Compare commits

..

16 Commits

Author SHA1 Message Date
dgtlmoon
7b664c43ea Oops 2023-02-11 16:29:15 +01:00
dgtlmoon
d4eb9f2b64 Use Loguru for logging 2023-02-11 16:26:09 +01:00
dgtlmoon
7b8b50138b Deleting a watch now removes the entire watch storage directory (#1408) 2023-02-11 14:10:54 +01:00
dgtlmoon
01af21f856 Use year/date in the backup snapshot zip filename instead of epoch seconds (#1377 #1407) 2023-02-11 13:44:16 +01:00
dgtlmoon
f7f4ab314b PDF text conversion - fix bug where it detected a site as a PDF file incorrectly Re #1392 #1393 2023-02-08 09:32:57 +01:00
dgtlmoon
ce0355c0ad Remove unused code (#1394) 2023-02-08 09:32:15 +01:00
dgtlmoon
0f43213d9d UI - preview page - Fix bug where playwright/chrome was system default and [preview] didnt show snapshot 2023-02-07 16:55:34 +01:00
dgtlmoon
93c57d9fad Adding example docker-compose.yml config to ignore errors from self-signed certs #1389 2023-02-06 17:24:12 +01:00
dgtlmoon
3cdd075baf 0.40.2 2023-02-03 19:20:13 +01:00
dgtlmoon
5c617e8530 Code cleanup - remove unused import 2023-02-03 18:35:58 +01:00
dgtlmoon
1a48965ba1 UI fix - Fix logic for showing screenshot on diff page (#1379) 2023-02-03 11:23:48 +01:00
dgtlmoon
41856c4ed8 Re #1365 - Playwright - Browser "Service Workers" should be enabled by default but unset via env var PLAYWRIGHT_SERVICE_WORKERS=block (#1367) 2023-02-01 20:50:40 +01:00
dgtlmoon
0ed897c50f New setting to allow passwordless access to your 'diff' page - perfect for sharing your diff page securely, refactored login code (#1357) 2023-01-29 22:36:55 +01:00
dgtlmoon
f8e587c415 Security - Possible stored XSS in watch list - Only permit HTTP/HTTP/FTP by default - override with env var SAFE_PROTOCOL_REGEX (#1359) 2023-01-29 11:12:06 +01:00
dgtlmoon
d47a25eb6d Playwright - Removing old bug fix where playwright needed screenshot called twice to make the full screen screenshot be actually fullscreen (#1356) 2023-01-28 15:02:53 +01:00
dgtlmoon
9a0792d185 Fetch backend UI default fixes for VisualSelector and BrowserSteps (#1344) 2023-01-25 19:47:54 +01:00
24 changed files with 391 additions and 244 deletions

View File

@@ -67,10 +67,10 @@ jobs:
sleep 3
# Should return 0 (no error) when grep finds it
curl -s http://localhost:5556 |grep -q checkbox-uuid
curl -s http://localhost:5556/rss|grep -q rss-specification
# and IPv6
curl -s -g -6 "http://[::1]:5556"|grep -q checkbox-uuid
curl -s -g -6 "http://[::1]:5556/rss"|grep -q rss-specification
#export WEBDRIVER_URL=http://localhost:4444/wd/hub
#pytest tests/fetchers/test_content.py

