Compare commits

..

5 Commits

Author SHA1 Message Date
dgtlmoon
a4b3a752f2 woops 2024-10-11 11:10:46 +02:00
dgtlmoon
242aae77e7 Update test_restock_itemprop.py 2024-10-11 10:41:31 +02:00
dgtlmoon
64cdd486f4 remove setup 2024-10-11 10:18:35 +02:00
dgtlmoon
b9dd874ad1 import fixes 2024-10-11 09:58:36 +02:00
dgtlmoon
9ab60def52 Restock multiprice improvements 2024-10-11 09:52:04 +02:00
40 changed files with 187 additions and 718 deletions

1
.gitignore vendored
View File

@@ -10,6 +10,5 @@ dist
venv
test-datastore/*
test-datastore
test-memory.log
*.egg-info*
.vscode/settings.json

View File

@@ -1,5 +1,4 @@
recursive-include changedetectionio/api *
recursive-include changedetectionio/apprise_plugin *
recursive-include changedetectionio/blueprint *
recursive-include changedetectionio/content_fetchers *
recursive-include changedetectionio/model *

View File

@@ -2,7 +2,7 @@
# Read more https://github.com/dgtlmoon/changedetection.io/wiki
__version__ = '0.47.05'
__version__ = '0.46.04'
from changedetectionio.strtobool import strtobool
from json.decoder import JSONDecodeError

View File

@@ -58,7 +58,7 @@ class Watch(Resource):
abort(404, message='No watch exists with the UUID of {}'.format(uuid))
if request.args.get('recheck'):
self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
return "OK", 200
if request.args.get('paused', '') == 'paused':
self.datastore.data['watching'].get(uuid).pause()
@@ -246,7 +246,7 @@ class CreateWatch(Resource):
new_uuid = self.datastore.add_watch(url=url, extras=extras, tag=tags)
if new_uuid:
self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': 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
@@ -303,7 +303,7 @@ class CreateWatch(Resource):
if request.args.get('recheck_all'):
for uuid in self.datastore.data['watching'].keys():
self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
self.update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
return {'status': "OK"}, 200
return list, 200

View File

@@ -13,7 +13,6 @@ from loguru import logger
def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
import requests
import json
from urllib.parse import unquote_plus
from apprise.utils import parse_url as apprise_parse_url
from apprise import URLBase
@@ -48,7 +47,7 @@ def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
if results:
# Add our headers that the user can potentially over-ride if they wish
# to to our returned result set and tidy entries by unquoting them
headers = {unquote_plus(x): unquote_plus(y)
headers = {URLBase.unquote(x): URLBase.unquote(y)
for x, y in results['qsd+'].items()}
# https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#get-parameter-manipulation
@@ -56,14 +55,14 @@ def apprise_custom_api_call_wrapper(body, title, notify_type, *args, **kwargs):
# but here we are making straight requests, so we need todo convert this against apprise's logic
for k, v in results['qsd'].items():
if not k.strip('+-') in results['qsd+'].keys():
params[unquote_plus(k)] = unquote_plus(v)
params[URLBase.unquote(k)] = URLBase.unquote(v)
# Determine Authentication
auth = ''
if results.get('user') and results.get('password'):
auth = (unquote_plus(results.get('user')), unquote_plus(results.get('user')))
auth = (URLBase.unquote(results.get('user')), URLBase.unquote(results.get('user')))
elif results.get('user'):
auth = (unquote_plus(results.get('user')))
auth = (URLBase.unquote(results.get('user')))
# Try to auto-guess if it's JSON
h = 'application/json; charset=utf-8'

View File

@@ -1,164 +0,0 @@
import datetime
import glob
import threading
from flask import Blueprint, render_template, send_from_directory, flash, url_for, redirect, abort
import os
from changedetectionio.store import ChangeDetectionStore
from changedetectionio.flask_app import login_optionally_required
from loguru import logger
BACKUP_FILENAME_FORMAT = "changedetection-backup-{}.zip"
def create_backup(datastore_path, watches: dict):
logger.debug("Creating backup...")
import zipfile
from pathlib import Path
# create a ZipFile object
timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
backupname = BACKUP_FILENAME_FORMAT.format(timestamp)
backup_filepath = os.path.join(datastore_path, backupname)
with zipfile.ZipFile(backup_filepath.replace('.zip', '.tmp'), "w",
compression=zipfile.ZIP_DEFLATED,
compresslevel=8) as zipObj:
# Add the index
zipObj.write(os.path.join(datastore_path, "url-watches.json"), arcname="url-watches.json")
# Add the flask app secret
zipObj.write(os.path.join(datastore_path, "secret.txt"), arcname="secret.txt")
# Add any data in the watch data directory.
for uuid, w in watches.items():
for f in Path(w.watch_data_dir).glob('*'):
zipObj.write(f,
# Use the full path to access the file, but make the file 'relative' in the Zip.
arcname=os.path.join(f.parts[-2], f.parts[-1]),
compress_type=zipfile.ZIP_DEFLATED,
compresslevel=8)
# Create a list file with just the URLs, so it's easier to port somewhere else in the future
list_file = "url-list.txt"
with open(os.path.join(datastore_path, list_file), "w") as f:
for uuid in watches:
url = watches[uuid]["url"]
f.write("{}\r\n".format(url))
list_with_tags_file = "url-list-with-tags.txt"
with open(
os.path.join(datastore_path, list_with_tags_file), "w"
) as f:
for uuid in watches:
url = watches[uuid].get('url')
tag = watches[uuid].get('tags', {})
f.write("{} {}\r\n".format(url, tag))
# Add it to the Zip
zipObj.write(
os.path.join(datastore_path, list_file),
arcname=list_file,
compress_type=zipfile.ZIP_DEFLATED,
compresslevel=8,
)
zipObj.write(
os.path.join(datastore_path, list_with_tags_file),
arcname=list_with_tags_file,
compress_type=zipfile.ZIP_DEFLATED,
compresslevel=8,
)
# Now it's done, rename it so it shows up finally and its completed being written.
os.rename(backup_filepath.replace('.zip', '.tmp'), backup_filepath.replace('.tmp', '.zip'))
def construct_blueprint(datastore: ChangeDetectionStore):
backups_blueprint = Blueprint('backups', __name__, template_folder="templates")
backup_threads = []
@login_optionally_required
@backups_blueprint.route("/request-backup", methods=['GET'])
def request_backup():
if any(thread.is_alive() for thread in backup_threads):
flash("A backup is already running, check back in a few minutes", "error")
return redirect(url_for('backups.index'))
if len(find_backups()) > int(os.getenv("MAX_NUMBER_BACKUPS", 100)):
flash("Maximum number of backups reached, please remove some", "error")
return redirect(url_for('backups.index'))
# Be sure we're written fresh
datastore.sync_to_json()
zip_thread = threading.Thread(target=create_backup, args=(datastore.datastore_path, datastore.data.get("watching")))
zip_thread.start()
backup_threads.append(zip_thread)
flash("Backup building in background, check back in a few minutes.")
return redirect(url_for('backups.index'))
def find_backups():
backup_filepath = os.path.join(datastore.datastore_path, BACKUP_FILENAME_FORMAT.format("*"))
backups = glob.glob(backup_filepath)
backup_info = []
for backup in backups:
size = os.path.getsize(backup) / (1024 * 1024)
creation_time = os.path.getctime(backup)
backup_info.append({
'filename': os.path.basename(backup),
'filesize': f"{size:.2f}",
'creation_time': creation_time
})
backup_info.sort(key=lambda x: x['creation_time'], reverse=True)
return backup_info
@login_optionally_required
@backups_blueprint.route("/download/<string:filename>", methods=['GET'])
def download_backup(filename):
import re
filename = filename.strip()
backup_filename_regex = BACKUP_FILENAME_FORMAT.format("\d+")
full_path = os.path.join(os.path.abspath(datastore.datastore_path), filename)
if not full_path.startswith(os.path.abspath(datastore.datastore_path)):
abort(404)
if filename == 'latest':
backups = find_backups()
filename = backups[0]['filename']
if not re.match(r"^" + backup_filename_regex + "$", filename):
abort(400) # Bad Request if the filename doesn't match the pattern
logger.debug(f"Backup download request for '{full_path}'")
return send_from_directory(os.path.abspath(datastore.datastore_path), filename, as_attachment=True)
@login_optionally_required
@backups_blueprint.route("/", methods=['GET'])
def index():
backups = find_backups()
output = render_template("overview.html",
available_backups=backups,
backup_running=any(thread.is_alive() for thread in backup_threads)
)
return output
@login_optionally_required
@backups_blueprint.route("/remove-backups", methods=['GET'])
def remove_backups():
backup_filepath = os.path.join(datastore.datastore_path, BACKUP_FILENAME_FORMAT.format("*"))
backups = glob.glob(backup_filepath)
for backup in backups:
os.unlink(backup)
flash("Backups were deleted.")
return redirect(url_for('backups.index'))
return backups_blueprint

