This commit is contained in:
dgtlmoon
2023-09-26 13:18:12 +02:00
parent 2ff65b53fb
commit 9b4fb80bef
2 changed files with 58 additions and 2 deletions
@@ -314,7 +314,11 @@ class perform_site_check(difference_detection_processor):
# 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 is_json and not empty_pages_are_a_change and len(stripped_text_from_html.strip()) == 0:
raise content_fetcher.ReplyWithContentButNoText(url=url, status_code=fetcher.get_last_status_code(), screenshot=screenshot, has_filters=has_filter_rule)
raise content_fetcher.ReplyWithContentButNoText(url=url,
status_code=fetcher.get_last_status_code(),
screenshot=screenshot,
has_filters=has_filter_rule and len(html_content)
)
# 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.
+53 -1
View File
@@ -2,7 +2,7 @@
import time
from flask import url_for
from . util import live_server_setup
from .util import live_server_setup, wait_for_all_checks
from ..html_tools import *
@@ -176,3 +176,55 @@ def test_check_multiple_filters(client, live_server):
assert b"Blob A" in res.data # CSS was ok
assert b"Blob B" in res.data # xPath was ok
assert b"Blob C" not in res.data # Should not be included
# The filter exists, but did not contain anything useful
# Mainly used when the filter contains just an IMG, this can happen when someone selects an image in the visual-selector
# @todo in the future, in the image-selector, if they choose an element that only contains IMG give a helpful suggestion
def test_filter_is_empty_help_suggestion(client, live_server):
live_server_setup(live_server)
include_filters = "#blob-a"
with open("test-datastore/endpoint-content.txt", "w") as f:
f.write("""<html><body>
<div id="blob-a">
<img src="something.jpg">
</div>
</body>
</html>
""")
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
res = client.post(
url_for("import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
wait_for_all_checks(client)
# 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={"include_filters": include_filters,
"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("index"),
follow_redirects=True
)
assert b'possible that the filters you have give an empty result' in res.data