Compare commits

..

1 Commits

Author SHA1 Message Date
dgtlmoon
114344f950 Re #653 fixing RSS feed HTML content formatting 2022-06-06 10:12:54 +02:00
17 changed files with 25 additions and 296 deletions

View File

@@ -21,7 +21,7 @@ Steps to reproduce the behavior:
3. Scroll down to '....'
4. See error
! ALWAYS INCLUDE AN EXAMPLE URL WHERE IT IS POSSIBLE TO RE-CREATE THE ISSUE - USE THE 'SHARE WATCH' FEATURE AND PASTE IN THE SHARE-LINK!
! ALWAYS INCLUDE AN EXAMPLE URL WHERE IT IS POSSIBLE TO RE-CREATE THE ISSUE !
**Expected behavior**
A clear and concise description of what you expected to happen.

1
.gitignore vendored
View File

@@ -8,6 +8,5 @@ __pycache__
build
dist
venv
test-datastore
*.egg-info*
.vscode/settings.json

View File

@@ -20,7 +20,6 @@ from copy import deepcopy
from threading import Event
import flask_login
import logging
import pytz
import timeago
from feedgen.feed import FeedGenerator
@@ -352,8 +351,9 @@ def changedetection_app(config=None, datastore_o=None):
latest_fname = watch.history[dates[-1]]
html_diff = diff.render_diff(prev_fname, latest_fname, include_equal=False, line_feed_sep="</br>")
fe.content(content="<html><body><h4>{}</h4>{}</body></html>".format(watch_title, html_diff),
type='CDATA')
fe.description(description="<![CDATA["
"<html><body><h4>{}</h4>{}</body></html>"
"]]>".format(watch_title, html_diff))
fe.guid(guid, permalink=False)
dt = datetime.datetime.fromtimestamp(int(watch.newest_history_key))
@@ -458,19 +458,6 @@ def changedetection_app(config=None, datastore_o=None):
return 'OK'
@app.route("/scrub/<string:uuid>", methods=['GET'])
@login_required
def scrub_watch(uuid):
try:
datastore.scrub_watch(uuid)
except KeyError:
flash('Watch not found', 'error')
else:
flash("Scrubbed watch {}".format(uuid))
return redirect(url_for('index'))
@app.route("/scrub", methods=['GET', 'POST'])
@login_required
def scrub_page():
@@ -822,13 +809,7 @@ def changedetection_app(config=None, datastore_o=None):
screenshot_url = datastore.get_screenshot(uuid)
system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
is_html_webdriver = True if watch.get('fetch_backend') == 'html_webdriver' or (
watch.get('fetch_backend', None) is None and system_uses_webdriver) else False
output = render_template("diff.html",
watch_a=watch,
output = render_template("diff.html", watch_a=watch,
newest=newest_version_file_contents,
previous=previous_version_file_contents,
extra_stylesheets=extra_stylesheets,
@@ -839,8 +820,7 @@ def changedetection_app(config=None, datastore_o=None):
current_diff_url=watch['url'],
extra_title=" - Diff - {}".format(watch['title'] if watch['title'] else watch['url']),
left_sticky=True,
screenshot=screenshot_url,
is_html_webdriver=is_html_webdriver)
screenshot=screenshot_url)
return output
@@ -901,11 +881,6 @@ def changedetection_app(config=None, datastore_o=None):
content.append({'line': "No history found", 'classes': ''})
screenshot_url = datastore.get_screenshot(uuid)
system_uses_webdriver = datastore.data['settings']['application']['fetch_backend'] == 'html_webdriver'
is_html_webdriver = True if watch.get('fetch_backend') == 'html_webdriver' or (
watch.get('fetch_backend', None) is None and system_uses_webdriver) else False
output = render_template("preview.html",
content=content,
extra_stylesheets=extra_stylesheets,
@@ -914,8 +889,7 @@ def changedetection_app(config=None, datastore_o=None):
current_diff_url=watch['url'],
screenshot=screenshot_url,
watch=watch,
uuid=uuid,
is_html_webdriver=is_html_webdriver)
uuid=uuid)
return output
@@ -924,7 +898,7 @@ def changedetection_app(config=None, datastore_o=None):
def notification_logs():
global notification_debug_log
output = render_template("notification-log.html",
logs=notification_debug_log if len(notification_debug_log) else ["Notification logs are empty - no notifications sent yet."])
logs=notification_debug_log if len(notification_debug_log) else ["No errors or warnings detected"])
return output
@@ -1195,8 +1169,7 @@ def changedetection_app(config=None, datastore_o=None):
except Exception as e:
logging.error("Error sharing -{}".format(str(e)))
flash("Could not share, something went wrong while communicating with the share server - {}".format(str(e)), 'error')
flash("Could not share, something went wrong while communicating with the share server.", 'error')
# https://changedetection.io/share/VrMv05wpXyQa
# in the browser - should give you a nice info page - wtf
@@ -1244,9 +1217,6 @@ def check_for_new_version():
def notification_runner():
global notification_debug_log
from datetime import datetime
import json
while not app.config.exit.is_set():
try:
# At the moment only one thread runs (single runner)
@@ -1255,16 +1225,13 @@ def notification_runner():
time.sleep(1)
else:
now = datetime.now()
# Process notifications
try:
from changedetectionio import notification
notification.process_notification(n_object, datastore)
except Exception as e:
logging.error("Watch URL: {} Error {}".format(n_object['watch_url'], str(e)))
print("Watch URL: {} Error {}".format(n_object['watch_url'], str(e)))
# UUID wont be present when we submit a 'test' from the global settings
if 'uuid' in n_object:
@@ -1274,11 +1241,10 @@ def notification_runner():
log_lines = str(e).splitlines()
notification_debug_log += log_lines
# Process notifications
notification_debug_log+= ["{} - SENDING {}".format(now.strftime("%Y/%m/%d %H:%M:%S,000"), json.dumps(n_object))]
# Trim the log length
notification_debug_log = notification_debug_log[-100:]
# Thread runner to check every minute, look for new watches to feed into the Queue.
def ticker_thread_check_time_launch_checks():
from changedetectionio import update_worker

