mirror of
https://github.com/thecyberlearn/chat-backend.git
synced 2026-08-18 21:52:53 +00:00
a0fce0b484
Features: - Django REST API backend - Multi-strategy web scraping system (Beautiful Soup, Playwright, Firecrawl) - Anti-detection features (proxy rotation, user-agent rotation) - Data export functionality (JSON, CSV, TXT) - Business and CrawledPage models - Enhanced crawling service with fallback mechanisms 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
30 lines
1.1 KiB
Python
30 lines
1.1 KiB
Python
import pytest
|
|
from unittest.mock import patch
|
|
from bs4.builder import DetectsXMLParsedAsHTML
|
|
|
|
class TestDetectsXMLParsedAsHTML(object):
|
|
|
|
@pytest.mark.parametrize(
|
|
"markup,looks_like_xml",
|
|
[("No xml declaration", False),
|
|
("<html>obviously HTML</html", False),
|
|
("<?xml ><html>Actually XHTML</html>", False),
|
|
("<?xml> < html>Tricky XHTML</html>", False),
|
|
("<?xml ><no-html-tag>", True),
|
|
]
|
|
)
|
|
def test_warn_if_markup_looks_like_xml(self, markup, looks_like_xml):
|
|
# Test of our ability to guess at whether markup looks XML-ish
|
|
# _and_ not HTML-ish.
|
|
with patch('bs4.builder.DetectsXMLParsedAsHTML._warn') as mock:
|
|
for data in markup, markup.encode('utf8'):
|
|
result = DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(
|
|
data
|
|
)
|
|
assert result == looks_like_xml
|
|
if looks_like_xml:
|
|
assert mock.called
|
|
else:
|
|
assert not mock.called
|
|
mock.reset_mock()
|