View File

@@ -1,36 +0,0 @@
{% extends 'base.html' %}
{% block content %}
{% from '_helpers.html' import render_simple_field, render_field %}
<div class="edit-form">
<div class="box-wrap inner">
<h4>Backups</h4>
{% if backup_running %}
<p>
<strong>A backup is running!</strong>
</p>
{% endif %}
<p>
Here you can download and request a new backup, when a backup is completed you will see it listed below.
</p>
<br>
{% if available_backups %}
<ul>
{% for backup in available_backups %}
<li><a href="{{ url_for('backups.download_backup', filename=backup["filename"]) }}">{{ backup["filename"] }}</a> {{ backup["filesize"] }} Mb</li>
{% endfor %}
</ul>
{% else %}
<p>
<strong>No backups found.</strong>
</p>
{% endif %}
<a class="pure-button pure-button-primary" href="{{ url_for('backups.request_backup') }}">Create backup</a>
{% if available_backups %}
<a class="pure-button button-small button-error " href="{{ url_for('backups.remove_backups') }}">Remove backups</a>
{% endif %}
</div>
</div>
{% endblock %}

View File

@@ -19,7 +19,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q: PriorityQueue
datastore.data['watching'][uuid]['track_ldjson_price_data'] = PRICE_DATA_TRACK_ACCEPT
datastore.data['watching'][uuid]['processor'] = 'restock_diff'
datastore.data['watching'][uuid].clear_watch()
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
return redirect(url_for("index"))
@login_required

View File

@@ -30,8 +30,6 @@ function isItemInStock() {
'dieser artikel ist bald wieder verfügbar',
'dostępne wkrótce',
'en rupture de stock',
'esgotado',
'indisponível',
'isn\'t in stock right now',
'isnt in stock right now',
'isnt in stock right now',
@@ -59,7 +57,6 @@ function isItemInStock() {
'notify me when available',
'notify me',
'notify when available',
'não disponível',
'não estamos a aceitar encomendas',
'out of stock',
'out-of-stock',

