Class YouTubeTranscriptApi

youtube_transcript_api/_api.py:12–127

class YouTubeTranscriptApi:
    def __init__(
        self,
        proxy_config: Optional[ProxyConfig] = None,
        http_client: Optional[Session] = None,
    ):
        """
        Note on thread-safety: As this class will initialize a `requests.Session`
        object, it is not thread-safe. Make sure to initialize an instance of
        `YouTubeTranscriptApi` per thread, if used in a multi-threading scenario!

        :param proxy_config: an optional ProxyConfig object, defining proxies used for
            all network requests. This can be used to work around your IP being blocked
            by YouTube, as described in the "Working around IP bans" section of the
            README
            (https://github.com/jdepoix/youtube-transcript-api?tab=readme-ov-file#working-around-ip-bans-requestblocked-or-ipblocked-exception)
        :param http_client: You can optionally pass in a requests.Session object, if you
            manually want to share cookies between different instances of
            `YouTubeTranscriptApi`, overwrite defaults, specify SSL certificates, etc.
        """
        http_client = Session() if http_client is None else http_client
        http_client.headers.update({"Accept-Language": "en-US"})
        # Cookie auth has been temporarily disabled, as it is not working properly with
        # YouTube's most recent changes.
        # if cookie_path is not None:
        #     http_client.cookies = _load_cookie_jar(cookie_path)
        if proxy_config is not None:
            http_client.proxies = proxy_config.to_requests_dict()
            if proxy_config.prevent_keeping_connections_alive:
                http_client.headers.update({"Connection": "close"})
            if proxy_config.retries_when_blocked > 0:
                retry_config = Retry(
                    total=proxy_config.retries_when_blocked,
                    status_forcelist=[429],
                )
                http_client.mount("http://", HTTPAdapter(max_retries=retry_config))
                http_client.mount("https://", HTTPAdapter(max_retries=retry_config))
        self._fetcher = TranscriptListFetcher(http_client, proxy_config=proxy_config)

    def fetch(
        self,
        video_id: str,
        languages: Iterable[str] = ("en",),
        preserve_formatting: bool = False,
    ) -> FetchedTranscript:
        """
        Retrieves the transcript for a single video. This is just a shortcut for
        calling:
        `YouTubeTranscriptApi().list(video_id).find_transcript(languages).fetch(preserve_formatting=preserve_formatting)`

        :param video_id: the ID of the video you want to retrieve the transcript for.
            Make sure that this is the actual ID, NOT the full URL to the video!
        :param languages: A list of language codes in a descending priority. For
            example, if this is set to ["de", "en"] it will first try to fetch the
            german transcript (de) and then fetch the english transcript (en) if
            it fails to do so. This defaults to ["en"].
        :param preserve_formatting: whether to keep select HTML text formatting
        """