View File

@@ -1,8 +1,18 @@
#!/usr/bin/python3
from changedetectionio import queuedWatchMetaData
from copy import deepcopy
from distutils.util import strtobool
from feedgen.feed import FeedGenerator
from flask_compress import Compress as FlaskCompress
from flask_login import current_user
from flask_restful import abort, Api
from flask_wtf import CSRFProtect
from functools import wraps
from threading import Event
import datetime
import flask_login
import logging
from loguru import logger
import os
import pytz
import queue
@@ -10,12 +20,6 @@ import threading
import time
import timeago
from changedetectionio import queuedWatchMetaData
from copy import deepcopy
from distutils.util import strtobool
from feedgen.feed import FeedGenerator
from threading import Event
from flask import (
Flask,
abort,
@@ -28,15 +32,11 @@ from flask import (
session,
url_for,
)
from flask_compress import Compress as FlaskCompress
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__ = '0.40.1.1'
__version__ = '0.40.2'
datastore = None
@@ -53,7 +53,6 @@ app = Flask(__name__,
static_url_path="",
static_folder="static",
template_folder="templates")
from flask_compress import Compress
# Super handy for compressing large BrowserSteps responses and others
FlaskCompress(app)
@@ -65,8 +64,6 @@ app.config.exit = Event()
app.config['NEW_VERSION_AVAILABLE'] = False
app.config['LOGIN_DISABLED'] = False
#app.config["EXPLAIN_TEMPLATE_LOADING"] = True
# Disables caching of the templates
@@ -74,7 +71,6 @@ app.config['TEMPLATES_AUTO_RELOAD'] = True
app.jinja_env.add_extension('jinja2.ext.loopcontrols')
csrf = CSRFProtect()
csrf.init_app(app)
notification_debug_log=[]
watch_api = Api(app, decorators=[csrf.exempt])
@@ -149,7 +145,6 @@ class User(flask_login.UserMixin):
# Compare given password against JSON store or Env var
def check_password(self, password):
import base64
import hashlib
@@ -157,11 +152,9 @@ class User(flask_login.UserMixin):
raw_salt_pass = os.getenv("SALTED_PASS", False)
if not raw_salt_pass:
raw_salt_pass = datastore.data['settings']['application']['password']
raw_salt_pass = datastore.data['settings']['application'].get('password')
raw_salt_pass = base64.b64decode(raw_salt_pass)
salt_from_storage = raw_salt_pass[:32] # 32 is the length of the salt
# Use the exact same setup you used to generate the key, but this time put in the password to check
@@ -171,21 +164,44 @@ class User(flask_login.UserMixin):
salt_from_storage,
100000
)
new_key = salt_from_storage + new_key
new_key = salt_from_storage + new_key
return new_key == raw_salt_pass
pass
def login_optionally_required(func):
@wraps(func)
def decorated_view(*args, **kwargs):
has_password_enabled = datastore.data['settings']['application'].get('password') or os.getenv("SALTED_PASS", False)
# Permitted
if request.endpoint == 'static_content' and request.view_args['group'] == 'styles':
return func(*args, **kwargs)
# Permitted
elif request.endpoint == 'diff_history_page' and datastore.data['settings']['application'].get('shared_diff_access'):
return func(*args, **kwargs)
elif request.method in flask_login.config.EXEMPT_METHODS:
return func(*args, **kwargs)
elif app.config.get('LOGIN_DISABLED'):
return func(*args, **kwargs)
elif has_password_enabled and not current_user.is_authenticated:
return app.login_manager.unauthorized()
return func(*args, **kwargs)
return decorated_view
def changedetection_app(config=None, datastore_o=None):
global datastore
datastore = datastore_o
# so far just for read-only via tests, but this will be moved eventually to be the main source
# (instead of the global var)
app.config['DATASTORE']=datastore_o
#app.config.update(config or {})
app.config['DATASTORE'] = datastore_o
login_manager = flask_login.LoginManager(app)
login_manager.login_view = 'login'
@@ -213,6 +229,8 @@ def changedetection_app(config=None, datastore_o=None):
# https://flask-cors.readthedocs.io/en/latest/
# CORS(app)
@login_manager.user_loader
def user_loader(email):
user = User()
@@ -221,7 +239,7 @@ def changedetection_app(config=None, datastore_o=None):
@login_manager.unauthorized_handler
def unauthorized_handler():
# @todo validate its a URL of this host and use that
flash("You must be logged in, please log in.", 'error')
return redirect(url_for('login', next=url_for('index')))
@app.route('/logout')
@@ -234,10 +252,6 @@ def changedetection_app(config=None, datastore_o=None):
@app.route('/login', methods=['GET', 'POST'])
def login():
if not datastore.data['settings']['application']['password'] and not os.getenv("SALTED_PASS", False):
flash("Login not required, no password enabled.", "notice")
return redirect(url_for('index'))
if request.method == 'GET':
if flask_login.current_user.is_authenticated:
flash("Already logged in")
@@ -272,27 +286,22 @@ def changedetection_app(config=None, datastore_o=None):
return redirect(url_for('login'))
@app.before_request
def do_something_whenever_a_request_comes_in():
# Disable password login if there is not one set
# (No password in settings or env var)
app.config['LOGIN_DISABLED'] = datastore.data['settings']['application']['password'] == False and os.getenv("SALTED_PASS", False) == False
def before_request_handle_cookie_x_settings():
# Set the auth cookie path if we're running as X-settings/X-Forwarded-Prefix
if os.getenv('USE_X_SETTINGS') and 'X-Forwarded-Prefix' in request.headers:
app.config['REMEMBER_COOKIE_PATH'] = request.headers['X-Forwarded-Prefix']
app.config['SESSION_COOKIE_PATH'] = request.headers['X-Forwarded-Prefix']
# For the RSS path, allow access via a token
if request.path == '/rss' and request.args.get('token'):
app_rss_token = datastore.data['settings']['application']['rss_access_token']
rss_url_token = request.args.get('token')
if app_rss_token == rss_url_token:
app.config['LOGIN_DISABLED'] = True
return None
@app.route("/rss", methods=['GET'])
@login_required
def rss():
# Always requires token set
app_rss_token = datastore.data['settings']['application'].get('rss_access_token')
rss_url_token = request.args.get('token')
if rss_url_token != app_rss_token:
return "Access denied, bad token", 403
from . import diff
limit_tag = request.args.get('tag')
@@ -366,7 +375,7 @@ def changedetection_app(config=None, datastore_o=None):
return response
@app.route("/", methods=['GET'])
@login_required
@login_optionally_required
def index():
from changedetectionio import forms
@@ -430,7 +439,7 @@ def changedetection_app(config=None, datastore_o=None):
# AJAX endpoint for sending a test
@app.route("/notification/send-test", methods=['POST'])
@login_required
@login_optionally_required
def ajax_callback_send_notification_test():
import apprise
@@ -463,7 +472,7 @@ def changedetection_app(config=None, datastore_o=None):
@app.route("/clear_history/<string:uuid>", methods=['GET'])
@login_required
@login_optionally_required
def clear_watch_history(uuid):
try:
datastore.clear_watch_history(uuid)
@@ -475,7 +484,7 @@ def changedetection_app(config=None, datastore_o=None):
return redirect(url_for('index'))
@app.route("/clear_history", methods=['GET', 'POST'])
@login_required
@login_optionally_required
def clear_all_history():
if request.method == 'POST':
@@ -496,43 +505,8 @@ def changedetection_app(config=None, datastore_o=None):
output = render_template("clear_all_history.html")
return output
# If they edited an existing watch, we need to know to reset the current/previous md5 to include
# the excluded text.
def get_current_checksum_include_ignore_text(uuid):
import hashlib
from changedetectionio import fetch_site_status
# Get the most recent one
newest_history_key = datastore.data['watching'][uuid].get('newest_history_key')
# 0 means that theres only one, so that there should be no 'unviewed' history available
if newest_history_key == 0:
newest_history_key = list(datastore.data['watching'][uuid].history.keys())[0]
if newest_history_key:
with open(datastore.data['watching'][uuid].history[newest_history_key],
encoding='utf-8') as file:
raw_content = file.read()
handler = fetch_site_status.perform_site_check(datastore=datastore)
stripped_content = html_tools.strip_ignore_text(raw_content,
datastore.data['watching'][uuid]['ignore_text'])
if datastore.data['settings']['application'].get('ignore_whitespace', False):
checksum = hashlib.md5(stripped_content.translate(None, b'\r\n\t ')).hexdigest()
else:
checksum = hashlib.md5(stripped_content).hexdigest()
return checksum
return datastore.data['watching'][uuid]['previous_md5']
@app.route("/edit/<string:uuid>", methods=['GET', 'POST'])
@login_required
@login_optionally_required
# https://stackoverflow.com/questions/42984453/wtforms-populate-form-with-data-if-data-exists
# https://wtforms.readthedocs.io/en/3.0.x/forms/#wtforms.form.Form.populate_obj ?
@@ -586,6 +560,7 @@ def changedetection_app(config=None, datastore_o=None):
if request.method == 'POST' and form.validate():
extra_update_obj = {}
if request.args.get('unpause_on_save'):
@@ -677,7 +652,7 @@ def changedetection_app(config=None, datastore_o=None):
return output
@app.route("/settings", methods=['GET', "POST"])
@login_required
@login_optionally_required
def settings_page():
from changedetectionio import content_fetcher, forms