View File

@@ -67,6 +67,7 @@ FlaskCompress(app)
# Stop browser caching of assets
app.config['SEND_FILE_MAX_AGE_DEFAULT'] = 0
app.config.exit = Event()
app.config['NEW_VERSION_AVAILABLE'] = False
@@ -469,7 +470,7 @@ def changedetection_app(config=None, datastore_o=None):
continue
if watch.get('last_error'):
errored_count += 1
if search_q:
if (watch.get('title') and search_q in watch.get('title').lower()) or search_q in watch.get('url', '').lower():
sorted_watches.append(watch)
@@ -532,32 +533,24 @@ def changedetection_app(config=None, datastore_o=None):
@login_optionally_required
def ajax_callback_send_notification_test(watch_uuid=None):
# Watch_uuid could be unset in the case it`s used in tag editor, global settings
# Watch_uuid could be unset in the case its used in tag editor, global setings
import apprise
import random
from .apprise_asset import asset
apobj = apprise.Apprise(asset=asset)
# so that the custom endpoints are registered
from changedetectionio.apprise_plugin import apprise_custom_api_call_wrapper
is_global_settings_form = request.args.get('mode', '') == 'global-settings'
is_group_settings_form = request.args.get('mode', '') == 'group-settings'
# Use an existing random one on the global/main settings form
if not watch_uuid and (is_global_settings_form or is_group_settings_form) \
and datastore.data.get('watching'):
if not watch_uuid and (is_global_settings_form or is_group_settings_form):
logger.debug(f"Send test notification - Choosing random Watch {watch_uuid}")
watch_uuid = random.choice(list(datastore.data['watching'].keys()))
if not watch_uuid:
return make_response("Error: You must have atleast one watch configured for 'test notification' to work", 400)
watch = datastore.data['watching'].get(watch_uuid)
notification_urls = None
if request.form.get('notification_urls'):
notification_urls = request.form['notification_urls'].strip().splitlines()
notification_urls = request.form['notification_urls'].strip().splitlines()
if not notification_urls:
logger.debug("Test notification - Trying by group/tag in the edit form if available")
@@ -575,12 +568,12 @@ def changedetection_app(config=None, datastore_o=None):
if not notification_urls:
return 'Error: No Notification URLs set/found'
return 'No Notification URLs set/found'
for n_url in notification_urls:
if len(n_url.strip()):
if not apobj.add(n_url):
return f'Error: {n_url} is not a valid AppRise URL.'
return f'Error - {n_url} is not a valid AppRise URL.'
try:
# use the same as when it is triggered, but then override it with the form test values
@@ -599,13 +592,11 @@ def changedetection_app(config=None, datastore_o=None):
if 'notification_body' in request.form and request.form['notification_body'].strip():
n_object['notification_body'] = request.form.get('notification_body', '').strip()
n_object.update(watch.extra_notification_token_values())
from . import update_worker
new_worker = update_worker.update_worker(update_q, notification_q, app, datastore)
new_worker.queue_notification_for_watch(notification_q=notification_q, n_object=n_object, watch=watch)
except Exception as e:
return make_response(f"Error: str(e)", 400)
return make_response({'error': str(e)}, 400)
return 'OK - Sent test notifications'
@@ -803,9 +794,8 @@ def changedetection_app(config=None, datastore_o=None):
# But in the case something is added we should save straight away
datastore.needs_write_urgent = True
if not datastore.data['watching'][uuid].get('paused'):
# Queue the watch for immediate recheck, with a higher priority
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
# Queue the watch for immediate recheck, with a higher priority
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
# Diff page [edit] link should go back to diff page
if request.args.get("next") and request.args.get("next") == 'diff':
@@ -986,7 +976,7 @@ def changedetection_app(config=None, datastore_o=None):
importer = import_url_list()
importer.run(data=request.values.get('urls'), flash=flash, datastore=datastore, processor=request.values.get('processor', 'text_json_diff'))
for uuid in importer.new_uuids:
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
if len(importer.remaining_data) == 0:
return redirect(url_for('index'))
@@ -999,7 +989,7 @@ def changedetection_app(config=None, datastore_o=None):
d_importer = import_distill_io_json()
d_importer.run(data=request.values.get('distill-io'), flash=flash, datastore=datastore)
for uuid in d_importer.new_uuids:
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
# XLSX importer
if request.files and request.files.get('xlsx_file'):
@@ -1023,7 +1013,7 @@ def changedetection_app(config=None, datastore_o=None):
w_importer.run(data=file, flash=flash, datastore=datastore)
for uuid in w_importer.new_uuids:
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': True}))
# Could be some remaining, or we could be on GET
form = forms.importForm(formdata=request.form if request.method == 'POST' else None)
@@ -1236,6 +1226,78 @@ def changedetection_app(config=None, datastore_o=None):
return output
# We're good but backups are even better!
@app.route("/backup", methods=['GET'])
@login_optionally_required
def get_backup():
import zipfile
from pathlib import Path
# Remove any existing backup file, for now we just keep one file
for previous_backup_filename in Path(datastore_o.datastore_path).rglob('changedetection-backup-*.zip'):
os.unlink(previous_backup_filename)
# create a ZipFile object
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",
compression=zipfile.ZIP_DEFLATED,
compresslevel=8) as zipObj:
# Be sure we're written fresh
datastore.sync_to_json()
# Add the index
zipObj.write(os.path.join(datastore_o.datastore_path, "url-watches.json"), arcname="url-watches.json")
# Add the flask app secret
zipObj.write(os.path.join(datastore_o.datastore_path, "secret.txt"), arcname="secret.txt")
# Add any data in the watch data directory.
for uuid, w in datastore.data['watching'].items():
for f in Path(w.watch_data_dir).glob('*'):
zipObj.write(f,
# Use the full path to access the file, but make the file 'relative' in the Zip.
arcname=os.path.join(f.parts[-2], f.parts[-1]),
compress_type=zipfile.ZIP_DEFLATED,
compresslevel=8)
# Create a list file with just the URLs, so it's easier to port somewhere else in the future
list_file = "url-list.txt"
with open(os.path.join(datastore_o.datastore_path, list_file), "w") as f:
for uuid in datastore.data["watching"]:
url = datastore.data["watching"][uuid]["url"]
f.write("{}\r\n".format(url))
list_with_tags_file = "url-list-with-tags.txt"
with open(
os.path.join(datastore_o.datastore_path, list_with_tags_file), "w"
) as f:
for uuid in datastore.data["watching"]:
url = datastore.data["watching"][uuid].get('url')
tag = datastore.data["watching"][uuid].get('tags', {})
f.write("{} {}\r\n".format(url, tag))
# Add it to the Zip
zipObj.write(
os.path.join(datastore_o.datastore_path, list_file),
arcname=list_file,
compress_type=zipfile.ZIP_DEFLATED,
compresslevel=8,
)
zipObj.write(
os.path.join(datastore_o.datastore_path, list_with_tags_file),
arcname=list_with_tags_file,
compress_type=zipfile.ZIP_DEFLATED,
compresslevel=8,
)
# Send_from_directory needs to be the full absolute path
return send_from_directory(os.path.abspath(datastore_o.datastore_path), backupname, as_attachment=True)
@app.route("/static/<string:group>/<string:filename>", methods=['GET'])
def static_content(group, filename):
from flask import make_response
@@ -1334,7 +1396,7 @@ def changedetection_app(config=None, datastore_o=None):
url = request.form.get('url').strip()
if datastore.url_exists(url):
flash(f'Warning, URL {url} already exists', "notice")
add_paused = request.form.get('edit_and_watch_submit_button') != None
processor = request.form.get('processor', 'text_json_diff')
new_uuid = datastore.add_watch(url=url, tag=request.form.get('tags').strip(), extras={'paused': add_paused, 'processor': processor})
@@ -1380,7 +1442,7 @@ def changedetection_app(config=None, datastore_o=None):
new_uuid = datastore.clone(uuid)
if new_uuid:
if not datastore.data['watching'].get(uuid).get('paused'):
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=5, item={'uuid': 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'))
@@ -1401,7 +1463,7 @@ def changedetection_app(config=None, datastore_o=None):
if uuid:
if uuid not in running_uuids:
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
i = 1
elif tag:
@@ -1412,7 +1474,7 @@ def changedetection_app(config=None, datastore_o=None):
continue
if watch_uuid not in running_uuids and not datastore.data['watching'][watch_uuid]['paused']:
update_q.put(
queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid})
queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False})
)
i += 1
@@ -1422,7 +1484,7 @@ def changedetection_app(config=None, datastore_o=None):
if watch_uuid not in running_uuids and not datastore.data['watching'][watch_uuid]['paused']:
if with_errors and not watch.get('last_error'):
continue
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid}))
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': watch_uuid, 'skip_when_checksum_same': False}))
i += 1
flash(f"{i} watches queued for rechecking.")
return redirect(url_for('index', tag=tag))
@@ -1480,7 +1542,7 @@ def changedetection_app(config=None, datastore_o=None):
uuid = uuid.strip()
if datastore.data['watching'].get(uuid):
# Recheck and require a full reprocessing
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid}))
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=1, item={'uuid': uuid, 'skip_when_checksum_same': False}))
flash("{} watches queued for rechecking".format(len(uuids)))
elif (op == 'clear-errors'):
@@ -1615,9 +1677,6 @@ def changedetection_app(config=None, datastore_o=None):
import changedetectionio.blueprint.check_proxies as check_proxies
app.register_blueprint(check_proxies.construct_blueprint(datastore=datastore), url_prefix='/check_proxy')
import changedetectionio.blueprint.backups as backups
app.register_blueprint(backups.construct_blueprint(datastore), url_prefix='/backups')
# @todo handle ctrl break
ticker_thread = threading.Thread(target=ticker_thread_check_time_launch_checks).start()
@@ -1807,7 +1866,7 @@ def ticker_thread_check_time_launch_checks():
f"{now - watch['last_checked']:0.2f}s since last checked")
# Into the queue with you
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=priority, item={'uuid': uuid}))
update_q.put(queuedWatchMetaData.PrioritizedItem(priority=priority, item={'uuid': uuid, 'skip_when_checksum_same': True}))
# Reset for next time
watch.jitter_seconds = 0

