Compare commits

..

17 Commits

Author SHA1 Message Date
dgtlmoon
fc1963f31e Fix RSS watch titles
Some checks failed
Publish Python 🐍distribution 📦 to PyPI and TestPyPI / Build distribution 📦 (push) Has been cancelled
ChangeDetection.io App Test / lint-code (push) Has been cancelled
Publish Python 🐍distribution 📦 to PyPI and TestPyPI / Test the built 📦 package works basically. (push) Has been cancelled
Publish Python 🐍distribution 📦 to PyPI and TestPyPI / Publish Python 🐍 distribution 📦 to PyPI (push) Has been cancelled
ChangeDetection.io App Test / test-application-3-10 (push) Has been cancelled
ChangeDetection.io App Test / test-application-3-11 (push) Has been cancelled
ChangeDetection.io App Test / test-application-3-12 (push) Has been cancelled
ChangeDetection.io App Test / test-application-3-13 (push) Has been cancelled
2025-09-10 14:11:06 +02:00
dgtlmoon
78ec18bbad For now notificaitons stay the same 2025-09-10 14:03:42 +02:00
dgtlmoon
410dae3e33 Set watch_title correctly 2025-09-10 13:53:21 +02:00
dgtlmoon
6bc94ff52f add missing files, tweaks to fields 2025-09-10 12:46:01 +02:00
dgtlmoon
00f96ec860 more tweaks 2025-09-10 12:40:34 +02:00
dgtlmoon
85e9cf7b0b field tweaks 2025-09-10 12:19:41 +02:00
dgtlmoon
26420503af WIP 2025-09-10 12:14:28 +02:00
dgtlmoon
9737dd0942 tweak names
Some checks failed
Publish Python 🐍distribution 📦 to PyPI and TestPyPI / Build distribution 📦 (push) Has been cancelled
Publish Python 🐍distribution 📦 to PyPI and TestPyPI / Test the built 📦 package works basically. (push) Has been cancelled
Publish Python 🐍distribution 📦 to PyPI and TestPyPI / Publish Python 🐍 distribution 📦 to PyPI (push) Has been cancelled
ChangeDetection.io App Test / lint-code (push) Has been cancelled
ChangeDetection.io App Test / test-application-3-10 (push) Has been cancelled
ChangeDetection.io App Test / test-application-3-11 (push) Has been cancelled
ChangeDetection.io App Test / test-application-3-12 (push) Has been cancelled
ChangeDetection.io App Test / test-application-3-13 (push) Has been cancelled
2025-09-09 19:12:48 +02:00
dgtlmoon
15f14e668e group like operators 2025-09-09 19:09:05 +02:00
dgtlmoon
96c564b514 tweaks 2025-09-09 19:06:51 +02:00
dgtlmoon
88fec4df48 Adding ternary field 2025-09-09 18:56:40 +02:00
dgtlmoon
99a3a23e01 On by default 2025-09-09 18:20:01 +02:00
dgtlmoon
9be52cb601 Fix log message 2025-09-09 18:14:12 +02:00
dgtlmoon
a973826e49 Lets use use_page_title_in_list to ON by default 2025-09-09 18:13:31 +02:00
dgtlmoon
256f7179eb Use watch placeholder title 2025-09-09 18:13:05 +02:00
dgtlmoon
359168f40a Improve logic 2025-09-09 18:04:43 +02:00
dgtlmoon
a7c21c566c Always extract page <title> Re #3402 2025-09-08 18:04:02 +02:00
98 changed files with 1319 additions and 2307 deletions

View File

@@ -33,6 +33,7 @@ venv/
# Test and development files
test-datastore/
tests/
docs/
*.md
!README.md

View File

@@ -4,11 +4,11 @@ updates:
directory: /
schedule:
interval: "weekly"
"caronc/apprise":
versioning-strategy: "increase"
schedule:
interval: "daily"
groups:
all:
patterns:
- "*"
- package-ecosystem: pip
directory: /
schedule:
interval: "weekly"

View File

@@ -34,7 +34,7 @@ jobs:
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@v4
uses: github/codeql-action/init@v3
with:
languages: ${{ matrix.language }}
# If you wish to specify custom queries, you can do so here or in a config file.
@@ -45,7 +45,7 @@ jobs:
# Autobuild attempts to build any compiled languages (C/C++, C#, or Java).
# If this step fails, then you should remove it and run the build manually (see below)
- name: Autobuild
uses: github/codeql-action/autobuild@v4
uses: github/codeql-action/autobuild@v3
# Command-line programs to run using the OS shell.
# 📚 https://git.io/JvXDl
@@ -59,4 +59,4 @@ jobs:
# make release
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@v4
uses: github/codeql-action/analyze@v3

View File

@@ -95,7 +95,7 @@ jobs:
push: true
tags: |
${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:dev,ghcr.io/${{ github.repository }}:dev
platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8
platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8,linux/arm64/v8
cache-from: type=gha
cache-to: type=gha,mode=max
@@ -133,7 +133,7 @@ jobs:
file: ./Dockerfile
push: true
tags: ${{ steps.meta.outputs.tags }}
platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8
platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8,linux/arm64/v8
cache-from: type=gha
cache-to: type=gha,mode=max
# Looks like this was disabled

View File

@@ -38,6 +38,8 @@ jobs:
dockerfile: ./Dockerfile
- platform: linux/arm/v8
dockerfile: ./Dockerfile
- platform: linux/arm64/v8
dockerfile: ./Dockerfile
# Alpine Dockerfile platforms (musl via alpine check)
- platform: linux/amd64
dockerfile: ./.github/test/Dockerfile-alpine
@@ -74,5 +76,5 @@ jobs:
file: ${{ matrix.dockerfile }}
platforms: ${{ matrix.platform }}
cache-from: type=gha
cache-to: type=gha,mode=min
cache-to: type=gha,mode=max

View File

@@ -84,11 +84,6 @@ EXPOSE 5000
# The actual flask app module
COPY changedetectionio /app/changedetectionio
# Also for OpenAPI validation wrapper - needs the YML
RUN [ ! -d "/app/docs" ] && mkdir /app/docs
COPY docs/api-spec.yaml /app/docs/api-spec.yaml
# Starting wrapper
COPY changedetection.py /app/changedetection.py

View File

@@ -2,7 +2,7 @@
# Read more https://github.com/dgtlmoon/changedetection.io/wiki
__version__ = '0.50.20'
__version__ = '0.50.12'
from changedetectionio.strtobool import strtobool
from json.decoder import JSONDecodeError

View File

@@ -14,39 +14,6 @@ import copy
from . import schema, schema_create_watch, schema_update_watch, validate_openapi_request
def validate_time_between_check_required(json_data):
"""
Validate that at least one time interval is specified when not using default settings.
Returns None if valid, or error message string if invalid.
Defaults to using global settings if time_between_check_use_default is not provided.
"""
# Default to using global settings if not specified
use_default = json_data.get('time_between_check_use_default', True)
# If using default settings, no validation needed
if use_default:
return None
# If not using defaults, check if time_between_check exists and has at least one non-zero value
time_check = json_data.get('time_between_check')
if not time_check:
# No time_between_check provided and not using defaults - this is an error
return "At least one time interval (weeks, days, hours, minutes, or seconds) must be specified when not using global settings."
# time_between_check exists, check if it has at least one non-zero value
if any([
(time_check.get('weeks') or 0) > 0,
(time_check.get('days') or 0) > 0,
(time_check.get('hours') or 0) > 0,
(time_check.get('minutes') or 0) > 0,
(time_check.get('seconds') or 0) > 0
]):
return None
# time_between_check exists but all values are 0 or empty - this is an error
return "At least one time interval (weeks, days, hours, minutes, or seconds) must be specified when not using global settings."
class Watch(Resource):
def __init__(self, **kwargs):
# datastore is a black box dependency
@@ -88,8 +55,6 @@ class Watch(Resource):
# attr .last_changed will check for the last written text snapshot on change
watch['last_changed'] = watch.last_changed
watch['viewed'] = watch.viewed
watch['link'] = watch.link,
return watch
@auth.check_token
@@ -116,11 +81,6 @@ class Watch(Resource):
if not request.json.get('proxy') in plist:
return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
# Validate time_between_check when not using defaults
validation_error = validate_time_between_check_required(request.json)
if validation_error:
return validation_error, 400
watch.update(request.json)
return "OK", 200
@@ -236,11 +196,6 @@ class CreateWatch(Resource):
if not json_data.get('proxy') in plist:
return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
# Validate time_between_check when not using defaults
validation_error = validate_time_between_check_required(json_data)
if validation_error:
return validation_error, 400
extras = copy.deepcopy(json_data)
# Because we renamed 'tag' to 'tags' but don't want to change the API (can do this in v2 of the API)
@@ -275,8 +230,6 @@ class CreateWatch(Resource):
'last_changed': watch.last_changed,
'last_checked': watch['last_checked'],
'last_error': watch['last_error'],
'link': watch.link,
'page_title': watch['page_title'],
'title': watch['title'],
'url': watch['url'],
'viewed': watch.viewed

View File

@@ -1,7 +1,9 @@
import copy
import yaml
import functools
from flask import request, abort
from loguru import logger
from openapi_core import OpenAPI
from openapi_core.contrib.flask import FlaskOpenAPIRequest
from . import api_schema
from ..model import watch_base
@@ -29,17 +31,17 @@ schema_create_notification_urls['required'] = ['notification_urls']
schema_delete_notification_urls = copy.deepcopy(schema_notification_urls)
schema_delete_notification_urls['required'] = ['notification_urls']
@functools.cache
def get_openapi_spec():
"""Lazy load OpenAPI spec and dependencies only when validation is needed."""
import os
import yaml # Lazy import - only loaded when API validation is actually used
from openapi_core import OpenAPI # Lazy import - saves ~10.7 MB on startup
# Load OpenAPI spec for validation
_openapi_spec = None
spec_path = os.path.join(os.path.dirname(__file__), '../../docs/api-spec.yaml')
with open(spec_path, 'r') as f:
spec_dict = yaml.safe_load(f)
_openapi_spec = OpenAPI.from_dict(spec_dict)
def get_openapi_spec():
global _openapi_spec
if _openapi_spec is None:
import os
spec_path = os.path.join(os.path.dirname(__file__), '../../docs/api-spec.yaml')
with open(spec_path, 'r') as f:
spec_dict = yaml.safe_load(f)
_openapi_spec = OpenAPI.from_dict(spec_dict)
return _openapi_spec
def validate_openapi_request(operation_id):
@@ -48,28 +50,16 @@ def validate_openapi_request(operation_id):
@functools.wraps(f)
def wrapper(*args, **kwargs):
try:
# Skip OpenAPI validation for GET requests since they don't have request bodies
if request.method.upper() != 'GET':
# Lazy import - only loaded when actually validating a request
from openapi_core.contrib.flask import FlaskOpenAPIRequest
spec = get_openapi_spec()
openapi_request = FlaskOpenAPIRequest(request)
result = spec.unmarshal_request(openapi_request)
if result.errors:
from werkzeug.exceptions import BadRequest
error_details = []
for error in result.errors:
error_details.append(str(error))
raise BadRequest(f"OpenAPI validation failed: {error_details}")
except BadRequest:
# Re-raise BadRequest exceptions (validation failures)
raise
spec = get_openapi_spec()
openapi_request = FlaskOpenAPIRequest(request)
result = spec.unmarshal_request(openapi_request)
if result.errors:
abort(400, message=f"OpenAPI validation failed: {result.errors}")
return f(*args, **kwargs)
except Exception as e:
# If OpenAPI spec loading fails, log but don't break existing functionality
logger.critical(f"OpenAPI validation warning for {operation_id}: {e}")
abort(500)
return f(*args, **kwargs)
# If OpenAPI validation fails, log but don't break existing functionality
print(f"OpenAPI validation warning for {operation_id}: {e}")
return f(*args, **kwargs)
return wrapper
return decorator
@@ -79,4 +69,3 @@ from .Tags import Tags, Tag
from .Import import Import
from .SystemInfo import SystemInfo
from .Notifications import Notifications

View File

@@ -119,12 +119,6 @@ def build_watch_json_schema(d):
schema['properties']['time_between_check'] = build_time_between_check_json_schema()
schema['properties']['time_between_check_use_default'] = {
"type": "boolean",
"default": True,
"description": "Whether to use global settings for time between checks - defaults to true if not set"
}
schema['properties']['browser_steps'] = {
"anyOf": [
{

View File

@@ -191,12 +191,6 @@ nav
</ul>
</span>
</fieldset>
<fieldset class="pure-group">
{{ render_checkbox_field(form.application.form.strip_ignored_lines) }}
<span class="pure-form-message-inline">Remove any text that appears in the "Ignore text" from the output (otherwise its just ignored for change-detection)<br>
<i>Note:</i> Changing this will change the status of your existing watches, possibly trigger alerts etc.
</span>
</fieldset>
</div>
<div class="tab-pane-inner" id="api">

View File

@@ -242,7 +242,6 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
'available_timezones': sorted(available_timezones()),
'browser_steps_config': browser_step_ui_config,
'emailprefix': os.getenv('NOTIFICATION_MAIL_BUTTON_PREFIX', False),
'extra_classes': 'checking-now' if worker_handler.is_watch_running(uuid) else '',
'extra_notification_token_placeholder_info': datastore.get_unique_notification_token_placeholders_available(),
'extra_processor_config': form.extra_tab_content(),
'extra_title': f" - Edit - {watch.label}",

View File

@@ -87,6 +87,7 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
form=form,
guid=datastore.data['app_guid'],
has_proxies=datastore.proxy_list,
has_unviewed=datastore.has_unviewed,
hosted_sticky=os.getenv("SALTED_PASS", False) == False,
now_time_server=round(time.time()),
pagination=pagination,
@@ -96,7 +97,6 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
sort_order=request.args.get('order') if request.args.get('order') else request.cookies.get('order'),
system_default_fetcher=datastore.data['settings']['application'].get('fetch_backend'),
tags=sorted_tags,
unread_changes_count=datastore.unread_changes_count,
watches=sorted_watches
)

View File

@@ -82,11 +82,8 @@ document.addEventListener('DOMContentLoaded', function() {
{%- set cols_required = cols_required + 1 -%}
{%- endif -%}
{%- set ui_settings = datastore.data['settings']['application']['ui'] -%}
{%- set wrapper_classes = [
'has-unread-changes' if unread_changes_count else '',
'has-error' if errored_count else '',
] -%}
<div id="watch-table-wrapper" class="{{ wrapper_classes | reject('equalto', '') | join(' ') }}">
<div id="watch-table-wrapper">
{%- set table_classes = [
'favicon-enabled' if 'favicons_enabled' not in ui_settings or ui_settings['favicons_enabled'] else 'favicon-not-enabled',
] -%}
@@ -161,9 +158,9 @@ document.addEventListener('DOMContentLoaded', function() {
<div>
<span class="watch-title">
{% if system_use_url_watchlist or watch.get('use_page_title_in_list') %}
{{ watch.label }}
{{watch.label}}
{% else %}
{{ watch.get('title') or watch.link }}
{{watch.url}}
{% endif %}
<a class="external" target="_blank" rel="noopener" href="{{ watch.link.replace('source:','') }}">&nbsp;</a>
</span>
@@ -244,10 +241,10 @@ document.addEventListener('DOMContentLoaded', function() {
</tbody>
</table>
<ul id="post-list-buttons">
<li id="post-list-with-errors" style="display: none;" >
<li id="post-list-with-errors" class="{%- if errored_count -%}has-error{%- endif -%}" style="display: none;" >
<a href="{{url_for('watchlist.index', with_errors=1, tag=request.args.get('tag')) }}" class="pure-button button-tag button-error">With errors ({{ errored_count }})</a>
</li>
<li id="post-list-mark-views" style="display: none;" >
<li id="post-list-mark-views" class="{%- if has_unviewed -%}has-unviewed{%- endif -%}" style="display: none;" >
<a href="{{url_for('ui.mark_all_viewed',with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag " id="mark-all-viewed">Mark all viewed</a>
</li>
{%- if active_tag_uuid -%}
@@ -255,8 +252,8 @@ document.addEventListener('DOMContentLoaded', function() {
<a href="{{url_for('ui.mark_all_viewed', tag=active_tag_uuid) }}" class="pure-button button-tag " id="mark-all-viewed">Mark all viewed in '{{active_tag.title}}'</a>
</li>
{%- endif -%}
<li id="post-list-unread" style="display: none;" >
<a href="{{url_for('watchlist.index', unread=1, tag=request.args.get('tag')) }}" class="pure-button button-tag">Unread (<span id="unread-tab-counter">{{ unread_changes_count }}</span>)</a>
<li id="post-list-unread" class="{%- if has_unviewed -%}has-unviewed{%- endif -%}" style="display: none;" >
<a href="{{url_for('watchlist.index', unread=1, tag=request.args.get('tag')) }}" class="pure-button button-tag">Unread</a>
</li>
<li>
<a href="{{ url_for('ui.form_watch_checknow', tag=active_tag_uuid, with_errors=request.args.get('with_errors',0)) }}" class="pure-button button-tag" id="recheck-all">Recheck

View File

@@ -23,7 +23,6 @@ from wtforms import (
)
from flask_wtf.file import FileField, FileAllowed
from wtforms.fields import FieldList
from wtforms.utils import unset_value
from wtforms.validators import ValidationError
@@ -57,8 +56,6 @@ valid_method = {
default_method = 'GET'
allow_simplehost = not strtobool(os.getenv('BLOCK_SIMPLEHOSTS', 'False'))
REQUIRE_ATLEAST_ONE_TIME_PART_MESSAGE_DEFAULT='At least one time interval (weeks, days, hours, minutes, or seconds) must be specified.'
REQUIRE_ATLEAST_ONE_TIME_PART_WHEN_NOT_GLOBAL_DEFAULT='At least one time interval (weeks, days, hours, minutes, or seconds) must be specified when not using global settings.'
class StringListField(StringField):
widget = widgets.TextArea()
@@ -215,35 +212,6 @@ class ScheduleLimitForm(Form):
self.sunday.form.enabled.label.text = "Sunday"
def validate_time_between_check_has_values(form):
"""
Custom validation function for TimeBetweenCheckForm.
Returns True if at least one time interval field has a value > 0.
"""
res = any([
form.weeks.data and int(form.weeks.data) > 0,
form.days.data and int(form.days.data) > 0,
form.hours.data and int(form.hours.data) > 0,
form.minutes.data and int(form.minutes.data) > 0,
form.seconds.data and int(form.seconds.data) > 0
])
return res
class RequiredTimeInterval(object):
"""
WTForms validator that ensures at least one time interval field has a value > 0.
Use this with FormField(TimeBetweenCheckForm, validators=[RequiredTimeInterval()]).
"""
def __init__(self, message=None):
self.message = message or 'At least one time interval (weeks, days, hours, minutes, or seconds) must be specified.'
def __call__(self, form, field):
if not validate_time_between_check_has_values(field.form):
raise ValidationError(self.message)
class TimeBetweenCheckForm(Form):
weeks = IntegerField('Weeks', validators=[validators.Optional(), validators.NumberRange(min=0, message="Should contain zero or more seconds")])
days = IntegerField('Days', validators=[validators.Optional(), validators.NumberRange(min=0, message="Should contain zero or more seconds")])
@@ -252,123 +220,6 @@ class TimeBetweenCheckForm(Form):
seconds = IntegerField('Seconds', validators=[validators.Optional(), validators.NumberRange(min=0, message="Should contain zero or more seconds")])
# @todo add total seconds minimum validatior = minimum_seconds_recheck_time
def __init__(self, formdata=None, obj=None, prefix="", data=None, meta=None, **kwargs):
super().__init__(formdata, obj, prefix, data, meta, **kwargs)
self.require_at_least_one = kwargs.get('require_at_least_one', False)
self.require_at_least_one_message = kwargs.get('require_at_least_one_message', REQUIRE_ATLEAST_ONE_TIME_PART_MESSAGE_DEFAULT)
def validate(self, **kwargs):
"""Custom validation that can optionally require at least one time interval."""
# Run normal field validation first
if not super().validate(**kwargs):
return False
# Apply optional "at least one" validation
if self.require_at_least_one:
if not validate_time_between_check_has_values(self):
# Add error to the form's general errors (not field-specific)
if not hasattr(self, '_formdata_errors'):
self._formdata_errors = []
self._formdata_errors.append(self.require_at_least_one_message)
return False
return True
class EnhancedFormField(FormField):
"""
An enhanced FormField that supports conditional validation with top-level error messages.
Adds a 'top_errors' property for validation errors at the FormField level.
"""
def __init__(self, form_class, label=None, validators=None, separator="-",
conditional_field=None, conditional_message=None, conditional_test_function=None, **kwargs):
"""
Initialize EnhancedFormField with optional conditional validation.
:param conditional_field: Name of the field this FormField depends on (e.g. 'time_between_check_use_default')
:param conditional_message: Error message to show when validation fails
:param conditional_test_function: Custom function to test if FormField has valid values.
Should take self.form as parameter and return True if valid.
"""
super().__init__(form_class, label, validators, separator, **kwargs)
self.top_errors = []
self.conditional_field = conditional_field
self.conditional_message = conditional_message or "At least one field must have a value when not using defaults."
self.conditional_test_function = conditional_test_function
def validate(self, form, extra_validators=()):
"""
Custom validation that supports conditional logic and stores top-level errors.
"""
self.top_errors = []
# First run the normal FormField validation
base_valid = super().validate(form, extra_validators)
# Apply conditional validation if configured
if self.conditional_field and hasattr(form, self.conditional_field):
conditional_field_obj = getattr(form, self.conditional_field)
# If the conditional field is False/unchecked, check if this FormField has any values
if not conditional_field_obj.data:
# Use custom test function if provided, otherwise use generic fallback
if self.conditional_test_function:
has_any_value = self.conditional_test_function(self.form)
else:
# Generic fallback - check if any field has truthy data
has_any_value = any(field.data for field in self.form if hasattr(field, 'data') and field.data)
if not has_any_value:
self.top_errors.append(self.conditional_message)
base_valid = False
return base_valid
class RequiredFormField(FormField):
"""
A FormField that passes require_at_least_one=True to TimeBetweenCheckForm.
Use this when you want the sub-form to always require at least one value.
"""
def __init__(self, form_class, label=None, validators=None, separator="-", **kwargs):
super().__init__(form_class, label, validators, separator, **kwargs)
def process(self, formdata, data=unset_value, extra_filters=None):
if extra_filters:
raise TypeError(
"FormField cannot take filters, as the encapsulated"
"data is not mutable."
)
if data is unset_value:
try:
data = self.default()
except TypeError:
data = self.default
self._obj = data
self.object_data = data
prefix = self.name + self.separator
# Pass require_at_least_one=True to the sub-form
if isinstance(data, dict):
self.form = self.form_class(formdata=formdata, prefix=prefix, require_at_least_one=True, **data)
else:
self.form = self.form_class(formdata=formdata, obj=data, prefix=prefix, require_at_least_one=True)
@property
def errors(self):
"""Include sub-form validation errors"""
form_errors = self.form.errors
# Add any general form errors to a special 'form' key
if hasattr(self.form, '_formdata_errors') and self.form._formdata_errors:
form_errors = dict(form_errors) # Make a copy
form_errors['form'] = self.form._formdata_errors
return form_errors
# Separated by key:value
class StringDictKeyValue(StringField):
widget = widgets.TextArea()
@@ -497,7 +348,7 @@ class ValidateJinja2Template(object):
joined_data = ' '.join(map(str, field.data)) if isinstance(field.data, list) else f"{field.data}"
try:
jinja2_env = ImmutableSandboxedEnvironment(loader=BaseLoader, extensions=['jinja2_time.TimeExtension'])
jinja2_env = ImmutableSandboxedEnvironment(loader=BaseLoader)
jinja2_env.globals.update(notification.valid_tokens)
# Extra validation tokens provided on the form_class(... extra_tokens={}) setup
if hasattr(field, 'extra_notification_tokens'):
@@ -732,16 +583,11 @@ class processor_text_json_diff_form(commonSettingsForm):
url = fields.URLField('URL', validators=[validateURL()])
tags = StringTagUUID('Group tag', [validators.Optional()], default='')
time_between_check = EnhancedFormField(
TimeBetweenCheckForm,
conditional_field='time_between_check_use_default',
conditional_message=REQUIRE_ATLEAST_ONE_TIME_PART_WHEN_NOT_GLOBAL_DEFAULT,
conditional_test_function=validate_time_between_check_has_values
)
time_between_check = FormField(TimeBetweenCheckForm)
time_schedule_limit = FormField(ScheduleLimitForm)
time_between_check_use_default = BooleanField('Use global settings for time between check and scheduler.', default=False)
time_between_check_use_default = BooleanField('Use global settings for time between check', default=False)
include_filters = StringListField('CSS/JSONPath/JQ/XPath Filters', [ValidateCSSJSONXPATHInput()], default='')
@@ -759,7 +605,6 @@ class processor_text_json_diff_form(commonSettingsForm):
check_unique_lines = BooleanField('Only trigger when unique lines appear in all history', default=False)
remove_duplicate_lines = BooleanField('Remove duplicate lines of text', default=False)
sort_text_alphabetically = BooleanField('Sort text alphabetically', default=False)
strip_ignored_lines = TernaryNoneBooleanField('Strip ignored lines', default=None)
trim_text_whitespace = BooleanField('Trim whitespace before and after text', default=False)
filter_text_added = BooleanField('Added lines', default=True)
@@ -883,7 +728,7 @@ class DefaultUAInputForm(Form):
# datastore.data['settings']['requests']..
class globalSettingsRequestForm(Form):
time_between_check = RequiredFormField(TimeBetweenCheckForm)
time_between_check = FormField(TimeBetweenCheckForm)
time_schedule_limit = FormField(ScheduleLimitForm)
proxy = RadioField('Proxy')
jitter_seconds = IntegerField('Random jitter seconds ± check',
@@ -937,7 +782,6 @@ class globalSettingsApplicationForm(commonSettingsForm):
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 anonymous access to watch history page when password is enabled', default=False, validators=[validators.Optional()])
strip_ignored_lines = BooleanField('Strip ignored lines')
rss_hide_muted_watches = BooleanField('Hide muted watches from RSS feed', default=True,
validators=[validators.Optional()])
filter_failure_notification_threshold_attempts = IntegerField('Number of times the filter can be missing before sending a notification',

