luciano/markitdown
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Support specifying YouTube transcript language

Browse source
This commit is contained in:
narumi 2024-12-16 13:16:00 +08:00
parent 81e3f24acd
commit 695100d5d8
1 changed files with 5 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
src/markitdown/_markitdown.py
View file

@ -344,8 +344,11 @@ class YouTubeConverter(DocumentConverter):
assert isinstance(params["v"][0], str) assert isinstance(params["v"][0], str)
video_id = str(params["v"][0]) video_id = str(params["v"][0])
try: try:
youtube_transcript_languages = kwargs.get(
"youtube_transcript_languages", ("en",)
)
# Must be a single transcript. # Must be a single transcript.
transcript = YouTubeTranscriptApi.get_transcript(video_id) # type: ignore transcript = YouTubeTranscriptApi.get_transcript(video_id, languages=youtube_transcript_languages) # type: ignore
transcript_text = " ".join([part["text"] for part in transcript]) # type: ignore transcript_text = " ".join([part["text"] for part in transcript]) # type: ignore
# Alternative formatting: # Alternative formatting:
# formatter = TextFormatter() # formatter = TextFormatter()
@ -1003,7 +1006,7 @@ class MarkItDown:
self._append_ext(extensions, g) self._append_ext(extensions, g)
# Convert # Convert
result = self._convert(temp_path, extensions, url=response.url) result = self._convert(temp_path, extensions, url=response.url, **kwargs)
# Clean up # Clean up
finally: finally:
try: try: