_cli.py

import argparse
from importlib.metadata import PackageNotFoundError, version
from typing import List

from .proxies import GenericProxyConfig, WebshareProxyConfig
from .formatters import FormatterLoader

from ._api import YouTubeTranscriptApi, FetchedTranscript, TranscriptList


class YouTubeTranscriptCli:
    def __init__(self, args: List[str]):
        self._args = args

    def run(self) -> str:
        parsed_args = self._parse_args()

        if parsed_args.exclude_manually_created and parsed_args.exclude_generated:
            return ""

        proxy_config = None
        if parsed_args.http_proxy != "" or parsed_args.https_proxy != "":
            proxy_config = GenericProxyConfig(
                http_url=parsed_args.http_proxy,
                https_url=parsed_args.https_proxy,
            )

        if (
            parsed_args.webshare_proxy_username is not None
            or parsed_args.webshare_proxy_password is not None
        ):
            proxy_config = WebshareProxyConfig(
                proxy_username=parsed_args.webshare_proxy_username,
                proxy_password=parsed_args.webshare_proxy_password,
            )

        transcripts = []
        exceptions = []

        ytt_api = YouTubeTranscriptApi(
            proxy_config=proxy_config,
            cookies_from_browser=parsed_args.cookies_from_browser,
        )

        for video_id in parsed_args.video_ids:
            try:
                transcript_list = ytt_api.list(video_id)
                if parsed_args.list_transcripts:
                    transcripts.append(transcript_list)
                else:
                    transcripts.append(
                        self._fetch_transcript(
                            parsed_args,
                            transcript_list,
                        )
                    )
            except Exception as exception:
                exceptions.append(exception)

        print_sections = [str(exception) for exception in exceptions]
        if transcripts:
            if parsed_args.list_transcripts:
                print_sections.extend(
                    str(transcript_list) for transcript_list in transcripts
                )
            else:
                print_sections.append(
                    FormatterLoader()
                    .load(parsed_args.format)
                    .format_transcripts(transcripts)
                )

        return "\n\n".join(print_sections)

    def _fetch_transcript(
        self,
        parsed_args,
        transcript_list: TranscriptList,
    ) -> FetchedTranscript:
        if parsed_args.exclude_manually_created:
            transcript = transcript_list.find_generated_transcript(
                parsed_args.languages
            )
        elif parsed_args.exclude_generated:
            transcript = transcript_list.find_manually_created_transcript(
                parsed_args.languages
            )
        else:
            transcript = transcript_list.find_transcript(parsed_args.languages)

        if parsed_args.translate:
            transcript = transcript.translate(parsed_args.translate)

        return transcript.fetch()

    def _get_version(self):
        try:
            return version("youtube-transcript-api")
        except PackageNotFoundError:
            return "unknown"

    def _parse_args(self):
        parser = argparse.ArgumentParser(
            description=(
                "This is a python API which allows you to get the transcripts/subtitles for a given YouTube video. "
                "It also works for automatically generated subtitles and it does not require a headless browser, like "
                "other selenium based solutions do!"
            )
        )
        parser.add_argument(
            "--version",
            action="version",
            version=f"%(prog)s, version {self._get_version()}",
        )
        parser.add_argument(
            "--list-transcripts",
            action="store_const",
            const=True,
            default=False,
            help="This will list the languages in which the given videos are available in.",
        )
        parser.add_argument(
            "video_ids", nargs="+", type=str, help="List of YouTube video IDs."
        )
        parser.add_argument(
            "--languages",
            nargs="*",
            default=[
                "en",
            ],
            type=str,
            help=(
                '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. As I can't provide a complete list of all working language codes with full certainty, you "
                "may have to play around with the language codes a bit, to find the one which is working for you!"
            ),
        )
        parser.add_argument(
            "--exclude-generated",
            action="store_const",
            const=True,
            default=False,
            help="If this flag is set transcripts which have been generated by YouTube will not be retrieved.",
        )
        parser.add_argument(
            "--exclude-manually-created",
            action="store_const",
            const=True,
            default=False,
            help="If this flag is set transcripts which have been manually created will not be retrieved.",
        )
        parser.add_argument(
            "--format",
            type=str,
            default="pretty",
            choices=tuple(FormatterLoader.TYPES.keys()),
        )
        parser.add_argument(
            "--translate",
            default="",
            help=(
                "The language code for the language you want this transcript to be translated to. Use the "
                "--list-transcripts feature to find out which languages are translatable and which translation "
                "languages are available."
            ),
        )
        parser.add_argument(
            "--webshare-proxy-username",
            default=None,
            type=str,
            help='Specify your Webshare "Proxy Username" found at https://dashboard.webshare.io/proxy/settings',
        )
        parser.add_argument(
            "--webshare-proxy-password",
            default=None,
            type=str,
            help='Specify your Webshare "Proxy Password" found at https://dashboard.webshare.io/proxy/settings',
        )
        parser.add_argument(
            "--http-proxy",
            default="",
            metavar="URL",
            help="Use the specified HTTP proxy.",
        )
        parser.add_argument(
            "--https-proxy",
            default="",
            metavar="URL",
            help="Use the specified HTTPS proxy.",
        )
        parser.add_argument(
            "--cookies-from-browser",
            dest="cookies_from_browser",
            default=None,
            choices=[
                "chrome",
                "firefox",
                "edge",
                "brave",
                "chromium",
                "opera",
                "vivaldi",
            ],
            help=(
                "Extract cookies from the specified browser for authentication. "
                "This enables access to age-restricted videos. "
                "Supported browsers: chrome, firefox, edge, brave, chromium, opera, vivaldi. "
                "Note: Chrome-based browsers require the 'cryptography' package. "
                "Install with: pip install 'youtube-transcript-api[cookies]'"
            ),
        )

        return self._sanitize_video_ids(parser.parse_args(self._args))

    def _sanitize_video_ids(self, args):
        args.video_ids = [video_id.replace("\\", "") for video_id in args.video_ids]
        return args