@@ -757,7 +732,7 @@ def changedetection_app(config=None, datastore_o=None):
return output
@app.route("/import", methods=['GET', "POST"])
@login_required
@login_optionally_required
def import_page():
remaining_urls = []
if request.method == 'POST':
@@ -795,7 +770,7 @@ def changedetection_app(config=None, datastore_o=None):
# Clear all statuses, so we do not see the 'unviewed' class
@app.route("/form/mark-all-viewed", methods=['GET'])
@login_required
@login_optionally_required
def mark_all_viewed():
# Save the current newest history as the most recently viewed
@@ -805,7 +780,7 @@ def changedetection_app(config=None, datastore_o=None):
return redirect(url_for('index'))
@app.route("/diff/<string:uuid>", methods=['GET', 'POST'])
@login_required
@login_optionally_required
def diff_history_page(uuid):
from changedetectionio import forms
@@ -881,8 +856,13 @@ def changedetection_app(config=None, datastore_o=None):
system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
is_html_webdriver = True if watch.get('fetch_backend') == 'html_webdriver' or (
watch.get('fetch_backend', None) is None and system_uses_webdriver) else False
is_html_webdriver = False
if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver':
is_html_webdriver = True
password_enabled_and_share_is_off = False
if datastore.data['settings']['application'].get('password') or os.getenv("SALTED_PASS", False):
password_enabled_and_share_is_off = not datastore.data['settings']['application'].get('shared_diff_access')
output = render_template("diff.html",
current_diff_url=watch['url'],
@@ -897,6 +877,7 @@ def changedetection_app(config=None, datastore_o=None):
left_sticky=True,
newest=newest_version_file_contents,
newest_version_timestamp=dates[-1],
password_enabled_and_share_is_off=password_enabled_and_share_is_off,
previous=previous_version_file_contents,
screenshot=screenshot_url,
uuid=uuid,
@@ -907,7 +888,7 @@ def changedetection_app(config=None, datastore_o=None):
return output
@app.route("/preview/<string:uuid>", methods=['GET'])
@login_required
@login_optionally_required
def preview_page(uuid):
content = []
ignored_line_numbers = []
@@ -927,8 +908,9 @@ def changedetection_app(config=None, datastore_o=None):
extra_stylesheets = [url_for('static_content', group='styles', filename='diff.css')]
is_html_webdriver = True if watch.get('fetch_backend') == 'html_webdriver' or (
watch.get('fetch_backend', None) is None and system_uses_webdriver) else False
is_html_webdriver = False
if (watch.get('fetch_backend') == 'system' and system_uses_webdriver) or watch.get('fetch_backend') == 'html_webdriver':
is_html_webdriver = True
# Never requested successfully, but we detected a fetch error
if datastore.data['watching'][uuid].history_n == 0 and (watch.get_error_text() or watch.get_error_snapshot()):
@@ -997,7 +979,7 @@ def changedetection_app(config=None, datastore_o=None):
return output
@app.route("/settings/notification-logs", methods=['GET'])
@login_required
@login_optionally_required
def notification_logs():
global notification_debug_log
output = render_template("notification-log.html",
@@ -1007,7 +989,7 @@ def changedetection_app(config=None, datastore_o=None):
# We're good but backups are even better!
@app.route("/backup", methods=['GET'])
@login_required
@login_optionally_required
def get_backup():
import zipfile
@@ -1019,7 +1001,8 @@ def changedetection_app(config=None, datastore_o=None):
os.unlink(previous_backup_filename)
# create a ZipFile object
backupname = "changedetection-backup-{}.zip".format(int(time.time()))
timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
backupname = "changedetection-backup-{}.zip".format(timestamp)
backup_filepath = os.path.join(datastore_o.datastore_path, backupname)
with zipfile.ZipFile(backup_filepath, "w",
@@ -1127,13 +1110,14 @@ def changedetection_app(config=None, datastore_o=None):
abort(404)
@app.route("/form/add/quickwatch", methods=['POST'])
@login_required
@login_optionally_required
def form_quick_watch_add():
from changedetectionio import forms
form = forms.quickWatchForm(request.form)
if not form.validate():
flash("Error")
for widget, l in form.errors.items():
flash(','.join(l), 'error')
return redirect(url_for('index'))
url = request.form.get('url').strip()
@@ -1144,22 +1128,21 @@ def changedetection_app(config=None, datastore_o=None):
add_paused = request.form.get('edit_and_watch_submit_button') != None
new_uuid = datastore.add_watch(url=url, tag=request.form.get('tag').strip(), extras={'paused': add_paused})
if not add_paused and new_uuid:
# Straight into the queue.
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
flash("Watch added.")
if add_paused:
flash('Watch added in Paused state, saving will unpause.')
return redirect(url_for('edit_page', uuid=new_uuid, unpause_on_save=1))
if new_uuid:
if add_paused:
flash('Watch added in Paused state, saving will unpause.')
return redirect(url_for('edit_page', uuid=new_uuid, unpause_on_save=1))
else:
# Straight into the queue.
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid}))
flash("Watch added.")
return redirect(url_for('index'))
@app.route("/api/delete", methods=['GET'])
@login_required
@login_optionally_required
def form_delete():
uuid = request.args.get('uuid')
@@ -1176,7 +1159,7 @@ def changedetection_app(config=None, datastore_o=None):
return redirect(url_for('index'))
@app.route("/api/clone", methods=['GET'])
@login_required
@login_optionally_required
def form_clone():
uuid = request.args.get('uuid')
# More for testing, possible to return the first/only
@@ -1184,13 +1167,14 @@ def changedetection_app(config=None, datastore_o=None):
uuid = list(datastore.data['watching'].keys()).pop()
new_uuid = datastore.clone(uuid)
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
flash('Cloned.')
if new_uuid:
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
flash('Cloned.')
return redirect(url_for('index'))
@app.route("/api/checknow", methods=['GET'])
@login_required
@login_optionally_required
def form_watch_checknow():
# Forced recheck will skip the 'skip if content is the same' rule (, 'reprocess_existing_data': True})))
tag = request.args.get('tag')
@@ -1224,7 +1208,7 @@ def changedetection_app(config=None, datastore_o=None):
return redirect(url_for('index', tag=tag))
@app.route("/form/checkbox-operations", methods=['POST'])
@login_required
@login_optionally_required
def form_watch_list_checkbox_operations():
op = request.form['op']
uuids = request.form.getlist('uuids')
@@ -1288,7 +1272,7 @@ def changedetection_app(config=None, datastore_o=None):
return redirect(url_for('index'))
@app.route("/api/share-url", methods=['GET'])
@login_required
@login_optionally_required
def form_share_put_watch():
"""Given a watch UUID, upload the info and return a share-link
the share-link can be imported/added"""
@@ -1333,7 +1317,7 @@ def changedetection_app(config=None, datastore_o=None):
except Exception as e:
logging.error("Error sharing -{}".format(str(e)))
logger.error("Error sharing -{}".format(str(e)))
flash("Could not share, something went wrong while communicating with the share server - {}".format(str(e)), 'error')
# https://changedetection.io/share/VrMv05wpXyQa
@@ -1408,7 +1392,7 @@ def notification_runner():
sent_obj = notification.process_notification(n_object, datastore)
except Exception as e:
logging.error("Watch URL: {} Error {}".format(n_object['watch_url'], str(e)))
logger.error("Watch URL: {} Error {}".format(n_object['watch_url'], str(e)))
# UUID wont be present when we submit a 'test' from the global settings
if 'uuid' in n_object:
@@ -1431,7 +1415,7 @@ def ticker_thread_check_time_launch_checks():
proxy_last_called_time = {}
recheck_time_minimum_seconds = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 20))
print("System env MINIMUM_SECONDS_RECHECK_TIME", recheck_time_minimum_seconds)
logger.info("System env MINIMUM_SECONDS_RECHECK_TIME - {}", recheck_time_minimum_seconds)
# Spin up Workers that do the fetching
# Can be overriden by ENV or use the default settings
@@ -1476,7 +1460,7 @@ def ticker_thread_check_time_launch_checks():
now = time.time()
watch = datastore.data['watching'].get(uuid)
if not watch:
logging.error("Watch: {} no longer present.".format(uuid))
logger.error("Watch: {} no longer present.".format(uuid))
continue
# No need todo further processing if it's paused
@@ -1509,7 +1493,7 @@ def ticker_thread_check_time_launch_checks():
time_since_proxy_used = int(time.time() - proxy_last_used_time)
if time_since_proxy_used < proxy_list_reuse_time_minimum:
# Not enough time difference reached, skip this watch
print("> Skipped UUID {} using proxy '{}', not enough time between proxy requests {}s/{}s".format(uuid,
logger.info("> Skipped UUID {} using proxy '{}', not enough time between proxy requests {}s/{}s".format(uuid,
watch_proxy,
time_since_proxy_used,
proxy_list_reuse_time_minimum))
@@ -1520,7 +1504,7 @@ def ticker_thread_check_time_launch_checks():
# Use Epoch time as priority, so we get a "sorted" PriorityQueue, but we can still push a priority 1 into it.
priority = int(time.time())
print(
logger.info(
"> Queued watch UUID {} last checked at {} queued at {:0.2f} priority {} jitter {:0.2f}s, {:0.2f}s since last checked".format(
uuid,
watch['last_checked'],

View File

@@ -202,8 +202,11 @@ class CreateWatch(Resource):
del extras['url']
new_uuid = self.datastore.add_watch(url=url, extras=extras)
self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
return {'uuid': new_uuid}, 201
if new_uuid:
self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': new_uuid, 'skip_when_checksum_same': True}))
return {'uuid': new_uuid}, 201
else:
return "Invalid or unsupported URL", 400
@auth.check_token
def get(self):

View File

@@ -23,11 +23,10 @@
from distutils.util import strtobool
from flask import Blueprint, request, make_response
from flask_login import login_required
import os
import logging
from loguru import logger
from changedetectionio.store import ChangeDetectionStore
from changedetectionio import login_optionally_required
browsersteps_live_ui_o = {}
browsersteps_playwright_browser_interface = None
browsersteps_playwright_browser_interface_browser = None
@@ -50,7 +49,7 @@ def cleanup_playwright_session():
browsersteps_playwright_browser_interface_end_time = None
browsersteps_playwright_browser_interface_start_time = None
print("Cleaning up old playwright session because time was up, calling .goodbye()")
logger.info("Cleaning up old playwright session because time was up, calling .goodbye()")
try:
browsersteps_playwright_browser_interface_context.goodbye()
except Exception as e:
@@ -65,7 +64,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
browser_steps_blueprint = Blueprint('browser_steps', __name__, template_folder="templates")
@login_required
@login_optionally_required
@browser_steps_blueprint.route("/browsersteps_update", methods=['GET', 'POST'])
def browsersteps_ui_update():
import base64
@@ -115,7 +114,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
this_session = browsersteps_live_ui_o.get(browsersteps_session_id)
if not this_session:
print("Browser exited")
logger.info("Browser exited")
return make_response('Browser session ran out of time :( Please reload this page.', 401)
this_session.call_action(action_name=step_operation,
@@ -123,7 +122,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
optional_value=step_optional_value)
except Exception as e:
print("Exception when calling step operation", step_operation, str(e))
logger.info("Exception when calling step operation", step_operation, str(e))
# Try to find something of value to give back to the user
return make_response(str(e).splitlines()[0], 401)
@@ -140,7 +139,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
if request.method == 'GET':
if not browsersteps_playwright_browser_interface:
print("Starting connection with playwright")
logger.info("Starting connection with playwright")
logging.debug("browser_steps.py connecting")
global browsersteps_playwright_browser_interface_context
@@ -163,7 +162,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
return make_response('Unable to start the Playwright session properly, is it running?', 401)
browsersteps_playwright_browser_interface_end_time = time.time() + (seconds_keepalive-3)
print("Starting connection with playwright - done")
logger.info("Starting connection with playwright - done")
if not browsersteps_live_ui_o.get(browsersteps_session_id):
# Boot up a new session
@@ -173,7 +172,7 @@ def construct_blueprint(datastore: ChangeDetectionStore):
proxy_url = datastore.proxy_list.get(proxy_id).get('url')
if proxy_url:
proxy = {'server': proxy_url}
print("Browser Steps: UUID {} Using proxy {}".format(uuid, proxy_url))
logger.info("Browser Steps: UUID {} Using proxy {}".format(uuid, proxy_url))
# Begin the new "Playwright Context" that re-uses the playwright interface
# Each session is a "Playwright Context" as a list, that uses the playwright interface

View File

@@ -51,7 +51,7 @@ class steppable_browser_interface():
if call_action_name == 'choose_one':
return
print("> action calling", call_action_name)
logger.info("> action calling", call_action_name)
# https://playwright.dev/python/docs/selectors#xpath-selectors
if selector.startswith('/') and not selector.startswith('//'):
selector = "xpath=" + selector
@@ -70,7 +70,7 @@ class steppable_browser_interface():
action_handler(selector, optional_value)
self.page.wait_for_timeout(3 * 1000)
print("Call action done in", time.time() - now)
logger.info("Call action done in", time.time() - now)
def action_goto_url(self, url, optional_value):
# self.page.set_viewport_size({"width": 1280, "height": 5000})
@@ -81,7 +81,7 @@ class steppable_browser_interface():
# - `'commit'` - consider operation to be finished when network response is received and the document started loading.
# Better to not use any smarts from Playwright and just wait an arbitrary number of seconds
# This seemed to solve nearly all 'TimeoutErrors'
print("Time to goto URL ", time.time() - now)
logger.info("Time to goto URL ", time.time() - now)
def action_click_element_containing_text(self, selector=None, value=''):
if not len(value.strip()):
@@ -100,14 +100,14 @@ class steppable_browser_interface():
self.page.evaluate(value)
def action_click_element(self, selector, value):
print("Clicking element")
logger.info("Clicking element")
if not len(selector.strip()):
return
self.page.click(selector, timeout=10 * 1000, delay=randint(200, 500))
def action_click_element_if_exists(self, selector, value):
import playwright._impl._api_types as _api_types
print("Clicking element if exists")
logger.info("Clicking element if exists")
if not len(selector.strip()):
return
try:
@@ -207,13 +207,13 @@ class browsersteps_live_ui(steppable_browser_interface):
self.mark_as_closed,
)
# Listen for all console events and handle errors
self.page.on("console", lambda msg: print(f"Browser steps console - {msg.type}: {msg.text} {msg.args}"))
self.page.on("console", lambda msg: logger.info(f"Browser steps console - {msg.type}: {msg.text} {msg.args}"))
print("Time to browser setup", time.time() - now)
logger.info("Time to browser setup", time.time() - now)
self.page.wait_for_timeout(1 * 1000)
def mark_as_closed(self):
print("Page closed, cleaning up..")
logger.info("Page closed, cleaning up..")
@property
def has_expired(self):
@@ -239,7 +239,7 @@ class browsersteps_live_ui(steppable_browser_interface):
xpath_data = self.page.evaluate("async () => {" + xpath_element_js + "}")
# So the JS will find the smallest one first
xpath_data['size_pos'] = sorted(xpath_data['size_pos'], key=lambda k: k['width'] * k['height'], reverse=True)
print("Time to complete get_current_state of browser", time.time() - now)
logger.info("Time to complete get_current_state of browser", time.time() - now)
# except
# playwright._impl._api_types.Error: Browser closed.
# @todo show some countdown timer?

