apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-05-01 11:56:25 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

feat: update YouTube transcript fetching to select primary language transcripts

Browse source
This commit is contained in:
DESKTOP-RTLN3BA\$punk 2026-02-06 14:02:46 -08:00
parent d97068882a
commit cdc217dbe2
2 changed files with 22 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

12
surfsense_backend/app/agents/new_chat/tools/scrape_webpage.py
View file

@ -110,7 +110,17 @@ async def _scrape_youtube_video(
if residential_proxies:
http_client.proxies.update(residential_proxies)
ytt_api = YouTubeTranscriptApi(http_client=http_client)
captions = ytt_api.fetch(video_id)
# List all available transcripts and pick the first one
# (the video's primary language) instead of defaulting to English
transcript_list = ytt_api.list(video_id)
transcript = next(iter(transcript_list))
captions = transcript.fetch()
logger.info(
f"[scrape_webpage] Fetched transcript for {video_id} "
f"in {transcript.language} ({transcript.language_code})"
)
transcript_segments = []
for line in captions: