Core API Functions

class YouTubeTranscriptApi:
    def __init__(self, proxy_config=None, http_client=None):
        """
        Initialize the YouTube Transcript API client.

        Args:
            proxy_config (ProxyConfig, optional): Proxy configuration for network requests
            http_client (requests.Session, optional): Custom HTTP client session

        Note:
            Not thread-safe due to requests.Session usage. Create separate instances per thread.
        """

    def fetch(self, video_id, languages=("en",), preserve_formatting=False):
        """
        Retrieve transcript for a single video (shortcut method).

        Args:
            video_id (str): YouTube video ID (not full URL)
            languages (tuple, optional): Language codes in priority order. Defaults to ("en",)
            preserve_formatting (bool, optional): Whether to keep HTML formatting. Defaults to False

        Returns:
            FetchedTranscript: The retrieved transcript with content

        Raises:
            VideoUnavailable: Video is no longer available
            TranscriptsDisabled: Subtitles are disabled for this video
            NoTranscriptFound: No transcript found for requested languages
            RequestBlocked: Requests blocked by YouTube (IP ban)
            InvalidVideoId: Invalid video ID provided
        """

    def list(self, video_id):
        """
        Get list of all available transcripts for a video.

        Args:
            video_id (str): YouTube video ID (not full URL)

        Returns:
            TranscriptList: Container with all available transcripts

        Raises:
            VideoUnavailable: Video is no longer available
            TranscriptsDisabled: Subtitles are disabled for this video
            RequestBlocked: Requests blocked by YouTube (IP ban)
            InvalidVideoId: Invalid video ID provided
        """

from youtube_transcript_api import YouTubeTranscriptApi

# Simple transcript fetch with default English
api = YouTubeTranscriptApi()
transcript = api.fetch('dQw4w9WgXcQ')

for snippet in transcript:
    print(f"[{snippet.start:.2f}s] {snippet.text}")

from youtube_transcript_api import YouTubeTranscriptApi

api = YouTubeTranscriptApi()

# Try Spanish first, then English as fallback
transcript = api.fetch('dQw4w9WgXcQ', languages=['es', 'en'])

# Or use the list method for more control
transcript_list = api.list('dQw4w9WgXcQ')
transcript = transcript_list.find_transcript(['es', 'en'])
fetched = transcript.fetch()

from youtube_transcript_api import YouTubeTranscriptApi
from youtube_transcript_api.proxies import GenericProxyConfig

# Configure generic proxy
proxy_config = GenericProxyConfig(
    http_url='http://proxy:8080',
    https_url='https://proxy:8080'
)

api = YouTubeTranscriptApi(proxy_config=proxy_config)
transcript = api.fetch('dQw4w9WgXcQ')

from youtube_transcript_api import YouTubeTranscriptApi
import requests

# Use custom session with timeout
session = requests.Session()
session.timeout = 30

api = YouTubeTranscriptApi(http_client=session)
transcript = api.fetch('dQw4w9WgXcQ')

from youtube_transcript_api import YouTubeTranscriptApi

api = YouTubeTranscriptApi()
transcript = api.fetch('dQw4w9WgXcQ', preserve_formatting=True)

# Text may contain HTML tags like <b>, <i>, etc.
for snippet in transcript:
    print(snippet.text)  # May include HTML formatting

from typing import Optional, Iterable
from requests import Session

# Type hints for main API
ProxyConfig = Union[GenericProxyConfig, WebshareProxyConfig]
LanguageCodes = Iterable[str]