View File

@@ -496,7 +496,7 @@ class processor_text_json_diff_form(commonSettingsForm):
text_should_not_be_present = StringListField('Block change-detection while text matches', [validators.Optional(), ValidateListRegex()])
webdriver_js_execute_code = TextAreaField('Execute JavaScript before change detection', render_kw={"rows": "5"}, validators=[validators.Optional()])
save_button = SubmitField('Save', render_kw={"class": "pure-button button-small pure-button-primary"})
save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
proxy = RadioField('Proxy')
filter_failure_notification_send = BooleanField(
@@ -515,7 +515,6 @@ class processor_text_json_diff_form(commonSettingsForm):
if not super().validate():
return False
from changedetectionio.safe_jinja import render as jinja_render
result = True
# Fail form validation when a body is set for a GET
@@ -525,46 +524,18 @@ class processor_text_json_diff_form(commonSettingsForm):
# Attempt to validate jinja2 templates in the URL
try:
from changedetectionio.safe_jinja import render as jinja_render
jinja_render(template_str=self.url.data)
except ModuleNotFoundError as e:
# incase jinja2_time or others is missing
logger.error(e)
self.url.errors.append(f'Invalid template syntax configuration: {e}')
self.url.errors.append(e)
result = False
except Exception as e:
logger.error(e)
self.url.errors.append(f'Invalid template syntax: {e}')
self.url.errors.append('Invalid template syntax')
result = False
# Attempt to validate jinja2 templates in the body
if self.body.data and self.body.data.strip():
try:
jinja_render(template_str=self.body.data)
except ModuleNotFoundError as e:
# incase jinja2_time or others is missing
logger.error(e)
self.body.errors.append(f'Invalid template syntax configuration: {e}')
result = False
except Exception as e:
logger.error(e)
self.body.errors.append(f'Invalid template syntax: {e}')
result = False
# Attempt to validate jinja2 templates in the headers
if len(self.headers.data) > 0:
try:
for header, value in self.headers.data.items():
jinja_render(template_str=value)
except ModuleNotFoundError as e:
# incase jinja2_time or others is missing
logger.error(e)
self.headers.errors.append(f'Invalid template syntax configuration: {e}')
result = False
except Exception as e:
logger.error(e)
self.headers.errors.append(f'Invalid template syntax in "{header}" header: {e}')
result = False
return result
class SingleExtraProxy(Form):
@@ -645,7 +616,7 @@ class globalSettingsForm(Form):
requests = FormField(globalSettingsRequestForm)
application = FormField(globalSettingsApplicationForm)
save_button = SubmitField('Save', render_kw={"class": "pure-button button-small pure-button-primary"})
save_button = SubmitField('Save', render_kw={"class": "pure-button pure-button-primary"})
class extractDataForm(Form):

View File

@@ -54,64 +54,29 @@ def include_filters(include_filters, html_content, append_pretty_line_formatting
def subtractive_css_selector(css_selector, html_content):
from bs4 import BeautifulSoup
soup = BeautifulSoup(html_content, "html.parser")
# So that the elements dont shift their index, build a list of elements here which will be pointers to their place in the DOM
elements_to_remove = soup.select(css_selector)
# Then, remove them in a separate loop
for item in elements_to_remove:
for item in soup.select(css_selector):
item.decompose()
return str(soup)
def subtractive_xpath_selector(selectors: List[str], html_content: str) -> str:
# Parse the HTML content using lxml
def subtractive_xpath_selector(xpath_selector, html_content):
html_tree = etree.HTML(html_content)
elements_to_remove = html_tree.xpath(xpath_selector)
# First, collect all elements to remove
elements_to_remove = []
# Iterate over the list of XPath selectors
for selector in selectors:
# Collect elements for each selector
elements_to_remove.extend(html_tree.xpath(selector))
# Then, remove them in a separate loop
for element in elements_to_remove:
if element.getparent() is not None: # Ensure the element has a parent before removing
element.getparent().remove(element)
element.getparent().remove(element)
# Convert the modified HTML tree back to a string
modified_html = etree.tostring(html_tree, method="html").decode("utf-8")
return modified_html
def element_removal(selectors: List[str], html_content):
"""Removes elements that match a list of CSS or XPath selectors."""
"""Removes elements that match a list of CSS or xPath selectors."""
modified_html = html_content
css_selectors = []
xpath_selectors = []
for selector in selectors:
if selector.startswith(('xpath:', 'xpath1:', '//')):
# Handle XPath selectors separately
xpath_selector = selector.removeprefix('xpath:').removeprefix('xpath1:')
xpath_selectors.append(xpath_selector)
modified_html = subtractive_xpath_selector(xpath_selector, modified_html)
else:
# Collect CSS selectors as one "hit", see comment in subtractive_css_selector
css_selectors.append(selector.strip().strip(","))
if xpath_selectors:
modified_html = subtractive_xpath_selector(xpath_selectors, modified_html)
if css_selectors:
# Remove duplicates, then combine all CSS selectors into one string, separated by commas
# This stops the elements index shifting
unique_selectors = list(set(css_selectors)) # Ensure uniqueness
combined_css_selector = " , ".join(unique_selectors)
modified_html = subtractive_css_selector(combined_css_selector, modified_html)
modified_html = subtractive_css_selector(selector, modified_html)
return modified_html
def elementpath_tostring(obj):

View File

@@ -89,10 +89,6 @@ class model(watch_base):
if ready_url.startswith('source:'):
ready_url=ready_url.replace('source:', '')
# Also double check it after any Jinja2 formatting just incase
if not is_safe_url(ready_url):
return 'DISABLED'
return ready_url
def clear_watch(self):

