Skip to content

fix(youtube): handle missing title metadata without raising AssertionError #2238

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
Adam Fourney (afourney) merged 3 commits into from
Sep 3, 2026
+41 −5
Merged

fix(youtube): handle missing title metadata without raising AssertionError #2238

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4b3c5bb
fix(youtube): handle missing title metadata without raising Assertion…
hsusul Jul 25, 2026
97dda08
Merge branch 'main' into fix-youtube-missing-title-metadata
afourney Sep 3, 2026
7c8c4fe
Empty titles would still raise assertion errors. Fixed.
afourney Sep 3, 2026
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
6 changes: 1 addition & 5 deletions packages/markitdown/src/markitdown/converters/_youtube_converter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,8 +118,7 @@ def convert(
# Start preparing the page
webpage_text = "# YouTube\n"

title = self._get(metadata, ["title", "og:title", "name"]) # type: ignore
assert isinstance(title, str)
title = self._get(metadata, ["title", "og:title", "name"]) or ""

if title:
webpage_text += f"\n## {title}\n"
Expand Down Expand Up @@ -188,9 +187,6 @@ def convert(
if transcript_text:
webpage_text += f"\n### Transcript\n{transcript_text}\n"

title = title if title else (soup.title.string if soup.title else "")
assert isinstance(title, str)

return DocumentConverterResult(
markdown=webpage_text,
title=title,
Expand Down
40 changes: 40 additions & 0 deletions packages/markitdown/tests/test_module_misc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -898,6 +898,46 @@ def test_markitdown_llm() -> None:
validate_strings(result, PPTX_TEST_STRINGS)


def test_youtube_converter_missing_title_metadata() -> None:
"""Test that YouTubeConverter converts streams with and without title metadata without raising AssertionError."""
from unittest.mock import patch
from markitdown.converters._youtube_converter import YouTubeConverter

converter = YouTubeConverter()
stream_info = StreamInfo(
mimetype="text/html",
extension=".html",
url="https://www.youtube.com/watch?v=12345",
)

with patch(
"markitdown.converters._youtube_converter.IS_YOUTUBE_TRANSCRIPT_CAPABLE",
False,
):
# Case 1: Stream with no title metadata or title tag
html_content_no_title = b"<html><head></head><body>Video Content</body></html>"
stream_no_title = io.BytesIO(html_content_no_title)
result_no_title = converter.convert(stream_no_title, stream_info)
assert result_no_title.title == ""
assert "# YouTube" in result_no_title.markdown

# Case 2: Stream with an empty <title> tag
html_content_empty_title = (
b"<html><head><title></title></head><body>Video Content</body></html>"
)
stream_empty_title = io.BytesIO(html_content_empty_title)
result_empty_title = converter.convert(stream_empty_title, stream_info)
assert result_empty_title.title == ""
assert "# YouTube" in result_empty_title.markdown

# Case 3: Stream whose title is only available from the <title> tag
html_content_title_tag = b"<html><head><title>Fallback Title</title></head><body>Video Content</body></html>"
stream_title_tag = io.BytesIO(html_content_title_tag)
result_title_tag = converter.convert(stream_title_tag, stream_info)
assert result_title_tag.title == "Fallback Title"
assert "# YouTube" in result_title_tag.markdown


def test_zip_stream_no_filename_header() -> None:
"""Regression test: ZipConverter must not render the literal string 'None'
in the output header when the stream has no associated URL, local path, or
Expand Down
Loading