Spaces:
Runtime error
Runtime error
File size: 11,707 Bytes
58d33f0 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 |
"""Loader that loads YouTube transcript."""
from __future__ import annotations
from pathlib import Path
from typing import Any, Dict, List, Optional
from pydantic import root_validator
from pydantic.dataclasses import dataclass
from langchain.docstore.document import Document
from langchain.document_loaders.base import BaseLoader
SCOPES = ["https://www.googleapis.com/auth/drive.readonly"]
@dataclass
class GoogleApiClient:
"""A Generic Google Api Client.
To use, you should have the ``google_auth_oauthlib,youtube_transcript_api,google``
python package installed.
As the google api expects credentials you need to set up a google account and
register your Service. "https://developers.google.com/docs/api/quickstart/python"
Example:
.. code-block:: python
from langchain.document_loaders import GoogleApiClient
google_api_client = GoogleApiClient(
service_account_path=Path("path_to_your_sec_file.json")
)
"""
credentials_path: Path = Path.home() / ".credentials" / "credentials.json"
service_account_path: Path = Path.home() / ".credentials" / "credentials.json"
token_path: Path = Path.home() / ".credentials" / "token.json"
def __post_init__(self) -> None:
self.creds = self._load_credentials()
@root_validator
def validate_channel_or_videoIds_is_set(
cls, values: Dict[str, Any]
) -> Dict[str, Any]:
"""Validate that either folder_id or document_ids is set, but not both."""
if not values.get("credentials_path") and not values.get(
"service_account_path"
):
raise ValueError("Must specify either channel_name or video_ids")
return values
def _load_credentials(self) -> Any:
"""Load credentials."""
# Adapted from https://developers.google.com/drive/api/v3/quickstart/python
try:
from google.auth.transport.requests import Request
from google.oauth2 import service_account
from google.oauth2.credentials import Credentials
from google_auth_oauthlib.flow import InstalledAppFlow
from youtube_transcript_api import YouTubeTranscriptApi # noqa: F401
except ImportError:
raise ImportError(
"You must run"
"`pip install --upgrade "
"google-api-python-client google-auth-httplib2 "
"google-auth-oauthlib"
"youtube-transcript-api`"
"to use the Google Drive loader"
)
creds = None
if self.service_account_path.exists():
return service_account.Credentials.from_service_account_file(
str(self.service_account_path)
)
if self.token_path.exists():
creds = Credentials.from_authorized_user_file(str(self.token_path), SCOPES)
if not creds or not creds.valid:
if creds and creds.expired and creds.refresh_token:
creds.refresh(Request())
else:
flow = InstalledAppFlow.from_client_secrets_file(
str(self.credentials_path), SCOPES
)
creds = flow.run_local_server(port=0)
with open(self.token_path, "w") as token:
token.write(creds.to_json())
return creds
class YoutubeLoader(BaseLoader):
"""Loader that loads Youtube transcripts."""
def __init__(
self, video_id: str, add_video_info: bool = False, language: str = "en"
):
"""Initialize with YouTube video ID."""
self.video_id = video_id
self.add_video_info = add_video_info
self.language = language
@classmethod
def from_youtube_channel(cls, youtube_url: str, **kwargs: Any) -> YoutubeLoader:
"""Given a channel name, load all videos."""
video_id = youtube_url.split("youtube.com/watch?v=")[-1]
return cls(video_id, **kwargs)
def load(self) -> List[Document]:
"""Load documents."""
try:
from youtube_transcript_api import NoTranscriptFound, YouTubeTranscriptApi
except ImportError:
raise ImportError(
"Could not import youtube_transcript_api python package. "
"Please it install it with `pip install youtube-transcript-api`."
)
metadata = {"source": self.video_id}
if self.add_video_info:
# Get more video meta info
# Such as title, description, thumbnail url, publish_date
video_info = self._get_video_info()
metadata.update(video_info)
transcript_list = YouTubeTranscriptApi.list_transcripts(self.video_id)
try:
transcript = transcript_list.find_transcript([self.language])
except NoTranscriptFound:
en_transcript = transcript_list.find_transcript(["en"])
transcript = en_transcript.translate(self.language)
transcript_pieces = transcript.fetch()
transcript = " ".join([t["text"].strip(" ") for t in transcript_pieces])
return [Document(page_content=transcript, metadata=metadata)]
def _get_video_info(self) -> dict:
"""Get important video information.
Components are:
- title
- description
- thumbnail url,
- publish_date
- channel_author
- and more.
"""
try:
from pytube import YouTube
except ImportError:
raise ImportError(
"Could not import pytube python package. "
"Please it install it with `pip install pytube`."