View File

@@ -31,15 +31,15 @@ class difference_detection_processor():
from requests.structures import CaseInsensitiveDict
url = self.watch.link
# Protect against file:// access, check the real "link" without any meta "source:" etc prepended.
if re.search(r'^file://', url, re.IGNORECASE):
# Protect against file:// access
if re.search(r'^file://', self.watch.get('url', '').strip(), re.IGNORECASE):
if not strtobool(os.getenv('ALLOW_FILE_URI', 'false')):
raise Exception(
"file:// type access is denied for security reasons."
)
url = self.watch.link
# Requests, playwright, other browser via wss:// etc, fetch_extra_something
prefer_fetch_backend = self.watch.get('fetch_backend', 'system')
@@ -102,7 +102,6 @@ class difference_detection_processor():
self.fetcher.browser_steps_screenshot_path = os.path.join(self.datastore.datastore_path, self.watch.get('uuid'))
# Tweak the base config with the per-watch ones
from changedetectionio.safe_jinja import render as jinja_render
request_headers = CaseInsensitiveDict()
ua = self.datastore.data['settings']['requests'].get('default_ua')
@@ -119,15 +118,9 @@ class difference_detection_processor():
if 'Accept-Encoding' in request_headers and "br" in request_headers['Accept-Encoding']:
request_headers['Accept-Encoding'] = request_headers['Accept-Encoding'].replace(', br', '')
for header_name in request_headers:
request_headers.update({header_name: jinja_render(template_str=request_headers.get(header_name))})
timeout = self.datastore.data['settings']['requests'].get('timeout')
request_body = self.watch.get('body')
if request_body:
request_body = jinja_render(template_str=self.watch.get('body'))
request_method = self.watch.get('method')
ignore_status_codes = self.watch.get('ignore_status_codes', False)
@@ -164,7 +157,7 @@ class difference_detection_processor():
# After init, call run_changedetection() which will do the actual change-detection
@abstractmethod
def run_changedetection(self, watch):
def run_changedetection(self, watch, skip_when_checksum_same: bool = True):
update_obj = {'last_notification_error': False, 'last_error': False}
some_data = 'xxxxx'
update_obj["previous_md5"] = hashlib.md5(some_data.encode('utf-8')).hexdigest()

View File

@@ -40,7 +40,7 @@ def _deduplicate_prices(data):
if isinstance(datum.value, list):
# Process each item in the list
normalized_value = set([float(re.sub(r'[^\d.]', '', str(item))) for item in datum.value if str(item).strip()])
normalized_value = set([float(re.sub(r'[^\d.]', '', str(item))) for item in datum.value])
unique_data.update(normalized_value)
else:
# Process single value
@@ -144,7 +144,7 @@ class perform_site_check(difference_detection_processor):
screenshot = None
xpath_data = None
def run_changedetection(self, watch):
def run_changedetection(self, watch, skip_when_checksum_same=True):
import hashlib
if not watch:

View File

@@ -11,7 +11,10 @@ def _task(watch, update_handler):
try:
# The slow process (we run 2 of these in parallel)
changed_detected, update_obj, text_after_filter = update_handler.run_changedetection(watch=watch)
changed_detected, update_obj, text_after_filter = update_handler.run_changedetection(
watch=watch,
skip_when_checksum_same=False,
)
except FilterNotFoundInResponse as e:
text_after_filter = f"Filter not found in HTML: {str(e)}"
except ReplyWithContentButNoText as e:

View File

@@ -35,7 +35,7 @@ class PDFToHTMLToolNotFound(ValueError):
# (set_proxy_from_list)
class perform_site_check(difference_detection_processor):
def run_changedetection(self, watch):
def run_changedetection(self, watch, skip_when_checksum_same=True):
changed_detected = False
html_content = ""
screenshot = False # as bytes
@@ -58,6 +58,9 @@ class perform_site_check(difference_detection_processor):
# 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(self.fetcher.content.encode('utf-8')).hexdigest()
if skip_when_checksum_same:
if update_obj['previous_md5_before_filters'] == watch.get('previous_md5_before_filters'):
raise content_fetchers.exceptions.checksumFromPreviousCheckWasTheSame()
# Fetching complete, now filters
@@ -331,21 +334,13 @@ class perform_site_check(difference_detection_processor):
if result:
blocked = True
# The main thing that all this at the moment comes down to :)
if watch.get('previous_md5') != fetched_md5:
changed_detected = True
# Looks like something changed, but did it match all the rules?
if blocked:
changed_detected = False
else:
# The main thing that all this at the moment comes down to :)
if watch.get('previous_md5') != fetched_md5:
changed_detected = True
# Always record the new checksum
update_obj["previous_md5"] = fetched_md5
# On the first run of a site, watch['previous_md5'] will be None, set it the current one.
if not watch.get('previous_md5'):
watch['previous_md5'] = fetched_md5
logger.debug(f"Watch UUID {watch.get('uuid')} content check - Previous MD5: {watch.get('previous_md5')}, Fetched MD5 {fetched_md5}")
@@ -365,6 +360,12 @@ class perform_site_check(difference_detection_processor):
else:
logger.debug(f"check_unique_lines: UUID {watch.get('uuid')} had unique content")
# Always record the new checksum
update_obj["previous_md5"] = fetched_md5
# On the first run of a site, watch['previous_md5'] will be None, set it the current one.
if not watch.get('previous_md5'):
watch['previous_md5'] = fetched_md5
# stripped_text_from_html - Everything after filters and NO 'ignored' content
return changed_detected, update_obj, stripped_text_from_html

View File

@@ -28,14 +28,17 @@ $(document).ready(function() {
url: notification_base_url,
data : data,
statusCode: {
400: function(data) {
// More than likely the CSRF token was lost when the server restarted
alert(data.responseText);
400: function() {
// More than likely the CSRF token was lost when the server restarted
alert("There was a problem processing the request, please reload the page.");
}
}
}).done(function(data){
console.log(data);
alert(data);
}).fail(function(data){
console.log(data);
alert('There was an error communicating with the server.');
})
});
});

View File

@@ -26,7 +26,8 @@ function set_active_tab() {
if (tab.length) {
tab[0].parentElement.className = "active";
}
// hash could move the page down
window.scrollTo(0, 0);
}
function focus_error_tab() {

View File

@@ -153,8 +153,7 @@ html[data-darkmode="true"] {
border: 1px solid transparent;
vertical-align: top;
font: 1em monospace;
text-align: left;
overflow: clip; }
text-align: left; }
#diff-ui pre {
white-space: pre-wrap; }
@@ -173,9 +172,7 @@ ins {
text-decoration: none; }
#result {
white-space: pre-wrap;
word-break: break-word;
overflow-wrap: break-word; }
white-space: pre-wrap; }
#settings {
background: rgba(0, 0, 0, 0.05);
@@ -234,12 +231,3 @@ td#diff-col div {
border-radius: 5px;
background: var(--color-background);
box-shadow: 1px 1px 4px var(--color-shadow-jump); }
.pure-form button.reset-margin {
margin: 0px; }
.diff-fieldset {
display: flex;
align-items: center;
gap: 4px;
flex-wrap: wrap; }