View File

@@ -204,20 +204,6 @@ class perform_site_check():
else:
stripped_text_from_html = stripped_text_from_html.encode('utf8')
# 615 Extract text by regex
extract_text = watch.get('extract_text', [])
if len(extract_text) > 0:
regex_matched_output = []
for s_re in extract_text:
result = re.findall(s_re.encode('utf8'), stripped_text_from_html,
flags=re.MULTILINE | re.DOTALL | re.LOCALE)
if result:
regex_matched_output.append(result[0])
if regex_matched_output:
stripped_text_from_html = b'\n'.join(regex_matched_output)
text_content_before_ignored_filter = stripped_text_from_html
# Re #133 - if we should strip whitespaces from triggering the change detected comparison
if self.datastore.data['settings']['application'].get('ignore_whitespace', False):
fetched_md5 = hashlib.md5(stripped_text_from_html.translate(None, b'\r\n\t ')).hexdigest()
@@ -235,7 +221,6 @@ class perform_site_check():
# Yeah, lets block first until something matches
blocked_by_not_found_trigger_text = True
# Filter and trigger works the same, so reuse it
# It should return the line numbers that match
result = html_tools.strip_ignore_text(content=str(stripped_text_from_html),
wordlist=watch['trigger_text'],
mode="line numbers")

View File

@@ -330,9 +330,6 @@ class watchForm(commonSettingsForm):
css_filter = StringField('CSS/JSON/XPATH Filter', [ValidateCSSJSONXPATHInput()], default='')
subtractive_selectors = StringListField('Remove elements', [ValidateCSSJSONXPATHInput(allow_xpath=False, allow_json=False)])
extract_text = StringListField('Extract text', [ValidateListRegex()])
title = StringField('Title', default='')
ignore_text = StringListField('Ignore text', [ValidateListRegex()])

View File

@@ -35,8 +35,7 @@ class model(dict):
'notification_title': default_notification_title,
'notification_body': default_notification_body,
'notification_format': default_notification_format,
'css_filter': '',
'extract_text': [], # Extract text by regex after filters
'css_filter': "",
'subtractive_selectors': [],
'trigger_text': [], # List of text or regex to wait for until a change is detected
'fetch_backend': None,

View File

@@ -97,8 +97,6 @@ def process_notification(n_object, datastore):
if log_value and 'WARNING' in log_value or 'ERROR' in log_value:
raise Exception(log_value)
# Notification title + body content parameters get created here.
def create_notification_parameters(n_object, datastore):
from copy import deepcopy

View File

@@ -1,17 +0,0 @@
$(document).ready(function () {
// Load it when the #screenshot tab is in use, so we dont give a slow experience when waiting for the text diff to load
window.addEventListener('hashchange', function (e) {
toggle(location.hash);
}, false);
toggle(location.hash);
function toggle(hash_name) {
if (hash_name === '#screenshot') {
$("img#screenshot-img").attr('src', screenshot_url);
$("#settings").hide();
} else {
$("#settings").show();
}
}
});