View File

@@ -8,6 +8,7 @@ from json.decoder import JSONDecodeError
import eventlet
import eventlet.wsgi
import getopt
from loguru import logger
import os
import signal
import socket
@@ -24,7 +25,7 @@ def sigterm_handler(_signo, _stack_frame):
global app
global datastore
# app.config.exit.set()
print('Shutdown: Got SIGTERM, DB saved to disk')
logger.warning('Shutdown: Got SIGTERM, DB saved to disk')
datastore.sync_to_json()
# raise SystemExit

View File

@@ -2,7 +2,7 @@ import hashlib
from abc import abstractmethod
import chardet
import json
import logging
from loguru import logger
import os
import requests
import sys
@@ -155,7 +155,7 @@ class Fetcher():
for step in valid_steps:
step_n += 1
print(">> Iterating check - browser Step n {} - {}...".format(step_n, step['operation']))
logger.info(">> Iterating check - browser Step n {} - {}...".format(step_n, step['operation']))
self.screenshot_step("before-"+str(step_n))
self.save_step_html("before-"+str(step_n))
try:
@@ -252,9 +252,6 @@ class base_html_playwright(Fetcher):
self.proxy['password'] = parsed.password
def screenshot_step(self, step_n=''):
# There's a bug where we need to do it twice or it doesnt take the whole page, dont know why.
self.page.screenshot(type='jpeg', clip={'x': 1.0, 'y': 1.0, 'width': 1280, 'height': 1024})
screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=85)
if self.browser_steps_screenshot_path is not None:
@@ -300,8 +297,8 @@ class base_html_playwright(Fetcher):
proxy=self.proxy,
# This is needed to enable JavaScript execution on GitHub and others
bypass_csp=True,
# Can't think why we need the service workers for our use case?
service_workers='block',
# Should be `allow` or `block` - sites like YouTube can transmit large amounts of data via Service Workers
service_workers=os.getenv('PLAYWRIGHT_SERVICE_WORKERS', 'allow'),
# Should never be needed
accept_downloads=False
)
@@ -361,28 +358,20 @@ class base_html_playwright(Fetcher):
print ("Content Fetcher > Response object was none")
raise EmptyReply(url=url, status_code=None)
# Bug 2(?) Set the viewport size AFTER loading the page
self.page.set_viewport_size({"width": 1280, "height": 1024})
# Run Browser Steps here
self.iterate_browser_steps()
extra_wait = int(os.getenv("WEBDRIVER_DELAY_BEFORE_CONTENT_READY", 5)) + self.render_extract_delay
time.sleep(extra_wait)
self.content = self.page.content()
self.status_code = response.status
if len(self.page.content().strip()) == 0:
context.close()
browser.close()
print ("Content Fetcher > Content was empty")
raise EmptyReply(url=url, status_code=response.status)
# Bug 2(?) Set the viewport size AFTER loading the page
self.page.set_viewport_size({"width": 1280, "height": 1024})
self.status_code = response.status
self.content = self.page.content()
self.headers = response.all_headers()
@@ -403,8 +392,6 @@ class base_html_playwright(Fetcher):
# which will significantly increase the IO size between the server and client, it's recommended to use the lowest
# acceptable screenshot quality here
try:
# Quality set to 1 because it's not used, just used as a work-around for a bug, no need to change this.
self.page.screenshot(type='jpeg', clip={'x': 1.0, 'y': 1.0, 'width': 1280, 'height': 1024}, quality=1)
# The actual screenshot
self.screenshot = self.page.screenshot(type='jpeg', full_page=True, quality=int(os.getenv("PLAYWRIGHT_SCREENSHOT_QUALITY", 72)))
except Exception as e:
@@ -523,7 +510,7 @@ class base_html_webdriver(Fetcher):
try:
self.driver.quit()
except Exception as e:
print("Content Fetcher > Exception in chrome shutdown/quit" + str(e))
logger.error("Content Fetcher > Exception in chrome shutdown/quit" + str(e))
# "html_requests" is listed as the default fetcher in store.py!

View File

@@ -1,6 +1,6 @@
import hashlib
import json
import logging
from loguru import logger
import os
import re
import urllib3
@@ -105,7 +105,7 @@ class perform_site_check():
proxy_url = None
if proxy_id:
proxy_url = self.datastore.proxy_list.get(proxy_id).get('url')
print("UUID {} Using proxy {}".format(uuid, proxy_url))
logger.info("UUID {} Using proxy {}".format(uuid, proxy_url))
fetcher = klass(proxy_override=proxy_url)
@@ -135,7 +135,7 @@ class perform_site_check():
# Track the content type
update_obj['content_type'] = fetcher.headers.get('Content-Type', '')
logger.info("UUID: {} - Fetch complete {:,} bytes".format(watch.get('uuid'), len(fetcher.content)))
# Watches added automatically in the queue manager will skip if its the same checksum as the previous run
# Saves a lot of CPU
update_obj['previous_md5_before_filters'] = hashlib.md5(fetcher.content.encode('utf-8')).hexdigest()
@@ -349,6 +349,7 @@ class perform_site_check():
# The main thing that all this at the moment comes down to :)
if watch.get('previous_md5') != fetched_md5:
logger.debug("UUID: {} - Change detected - Prev MD5: {} - Fetched MD5: {}, applying filters...".format(uuid, watch.get('previous_md5'), fetched_md5))
changed_detected = True
# Looks like something changed, but did it match all the rules?
@@ -366,10 +367,10 @@ class perform_site_check():
has_unique_lines = watch.lines_contain_something_unique_compared_to_history(lines=stripped_text_from_html.splitlines())
# One or more lines? unsure?
if not has_unique_lines:
logging.debug("check_unique_lines: UUID {} didnt have anything new setting change_detected=False".format(uuid))
logger.debug("check_unique_lines: UUID {} didnt have anything new setting change_detected=False".format(uuid))
changed_detected = False
else:
logging.debug("check_unique_lines: UUID {} had unique content".format(uuid))
logger.debug("check_unique_lines: UUID {} had unique content".format(uuid))
# Always record the new checksum
update_obj["previous_md5"] = fetched_md5
@@ -378,4 +379,9 @@ class perform_site_check():
if not watch.get('previous_md5'):
watch['previous_md5'] = fetched_md5
if changed_detected:
logger.success("UUID: {} Change detected after all filters applied.", uuid)
else:
logger.info("UUID: {} NO Change detected after all filters applied.", uuid)
return changed_detected, update_obj, text_content_before_ignored_filter

View File

@@ -232,12 +232,17 @@ class validateURL(object):
def __call__(self, form, field):
import validators
try:
validators.url(field.data.strip())
except validators.ValidationFailure:
message = field.gettext('\'%s\' is not a valid URL.' % (field.data.strip()))
raise ValidationError(message)
from .model.Watch import is_safe_url
if not is_safe_url(field.data):
raise ValidationError('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX')
class ValidateListRegex(object):
"""
@@ -454,17 +459,17 @@ class globalSettingsRequestForm(Form):
# datastore.data['settings']['application']..
class globalSettingsApplicationForm(commonSettingsForm):
base_url = StringField('Base URL', validators=[validators.Optional()])
global_subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
ignore_whitespace = BooleanField('Ignore whitespace')
removepassword_button = SubmitField('Remove password', render_kw={"class": "pure-button pure-button-primary"})
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()])
base_url = StringField('Base URL', validators=[validators.Optional()])
empty_pages_are_a_change = BooleanField('Treat empty pages as a change?', default=False)
fetch_backend = RadioField('Fetch Method', default="html_requests", choices=content_fetcher.available_fetchers(), validators=[ValidateContentFetcherIsReady()])
global_ignore_text = StringListField('Ignore Text', [ValidateListRegex()])
global_subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
ignore_whitespace = BooleanField('Ignore whitespace')
password = SaltyPasswordField()
removepassword_button = SubmitField('Remove password', render_kw={"class": "pure-button pure-button-primary"})
render_anchor_tag_content = BooleanField('Render anchor tag content', default=False)
shared_diff_access = BooleanField('Allow access to view diff page when password is enabled', default=False, validators=[validators.Optional()])
filter_failure_notification_threshold_attempts = IntegerField('Number of times the filter can be missing before sending a notification',
render_kw={"style": "width: 5em;"},
validators=[validators.NumberRange(min=0,