View File

@@ -100,7 +100,7 @@ def element_removal(selectors: List[str], html_content):
xpath_selectors = []
for selector in selectors:
if selector.strip().startswith(('xpath:', 'xpath1:', '//')):
if selector.startswith(('xpath:', 'xpath1:', '//')):
# Handle XPath selectors separately
xpath_selector = selector.removeprefix('xpath:').removeprefix('xpath1:')
xpath_selectors.append(xpath_selector)

View File

@@ -57,7 +57,6 @@ class model(dict):
'rss_hide_muted_watches': True,
'schema_version' : 0,
'shared_diff_access': False,
'strip_ignored_lines': False,
'tags': {}, #@todo use Tag.model initialisers
'timezone': None, # Default IANA timezone name
'webdriver_delay': None , # Extra delay in seconds before extracting text

View File

@@ -170,7 +170,7 @@ class model(watch_base):
@property
def label(self):
# Used for sorting, display, etc
return self.get('title') or self.get('page_title') or self.link
return self.get('title') or self.get('page_title') or self.get('url')
@property
def last_changed(self):

View File

@@ -58,7 +58,6 @@ class watch_base(dict):
'proxy': None, # Preferred proxy connection
'remote_server_reply': None, # From 'server' reply header
'sort_text_alphabetically': False,
'strip_ignored_lines': None,
'subtractive_selectors': [],
'tag': '', # Old system of text name for a tag, to be removed
'tags': [], # list of UUIDs to App.Tags

View File

@@ -1,125 +0,0 @@
"""
Content Type Detection and Stream Classification
This module provides intelligent content-type detection for changedetection.io.
It addresses the common problem where HTTP Content-Type headers are missing, incorrect,
or too generic, which would otherwise cause the wrong processor to be used.
The guess_stream_type class combines:
1. HTTP Content-Type headers (when available and reliable)
2. Python-magic library for MIME detection (analyzing actual file content)
3. Content-based pattern matching for text formats (HTML tags, XML declarations, etc.)
This multi-layered approach ensures accurate detection of RSS feeds, JSON, HTML, PDF,
plain text, CSV, YAML, and XML formats - even when servers provide misleading headers.
Used by: processors/text_json_diff/processor.py and other content processors
"""
# When to apply the 'cdata to real HTML' hack
RSS_XML_CONTENT_TYPES = [
"application/rss+xml",
"application/rdf+xml",
"application/atom+xml",
"text/rss+xml", # rare, non-standard
"application/x-rss+xml", # legacy (older feed software)
"application/x-atom+xml", # legacy (older Atom)
]
# JSON Content-types
JSON_CONTENT_TYPES = [
"application/activity+json",
"application/feed+json",
"application/json",
"application/ld+json",
"application/vnd.api+json",
]
# Generic XML Content-types (non-RSS/Atom)
XML_CONTENT_TYPES = [
"text/xml",
"application/xml",
]
HTML_PATTERNS = ['<!doctype html', '<html', '<head', '<body', '<script', '<iframe', '<div']
from loguru import logger
class guess_stream_type():
is_pdf = False
is_json = False
is_html = False
is_plaintext = False
is_rss = False
is_csv = False
is_xml = False # Generic XML, not RSS/Atom
is_yaml = False
def __init__(self, http_content_header, content):
import re
magic_content_header = http_content_header
test_content = content[:200].lower().strip()
# Remove whitespace between < and tag name for robust detection (handles '< html', '<\nhtml', etc.)
test_content_normalized = re.sub(r'<\s+', '<', test_content)
# Magic will sometimes call text/plain as text/html!
magic_result = None
try:
import magic
mime = magic.from_buffer(content[:200], mime=True) # Send the original content
logger.debug(f"Guessing mime type, original content_type '{http_content_header}', mime type detected '{mime}'")
if mime and "/" in mime:
magic_result = mime
# Ignore generic/fallback mime types from magic
if mime in ['application/octet-stream', 'application/x-empty', 'binary']:
logger.debug(f"Ignoring generic mime type '{mime}' from magic library")
# Trust magic for non-text types immediately
elif mime not in ['text/html', 'text/plain']:
magic_content_header = mime
except Exception as e:
logger.error(f"Error getting a more precise mime type from 'magic' library ({str(e)}), using content-based detection")
# Content-based detection (most reliable for text formats)
# Check for HTML patterns first - if found, override magic's text/plain
has_html_patterns = any(p in test_content_normalized for p in HTML_PATTERNS)
# Always trust headers first
if 'text/plain' in http_content_header:
self.is_plaintext = True
if any(s in http_content_header for s in RSS_XML_CONTENT_TYPES):
self.is_rss = True
elif any(s in http_content_header for s in JSON_CONTENT_TYPES):
self.is_json = True
elif any(s in http_content_header for s in XML_CONTENT_TYPES):
# Only mark as generic XML if not already detected as RSS
if not self.is_rss:
self.is_xml = True
elif 'pdf' in magic_content_header:
self.is_pdf = True
###
elif has_html_patterns or http_content_header == 'text/html':
self.is_html = True
# If magic says text/plain and we found no HTML patterns, trust it
elif magic_result == 'text/plain':
self.is_plaintext = True
logger.debug(f"Trusting magic's text/plain result (no HTML patterns detected)")
elif any(s in magic_content_header for s in JSON_CONTENT_TYPES):
self.is_json = True
# magic will call a rss document 'xml'
elif '<rss' in test_content_normalized or '<feed' in test_content_normalized or any(s in magic_content_header for s in RSS_XML_CONTENT_TYPES):
self.is_rss = True
elif test_content_normalized.startswith('<?xml') or any(s in magic_content_header for s in XML_CONTENT_TYPES):
# Generic XML that's not RSS/Atom (RSS/Atom checked above)
self.is_xml = True
elif '%pdf-1' in test_content:
self.is_pdf = True
elif http_content_header.startswith('text/'):
self.is_plaintext = True
# Only trust magic for 'text' if no other patterns matched
elif 'text' in magic_content_header:
self.is_plaintext = True

View File

@@ -13,8 +13,6 @@ from changedetectionio import html_tools, content_fetchers
from changedetectionio.blueprint.price_data_follower import PRICE_DATA_TRACK_ACCEPT, PRICE_DATA_TRACK_REJECT
from loguru import logger
from changedetectionio.processors.magic import guess_stream_type
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
name = 'Webpage Text/HTML, JSON and PDF changes'
@@ -22,9 +20,6 @@ description = 'Detects all text changes where possible'
json_filter_prefixes = ['json:', 'jq:', 'jqraw:']
# Assume it's this type if the server says nothing on content-type
DEFAULT_WHEN_NO_CONTENT_TYPE_HEADER = 'text/html'
class FilterNotFoundInResponse(ValueError):
def __init__(self, msg, screenshot=None, xpath_data=None):
self.screenshot = screenshot
@@ -37,520 +32,353 @@ class PDFToHTMLToolNotFound(ValueError):
ValueError.__init__(self, msg)
class FilterConfig:
"""Consolidates all filter and rule configurations from watch, tags, and global settings."""
def __init__(self, watch, datastore):
self.watch = watch
self.datastore = datastore
self.watch_uuid = watch.get('uuid')
# Cache computed properties to avoid repeated list operations
self._include_filters_cache = None
self._subtractive_selectors_cache = None
def _get_merged_rules(self, attr, include_global=False):
"""Merge rules from watch, tags, and optionally global settings."""
watch_rules = self.watch.get(attr, [])
tag_rules = self.datastore.get_tag_overrides_for_watch(uuid=self.watch_uuid, attr=attr)
rules = list(dict.fromkeys(watch_rules + tag_rules))
if include_global:
global_rules = self.datastore.data['settings']['application'].get(f'global_{attr}', [])
rules = list(dict.fromkeys(rules + global_rules))
return rules
@property
def include_filters(self):
if self._include_filters_cache is None:
filters = self._get_merged_rules('include_filters')
# Inject LD+JSON price tracker rule if enabled
if self.watch.get('track_ldjson_price_data', '') == PRICE_DATA_TRACK_ACCEPT:
filters += html_tools.LD_JSON_PRODUCT_OFFER_SELECTORS
self._include_filters_cache = filters
return self._include_filters_cache
@property
def subtractive_selectors(self):
if self._subtractive_selectors_cache is None:
watch_selectors = self.watch.get("subtractive_selectors", [])
tag_selectors = self.datastore.get_tag_overrides_for_watch(uuid=self.watch_uuid, attr='subtractive_selectors')
global_selectors = self.datastore.data["settings"]["application"].get("global_subtractive_selectors", [])
self._subtractive_selectors_cache = [*tag_selectors, *watch_selectors, *global_selectors]
return self._subtractive_selectors_cache
@property
def extract_text(self):
return self._get_merged_rules('extract_text')
@property
def ignore_text(self):
return self._get_merged_rules('ignore_text', include_global=True)
@property
def trigger_text(self):
return self._get_merged_rules('trigger_text')
@property
def text_should_not_be_present(self):
return self._get_merged_rules('text_should_not_be_present')
@property
def has_include_filters(self):
return bool(self.include_filters) and bool(self.include_filters[0].strip())
@property
def has_subtractive_selectors(self):
return bool(self.subtractive_selectors) and bool(self.subtractive_selectors[0].strip())
class ContentTransformer:
"""Handles text transformations like trimming, sorting, and deduplication."""
@staticmethod
def trim_whitespace(text):
"""Remove leading/trailing whitespace from each line."""
# Use generator expression to avoid building intermediate list
return '\n'.join(line.strip() for line in text.replace("\n\n", "\n").splitlines())
@staticmethod
def remove_duplicate_lines(text):
"""Remove duplicate lines while preserving order."""
return '\n'.join(dict.fromkeys(line for line in text.replace("\n\n", "\n").splitlines()))
@staticmethod
def sort_alphabetically(text):
"""Sort lines alphabetically (case-insensitive)."""
# Remove double line feeds before sorting
text = text.replace("\n\n", "\n")
return '\n'.join(sorted(text.splitlines(), key=lambda x: x.lower()))
@staticmethod
def extract_by_regex(text, regex_patterns):
"""Extract text matching regex patterns."""
# Use list of strings instead of concatenating lists repeatedly (avoids O(n²) behavior)
regex_matched_output = []
for s_re in regex_patterns:
# Check if it's perl-style regex /.../
if re.search(PERL_STYLE_REGEX, s_re, re.IGNORECASE):
regex = html_tools.perl_style_slash_enclosed_regex_to_options(s_re)
result = re.findall(regex, text)
for match in result:
if type(match) is tuple:
regex_matched_output.extend(match)
regex_matched_output.append('\n')
else:
regex_matched_output.append(match)
regex_matched_output.append('\n')
else:
# Plain text search (case-insensitive)
r = re.compile(re.escape(s_re), re.IGNORECASE)
res = r.findall(text)
if res:
for match in res:
regex_matched_output.append(match)
regex_matched_output.append('\n')
return ''.join(regex_matched_output) if regex_matched_output else ''
class RuleEngine:
"""Evaluates blocking rules (triggers, conditions, text_should_not_be_present)."""
@staticmethod
def evaluate_trigger_text(content, trigger_patterns):
"""
Check if trigger text is present. If trigger_text is configured,
content is blocked UNLESS the trigger is found.
Returns True if blocked, False if allowed.
"""
if not trigger_patterns:
return False
# Assume blocked if trigger_text is configured
result = html_tools.strip_ignore_text(
content=str(content),
wordlist=trigger_patterns,
mode="line numbers"
)
# Unblock if trigger was found
return not bool(result)
@staticmethod
def evaluate_text_should_not_be_present(content, patterns):
"""
Check if forbidden text is present. If found, block the change.
Returns True if blocked, False if allowed.
"""
if not patterns:
return False
result = html_tools.strip_ignore_text(
content=str(content),
wordlist=patterns,
mode="line numbers"
)
# Block if forbidden text was found
return bool(result)
@staticmethod
def evaluate_conditions(watch, datastore, content):
"""
Evaluate custom conditions ruleset.
Returns True if blocked, False if allowed.
"""
if not watch.get('conditions') or not watch.get('conditions_match_logic'):
return False
conditions_result = execute_ruleset_against_all_plugins(
current_watch_uuid=watch.get('uuid'),
application_datastruct=datastore.data,
ephemeral_data={'text': content}
)
# Block if conditions not met
return not conditions_result.get('result')
class ContentProcessor:
"""Handles content preprocessing, filtering, and extraction."""
def __init__(self, fetcher, watch, filter_config, datastore):
self.fetcher = fetcher
self.watch = watch
self.filter_config = filter_config
self.datastore = datastore
def preprocess_rss(self, content):
"""Convert CDATA/comments in RSS to usable text."""
return cdata_in_document_to_text(html_content=content)
def preprocess_pdf(self, raw_content):
"""Convert PDF to HTML using external tool."""
from shutil import which
tool = os.getenv("PDF_TO_HTML_TOOL", "pdftohtml")
if not which(tool):
raise PDFToHTMLToolNotFound(
f"Command-line `{tool}` tool was not found in system PATH, was it installed?"
)
import subprocess
proc = subprocess.Popen(
[tool, '-stdout', '-', '-s', 'out.pdf', '-i'],
stdout=subprocess.PIPE,
stdin=subprocess.PIPE
)
proc.stdin.write(raw_content)
proc.stdin.close()
html_content = proc.stdout.read().decode('utf-8')
proc.wait(timeout=60)
# Add metadata for change detection
metadata = (
f"<p>Added by changedetection.io: Document checksum - "
f"{hashlib.md5(raw_content).hexdigest().upper()} "
f"Original file size - {len(raw_content)} bytes</p>"
)
return html_content.replace('</body>', metadata + '</body>')
def preprocess_json(self, content, has_filters):
"""Format and sort JSON content."""
# Force reformat if no filters specified
if not has_filters:
content = html_tools.extract_json_as_string(content=content, json_filter="json:$")
# Sort JSON to avoid false alerts from reordering
try:
content = json.dumps(json.loads(content), sort_keys=True)
except Exception:
# Might be malformed JSON, continue anyway
pass
return content
def apply_include_filters(self, content, stream_content_type):
"""Apply CSS, XPath, or JSON filters to extract specific content."""
filtered_content = ""
for filter_rule in self.filter_config.include_filters:
# XPath filters
if filter_rule[0] == '/' or filter_rule.startswith('xpath:'):
filtered_content += html_tools.xpath_filter(
xpath_filter=filter_rule.replace('xpath:', ''),
html_content=content,
append_pretty_line_formatting=not self.watch.is_source_type_url,
is_rss=stream_content_type.is_rss
)
# XPath1 filters (first match only)
elif filter_rule.startswith('xpath1:'):
filtered_content += html_tools.xpath1_filter(
xpath_filter=filter_rule.replace('xpath1:', ''),
html_content=content,
append_pretty_line_formatting=not self.watch.is_source_type_url,
is_rss=stream_content_type.is_rss
)
# JSON filters
elif any(filter_rule.startswith(prefix) for prefix in json_filter_prefixes):
filtered_content += html_tools.extract_json_as_string(
content=content,
json_filter=filter_rule
)
# CSS selectors, default fallback
else:
filtered_content += html_tools.include_filters(
include_filters=filter_rule,
html_content=content,
append_pretty_line_formatting=not self.watch.is_source_type_url
)
# Raise error if filter returned nothing
if not filtered_content.strip():
raise FilterNotFoundInResponse(
msg=self.filter_config.include_filters,
screenshot=self.fetcher.screenshot,
xpath_data=self.fetcher.xpath_data
)
return filtered_content
def apply_subtractive_selectors(self, content):
"""Remove elements matching subtractive selectors."""
return html_tools.element_removal(self.filter_config.subtractive_selectors, content)
def extract_text_from_html(self, html_content, stream_content_type):
"""Convert HTML to plain text."""
do_anchor = self.datastore.data["settings"]["application"].get("render_anchor_tag_content", False)
return html_tools.html_to_text(
html_content=html_content,
render_anchor_tag_content=do_anchor,
is_rss=stream_content_type.is_rss
)
class ChecksumCalculator:
"""Calculates checksums with various options."""
@staticmethod
def calculate(text, ignore_whitespace=False):
"""Calculate MD5 checksum of text content."""
if ignore_whitespace:
text = text.translate(TRANSLATE_WHITESPACE_TABLE)
return hashlib.md5(text.encode('utf-8')).hexdigest()
# Some common stuff here that can be moved to a base class
# (set_proxy_from_list)
class perform_site_check(difference_detection_processor):
def run_changedetection(self, watch):
changed_detected = False
html_content = ""
screenshot = False # as bytes
stripped_text_from_html = ""
if not watch:
raise Exception("Watch no longer exists.")
# Initialize components
filter_config = FilterConfig(watch, self.datastore)
content_processor = ContentProcessor(self.fetcher, watch, filter_config, self.datastore)
transformer = ContentTransformer()
rule_engine = RuleEngine()
# Get content type and stream info
ctype_header = self.fetcher.get_all_headers().get('content-type', DEFAULT_WHEN_NO_CONTENT_TYPE_HEADER).lower()
stream_content_type = guess_stream_type(http_content_header=ctype_header, content=self.fetcher.content)
# Unset any existing notification error
update_obj = {'last_notification_error': False, 'last_error': False}
url = watch.link
self.screenshot = self.fetcher.screenshot
self.xpath_data = self.fetcher.xpath_data
# Track the content type and checksum before filters
update_obj['content_type'] = ctype_header
# Track the content type
update_obj['content_type'] = self.fetcher.get_all_headers().get('content-type', '').lower()
# 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()
# === CONTENT PREPROCESSING ===
# Avoid creating unnecessary intermediate string copies by reassigning only when needed
content = self.fetcher.content
# Fetching complete, now filters
# RSS preprocessing
if stream_content_type.is_rss:
content = content_processor.preprocess_rss(content)
# @note: I feel like the following should be in a more obvious chain system
# - Check filter text
# - Is the checksum different?
# - Do we convert to JSON?
# https://stackoverflow.com/questions/41817578/basic-method-chaining ?
# return content().textfilter().jsonextract().checksumcompare() ?
# PDF preprocessing
if watch.is_pdf or stream_content_type.is_pdf:
content = content_processor.preprocess_pdf(raw_content=self.fetcher.raw_content)
stream_content_type.is_html = True
is_json = 'application/json' in self.fetcher.get_all_headers().get('content-type', '').lower()
is_html = not is_json
is_rss = False
# JSON preprocessing
if stream_content_type.is_json:
content = content_processor.preprocess_json(content, filter_config.has_include_filters)
ctype_header = self.fetcher.get_all_headers().get('content-type', '').lower()
# Go into RSS preprocess for converting CDATA/comment to usable text
if any(substring in ctype_header for substring in ['application/xml', 'application/rss', 'text/xml']):
if '<rss' in self.fetcher.content[:100].lower():
self.fetcher.content = cdata_in_document_to_text(html_content=self.fetcher.content)
is_rss = True
# HTML obfuscation workarounds
if stream_content_type.is_html:
content = html_tools.workarounds_for_obfuscations(content)
# Check for LD+JSON price data (for HTML content)
if stream_content_type.is_html:
update_obj['has_ldjson_price_data'] = html_tools.has_ldjson_product_info(content)
# === FILTER APPLICATION ===
# Start with content reference, avoid copy until modification
html_content = content
# Apply include filters (CSS, XPath, JSON)
if filter_config.has_include_filters:
html_content = content_processor.apply_include_filters(content, stream_content_type)
# Apply subtractive selectors
if filter_config.has_subtractive_selectors:
html_content = content_processor.apply_subtractive_selectors(html_content)
# === TEXT EXTRACTION ===
# source: support, basically treat it as plaintext
if watch.is_source_type_url:
# For source URLs, keep raw content
stripped_text = html_content
elif stream_content_type.is_plaintext:
# For plaintext, keep as-is without HTML-to-text conversion
stripped_text = html_content
else:
# Extract text from HTML/RSS content (not generic XML)
if stream_content_type.is_html or stream_content_type.is_rss:
stripped_text = content_processor.extract_text_from_html(html_content, stream_content_type)
is_html = False
is_json = False
inline_pdf = self.fetcher.get_all_headers().get('content-disposition', '') and '%PDF-1' in self.fetcher.content[:10]
if watch.is_pdf or 'application/pdf' in self.fetcher.get_all_headers().get('content-type', '').lower() or inline_pdf:
from shutil import which
tool = os.getenv("PDF_TO_HTML_TOOL", "pdftohtml")
if not which(tool):
raise PDFToHTMLToolNotFound("Command-line `{}` tool was not found in system PATH, was it installed?".format(tool))
import subprocess
proc = subprocess.Popen(
[tool, '-stdout', '-', '-s', 'out.pdf', '-i'],
stdout=subprocess.PIPE,
stdin=subprocess.PIPE)
proc.stdin.write(self.fetcher.raw_content)
proc.stdin.close()
self.fetcher.content = proc.stdout.read().decode('utf-8')
proc.wait(timeout=60)
# Add a little metadata so we know if the file changes (like if an image changes, but the text is the same
# @todo may cause problems with non-UTF8?
metadata = "<p>Added by changedetection.io: Document checksum - {} Filesize - {} bytes</p>".format(
hashlib.md5(self.fetcher.raw_content).hexdigest().upper(),
len(self.fetcher.content))
self.fetcher.content = self.fetcher.content.replace('</body>', metadata + '</body>')
# Better would be if Watch.model could access the global data also
# and then use getattr https://docs.python.org/3/reference/datamodel.html#object.__getitem__
# https://realpython.com/inherit-python-dict/ instead of doing it procedurely
include_filters_from_tags = self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='include_filters')
# 1845 - remove duplicated filters in both group and watch include filter
include_filters_rule = list(dict.fromkeys(watch.get('include_filters', []) + include_filters_from_tags))
subtractive_selectors = [*self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='subtractive_selectors'),
*watch.get("subtractive_selectors", []),
*self.datastore.data["settings"]["application"].get("global_subtractive_selectors", [])
]
# Inject a virtual LD+JSON price tracker rule
if watch.get('track_ldjson_price_data', '') == PRICE_DATA_TRACK_ACCEPT:
include_filters_rule += html_tools.LD_JSON_PRODUCT_OFFER_SELECTORS
has_filter_rule = len(include_filters_rule) and len(include_filters_rule[0].strip())
has_subtractive_selectors = len(subtractive_selectors) and len(subtractive_selectors[0].strip())
if is_json and not has_filter_rule:
include_filters_rule.append("json:$")
has_filter_rule = True
if is_json:
# Sort the JSON so we dont get false alerts when the content is just re-ordered
try:
self.fetcher.content = json.dumps(json.loads(self.fetcher.content), sort_keys=True)
except Exception as e:
# Might have just been a snippet, or otherwise bad JSON, continue
pass
if has_filter_rule:
for filter in include_filters_rule:
if any(prefix in filter for prefix in json_filter_prefixes):
stripped_text_from_html += html_tools.extract_json_as_string(content=self.fetcher.content, json_filter=filter)
is_html = False
if is_html or watch.is_source_type_url:
# CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
self.fetcher.content = html_tools.workarounds_for_obfuscations(self.fetcher.content)
html_content = self.fetcher.content
# If not JSON, and if it's not text/plain..
if 'text/plain' in self.fetcher.get_all_headers().get('content-type', '').lower():
# Don't run get_text or xpath/css filters on plaintext
stripped_text_from_html = html_content
else:
stripped_text = html_content
# Does it have some ld+json price data? used for easier monitoring
update_obj['has_ldjson_price_data'] = html_tools.has_ldjson_product_info(self.fetcher.content)
# Then we assume HTML
if has_filter_rule:
html_content = ""
for filter_rule in include_filters_rule:
# For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
if filter_rule[0] == '/' or filter_rule.startswith('xpath:'):
html_content += html_tools.xpath_filter(xpath_filter=filter_rule.replace('xpath:', ''),
html_content=self.fetcher.content,
append_pretty_line_formatting=not watch.is_source_type_url,
is_rss=is_rss)
elif filter_rule.startswith('xpath1:'):
html_content += html_tools.xpath1_filter(xpath_filter=filter_rule.replace('xpath1:', ''),
html_content=self.fetcher.content,
append_pretty_line_formatting=not watch.is_source_type_url,
is_rss=is_rss)
else:
html_content += html_tools.include_filters(include_filters=filter_rule,
html_content=self.fetcher.content,
append_pretty_line_formatting=not watch.is_source_type_url)
if not html_content.strip():
raise FilterNotFoundInResponse(msg=include_filters_rule, screenshot=self.fetcher.screenshot, xpath_data=self.fetcher.xpath_data)
if has_subtractive_selectors:
html_content = html_tools.element_removal(subtractive_selectors, html_content)
if watch.is_source_type_url:
stripped_text_from_html = html_content
else:
# extract text
do_anchor = self.datastore.data["settings"]["application"].get("render_anchor_tag_content", False)
stripped_text_from_html = html_tools.html_to_text(html_content=html_content,
render_anchor_tag_content=do_anchor,
is_rss=is_rss) # 1874 activate the <title workaround hack
# === TEXT TRANSFORMATIONS ===
if watch.get('trim_text_whitespace'):
stripped_text = transformer.trim_whitespace(stripped_text)
stripped_text_from_html = '\n'.join(line.strip() for line in stripped_text_from_html.replace("\n\n", "\n").splitlines())
# Save text before ignore filters (for diff calculation)
text_content_before_ignored_filter = stripped_text
# Re #340 - return the content before the 'ignore text' was applied
# Also used to calculate/show what was removed
text_content_before_ignored_filter = stripped_text_from_html
# @todo whitespace coming from missing rtrim()?
# stripped_text_from_html could be based on their preferences, replace the processed text with only that which they want to know about.
# Rewrite's the processing text based on only what diff result they want to see
# === DIFF FILTERING ===
# If user wants specific diff types (added/removed/replaced only)
if watch.has_special_diff_filter_options_set() and len(watch.history.keys()):
stripped_text = self._apply_diff_filtering(watch, stripped_text, text_content_before_ignored_filter)
if stripped_text is None:
# No differences found, but content exists
c = ChecksumCalculator.calculate(text_content_before_ignored_filter, ignore_whitespace=True)
return False, {'previous_md5': c}, text_content_before_ignored_filter.encode('utf-8')
# Now the content comes from the diff-parser and not the returned HTTP traffic, so could be some differences
from changedetectionio import diff
# needs to not include (added) etc or it may get used twice
# Replace the processed text with the preferred result
rendered_diff = diff.render_diff(previous_version_file_contents=watch.get_last_fetched_text_before_filters(),
newest_version_file_contents=stripped_text_from_html,
include_equal=False, # not the same lines
include_added=watch.get('filter_text_added', True),
include_removed=watch.get('filter_text_removed', True),
include_replaced=watch.get('filter_text_replaced', True),
line_feed_sep="\n",
include_change_type_prefix=False)
# === EMPTY PAGE CHECK ===
watch.save_last_text_fetched_before_filters(text_content_before_ignored_filter.encode('utf-8'))
if not rendered_diff and stripped_text_from_html:
# We had some content, but no differences were found
# Store our new file as the MD5 so it will trigger in the future
c = hashlib.md5(stripped_text_from_html.translate(TRANSLATE_WHITESPACE_TABLE).encode('utf-8')).hexdigest()
return False, {'previous_md5': c}, stripped_text_from_html.encode('utf-8')
else:
stripped_text_from_html = rendered_diff
# Treat pages with no renderable text content as a change? No by default
empty_pages_are_a_change = self.datastore.data['settings']['application'].get('empty_pages_are_a_change', False)
if not stream_content_type.is_json and not empty_pages_are_a_change and len(stripped_text.strip()) == 0:
raise content_fetchers.exceptions.ReplyWithContentButNoText(
url=url,
status_code=self.fetcher.get_last_status_code(),
screenshot=self.fetcher.screenshot,
has_filters=filter_config.has_include_filters,
html_content=html_content,
xpath_data=self.fetcher.xpath_data
)
if not is_json and not empty_pages_are_a_change and len(stripped_text_from_html.strip()) == 0:
raise content_fetchers.exceptions.ReplyWithContentButNoText(url=url,
status_code=self.fetcher.get_last_status_code(),
screenshot=self.fetcher.screenshot,
has_filters=has_filter_rule,
html_content=html_content,
xpath_data=self.fetcher.xpath_data
)
# We rely on the actual text in the html output.. many sites have random script vars etc,
# in the future we'll implement other mechanisms.
update_obj["last_check_status"] = self.fetcher.get_last_status_code()
# === REGEX EXTRACTION ===
if filter_config.extract_text:
extracted = transformer.extract_by_regex(stripped_text, filter_config.extract_text)
stripped_text = extracted
# 615 Extract text by regex
extract_text = list(dict.fromkeys(watch.get('extract_text', []) + self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='extract_text')))
if len(extract_text) > 0:
regex_matched_output = []
for s_re in extract_text:
# incase they specified something in '/.../x'
if re.search(PERL_STYLE_REGEX, s_re, re.IGNORECASE):
regex = html_tools.perl_style_slash_enclosed_regex_to_options(s_re)
result = re.findall(regex, stripped_text_from_html)
for l in result:
if type(l) is tuple:
# @todo - some formatter option default (between groups)
regex_matched_output += list(l) + ['\n']
else:
# @todo - some formatter option default (between each ungrouped result)
regex_matched_output += [l] + ['\n']
else:
# Doesnt look like regex, just hunt for plaintext and return that which matches
# `stripped_text_from_html` will be bytes, so we must encode s_re also to bytes
r = re.compile(re.escape(s_re), re.IGNORECASE)
res = r.findall(stripped_text_from_html)
if res:
for match in res:
regex_matched_output += [match] + ['\n']
##########################################################
stripped_text_from_html = ''
if regex_matched_output:
# @todo some formatter for presentation?
stripped_text_from_html = ''.join(regex_matched_output)
# === MORE TEXT TRANSFORMATIONS ===
if watch.get('remove_duplicate_lines'):
stripped_text = transformer.remove_duplicate_lines(stripped_text)
stripped_text_from_html = '\n'.join(dict.fromkeys(line for line in stripped_text_from_html.replace("\n\n", "\n").splitlines()))
if watch.get('sort_text_alphabetically'):
stripped_text = transformer.sort_alphabetically(stripped_text)
# Note: Because a <p>something</p> will add an extra line feed to signify the paragraph gap
# we end up with 'Some text\n\n', sorting will add all those extra \n at the start, so we remove them here.
stripped_text_from_html = stripped_text_from_html.replace("\n\n", "\n")
stripped_text_from_html = '\n'.join(sorted(stripped_text_from_html.splitlines(), key=lambda x: x.lower()))
# === CHECKSUM CALCULATION ===
text_for_checksuming = stripped_text
### CALCULATE MD5
# If there's text to ignore
text_to_ignore = watch.get('ignore_text', []) + self.datastore.data['settings']['application'].get('global_ignore_text', [])
text_to_ignore += self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='ignore_text')
# Apply ignore_text for checksum calculation
if filter_config.ignore_text:
text_for_checksuming = html_tools.strip_ignore_text(stripped_text, filter_config.ignore_text)
text_for_checksuming = stripped_text_from_html
if text_to_ignore:
text_for_checksuming = html_tools.strip_ignore_text(stripped_text_from_html, text_to_ignore)
# Optionally remove ignored lines from output
strip_ignored_lines = watch.get('strip_ignored_lines')
if strip_ignored_lines is None:
strip_ignored_lines = self.datastore.data['settings']['application'].get('strip_ignored_lines')
if strip_ignored_lines:
stripped_text = text_for_checksuming
# Re #133 - if we should strip whitespaces from triggering the change detected comparison
if text_for_checksuming and self.datastore.data['settings']['application'].get('ignore_whitespace', False):
fetched_md5 = hashlib.md5(text_for_checksuming.translate(TRANSLATE_WHITESPACE_TABLE).encode('utf-8')).hexdigest()
else:
fetched_md5 = hashlib.md5(text_for_checksuming.encode('utf-8')).hexdigest()
# Calculate checksum
ignore_whitespace = self.datastore.data['settings']['application'].get('ignore_whitespace', False)
fetched_md5 = ChecksumCalculator.calculate(text_for_checksuming, ignore_whitespace=ignore_whitespace)
# === BLOCKING RULES EVALUATION ===
############ Blocking rules, after checksum #################
blocked = False
# Check trigger_text
if rule_engine.evaluate_trigger_text(stripped_text, filter_config.trigger_text):
trigger_text = list(dict.fromkeys(watch.get('trigger_text', []) + self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='trigger_text')))
if len(trigger_text):
# Assume blocked
blocked = True
# Filter and trigger works the same, so reuse it
# It should return the line numbers that match
# Unblock flow if the trigger was found (some text remained after stripped what didnt match)
result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
wordlist=trigger_text,
mode="line numbers")
# Unblock if the trigger was found
if result:
blocked = False
# Check text_should_not_be_present
if rule_engine.evaluate_text_should_not_be_present(stripped_text, filter_config.text_should_not_be_present):
blocked = True
text_should_not_be_present = list(dict.fromkeys(watch.get('text_should_not_be_present', []) + self.datastore.get_tag_overrides_for_watch(uuid=watch.get('uuid'), attr='text_should_not_be_present')))
if len(text_should_not_be_present):
# If anything matched, then we should block a change from happening
result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
wordlist=text_should_not_be_present,
mode="line numbers")
if result:
blocked = True
# Check custom conditions
if rule_engine.evaluate_conditions(watch, self.datastore, stripped_text):
blocked = True
# And check if 'conditions' will let this pass through
if watch.get('conditions') and watch.get('conditions_match_logic'):
conditions_result = execute_ruleset_against_all_plugins(current_watch_uuid=watch.get('uuid'),
application_datastruct=self.datastore.data,
ephemeral_data={
'text': stripped_text_from_html
}
)
# === CHANGE DETECTION ===
if not conditions_result.get('result'):
# Conditions say "Condition not met" so we block it.
blocked = True
# Looks like something changed, but did it match all the rules?
if blocked:
changed_detected = False
else:
# Compare checksums
# 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 first run, initialize previous_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}")
# === UNIQUE LINES CHECK ===
if changed_detected and watch.get('check_unique_lines', False):
has_unique_lines = watch.lines_contain_something_unique_compared_to_history(
lines=stripped_text.splitlines(),
ignore_whitespace=ignore_whitespace
)
if changed_detected:
if watch.get('check_unique_lines', False):
ignore_whitespace = self.datastore.data['settings']['application'].get('ignore_whitespace')
if not has_unique_lines:
logger.debug(f"check_unique_lines: UUID {watch.get('uuid')} didnt have anything new setting change_detected=False")
changed_detected = False
else:
logger.debug(f"check_unique_lines: UUID {watch.get('uuid')} had unique content")
has_unique_lines = watch.lines_contain_something_unique_compared_to_history(
lines=stripped_text_from_html.splitlines(),
ignore_whitespace=ignore_whitespace
)
return changed_detected, update_obj, stripped_text
# One or more lines? unsure?
if not has_unique_lines:
logger.debug(f"check_unique_lines: UUID {watch.get('uuid')} didnt have anything new setting change_detected=False")
changed_detected = False
else:
logger.debug(f"check_unique_lines: UUID {watch.get('uuid')} had unique content")
def _apply_diff_filtering(self, watch, stripped_text, text_before_filter):
"""Apply user's diff filtering preferences (show only added/removed/replaced lines)."""
from changedetectionio import diff
rendered_diff = diff.render_diff(
previous_version_file_contents=watch.get_last_fetched_text_before_filters(),
newest_version_file_contents=stripped_text,
include_equal=False,
include_added=watch.get('filter_text_added', True),
include_removed=watch.get('filter_text_removed', True),
include_replaced=watch.get('filter_text_replaced', True),
line_feed_sep="\n",
include_change_type_prefix=False
)
watch.save_last_text_fetched_before_filters(text_before_filter.encode('utf-8'))
if not rendered_diff and stripped_text:
# No differences found
return None
return rendered_diff
# stripped_text_from_html - Everything after filters and NO 'ignored' content
return changed_detected, update_obj, stripped_text_from_html

