File size: 2,913 Bytes
1554d3e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 |
from typing import Any, Dict, Generator, List, Optional, Sequence, Union
from urllib.parse import parse_qs, urlparse
from langchain_core.documents import Document
ALLOWED_SCHEMES = {"http", "https"}
ALLOWED_NETLOCS = {
"youtu.be",
"m.youtube.com",
"youtube.com",
"www.youtube.com",
"www.youtube-nocookie.com",
"vid.plus",
}
def _parse_video_id(url: str) -> Optional[str]:
"""Parse a YouTube URL and return the video ID if valid, otherwise None."""
parsed_url = urlparse(url)
if parsed_url.scheme not in ALLOWED_SCHEMES:
return None
if parsed_url.netloc not in ALLOWED_NETLOCS:
return None
path = parsed_url.path
if path.endswith("/watch"):
query = parsed_url.query
parsed_query = parse_qs(query)
if "v" in parsed_query:
ids = parsed_query["v"]
video_id = ids if isinstance(ids, str) else ids[0]
else:
return None
else:
path = parsed_url.path.lstrip("/")
video_id = path.split("/")[-1]
if len(video_id) != 11: # Video IDs are 11 characters long
return None
return video_id
class YoutubeLoader:
"""Load `YouTube` video transcripts."""
def __init__(
self,
video_id: str,
language: Union[str, Sequence[str]] = "en",
):
"""Initialize with YouTube video ID."""
_video_id = _parse_video_id(video_id)
self.video_id = _video_id if _video_id is not None else video_id
self._metadata = {"source": video_id}
self.language = language
if isinstance(language, str):
self.language = [language]
else:
self.language = language
def load(self) -> List[Document]:
"""Load YouTube transcripts into `Document` objects."""
try:
from youtube_transcript_api import (
NoTranscriptFound,
TranscriptsDisabled,
YouTubeTranscriptApi,
)
except ImportError:
raise ImportError(
'Could not import "youtube_transcript_api" Python package. '
"Please install it with `pip install youtube-transcript-api`."
)
try:
transcript_list = YouTubeTranscriptApi.list_transcripts(self.video_id)
except Exception as e:
print(e)
return []
try:
transcript = transcript_list.find_transcript(self.language)
except NoTranscriptFound:
transcript = transcript_list.find_transcript(["en"])
transcript_pieces: List[Dict[str, Any]] = transcript.fetch()
transcript = " ".join(
map(
lambda transcript_piece: transcript_piece["text"].strip(" "),
transcript_pieces,
)
)
return [Document(page_content=transcript, metadata=self._metadata)]
|