View File

@@ -40,6 +40,7 @@ class model(dict):
'notification_body': default_notification_body,
'notification_format': default_notification_format,
'schema_version' : 0,
'shared_diff_access': False,
'webdriver_delay': None # Extra delay in seconds before extracting text
}
}

View File

@@ -1,9 +1,14 @@
from distutils.util import strtobool
import logging
from loguru import logger
import os
import re
import time
import uuid
# Allowable protocols, protects against javascript: etc
# file:// is further checked by ALLOW_FILE_URI
SAFE_PROTOCOL_REGEX='^(http|https|ftp|file):'
minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 60))
mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
@@ -55,6 +60,22 @@ base_config = {
'webdriver_js_execute_code': None, # Run before change-detection
}
def is_safe_url(test_url):
# See https://github.com/dgtlmoon/changedetection.io/issues/1358
# Remove 'source:' prefix so we dont get 'source:javascript:' etc
# 'source:' is a valid way to tell us to return the source
r = re.compile(re.escape('source:'), re.IGNORECASE)
test_url = r.sub('', test_url)
pattern = re.compile(os.getenv('SAFE_PROTOCOL_REGEX', SAFE_PROTOCOL_REGEX), re.IGNORECASE)
if not pattern.match(test_url.strip()):
return False
return True
class model(dict):
__newest_history_key = None
__history_n = 0
@@ -88,12 +109,16 @@ class model(dict):
def ensure_data_dir_exists(self):
if not os.path.isdir(self.watch_data_dir):
print ("> Creating data dir {}".format(self.watch_data_dir))
logger.debug("> Creating data dir {}".format(self.watch_data_dir))
os.mkdir(self.watch_data_dir)
@property
def link(self):
url = self.get('url', '')
if not is_safe_url(url):
return 'DISABLED'
ready_url = url
if '{%' in url or '{{' in url:
from jinja2 import Environment
@@ -128,7 +153,9 @@ class model(dict):
@property
def is_pdf(self):
# content_type field is set in the future
return '.pdf' in self.get('url', '').lower() or 'pdf' in self.get('content_type', '').lower()
# https://github.com/dgtlmoon/changedetection.io/issues/1392
# Not sure the best logic here
return self.get('url', '').lower().endswith('.pdf') or 'pdf' in self.get('content_type', '').lower()
@property
def label(self):
@@ -167,7 +194,7 @@ class model(dict):
# Read the history file as a dict
fname = os.path.join(self.watch_data_dir, "history.txt")
if os.path.isfile(fname):
logging.debug("Reading history index " + str(time.time()))
logger.debug("UUID: {} Reading history index".format(self.get('uuid')))
with open(fname, "r") as f:
for i in f.readlines():
if ',' in i:

View File

@@ -101,7 +101,7 @@ def process_notification(n_object, datastore):
apobj = apprise.Apprise(debug=True, asset=asset)
url = url.strip()
if len(url):
print(">> Process Notification: AppRise notifying {}".format(url))
logger.info(">> Process Notification: AppRise notifying {}".format(url))
with apprise.LogCapture(level=apprise.logging.DEBUG) as logs:
# Re 323 - Limit discord length to their 2000 char limit total or it wont send.
# Because different notifications may require different pre-processing, run each sequentially :(

View File

@@ -1,20 +1,20 @@
from flask import (
flash
)
import json
import logging
import os
import threading
import time
import uuid as uuid_builder
from . model import App, Watch
from copy import deepcopy
from os import path, unlink
from threading import Lock
import json
from loguru import logger
import os
import re
import requests
import secrets
from . model import App, Watch
import threading
import time
import uuid as uuid_builder
# Is there an existing library to ensure some data store (JSON etc) is in sync with CRUD methods?
# Open a github issue if you know something :)
@@ -75,12 +75,12 @@ class ChangeDetectionStore:
for uuid, watch in self.__data['watching'].items():
watch['uuid']=uuid
self.__data['watching'][uuid] = Watch.model(datastore_path=self.datastore_path, default=watch)
print("Watching:", uuid, self.__data['watching'][uuid]['url'])
logger.info("Watching: {} - {}", uuid, self.__data['watching'][uuid]['url'])
# First time ran, Create the datastore.
except (FileNotFoundError):
if include_default_watches:
print("No JSON DB found at {}, creating JSON store at {}".format(self.json_store_path, self.datastore_path))
logger.info("No JSON DB found at {}, creating JSON store at {}".format(self.json_store_path, self.datastore_path))
self.add_watch(url='https://news.ycombinator.com/',
tag='Tech news',
extras={'fetch_backend': 'html_requests'})
@@ -192,27 +192,24 @@ class ChangeDetectionStore:
tags.sort()
return tags
def unlink_history_file(self, path):
try:
unlink(path)
except (FileNotFoundError, IOError):
pass
# Delete a single watch by UUID
def delete(self, uuid):
import pathlib
import shutil
with self.lock:
if uuid == 'all':
self.__data['watching'] = {}
# GitHub #30 also delete history records
for uuid in self.data['watching']:
for path in self.data['watching'][uuid].history.values():
self.unlink_history_file(path)
path = pathlib.Path(os.path.join(self.datastore_path, uuid))
shutil.rmtree(path)
self.needs_write_urgent = True
else:
for path in self.data['watching'][uuid].history.values():
self.unlink_history_file(path)
path = pathlib.Path(os.path.join(self.datastore_path, uuid))
shutil.rmtree(path)
del self.data['watching'][uuid]
self.needs_write_urgent = True
@@ -306,12 +303,15 @@ class ChangeDetectionStore:
apply_extras['include_filters'] = [res['css_filter']]
except Exception as e:
logging.error("Error fetching metadata for shared watch link", url, str(e))
logger.error("Error fetching metadata for shared watch link", url, str(e))
flash("Error fetching metadata for {}".format(url), 'error')
return False
from .model.Watch import is_safe_url
if not is_safe_url(url):
flash('Watch protocol is not permitted by SAFE_PROTOCOL_REGEX', 'error')
return None
with self.lock:
# #Re 569
new_watch = Watch.model(datastore_path=self.datastore_path, default={
'url': url,
@@ -388,14 +388,13 @@ class ChangeDetectionStore:
def sync_to_json(self):
logging.info("Saving JSON..")
print("Saving JSON..")
logger.debug("Saving JSON DB")
try:
data = deepcopy(self.__data)
except RuntimeError as e:
# Try again in 15 seconds
time.sleep(15)
logging.error ("! Data changed when writing to JSON, trying again.. %s", str(e))
logger.error ("! Data changed when writing to JSON, trying again.. %s", str(e))
self.sync_to_json()
return
else:
@@ -408,7 +407,7 @@ class ChangeDetectionStore:
json.dump(data, json_file, indent=4)
os.replace(self.json_store_path+".tmp", self.json_store_path)
except Exception as e:
logging.error("Error writing JSON!! (Main JSON file save was skipped) : %s", str(e))
logger.error("Error writing JSON!! (Main JSON file save was skipped) : %s", str(e))
self.needs_write = False
self.needs_write_urgent = False
@@ -419,7 +418,7 @@ class ChangeDetectionStore:
while True:
if self.stop_thread:
print("Shutting down datastore thread")
logger.info("Shutting down datastore thread")
return
if self.needs_write or self.needs_write_urgent:
@@ -533,8 +532,8 @@ class ChangeDetectionStore:
try:
update_method = getattr(self, "update_{}".format(update_n))()
except Exception as e:
print("Error while trying update_{}".format((update_n)))
print(e)
logger.error("Error while trying update_{}".format((update_n)))
logger.error(str(e))
# Don't run any more updates
return
else:
@@ -572,7 +571,7 @@ class ChangeDetectionStore:
with open(os.path.join(target_path, "history.txt"), "w") as f:
f.writelines(history)
else:
logging.warning("Datastore history directory {} does not exist, skipping history import.".format(target_path))
logger.warning("Datastore history directory {} does not exist, skipping history import.".format(target_path))
# No longer needed, dynamically pulled from the disk when needed.
# But we should set it back to a empty dict so we don't break if this schema runs on an earlier version.