)
yt = YouTube(f"https://www.youtube.com/watch?v={self.video_id}")
video_info = {
"title": yt.title,
"description": yt.description,
"view_count": yt.views,
"thumbnail_url": yt.thumbnail_url,
"publish_date": yt.publish_date,
"length": yt.length,
"author": yt.author,
}
return video_info
@dataclass
class GoogleApiYoutubeLoader(BaseLoader):
"""Loader that loads all Videos from a Channel
To use, you should have the ``googleapiclient,youtube_transcript_api``
python package installed.
As the service needs a google_api_client, you first have to initialize
the GoogleApiClient.
Additionally you have to either provide a channel name or a list of videoids
"https://developers.google.com/docs/api/quickstart/python"
Example:
.. code-block:: python
from langchain.document_loaders import GoogleApiClient
from langchain.document_loaders import GoogleApiYoutubeLoader
google_api_client = GoogleApiClient(
service_account_path=Path("path_to_your_sec_file.json")
)
loader = GoogleApiYoutubeLoader(
google_api_client=google_api_client,
channel_name = "CodeAesthetic"
)
load.load()
"""
google_api_client: GoogleApiClient
channel_name: Optional[str] = None
video_ids: Optional[List[str]] = None
add_video_info: bool = True
captions_language: str = "en"
def __post_init__(self) -> None:
self.youtube_client = self._build_youtube_client(self.google_api_client.creds)
def _build_youtube_client(self, creds: Any) -> Any:
try:
from googleapiclient.discovery import build
from youtube_transcript_api import YouTubeTranscriptApi # noqa: F401
except ImportError:
raise ImportError(
"You must run"
"`pip install --upgrade "
"google-api-python-client google-auth-httplib2 "
"google-auth-oauthlib"
"youtube-transcript-api`"
"to use the Google Drive loader"
)
return build("youtube", "v3", credentials=creds)
@root_validator
def validate_channel_or_videoIds_is_set(
cls, values: Dict[str, Any]
) -> Dict[str, Any]:
"""Validate that either folder_id or document_ids is set, but not both."""
if not values.get("channel_name") and not values.get("video_ids"):
raise ValueError("Must specify either channel_name or video_ids")
return values
def _get_transcripe_for_video_id(self, video_id: str) -> str:
from youtube_transcript_api import NoTranscriptFound, YouTubeTranscriptApi
transcript_list = YouTubeTranscriptApi.list_transcripts(self.video_ids)
try:
transcript = transcript_list.find_transcript([self.captions_language])
except NoTranscriptFound:
en_transcript = transcript_list.find_transcript(["en"])
transcript = en_transcript.translate(self.captions_language)
transcript_pieces = transcript.fetch()
return " ".join([t["text"].strip(" ") for t in transcript_pieces])
def _get_document_for_video_id(self, video_id: str, **kwargs: Any) -> Document:
captions = self._get_transcripe_for_video_id(video_id)
video_response = (
self.youtube_client.videos()
.list(
part="id,snippet",
id=video_id,
)
.execute()
)
return Document(
page_content=captions,
metadata=video_response.get("items")[0],
)
def _get_channel_id(self, channel_name: str) -> str:
request = self.youtube_client.search().list(
part="id",
q=channel_name,
type="channel",
maxResults=1, # we only need one result since channel names are unique
)
response = request.execute()
channel_id = response["items"][0]["id"]["channelId"]
return channel_id
def _get_document_for_channel(self, channel: str, **kwargs: Any) -> List[Document]:
channel_id = self._get_channel_id(channel)
request = self.youtube_client.search().list(
part="id,snippet",
channelId=channel_id,
maxResults=50, # adjust this value to retrieve more or fewer videos
)
video_ids = []
while request is not None:
response = request.execute()
# Add each video ID to the list
for item in response["items"]:
if not item["id"].get("videoId"):
continue
meta_data = {"videoId": item["id"]["videoId"]}
if self.add_video_info:
item["snippet"].pop("thumbnails")
meta_data.update(item["snippet"])
video_ids.append(
Document(
page_content=self._get_transcripe_for_video_id(
item["id"]["videoId"]
),
metadata=meta_data,
)
)
request = self.youtube_client.search().list_next(request, response)
return video_ids
def load(self) -> List[Document]:
"""Load documents."""
document_list = []
if self.channel_name:
document_list.extend(self._get_document_for_channel(self.channel_name))
elif self.video_ids:
document_list.extend(
[
self._get_document_for_video_id(video_id)
for video_id in self.video_ids
]
)
else:
raise ValueError("Must specify either channel_name or video_ids")
return document_list
|