View File

@@ -49,8 +49,6 @@ $(document).ready(function() {
}
state_clicked=false;
ctx.clearRect(0, 0, c.width, c.height);
xctx.clearRect(0, 0, c.width, c.height);
$("#css_filter").val('');
});

View File

@@ -254,23 +254,12 @@ class ChangeDetectionStore:
def scrub_watch(self, uuid):
import pathlib
self.__data['watching'][uuid].update(
{'last_checked': 0,
'last_changed': 0,
'last_viewed': 0,
'previous_md5': False,
'last_notification_error': False,
'last_error': False})
# JSON Data, Screenshots, Textfiles (history index and snapshots), HTML in the future etc
for item in pathlib.Path(os.path.join(self.datastore_path, uuid)).rglob("*.*"):
unlink(item)
# Force the attr to recalculate
bump = self.__data['watching'][uuid].history
self.__data['watching'][uuid].update({'history': {}, 'last_checked': 0, 'last_changed': 0, 'previous_md5': False})
self.needs_write_urgent = True
for item in pathlib.Path(self.datastore_path).rglob(uuid+"/*.txt"):
unlink(item)
def add_watch(self, url, tag="", extras=None, write_to_disk_now=True):
if extras is None:
@@ -298,7 +287,7 @@ class ChangeDetectionStore:
'body', 'method',
'ignore_text', 'css_filter',
'subtractive_selectors', 'trigger_text',
'extract_title_as_title', 'extract_text']:
'extract_title_as_title']:
if res.get(k):
apply_extras[k] = res[k]

View File

@@ -14,7 +14,7 @@
<li>Use <a target=_new href="https://github.com/caronc/apprise">AppRise URLs</a> for notification to just about any service! <i><a target=_new href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes">Please read the notification services wiki here for important configuration notes</a></i>.</li>
<li><code>discord://</code> only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
<li><code>tgram://</code> bots cant send messages to other bots, so you should specify chat ID of non-bot user.</li>
<li>Go here for <a href="{{url_for('notification_logs')}}">notification debug logs</a></li>
</ul>
</div>
<br/>
@@ -22,7 +22,6 @@
{% if emailprefix %}
<a id="add-email-helper" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Add email</a>
{% endif %}
<a href="{{url_for('notification_logs')}}" class="pure-button button-secondary button-xsmall" style="font-size: 70%">Notification debug logs</a>
</div>
<div id="notification-customisation" class="pure-control-group">
<div class="pure-control-group">

View File

@@ -1,11 +1,6 @@
{% extends 'base.html' %}
{% block content %}
<script>
const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
</script>
<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
<div id="settings">
<h1>Differences</h1>
<form class="pure-form " action="" method="GET">
@@ -44,7 +39,6 @@
<div class="tabs">
<ul>
<li class="tab" id="default-tab"><a href="#text">Text</a></li>
<li class="tab" id="screenshot-tab"><a href="#screenshot">Screenshot</a></li>
</ul>
</div>
@@ -66,21 +60,6 @@
</table>
Diff algorithm from the amazing <a href="https://github.com/kpdecker/jsdiff">github.com/kpdecker/jsdiff</a>
</div>
<div class="tab-pane-inner" id="screenshot">
<div class="tip">
For now, Differences are performed on text, not graphically, only the latest screenshot is available.
</div>
</br>
{% if is_html_webdriver %}
{% if screenshot %}
<img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request"/>
{% else %}
No screenshot available just yet! Try rechecking the page.
{% endif %}
{% else %}
<strong>Screenshot requires Playwright/WebDriver enabled</strong>
{% endif %}
</div>
</div>

View File

@@ -199,17 +199,6 @@ nav
</span>
</div>
</fieldset>
<fieldset>
<div class="pure-control-group">
{{ render_field(form.extract_text, rows=5, placeholder="\d+ online") }}
<span class="pure-form-message-inline">
<ul>
<li>Extracts text in the final output after other filters using regular expressions, for example <code>\d+ online</code></li>
<li>One line per regular-expression.</li>
</ul>
</span>
</div>
</fieldset>
</div>
<div class="tab-pane-inner visual-selector-ui" id="visualselector">
@@ -259,8 +248,6 @@ nav
<a href="{{url_for('form_delete', uuid=uuid)}}"
class="pure-button button-small button-error ">Delete</a>
<a href="{{url_for('scrub_watch', uuid=uuid)}}"
class="pure-button button-small button-error ">Scrub</a>
<a href="{{url_for('form_clone', uuid=uuid)}}"
class="pure-button button-small ">Create Copy</a>
</div>