View File

@@ -76,8 +76,12 @@
</div>
<div class="tab-pane-inner" id="text">
<div class="tip">Pro-tip: Use <strong>show current snapshot</strong> tab to visualise what will be ignored.
</div>
<div class="tip">Pro-tip: Use <strong>show current snapshot</strong> tab to visualise what will be ignored.</div>
{% if password_enabled_and_share_is_off %}
<div class="tip">Pro-tip: You can enable <strong>"share access when password is enabled"</strong> from settings</div>
{% endif %}
<div class="snapshot-age">{{watch_a.snapshot_text_ctime|format_timestamp_timeago}}</div>
<table>

View File

@@ -57,6 +57,11 @@
{% endif %}
</div>
<div class="pure-control-group">
{{ render_checkbox_field(form.application.form.shared_diff_access, class="shared_diff_access") }}
<span class="pure-form-message-inline">Allow access to view watch diff page when password is enabled (Good for sharing the diff page)
</span>
</div>
<div class="pure-control-group">
{{ render_field(form.application.form.base_url, placeholder="http://yoursite.com:5000/",
class="m-d") }}

View File

@@ -1,18 +1,34 @@
from . util import live_server_setup, extract_UUID_from_client
from flask import url_for
from . util import live_server_setup
import time
def test_check_access_control(app, client):
def test_check_access_control(app, client, live_server):
# Still doesnt work, but this is closer.
live_server_setup(live_server)
with app.test_client(use_cookies=True) as c:
# Check we don't have any password protection enabled yet.
res = c.get(url_for("settings_page"))
assert b"Remove password" not in res.data
# Enable password check.
# add something that we can hit via diff page later
res = c.post(
url_for("import_page"),
data={"urls": url_for('test_random_content_endpoint', _external=True)},
follow_redirects=True
)
assert b"1 Imported" in res.data
time.sleep(2)
res = client.get(url_for("form_watch_checknow"), follow_redirects=True)
assert b'1 watches queued for rechecking.' in res.data
time.sleep(2)
# Enable password check and diff page access bypass
res = c.post(
url_for("settings_page"),
data={"application-password": "foobar",
"application-shared_diff_access": "True",
"requests-time_between_check-minutes": 180,
'application-fetch_backend': "html_requests"},
follow_redirects=True
@@ -22,9 +38,15 @@ def test_check_access_control(app, client):
# Check we hit the login
res = c.get(url_for("index"), follow_redirects=True)
# Should be logged out
assert b"Login" in res.data
# The diff page should return something valid when logged out
res = client.get(url_for("diff_history_page", uuid="first"))
assert b'Random content' in res.data
# Menu should not be available yet
# assert b"SETTINGS" not in res.data
# assert b"BACKUP" not in res.data
@@ -109,3 +131,25 @@ def test_check_access_control(app, client):
assert b"Password protection enabled" not in res.data
# Now checking the diff access
# Enable password check and diff page access bypass
res = c.post(
url_for("settings_page"),
data={"application-password": "foobar",
# Should be disabled
# "application-shared_diff_access": "True",
"requests-time_between_check-minutes": 180,
'application-fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Password protection enabled." in res.data
# Check we hit the login
res = c.get(url_for("index"), follow_redirects=True)
# Should be logged out
assert b"Login" in res.data
# The diff page should return something valid when logged out
res = client.get(url_for("diff_history_page", uuid="first"))
assert b'Random content' not in res.data

View File

@@ -3,7 +3,7 @@
import time
from flask import url_for
from urllib.request import urlopen
from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, extract_rss_token_from_UI
sleep_time_for_fetch_thread = 3
@@ -76,7 +76,8 @@ def test_check_basic_change_detection_functionality(client, live_server):
assert b'unviewed' in res.data
# #75, and it should be in the RSS feed
res = client.get(url_for("rss"))
rss_token = extract_rss_token_from_UI(client)
res = client.get(url_for("rss", token=rss_token, _external=True))
expected_url = url_for('test_endpoint', _external=True)
assert b'<rss' in res.data

View File

@@ -69,8 +69,6 @@ def test_filter_doesnt_exist_then_exists_should_get_notification(client, live_se
url = url_for('test_notification_endpoint', _external=True)
notification_url = url.replace('http', 'json')
print(">>>> Notification URL: " + notification_url)
# Just a regular notification setting, this will be used by the special 'filter not found' notification
notification_form_data = {"notification_urls": notification_url,
"notification_title": "New ChangeDetection.io Notification - {{watch_url}}",

View File

@@ -0,0 +1,39 @@
#!/usr/bin/python3
import time
from flask import url_for
from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, extract_rss_token_from_UI
def test_rss_and_token(client, live_server):
set_original_response()
live_server_setup(live_server)
# Add our URL to the import page
res = client.post(
url_for("import_page"),
data={"urls": url_for('test_random_content_endpoint', _external=True)},
follow_redirects=True
)
assert b"1 Imported" in res.data
rss_token = extract_rss_token_from_UI(client)
time.sleep(2)
client.get(url_for("form_watch_checknow"), follow_redirects=True)
time.sleep(2)
# Add our URL to the import page
res = client.get(
url_for("rss", token="bad token", _external=True),
follow_redirects=True
)
assert b"Access denied, bad token" in res.data
res = client.get(
url_for("rss", token=rss_token, _external=True),
follow_redirects=True
)
assert b"Access denied, bad token" not in res.data
assert b"Random content" in res.data

View File

@@ -2,11 +2,9 @@ from flask import url_for
from . util import set_original_response, set_modified_response, live_server_setup
import time
def test_setup(live_server):
def test_bad_access(client, live_server):
live_server_setup(live_server)
def test_file_access(client, live_server):
res = client.post(
url_for("import_page"),
data={"urls": 'https://localhost'},
@@ -19,18 +17,49 @@ def test_file_access(client, live_server):
res = client.post(
url_for("edit_page", uuid="first"),
data={
"url": 'file:///etc/passwd',
"url": 'javascript:alert(document.domain)',
"tag": "",
"method": "GET",
"fetch_backend": "html_requests",
"body": ""},
follow_redirects=True
)
time.sleep(3)
res = client.get(
url_for("index", uuid="first"),
assert b'Watch protocol is not permitted by SAFE_PROTOCOL_REGEX' in res.data
res = client.post(
url_for("form_quick_watch_add"),
data={"url": ' javascript:alert(123)', "tag": ''},
follow_redirects=True
)
assert b'denied for security reasons' in res.data
assert b'Watch protocol is not permitted by SAFE_PROTOCOL_REGEX' in res.data
res = client.post(
url_for("form_quick_watch_add"),
data={"url": '%20%20%20javascript:alert(123)%20%20', "tag": ''},
follow_redirects=True
)
assert b'Watch protocol is not permitted by SAFE_PROTOCOL_REGEX' in res.data
res = client.post(
url_for("form_quick_watch_add"),
data={"url": ' source:javascript:alert(document.domain)', "tag": ''},
follow_redirects=True
)
assert b'Watch protocol is not permitted by SAFE_PROTOCOL_REGEX' in res.data
# file:// is permitted by default, but it will be caught by ALLOW_FILE_URI
client.post(
url_for("form_quick_watch_add"),
data={"url": 'file:///tasty/disk/drive', "tag": ''},
follow_redirects=True
)
time.sleep(1)
res = client.get(url_for("index"))
assert b'file:// type access is denied for security reasons.' in res.data

