Skip to content

fix: support YouTube short URLs (youtu.be) #1740

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

Open
Jah-yee wants to merge 2 commits into
base: main
Choose a base branch
from
+29 −4
Open

fix: support YouTube short URLs (youtu.be) #1740

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4d73cd2
fix: support YouTube short URLs (youtu.be) in YouTubeConverter
Apr 13, 2026
80d95ac
fix: decode percent-encoded URI path before url2pathname
Apr 13, 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
5 changes: 3 additions & 2 deletions packages/markitdown/src/markitdown/_uri_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
import os
from typing import Tuple, Dict
from urllib.request import url2pathname
from urllib.parse import urlparse, unquote_to_bytes
from urllib.parse import urlparse, unquote, unquote_to_bytes


def file_uri_to_path(file_uri: str) -> Tuple[str | None, str]:
Expand All @@ -12,7 +12,8 @@ def file_uri_to_path(file_uri: str) -> Tuple[str | None, str]:
raise ValueError(f"Not a file URL: {file_uri}")

netloc = parsed.netloc if parsed.netloc else None
path = os.path.abspath(url2pathname(parsed.path))
decoded_path = unquote(parsed.path)
path = os.path.abspath(url2pathname(decoded_path))
return netloc, path


Expand Down
28 changes: 26 additions & 2 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 @@ -53,7 +53,15 @@ def accepts(
url = unquote(url)
url = url.replace(r"\?", "?").replace(r"\=", "=")

if not url.startswith("https://www.youtube.com/watch?"):
# Support multiple YouTube URL formats:
# - https://www.youtube.com/watch?v=...
# - https://youtu.be/... (short URL)
# - https://www.youtube.com/shorts/...
if not (
url.startswith("https://www.youtube.com/watch?")
or url.startswith("https://youtu.be/")
or url.startswith("https://www.youtube.com/shorts/")
):
# Not a YouTube URL
return False

Expand Down Expand Up @@ -148,9 +156,25 @@ def convert(
ytt_api = YouTubeTranscriptApi()
transcript_text = ""
parsed_url = urlparse(stream_info.url) # type: ignore
params = parse_qs(parsed_url.query) # type: ignore
# Extract video ID from various YouTube URL formats:
# - https://www.youtube.com/watch?v=VIDEO_ID
# - https://youtu.be/VIDEO_ID
# - https://www.youtube.com/shorts/VIDEO_ID
video_id = None
params = parse_qs(parsed_url.query)
if "v" in params and params["v"][0]:
video_id = str(params["v"][0])
elif parsed_url.path.startswith("/watch"):
params = parse_qs(parsed_url.query)
if "v" in params and params["v"][0]:
video_id = str(params["v"][0])
elif parsed_url.path.startswith("/shorts/"):
video_id = parsed_url.path.split("/shorts/")[1].split("/")[0]
elif parsed_url.path.startswith("/"):
# Handle youtu.be/VIDEO_ID short URLs
video_id = parsed_url.path.lstrip("/")

if video_id:
transcript_list = ytt_api.list(video_id)
languages = ["en"]
for transcript in transcript_list:
Expand Down