View File

@@ -243,15 +243,14 @@ def handle_watch_update(socketio, **kwargs):
general_stats = {
'count_errors': errored_count,
'unread_changes_count': datastore.unread_changes_count
'has_unviewed': datastore.has_unviewed
}
# Debug what's being emitted
# logger.debug(f"Emitting 'watch_update' event for {watch.get('uuid')}, data: {watch_data}")
# Emit to all clients (no 'broadcast' parameter needed - it's the default behavior)
socketio.emit("watch_update", {'watch': watch_data})
socketio.emit("general_stats_update", general_stats)
socketio.emit("watch_update", {'watch': watch_data, 'general_stats': general_stats})
# Log after successful emit - use watch_data['uuid'] to avoid variable shadowing issues
logger.trace(f"Socket.IO: Emitted update for watch {watch_data['uuid']}, Checking now: {watch_data['checking_now']}")

View File

@@ -9,7 +9,7 @@ set -x
# SOCKS5 related - start simple Socks5 proxy server
# SOCKSTEST=xyz should show in the logs of this service to confirm it fetched
docker run --network changedet-network -d --hostname socks5proxy --rm --name socks5proxy -p 1080:1080 -e PROXY_USER=proxy_user123 -e PROXY_PASSWORD=proxy_pass123 serjs/go-socks5-proxy
docker run --network changedet-network -d --hostname socks5proxy-noauth --rm -p 1081:1080 --name socks5proxy-noauth -e REQUIRE_AUTH=false serjs/go-socks5-proxy
docker run --network changedet-network -d --hostname socks5proxy-noauth --rm -p 1081:1080 --name socks5proxy-noauth serjs/go-socks5-proxy
echo "---------------------------------- SOCKS5 -------------------"
# SOCKS5 related - test from proxies.json

View File

@@ -117,16 +117,15 @@ $(document).ready(function () {
}
})
socket.on('general_stats_update', function (general_stats) {
// Tabs at bottom of list
$('#watch-table-wrapper').toggleClass("has-unread-changes", general_stats.unread_changes_count !==0)
$('#watch-table-wrapper').toggleClass("has-error", general_stats.count_errors !== 0)
$('#post-list-with-errors a').text(`With errors (${ new Intl.NumberFormat(navigator.language).format(general_stats.count_errors) })`);
$('#unread-tab-counter').text(new Intl.NumberFormat(navigator.language).format(general_stats.unread_changes_count));
});
socket.on('watch_update', function (data) {
const watch = data.watch;
const general_stats = data.general_stats;
// Log the entire watch object for debugging
console.log('!!! WATCH UPDATE EVENT RECEIVED !!!');
console.log(`${watch.event_timestamp} - Watch update ${watch.uuid} - Checking now - ${watch.checking_now} - UUID in URL ${window.location.href.includes(watch.uuid)}`);
console.log('Watch data:', watch);
console.log('General stats:', general_stats);
// Updating watch table rows
const $watchRow = $('tr[data-watch-uuid="' + watch.uuid + '"]');
@@ -151,6 +150,13 @@ $(document).ready(function () {
console.log('Updated UI for watch:', watch.uuid);
}
// Tabs at bottom of list
$('#post-list-mark-views').toggleClass("has-unviewed", general_stats.has_unviewed);
$('#post-list-unread').toggleClass("has-unviewed", general_stats.has_unviewed);
$('#post-list-with-errors').toggleClass("has-error", general_stats.count_errors !== 0)
$('#post-list-with-errors a').text(`With errors (${ general_stats.count_errors })`);
$('body').toggleClass('checking-now', watch.checking_now && window.location.href.includes(watch.uuid));
});

View File

@@ -17,6 +17,18 @@ body.checking-now {
position: fixed;
}
#post-list-buttons {
#post-list-with-errors.has-error {
display: inline-block !important;
}
#post-list-mark-views.has-unviewed {
display: inline-block !important;
}
#post-list-unread.has-unviewed {
display: inline-block !important;
}
}

View File

@@ -127,44 +127,5 @@
display: inline-block !important;
}
}
}
#watch-table-wrapper {
/* general styling */
#post-list-buttons {
text-align: right;
padding: 0px;
margin: 0px;
li {
display: inline-block;
}
a {
border-top-left-radius: initial;
border-top-right-radius: initial;
border-bottom-left-radius: 5px;
border-bottom-right-radius: 5px;
}
}
/* post list dynamically on/off stuff */
&.has-error {
#post-list-buttons {
#post-list-with-errors {
display: inline-block !important;
}
}
}
&.has-unread-changes {
#post-list-buttons {
#post-list-unread, #post-list-mark-views, #post-list-unread {
display: inline-block !important;
}
}
}
}

View File

@@ -34,6 +34,7 @@
transition: all 0.2s ease;
cursor: pointer;
display: block;
min-width: 60px;
text-align: center;
}

View File

@@ -203,6 +203,24 @@ code {
}
#post-list-buttons {
text-align: right;
padding: 0px;
margin: 0px;
li {
display: inline-block;
}
a {
border-top-left-radius: initial;
border-top-right-radius: initial;
border-bottom-left-radius: 5px;
border-bottom-right-radius: 5px;
}
}
body:after {
content: "";
background: linear-gradient(130deg, var(--color-background-gradient-first), var(--color-background-gradient-second) 41.07%, var(--color-background-gradient-third) 84.05%);

File diff suppressed because one or more lines are too long

View File

@@ -202,13 +202,14 @@ class ChangeDetectionStore:
return seconds
@property
def unread_changes_count(self):
unread_changes_count = 0
def has_unviewed(self):
if not self.__data.get('watching'):
return None
for uuid, watch in self.__data['watching'].items():
if watch.history_n >= 2 and watch.viewed == False:
unread_changes_count += 1
return unread_changes_count
return True
return False
@property
def data(self):

View File

@@ -1,29 +1,14 @@
{% macro render_field(field) %}
<div {% if field.errors or field.top_errors %} class="error" {% endif %}>{{ field.label }}</div>
<div {% if field.errors or field.top_errors %} class="error" {% endif %}>{{ field(**kwargs)|safe }}
{% if field.top_errors %}
top
<ul class="errors top-errors">
{% for error in field.top_errors %}
<li>{{ error }}</li>
{% endfor %}
</ul>
{% endif %}
{% if field.errors %}
<ul class=errors>
{% if field.errors is mapping and 'form' in field.errors %}
{# and subfield form errors, such as used in RequiredFormField() for TimeBetweenCheckForm sub form #}
{% set errors = field.errors['form'] %}
{% else %}
{# regular list of errors with this field #}
{% set errors = field.errors %}
{% endif %}
{% for error in errors %}
<li>{{ error }}</li>
{% endfor %}
</ul>
{% endif %}
</div>
<div {% if field.errors %} class="error" {% endif %}>{{ field.label }}</div>
<div {% if field.errors %} class="error" {% endif %}>{{ field(**kwargs)|safe }}
{% if field.errors %}
<ul class=errors>
{% for error in field.errors %}
<li>{{ error }}</li>
{% endfor %}
</ul>
{% endif %}
</div>
{% endmacro %}
{% macro render_checkbox_field(field) %}

View File

@@ -5,7 +5,6 @@
<meta charset="utf-8" >
<meta name="viewport" content="width=device-width, initial-scale=1.0" >
<meta name="description" content="Self hosted website change detection." >
<meta name="robots" content="noindex">
<title>Change Detection{{extra_title}}</title>
{% if app_rss_token %}
<link rel="alternate" type="application/rss+xml" title="Changedetection.io » Feed{% if active_tag_uuid %}- {{active_tag.title}}{% endif %}" href="{{ url_for('rss.feed', tag=active_tag_uuid , token=app_rss_token)}}" >
@@ -41,7 +40,7 @@
{% endif %}
</head>
<body class="{{extra_classes}}">
<body class="">
<div class="header">
<div class="pure-menu-fixed" style="width: 100%;">
<div class="home-menu pure-menu pure-menu-horizontal" id="nav-menu">

View File

@@ -26,10 +26,7 @@
<li>Changing this will affect the comparison checksum which may trigger an alert</li>
</ul>
</span>
<br><br>
<div class="pure-control-group">
{{ render_ternary_field(form.strip_ignored_lines) }}
</div>
</fieldset>
<fieldset>

View File

@@ -29,28 +29,16 @@ def reportlog(pytestconfig):
logger.remove(handler_id)
def format_memory_human(bytes_value):
"""Format memory in human-readable units (KB, MB, GB)"""
if bytes_value < 1024:
return f"{bytes_value} B"
elif bytes_value < 1024 ** 2:
return f"{bytes_value / 1024:.2f} KB"
elif bytes_value < 1024 ** 3:
return f"{bytes_value / (1024 ** 2):.2f} MB"
else:
return f"{bytes_value / (1024 ** 3):.2f} GB"
def track_memory(memory_usage, ):
process = psutil.Process(os.getpid())
while not memory_usage["stop"]:
current_rss = process.memory_info().rss
memory_usage["peak"] = max(memory_usage["peak"], current_rss)
memory_usage["current"] = current_rss # Keep updating current
time.sleep(0.01) # Adjust the sleep time as needed
@pytest.fixture(scope='function')
def measure_memory_usage(request):
memory_usage = {"peak": 0, "current": 0, "stop": False}
memory_usage = {"peak": 0, "stop": False}
tracker_thread = Thread(target=track_memory, args=(memory_usage,))
tracker_thread.start()
@@ -59,17 +47,16 @@ def measure_memory_usage(request):
memory_usage["stop"] = True
tracker_thread.join()
# Note: psutil returns RSS memory in bytes
peak_human = format_memory_human(memory_usage["peak"])
s = f"{time.time()} {request.node.fspath} - '{request.node.name}' - Peak memory: {peak_human}"
# Note: ru_maxrss is in kilobytes on Unix-based systems
max_memory_used = memory_usage["peak"] / 1024 # Convert to MB
s = f"Peak memory used by the test {request.node.fspath} - '{request.node.name}': {max_memory_used:.2f} MB"
logger.debug(s)
with open("test-memory.log", 'a') as f:
f.write(f"{s}\n")
# Assert that the memory usage is less than 200MB
# assert peak_memory_kb < 150 * 1024, f"Memory usage exceeded 150MB: {peak_human}"
# assert max_memory_used < 150, f"Memory usage exceeded 200MB: {max_memory_used:.2f} MB"
def cleanup(datastore_path):

View File

@@ -29,8 +29,13 @@ def do_test(client, live_server, make_test_use_extra_browser=False):
assert b"Settings updated." in res.data
# Add our URL to the import page
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
if make_test_use_extra_browser:
@@ -50,8 +55,7 @@ def do_test(client, live_server, make_test_use_extra_browser=False):
"tags": "",
"headers": "",
'fetch_backend': f"extra_browser_{custom_browser_name}",
'webdriver_js_execute_code': '',
"time_between_check_use_default": "y"
'webdriver_js_execute_code': ''
},
follow_redirects=True
)

View File

@@ -28,7 +28,6 @@ def test_execute_custom_js(client, live_server, measure_memory_usage):
'fetch_backend': "html_webdriver",
'webdriver_js_execute_code': 'document.querySelector("button[name=test-button]").click();',
'headers': "testheader: yes\buser-agent: MyCustomAgent",
"time_between_check_use_default": "y",
},
follow_redirects=True
)

View File

@@ -27,7 +27,6 @@ def test_preferred_proxy(client, live_server, measure_memory_usage):
"proxy": "proxy-two",
"tags": "",
"url": url,
"time_between_check_use_default": "y",
},
follow_redirects=True
)

View File

@@ -62,7 +62,6 @@ def test_noproxy_option(client, live_server, measure_memory_usage):
"proxy": "no-proxy",
"tags": "",
"url": url,
"time_between_check_use_default": "y",
},
follow_redirects=True
)

View File

@@ -44,7 +44,6 @@ def test_proxy_noconnect_custom(client, live_server, measure_memory_usage):
"url": test_url,
"fetch_backend": "html_webdriver" if os.getenv('PLAYWRIGHT_DRIVER_URL') or os.getenv("WEBDRIVER_URL") else "html_requests",
"proxy": "ui-0custom-test-proxy",
"time_between_check_use_default": "y",
}
res = client.post(

View File

@@ -2,7 +2,7 @@
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, delete_all_watches
from changedetectionio.tests.util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
def set_response():
@@ -66,7 +66,6 @@ def test_socks5(client, live_server, measure_memory_usage):
"proxy": "ui-0socks5proxy",
"tags": "",
"url": test_url,
"time_between_check_use_default": "y",
},
follow_redirects=True
)
@@ -98,5 +97,6 @@ def test_socks5(client, live_server, measure_memory_usage):
)
assert b"OK" in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -53,7 +53,6 @@ def test_socks5_from_proxiesjson_file(client, live_server, measure_memory_usage)
"proxy": "socks5proxy",
"tags": "",
"url": test_url,
"time_between_check_use_default": "y",
},
follow_redirects=True
)

View File

@@ -5,7 +5,7 @@ import re
from flask import url_for
from changedetectionio.tests.util import set_original_response, set_modified_response, set_more_modified_response, live_server_setup, \
wait_for_all_checks, \
set_longer_modified_response, delete_all_watches
set_longer_modified_response
from changedetectionio.tests.util import extract_UUID_from_client
import logging
import base64
@@ -85,7 +85,8 @@ def test_check_notification_email_formats_default_HTML(client, live_server, meas
assert '(added) So let\'s see what happens.\r\n' in msg # The plaintext part with \r\n
assert 'Content-Type: text/html' in msg
assert '(added) So let\'s see what happens.<br>' in msg # the html part
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_check_notification_email_formats_default_Text_override_HTML(client, live_server, measure_memory_usage):
@@ -156,8 +157,7 @@ def test_check_notification_email_formats_default_Text_override_HTML(client, liv
data={
"url": test_url,
"notification_format": 'HTML',
'fetch_backend': "html_requests",
"time_between_check_use_default": "y"},
'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -178,4 +178,5 @@ def test_check_notification_email_formats_default_Text_override_HTML(client, liv
assert '&lt;' not in msg
assert 'Content-Type: text/html' in msg
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -2,7 +2,7 @@ from .util import live_server_setup, wait_for_all_checks
from flask import url_for
import time
def test_check_access_control(app, client, live_server, measure_memory_usage):
def test_check_access_control(app, client, live_server):
# Still doesnt work, but this is closer.
# live_server_setup(live_server) # Setup on conftest per function

View File

@@ -3,7 +3,7 @@
import os.path
from flask import url_for
from .util import live_server_setup, wait_for_all_checks, wait_for_notification_endpoint_output, delete_all_watches
from .util import live_server_setup, wait_for_all_checks, wait_for_notification_endpoint_output
import time
def set_original(excluding=None, add_line=None):
@@ -44,8 +44,12 @@ def test_check_removed_line_contains_trigger(client, live_server, measure_memory
set_original()
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Give the thread time to pick it up
wait_for_all_checks(client)
@@ -57,8 +61,7 @@ def test_check_removed_line_contains_trigger(client, live_server, measure_memory
data={"trigger_text": 'The golden line',
"url": test_url,
'fetch_backend': "html_requests",
'filter_text_removed': 'y',
"time_between_check_use_default": "y"},
'filter_text_removed': 'y'},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -71,7 +74,7 @@ def test_check_removed_line_contains_trigger(client, live_server, measure_memory
wait_for_all_checks(client)
time.sleep(0.5)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
# The trigger line is REMOVED, this should trigger
set_original(excluding='The golden line')
@@ -80,7 +83,7 @@ def test_check_removed_line_contains_trigger(client, live_server, measure_memory
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
time.sleep(1)
@@ -94,21 +97,23 @@ def test_check_removed_line_contains_trigger(client, live_server, measure_memory
wait_for_all_checks(client)
time.sleep(1)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
# Remove it again, and we should get a trigger
set_original(excluding='The golden line')
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_check_add_line_contains_trigger(client, live_server, measure_memory_usage):
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
time.sleep(1)
# Give the endpoint time to spin up
@@ -131,8 +136,12 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
set_original()
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Give the thread time to pick it up
wait_for_all_checks(client)
@@ -145,8 +154,7 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
'processor': 'text_json_diff',
'fetch_backend': "html_requests",
'filter_text_removed': '',
'filter_text_added': 'y',
"time_between_check_use_default": "y"},
'filter_text_added': 'y'},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -159,7 +167,7 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
# The trigger line is ADDED, this should trigger
set_original(add_line='<p>Oh yes please</p>')
@@ -167,7 +175,7 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
# Takes a moment for apprise to fire
wait_for_notification_endpoint_output()
@@ -177,4 +185,5 @@ def test_check_add_line_contains_trigger(client, live_server, measure_memory_usa
assert b'-Oh yes please' in response
assert '网站监测 内容更新了'.encode('utf-8') in response
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -2,7 +2,7 @@
import time
from flask import url_for
from .util import live_server_setup, wait_for_all_checks, delete_all_watches
from .util import live_server_setup, wait_for_all_checks
import json
import uuid
@@ -276,7 +276,8 @@ def test_access_denied(client, live_server, measure_memory_usage):
assert res.status_code == 200
# Cleanup everything
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
res = client.post(
url_for("settings.settings_page"),
@@ -384,7 +385,8 @@ def test_api_watch_PUT_update(client, live_server, measure_memory_usage):
assert b'Additional properties are not allowed' in res.data
# Cleanup everything
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_api_import(client, live_server, measure_memory_usage):
@@ -394,7 +396,7 @@ def test_api_import(client, live_server, measure_memory_usage):
res = client.post(
url_for("import") + "?tag=import-test",
data='https://website1.com\r\nhttps://website2.com',
headers={'x-api-key': api_key, 'content-type': 'text/plain'},
headers={'x-api-key': api_key},
follow_redirects=True
)

View File

@@ -4,7 +4,7 @@ from flask import url_for
from .util import live_server_setup
import json
def test_api_notifications_crud(client, live_server, measure_memory_usage):
def test_api_notifications_crud(client, live_server):
# live_server_setup(live_server) # Setup on conftest per function
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')

View File

@@ -1,199 +0,0 @@
#!/usr/bin/env python3
"""
OpenAPI validation tests for ChangeDetection.io API
This test file specifically verifies that OpenAPI validation is working correctly
by testing various scenarios that should trigger validation errors.
"""
import time
import json
from flask import url_for
from .util import live_server_setup, wait_for_all_checks
def test_openapi_validation_invalid_content_type_on_create_watch(client, live_server, measure_memory_usage):
"""Test that creating a watch with invalid content-type triggers OpenAPI validation error."""
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
# Try to create a watch with JSON data but without proper content-type header
res = client.post(
url_for("createwatch"),
data=json.dumps({"url": "https://example.com", "title": "Test Watch"}),
headers={'x-api-key': api_key}, # Missing 'content-type': 'application/json'
follow_redirects=True
)
# Should get 400 error due to OpenAPI validation failure
assert res.status_code == 400, f"Expected 400 but got {res.status_code}"
assert b"OpenAPI validation failed" in res.data, "Should contain OpenAPI validation error message"
def test_openapi_validation_missing_required_field_create_watch(client, live_server, measure_memory_usage):
"""Test that creating a watch without required URL field triggers OpenAPI validation error."""
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
# Try to create a watch without the required 'url' field
res = client.post(
url_for("createwatch"),
data=json.dumps({"title": "Test Watch Without URL"}), # Missing required 'url' field
headers={'x-api-key': api_key, 'content-type': 'application/json'},
follow_redirects=True
)
# Should get 400 error due to missing required field
assert res.status_code == 400, f"Expected 400 but got {res.status_code}"
assert b"OpenAPI validation failed" in res.data, "Should contain OpenAPI validation error message"
def test_openapi_validation_invalid_field_in_request_body(client, live_server, measure_memory_usage):
"""Test that including invalid fields triggers OpenAPI validation error."""
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
# First create a valid watch
res = client.post(
url_for("createwatch"),
data=json.dumps({"url": "https://example.com", "title": "Test Watch"}),
headers={'x-api-key': api_key, 'content-type': 'application/json'},
follow_redirects=True
)
assert res.status_code == 201, "Watch creation should succeed"
# Get the watch list to find the UUID
res = client.get(
url_for("createwatch"),
headers={'x-api-key': api_key}
)
assert res.status_code == 200
watch_uuid = list(res.json.keys())[0]
# Now try to update the watch with an invalid field
res = client.put(
url_for("watch", uuid=watch_uuid),
headers={'x-api-key': api_key, 'content-type': 'application/json'},
data=json.dumps({
"title": "Updated title",
"invalid_field_that_doesnt_exist": "this should cause validation error"
}),
)
# Should get 400 error due to invalid field (this will be caught by internal validation)
# Note: This tests the flow where OpenAPI validation passes but internal validation catches it
assert res.status_code == 400, f"Expected 400 but got {res.status_code}"
assert b"Additional properties are not allowed" in res.data, "Should contain validation error about additional properties"
def test_openapi_validation_import_wrong_content_type(client, live_server, measure_memory_usage):
"""Test that import endpoint with wrong content-type triggers OpenAPI validation error."""
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
# Try to import URLs with JSON content-type instead of text/plain
res = client.post(
url_for("import") + "?tag=test-import",
data='https://website1.com\nhttps://website2.com',
headers={'x-api-key': api_key, 'content-type': 'application/json'}, # Wrong content-type
follow_redirects=True
)
# Should get 400 error due to content-type mismatch
assert res.status_code == 400, f"Expected 400 but got {res.status_code}"
assert b"OpenAPI validation failed" in res.data, "Should contain OpenAPI validation error message"
def test_openapi_validation_import_correct_content_type_succeeds(client, live_server, measure_memory_usage):
"""Test that import endpoint with correct content-type succeeds (positive test)."""
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
# Import URLs with correct text/plain content-type
res = client.post(
url_for("import") + "?tag=test-import",
data='https://website1.com\nhttps://website2.com',
headers={'x-api-key': api_key, 'content-type': 'text/plain'}, # Correct content-type
follow_redirects=True
)
# Should succeed
assert res.status_code == 200, f"Expected 200 but got {res.status_code}"
assert len(res.json) == 2, "Should import 2 URLs"
def test_openapi_validation_get_requests_bypass_validation(client, live_server, measure_memory_usage):
"""Test that GET requests bypass OpenAPI validation entirely."""
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
# Disable API token requirement first
res = client.post(
url_for("settings.settings_page"),
data={
"requests-time_between_check-minutes": 180,
"application-fetch_backend": "html_requests",
"application-api_access_token_enabled": ""
},
follow_redirects=True
)
assert b"Settings updated." in res.data
# Make GET request to list watches - should succeed even without API key or content-type
res = client.get(url_for("createwatch")) # No headers needed for GET
assert res.status_code == 200, f"GET requests should succeed without OpenAPI validation, got {res.status_code}"
# Should return JSON with watch list (empty in this case)
assert isinstance(res.json, dict), "Should return JSON dictionary for watch list"
def test_openapi_validation_create_tag_missing_required_title(client, live_server, measure_memory_usage):
"""Test that creating a tag without required title triggers OpenAPI validation error."""
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
# Try to create a tag without the required 'title' field
res = client.post(
url_for("tag"),
data=json.dumps({"notification_urls": ["mailto:test@example.com"]}), # Missing required 'title' field
headers={'x-api-key': api_key, 'content-type': 'application/json'},
follow_redirects=True
)
# Should get 400 error due to missing required field
assert res.status_code == 400, f"Expected 400 but got {res.status_code}"
assert b"OpenAPI validation failed" in res.data, "Should contain OpenAPI validation error message"
def test_openapi_validation_watch_update_allows_partial_updates(client, live_server, measure_memory_usage):
"""Test that watch updates allow partial updates without requiring all fields (positive test)."""
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
# First create a valid watch
res = client.post(
url_for("createwatch"),
data=json.dumps({"url": "https://example.com", "title": "Test Watch"}),
headers={'x-api-key': api_key, 'content-type': 'application/json'},
follow_redirects=True
)
assert res.status_code == 201, "Watch creation should succeed"
# Get the watch list to find the UUID
res = client.get(
url_for("createwatch"),
headers={'x-api-key': api_key}
)
assert res.status_code == 200
watch_uuid = list(res.json.keys())[0]
# Update only the title (partial update) - should succeed
res = client.put(
url_for("watch", uuid=watch_uuid),
headers={'x-api-key': api_key, 'content-type': 'application/json'},
data=json.dumps({"title": "Updated Title Only"}), # Only updating title, not URL
)
# Should succeed because UpdateWatch schema allows partial updates
assert res.status_code == 200, f"Partial updates should succeed, got {res.status_code}"
# Verify the update worked
res = client.get(
url_for("watch", uuid=watch_uuid),
headers={'x-api-key': api_key}
)
assert res.status_code == 200
assert res.json.get('title') == 'Updated Title Only', "Title should be updated"
assert res.json.get('url') == 'https://example.com', "URL should remain unchanged"

View File

@@ -6,7 +6,7 @@ import time
from .util import live_server_setup, wait_for_all_checks
def test_api_search(client, live_server, measure_memory_usage):
def test_api_search(client, live_server):
# live_server_setup(live_server) # Setup on conftest per function
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')

View File

@@ -12,14 +12,18 @@ def test_basic_auth(client, live_server, measure_memory_usage):
# This page will echo back any auth info
test_url = url_for('test_basicauth_method', _external=True).replace("//","//myuser:mypass@")
time.sleep(1)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
time.sleep(1)
# Check form validation
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"include_filters": "", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
data={"include_filters": "", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data

View File

@@ -86,8 +86,12 @@ def test_check_ldjson_price_autodetect(client, live_server, measure_memory_usage
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
# Should get a notice that it's available
@@ -125,8 +129,12 @@ def test_check_ldjson_price_autodetect(client, live_server, measure_memory_usage
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'ldjson-price-track-offer' not in res.data
@@ -138,8 +146,12 @@ def test_check_ldjson_price_autodetect(client, live_server, measure_memory_usage
def _test_runner_check_bad_format_ignored(live_server, client, has_ldjson_price_data):
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
for k,v in client.application.config.get('DATASTORE').data['watching'].items():

View File

@@ -3,7 +3,7 @@
import time
from flask import url_for
from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, extract_rss_token_from_UI, \
extract_UUID_from_client, delete_all_watches
extract_UUID_from_client
sleep_time_for_fetch_thread = 3
@@ -38,9 +38,9 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
# Give the thread time to pick it up
wait_for_all_checks(client)
# It should report nothing found (no new 'has-unread-changes' class)
# It should report nothing found (no new 'unviewed' class)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
assert b'test-endpoint' in res.data
# Default no password set, this stuff should be always available.
@@ -74,9 +74,9 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
res = client.get(url_for("ui.ui_edit.watch_get_latest_html", uuid=uuid))
assert b'which has this one new line' in res.data
# Now something should be ready, indicated by having a 'has-unread-changes' class
# Now something should be ready, indicated by having a 'unviewed' class
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
# #75, and it should be in the RSS feed
rss_token = extract_rss_token_from_UI(client)
@@ -90,7 +90,7 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
assert expected_url.encode('utf-8') in res.data
#
# Following the 'diff' link, it should no longer display as 'has-unread-changes' even after we recheck it a few times
# Following the 'diff' link, it should no longer display as 'unviewed' even after we recheck it a few times
res = client.get(url_for("ui.ui_views.diff_history_page", uuid=uuid))
assert b'selected=""' in res.data, "Confirm diff history page loaded"
@@ -111,12 +111,12 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
# Give the thread time to pick it up
wait_for_all_checks(client)
# It should report nothing found (no new 'has-unread-changes' class)
# It should report nothing found (no new 'unviewed' class)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'class="has-unread-changes' not in res.data
assert b'unviewed' not in res.data
assert b'class="has-unviewed' not in res.data
assert b'head title' in res.data # Should be ON by default
assert b'test-endpoint' in res.data
@@ -140,8 +140,8 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'class="has-unread-changes' in res.data
assert b'unviewed' in res.data
assert b'class="has-unviewed' in res.data
assert b'head title' not in res.data # should now be off
@@ -151,8 +151,8 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
# hit the mark all viewed link
res = client.get(url_for("ui.mark_all_viewed"), follow_redirects=True)
assert b'class="has-unread-changes' not in res.data
assert b'has-unread-changes' not in res.data
assert b'class="has-unviewed' not in res.data
assert b'unviewed' not in res.data
# #2458 "clear history" should make the Watch object update its status correctly when the first snapshot lands again
client.get(url_for("ui.clear_watch_history", uuid=uuid))
@@ -163,179 +163,5 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
#
# Cleanup everything
delete_all_watches(client)
def test_non_text_mime_or_downloads(client, live_server, measure_memory_usage):
"""
https://github.com/dgtlmoon/changedetection.io/issues/3434
I noticed that a watched website can be monitored fine as long as the server sends content-type: text/plain; charset=utf-8,
but once the server sends content-type: application/octet-stream (which is usually done to force the browser to show the Download dialog),
changedetection somehow ignores all line breaks and treats the document file as if everything is on one line.
WHAT THIS DOES - makes the system rely on 'magic' to determine what is it
:param client:
:param live_server:
:param measure_memory_usage:
:return:
"""
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write("""some random text that should be split by line
and not parsed with html_to_text
this way we know that it correctly parsed as plain text
\r\n
ok\r\n
got it\r\n
""")
test_url = url_for('test_endpoint', content_type="application/octet-stream", _external=True)
# Add our URL to the import page
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
### check the front end
res = client.get(
url_for("ui.ui_views.preview_page", uuid="first"),
follow_redirects=True
)
assert b"some random text that should be split by line\n" in res.data
####
# Check the snapshot by API that it has linefeeds too
watch_uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
res = client.get(
url_for("watchhistory", uuid=watch_uuid),
headers={'x-api-key': api_key},
)
# Fetch a snapshot by timestamp, check the right one was found
res = client.get(
url_for("watchsinglehistory", uuid=watch_uuid, timestamp=list(res.json.keys())[-1]),
headers={'x-api-key': api_key},
)
assert b"some random text that should be split by line\n" in res.data
delete_all_watches(client)
def test_standard_text_plain(client, live_server, measure_memory_usage):
"""
https://github.com/dgtlmoon/changedetection.io/issues/3434
I noticed that a watched website can be monitored fine as long as the server sends content-type: text/plain; charset=utf-8,
but once the server sends content-type: application/octet-stream (which is usually done to force the browser to show the Download dialog),
changedetection somehow ignores all line breaks and treats the document file as if everything is on one line.
The real bug here can be that it will try to process plain-text as HTML, losing <etc>
:param client:
:param live_server:
:param measure_memory_usage:
:return:
"""
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write("""some random text that should be split by line
and not parsed with html_to_text
<title>Even this title should stay because we are just plain text</title>
this way we know that it correctly parsed as plain text
\r\n
ok\r\n
got it\r\n
""")
test_url = url_for('test_endpoint', content_type="text/plain", _external=True)
# Add our URL to the import page
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
### check the front end
res = client.get(
url_for("ui.ui_views.preview_page", uuid="first"),
follow_redirects=True
)
assert b"some random text that should be split by line\n" in res.data
####
# Check the snapshot by API that it has linefeeds too
watch_uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
res = client.get(
url_for("watchhistory", uuid=watch_uuid),
headers={'x-api-key': api_key},
)
# Fetch a snapshot by timestamp, check the right one was found
res = client.get(
url_for("watchsinglehistory", uuid=watch_uuid, timestamp=list(res.json.keys())[-1]),
headers={'x-api-key': api_key},
)
assert b"some random text that should be split by line\n" in res.data
assert b"<title>Even this title should stay because we are just plain text</title>" in res.data
delete_all_watches(client)
# Server says its plaintext, we should always treat it as plaintext
def test_plaintext_even_if_xml_content(client, live_server, measure_memory_usage):
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write("""<?xml version="1.0" encoding="utf-8"?>
<resources xmlns:tools="http://schemas.android.com/tools">
<!--Activity and fragment titles-->
<string name="feed_update_receiver_name">Abonnementen bijwerken</string>
</resources>
""")
test_url = url_for('test_endpoint', content_type="text/plain", _external=True)
# Add our URL to the import page
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
res = client.get(
url_for("ui.ui_views.preview_page", uuid="first"),
follow_redirects=True
)
assert b'&lt;string name=&#34;feed_update_receiver_name&#34;' in res.data
delete_all_watches(client)
# Server says its plaintext, we should always treat it as plaintext, and then if they have a filter, try to apply that
def test_plaintext_even_if_xml_content_and_can_apply_filters(client, live_server, measure_memory_usage):
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write("""<?xml version="1.0" encoding="utf-8"?>
<resources xmlns:tools="http://schemas.android.com/tools">
<!--Activity and fragment titles-->
<string name="feed_update_receiver_name">Abonnementen bijwerken</string>
<foobar>ok man</foobar>
</resources>
""")
test_url=url_for('test_endpoint', content_type="text/plain", _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url, extras={"include_filters": ['//string']})
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
res = client.get(
url_for("ui.ui_views.preview_page", uuid="first"),
follow_redirects=True
)
assert b'&lt;string name=&#34;feed_update_receiver_name&#34;' in res.data
assert b'&lt;foobar' not in res.data
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -58,7 +58,6 @@ def run_socketio_watch_update_test(client, live_server, password_mode=""):
has_watch_update = False
has_unviewed_update = False
got_general_stats_update = False
for i in range(10):
# Get received events
@@ -66,11 +65,15 @@ def run_socketio_watch_update_test(client, live_server, password_mode=""):
if received:
logger.info(f"Received {len(received)} events after {i+1} seconds")
# Check for watch_update events with unviewed=True
for event in received:
if event['name'] == 'watch_update':
has_watch_update = True
if event['name'] == 'general_stats_update':
got_general_stats_update = True
if event['args'][0]['watch'].get('unviewed', False):
has_unviewed_update = True
logger.info("Found unviewed update event!")
break
if has_unviewed_update:
break
@@ -89,7 +92,7 @@ def run_socketio_watch_update_test(client, live_server, password_mode=""):
assert has_watch_update, "No watch_update events received"
# Verify we received an unviewed event
assert got_general_stats_update, "Got general stats update event"
assert has_unviewed_update, "No watch_update event with unviewed=True received"
# Alternatively, check directly if the watch in the datastore is marked as unviewed
from changedetectionio.flask_app import app

View File

@@ -2,7 +2,7 @@
import time
from flask import url_for
from .util import live_server_setup, wait_for_all_checks, delete_all_watches
from .util import live_server_setup, wait_for_all_checks
from changedetectionio import html_tools
def set_original_ignore_response():
@@ -70,8 +70,12 @@ def test_check_block_changedetection_text_NOT_present(client, live_server, measu
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Give the thread time to pick it up
wait_for_all_checks(client)
@@ -82,8 +86,7 @@ def test_check_block_changedetection_text_NOT_present(client, live_server, measu
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"text_should_not_be_present": ignore_text,
"url": test_url,
'fetch_backend': "html_requests",
"time_between_check_use_default": "y"
'fetch_backend': "html_requests"
},
follow_redirects=True
)
@@ -103,9 +106,9 @@ def test_check_block_changedetection_text_NOT_present(client, live_server, measu
# Give the thread time to pick it up
wait_for_all_checks(client)
# It should report nothing found (no new 'has-unread-changes' class)
# It should report nothing found (no new 'unviewed' class)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
assert b'/test-endpoint' in res.data
# The page changed, BUT the text is still there, just the rest of it changes, we should not see a change
@@ -116,9 +119,9 @@ def test_check_block_changedetection_text_NOT_present(client, live_server, measu
# Give the thread time to pick it up
wait_for_all_checks(client)
# It should report nothing found (no new 'has-unread-changes' class)
# It should report nothing found (no new 'unviewed' class)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
assert b'/test-endpoint' in res.data
# 2548
@@ -127,7 +130,7 @@ def test_check_block_changedetection_text_NOT_present(client, live_server, measu
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
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
@@ -135,9 +138,10 @@ def test_check_block_changedetection_text_NOT_present(client, live_server, measu
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -14,8 +14,12 @@ def test_clone_functionality(client, live_server, measure_memory_usage):
test_url = url_for('test_endpoint', _external=True)
# Add our URL to the import page
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
# So that we can be sure the same history doesnt carry over

View File

@@ -3,7 +3,7 @@ import json
import time
from flask import url_for
from .util import live_server_setup, wait_for_all_checks, delete_all_watches
from .util import live_server_setup, wait_for_all_checks
from ..model import CONDITIONS_MATCH_LOGIC_DEFAULT
@@ -47,11 +47,11 @@ def set_number_out_of_range_response(number="150"):
f.write(test_return_data)
# def test_setup(client, live_server, measure_memory_usage):
# def test_setup(client, live_server):
"""Test that both text and number conditions work together with AND logic."""
# live_server_setup(live_server) # Setup on conftest per function
def test_conditions_with_text_and_number(client, live_server, measure_memory_usage):
def test_conditions_with_text_and_number(client, live_server):
"""Test that both text and number conditions work together with AND logic."""
set_original_response("50")
@@ -60,8 +60,12 @@ def test_conditions_with_text_and_number(client, live_server, measure_memory_usa
test_url = url_for('test_endpoint', _external=True)
# Add our URL to the import page
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
# Configure the watch with two conditions connected with AND:
@@ -101,7 +105,6 @@ def test_conditions_with_text_and_number(client, live_server, measure_memory_usa
"conditions-5-operator": "contains_regex",
"conditions-5-field": "page_filtered_text",
"conditions-5-value": "\d",
"time_between_check_use_default": "y",
},
follow_redirects=True
)
@@ -121,7 +124,7 @@ def test_conditions_with_text_and_number(client, live_server, measure_memory_usa
time.sleep(2)
# 75 is > 20 and < 100 and contains "5"
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
# Case 2: Change with one condition violated
@@ -137,20 +140,25 @@ def test_conditions_with_text_and_number(client, live_server, measure_memory_usa
# Should NOT be marked as having changes since not all conditions are met
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
# The 'validate' button next to each rule row
def test_condition_validate_rule_row(client, live_server, measure_memory_usage):
def test_condition_validate_rule_row(client, live_server):
set_original_response("50")
test_url = url_for('test_endpoint', _external=True)
# Add our URL to the import page
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
@@ -221,8 +229,12 @@ def test_wordcount_conditions_plugin(client, live_server, measure_memory_usage):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Give the thread time to pick it up
wait_for_all_checks(client)
@@ -276,8 +288,7 @@ def test_lev_conditions_plugin(client, live_server, measure_memory_usage):
"conditions_match_logic": CONDITIONS_MATCH_LOGIC_DEFAULT, # ALL = AND logic
"conditions-0-field": "levenshtein_ratio",
"conditions-0-operator": "<",
"conditions-0-value": "0.8", # needs to be more of a diff to trigger a change
"time_between_check_use_default": "y"
"conditions-0-value": "0.8" # needs to be more of a diff to trigger a change
},
follow_redirects=True
)
@@ -286,7 +297,7 @@ def test_lev_conditions_plugin(client, live_server, measure_memory_usage):
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
# Check the content saved initially, even tho a condition was set - this is the first snapshot so shouldnt be affected by conditions
res = client.get(
@@ -313,7 +324,7 @@ def test_lev_conditions_plugin(client, live_server, measure_memory_usage):
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data #because this will be like 0.90 not 0.8 threshold
assert b'unviewed' not in res.data #because this will be like 0.90 not 0.8 threshold
############### Now change it a MORE THAN 50%
test_return_data = """<html>
@@ -332,7 +343,7 @@ def test_lev_conditions_plugin(client, live_server, measure_memory_usage):
assert b'Queued 1 watch for rechecking.' in res.data
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
# cleanup for the next
client.get(
url_for("ui.form_delete", uuid="all"),

View File

@@ -81,8 +81,12 @@ def test_check_markup_include_filters_restriction(client, live_server, measure_m
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -91,7 +95,7 @@ def test_check_markup_include_filters_restriction(client, live_server, measure_m
# Add our URL to the import page
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"include_filters": include_filters, "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
data={"include_filters": include_filters, "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -112,10 +116,10 @@ def test_check_markup_include_filters_restriction(client, live_server, measure_m
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
# It should have 'has-unread-changes' still
# It should have 'unviewed' still
# Because it should be looking at only that 'sametext' id
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
# Tests the whole stack works with the CSS Filter
@@ -134,8 +138,12 @@ def test_check_multiple_filters(client, live_server, measure_memory_usage):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
# Goto the edit page, add our ignore text
@@ -146,8 +154,7 @@ def test_check_multiple_filters(client, live_server, measure_memory_usage):
"url": test_url,
"tags": "",
"headers": "",
'fetch_backend': "html_requests",
"time_between_check_use_default": "y"},
'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -185,8 +192,12 @@ def test_filter_is_empty_help_suggestion(client, live_server, measure_memory_usa
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
# Goto the edit page, add our ignore text
@@ -197,8 +208,7 @@ def test_filter_is_empty_help_suggestion(client, live_server, measure_memory_usa
"url": test_url,
"tags": "",
"headers": "",
'fetch_backend': "html_requests",
"time_between_check_use_default": "y"},
'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data

View File

@@ -5,7 +5,7 @@ import time
from flask import url_for
from ..html_tools import *
from .util import live_server_setup, wait_for_all_checks, delete_all_watches
from .util import live_server_setup, wait_for_all_checks
@@ -171,7 +171,6 @@ def test_element_removal_full(client, live_server, measure_memory_usage):
"tags": "",
"headers": "",
"fetch_backend": "html_requests",
"time_between_check_use_default": "y",
},
follow_redirects=True,
)
@@ -190,7 +189,7 @@ def test_element_removal_full(client, live_server, measure_memory_usage):
wait_for_all_checks(client)
# so that we set the state to 'has-unread-changes' after all the edits
# so that we set the state to 'unviewed' after all the edits
client.get(url_for("ui.ui_views.diff_history_page", uuid="first"))
# Make a change to header/footer/nav
@@ -209,32 +208,47 @@ def test_element_removal_full(client, live_server, measure_memory_usage):
# Re #2752
def test_element_removal_nth_offset_no_shift(client, live_server, measure_memory_usage):
set_response_with_multiple_index()
subtractive_selectors_data = [
### css style ###
"""body > table > tr:nth-child(1) > th:nth-child(2)
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)""",
### second type, xpath ###
"""//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]"""]
test_url = url_for("test_endpoint", _external=True)
for selector_list in subtractive_selectors_data:
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url, extras={"subtractive_selectors": selector_list.splitlines()})
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
# Add our URL to the import page
test_url = url_for("test_endpoint", _external=True)
res = client.post(
url_for("imports.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("ui.ui_edit.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(
@@ -242,7 +256,6 @@ body > table > tr:nth-child(3) > td:nth-child(3)""",
follow_redirects=True
)
# the filters above should have removed this but they never say to remove the "emil" column
assert b"Tobias" not in res.data
assert b"Linus" not in res.data
assert b"Person 2" not in res.data

View File

@@ -28,8 +28,11 @@ def test_check_encoding_detection(client, live_server, measure_memory_usage):
# Add our URL to the import page
test_url = url_for('test_endpoint', content_type="text/html", _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
# Give the thread time to pick it up
wait_for_all_checks(client)
@@ -56,8 +59,11 @@ def test_check_encoding_detection_missing_content_type_header(client, live_serve
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
wait_for_all_checks(client)

View File

@@ -3,7 +3,7 @@
import time
from flask import url_for
from .util import live_server_setup, wait_for_all_checks, delete_all_watches
from .util import live_server_setup, wait_for_all_checks
@@ -19,15 +19,19 @@ def _runner_test_http_errors(client, live_server, http_code, expected_text):
status_code=http_code,
_external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Give the thread time to pick it up
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
# no change
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
assert bytes(expected_text.encode('utf-8')) in res.data
@@ -43,7 +47,8 @@ def _runner_test_http_errors(client, live_server, http_code, expected_text):
#assert b'Error Screenshot' in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_http_error_handler(client, live_server, measure_memory_usage):
@@ -51,7 +56,8 @@ def test_http_error_handler(client, live_server, measure_memory_usage):
_runner_test_http_errors(client, live_server, 404, 'Page not found')
_runner_test_http_errors(client, live_server, 500, '(Internal server error) received')
_runner_test_http_errors(client, live_server, 400, 'Error - Request returned a HTTP error code 400')
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
# Just to be sure error text is properly handled
def test_DNS_errors(client, live_server, measure_memory_usage):
@@ -81,7 +87,8 @@ def test_DNS_errors(client, live_server, measure_memory_usage):
assert found_name_resolution_error
# Should always record that we tried
assert bytes("just now".encode('utf-8')) in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
# Re 1513
def test_low_level_errors_clear_correctly(client, live_server, measure_memory_usage):
@@ -120,8 +127,7 @@ def test_low_level_errors_clear_correctly(client, live_server, measure_memory_us
url_for("ui.ui_edit.edit_page", uuid="first"),
data={
"url": test_url,
"fetch_backend": "html_requests",
"time_between_check_use_default": "y"},
"fetch_backend": "html_requests"},
follow_redirects=True
)
@@ -138,4 +144,5 @@ def test_low_level_errors_clear_correctly(client, live_server, measure_memory_us
)
assert not found_name_resolution_error
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -2,7 +2,7 @@
import time
from flask import url_for
from .util import live_server_setup, wait_for_all_checks, delete_all_watches
from .util import live_server_setup, wait_for_all_checks
from ..html_tools import *
@@ -76,8 +76,12 @@ def test_check_filter_multiline(client, live_server, measure_memory_usage):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
@@ -91,8 +95,7 @@ def test_check_filter_multiline(client, live_server, measure_memory_usage):
"url": test_url,
"tags": "",
"headers": "",
'fetch_backend': "html_requests",
"time_between_check_use_default": "y"
'fetch_backend': "html_requests"
},
follow_redirects=True
)
@@ -127,8 +130,12 @@ def test_check_filter_and_regex_extract(client, live_server, measure_memory_usag
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Give the thread time to pick it up
wait_for_all_checks(client)
@@ -142,8 +149,7 @@ def test_check_filter_and_regex_extract(client, live_server, measure_memory_usag
"url": test_url,
"tags": "",
"headers": "",
'fetch_backend': "html_requests",
"time_between_check_use_default": "y"
'fetch_backend': "html_requests"
},
follow_redirects=True
)
@@ -166,10 +172,10 @@ def test_check_filter_and_regex_extract(client, live_server, measure_memory_usag
# Give the thread time to pick it up
wait_for_all_checks(client)
# It should have 'has-unread-changes' still
# It should have 'unviewed' still
# Because it should be looking at only that 'sametext' id
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
# Check HTML conversion detected and workd
res = client.get(
@@ -204,19 +210,23 @@ def test_regex_error_handling(client, live_server, measure_memory_usage):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
### test regex error handling
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"extract_text": '/something bad\d{3/XYZ',
"url": test_url,
"fetch_backend": "html_requests",
"time_between_check_use_default": "y"},
"fetch_backend": "html_requests"},
follow_redirects=True
)
assert b'is not a valid regular expression.' in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -94,8 +94,7 @@ def test_filter_doesnt_exist_then_exists_should_get_notification(client, live_se
"title": "my title",
"headers": "",
"include_filters": '.ticket-available',
"fetch_backend": "html_requests",
"time_between_check_use_default": "y"})
"fetch_backend": "html_requests"})
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),

View File

@@ -42,8 +42,13 @@ def run_filter_test(client, live_server, content_filter):
if os.path.isfile("test-datastore/notification.txt"):
os.unlink("test-datastore/notification.txt")
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
@@ -67,7 +72,6 @@ def run_filter_test(client, live_server, content_filter):
"notification_format": "Text",
"fetch_backend": "html_requests",
"filter_failure_notification_send": 'y',
"time_between_check_use_default": "y",
"headers": "",
"tags": "my tag",
"title": "my title 123",

View File

@@ -2,7 +2,7 @@
import time
from flask import url_for
from .util import live_server_setup, wait_for_all_checks, extract_rss_token_from_UI, get_UUID_for_tag_name, extract_UUID_from_client, delete_all_watches
from .util import live_server_setup, wait_for_all_checks, extract_rss_token_from_UI, get_UUID_for_tag_name, extract_UUID_from_client
import os
@@ -127,7 +127,8 @@ def test_setup_group_tag(client, live_server, measure_memory_usage):
assert b"should-be-excluded" not in res.data
assert res.status_code == 200
assert b"first-imported=1" in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_tag_import_singular(client, live_server, measure_memory_usage):
@@ -146,7 +147,8 @@ def test_tag_import_singular(client, live_server, measure_memory_usage):
)
# Should be only 1 tag because they both had the same
assert res.data.count(b'test-tag') == 1
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_tag_add_in_ui(client, live_server, measure_memory_usage):
@@ -162,7 +164,8 @@ def test_tag_add_in_ui(client, live_server, measure_memory_usage):
res = client.get(url_for("tags.delete_all"), follow_redirects=True)
assert b'All tags deleted' in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_group_tag_notification(client, live_server, measure_memory_usage):
@@ -229,7 +232,8 @@ def test_group_tag_notification(client, live_server, measure_memory_usage):
#@todo Test that multiple notifications fired
#@todo Test that each of multiple notifications with different settings
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_limit_tag_ui(client, live_server, measure_memory_usage):
@@ -260,12 +264,15 @@ def test_limit_tag_ui(client, live_server, measure_memory_usage):
client.get(url_for('ui.mark_all_viewed', tag=tag_uuid), follow_redirects=True)
wait_for_all_checks(client)
with open('/tmp/fuck.html', 'wb') as f:
f.write(res.data)
# Should be only 1 unviewed
res = client.get(url_for("watchlist.index"))
assert res.data.count(b' unviewed ') == 1
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
res = client.get(url_for("tags.delete_all"), follow_redirects=True)
assert b'All tags deleted' in res.data
@@ -292,7 +299,8 @@ def test_clone_tag_on_import(client, live_server, measure_memory_usage):
# 2 times plus the top link to tag
assert res.data.count(b'test-tag') == 3
assert res.data.count(b'another-tag') == 3
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_clone_tag_on_quickwatchform_add(client, live_server, measure_memory_usage):
@@ -319,7 +327,8 @@ def test_clone_tag_on_quickwatchform_add(client, live_server, measure_memory_usa
# 2 times plus the top link to tag
assert res.data.count(b'test-tag') == 3
assert res.data.count(b'another-tag') == 3
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
res = client.get(url_for("tags.delete_all"), follow_redirects=True)
assert b'All tags deleted' in res.data
@@ -382,8 +391,12 @@ def test_order_of_filters_tag_filter_and_watch_filter(client, live_server, measu
f.write(d)
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
filters = [
@@ -411,8 +424,7 @@ def test_order_of_filters_tag_filter_and_watch_filter(client, live_server, measu
"url": test_url,
"tags": "test-tag-keep-order",
"headers": "",
'fetch_backend': "html_requests",
"time_between_check_use_default": "y"},
'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -469,4 +481,5 @@ the {test} appeared before. {test in res.data[:n]=}
"""
n += t_index + len(test)
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -3,8 +3,9 @@
import time
import os
import json
import logging
from flask import url_for
from .util import wait_for_all_checks, delete_all_watches
from .util import live_server_setup, wait_for_all_checks
from urllib.parse import urlparse, parse_qs
def test_consistent_history(client, live_server, measure_memory_usage):
@@ -80,15 +81,19 @@ def test_consistent_history(client, live_server, measure_memory_usage):
assert '"default"' not in f.read(), "'default' probably shouldnt be here, it came from when the 'default' Watch vars were accidently being saved"
def test_check_text_history_view(client, live_server, measure_memory_usage):
def test_check_text_history_view(client, live_server):
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write("<html>test-one</html>")
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Give the thread time to pick it up
wait_for_all_checks(client)
@@ -117,4 +122,5 @@ def test_check_text_history_view(client, live_server, measure_memory_usage):
assert b'test-two' in res.data
assert b'test-one' not in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -27,8 +27,12 @@ def test_ignore(client, live_server, measure_memory_usage):
# live_server_setup(live_server) # Setup on conftest per function
set_original_ignore_response()
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Give the thread time to pick it up
wait_for_all_checks(client)
@@ -54,35 +58,3 @@ def test_ignore(client, live_server, measure_memory_usage):
# Should be in base.html
assert b'csrftoken' in res.data
def test_strip_ignore_lines(client, live_server, measure_memory_usage):
# live_server_setup(live_server) # Setup on conftest per function
set_original_ignore_response()
# Goto the settings page, add our ignore text
res = client.post(
url_for("settings.settings_page"),
data={
"requests-time_between_check-minutes": 180,
"application-ignore_whitespace": "y",
"application-strip_ignored_lines": "y",
"application-global_ignore_text": "Which is across multiple",
'application-fetch_backend': "html_requests"
},
follow_redirects=True
)
assert b"Settings updated." in res.data
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
wait_for_all_checks(client)
uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
# It should not be in the preview anymore
res = client.get(url_for("ui.ui_views.preview_page", uuid=uuid))
assert b'<div class="ignored">' not in res.data
assert b'Which is across multiple' not in res.data

View File

@@ -2,7 +2,7 @@
import time
from flask import url_for
from .util import live_server_setup, wait_for_all_checks, delete_all_watches
from .util import live_server_setup, wait_for_all_checks
from changedetectionio import html_tools
@@ -97,8 +97,12 @@ def test_check_ignore_text_functionality(client, live_server, measure_memory_usa
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Give the thread time to pick it up
wait_for_all_checks(client)
@@ -107,7 +111,7 @@ def test_check_ignore_text_functionality(client, live_server, measure_memory_usa
# Add our URL to the import page
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"ignore_text": ignore_text, "url": test_url, 'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
data={"ignore_text": ignore_text, "url": test_url, 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -124,9 +128,9 @@ def test_check_ignore_text_functionality(client, live_server, measure_memory_usa
# Give the thread time to pick it up
wait_for_all_checks(client)
# It should report nothing found (no new 'has-unread-changes' class)
# It should report nothing found (no new 'unviewed' class)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
assert b'/test-endpoint' in res.data
# Make a change
@@ -137,9 +141,9 @@ def test_check_ignore_text_functionality(client, live_server, measure_memory_usa
# Give the thread time to pick it up
wait_for_all_checks(client)
# It should report nothing found (no new 'has-unread-changes' class)
# It should report nothing found (no new 'unviewed' class)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
assert b'/test-endpoint' in res.data
@@ -150,7 +154,7 @@ def test_check_ignore_text_functionality(client, live_server, measure_memory_usa
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
res = client.get(url_for("ui.ui_views.preview_page", uuid="first"))
@@ -159,7 +163,8 @@ def test_check_ignore_text_functionality(client, live_server, measure_memory_usa
# it is only ignored, it is not removed (it will be highlighted too)
assert b'new ignore stuff' in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
# When adding some ignore text, it should not trigger a change, even if something else on that line changes
def _run_test_global_ignore(client, as_source=False, extra_ignore=""):
@@ -187,8 +192,12 @@ def _run_test_global_ignore(client, as_source=False, extra_ignore=""):
# Switch to source mode so we can test that too!
test_url = "source:"+test_url
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Give the thread time to pick it up
wait_for_all_checks(client)
@@ -196,7 +205,7 @@ def _run_test_global_ignore(client, as_source=False, extra_ignore=""):
#Adding some ignore text should not trigger a change
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"ignore_text": "something irrelevent but just to check", "url": test_url, 'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
data={"ignore_text": "something irrelevent but just to check", "url": test_url, 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -213,9 +222,9 @@ def _run_test_global_ignore(client, as_source=False, extra_ignore=""):
# Trigger a check
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
# It should report nothing found (no new 'has-unread-changes' class), adding random ignore text should not cause a change
# It should report nothing found (no new 'unviewed' class), adding random ignore text should not cause a change
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
assert b'/test-endpoint' in res.data
#####
@@ -229,10 +238,10 @@ def _run_test_global_ignore(client, as_source=False, extra_ignore=""):
# Give the thread time to pick it up
wait_for_all_checks(client)
# It should report nothing found (no new 'has-unread-changes' class)
# It should report nothing found (no new 'unviewed' class)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
assert b'/test-endpoint' in res.data
# Just to be sure.. set a regular modified change that will trigger it
@@ -240,14 +249,15 @@ def _run_test_global_ignore(client, as_source=False, extra_ignore=""):
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_check_global_ignore_text_functionality(client, live_server, measure_memory_usage):
def test_check_global_ignore_text_functionality(client, live_server):
_run_test_global_ignore(client, as_source=False)
def test_check_global_ignore_text_functionality_as_source(client, live_server, measure_memory_usage):
def test_check_global_ignore_text_functionality_as_source(client, live_server):
_run_test_global_ignore(client, as_source=True, extra_ignore='/\?v=\d/')

View File

@@ -3,7 +3,9 @@
import time
from flask import url_for
from .util import live_server_setup, wait_for_all_checks, delete_all_watches
from .util import live_server_setup, wait_for_all_checks
def set_original_ignore_response():
@@ -109,11 +111,13 @@ def test_render_anchor_tag_content_true(client, live_server, measure_memory_usag
assert '(/modified_link)' in res.data.decode()
# since the link has changed, and we chose to render anchor tag content,
# we should detect a change (new 'has-unread-changes' class)
# we should detect a change (new 'unviewed' class)
res = client.get(url_for("watchlist.index"))
assert b"unviewed" in res.data
assert b"/test-endpoint" in res.data
# Cleanup everything
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"),
follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -60,8 +60,12 @@ def test_normal_page_check_works_with_ignore_status_code(client, live_server, me
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
@@ -73,9 +77,9 @@ def test_normal_page_check_works_with_ignore_status_code(client, live_server, me
# Give the thread time to pick it up
wait_for_all_checks(client)
# It should report nothing found (no new 'has-unread-changes' class)
# It should report nothing found (no new 'unviewed' class)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
assert b'/test-endpoint' in res.data
@@ -90,8 +94,12 @@ def test_403_page_check_works_with_ignore_status_code(client, live_server, measu
# Add our URL to the import page
test_url = url_for('test_endpoint', status_code=403, _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
@@ -100,7 +108,7 @@ def test_403_page_check_works_with_ignore_status_code(client, live_server, measu
# Add our URL to the import page
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"ignore_status_codes": "y", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
data={"ignore_status_codes": "y", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -116,8 +124,8 @@ def test_403_page_check_works_with_ignore_status_code(client, live_server, measu
# Give the thread time to pick it up
wait_for_all_checks(client)
# It should have 'has-unread-changes' still
# It should have 'unviewed' still
# Because it should be looking at only that 'sametext' id
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data

View File

@@ -70,8 +70,12 @@ def test_check_ignore_whitespace(client, live_server, measure_memory_usage):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
time.sleep(sleep_time_for_fetch_thread)
# Trigger a check
@@ -85,7 +89,7 @@ def test_check_ignore_whitespace(client, live_server, measure_memory_usage):
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
# It should report nothing found (no new 'has-unread-changes' class)
# It should report nothing found (no new 'unviewed' class)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
assert b'/test-endpoint' in res.data

View File

@@ -5,7 +5,7 @@ import time
from flask import url_for
from .util import live_server_setup, wait_for_all_checks, delete_all_watches
from .util import live_server_setup, wait_for_all_checks
# def test_setup(client, live_server, measure_memory_usage):
@@ -28,7 +28,7 @@ https://example.com tag1, other tag"""
assert b"3 Imported" in res.data
assert b"tag1" in res.data
assert b"other tag" in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
# Clear flask alerts
res = client.get( url_for("watchlist.index"))
@@ -53,7 +53,7 @@ def xtest_import_skip_url(client, live_server, measure_memory_usage):
assert b"1 Imported" in res.data
assert b"ht000000broken" in res.data
assert b"1 Skipped" in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
# Clear flask alerts
res = client.get( url_for("watchlist.index"))
@@ -119,7 +119,7 @@ def test_import_distillio(client, live_server, measure_memory_usage):
assert b"nice stuff" in res.data
assert b"nerd-news" in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
# Clear flask alerts
res = client.get(url_for("watchlist.index"))
@@ -169,7 +169,8 @@ def test_import_custom_xlsx(client, live_server, measure_memory_usage):
assert filters[0] == '/html[1]/body[1]/div[4]/div[1]/div[1]/div[1]||//*[@id=\'content\']/div[3]/div[1]/div[1]||//*[@id=\'content\']/div[1]'
assert watch.get('time_between_check') == {'weeks': 0, 'days': 1, 'hours': 6, 'minutes': 24, 'seconds': 0}
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_import_watchete_xlsx(client, live_server, measure_memory_usage):
"""Test can upload a excel spreadsheet and the watches are created correctly"""
@@ -213,4 +214,5 @@ def test_import_watchete_xlsx(client, live_server, measure_memory_usage):
if watch.get('title') == 'system default website':
assert watch.get('fetch_backend') == 'system' # uses default if blank
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -26,7 +26,7 @@ def test_jinja2_in_url_query(client, live_server, measure_memory_usage):
assert b"Watch added" in res.data
wait_for_all_checks(client)
# It should report nothing found (no new 'has-unread-changes' class)
# It should report nothing found (no new 'unviewed' class)
res = client.get(
url_for("ui.ui_views.preview_page", uuid="first"),
follow_redirects=True
@@ -51,7 +51,7 @@ def test_jinja2_security_url_query(client, live_server, measure_memory_usage):
assert b"Watch added" in res.data
wait_for_all_checks(client)
# It should report nothing found (no new 'has-unread-changes' class)
# It should report nothing found (no new 'unviewed' class)
res = client.get(url_for("watchlist.index"))
assert b'is invalid and cannot be used' in res.data
# Some of the spewed output from the subclasses

View File

@@ -3,7 +3,7 @@
import time
from flask import url_for, escape
from . util import live_server_setup, wait_for_all_checks, delete_all_watches
from . util import live_server_setup, wait_for_all_checks
import pytest
jq_support = True
@@ -205,10 +205,16 @@ def test_check_json_without_filter(client, live_server, measure_memory_usage):
# and be sure it doesn't get chewed up by instriptis
set_json_response_with_html()
# Give the endpoint time to spin up
time.sleep(1)
# Add our URL to the import page
test_url = url_for('test_endpoint', content_type="application/json", _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
# Give the thread time to pick it up
wait_for_all_checks(client)
@@ -222,16 +228,23 @@ def test_check_json_without_filter(client, live_server, measure_memory_usage):
assert b'&#34;html&#34;: &#34;&lt;b&gt;&#34;' in res.data
assert res.data.count(b'{') >= 2
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def check_json_filter(json_filter, client, live_server):
set_original_response()
# Give the endpoint time to spin up
time.sleep(1)
# Add our URL to the import page
test_url = url_for('test_endpoint', content_type="application/json", _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Give the thread time to pick it up
wait_for_all_checks(client)
@@ -244,8 +257,7 @@ def check_json_filter(json_filter, client, live_server):
"url": test_url,
"tags": "",
"headers": "",
"fetch_backend": "html_requests",
"time_between_check_use_default": "y"
"fetch_backend": "html_requests"
},
follow_redirects=True
)
@@ -267,9 +279,9 @@ def check_json_filter(json_filter, client, live_server):
# Give the thread time to pick it up
wait_for_all_checks(client)
# It should have 'has-unread-changes' still
# It should have 'unviewed' still
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
# Should not see this, because its not in the JSONPath we entered
res = client.get(url_for("ui.ui_views.diff_history_page", uuid="first"))
@@ -278,7 +290,8 @@ def check_json_filter(json_filter, client, live_server):
# And #462 - check we see the proper utf-8 string there
assert "Örnsköldsvik".encode('utf-8') in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_check_jsonpath_filter(client, live_server, measure_memory_usage):
check_json_filter('json:boss.name', client, live_server)
@@ -299,8 +312,12 @@ def check_json_filter_bool_val(json_filter, client, live_server):
test_url = url_for('test_endpoint', content_type="application/json", _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
# Goto the edit page, add our ignore text
@@ -311,8 +328,7 @@ def check_json_filter_bool_val(json_filter, client, live_server):
"url": test_url,
"tags": "",
"headers": "",
"fetch_backend": "html_requests",
"time_between_check_use_default": "y"
"fetch_backend": "html_requests"
},
follow_redirects=True
)
@@ -332,7 +348,8 @@ def check_json_filter_bool_val(json_filter, client, live_server):
# But the change should be there, tho its hard to test the change was detected because it will show old and new versions
assert b'false' in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_check_jsonpath_filter_bool_val(client, live_server, measure_memory_usage):
check_json_filter_bool_val("json:$['available']", client, live_server)
@@ -358,8 +375,12 @@ def check_json_ext_filter(json_filter, client, live_server):
# Add our URL to the import page
test_url = url_for('test_endpoint', content_type="application/json", _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Give the thread time to pick it up
wait_for_all_checks(client)
@@ -372,8 +393,7 @@ def check_json_ext_filter(json_filter, client, live_server):
"url": test_url,
"tags": "",
"headers": "",
"fetch_backend": "html_requests",
"time_between_check_use_default": "y"
"fetch_backend": "html_requests"
},
follow_redirects=True
)
@@ -395,14 +415,14 @@ def check_json_ext_filter(json_filter, client, live_server):
# Give the thread time to pick it up
wait_for_all_checks(client)
# It should have 'has-unread-changes'
# It should have 'unviewed'
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
res = client.get(url_for("ui.ui_views.preview_page", uuid="first"))
# We should never see 'ForSale' because we are selecting on 'Sold' in the rule,
# But we should know it triggered ('has-unread-changes' assert above)
# But we should know it triggered ('unviewed' assert above)
assert b'ForSale' not in res.data
assert b'Sold' in res.data
@@ -413,7 +433,8 @@ def check_json_ext_filter(json_filter, client, live_server):
assert b'ForSale' in res.data
assert b'Sold' in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_ignore_json_order(client, live_server, measure_memory_usage):
# A change in order shouldn't trigger a notification
@@ -424,8 +445,12 @@ def test_ignore_json_order(client, live_server, measure_memory_usage):
# Add our URL to the import page
test_url = url_for('test_endpoint', content_type="application/json", _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
@@ -437,7 +462,7 @@ def test_ignore_json_order(client, live_server, measure_memory_usage):
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
# Just to be sure it still works
with open("test-datastore/endpoint-content.txt", "w") as f:
@@ -448,9 +473,10 @@ def test_ignore_json_order(client, live_server, measure_memory_usage):
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_correct_header_detect(client, live_server, measure_memory_usage):
# Like in https://github.com/dgtlmoon/changedetection.io/pull/1593
@@ -461,8 +487,12 @@ def test_correct_header_detect(client, live_server, measure_memory_usage):
# Add our URL to the import page
# Check weird casing is cleaned up and detected also
test_url = url_for('test_endpoint', content_type="aPPlication/JSon", uppercase_headers=True, _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
@@ -477,7 +507,8 @@ def test_correct_header_detect(client, live_server, measure_memory_usage):
assert b'&#34;hello&#34;: 123,' in res.data
assert b'&#34;world&#34;: 123' in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_check_jsonpath_ext_filter(client, live_server, measure_memory_usage):
check_json_ext_filter('json:$[?(@.status==Sold)]', client, live_server)

View File

@@ -1,7 +1,7 @@
#!/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, delete_all_watches
from changedetectionio.tests.util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
def set_response():
@@ -38,7 +38,6 @@ def test_content_filter_live_preview(client, live_server, measure_memory_usage):
"ignore_text": "something to ignore",
"trigger_text": "something to trigger",
"url": test_url,
"time_between_check_use_default": "y",
},
follow_redirects=True
)
@@ -75,4 +74,5 @@ def test_content_filter_live_preview(client, live_server, measure_memory_usage):
assert reply.get('ignore_line_numbers') == [2] # Ignored - "socks" on line 2
assert reply.get('trigger_line_numbers') == [1] # Triggers "Awesome" in line 1
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -1,7 +1,7 @@
#!/usr/bin/env python3
from flask import url_for
from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, delete_all_watches
from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
import time
@@ -40,9 +40,9 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
wait_for_all_checks(client)
# It should report nothing found (no new 'has-unread-changes' class)
# It should report nothing found (no new 'unviewed' class)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
#####################
@@ -62,9 +62,9 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
# Give the thread time to pick it up
wait_for_all_checks(client)
# It should report nothing found (no new 'has-unread-changes' class)
# It should report nothing found (no new 'unviewed' class)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
watch = live_server.app.config['DATASTORE'].data['watching'][uuid]
@@ -92,9 +92,9 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
# Give the thread time to pick it up
wait_for_all_checks(client)
# It should report nothing found (no new 'has-unread-changes' class)
# It should report nothing found (no new 'unviewed' class)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
client.get(url_for("ui.mark_all_viewed"), follow_redirects=True)
time.sleep(0.2)
@@ -108,10 +108,11 @@ def test_check_basic_change_detection_functionality(client, live_server, measure
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data # A change should have registered because empty_pages_are_a_change is ON
assert b'unviewed' in res.data # A change should have registered because empty_pages_are_a_change is ON
assert b'fetch-error' not in res.data
#
# Cleanup everything
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -108,8 +108,7 @@ def test_check_notification(client, live_server, measure_memory_usage):
"tags": "my tag, my second tag",
"title": "my title",
"headers": "",
"fetch_backend": "html_requests",
"time_between_check_use_default": "y"})
"fetch_backend": "html_requests"})
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
@@ -226,8 +225,7 @@ def test_check_notification(client, live_server, measure_memory_usage):
"notification_title": '',
"notification_body": '',
"notification_format": default_notification_format,
"fetch_backend": "html_requests",
"time_between_check_use_default": "y"},
"fetch_backend": "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data

View File

@@ -36,8 +36,7 @@ def test_check_notification_error_handling(client, live_server, measure_memory_u
"title": "",
"headers": "",
"time_between_check-minutes": "180",
"fetch_backend": "html_requests",
"time_between_check_use_default": "y"},
"fetch_backend": "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data

View File

@@ -24,8 +24,12 @@ def test_obfuscations(client, live_server, measure_memory_usage):
time.sleep(1)
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Give the thread time to pick it up
time.sleep(3)

View File

@@ -8,30 +8,30 @@ from .util import set_original_response, set_modified_response, live_server_setu
# `subtractive_selectors` should still work in `source:` type requests
def test_fetch_pdf(client, live_server, measure_memory_usage):
import shutil
import os
shutil.copy("tests/test.pdf", "test-datastore/endpoint-test.pdf")
first_version_size = os.path.getsize("test-datastore/endpoint-test.pdf")
# live_server_setup(live_server) # Setup on conftest per function
test_url = url_for('test_pdf_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
# Add our URL to the import page
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
watch = live_server.app.config['DATASTORE'].data['watching'][uuid]
dates = list(watch.history.keys())
snapshot_contents = watch.get_history_snapshot(dates[0])
res = client.get(
url_for("ui.ui_views.preview_page", uuid="first"),
follow_redirects=True
)
# PDF header should not be there (it was converted to text)
assert 'PDF' not in snapshot_contents
# Was converted away from HTML
assert 'pdftohtml' not in snapshot_contents.lower() # Generator tag shouldnt be there
assert f'Original file size - {first_version_size}' in snapshot_contents
assert 'html' not in snapshot_contents.lower() # is converted from html
assert 'body' not in snapshot_contents.lower() # is converted from html
# And our text content was there
assert 'hello world' in snapshot_contents
assert b'PDF' not in res.data[:10]
assert b'hello world' in res.data
# So we know if the file changes in other ways
import hashlib
@@ -39,7 +39,8 @@ def test_fetch_pdf(client, live_server, measure_memory_usage):
# We should have one
assert len(original_md5) >0
# And it's going to be in the document
assert f'Document checksum - {original_md5}' in snapshot_contents
assert b'Document checksum - '+bytes(str(original_md5).encode('utf-8')) in res.data
shutil.copy("tests/test2.pdf", "test-datastore/endpoint-test.pdf")
changed_md5 = hashlib.md5(open("test-datastore/endpoint-test.pdf", 'rb').read()).hexdigest().upper()
@@ -48,9 +49,9 @@ def test_fetch_pdf(client, live_server, measure_memory_usage):
wait_for_all_checks(client)
# Now something should be ready, indicated by having a 'has-unread-changes' class
# Now something should be ready, indicated by having a 'unviewed' class
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
# The original checksum should be not be here anymore (cdio adds it to the bottom of the text)
@@ -62,6 +63,7 @@ def test_fetch_pdf(client, live_server, measure_memory_usage):
assert original_md5.encode('utf-8') not in res.data
assert changed_md5.encode('utf-8') in res.data
res = client.get(
url_for("ui.ui_views.diff_history_page", uuid="first"),
follow_redirects=True
@@ -69,16 +71,6 @@ def test_fetch_pdf(client, live_server, measure_memory_usage):
assert original_md5.encode('utf-8') in res.data
assert changed_md5.encode('utf-8') in res.data
assert b'here is a change' in res.data
dates = list(watch.history.keys())
# new snapshot was also OK, no HTML
snapshot_contents = watch.get_history_snapshot(dates[1])
assert 'html' not in snapshot_contents.lower()
assert f'Original file size - {os.path.getsize("test-datastore/endpoint-test.pdf")}' in snapshot_contents
assert f'here is a change' in snapshot_contents
assert os.path.getsize("test-datastore/endpoint-test.pdf") != first_version_size # And the disk change worked

View File

@@ -13,8 +13,13 @@ def test_fetch_pdf(client, live_server, measure_memory_usage):
# live_server_setup(live_server) # Setup on conftest per function
test_url = url_for('test_pdf_endpoint', _external=True)
# Add our URL to the import page
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
@@ -42,9 +47,9 @@ def test_fetch_pdf(client, live_server, measure_memory_usage):
wait_for_all_checks(client)
# Now something should be ready, indicated by having a 'has-unread-changes' class
# Now something should be ready, indicated by having a 'unviewed' class
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
# The original checksum should be not be here anymore (cdio adds it to the bottom of the text)

View File

@@ -2,7 +2,7 @@ import json
import os
import time
from flask import url_for
from . util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, extract_UUID_from_client, delete_all_watches
from . util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, extract_UUID_from_client
@@ -17,13 +17,21 @@ def test_headers_in_request(client, live_server, measure_memory_usage):
test_url = test_url.replace('localhost', 'changedet')
# Add the test URL twice, we will check
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
cookie_header = '_ga=GA1.2.1022228332; cookie-preferences=analytics:accepted;'
@@ -36,8 +44,7 @@ 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,
"time_between_check_use_default": "y"},
"headers": "jinja2:{{ 1+1 }}\nxxx:ooo\ncool:yeah\r\ncookie:"+cookie_header},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -74,7 +81,8 @@ def test_headers_in_request(client, live_server, measure_memory_usage):
for k, watch in client.application.config.get('DATASTORE').data.get('watching').items():
assert 'custom' in watch.get('remote_server_reply') # added in util.py
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_body_in_request(client, live_server, measure_memory_usage):
@@ -84,8 +92,12 @@ def test_body_in_request(client, live_server, measure_memory_usage):
# Because its no longer calling back to localhost but from the browser container, set in test-only.yml
test_url = test_url.replace('localhost', 'cdio')
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
@@ -97,8 +109,7 @@ def test_body_in_request(client, live_server, measure_memory_usage):
"tags": "",
"method": "POST",
"fetch_backend": "html_requests",
"body": "something something",
"time_between_check_use_default": "y"},
"body": "something something"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -115,8 +126,7 @@ def test_body_in_request(client, live_server, measure_memory_usage):
"tags": "",
"method": "POST",
"fetch_backend": "html_requests",
"body": body_value,
"time_between_check_use_default": "y"},
"body": body_value},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -137,8 +147,12 @@ def test_body_in_request(client, live_server, measure_memory_usage):
####### data sanity checks
# Add the test URL twice, we will check
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
watches_with_body = 0
with open('test-datastore/url-watches.json') as f:
@@ -158,12 +172,12 @@ def test_body_in_request(client, live_server, measure_memory_usage):
"tags": "",
"method": "GET",
"fetch_backend": "html_requests",
"body": "invalid",
"time_between_check_use_default": "y"},
"body": "invalid"},
follow_redirects=True
)
assert b"Body must be empty when Request Method is set to GET" in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_method_in_request(client, live_server, measure_memory_usage):
# Add our URL to the import page
@@ -173,12 +187,20 @@ def test_method_in_request(client, live_server, measure_memory_usage):
test_url = test_url.replace('localhost', 'cdio')
# Add the test URL twice, we will check
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
@@ -189,8 +211,7 @@ def test_method_in_request(client, live_server, measure_memory_usage):
"url": test_url,
"tags": "",
"fetch_backend": "html_requests",
"method": "invalid",
"time_between_check_use_default": "y"},
"method": "invalid"},
follow_redirects=True
)
assert b"Not a valid choice" in res.data
@@ -202,8 +223,7 @@ def test_method_in_request(client, live_server, measure_memory_usage):
"url": test_url,
"tags": "",
"fetch_backend": "html_requests",
"method": "PATCH",
"time_between_check_use_default": "y"},
"method": "PATCH"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -232,7 +252,8 @@ def test_method_in_request(client, live_server, measure_memory_usage):
# Should be only one with method set to PATCH
assert watches_with_method == 1
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
# Re #2408 - user-agent override test, also should handle case-insensitive header deduplication
def test_ua_global_override(client, live_server, measure_memory_usage):
@@ -250,8 +271,12 @@ def test_ua_global_override(client, live_server, measure_memory_usage):
)
assert b'Settings updated' in res.data
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
res = client.get(
@@ -272,8 +297,7 @@ def test_ua_global_override(client, live_server, measure_memory_usage):
"tags": "testtag",
"fetch_backend": 'html_requests',
# Important - also test case-insensitive
"headers": "User-AGent: agent-from-watch",
"time_between_check_use_default": "y"},
"headers": "User-AGent: agent-from-watch"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -284,7 +308,8 @@ def test_ua_global_override(client, live_server, measure_memory_usage):
)
assert b"agent-from-watch" in res.data
assert b"html-requests-user-agent" not in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_headers_textfile_in_request(client, live_server, measure_memory_usage):
@@ -324,8 +349,12 @@ def test_headers_textfile_in_request(client, live_server, measure_memory_usage):
assert b"requests-default_ua-html_requests" in res.data
# Add the test URL twice, we will check
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
@@ -336,8 +365,7 @@ def test_headers_textfile_in_request(client, live_server, measure_memory_usage):
"url": test_url,
"tags": "testtag",
"fetch_backend": 'html_webdriver' if os.getenv('PLAYWRIGHT_DRIVER_URL') else 'html_requests',
"headers": "xxx:ooo\ncool:yeah\r\n",
"time_between_check_use_default": "y"},
"headers": "xxx:ooo\ncool:yeah\r\n"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -393,22 +421,26 @@ def test_headers_textfile_in_request(client, live_server, measure_memory_usage):
assert "User-Agent:".encode('utf-8') + requests_ua.encode('utf-8') in res.data
# unlink headers.txt on start/stop
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_headers_validation(client, live_server, measure_memory_usage):
def test_headers_validation(client, live_server):
test_url = url_for('test_headers', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={
"url": test_url,
"fetch_backend": 'html_requests',
"headers": "User-AGent agent-from-watch\r\nsadfsadfsadfsdaf\r\n:foobar",
"time_between_check_use_default": "y"},
"headers": "User-AGent agent-from-watch\r\nsadfsadfsadfsdaf\r\n:foobar"},
follow_redirects=True
)

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, delete_all_watches
from .util import live_server_setup, wait_for_all_checks, wait_for_notification_endpoint_output, extract_UUID_from_client
from ..notification import default_notification_format
instock_props = [
@@ -44,11 +44,11 @@ def set_original_response(props_markup='', price="121.95"):
# def test_setup(client, live_server, measure_memory_usage):
# def test_setup(client, live_server):
# live_server_setup(live_server) # Setup on conftest per function
def test_restock_itemprop_basic(client, live_server, measure_memory_usage):
def test_restock_itemprop_basic(client, live_server):
@@ -69,7 +69,8 @@ def test_restock_itemprop_basic(client, live_server, measure_memory_usage):
assert b'has-restock-info' in res.data
assert b' in-stock' in res.data
assert b' not-in-stock' not in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
for p in out_of_stock_props:
@@ -84,9 +85,10 @@ def test_restock_itemprop_basic(client, live_server, measure_memory_usage):
assert b'has-restock-info not-in-stock' in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_itemprop_price_change(client, live_server, measure_memory_usage):
def test_itemprop_price_change(client, live_server):
# Out of the box 'Follow price changes' should be ON
@@ -110,7 +112,7 @@ def test_itemprop_price_change(client, live_server, measure_memory_usage):
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'180.45' in res.data
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
client.get(url_for("ui.mark_all_viewed"), follow_redirects=True)
time.sleep(0.2)
@@ -119,7 +121,7 @@ def test_itemprop_price_change(client, live_server, measure_memory_usage):
set_original_response(props_markup=instock_props[0], price='120.45')
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"restock_settings-follow_price_changes": "", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
data={"restock_settings-follow_price_changes": "", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -127,14 +129,16 @@ def test_itemprop_price_change(client, live_server, measure_memory_usage):
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'120.45' in res.data
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def _run_test_minmax_limit(client, extra_watch_edit_form):
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
test_url = url_for('test_endpoint', _external=True)
@@ -151,8 +155,7 @@ def _run_test_minmax_limit(client, extra_watch_edit_form):
"url": test_url,
"headers": "",
"time_between_check-hours": 5,
'fetch_backend': "html_requests",
"time_between_check_use_default": "y"
'fetch_backend': "html_requests"
}
data.update(extra_watch_edit_form)
res = client.post(
@@ -174,7 +177,7 @@ def _run_test_minmax_limit(client, extra_watch_edit_form):
assert b'more than one price detected' not in res.data
# BUT the new price should show, even tho its within limits
assert b'1,000.45' or b'1000.45' in res.data #depending on locale
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
# price changed to something LESS than min (900), SHOULD be a change
set_original_response(props_markup=instock_props[0], price='890.45')
@@ -184,7 +187,7 @@ def _run_test_minmax_limit(client, extra_watch_edit_form):
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'890.45' in res.data
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
client.get(url_for("ui.mark_all_viewed"))
@@ -196,7 +199,7 @@ def _run_test_minmax_limit(client, extra_watch_edit_form):
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'820.45' in res.data
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
client.get(url_for("ui.mark_all_viewed"))
# price changed to something MORE than max (1100.10), SHOULD be a change
@@ -206,12 +209,13 @@ def _run_test_minmax_limit(client, extra_watch_edit_form):
res = client.get(url_for("watchlist.index"))
# Depending on the LOCALE it may be either of these (generally for US/default/etc)
assert b'1,890.45' in res.data or b'1890.45' in res.data
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_restock_itemprop_minmax(client, live_server, measure_memory_usage):
def test_restock_itemprop_minmax(client, live_server):
extras = {
"restock_settings-follow_price_changes": "y",
@@ -220,7 +224,7 @@ def test_restock_itemprop_minmax(client, live_server, measure_memory_usage):
}
_run_test_minmax_limit(client, extra_watch_edit_form=extras)
def test_restock_itemprop_with_tag(client, live_server, measure_memory_usage):
def test_restock_itemprop_with_tag(client, live_server):
res = client.post(
@@ -249,10 +253,11 @@ def test_restock_itemprop_with_tag(client, live_server, measure_memory_usage):
def test_itemprop_percent_threshold(client, live_server, measure_memory_usage):
def test_itemprop_percent_threshold(client, live_server):
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
test_url = url_for('test_endpoint', _external=True)
@@ -273,8 +278,7 @@ def test_itemprop_percent_threshold(client, live_server, measure_memory_usage):
"url": test_url,
"tags": "",
"headers": "",
'fetch_backend': "html_requests",
"time_between_check_use_default": "y"
'fetch_backend': "html_requests"
},
follow_redirects=True
)
@@ -288,7 +292,7 @@ def test_itemprop_percent_threshold(client, live_server, measure_memory_usage):
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'960.45' in res.data
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
# Bigger INCREASE change than the threshold should trigger
set_original_response(props_markup=instock_props[0], price='1960.45')
@@ -296,7 +300,7 @@ def test_itemprop_percent_threshold(client, live_server, measure_memory_usage):
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'1,960.45' or b'1960.45' in res.data #depending on locale
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
# Small decrease should NOT trigger
@@ -306,16 +310,17 @@ def test_itemprop_percent_threshold(client, live_server, measure_memory_usage):
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'1,950.45' or b'1950.45' in res.data #depending on locale
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_change_with_notification_values(client, live_server, measure_memory_usage):
def test_change_with_notification_values(client, live_server):
if os.path.isfile("test-datastore/notification.txt"):
@@ -383,10 +388,11 @@ def test_change_with_notification_values(client, live_server, measure_memory_usa
assert os.path.isfile("test-datastore/notification.txt"), "Notification received"
def test_data_sanity(client, live_server, measure_memory_usage):
def test_data_sanity(client, live_server):
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
test_url = url_for('test_endpoint', _external=True)
test_url2 = url_for('test_endpoint2', _external=True)
@@ -413,7 +419,8 @@ def test_data_sanity(client, live_server, measure_memory_usage):
assert str(res.data.decode()).count("950.95") == 1, "Price should only show once (for the watch added, no other watches yet)"
## different test, check the edit page works on an empty request result
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
client.post(
url_for("ui.ui_views.form_quick_watch_add"),
@@ -426,10 +433,11 @@ def test_data_sanity(client, live_server, measure_memory_usage):
url_for("ui.ui_edit.edit_page", uuid="first"))
assert test_url2.encode('utf-8') in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
# All examples should give a prive of 666.66
def test_special_prop_examples(client, live_server, measure_memory_usage):
def test_special_prop_examples(client, live_server):
import glob

View File

@@ -3,7 +3,7 @@
import time
from flask import url_for
from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, extract_rss_token_from_UI, \
extract_UUID_from_client, delete_all_watches
extract_UUID_from_client
def set_original_cdata_xml():
@@ -111,11 +111,16 @@ def test_basic_cdata_rss_markup(client, live_server, measure_memory_usage):
set_original_cdata_xml()
test_url = url_for('test_endpoint', content_type="application/atom+xml; charset=UTF-8", _external=True)
test_url = url_for('test_endpoint', content_type="application/xml", _external=True)
# Add our URL to the import page
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
@@ -127,14 +132,14 @@ def test_basic_cdata_rss_markup(client, live_server, measure_memory_usage):
assert b'<![' not in res.data
assert b'Hackers can access your computer' in res.data
assert b'The days of Terminator' in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
def test_rss_xpath_filtering(client, live_server, measure_memory_usage):
set_original_cdata_xml()
test_url = url_for('test_endpoint', content_type="application/atom+xml; charset=UTF-8", _external=True)
test_url = url_for('test_endpoint', content_type="application/xml", _external=True)
res = client.post(
url_for("ui.ui_views.form_quick_watch_add"),
@@ -153,7 +158,6 @@ def test_rss_xpath_filtering(client, live_server, measure_memory_usage):
"proxy": "no-proxy",
"tags": "",
"url": test_url,
"time_between_check_use_default": "y",
},
follow_redirects=True
)
@@ -175,10 +179,10 @@ def test_rss_xpath_filtering(client, live_server, measure_memory_usage):
assert b'The days of Terminator' not in res.data # Should NOT be selected by the xpath
assert b'Some other description' not in res.data # Should NOT be selected by the xpath
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
def test_rss_bad_chars_breaking(client, live_server, measure_memory_usage):
def test_rss_bad_chars_breaking(client, live_server):
"""This should absolutely trigger the RSS builder to go into worst state mode
- source: prefix means no html conversion (which kinda filters out the bad stuff)

View File

@@ -1,15 +1,12 @@
#!/usr/bin/env python3
import time
from copy import copy
from datetime import datetime, timezone
from zoneinfo import ZoneInfo
from flask import url_for
from .util import live_server_setup, wait_for_all_checks, extract_UUID_from_client, delete_all_watches
from ..forms import REQUIRE_ATLEAST_ONE_TIME_PART_MESSAGE_DEFAULT, REQUIRE_ATLEAST_ONE_TIME_PART_WHEN_NOT_GLOBAL_DEFAULT
from .util import live_server_setup, wait_for_all_checks, extract_UUID_from_client
# def test_setup(client, live_server, measure_memory_usage):
# def test_setup(client, live_server):
# live_server_setup(live_server) # Setup on conftest per function
def test_check_basic_scheduler_functionality(client, live_server, measure_memory_usage):
@@ -34,18 +31,22 @@ def test_check_basic_scheduler_functionality(client, live_server, measure_memory
res = client.get(url_for("settings.settings_page"))
assert b'Pacific/Kiritimati' in res.data
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
# Setup all the days of the weeks using XXX as the placeholder for monday/tuesday/etc
last_check = copy(live_server.app.config['DATASTORE'].data['watching'][uuid]['last_checked'])
tpl = {
"time_schedule_limit-XXX-start_time": "00:00",
"time_schedule_limit-XXX-duration-hours": 24,
"time_schedule_limit-XXX-duration-minutes": 0,
"time_between_check-seconds": 1,
"time_schedule_limit-XXX-enabled": '', # All days are turned off
"time_schedule_limit-enabled": 'y', # Scheduler is enabled, all days however are off.
}
@@ -57,13 +58,13 @@ def test_check_basic_scheduler_functionality(client, live_server, measure_memory
new_key = key.replace("XXX", day)
scheduler_data[new_key] = value
last_check = live_server.app.config['DATASTORE'].data['watching'][uuid]['last_checked']
data = {
"url": test_url,
"fetch_backend": "html_requests",
"time_between_check_use_default": "" # no
"fetch_backend": "html_requests"
}
data.update(scheduler_data)
time.sleep(1)
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data=data,
@@ -76,7 +77,6 @@ def test_check_basic_scheduler_functionality(client, live_server, measure_memory
# "Edit" should not trigger a check because it's not enabled in the schedule.
time.sleep(2)
# "time_schedule_limit-XXX-enabled": '', # All days are turned off, therefor, nothing should happen here..
assert live_server.app.config['DATASTORE'].data['watching'][uuid]['last_checked'] == last_check
# Enabling today in Kiritimati should work flawless
@@ -87,7 +87,8 @@ def test_check_basic_scheduler_functionality(client, live_server, measure_memory
assert live_server.app.config['DATASTORE'].data['watching'][uuid]['last_checked'] != last_check
# Cleanup everything
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_check_basic_global_scheduler_functionality(client, live_server, measure_memory_usage):
@@ -95,8 +96,13 @@ def test_check_basic_global_scheduler_functionality(client, live_server, measure
days = ['monday', 'tuesday', 'wednesday', 'thursday', 'friday', 'saturday', 'sunday']
test_url = url_for('test_random_content_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
@@ -169,41 +175,5 @@ def test_check_basic_global_scheduler_functionality(client, live_server, measure
assert live_server.app.config['DATASTORE'].data['watching'][uuid]['last_checked'] != last_check
# Cleanup everything
delete_all_watches(client)
def test_validation_time_interval_field(client, live_server, measure_memory_usage):
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"trigger_text": 'The golden line',
"url": test_url,
'fetch_backend': "html_requests",
'filter_text_removed': 'y',
"time_between_check_use_default": ""
},
follow_redirects=True
)
assert REQUIRE_ATLEAST_ONE_TIME_PART_WHEN_NOT_GLOBAL_DEFAULT.encode('utf-8') in res.data
# Now set atleast something
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"trigger_text": 'The golden line',
"url": test_url,
'fetch_backend': "html_requests",
"time_between_check-minutes": 1,
"time_between_check_use_default": ""
},
follow_redirects=True
)
assert REQUIRE_ATLEAST_ONE_TIME_PART_WHEN_NOT_GLOBAL_DEFAULT.encode('utf-8') not in res.data
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -27,7 +27,7 @@ def test_basic_search(client, live_server, measure_memory_usage):
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"title": "xxx-title", "url": urls[0], "tags": "", "headers": "", 'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
data={"title": "xxx-title", "url": urls[0], "tags": "", "headers": "", 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -62,7 +62,7 @@ def test_search_in_tag_limit(client, live_server, measure_memory_usage):
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"title": "xxx-title", "url": urls[0].split(' ')[0], "tags": urls[0].split(' ')[1], "headers": "",
'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data

View File

@@ -1,7 +1,7 @@
import os
from flask import url_for
from .util import live_server_setup, wait_for_all_checks, delete_all_watches
from .util import live_server_setup, wait_for_all_checks
from .. import strtobool
@@ -41,8 +41,7 @@ def test_bad_access(client, live_server, measure_memory_usage):
"tags": "",
"method": "GET",
"fetch_backend": "html_requests",
"body": "",
"time_between_check_use_default": "y"},
"body": ""},
follow_redirects=True
)
@@ -100,7 +99,8 @@ def _runner_test_various_file_slash(client, file_uri):
# This will give some error from requests or if it went to chrome, will give some other error :-)
assert any(s in res.data for s in substrings)
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_file_slash_access(client, live_server, measure_memory_usage):
@@ -150,8 +150,7 @@ def test_xss_watch_last_error(client, live_server, measure_memory_usage):
data={
"include_filters": '<a href="https://foobar"></a><script>alert(123);</script>',
"url": url_for('test_endpoint', _external=True),
'fetch_backend': "html_requests",
"time_between_check_use_default": "y"
'fetch_backend': "html_requests"
},
follow_redirects=True
)

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, delete_all_watches
from .util import set_original_response, set_modified_response, live_server_setup
import re
sleep_time_for_fetch_thread = 3
@@ -17,14 +17,19 @@ def test_share_watch(client, live_server, measure_memory_usage):
include_filters = ".nice-filter"
# Add our URL to the import page
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Goto the edit page, add our ignore text
# Add our URL to the import page
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"include_filters": include_filters, "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
data={"include_filters": include_filters, "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -49,7 +54,8 @@ def test_share_watch(client, live_server, measure_memory_usage):
# Now delete what we have, we will try to re-import it
# Cleanup everything
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
# Add our URL to the import page
res = client.post(

View File

@@ -13,8 +13,13 @@ def test_check_basic_change_detection_functionality_source(client, live_server,
set_original_response()
test_url = 'source:'+url_for('test_endpoint', _external=True)
# Add our URL to the import page
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
time.sleep(sleep_time_for_fetch_thread)
@@ -38,9 +43,9 @@ def test_check_basic_change_detection_functionality_source(client, live_server,
wait_for_all_checks(client)
# Now something should be ready, indicated by having a 'has-unread-changes' class
# Now something should be ready, indicated by having a 'unviewed' class
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
res = client.get(
url_for("ui.ui_views.diff_history_page", uuid="first"),
@@ -57,8 +62,13 @@ def test_check_ignore_elements(client, live_server, measure_memory_usage):
time.sleep(1)
test_url = 'source:'+url_for('test_endpoint', _external=True)
# Add our URL to the import page
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
@@ -67,7 +77,7 @@ def test_check_ignore_elements(client, live_server, measure_memory_usage):
client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"include_filters": 'span,p', "url": test_url, "tags": "", "subtractive_selectors": ".foobar-detection", 'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
data={"include_filters": 'span,p', "url": test_url, "tags": "", "subtractive_selectors": ".foobar-detection", 'fetch_backend': "html_requests"},
follow_redirects=True
)

View File

@@ -65,8 +65,12 @@ def test_trigger_functionality(client, live_server, measure_memory_usage):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Trigger a check
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
@@ -77,8 +81,7 @@ def test_trigger_functionality(client, live_server, measure_memory_usage):
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"trigger_text": trigger_text,
"url": test_url,
"fetch_backend": "html_requests",
"time_between_check_use_default": "y"},
"fetch_backend": "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -92,7 +95,7 @@ def test_trigger_functionality(client, live_server, measure_memory_usage):
# so that we set the state to 'has-unread-changes' after all the edits
# so that we set the state to 'unviewed' after all the edits
client.get(url_for("ui.ui_views.diff_history_page", uuid="first"))
# Trigger a check
@@ -100,9 +103,9 @@ def test_trigger_functionality(client, live_server, measure_memory_usage):
wait_for_all_checks(client)
# It should report nothing found (no new 'has-unread-changes' class)
# It should report nothing found (no new 'unviewed' class)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
assert b'/test-endpoint' in res.data
# Make a change
@@ -112,9 +115,9 @@ def test_trigger_functionality(client, live_server, measure_memory_usage):
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
# It should report nothing found (no new 'has-unread-changes' class)
# It should report nothing found (no new 'unviewed' class)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
# Now set the content which contains the trigger text
set_modified_with_trigger_text_response()
@@ -122,7 +125,7 @@ def test_trigger_functionality(client, live_server, measure_memory_usage):
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
# https://github.com/dgtlmoon/changedetection.io/issues/616
# Apparently the actual snapshot that contains the trigger never shows

View File

@@ -2,7 +2,7 @@
import time
from flask import url_for
from .util import live_server_setup, wait_for_all_checks, delete_all_watches
from .util import live_server_setup, wait_for_all_checks
def set_original_ignore_response():
@@ -30,27 +30,30 @@ def test_trigger_regex_functionality(client, live_server, measure_memory_usage):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Give the thread time to pick it up
wait_for_all_checks(client)
# It should report nothing found (just a new one shouldnt have anything)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
### test regex
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"trigger_text": '/something \d{3}/',
"url": test_url,
"fetch_backend": "html_requests",
"time_between_check_use_default": "y"},
"fetch_backend": "html_requests"},
follow_redirects=True
)
wait_for_all_checks(client)
# so that we set the state to 'has-unread-changes' after all the edits
# so that we set the state to 'unviewed' after all the edits
client.get(url_for("ui.ui_views.diff_history_page", uuid="first"))
with open("test-datastore/endpoint-content.txt", "w") as f:
@@ -61,7 +64,7 @@ def test_trigger_regex_functionality(client, live_server, measure_memory_usage):
# It should report nothing found (nothing should match the regex)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write("regex test123<br>\nsomething 123")
@@ -69,7 +72,8 @@ def test_trigger_regex_functionality(client, live_server, measure_memory_usage):
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
# Cleanup everything
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -2,7 +2,7 @@
import time
from flask import url_for
from . util import live_server_setup, delete_all_watches
from . util import live_server_setup
def set_original_ignore_response():
@@ -34,8 +34,12 @@ def test_trigger_regex_functionality_with_filter(client, live_server, measure_me
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# it needs time to save the original version
time.sleep(sleep_time_for_fetch_thread)
@@ -46,8 +50,7 @@ def test_trigger_regex_functionality_with_filter(client, live_server, measure_me
data={"trigger_text": "/cool.stuff/",
"url": test_url,
"include_filters": '#in-here',
"fetch_backend": "html_requests",
"time_between_check_use_default": "y"},
"fetch_backend": "html_requests"},
follow_redirects=True
)
@@ -65,7 +68,7 @@ def test_trigger_regex_functionality_with_filter(client, live_server, measure_me
# It should report nothing found (nothing should match the regex and filter)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
# now this should trigger something
with open("test-datastore/endpoint-content.txt", "w") as f:
@@ -74,7 +77,8 @@ def test_trigger_regex_functionality_with_filter(client, live_server, measure_me
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
time.sleep(sleep_time_for_fetch_thread)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
# Cleanup everything
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -1,103 +1,13 @@
#!/usr/bin/env python3
from flask import url_for
from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks, delete_all_watches
from ..forms import REQUIRE_ATLEAST_ONE_TIME_PART_WHEN_NOT_GLOBAL_DEFAULT, REQUIRE_ATLEAST_ONE_TIME_PART_MESSAGE_DEFAULT
from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
def test_recheck_time_field_validation_global_settings(client, live_server, measure_memory_usage):
"""
Tests that the global settings time field has atleast one value for week/day/hours/minute/seconds etc entered
class globalSettingsRequestForm(Form):
time_between_check = RequiredFormField(TimeBetweenCheckForm)
"""
res = client.post(
url_for("settings.settings_page"),
data={
"requests-time_between_check-weeks": '',
"requests-time_between_check-days": '',
"requests-time_between_check-hours": '',
"requests-time_between_check-minutes": '',
"requests-time_between_check-seconds": '',
},
follow_redirects=True
)
assert REQUIRE_ATLEAST_ONE_TIME_PART_MESSAGE_DEFAULT.encode('utf-8') in res.data
def test_recheck_time_field_validation_single_watch(client, live_server, measure_memory_usage):
"""
Tests that the global settings time field has atleast one value for week/day/hours/minute/seconds etc entered
class globalSettingsRequestForm(Form):
time_between_check = RequiredFormField(TimeBetweenCheckForm)
"""
test_url = url_for('test_endpoint', _external=True)
# Add our URL to the import page
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={
"url": test_url,
'fetch_backend': "html_requests",
"time_between_check_use_default": "", # OFF
"time_between_check-weeks": '',
"time_between_check-days": '',
"time_between_check-hours": '',
"time_between_check-minutes": '',
"time_between_check-seconds": '',
},
follow_redirects=True
)
assert REQUIRE_ATLEAST_ONE_TIME_PART_WHEN_NOT_GLOBAL_DEFAULT.encode('utf-8') in res.data
# Now set some time
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={
"url": test_url,
'fetch_backend': "html_requests",
"time_between_check_use_default": "", # OFF
"time_between_check-weeks": '',
"time_between_check-days": '',
"time_between_check-hours": '',
"time_between_check-minutes": '5',
"time_between_check-seconds": '',
},
follow_redirects=True
)
assert b"Updated watch." in res.data
assert REQUIRE_ATLEAST_ONE_TIME_PART_WHEN_NOT_GLOBAL_DEFAULT.encode('utf-8') not in res.data
# Now set to use defaults
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={
"url": test_url,
'fetch_backend': "html_requests",
"time_between_check_use_default": "y", # ON YES
"time_between_check-weeks": '',
"time_between_check-days": '',
"time_between_check-hours": '',
"time_between_check-minutes": '',
"time_between_check-seconds": '',
},
follow_redirects=True
)
assert b"Updated watch." in res.data
assert REQUIRE_ATLEAST_ONE_TIME_PART_WHEN_NOT_GLOBAL_DEFAULT.encode('utf-8') not in res.data
def test_checkbox_open_diff_in_new_tab(client, live_server, measure_memory_usage):
def test_checkbox_open_diff_in_new_tab(client, live_server):
set_original_response()
# live_server_setup(live_server) # Setup on conftest per function
# Add our URL to the import page
res = client.post(
url_for("imports.import_page"),
@@ -166,120 +76,5 @@ def test_checkbox_open_diff_in_new_tab(client, live_server, measure_memory_usage
assert 'target=' not in target_line
# Cleanup everything
delete_all_watches(client)
def test_page_title_listing_behaviour(client, live_server, measure_memory_usage):
set_original_response(extra_title="custom html")
# either the manually entered title/description or the page link should be visible
res = client.post(
url_for("settings.settings_page"),
data={"application-ui-use_page_title_in_list": "",
"requests-time_between_check-minutes": 180,
'application-fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Settings updated." in res.data
# Add our URL to the import page
res = client.post(
url_for("imports.import_page"),
data={"urls": url_for('test_endpoint', _external=True)},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
# We see the URL only, no title/description was manually entered
res = client.get(url_for("watchlist.index"))
assert url_for('test_endpoint', _external=True).encode('utf-8') in res.data
# Now 'my title' should override
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={
"url": url_for('test_endpoint', _external=True),
"title": "my title",
"fetch_backend": "html_requests",
"time_between_check_use_default": "y"},
follow_redirects=True
)
assert b"Updated watch." in res.data
res = client.get(url_for("watchlist.index"))
assert b"my title" in res.data
# Now we enable page <title> and unset the override title/description
res = client.post(
url_for("settings.settings_page"),
data={"application-ui-use_page_title_in_list": "y",
"requests-time_between_check-minutes": 180,
'application-fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Settings updated." in res.data
# Page title description override should take precedence
res = client.get(url_for("watchlist.index"))
assert b"my title" in res.data
# Remove page title description override and it should fall back to title
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={
"url": url_for('test_endpoint', _external=True),
"title": "",
"fetch_backend": "html_requests",
"time_between_check_use_default": "y"},
follow_redirects=True
)
assert b"Updated watch." in res.data
# No page title description, and 'use_page_title_in_list' is on, it should show the <title>
res = client.get(url_for("watchlist.index"))
assert b"head titlecustom html" in res.data
def test_ui_viewed_unread_flag(client, live_server, measure_memory_usage):
import time
set_original_response(extra_title="custom html")
# Add our URL to the import page
res = client.post(
url_for("imports.import_page"),
data={"urls": url_for('test_endpoint', _external=True)+"\r\n"+url_for('test_endpoint', _external=True)},
follow_redirects=True
)
assert b"2 Imported" in res.data
wait_for_all_checks(client)
set_modified_response()
res = client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
assert b'Queued 2 watches for rechecking.' in res.data
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'<span id="unread-tab-counter">2</span>' in res.data
assert res.data.count(b'data-watch-uuid') == 2
# one should now be viewed, but two in total still
client.get(url_for("ui.ui_views.diff_history_page", uuid="first"))
res = client.get(url_for("watchlist.index"))
assert b'<span id="unread-tab-counter">1</span>' in res.data
assert res.data.count(b'data-watch-uuid') == 2
# check ?unread=1 works
res = client.get(url_for("watchlist.index")+"?unread=1")
assert res.data.count(b'data-watch-uuid') == 1
assert b'<span id="unread-tab-counter">1</span>' in res.data
# Mark all viewed test again
client.get(url_for("ui.mark_all_viewed"), follow_redirects=True)
time.sleep(0.2)
res = client.get(url_for("watchlist.index"))
assert b'<span id="unread-tab-counter">0</span>' in res.data
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -2,7 +2,7 @@
import time
from flask import url_for
from .util import live_server_setup, wait_for_all_checks, delete_all_watches
from .util import live_server_setup, wait_for_all_checks
def set_original_ignore_response():
@@ -79,8 +79,12 @@ def test_unique_lines_functionality(client, live_server, measure_memory_usage):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
# Add our URL to the import page
@@ -88,12 +92,11 @@ def test_unique_lines_functionality(client, live_server, measure_memory_usage):
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"check_unique_lines": "y",
"url": test_url,
"fetch_backend": "html_requests",
"time_between_check_use_default": "y"},
"fetch_backend": "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
# Make a change
set_modified_swapped_lines()
@@ -104,17 +107,18 @@ def test_unique_lines_functionality(client, live_server, measure_memory_usage):
# Give the thread time to pick it up
wait_for_all_checks(client)
# It should report nothing found (no new 'has-unread-changes' class)
# It should report nothing found (no new 'unviewed' class)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
assert b'unviewed' not in res.data
# Now set the content which contains the new text and re-ordered existing text
set_modified_with_trigger_text_response()
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' in res.data
delete_all_watches(client)
assert b'unviewed' in res.data
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_sort_lines_functionality(client, live_server, measure_memory_usage):
@@ -123,8 +127,12 @@ def test_sort_lines_functionality(client, live_server, measure_memory_usage):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
# Add our URL to the import page
@@ -132,8 +140,7 @@ def test_sort_lines_functionality(client, live_server, measure_memory_usage):
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"sort_text_alphabetically": "n",
"url": test_url,
"fetch_backend": "html_requests",
"time_between_check_use_default": "y"},
"fetch_backend": "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -148,7 +155,7 @@ def test_sort_lines_functionality(client, live_server, measure_memory_usage):
res = client.get(url_for("watchlist.index"))
# Should be a change registered
assert b'has-unread-changes' in res.data
assert b'unviewed' in res.data
res = client.get(
url_for("ui.ui_views.preview_page", uuid="first"),
@@ -159,7 +166,8 @@ def test_sort_lines_functionality(client, live_server, measure_memory_usage):
assert res.data.find(b'A uppercase') < res.data.find(b'Z last')
assert res.data.find(b'Some initial text') < res.data.find(b'Which is across multiple lines')
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_extra_filters(client, live_server, measure_memory_usage):
@@ -169,8 +177,12 @@ def test_extra_filters(client, live_server, measure_memory_usage):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
# Add our URL to the import page
@@ -180,8 +192,7 @@ def test_extra_filters(client, live_server, measure_memory_usage):
"trim_text_whitespace": "y",
"sort_text_alphabetically": "", # leave this OFF for testing
"url": test_url,
"fetch_backend": "html_requests",
"time_between_check_use_default": "y"},
"fetch_backend": "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -202,4 +213,5 @@ def test_extra_filters(client, live_server, measure_memory_usage):
# still should remain unsorted ('A - sortable line') stays at the end
assert res.data.find(b'A - sortable line') > res.data.find(b'Which is across multiple lines')
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data