View File

@@ -24,7 +24,6 @@
vertical-align: top;
font: 1em monospace;
text-align: left;
overflow: clip; // clip overflowing contents to cell boundariess
}
pre {
@@ -51,8 +50,6 @@ ins {
#result {
white-space: pre-wrap;
word-break: break-word;
overflow-wrap: break-word;
.change {
span {}
@@ -137,15 +134,3 @@ td#diff-col div {
background: var(--color-background);
box-shadow: 1px 1px 4px var(--color-shadow-jump);
}
// resets button margin to 0px
.pure-form button.reset-margin {
margin: 0px;
}
.diff-fieldset {
display: flex;
align-items: center;
gap: 4px;
flex-wrap: wrap;
}

View File

@@ -11,22 +11,7 @@ ul#requests-extra_browsers {
/* each proxy entry is a `table` */
table {
tr {
display: table-row; // default display for small screens
input[type=text] {
width: 100%;
}
}
}
// apply inline display for larger screens
@media only screen and (min-width: 1280px) {
table {
tr {
display: inline;
input[type=text] {
width: 100%;
}
}
display: inline;
}
}
}

View File

@@ -11,19 +11,7 @@ ul#requests-extra_proxies {
/* each proxy entry is a `table` */
table {
tr {
display: table-row; // default display for small screens
input[type=text] {
width: 100%;
}
}
}
// apply inline display for large screens
@media only screen and (min-width: 1024px) {
table {
tr {
display: inline;
}
display: inline;
}
}
}

View File

@@ -147,14 +147,8 @@ body.spinner-active {
}
}
.tab-pane-inner {
// .tab-pane-inner will have the #id that the tab button jumps/anchors to
scroll-margin-top: 200px;
}
section.content {
padding-top: 100px;
padding-top: 5em;
padding-bottom: 1em;
flex-direction: column;
display: flex;
@@ -937,7 +931,6 @@ $form-edge-padding: 20px;
}
.tab-pane-inner {
&:not(:target) {
display: none;
}

View File

@@ -112,12 +112,7 @@ ul#requests-extra_proxies {
ul#requests-extra_proxies li > label {
display: none; }
ul#requests-extra_proxies table tr {
display: table-row; }
ul#requests-extra_proxies table tr input[type=text] {
width: 100%; }
@media only screen and (min-width: 1024px) {
ul#requests-extra_proxies table tr {
display: inline; } }
display: inline; }
#request {
/* Auto proxy scan/checker */ }
@@ -166,14 +161,7 @@ ul#requests-extra_browsers {
ul#requests-extra_browsers li > label {
display: none; }
ul#requests-extra_browsers table tr {
display: table-row; }
ul#requests-extra_browsers table tr input[type=text] {
width: 100%; }
@media only screen and (min-width: 1280px) {
ul#requests-extra_browsers table tr {
display: inline; }
ul#requests-extra_browsers table tr input[type=text] {
width: 100%; } }
display: inline; }
#extra-browsers-setting {
border: 1px solid var(--color-grey-800);
@@ -617,11 +605,8 @@ body.spinner-active #pure-menu-horizontal-spinner {
background-color: var(--color-background-menu-link-hover);
color: var(--color-text-menu-link-hover); }
.tab-pane-inner {
scroll-margin-top: 200px; }
section.content {
padding-top: 100px;
padding-top: 5em;
padding-bottom: 1em;
flex-direction: column;
display: flex;

View File

@@ -70,7 +70,7 @@
<a href="{{ url_for('import_page')}}" class="pure-menu-link">IMPORT</a>
</li>
<li class="pure-menu-item">
<a href="{{ url_for('backups.index')}}" class="pure-menu-link">BACKUPS</a>
<a href="{{ url_for('get_backup')}}" class="pure-menu-link">BACKUP</a>
</li>
{% else %}
<li class="pure-menu-item">

View File

@@ -14,7 +14,7 @@
<div id="settings">
<form class="pure-form " action="" method="GET" id="diff-form">
<fieldset class="diff-fieldset">
<fieldset>
{% if versions|length >= 1 %}
<strong>Compare</strong>
<del class="change"><span>from</span></del>
@@ -33,7 +33,7 @@
</option>
{% endfor %}
</select>
<button type="submit" class="pure-button pure-button-primary reset-margin">Go</button>
<button type="submit" class="pure-button pure-button-primary">Go</button>
{% endif %}
</fieldset>
<fieldset>

View File

@@ -65,8 +65,8 @@
<fieldset>
<div class="pure-control-group">
{{ render_field(form.url, placeholder="https://...", required=true, class="m-d") }}
<div class="pure-form-message">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></div>
<div class="pure-form-message">Variables are supported in the URL (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a>).</div>
<span class="pure-form-message-inline">Some sites use JavaScript to create the content, for this you should <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Fetching-pages-with-WebDriver">use the Chrome/WebDriver Fetcher</a></span><br>
<span class="pure-form-message-inline">You can use variables in the URL, perfect for inserting the current date and other logic, <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a></span><br>
</div>
<div class="pure-control-group inline-radio">
{{ render_field(form.processor) }}
@@ -149,24 +149,21 @@
{{ render_field(form.method) }}
</div>
<div id="request-body">
{{ render_field(form.body, rows=7, placeholder="Example
{{ render_field(form.body, rows=5, placeholder="Example
{
\"name\":\"John\",
\"age\":30,
\"car\":null,
\"year\":{% now 'Europe/Berlin', '%Y' %}
\"car\":null
}") }}
</div>
<div class="pure-form-message">Variables are supported in the request body (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a>).</div>
</div>
</fieldset>
<!-- hmm -->
<div class="pure-control-group advanced-options" style="display: none;">
{{ render_field(form.headers, rows=7, placeholder="Example
{{ render_field(form.headers, rows=5, placeholder="Example
Cookie: foobar
User-Agent: wonderbra 1.0
Math: {{ 1 + 1 }}") }}
<div class="pure-form-message">Variables are supported in the request header values (<a href="https://github.com/dgtlmoon/changedetection.io/wiki/Handling-variables-in-the-watched-URL">help and examples here</a>).</div>
User-Agent: wonderbra 1.0") }}
<div class="pure-form-message-inline">
{% if has_extra_headers_file %}
<strong>Alert! Extra headers file found and will be added to this watch!</strong>

View File

@@ -276,7 +276,7 @@ nav
<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('clear_all_history')}}" class="pure-button button-small button-error">Clear Snapshot History</a>
<a href="{{url_for('clear_all_history')}}" class="pure-button button-small button-cancel">Clear Snapshot History</a>
</div>
</div>
</form>

View File

@@ -16,4 +16,4 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
time.sleep(3)

