screenshot = page.screenshot(type='jpeg', full_page=True, quality=90)
context.close()
browser.close()
@@ -351,8 +225,7 @@ class base_html_webdriver(Fetcher):
request_headers,
request_body,
request_method,
ignore_status_codes=False,
current_css_filter=None):
ignore_status_codes=False):
from selenium import webdriver
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
@@ -372,10 +245,6 @@ class base_html_webdriver(Fetcher):
self.quit()
raise
self.driver.set_window_size(1280, 1024)
self.driver.implicitly_wait(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)))
self.screenshot = self.driver.get_screenshot_as_png()
# @todo - how to check this? is it possible?
self.status_code = 200
# @todo somehow we should try to get this working for WebDriver
@@ -385,6 +254,8 @@ class base_html_webdriver(Fetcher):
time.sleep(int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay)
self.content = self.driver.page_source
self.headers = {}
self.screenshot = self.driver.get_screenshot_as_png()
self.quit()
# Does the connection to the webdriver work? run a test connection.
def is_ready(self):
@@ -421,8 +292,7 @@ class html_requests(Fetcher):
request_headers,
request_body,
request_method,
ignore_status_codes=False,
current_css_filter=None):
ignore_status_codes=False):
proxies={}

View File

@@ -94,7 +94,6 @@ class perform_site_check():
# If the klass doesnt exist, just use a default
klass = getattr(content_fetcher, "html_requests")
proxy_args = self.set_proxy_from_list(watch)
fetcher = klass(proxy_override=proxy_args)
@@ -105,8 +104,7 @@ class perform_site_check():
elif system_webdriver_delay is not None:
fetcher.render_extract_delay = system_webdriver_delay
fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_code, watch['css_filter'])
fetcher.quit()
fetcher.run(url, timeout, request_headers, request_body, request_method, ignore_status_code)
# Fetching complete, now filters
# @todo move to class / maybe inside of fetcher abstract base?
@@ -238,4 +236,4 @@ class perform_site_check():
if not watch['title'] or not len(watch['title']):
update_obj['title'] = html_tools.extract_element(find='title', html_content=fetcher.content)
return changed_detected, update_obj, text_content_before_ignored_filter, fetcher.screenshot, fetcher.xpath_data
return changed_detected, update_obj, text_content_before_ignored_filter, fetcher.screenshot

View File

@@ -374,7 +374,6 @@ class globalSettingsApplicationForm(commonSettingsForm):
empty_pages_are_a_change = BooleanField('Treat empty pages as a change?', default=False)
render_anchor_tag_content = BooleanField('Render anchor tag content', default=False)
fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
api_access_token_enabled = BooleanField('API access token security check enabled', default=True, validators=[validators.Optional()])
password = SaltyPasswordField()

View File

@@ -39,7 +39,7 @@ def element_removal(selectors: List[str], html_content):
def xpath_filter(xpath_filter, html_content):
from lxml import etree, html
tree = html.fromstring(bytes(html_content, encoding='utf-8'))
tree = html.fromstring(html_content)
html_block = ""
for item in tree.xpath(xpath_filter.strip(), namespaces={'re':'http://exslt.org/regular-expressions'}):

View File

@@ -27,7 +27,6 @@ class model(dict):
'proxy': None # Preferred proxy connection
},
'application': {
'api_access_token_enabled': True,
'password': False,
'base_url' : None,
'extract_title_as_title': False,

View File

@@ -22,26 +22,3 @@ echo "RUNNING WITH BASE_URL SET"
export BASE_URL="https://really-unique-domain.io"
pytest tests/test_notification.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
echo "TESTING WEBDRIVER FETCH > SELENIUM/WEBDRIVER..."
docker run -d --name $$-test_selenium -p 4444:4444 --rm --shm-size="2g" selenium/standalone-chrome-debug:3.141.59
# takes a while to spin up
sleep 5
export WEBDRIVER_URL=http://localhost:4444/wd/hub
pytest tests/fetchers/test_content.py
unset WEBDRIVER_URL
docker kill $$-test_selenium
echo "TESTING WEBDRIVER FETCH > PLAYWRIGHT/BROWSERLESS..."
# Not all platforms support playwright (not ARM/rPI), so it's not packaged in requirements.txt
pip3 install playwright~=1.22
docker run -d --name $$-test_browserless -e "DEFAULT_LAUNCH_ARGS=[\"--window-size=1920,1080\"]" --rm -p 3000:3000 --shm-size="2g" browserless/chrome:1.53-chrome-stable
# takes a while to spin up
sleep 5
export PLAYWRIGHT_DRIVER_URL=ws://127.0.0.1:3000
pytest tests/fetchers/test_content.py
unset PLAYWRIGHT_DRIVER_URL
docker kill $$-test_browserless

Binary file not shown.

Before

Width:  |  Height:  |  Size: 6.2 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 12 KiB

View File

@@ -1,4 +1,4 @@
$(document).ready(function () {
$(document).ready(function() {
function toggle() {
if ($('input[name="application-fetch_backend"]:checked').val() != 'html_requests') {
$('#requests-override-options').hide();
@@ -8,29 +8,9 @@ $(document).ready(function () {
$('#webdriver-override-options').hide();
}
}
$('input[name="application-fetch_backend"]').click(function (e) {
toggle();
});
toggle();
$("#api-key").hover(
function () {
$("#api-key-copy").html('copy').fadeIn();
},
function () {
$("#api-key-copy").hide();
}
).click(function (e) {
$("#api-key-copy").html('copied');
var range = document.createRange();
var n = $("#api-key")[0];
range.selectNode(n);
window.getSelection().removeAllRanges();
window.getSelection().addRange(range);
document.execCommand("copy");
window.getSelection().removeAllRanges();
});
});

View File

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

View File

@@ -1,219 +0,0 @@
// Horrible proof of concept code :)
// yes - this is really a hack, if you are a front-ender and want to help, please get in touch!
$(document).ready(function() {
$('#visualselector-tab').click(function () {
$("img#selector-background").off('load');
bootstrap_visualselector();
});
$(document).on('keydown', function(event) {
if ($("img#selector-background").is(":visible")) {
if (event.key == "Escape") {
state_clicked=false;
ctx.clearRect(0, 0, c.width, c.height);
}
}
});
// For when the page loads
if(!window.location.hash || window.location.hash != '#visualselector') {
$("img#selector-background").attr('src','');
return;
}
// Handle clearing button/link
$('#clear-selector').on('click', function(event) {
if(!state_clicked) {
alert('Oops, Nothing selected!');
}
state_clicked=false;
ctx.clearRect(0, 0, c.width, c.height);
});
bootstrap_visualselector();
var current_selected_i;
var state_clicked=false;
var c;
// greyed out fill context
var xctx;
// redline highlight context
var ctx;
var current_default_xpath;
var x_scale=1;
var y_scale=1;
var selector_image;
var selector_image_rect;
var vh;
var selector_data;
function bootstrap_visualselector() {
if ( 1 ) {
// bootstrap it, this will trigger everything else
$("img#selector-background").bind('load', function () {
console.log("Loaded background...");
c = document.getElementById("selector-canvas");
// greyed out fill context
xctx = c.getContext("2d");
// redline highlight context
ctx = c.getContext("2d");
current_default_xpath =$("#css_filter").val();
fetch_data();
$('#selector-canvas').off("mousemove");
// screenshot_url defined in the edit.html template
}).attr("src", screenshot_url);
}
}
function fetch_data() {
// Image is ready
$('.fetching-update-notice').html("Fetching element data..");
$.ajax({
url: watch_visual_selector_data_url,
context: document.body
}).done(function (data) {
$('.fetching-update-notice').html("Rendering..");
selector_data = data;
console.log("Reported browser width from backend: "+data['browser_width']);
state_clicked=false;
set_scale();
reflow_selector();
$('.fetching-update-notice').fadeOut();
});
};
function set_scale() {
// some things to check if the scaling doesnt work
// - that the widths/sizes really are about the actual screen size cat elements.json |grep -o width......|sort|uniq
selector_image = $("img#selector-background")[0];
selector_image_rect = selector_image.getBoundingClientRect();
// make the canvas the same size as the image
$('#selector-canvas').attr('height', selector_image_rect.height);
$('#selector-canvas').attr('width', selector_image_rect.width);
$('#selector-wrapper').attr('width', selector_image_rect.width);
x_scale = selector_image_rect.width / selector_data['browser_width'];
y_scale = selector_image_rect.height / selector_image.naturalHeight;
ctx.strokeStyle = 'rgba(255,0,0, 0.9)';
ctx.fillStyle = 'rgba(255,0,0, 0.1)';
ctx.lineWidth = 3;
console.log("scaling set x: "+x_scale+" by y:"+y_scale);
$("#selector-current-xpath").css('max-width', selector_image_rect.width);
}
function reflow_selector() {
$(window).resize(function() {
set_scale();
highlight_current_selected_i();
});
var selector_currnt_xpath_text=$("#selector-current-xpath span");
set_scale();
console.log(selector_data['size_pos'].length + " selectors found");
// highlight the default one if we can find it in the xPath list
// or the xpath matches the default one
found = false;
if(current_default_xpath.length) {
for (var i = selector_data['size_pos'].length; i!==0; i--) {
var sel = selector_data['size_pos'][i-1];
if(selector_data['size_pos'][i - 1].xpath == current_default_xpath) {
console.log("highlighting "+current_default_xpath);
current_selected_i = i-1;
highlight_current_selected_i();
found = true;
break;
}
}
if(!found) {
alert("unfortunately your existing CSS/xPath Filter was no longer found!");
}
}
$('#selector-canvas').bind('mousemove', function (e) {
if(state_clicked) {
return;
}
ctx.clearRect(0, 0, c.width, c.height);
current_selected_i=null;
// Reverse order - the most specific one should be deeper/"laster"
// Basically, find the most 'deepest'
var found=0;
ctx.fillStyle = 'rgba(205,0,0,0.35)';
for (var i = selector_data['size_pos'].length; i!==0; i--) {
// draw all of them? let them choose somehow?
var sel = selector_data['size_pos'][i-1];
// If we are in a bounding-box
if (e.offsetY > sel.top * y_scale && e.offsetY < sel.top * y_scale + sel.height * y_scale
&&
e.offsetX > sel.left * y_scale && e.offsetX < sel.left * y_scale + sel.width * y_scale
) {
// FOUND ONE
set_current_selected_text(sel.xpath);
ctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
ctx.fillRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
// no need to keep digging
// @todo or, O to go out/up, I to go in
// or double click to go up/out the selector?
current_selected_i=i-1;
found+=1;
break;
}
}
}.debounce(5));
function set_current_selected_text(s) {
selector_currnt_xpath_text[0].innerHTML=s;
}
function highlight_current_selected_i() {
if(state_clicked) {
state_clicked=false;
xctx.clearRect(0,0,c.width, c.height);
return;
}
var sel = selector_data['size_pos'][current_selected_i];
if (sel[0] == '/') {
// @todo - not sure just checking / is right
$("#css_filter").val('xpath:'+sel.xpath);
} else {
$("#css_filter").val(sel.xpath);
}
xctx.fillStyle = 'rgba(205,205,205,0.95)';
xctx.strokeStyle = 'rgba(225,0,0,0.9)';
xctx.lineWidth = 3;
xctx.fillRect(0,0,c.width, c.height);
// Clear out what only should be seen (make a clear/clean spot)
xctx.clearRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
xctx.strokeRect(sel.left * x_scale, sel.top * y_scale, sel.width * x_scale, sel.height * y_scale);
state_clicked=true;
set_current_selected_text(sel.xpath);
}
$('#selector-canvas').bind('mousedown', function (e) {
highlight_current_selected_i();
});
}
});

View File

@@ -4,7 +4,6 @@ $(function () {
$(this).closest('.unviewed').removeClass('unviewed');
});
$('.with-share-link > *').click(function () {
$("#copied-clipboard").remove();
@@ -21,6 +20,5 @@ $(function () {
$(this).remove();
});
});
});

View File

@@ -284,11 +284,6 @@ footer {
.pure-form {
/* The input fields with errors */
/* The list of errors */ }
.pure-form fieldset {
padding-top: 0px; }
.pure-form fieldset ul {
padding-bottom: 0px;
margin-bottom: 0px; }
.pure-form .pure-control-group, .pure-form .pure-group, .pure-form .pure-controls {
padding-bottom: 1em; }
.pure-form .pure-control-group div, .pure-form .pure-group div, .pure-form .pure-controls div {
@@ -338,8 +333,7 @@ footer {
padding-top: 110px; }
div.tabs.collapsable ul li {
display: block;
border-radius: 0px;
margin-right: 0px; }
border-radius: 0px; }
input[type='text'] {
width: 100%; }
/*
@@ -430,15 +424,6 @@ and also iPads specifically.
.tab-pane-inner:target {
display: block; }
#beta-logo {
height: 50px;
right: -3px;
top: -3px;
position: absolute; }
#selector-header {
padding-bottom: 1em; }
.edit-form {
min-width: 70%;
/* so it cant overflow */
@@ -462,31 +447,4 @@ ul {
.time-check-widget tr {
display: inline; }
.time-check-widget tr input[type="number"] {
width: 5em; }
#selector-wrapper {
height: 600px;
overflow-y: scroll;
position: relative; }
#selector-wrapper > img {
position: absolute;
z-index: 4;
max-width: 100%; }
#selector-wrapper > canvas {
position: relative;
z-index: 5;
max-width: 100%; }
#selector-wrapper > canvas:hover {
cursor: pointer; }
#selector-current-xpath {
font-size: 80%; }
#webdriver-override-options input[type="number"] {
width: 5em; }
#api-key:hover {
cursor: pointer; }
#api-key-copy {
color: #0078e7; }
width: 4em; }