View File

@@ -70,6 +70,15 @@ def extract_api_key_from_UI(client):
api_key = m.group(1)
return api_key.strip()
# kinda funky, but works for now
def extract_rss_token_from_UI(client):
import re
res = client.get(
url_for("index"),
)
m = re.search('token=(.+?)"', str(res.data))
token_key = m.group(1)
return token_key.strip()
# kinda funky, but works for now
def extract_UUID_from_client(client):
@@ -98,6 +107,12 @@ def wait_for_all_checks(client):
def live_server_setup(live_server):
@live_server.app.route('/test-random-content-endpoint')
def test_random_content_endpoint():
import secrets
return "Random content - {}\n".format(secrets.token_hex(64))
@live_server.app.route('/test-endpoint')
def test_endpoint():
ctype = request.args.get('content_type')

View File

@@ -2,6 +2,7 @@ import os
import threading
import queue
import time
from loguru import logger
from changedetectionio import content_fetcher
from changedetectionio import queuedWatchMetaData
@@ -12,14 +13,12 @@ from changedetectionio.fetch_site_status import FilterNotFoundInResponse
# Requests for checking on a single site(watch) from a queue of watches
# (another process inserts watches into the queue that are time-ready for checking)
import logging
import sys
class update_worker(threading.Thread):
current_uuid = None
def __init__(self, q, notification_q, app, datastore, *args, **kwargs):
logging.basicConfig(stream=sys.stderr, level=logging.DEBUG)
self.q = q
self.app = app
self.notification_q = notification_q
@@ -80,10 +79,10 @@ class update_worker(threading.Thread):
'diff': diff.render_diff(watch_history[dates[-2]], watch_history[dates[-1]], line_feed_sep=line_feed_sep),
'diff_full': diff.render_diff(watch_history[dates[-2]], watch_history[dates[-1]], True, line_feed_sep=line_feed_sep)
})
logging.info (">> SENDING NOTIFICATION")
logger.info ("UUID: {} - Sending notification".format(watch_uuid))
self.notification_q.put(n_object)
else:
logging.info (">> NO Notification sent, notification_url was empty in both watch and system")
logger.info("UUID: {} - NO Notification sent, notification_url was empty in both watch and system".format(watch_uuid))
def send_filter_failure_notification(self, watch_uuid):
@@ -112,7 +111,7 @@ class update_worker(threading.Thread):
'screenshot': None
})
self.notification_q.put(n_object)
print("Sent filter not found notification for {}".format(watch_uuid))
logger.info("Sent filter not found notification for {}".format(watch_uuid))
def send_step_failure_notification(self, watch_uuid, step_n):
watch = self.datastore.data['watching'].get(watch_uuid, False)
@@ -139,7 +138,7 @@ class update_worker(threading.Thread):
'uuid': watch_uuid
})
self.notification_q.put(n_object)
print("Sent step not found notification for {}".format(watch_uuid))
logger.error("Sent step not found notification for {}".format(watch_uuid))
def cleanup_error_artifacts(self, uuid):
@@ -173,7 +172,7 @@ class update_worker(threading.Thread):
update_obj= {}
xpath_data = False
process_changedetection_results = True
print("> Processing UUID {} Priority {} URL {}".format(uuid, queued_item_data.priority, self.datastore.data['watching'][uuid]['url']))
logger.info("UUID: {} Start processing, Priority {} URL {}",uuid, queued_item_data.priority, self.datastore.data['watching'][uuid]['url'])
now = time.time()
try:
@@ -184,7 +183,7 @@ class update_worker(threading.Thread):
if not isinstance(contents, (bytes, bytearray)):
raise Exception("Error - returned data from the fetch handler SHOULD be bytes")
except PermissionError as e:
self.app.logger.error("File permission error updating", uuid, str(e))
logger.error("UUID: {} File permission error updating - {}", uuid, str(e))
process_changedetection_results = False
except content_fetcher.ReplyWithContentButNoText as e:
# Totally fine, it's by choice - just continue on, nothing more to care about
@@ -233,7 +232,7 @@ class update_worker(threading.Thread):
# Send notification if we reached the threshold?
threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts',
0)
print("Filter for {} not found, consecutive_filter_failures: {}".format(uuid, c))
logger.error("Filter for {} not found, consecutive_filter_failures: {}".format(uuid, c))
if threshold > 0 and c >= threshold:
if not self.datastore.data['watching'][uuid].get('notification_muted'):
self.send_filter_failure_notification(uuid)
@@ -264,7 +263,7 @@ class update_worker(threading.Thread):
# Send notification if we reached the threshold?
threshold = self.datastore.data['settings']['application'].get('filter_failure_notification_threshold_attempts',
0)
print("Step for {} not found, consecutive_filter_failures: {}".format(uuid, c))
logger.error("Step for {} not found, consecutive_filter_failures: {}".format(uuid, c))
if threshold > 0 and c >= threshold:
if not self.datastore.data['watching'][uuid].get('notification_muted'):
self.send_step_failure_notification(watch_uuid=uuid, step_n=e.step_n)
@@ -330,8 +329,6 @@ class update_worker(threading.Thread):
# A change was detected
if changed_detected:
print (">> Change detected in UUID {} - {}".format(uuid, watch['url']))
# Notifications should only trigger on the second time (first time, we gather the initial snapshot)
if watch.history_n >= 2:
if not self.datastore.data['watching'][uuid].get('notification_muted'):
@@ -340,7 +337,7 @@ class update_worker(threading.Thread):
except Exception as e:
# Catch everything possible here, so that if a worker crashes, we don't lose it until restart!
print("!!!! Exception in update_worker !!!\n", e)
logger.error("!!!! Exception in update_worker !!!\n", e)
self.app.logger.error("Exception reached processing watch UUID: %s - %s", uuid, str(e))
self.datastore.update_watch(uuid=uuid, update_obj={'last_error': str(e)})

View File

@@ -41,7 +41,6 @@ services:
#
# Base URL of your changedetection.io install (Added to the notification alert)
# - BASE_URL=https://mysite.com
# 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
@@ -95,7 +94,10 @@ services:
# - CHROME_REFRESH_TIME=600000
# - DEFAULT_BLOCK_ADS=true
# - DEFAULT_STEALTH=true
#
# Ignore HTTPS errors, like for self-signed certs
# - DEFAULT_IGNORE_HTTPS_ERRORS=true
#
volumes:
changedetection-data:

View File

@@ -10,6 +10,7 @@ inscriptis~=2.2
pytz
timeago~=1.0
validators
loguru
# Set these versions together to avoid a RequestsDependencyWarning
# >= 2.26 also adds Brotli support if brotli is installed