View File

@@ -10,8 +10,12 @@ def test_check_watch_field_storage(client, live_server, measure_memory_usage):
test_url = "http://somerandomsitewewatch.com"
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
res = client.post(
@@ -24,8 +28,7 @@ def test_check_watch_field_storage(client, live_server, measure_memory_usage):
"url": test_url,
"tags": "woohoo",
"headers": "curl:foo",
'fetch_backend': "html_requests",
"time_between_check_use_default": "y"
'fetch_backend': "html_requests"
},
follow_redirects=True
)

View File

@@ -1,42 +1,12 @@
# -*- coding: utf-8 -*-
import time
from flask import url_for
from .util import wait_for_all_checks, delete_all_watches
from ..processors.magic import RSS_XML_CONTENT_TYPES
from .util import live_server_setup, wait_for_all_checks
from ..html_tools import *
def set_rss_atom_feed_response(header=''):
test_return_data = f"""{header}<!-- Generated on Wed, 08 Oct 2025 08:42:33 -0700, really really honestly -->
<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
<channel>
<atom:link href="https://store.waterpowered.com/news/collection//" rel="self" type="application/rss+xml"/>
<title>RSS Feed</title>
<link>
<![CDATA[ https://store.waterpowered.com/news/collection// ]]>
</link>
<description>
<![CDATA[ Events and Announcements for ]]>
</description>
<language>en-us</language>
<generator>water News RSS</generator>
<item>
<title> 🍁 Lets go discount</title>
<description><p class="bb_paragraph">ok heres the description</p></description>
<link>
<![CDATA[ https://store.waterpowered.com/news/app/1643320/view/511845698831908921 ]]>
</link>
<pubDate>Wed, 08 Oct 2025 15:28:55 +0000</pubDate>
<guid isPermaLink="true">https://store.waterpowered.com/news/app/1643320/view/511845698831908921</guid>
<enclosure url="https://clan.fastly.waterstatic.com/images/40721482/42822e5f00b2becf520ace9500981bb56f3a89f2.jpg" length="0" type="image/jpeg"/>
</item>
</channel>
</rss>"""
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write(test_return_data)
return None
@@ -113,19 +83,24 @@ def test_check_xpath_filter_utf8(client, live_server, measure_memory_usage):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True, content_type="application/rss+xml;charset=UTF-8")
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.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("ui.ui_edit.edit_page", uuid="first"),
data={"include_filters": filter, "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
data={"include_filters": filter, "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'Unicode strings with encoding declaration are not supported.' not in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
# Handle utf-8 charset replies https://github.com/dgtlmoon/changedetection.io/pull/613
@@ -162,12 +137,16 @@ def test_check_xpath_text_function_utf8(client, live_server, measure_memory_usag
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True, content_type="application/rss+xml;charset=UTF-8")
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.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("ui.ui_edit.edit_page", uuid="first"),
data={"include_filters": filter, "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
data={"include_filters": filter, "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -184,7 +163,8 @@ def test_check_xpath_text_function_utf8(client, live_server, measure_memory_usag
assert b'Stock Alert (UK): RPi CM4' in res.data
assert b'Stock Alert (UK): Big monitor' in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_check_markup_xpath_filter_restriction(client, live_server, measure_memory_usage):
@@ -194,8 +174,12 @@ def test_check_markup_xpath_filter_restriction(client, live_server, measure_memo
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Give the thread time to pick it up
wait_for_all_checks(client)
@@ -204,7 +188,7 @@ def test_check_markup_xpath_filter_restriction(client, live_server, measure_memo
# Add our URL to the import page
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first"),
data={"include_filters": xpath_filter, "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
data={"include_filters": xpath_filter, "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
@@ -224,40 +208,51 @@ def test_check_markup_xpath_filter_restriction(client, live_server, measure_memo
wait_for_all_checks(client)
res = client.get(url_for("watchlist.index"))
assert b'has-unread-changes' not in res.data
delete_all_watches(client)
assert b'unviewed' not in res.data
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_xpath_validation(client, live_server, measure_memory_usage):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.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("ui.ui_edit.edit_page", uuid="first"),
data={"include_filters": "/something horrible", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
data={"include_filters": "/something horrible", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"is not a valid XPath expression" in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_xpath23_prefix_validation(client, live_server, measure_memory_usage):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.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("ui.ui_edit.edit_page", uuid="first"),
data={"include_filters": "xpath:/something horrible", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
data={"include_filters": "xpath:/something horrible", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"is not a valid XPath expression" in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_xpath1_lxml(client, live_server, measure_memory_usage):
@@ -292,14 +287,18 @@ def test_xpath1_lxml(client, live_server, measure_memory_usage):
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.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("ui.ui_edit.edit_page", uuid="first"),
data={"include_filters": "xpath1://title/text()", "url": test_url, "tags": "", "headers": "",
'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
'fetch_backend': "html_requests"},
follow_redirects=True
)
@@ -322,35 +321,45 @@ def test_xpath1_lxml(client, live_server, measure_memory_usage):
def test_xpath1_validation(client, live_server, measure_memory_usage):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.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("ui.ui_edit.edit_page", uuid="first"),
data={"include_filters": "xpath1:/something horrible", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
data={"include_filters": "xpath1:/something horrible", "url": test_url, "tags": "", "headers": "", 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"is not a valid XPath expression" in res.data
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
# actually only really used by the distll.io importer, but could be handy too
def test_check_with_prefix_include_filters(client, live_server, measure_memory_usage):
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
set_original_response()
wait_for_all_checks(client)
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.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("ui.ui_edit.edit_page", uuid="first"),
data={"include_filters": "xpath://*[contains(@class, 'sametext')]", "url": test_url, "tags": "", "headers": "",
'fetch_backend': "html_requests", "time_between_check_use_default": "y"},
'fetch_backend': "html_requests"},
follow_redirects=True
)
@@ -389,8 +398,12 @@ def test_various_rules(client, live_server, measure_memory_usage):
""")
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
for r in ['//div', '//a', 'xpath://div', 'xpath://a']:
@@ -400,8 +413,7 @@ def test_various_rules(client, live_server, measure_memory_usage):
"url": test_url,
"tags": "",
"headers": "",
'fetch_backend': "html_requests",
"time_between_check_use_default": "y"},
'fetch_backend': "html_requests"},
follow_redirects=True
)
wait_for_all_checks(client)
@@ -409,13 +421,18 @@ def test_various_rules(client, live_server, measure_memory_usage):
res = client.get(url_for("watchlist.index"))
assert b'fetch-error' not in res.data, f"Should not see errors after '{r} filter"
delete_all_watches(client)
res = client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
def test_xpath_20(client, live_server, measure_memory_usage):
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
set_original_response()
@@ -427,8 +444,7 @@ def test_xpath_20(client, live_server, measure_memory_usage):
"url": test_url,
"tags": "",
"headers": "",
'fetch_backend': "html_requests",
"time_between_check_use_default": "y"},
'fetch_backend': "html_requests"},
follow_redirects=True
)
@@ -451,8 +467,12 @@ def test_xpath_20_function_count(client, live_server, measure_memory_usage):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
res = client.post(
@@ -461,8 +481,7 @@ def test_xpath_20_function_count(client, live_server, measure_memory_usage):
"url": test_url,
"tags": "",
"headers": "",
'fetch_backend': "html_requests",
"time_between_check_use_default": "y"},
'fetch_backend': "html_requests"},
follow_redirects=True
)
@@ -484,8 +503,12 @@ def test_xpath_20_function_count2(client, live_server, measure_memory_usage):
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
res = client.post(
@@ -494,8 +517,7 @@ def test_xpath_20_function_count2(client, live_server, measure_memory_usage):
"url": test_url,
"tags": "",
"headers": "",
'fetch_backend': "html_requests",
"time_between_check_use_default": "y"},
'fetch_backend': "html_requests"},
follow_redirects=True
)
@@ -517,19 +539,22 @@ def test_xpath_20_function_string_join_matches(client, live_server, measure_memo
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
res = client.post(
url_for("imports.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("ui.ui_edit.edit_page", uuid=uuid),
url_for("ui.ui_edit.edit_page", uuid="first"),
data={
"include_filters": "xpath:string-join(//*[contains(@class, 'sametext')]|//*[matches(@class, 'changetext')], 'specialconjunction')",
"url": test_url,
"tags": "",
"headers": "",
'fetch_backend': "html_requests",
"time_between_check_use_default": "y"},
'fetch_backend': "html_requests"},
follow_redirects=True
)
@@ -537,7 +562,7 @@ def test_xpath_20_function_string_join_matches(client, live_server, measure_memo
wait_for_all_checks(client)
res = client.get(
url_for("ui.ui_views.preview_page", uuid=uuid),
url_for("ui.ui_views.preview_page", uuid="first"),
follow_redirects=True
)
@@ -545,47 +570,3 @@ def test_xpath_20_function_string_join_matches(client, live_server, measure_memo
client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
def _subtest_xpath_rss(client, content_type='text/html'):
# Add our URL to the import page
test_url = url_for('test_endpoint', content_type=content_type, _external=True)
res = client.post(
url_for("ui.ui_views.form_quick_watch_add"),
data={"url": test_url, "tags": '', 'edit_and_watch_submit_button': 'Edit > Watch'},
follow_redirects=True
)
assert b"Watch added in Paused state, saving will unpause" in res.data
res = client.post(
url_for("ui.ui_edit.edit_page", uuid="first", unpause_on_save=1),
data={
"url": test_url,
"include_filters": "xpath://item",
"tags": '',
"fetch_backend": "html_requests",
"time_between_check_use_default": "y",
},
follow_redirects=True
)
assert b"unpaused" in res.data
wait_for_all_checks(client)
res = client.get(
url_for("ui.ui_views.preview_page", uuid="first"),
follow_redirects=True
)
assert b"Lets go discount" in res.data, f"When testing for Lets go discount called with content type '{content_type}'"
assert b"Events and Announcements" not in res.data, f"When testing for Lets go discount called with content type '{content_type}'" # It should not be here because thats not our selector target
client.get(url_for("ui.form_delete", uuid="all"), follow_redirects=True)
# Be sure all-in-the-wild types of RSS feeds work with xpath
def test_rss_xpath(client, live_server, measure_memory_usage):
for feed_header in ['', '<?xml version="1.0" encoding="utf-8"?>']:
set_rss_atom_feed_response(header=feed_header)
for content_type in RSS_XML_CONTENT_TYPES:
_subtest_xpath_rss(client, content_type=content_type)

View File

@@ -127,11 +127,6 @@ def extract_UUID_from_client(client):
uuid = m.group(1)
return uuid.strip()
def delete_all_watches(client=None):
uuids = list(client.application.config.get('DATASTORE').data['watching'])
for uuid in uuids:
client.application.config.get('DATASTORE').delete(uuid)
def wait_for_all_checks(client=None):
"""
@@ -140,6 +135,8 @@ def wait_for_all_checks(client=None):
"""
from changedetectionio.flask_app import update_q as global_update_q
from changedetectionio import worker_handler
logger = logging.getLogger()
empty_since = None
attempt = 0
max_attempts = 150 # Still reasonable upper bound
@@ -147,9 +144,9 @@ def wait_for_all_checks(client=None):
while attempt < max_attempts:
# Start with fast checks, slow down if needed
if attempt < 10:
time.sleep(0.2) # Very fast initial checks
time.sleep(0.1) # Very fast initial checks
elif attempt < 30:
time.sleep(0.4) # Medium speed
time.sleep(0.3) # Medium speed
else:
time.sleep(0.8) # Slower for persistent issues
@@ -325,3 +322,4 @@ def new_live_server_setup(live_server):
return resp
live_server.start()

View File

@@ -4,7 +4,7 @@ import os
from flask import url_for
from ..util import live_server_setup, wait_for_all_checks
# def test_setup(client, live_server, measure_memory_usage):
# def test_setup(client, live_server):
# live_server_setup(live_server) # Setup on conftest per function
@@ -36,7 +36,6 @@ def test_visual_selector_content_ready(client, live_server, measure_memory_usage
# For now, cookies doesnt work in headers because it must be a full cookiejar object
'headers': "testheader: yes\buser-agent: MyCustomAgent",
'fetch_backend': "html_webdriver",
"time_between_check_use_default": "y",
},
follow_redirects=True
)
@@ -117,7 +116,6 @@ def test_basic_browserstep(client, live_server, measure_memory_usage):
'browser_steps-1-optional_value': '',
# For now, cookies doesnt work in headers because it must be a full cookiejar object
'headers': "testheader: yes\buser-agent: MyCustomAgent",
"time_between_check_use_default": "y",
},
follow_redirects=True
)
@@ -142,7 +140,7 @@ def test_basic_browserstep(client, live_server, measure_memory_usage):
assert b"testheader: yes" in res.data
assert b"user-agent: mycustomagent" in res.data
def test_non_200_errors_report_browsersteps(client, live_server, measure_memory_usage):
def test_non_200_errors_report_browsersteps(client, live_server):
four_o_four_url = url_for('test_endpoint', status_code=404, _external=True)
@@ -169,8 +167,7 @@ def test_non_200_errors_report_browsersteps(client, live_server, measure_memory_
'fetch_backend': "html_webdriver",
'browser_steps-0-operation': 'Click element',
'browser_steps-0-selector': 'button[name=test-button]',
'browser_steps-0-optional_value': '',
"time_between_check_use_default": "y"
'browser_steps-0-optional_value': ''
},
follow_redirects=True
)

View File

@@ -1,4 +1,4 @@
openapi: 3.1.0
openapi: 3.0.3
info:
title: ChangeDetection.io API
description: |
@@ -28,7 +28,7 @@ info:
For example: `x-api-key: YOUR_API_KEY`
version: 0.1.1
version: 0.1.0
contact:
name: ChangeDetection.io
url: https://github.com/dgtlmoon/changedetection.io
@@ -129,7 +129,7 @@ components:
maxLength: 5000
title:
type: string
description: Custom title for the web page change monitor (watch), not to be confused with page_title
description: Custom title for the web page change monitor (watch)
maxLength: 5000
tag:
type: string
@@ -188,10 +188,6 @@ components:
seconds:
type: integer
description: Time intervals between checks
time_between_check_use_default:
type: boolean
default: true
description: Whether to use global settings for time between checks - defaults to true if not set
notification_urls:
type: array
items:
@@ -228,6 +224,8 @@ components:
maxLength: 5000
required: [operation, selector, optional_value]
description: Browser automation steps
required:
- url
Watch:
allOf:
@@ -255,11 +253,6 @@ components:
type: integer
description: Unix timestamp in seconds of the last time the watch was viewed. Setting it to a value higher than `last_changed` in the "Update watch" endpoint marks the watch as viewed.
minimum: 0
link:
type: string
format: string
description: The watch URL rendered in case of any Jinja2 markup, always use this for listing.
readOnly: true
CreateWatch:
allOf:
@@ -268,16 +261,6 @@ components:
required:
- url
UpdateWatch:
allOf:
- $ref: '#/components/schemas/WatchBase'
- type: object
properties:
last_viewed:
type: integer
description: Unix timestamp in seconds of the last time the watch was viewed. Setting it to a value higher than `last_changed` in the "Update watch" endpoint marks the watch as viewed.
minimum: 0
Tag:
type: object
properties:
@@ -298,13 +281,8 @@ components:
notification_muted:
type: boolean
description: Whether notifications are muted for this tag
CreateTag:
allOf:
- $ref: '#/components/schemas/Tag'
- type: object
required:
- title
required:
- title
NotificationUrls:
type: object
@@ -400,10 +378,9 @@ paths:
example:
"095be615-a8ad-4c33-8e9c-c7612fbf6c9f":
uuid: "095be615-a8ad-4c33-8e9c-c7612fbf6c9f"
url: "http://example.com?id={{1+1}} - the raw URL"
link: "http://example.com?id=2 - the rendered URL, always use this for listing."
title: "Example Website Monitor - manually entered title/description"
page_title: "The HTML <title> from the page"
url: "http://example.com"
title: "Example Website Monitor"
tag: "550e8400-e29b-41d4-a716-446655440000"
tags: ["550e8400-e29b-41d4-a716-446655440000"]
paused: false
muted: false
@@ -413,10 +390,9 @@ paths:
last_changed: 1640995200
"7c9e6b8d-f2a1-4e5c-9d3b-8a7f6e4c2d1a":
uuid: "7c9e6b8d-f2a1-4e5c-9d3b-8a7f6e4c2d1a"
url: "http://example.com?id={{1+1}} - the raw URL"
link: "http://example.com?id=2 - the rendered URL, always use this for listing."
title: "News Site Tracker - manually entered title/description"
page_title: "The HTML <title> from the page"
url: "https://news.example.org"
title: "News Site Tracker"
tag: "330e8400-e29b-41d4-a716-446655440001"
tags: ["330e8400-e29b-41d4-a716-446655440001"]
paused: false
muted: true
@@ -596,7 +572,7 @@ paths:
content:
application/json:
schema:
$ref: '#/components/schemas/UpdateWatch'
$ref: '#/components/schemas/Watch'
responses:
'200':
description: Web page change monitor (watch) updated successfully
@@ -839,7 +815,7 @@ paths:
'Content-Type': 'application/json'
}
data = {'title': 'Important Sites'}
response = requests.post('http://localhost:5000/api/v1/tag',
response = requests.post('http://localhost:5000/api/v1/tag',
headers=headers, json=data)
print(response.json())
requestBody:
@@ -847,7 +823,7 @@ paths:
content:
application/json:
schema:
$ref: '#/components/schemas/CreateTag'
$ref: '#/components/schemas/Tag'
example:
title: "Important Sites"
responses:
@@ -1222,6 +1198,7 @@ paths:
uuid: "095be615-a8ad-4c33-8e9c-c7612fbf6c9f"
url: "http://example.com"
title: "Example Website Monitor"
tag: "550e8400-e29b-41d4-a716-446655440000"
tags: ["550e8400-e29b-41d4-a716-446655440000"]
paused: false
muted: false

View File

@@ -12,7 +12,7 @@ flask_wtf~=1.2
flask~=2.3
flask-socketio~=5.5.1
python-socketio~=5.13.0
python-engineio~=4.12.3
python-engineio~=4.12.0
inscriptis~=2.2
pytz
timeago~=1.0
@@ -39,7 +39,7 @@ jsonpath-ng~=1.5.3
# jq not available on Windows so must be installed manually
# Notification library
apprise==1.9.5
apprise==1.9.3
# - Needed for apprise/spush, and maybe others? hopefully doesnt trigger a rust compile.
# - Requires extra wheel for rPi, adds build time for arm/v8 which is not in piwheels
@@ -51,8 +51,8 @@ cryptography==44.0.1
# use any version other than 2.0.x due to https://github.com/eclipse/paho.mqtt.python/issues/814
paho-mqtt!=2.0.*
# Used for CSS filtering, JSON extraction from HTML
beautifulsoup4>=4.0.0,<=4.13.5
# Used for CSS filtering
beautifulsoup4>=4.0.0
# XPath filtering, lxml is required by bs4 anyway, but put it here to be safe.
# #2328 - 5.2.0 and 5.2.1 had extra CPU flag CFLAGS set which was not compatible on older hardware
@@ -135,7 +135,7 @@ tzdata
pluggy ~= 1.5
# Needed for testing, cross-platform for process and system monitoring
psutil==7.1.0
psutil==7.0.0
ruff >= 0.11.2
pre_commit >= 4.2.0