Skip to content

fix: do not treat empty href quotes as URLs #143

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
adbar merged 1 commit into from
Jul 20, 2026
Merged

fix: do not treat empty href quotes as URLs #143

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion courlan/core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,8 @@

FIND_LINKS_REGEX = re.compile(r"<a\s+[^<>]+?>", re.I)
HREFLANG_REGEX = re.compile(r'hreflang=["\']?([a-z-]+)', re.I)
LINK_REGEX = re.compile(r'href=["\']?([^ ]+?)(["\' >])', re.I)
# *? so empty href="" / href='' do not capture the closing quote as the URL
LINK_REGEX = re.compile(r'href=["\']?([^ ]*?)(["\' >])', re.I)


def check_url(
Expand Down
15 changes: 15 additions & 0 deletions tests/unit_tests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1248,6 +1248,21 @@ def test_extraction():
# hreflang matches the target language but the tag has no href
pagecontent = '<html><a hreflang="de-DE">no href</a></html>'
assert not extract_links(pagecontent, "https://test.com/", False, language="de")
# empty quoted href must not capture the closing quote as a path (/%27)
pagecontent = "<html><a href=''>x</a></html>"
assert extract_links(pagecontent, "https://example.org", False) == {
"https://example.org"
}
assert extract_links(pagecontent, "https://example.org", no_filter=True) == {
"https://example.org"
}
pagecontent = '<html><a href="">x</a></html>'
assert extract_links(pagecontent, "https://example.org", False) == {
"https://example.org"
}
assert extract_links(pagecontent, "https://example.org", no_filter=True) == {
"https://example.org"
}
# link known under another form
pagecontent = '<html><a href="https://test.org/example"/><a href="https://test.org/example/&"/></html>'
assert len(extract_links(pagecontent, "https://test.org", False)) == 1
Expand Down
Loading