View File

@@ -375,13 +375,6 @@ footer {
.pure-form {
fieldset {
padding-top: 0px;
ul {
padding-bottom: 0px;
margin-bottom: 0px;
}
}
.pure-control-group, .pure-group, .pure-controls {
padding-bottom: 1em;
div {
@@ -469,7 +462,6 @@ footer {
div.tabs.collapsable ul li {
display: block;
border-radius: 0px;
margin-right: 0px;
}
input[type='text'] {
@@ -614,18 +606,6 @@ $form-edge-padding: 20px;
padding: 0px;
}
#beta-logo {
height: 50px;
// looks better when it's hanging off a little
right: -3px;
top: -3px;
position: absolute;
}
#selector-header {
padding-bottom: 1em;
}
.edit-form {
min-width: 70%;
/* so it cant overflow */
@@ -657,47 +637,7 @@ ul {
tr {
display: inline;
input[type="number"] {
width: 5em;
width: 4em;
}
}
}
#selector-wrapper {
height: 600px;
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"] {
width: 5em;
}
}
#api-key {
&:hover {
cursor: pointer;
}
}
#api-key-copy {
color: #0078e7;
}
}

View File

@@ -12,7 +12,6 @@ from os import mkdir, path, unlink
from threading import Lock
import re
import requests
import secrets
from . model import App, Watch
@@ -108,13 +107,10 @@ class ChangeDetectionStore:
# Generate the URL access token for RSS feeds
if not 'rss_access_token' in self.__data['settings']['application']:
import secrets
secret = secrets.token_hex(16)
self.__data['settings']['application']['rss_access_token'] = secret
# Generate the API access token
if not 'api_access_token' in self.__data['settings']['application']:
secret = secrets.token_hex(16)
self.__data['settings']['application']['api_access_token'] = secret
# Proxy list support - available as a selection in settings when text file is imported
# CSV list
@@ -215,8 +211,7 @@ class ChangeDetectionStore:
def get_all_tags(self):
tags = []
for uuid, watch in self.data['watching'].items():
if watch['tag'] is None:
continue
# Support for comma separated list of tags.
for tag in watch['tag'].split(','):
tag = tag.strip()
@@ -285,10 +280,6 @@ class ChangeDetectionStore:
def add_watch(self, url, tag="", extras=None, write_to_disk_now=True):
if extras is None:
extras = {}
# should always be str
if tag is None or not tag:
tag=''
# Incase these are copied across, assume it's a reference and deepcopy()
apply_extras = deepcopy(extras)
@@ -372,15 +363,6 @@ class ChangeDetectionStore:
return False
def visualselector_data_is_ready(self, watch_uuid):
output_path = "{}/{}".format(self.datastore_path, watch_uuid)
screenshot_filename = "{}/last-screenshot.png".format(output_path)
elements_index_filename = "{}/elements.json".format(output_path)
if path.isfile(screenshot_filename) and path.isfile(elements_index_filename) :
return True
return False
# Save as PNG, PNG is larger but better for doing visual diff in the future
def save_screenshot(self, watch_uuid, screenshot: bytes):
output_path = "{}/{}".format(self.datastore_path, watch_uuid)
@@ -389,14 +371,6 @@ class ChangeDetectionStore:
f.write(screenshot)
f.close()
def save_xpath_data(self, watch_uuid, data):
output_path = "{}/{}".format(self.datastore_path, watch_uuid)
fname = "{}/elements.json".format(output_path)
with open(fname, 'w') as f:
f.write(json.dumps(data))
f.close()
def sync_to_json(self):
logging.info("Saving JSON..")
print("Saving JSON..")

View File

@@ -39,6 +39,9 @@
<div class="tabs">
<ul>
<li class="tab" id="default-tab"><a href="#text">Text</a></li>
{% if screenshot %}
<li class="tab"><a href="#screenshot">Current screenshot</a></li>
{% endif %}
</ul>
</div>
@@ -60,6 +63,17 @@
</table>
Diff algorithm from the amazing <a href="https://github.com/kpdecker/jsdiff">github.com/kpdecker/jsdiff</a>
</div>
{% if screenshot %}
<div class="tab-pane-inner" id="screenshot">
<p>
<i>For now, only the most recent screenshot is saved and displayed.</i>
</p>
<img src="{{url_for('static_content', group='screenshot', filename=uuid)}}">
</div>
{% endif %}
</div>

View File

@@ -5,18 +5,12 @@
<script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
<script>
const notification_base_url="{{url_for('ajax_callback_send_notification_test')}}";
const watch_visual_selector_data_url="{{url_for('static_content', group='visual_selector_data', filename=uuid)}}";
const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
{% if emailprefix %}
const email_notification_prefix=JSON.parse('{{ emailprefix|tojson }}');
{% endif %}
</script>
<script type="text/javascript" src="{{url_for('static_content', group='js', filename='watch-settings.js')}}" defer></script>
<script type="text/javascript" src="{{url_for('static_content', group='js', filename='notifications.js')}}" defer></script>
<script type="text/javascript" src="{{url_for('static_content', group='js', filename='visual-selector.js')}}" defer></script>
<script type="text/javascript" src="{{url_for('static_content', group='js', filename='limit.js')}}" defer></script>
<div class="edit-form monospaced-textarea">
@@ -24,7 +18,6 @@
<ul>
<li class="tab" id="default-tab"><a href="#general">General</a></li>
<li class="tab"><a href="#request">Request</a></li>
<li class="tab"><a id="visualselector-tab" href="#visualselector">Visual Selector</a></li>
<li class="tab"><a href="#filters-and-triggers">Filters &amp; Triggers</a></li>
<li class="tab"><a href="#notifications">Notifications</a></li>
</ul>
@@ -80,7 +73,7 @@
</span>
</div>
{% endif %}
<fieldset id="webdriver-override-options">
<fieldset class="pure-group" id="webdriver-override-options">
<div class="pure-form-message-inline">
<strong>If you're having trouble waiting for the page to be fully rendered (text missing etc), try increasing the 'wait' time here.</strong>
<br/>
@@ -132,7 +125,8 @@ User-Agent: wonderbra 1.0") }}
</div>
<div class="tab-pane-inner" id="filters-and-triggers">
<div class="pure-control-group">
<fieldset>
<div class="pure-control-group">
<strong>Pro-tips:</strong><br/>
<ul>
<li>
@@ -143,6 +137,7 @@ User-Agent: wonderbra 1.0") }}
</li>
</ul>
</div>
<div class="pure-control-group">
{{ render_field(form.css_filter, placeholder=".class-name or #some-id, or other CSS selector rule.",
class="m-d") }}
@@ -158,7 +153,7 @@ User-Agent: wonderbra 1.0") }}
href="https://github.com/dgtlmoon/changedetection.io/wiki/CSS-Selector-help">here for more CSS selector help</a>.<br/>
</span>
</div>
<div class="pure-control-group">
<fieldset class="pure-group">
{{ render_field(form.subtractive_selectors, rows=5, placeholder="header
footer
nav
@@ -169,7 +164,8 @@ nav
<li> Add multiple elements or CSS selectors per line to ignore multiple parts of the HTML. </li>
</ul>
</span>
</div>
</fieldset>
</fieldset>
<fieldset class="pure-group">
{{ render_field(form.ignore_text, rows=5, placeholder="Some text to ignore in a line
/some.regex\d{2}/ for case-INsensitive regex
@@ -201,54 +197,14 @@ nav
</fieldset>
</div>
<div class="tab-pane-inner visual-selector-ui" id="visualselector">
<img id="beta-logo" src="{{url_for('static_content', group='images', filename='beta-logo.png')}}">
<fieldset>
<div class="pure-control-group">
{% if visualselector_enabled %}
{% if visualselector_data_is_ready %}
<div id="selector-header">
<a id="clear-selector" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Clear selection</a>
<i class="fetching-update-notice" style="font-size: 80%;">One moment, fetching screenshot and element information..</i>
</div>
<div id="selector-wrapper">
<!-- request the screenshot and get the element offset info ready -->
<!-- use img src ready load to know everything is ready to map out -->
<!-- @todo: maybe something interesting like a field to select 'elements that contain text... and their parents n' -->
<img id="selector-background" />
<canvas id="selector-canvas"></canvas>
</div>
<div id="selector-current-xpath" style="overflow-x: hidden"><strong>Currently:</strong>&nbsp;<span class="text">Loading...</span></div>
<span class="pure-form-message-inline">
<p><span style="font-weight: bold">Beta!</span> The Visual Selector is new and there may be minor bugs, please report pages that dont work, help us to improve this software!</p>
</span>
{% else %}
<span class="pure-form-message-inline">Screenshot and element data is not available or not yet ready.</span>
{% endif %}
{% else %}
<span class="pure-form-message-inline">
<p>Sorry, this functionality only works with Playwright/Chrome enabled watches.</p>
<p>Enable the Playwright Chrome fetcher, or alternatively try our <a href="https://lemonade.changedetection.io/start">very affordable subscription based service</a>.</p>
<p>This is because Selenium/WebDriver can not extract full page screenshots reliably.</p>
</span>
{% endif %}
</div>
</fieldset>
</div>
<div id="actions">
<div class="pure-control-group">
{{ render_button(form.save_button) }} {{ render_button(form.save_and_preview_button) }}
<a href="{{url_for('form_delete', uuid=uuid)}}"
<a href="{{url_for('api_delete', uuid=uuid)}}"
class="pure-button button-small button-error ">Delete</a>
<a href="{{url_for('form_clone', uuid=uuid)}}"
<a href="{{url_for('api_clone', uuid=uuid)}}"
class="pure-button button-small ">Create Copy</a>
</div>
</div>

View File

@@ -10,6 +10,9 @@
<div class="tabs">
<ul>
<li class="tab" id="default-tab"><a href="#text">Text</a></li>
{% if screenshot %}
<li class="tab"><a href="#screenshot">Current screenshot</a></li>
{% endif %}
</ul>
</div>
@@ -28,5 +31,15 @@
</tbody>
</table>
</div>
{% if screenshot %}
<div class="tab-pane-inner" id="screenshot">
<p>
<i>For now, only the most recent screenshot is saved and displayed.</i>
</p>
<img src="{{url_for('static_content', group='screenshot', filename=uuid)}}">
</div>
{% endif %}
</div>
{% endblock %}

View File

@@ -20,7 +20,6 @@
<li class="tab"><a href="#notifications">Notifications</a></li>
<li class="tab"><a href="#fetching">Fetching</a></li>
<li class="tab"><a href="#filters">Global Filters</a></li>
<li class="tab"><a href="#api">API</a></li>
</ul>
</div>
<div class="box-wrap inner">
@@ -44,7 +43,6 @@
<span class="pure-form-message-inline">Password is locked.</span>
{% endif %}
</div>
<div class="pure-control-group">
{{ render_field(form.application.form.base_url, placeholder="http://yoursite.com:5000/",
class="m-d") }}
@@ -107,6 +105,7 @@
</fieldset>
</div>
<div class="tab-pane-inner" id="filters">
<fieldset class="pure-group">
@@ -151,26 +150,12 @@ nav
</fieldset>
</div>
<div class="tab-pane-inner" id="api">
<p>Drive your changedetection.io via API, More about <a href="https://github.com/dgtlmoon/changedetection.io/wiki/API-Reference">API access here</a></p>
<div class="pure-control-group">
{{ render_checkbox_field(form.application.form.api_access_token_enabled) }}
<div class="pure-form-message-inline">Restrict API access limit by using <code>x-api-key</code> header</div><br/>
<div class="pure-form-message-inline"><br/>API Key <span id="api-key">{{api_key}}</span>
<span style="display:none;" id="api-key-copy" >copy</span>
</div>
</div>
</div>
<div id="actions">
<div class="pure-control-group">
{{ render_button(form.save_button) }}
<a href="{{url_for('index')}}" class="pure-button button-small button-cancel">Back</a>
<a href="{{url_for('scrub_page')}}" class="pure-button button-small button-cancel">Delete History Snapshot Data</a>
</div>
</div>
</form>
</div>

View File

@@ -3,10 +3,9 @@
{% from '_helpers.jinja' import render_simple_field %}
<script type="text/javascript" src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
<script type="text/javascript" src="{{url_for('static_content', group='js', filename='watch-overview.js')}}" defer></script>
<div class="box">
<form class="pure-form" action="{{ url_for('form_watch_add') }}" method="POST" id="new-watch-form">
<form class="pure-form" action="{{ url_for('api_watch_add') }}" method="POST" id="new-watch-form">
<input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
<fieldset>
<legend>Add a new change detection watch</legend>
@@ -53,7 +52,7 @@
<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.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>
<a href="{{url_for('api_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 %}
@@ -75,7 +74,7 @@
{% endif %}
</td>
<td>
<a {% if watch.uuid in queued_uuids %}disabled="true"{% endif %} href="{{ url_for('form_watch_checknow', uuid=watch.uuid, tag=request.args.get('tag')) }}"
<a {% if watch.uuid in queued_uuids %}disabled="true"{% endif %} href="{{ url_for('api_watch_checknow', uuid=watch.uuid, tag=request.args.get('tag')) }}"
class="recheck pure-button button-small pure-button-primary">{% if watch.uuid in queued_uuids %}Queued{% else %}Recheck{% endif %}</a>
<a href="{{ url_for('edit_page', uuid=watch.uuid)}}" class="pure-button button-small pure-button-primary">Edit</a>
{% if watch.history|length >= 2 %}
@@ -97,7 +96,7 @@
</li>
{% endif %}
<li>
<a href="{{ url_for('form_watch_checknow', tag=active_tag) }}" class="pure-button button-tag ">Recheck
<a href="{{ url_for('api_watch_checknow', tag=active_tag) }}" class="pure-button button-tag ">Recheck
all {% if active_tag%}in "{{active_tag}}"{%endif%}</a>
</li>
<li>

View File

@@ -1,2 +0,0 @@
"""Tests for the app."""

View File

@@ -1,3 +0,0 @@
#!/usr/bin/python3
from .. import conftest

View File

@@ -1,48 +0,0 @@
#!/usr/bin/python3
import time
from flask import url_for
from ..util import live_server_setup
import logging
def test_fetch_webdriver_content(client, live_server):
live_server_setup(live_server)
#####################
res = client.post(
url_for("settings_page"),
data={"application-empty_pages_are_a_change": "",
"requests-time_between_check-minutes": 180,
'application-fetch_backend': "html_webdriver"},
follow_redirects=True
)
assert b"Settings updated." in res.data
# Add our URL to the import page
res = client.post(
url_for("import_page"),
data={"urls": "https://changedetection.io/ci-test.html"},
follow_redirects=True
)
assert b"1 Imported" in res.data
time.sleep(3)
attempt = 0
while attempt < 20:
res = client.get(url_for("index"))
if not b'Checking now' in res.data:
break
logging.getLogger().info("Waiting for check to not say 'Checking now'..")
time.sleep(3)
attempt += 1
res = client.get(
url_for("preview_page", uuid="first"),
follow_redirects=True
)
logging.getLogger().info("Looking for correct fetched HTML (text) from server")
assert b'cool it works' in res.data

View File

@@ -2,205 +2,73 @@
import time
from flask import url_for
from .util import live_server_setup
from . util import live_server_setup
import json
import uuid
def set_original_response():
test_return_data = """<html>
<body>
Some initial text</br>
<p>Which is across multiple lines</p>
</br>
So let's see what happens. </br>
<div id="sametext">Some text thats the same</div>
<div id="changetext">Some text that will change</div>
</body>
</html>
"""
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write(test_return_data)
return None
def set_modified_response():
test_return_data = """<html>
<body>
Some initial text</br>
<p>which has this one new line</p>
</br>
So let's see what happens. </br>
<div id="sametext">Some text thats the same</div>
<div id="changetext">Some text that changes</div>
</body>
</html>
"""
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write(test_return_data)
return None
def is_valid_uuid(val):
try:
uuid.UUID(str(val))
return True
except ValueError:
return False
# kinda funky, but works for now
def _extract_api_key_from_UI(client):
import re
res = client.get(
url_for("settings_page"),
)
# <span id="api-key">{{api_key}}</span>
m = re.search('<span id="api-key">(.+?)</span>', str(res.data))
api_key = m.group(1)
return api_key.strip()
def test_api_simple(client, live_server):
def test_setup(live_server):
live_server_setup(live_server)
api_key = _extract_api_key_from_UI(client)
# Create a watch
set_original_response()
watch_uuid = None
def set_response_data(test_return_data):
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write(test_return_data)
# Validate bad URL
test_url = url_for('test_endpoint', _external=True,
headers={'x-api-key': api_key}, )
def test_snapshot_api_detects_change(client, live_server):
test_return_data = "Some initial text"
test_return_data_modified = "Some NEW nice initial text"
sleep_time_for_fetch_thread = 3
set_response_data(test_return_data)
# Give the endpoint time to spin up
time.sleep(1)
# Add our URL to the import page
test_url = url_for('test_endpoint', content_type="text/plain",
_external=True)
res = client.post(
url_for("createwatch"),
data=json.dumps({"url": "h://xxxxxxxxxom"}),
headers={'content-type': 'application/json', 'x-api-key': api_key},
url_for("import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Trigger a check
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
res = client.get(
url_for("api_snapshot", uuid="first"),
follow_redirects=True
)
assert test_return_data.encode() == res.data
# Make a change
set_response_data(test_return_data_modified)
# Trigger a check
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
res = client.get(
url_for("api_snapshot", uuid="first"),
follow_redirects=True
)
assert test_return_data_modified.encode() == res.data
def test_snapshot_api_invalid_uuid(client, live_server):
res = client.get(
url_for("api_snapshot", uuid="invalid"),
follow_redirects=True
)
assert res.status_code == 400
# Create new
res = client.post(
url_for("createwatch"),
data=json.dumps({"url": test_url, 'tag': "One, Two", "title": "My test URL"}),
headers={'content-type': 'application/json', 'x-api-key': api_key},
follow_redirects=True
)
s = json.loads(res.data)
assert is_valid_uuid(s['uuid'])
watch_uuid = s['uuid']
assert res.status_code == 201
time.sleep(3)
# Verify its in the list and that recheck worked
res = client.get(
url_for("createwatch"),
headers={'x-api-key': api_key}
)
assert watch_uuid in json.loads(res.data).keys()
before_recheck_info = json.loads(res.data)[watch_uuid]
assert before_recheck_info['last_checked'] != 0
assert before_recheck_info['title'] == 'My test URL'
set_modified_response()
# Trigger recheck of all ?recheck_all=1
client.get(
url_for("createwatch", recheck_all='1'),
headers={'x-api-key': api_key},
)
time.sleep(3)
# Did the recheck fire?
res = client.get(
url_for("createwatch"),
headers={'x-api-key': api_key},
)
after_recheck_info = json.loads(res.data)[watch_uuid]
assert after_recheck_info['last_checked'] != before_recheck_info['last_checked']
assert after_recheck_info['last_changed'] != 0
# Check history index list
res = client.get(
url_for("watchhistory", uuid=watch_uuid),
headers={'x-api-key': api_key},
)
history = json.loads(res.data)
assert len(history) == 2, "Should have two history entries (the original and the changed)"
# Fetch a snapshot by timestamp, check the right one was found
res = client.get(
url_for("watchsinglehistory", uuid=watch_uuid, timestamp=list(history.keys())[-1]),
headers={'x-api-key': api_key},
)
assert b'which has this one new line' in res.data
# Fetch a snapshot by 'latest'', check the right one was found
res = client.get(
url_for("watchsinglehistory", uuid=watch_uuid, timestamp='latest'),
headers={'x-api-key': api_key},
)
assert b'which has this one new line' in res.data
# Fetch the whole watch
res = client.get(
url_for("watch", uuid=watch_uuid),
headers={'x-api-key': api_key}
)
watch = json.loads(res.data)
# @todo how to handle None/default global values?
assert watch['history_n'] == 2, "Found replacement history section, which is in its own API"
# Finally delete the watch
res = client.delete(
url_for("watch", uuid=watch_uuid),
headers={'x-api-key': api_key},
)
assert res.status_code == 204
# Check via a relist
res = client.get(
url_for("createwatch"),
headers={'x-api-key': api_key}
)
watch_list = json.loads(res.data)
assert len(watch_list) == 0, "Watch list should be empty"
def test_access_denied(client, live_server):
# `config_api_token_enabled` Should be On by default
res = client.get(
url_for("createwatch")
)
assert res.status_code == 403
res = client.get(
url_for("createwatch"),
headers={'x-api-key': "something horrible"}
)
assert res.status_code == 403
# Disable config_api_token_enabled and it should work
res = client.post(
url_for("settings_page"),
data={
"requests-time_between_check-minutes": 180,
"application-fetch_backend": "html_requests",
"application-api_access_token_enabled": ""
},
follow_redirects=True
)
assert b"Settings updated." in res.data
res = client.get(
url_for("createwatch")
)
assert res.status_code == 200

View File

@@ -29,7 +29,7 @@ def test_basic_auth(client, live_server):
assert b"Updated watch." in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
time.sleep(1)
res = client.get(
url_for("preview_page", uuid="first"),

View File

@@ -32,7 +32,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
# Do this a few times.. ensures we dont accidently set the status
for n in range(3):
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -65,7 +65,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
assert b'which has this one new line' in res.read()
# Force recheck
res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
res = client.get(url_for("api_watch_checknow"), follow_redirects=True)
assert b'1 watches are queued for rechecking.' in res.data
time.sleep(sleep_time_for_fetch_thread)
@@ -93,7 +93,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
# Do this a few times.. ensures we dont accidently set the status
for n in range(2):
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -113,7 +113,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
follow_redirects=True
)
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
time.sleep(sleep_time_for_fetch_thread)
res = client.get(url_for("index"))
@@ -123,6 +123,6 @@ def test_check_basic_change_detection_functionality(client, live_server):
#
# Cleanup everything
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -23,7 +23,7 @@ def test_trigger_functionality(client, live_server):
res = client.get(
url_for("form_clone", uuid="first"),
url_for("api_clone", uuid="first"),
follow_redirects=True
)

View File

@@ -89,7 +89,7 @@ def test_check_markup_css_filter_restriction(client, live_server):
assert b"1 Imported" in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -110,7 +110,7 @@ def test_check_markup_css_filter_restriction(client, live_server):
assert bytes(css_filter.encode('utf-8')) in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -118,7 +118,7 @@ def test_check_markup_css_filter_restriction(client, live_server):
set_modified_response()
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)

View File

@@ -145,7 +145,7 @@ def test_element_removal_full(client, live_server):
assert bytes(subtractive_selectors_data.encode("utf-8")) in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -158,7 +158,7 @@ def test_element_removal_full(client, live_server):
set_modified_response()
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)

View File

@@ -39,7 +39,7 @@ def test_check_encoding_detection(client, live_server):
)
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(2)
@@ -71,7 +71,7 @@ def test_check_encoding_detection_missing_content_type_header(client, live_serve
)
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(2)

View File

@@ -29,7 +29,7 @@ def test_error_handler(client, live_server):
assert b"1 Imported" in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(3)
@@ -54,7 +54,7 @@ def test_error_text_handler(client, live_server):
assert b"1 Imported" in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(3)

View File

@@ -102,7 +102,7 @@ def test_check_ignore_text_functionality(client, live_server):
assert b"1 Imported" in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -123,7 +123,7 @@ def test_check_ignore_text_functionality(client, live_server):
assert bytes(ignore_text.encode('utf-8')) in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -137,7 +137,7 @@ def test_check_ignore_text_functionality(client, live_server):
set_modified_ignore_response()
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -152,7 +152,7 @@ def test_check_ignore_text_functionality(client, live_server):
# Just to be sure.. set a regular modified change..
set_modified_original_ignore_response()
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
time.sleep(sleep_time_for_fetch_thread)
res = client.get(url_for("index"))
@@ -165,7 +165,7 @@ def test_check_ignore_text_functionality(client, live_server):
# We should be able to see what we ignored
assert b'<div class="ignored">new ignore stuff' in res.data
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_check_global_ignore_text_functionality(client, live_server):
@@ -200,7 +200,7 @@ def test_check_global_ignore_text_functionality(client, live_server):
assert b"1 Imported" in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -222,7 +222,7 @@ def test_check_global_ignore_text_functionality(client, live_server):
assert bytes(ignore_text.encode('utf-8')) in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -240,7 +240,7 @@ def test_check_global_ignore_text_functionality(client, live_server):
set_modified_ignore_response()
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -251,10 +251,10 @@ def test_check_global_ignore_text_functionality(client, live_server):
# Just to be sure.. set a regular modified change that will trigger it
set_modified_original_ignore_response()
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
time.sleep(sleep_time_for_fetch_thread)
res = client.get(url_for("index"))
assert b'unviewed' in res.data
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -72,14 +72,14 @@ def test_render_anchor_tag_content_true(client, live_server):
time.sleep(sleep_time_for_fetch_thread)
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# set a new html text with a modified link
set_modified_ignore_response()
time.sleep(sleep_time_for_fetch_thread)
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -101,7 +101,7 @@ def test_render_anchor_tag_content_true(client, live_server):
assert b"Settings updated." in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -119,7 +119,7 @@ def test_render_anchor_tag_content_true(client, live_server):
assert b"/test-endpoint" in res.data
# Cleanup everything
res = client.get(url_for("form_delete", uuid="all"),
res = client.get(url_for("api_delete", uuid="all"),
follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -70,12 +70,12 @@ def test_normal_page_check_works_with_ignore_status_code(client, live_server):
time.sleep(sleep_time_for_fetch_thread)
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
set_some_changed_response()
time.sleep(sleep_time_for_fetch_thread)
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -105,7 +105,7 @@ def test_403_page_check_works_with_ignore_status_code(client, live_server):
assert b"1 Imported" in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -120,7 +120,7 @@ def test_403_page_check_works_with_ignore_status_code(client, live_server):
assert b"Updated watch." in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -128,7 +128,7 @@ def test_403_page_check_works_with_ignore_status_code(client, live_server):
set_some_changed_response()
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -157,7 +157,7 @@ def test_403_page_check_fails_without_ignore_status_code(client, live_server):
assert b"1 Imported" in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -172,7 +172,7 @@ def test_403_page_check_fails_without_ignore_status_code(client, live_server):
assert b"Updated watch." in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -180,7 +180,7 @@ def test_403_page_check_fails_without_ignore_status_code(client, live_server):
set_some_changed_response()
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)

View File

@@ -80,12 +80,12 @@ def test_check_ignore_whitespace(client, live_server):
time.sleep(sleep_time_for_fetch_thread)
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
set_original_ignore_response_but_with_whitespace()
time.sleep(sleep_time_for_fetch_thread)
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)

View File

@@ -25,7 +25,7 @@ https://example.com tag1, other tag"""
assert b"3 Imported" in res.data
assert b"tag1" in res.data
assert b"other tag" in res.data
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
# Clear flask alerts
res = client.get( url_for("index"))
@@ -50,7 +50,7 @@ def xtest_import_skip_url(client, live_server):
assert b"1 Imported" in res.data
assert b"ht000000broken" in res.data
assert b"1 Skipped" in res.data
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
# Clear flask alerts
res = client.get( url_for("index"))
@@ -79,7 +79,7 @@ def test_import_distillio(client, live_server):
# Give the endpoint time to spin up
time.sleep(1)
client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
res = client.post(
url_for("import_page"),
data={
@@ -115,6 +115,6 @@ def test_import_distillio(client, live_server):
assert b"nice stuff" in res.data
assert b"nerd-news" in res.data
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
# Clear flask alerts
res = client.get(url_for("index"))

View File

@@ -171,7 +171,7 @@ def test_check_json_without_filter(client, live_server):
)
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(3)
@@ -203,7 +203,7 @@ def test_check_json_filter(client, live_server):
assert b"1 Imported" in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(3)
@@ -229,7 +229,7 @@ def test_check_json_filter(client, live_server):
assert bytes(json_filter.encode('utf-8')) in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(3)
@@ -237,7 +237,7 @@ def test_check_json_filter(client, live_server):
set_modified_response()
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(4)
@@ -288,7 +288,7 @@ def test_check_json_filter_bool_val(client, live_server):
time.sleep(3)
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(3)
@@ -296,7 +296,7 @@ def test_check_json_filter_bool_val(client, live_server):
set_modified_response()
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(3)
@@ -327,7 +327,7 @@ def test_check_json_ext_filter(client, live_server):
assert b"1 Imported" in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(3)
@@ -353,7 +353,7 @@ def test_check_json_ext_filter(client, live_server):
assert bytes(json_filter.encode('utf-8')) in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(3)
@@ -361,7 +361,7 @@ def test_check_json_ext_filter(client, live_server):
set_modified_ext_response()
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(4)

View File

@@ -39,7 +39,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
# Do this a few times.. ensures we dont accidently set the status
for n in range(3):
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -61,7 +61,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
# this should not trigger a change, because no good text could be converted from the HTML
set_nonrenderable_response()
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -83,7 +83,7 @@ def test_check_basic_change_detection_functionality(client, live_server):
set_modified_response()
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -97,6 +97,6 @@ def test_check_basic_change_detection_functionality(client, live_server):
#
# Cleanup everything
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -36,7 +36,7 @@ def test_check_notification(client, live_server):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
res = client.post(
url_for("form_watch_add"),
url_for("api_watch_add"),
data={"url": test_url, "tag": ''},
follow_redirects=True
)
@@ -98,7 +98,7 @@ def test_check_notification(client, live_server):
notification_submission = None
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
time.sleep(3)
# Verify what was sent as a notification, this file should exist
with open("test-datastore/notification.txt", "r") as f:
@@ -133,7 +133,7 @@ def test_check_notification(client, live_server):
# This should insert the {current_snapshot}
set_more_modified_response()
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
time.sleep(3)
# Verify what was sent as a notification, this file should exist
with open("test-datastore/notification.txt", "r") as f:
@@ -146,17 +146,17 @@ def test_check_notification(client, live_server):
os.unlink("test-datastore/notification.txt")
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
time.sleep(1)
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
time.sleep(1)
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
time.sleep(1)
assert os.path.exists("test-datastore/notification.txt") == False
# cleanup for the next
client.get(
url_for("form_delete", uuid="all"),
url_for("api_delete", uuid="all"),
follow_redirects=True
)
@@ -168,7 +168,7 @@ def test_notification_validation(client, live_server):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
res = client.post(
url_for("form_watch_add"),
url_for("api_watch_add"),
data={"url": test_url, "tag": 'nice one'},
follow_redirects=True
)
@@ -208,6 +208,6 @@ def test_notification_validation(client, live_server):
# cleanup for the next
client.get(
url_for("form_delete", uuid="all"),
url_for("api_delete", uuid="all"),
follow_redirects=True
)

View File

@@ -16,7 +16,7 @@ def test_check_notification_error_handling(client, live_server):
# use a different URL so that it doesnt interfere with the actual check until we are ready
test_url = url_for('test_endpoint', _external=True)
res = client.post(
url_for("form_watch_add"),
url_for("api_watch_add"),
data={"url": "https://changedetection.io/CHANGELOG.txt", "tag": ''},
follow_redirects=True
)

View File

@@ -41,7 +41,7 @@ def test_share_watch(client, live_server):
# click share the link
res = client.get(
url_for("form_share_put_watch", uuid="first"),
url_for("api_share_put_watch", uuid="first"),
follow_redirects=True
)
@@ -54,7 +54,7 @@ def test_share_watch(client, live_server):
# Now delete what we have, we will try to re-import it
# Cleanup everything
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
# Add our URL to the import page

View File

@@ -39,7 +39,7 @@ def test_check_basic_change_detection_functionality_source(client, live_server):
set_modified_response()
# Force recheck
res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
res = client.get(url_for("api_watch_checknow"), follow_redirects=True)
assert b'1 watches are queued for rechecking.' in res.data
time.sleep(5)

View File

@@ -76,7 +76,7 @@ def test_trigger_functionality(client, live_server):
assert b"1 Imported" in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -99,7 +99,7 @@ def test_trigger_functionality(client, live_server):
assert bytes(trigger_text.encode('utf-8')) in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -113,7 +113,7 @@ def test_trigger_functionality(client, live_server):
set_modified_original_ignore_response()
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -121,21 +121,15 @@ def test_trigger_functionality(client, live_server):
res = client.get(url_for("index"))
assert b'unviewed' not in res.data
# Now set the content which contains the trigger text
# Just to be sure.. set a regular modified change..
time.sleep(sleep_time_for_fetch_thread)
set_modified_with_trigger_text_response()
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
time.sleep(sleep_time_for_fetch_thread)
res = client.get(url_for("index"))
assert b'unviewed' in res.data
# https://github.com/dgtlmoon/changedetection.io/issues/616
# Apparently the actual snapshot that contains the trigger never shows
res = client.get(url_for("diff_history_page", uuid="first"))
assert b'foobar123' in res.data
# Check the preview/highlighter, we should be able to see what we triggered on, but it should be highlighted
res = client.get(url_for("preview_page", uuid="first"))
# We should be able to see what we ignored

View File

@@ -43,7 +43,7 @@ def test_trigger_regex_functionality(client, live_server):
assert b"1 Imported" in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -65,7 +65,7 @@ def test_trigger_regex_functionality(client, live_server):
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write("some new noise")
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
time.sleep(sleep_time_for_fetch_thread)
# It should report nothing found (nothing should match the regex)
@@ -75,7 +75,7 @@ def test_trigger_regex_functionality(client, live_server):
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write("regex test123<br/>\nsomething 123")
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
time.sleep(sleep_time_for_fetch_thread)
res = client.get(url_for("index"))
assert b'unviewed' in res.data

View File

@@ -43,7 +43,7 @@ def test_trigger_regex_functionality(client, live_server):
assert b"1 Imported" in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -66,7 +66,7 @@ def test_trigger_regex_functionality(client, live_server):
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write("<html>some new noise with cool stuff2 ok</html>")
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
time.sleep(sleep_time_for_fetch_thread)
# It should report nothing found (nothing should match the regex and filter)
@@ -76,7 +76,7 @@ def test_trigger_regex_functionality(client, live_server):
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write("<html>some new noise with <span id=in-here>cool stuff6</span> ok</html>")
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
time.sleep(sleep_time_for_fetch_thread)
res = client.get(url_for("index"))
assert b'unviewed' in res.data

View File

@@ -44,61 +44,6 @@ def set_modified_response():
return None
# Handle utf-8 charset replies https://github.com/dgtlmoon/changedetection.io/pull/613
def test_check_xpath_filter_utf8(client, live_server):
filter='//item/*[self::description]'
d='''<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
<channel>
<title>rpilocator.com</title>
<link>https://rpilocator.com</link>
<description>Find Raspberry Pi Computers in Stock</description>
<lastBuildDate>Thu, 19 May 2022 23:27:30 GMT</lastBuildDate>
<image>
<url>https://rpilocator.com/favicon.png</url>
<title>rpilocator.com</title>
<link>https://rpilocator.com/</link>
<width>32</width>
<height>32</height>
</image>
<item>
<title>Stock Alert (UK): RPi CM4 - 1GB RAM, No MMC, No Wifi is In Stock at Pimoroni</title>
<description>Stock Alert (UK): RPi CM4 - 1GB RAM, No MMC, No Wifi is In Stock at Pimoroni</description>
<link>https://rpilocator.com?vendor=pimoroni&amp;utm_source=feed&amp;utm_medium=rss</link>
<category>pimoroni</category>
<category>UK</category>
<category>CM4</category>
<guid isPermaLink="false">F9FAB0D9-DF6F-40C8-8DEE5FC0646BB722</guid>
<pubDate>Thu, 19 May 2022 14:32:32 GMT</pubDate>
</item>
</channel>
</rss>'''
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write(d)
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True, content_type="application/rss+xml;charset=UTF-8")
res = client.post(
url_for("import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
res = client.post(
url_for("edit_page", uuid="first"),
data={"css_filter": filter, "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
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)
assert b'Deleted' in res.data
def test_check_markup_xpath_filter_restriction(client, live_server):
sleep_time_for_fetch_thread = 3
@@ -120,7 +65,7 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
assert b"1 Imported" in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -144,14 +89,12 @@ def test_check_markup_xpath_filter_restriction(client, live_server):
set_modified_response()
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
client.get(url_for("api_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
res = client.get(url_for("index"))
assert b'unviewed' not in res.data
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_xpath_validation(client, live_server):
@@ -174,13 +117,11 @@ def test_xpath_validation(client, live_server):
follow_redirects=True
)
assert b"is not a valid XPath expression" in res.data
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
# actually only really used by the distll.io importer, but could be handy too
def test_check_with_prefix_css_filter(client, live_server):
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
# Give the endpoint time to spin up
@@ -212,7 +153,9 @@ def test_check_with_prefix_css_filter(client, live_server):
follow_redirects=True
)
with open('/tmp/fuck.html', 'wb') as f:
f.write(res.data)
assert b"Some text thats the same" in res.data #in selector
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)
client.get(url_for("api_delete", uuid="all"), follow_redirects=True)

View File

@@ -40,11 +40,10 @@ class update_worker(threading.Thread):
contents = ""
screenshot = False
update_obj= {}
xpath_data = False
now = time.time()
try:
changed_detected, update_obj, contents, screenshot, xpath_data = update_handler.run(uuid)
changed_detected, update_obj, contents, screenshot = update_handler.run(uuid)
# Re #342
# In Python 3, all strings are sequences of Unicode characters. There is a bytes type that holds raw bytes.
@@ -56,7 +55,6 @@ class update_worker(threading.Thread):
except content_fetcher.ReplyWithContentButNoText as e:
# Totally fine, it's by choice - just continue on, nothing more to care about
# Page had elements/content but no renderable text
self.datastore.update_watch(uuid=uuid, update_obj={'last_error': "Got HTML content but no text found."})
pass
except content_fetcher.EmptyReply as e:
# Some kind of custom to-str handler in the exception handler that does this?
@@ -150,9 +148,6 @@ class update_worker(threading.Thread):
# Always save the screenshot if it's available
if screenshot:
self.datastore.save_screenshot(watch_uuid=uuid, screenshot=screenshot)
if xpath_data:
self.datastore.save_xpath_data(watch_uuid=uuid, data=xpath_data)
self.current_uuid = None # Done
self.q.task_done()

1532
f

File diff suppressed because one or more lines are too long

View File

@@ -6,7 +6,6 @@ timeago ~=1.0
inscriptis ~= 2.2
feedgen ~= 0.9
flask-login ~= 0.5
flask_restful
pytz
# Set these versions together to avoid a RequestsDependencyWarning