View File

@@ -1,8 +1,7 @@
#!/usr/bin/env python3
import json
import os
from flask import url_for
from changedetectionio.tests.util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
from changedetectionio.tests.util import live_server_setup, wait_for_all_checks
def set_response():
@@ -19,6 +18,7 @@ def set_response():
f.write(data)
time.sleep(1)
def test_socks5(client, live_server, measure_memory_usage):
live_server_setup(live_server)
set_response()
@@ -79,24 +79,3 @@ def test_socks5(client, live_server, measure_memory_usage):
# Should see the proper string
assert "Awesome, you made it".encode('utf-8') in res.data
# PROXY CHECKER WIDGET CHECK - this needs more checking
uuid = extract_UUID_from_client(client)
res = client.get(
url_for("check_proxies.start_check", uuid=uuid),
follow_redirects=True
)
# It's probably already finished super fast :(
#assert b"RUNNING" in res.data
wait_for_all_checks(client)
res = client.get(
url_for("check_proxies.get_recheck_status", uuid=uuid),
follow_redirects=True
)
assert b"OK" in res.data
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -26,24 +26,8 @@ def test_backup(client, live_server, measure_memory_usage):
assert b"1 Imported" in res.data
wait_for_all_checks(client)
# Launch the thread in the background to create the backup
res = client.get(
url_for("backups.request_backup"),
follow_redirects=True
)
time.sleep(2)
res = client.get(
url_for("backups.index"),
follow_redirects=True
)
# Can see the download link to the backup
assert b'<a href="/backups/download/changedetection-backup-20' in res.data
assert b'Remove backups' in res.data
# Get the latest one
res = client.get(
url_for("backups.download_backup", filename="latest"),
url_for("get_backup"),
follow_redirects=True
)
@@ -60,11 +44,3 @@ def test_backup(client, live_server, measure_memory_usage):
# Should be two txt files in the archive (history and the snapshot)
assert len(newlist) == 2
# Get the latest one
res = client.get(
url_for("backups.remove_backups"),
follow_redirects=True
)
assert b'No backups found.' in res.data

View File

@@ -65,8 +65,11 @@ def test_check_block_changedetection_text_NOT_present(client, live_server, measu
live_server_setup(live_server)
# Use a mix of case in ZzZ to prove it works case-insensitive.
ignore_text = "out of stoCk\r\nfoobar"
set_original_ignore_response()
# Give the endpoint time to spin up
time.sleep(1)
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
@@ -124,24 +127,13 @@ def test_check_block_changedetection_text_NOT_present(client, live_server, measu
assert b'unviewed' not in res.data
assert b'/test-endpoint' in res.data
# 2548
# Going back to the ORIGINAL should NOT trigger a change
set_original_ignore_response()
client.get(url_for("form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
res = client.get(url_for("index"))
assert b'unviewed' not in res.data
# Now we set a change where the text is gone AND its different content, it should now trigger
# Now we set a change where the text is gone, it should now trigger
set_modified_response_minus_block_text()
client.get(url_for("form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
res = client.get(url_for("index"))
assert b'unviewed' in res.data
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -11,35 +11,6 @@ from .util import live_server_setup, wait_for_all_checks
def test_setup(live_server):
live_server_setup(live_server)
def set_response_with_multiple_index():
data= """<!DOCTYPE html>
<html>
<body>
<!-- NOTE!! CHROME WILL ADD TBODY HERE IF ITS NOT THERE!! -->
<table style="width:100%">
<tr>
<th>Person 1</th>
<th>Person 2</th>
<th>Person 3</th>
</tr>
<tr>
<td>Emil</td>
<td>Tobias</td>
<td>Linus</td>
</tr>
<tr>
<td>16</td>
<td>14</td>
<td>10</td>
</tr>
</table>
</body>
</html>
"""
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write(data)
def set_original_response():
test_return_data = """<html>
@@ -206,61 +177,3 @@ def test_element_removal_full(client, live_server, measure_memory_usage):
# There should not be an unviewed change, as changes should be removed
res = client.get(url_for("index"))
assert b"unviewed" not in res.data
# Re #2752
def test_element_removal_nth_offset_no_shift(client, live_server, measure_memory_usage):
#live_server_setup(live_server)
set_response_with_multiple_index()
subtractive_selectors_data = ["""
body > table > tr:nth-child(1) > th:nth-child(2)
body > table > tr:nth-child(2) > td:nth-child(2)
body > table > tr:nth-child(3) > td:nth-child(2)
body > table > tr:nth-child(1) > th:nth-child(3)
body > table > tr:nth-child(2) > td:nth-child(3)
body > table > tr:nth-child(3) > td:nth-child(3)""",
"""//body/table/tr[1]/th[2]
//body/table/tr[2]/td[2]
//body/table/tr[3]/td[2]
//body/table/tr[1]/th[3]
//body/table/tr[2]/td[3]
//body/table/tr[3]/td[3]"""]
for selector_list in subtractive_selectors_data:
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
# Add our URL to the import page
test_url = url_for("test_endpoint", _external=True)
res = client.post(
url_for("import_page"), data={"urls": test_url}, follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
res = client.post(
url_for("edit_page", uuid="first"),
data={
"subtractive_selectors": selector_list,
"url": test_url,
"tags": "",
"fetch_backend": "html_requests",
},
follow_redirects=True,
)
assert b"Updated watch." in res.data
wait_for_all_checks(client)
res = client.get(
url_for("preview_page", uuid="first"),
follow_redirects=True
)
assert b"Tobias" not in res.data
assert b"Linus" not in res.data
assert b"Person 2" not in res.data
assert b"Person 3" not in res.data
# First column should exist
assert b"Emil" in res.data

View File

@@ -1,78 +0,0 @@
#!/usr/bin/env python3
from flask import url_for
from changedetectionio.tests.util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
def set_response():
data = f"""<html>
<body>Awesome, you made it<br>
yeah the socks request worked<br>
something to ignore<br>
something to trigger<br>
</body>
</html>
"""
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write(data)
def test_content_filter_live_preview(client, live_server, measure_memory_usage):
live_server_setup(live_server)
set_response()
test_url = url_for('test_endpoint', _external=True)
res = client.post(
url_for("form_quick_watch_add"),
data={"url": test_url, "tags": ''},
follow_redirects=True
)
uuid = extract_UUID_from_client(client)
res = client.post(
url_for("edit_page", uuid=uuid),
data={
"include_filters": "",
"fetch_backend": 'html_requests',
"ignore_text": "something to ignore",
"trigger_text": "something to trigger",
"url": test_url,
},
follow_redirects=True
)
assert b"Updated watch." in res.data
wait_for_all_checks(client)
# The endpoint is a POST and accepts the form values to override the watch preview
import json
# DEFAULT OUTPUT WITHOUT ANYTHING UPDATED/CHANGED - SHOULD SEE THE WATCH DEFAULTS
res = client.post(
url_for("watch_get_preview_rendered", uuid=uuid)
)
default_return = json.loads(res.data.decode('utf-8'))
assert default_return.get('after_filter')
assert default_return.get('before_filter')
assert default_return.get('ignore_line_numbers') == [3] # "something to ignore" line 3
assert default_return.get('trigger_line_numbers') == [4] # "something to trigger" line 4
# SEND AN UPDATE AND WE SHOULD SEE THE OUTPUT CHANGE SO WE KNOW TO HIGHLIGHT NEW STUFF
res = client.post(
url_for("watch_get_preview_rendered", uuid=uuid),
data={
"include_filters": "",
"fetch_backend": 'html_requests',
"ignore_text": "sOckS", # Also be sure case insensitive works
"trigger_text": "AweSOme",
"url": test_url,
},
)
reply = json.loads(res.data.decode('utf-8'))
assert reply.get('after_filter')
assert reply.get('before_filter')
assert reply.get('ignore_line_numbers') == [2] # Ignored - "socks" on line 2
assert reply.get('trigger_line_numbers') == [1] # Triggers "Awesome" in line 1
res = client.get(url_for("form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -284,7 +284,7 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server, measure_me
# CUSTOM JSON BODY CHECK for POST://
set_original_response()
# https://github.com/caronc/apprise/wiki/Notify_Custom_JSON#header-manipulation
test_notification_url = url_for('test_notification_endpoint', _external=True).replace('http://', 'post://')+"?xxx={{ watch_url }}&+custom-header=123&+second=hello+world%20%22space%22"
test_notification_url = url_for('test_notification_endpoint', _external=True).replace('http://', 'post://')+"?xxx={{ watch_url }}&+custom-header=123"
res = client.post(
url_for("settings_page"),
@@ -326,7 +326,6 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server, measure_me
assert j['secret'] == 444
assert j['somebug'] == '网站监测 内容更新了'
# URL check, this will always be converted to lowercase
assert os.path.isfile("test-datastore/notification-url.txt")
with open("test-datastore/notification-url.txt", 'r') as f:
@@ -338,7 +337,6 @@ def test_notification_custom_endpoint_and_jinja2(client, live_server, measure_me
with open("test-datastore/notification-headers.txt", 'r') as f:
notification_headers = f.read()
assert 'custom-header: 123' in notification_headers.lower()
assert 'second: hello world "space"' in notification_headers.lower()
# Should always be automatically detected as JSON content type even when we set it as 'Text' (default)
@@ -431,15 +429,3 @@ def test_global_send_test_notification(client, live_server, measure_memory_usage
follow_redirects=True
)
######### Test global/system settings - When everything is deleted it should give a helpful error
# See #2727
res = client.post(
url_for("ajax_callback_send_notification_test")+"?mode=global-settings",
data={"notification_urls": test_notification_url},
follow_redirects=True
)
assert res.status_code == 400
assert b"Error: You must have atleast one watch configured for 'test notification' to work" in res.data

View File

@@ -45,7 +45,7 @@ def test_headers_in_request(client, live_server, measure_memory_usage):
"url": test_url,
"tags": "",
"fetch_backend": 'html_webdriver' if os.getenv('PLAYWRIGHT_DRIVER_URL') else 'html_requests',
"headers": "jinja2:{{ 1+1 }}\nxxx:ooo\ncool:yeah\r\ncookie:"+cookie_header},
"headers": "xxx:ooo\ncool:yeah\r\ncookie:"+cookie_header},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -61,7 +61,6 @@ def test_headers_in_request(client, live_server, measure_memory_usage):
)
# Flask will convert the header key to uppercase
assert b"Jinja2:2" in res.data
assert b"Xxx:ooo" in res.data
assert b"Cool:yeah" in res.data
@@ -118,8 +117,7 @@ def test_body_in_request(client, live_server, measure_memory_usage):
wait_for_all_checks(client)
# Now the change which should trigger a change
body_value = 'Test Body Value {{ 1+1 }}'
body_value_formatted = 'Test Body Value 2'
body_value = 'Test Body Value'
res = client.post(
url_for("edit_page", uuid="first"),
data={
@@ -142,9 +140,8 @@ def test_body_in_request(client, live_server, measure_memory_usage):
# If this gets stuck something is wrong, something should always be there
assert b"No history found" not in res.data
# We should see the formatted value of what we sent in the reply
assert str.encode(body_value) not in res.data
assert str.encode(body_value_formatted) in res.data
# We should see what we sent in the reply
assert str.encode(body_value) in res.data
####### data sanity checks
# Add the test URL twice, we will check

View File

@@ -3,7 +3,7 @@ import os
import time
from flask import url_for
from .util import live_server_setup, wait_for_all_checks, wait_for_notification_endpoint_output, extract_UUID_from_client
from .util import live_server_setup, wait_for_all_checks, wait_for_notification_endpoint_output
from ..notification import default_notification_format
instock_props = [
@@ -367,12 +367,6 @@ def test_change_with_notification_values(client, live_server):
assert "new price 1950.45" in notification
assert "title new price 1950.45" in notification
## Now test the "SEND TEST NOTIFICATION" is working
os.unlink("test-datastore/notification.txt")
uuid = extract_UUID_from_client(client)
res = client.post(url_for("ajax_callback_send_notification_test", watch_uuid=uuid), data={}, follow_redirects=True)
time.sleep(5)
assert os.path.isfile("test-datastore/notification.txt"), "Notification received"
def test_data_sanity(client, live_server):

View File

@@ -81,8 +81,7 @@ class update_worker(threading.Thread):
'watch_url': watch.get('url') if watch else None,
})
if watch:
n_object.update(watch.extra_notification_token_values())
n_object.update(watch.extra_notification_token_values())
logger.trace(f"Main rendered notification placeholders (diff_added etc) calculated in {time.time()-now:.3f}s")
logger.debug("Queued notification for sending")
@@ -261,6 +260,9 @@ class update_worker(threading.Thread):
try:
# Processor is what we are using for detecting the "Change"
processor = watch.get('processor', 'text_json_diff')
# Abort processing when the content was the same as the last fetch
skip_when_same_checksum = queued_item_data.item.get('skip_when_checksum_same')
# Init a new 'difference_detection_processor', first look in processors
processor_module_name = f"changedetectionio.processors.{processor}.processor"
@@ -276,7 +278,10 @@ class update_worker(threading.Thread):
update_handler.call_browser()
changed_detected, update_obj, contents = update_handler.run_changedetection(watch=watch)
changed_detected, update_obj, contents = update_handler.run_changedetection(
watch=watch,
skip_when_checksum_same=skip_when_same_checksum,
)
# Re #342
# In Python 3, all strings are sequences of Unicode characters. There is a bytes type that holds raw bytes.

View File

@@ -59,9 +59,7 @@ elementpath==4.1.5
selenium~=4.14.0
# https://github.com/pallets/werkzeug/issues/2985
# Maybe related to pytest?
werkzeug==3.0.6
werkzeug~=3.0
# Templating, so far just in the URLs but in the future can be for the notifications also
jinja2~=3.1