View File

@@ -4,7 +4,7 @@
<div class="edit-form">
<div class="inner">
<h4 style="margin-top: 0px;">Notification debug log</h4>
<h4 style="margin-top: 0px;">The following issues were detected when sending notifications</h4>
<div id="notification-error-log">
<ul style="font-size: 80%; margin:0px; padding: 0 0 0 7px">
{% for log in logs|reverse %}

View File

@@ -1,10 +1,6 @@
{% extends 'base.html' %}
{% block content %}
<script>
const screenshot_url="{{url_for('static_content', group='screenshot', filename=uuid)}}";
</script>
<script type="text/javascript" src="{{url_for('static_content', group='js', filename='diff-overview.js')}}" defer></script>
<div id="settings">
<h1>Current - {{watch.last_checked|format_timestamp_timeago}}</h1>
@@ -14,7 +10,6 @@
<div class="tabs">
<ul>
<li class="tab" id="default-tab"><a href="#text">Text</a></li>
<li class="tab" id="screenshot-tab"><a href="#screenshot">Screenshot</a></li>
</ul>
</div>
@@ -33,20 +28,5 @@
</tbody>
</table>
</div>
<div class="tab-pane-inner" id="screenshot">
<div class="tip">
For now, Differences are performed on text, not graphically, only the latest screenshot is available.
</div>
</br>
{% if is_html_webdriver %}
{% if screenshot %}
<img style="max-width: 80%" id="screenshot-img" alt="Current screenshot from most recent request"/>
{% else %}
No screenshot available just yet! Try rechecking the page.
{% endif %}
{% else %}
<strong>Screenshot requires Playwright/WebDriver enabled</strong>
{% endif %}
</div>
</div>
{% endblock %}

View File

@@ -1,127 +0,0 @@
#!/usr/bin/python3
import time
from flask import url_for
from .util import live_server_setup
from ..html_tools import *
def set_original_response():
test_return_data = """<html>
<body>
Some initial text</br>
<p>Which is across multiple lines</p>
</br>
So let's see what happens. </br>
<div id="sametext">Some text thats the same</div>
<div id="changetext">Some text that will change</div>
</body>
</html>
"""
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write(test_return_data)
return None
def set_modified_response():
test_return_data = """<html>
<body>
Some initial text</br>
<p>which has this one new line</p>
</br>
So let's see what happens. </br>
<div id="sametext">Some text thats the same</div>
<div id="changetext">Some text that did change ( 1000 online <br/> 80 guests)</div>
</body>
</html>
"""
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write(test_return_data)
return None
def test_check_filter_and_regex_extract(client, live_server):
sleep_time_for_fetch_thread = 3
live_server_setup(live_server)
css_filter = "#changetext"
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', _external=True)
res = client.post(
url_for("import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
# Goto the edit page, add our ignore text
# Add our URL to the import page
res = client.post(
url_for("edit_page", uuid="first"),
data={"css_filter": css_filter,
'extract_text': '\d+ online\n\d+ guests',
"url": test_url,
"tag": "",
"headers": "",
'fetch_backend': "html_requests"
},
follow_redirects=True
)
assert b"Updated watch." in res.data
# Check it saved
res = client.get(
url_for("edit_page", uuid="first"),
)
assert b'\d+ online' in res.data
# Trigger a check
# client.get(url_for("form_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
# Make a change
set_modified_response()
# Trigger a check
client.get(url_for("form_watch_checknow"), follow_redirects=True)
# Give the thread time to pick it up
time.sleep(sleep_time_for_fetch_thread)
# It should have 'unviewed' still
# Because it should be looking at only that 'sametext' id
res = client.get(url_for("index"))
assert b'unviewed' in res.data
# Check HTML conversion detected and workd
res = client.get(
url_for("preview_page", uuid="first"),
follow_redirects=True
)
# Class will be blank for now because the frontend didnt apply the diff
assert b'<div class="">1000 online' in res.data
# Both regexs should be here
assert b'<div class="">80 guests' in res.data
# Should not be here
assert b'Some text that did change' not in res.data

View File

@@ -56,9 +56,6 @@ class update_worker(threading.Thread):
except content_fetcher.ReplyWithContentButNoText as e:
# Totally fine, it's by choice - just continue on, nothing more to care about
# Page had elements/content but no renderable text
if self.datastore.data['watching'][uuid].get('css_filter'):
self.datastore.update_watch(uuid=uuid, update_obj={'last_error': "Got HTML content but no text found (CSS / xPath Filter not found in page?)"})
else:
self.datastore.update_watch(uuid=uuid, update_obj={'last_error': "Got HTML content but no text found."})
pass
except content_fetcher.EmptyReply as e: