j4ddlZddlmZddlmZmZmZddlmZm Z ddl m Z ddl m Z mZddlmZmZmZdd lmZmZd eeefd efd ZGd dZy)N)Path)OptionalIterableUnion)MozillaCookieJar LoadError)Session) ProxyConfigGenericProxyConfig)TranscriptListFetcherFetchedTranscriptTranscriptList)CookiePathInvalid CookieInvalidcookiesreturnc t}|jt||s t||S#tt f$r t |wxYw)N)rloadstrrFileNotFoundErrorrr)r cookie_jars \/root/aria/tools/markitdown-venv/lib/python3.12/site-packages/youtube_transcript_api/_api.py_load_cookie_jarrsR)%' G %( ( y ))(()s 25Ac eZdZ ddeeeefdeedeefdZ ddede ede d e fd Z ded efd Zedd Ze dd Ze ddZy)YouTubeTranscriptApiN cookie_path proxy_config http_clientc"| tn|}|jjddi|t||_|>|j |_|jr|jjddit|||_ y)a Note on thread-safety: As this class will initialize a `requests.Session` object, it is not thread-safe. Make sure to initialize an instance of `YouTubeTranscriptApi` per thread, if used in a multi-threading scenario! :param cookie_path: Path to a text file containing YouTube authorization cookies :param proxy_config: an optional ProxyConfig object, defining proxies used for all network requests. This can be used to work around your IP being blocked by YouTube, as described in the "Working around IP bans" section of the README (https://github.com/jdepoix/youtube-transcript-api?tab=readme-ov-file#working-around-ip-bans-requestblocked-or-ipblocked-exception) :param http_client: You can optionally pass in a requests.Session object, if you manually want to share cookies between different instances of `YouTubeTranscriptApi`, overwrite defaults, specify SSL certificates, etc. NzAccept-Languagezen-US Connectionclose)r) r headersupdaterrto_requests_dictproxies!prevent_keeping_connections_aliver _fetcher)selfrrrs r__init__zYouTubeTranscriptApi.__init__s*$/#6giK ""$5w#?@  ""2;"?K   #"."?"?"AK ==##**L'+BC-k U video_id languagespreserve_formattingrcb|j|j|j|S)a  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 r.)listfind_transcriptfetch)r)r,r-r.s rr3zYouTubeTranscriptApi.fetch;s,( IIh  _Y ' U':U ; r+c8|jj|S)a Retrieves the list of transcripts which are available for a given video. It returns a `TranscriptList` object which is iterable and provides methods to filter the list of transcripts for specific languages. While iterating over the `TranscriptList` the individual transcripts are represented by `Transcript` objects, which provide metadata and can either be fetched by calling `transcript.fetch()` or translated by calling `transcript.translate( 'en')`. Example: ``` ytt_api = YouTubeTranscriptApi() # retrieve the available transcripts transcript_list = ytt_api.list('video_id') # iterate over all available transcripts for transcript in transcript_list: # the Transcript object provides metadata properties print( transcript.video_id, transcript.language, transcript.language_code, # whether it has been manually created or generated by YouTube transcript.is_generated, # a list of languages the transcript can be translated to transcript.translation_languages, ) # fetch the actual transcript data print(transcript.fetch()) # translating the transcript will return another transcript object print(transcript.translate('en').fetch()) # you can also directly filter for the language you are looking for, using the transcript list transcript = transcript_list.find_transcript(['de', 'en']) # or just filter for manually created transcripts transcript = transcript_list.find_manually_created_transcript(['de', 'en']) # or automatically generated ones transcript = transcript_list.find_generated_transcript(['de', 'en']) ``` :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! )r(r3)r)r,s rr1zYouTubeTranscriptApi.listTsf}}""8,,r+ctjdtd}|r>t|tr|}n+t |j d|j d}t||r t|nd}|j|S)a DEPRECATED: use the `list` method instead! Retrieves the list of transcripts which are available for a given video. It returns a `TranscriptList` object which is iterable and provides methods to filter the list of transcripts for specific languages. While iterating over the `TranscriptList` the individual transcripts are represented by `Transcript` objects, which provide metadata and can either be fetched by calling `transcript.fetch()` or translated by calling `transcript.translate('en')`. Example: # retrieve the available transcripts transcript_list = YouTubeTranscriptApi.list_transcripts('video_id') # iterate over all available transcripts for transcript in transcript_list: # the Transcript object provides metadata properties print( transcript.video_id, transcript.language, transcript.language_code, # whether it has been manually created or generated by YouTube transcript.is_generated, # a list of languages the transcript can be translated to transcript.translation_languages, ) # fetch the actual transcript data print(transcript.fetch()) # translating the transcript will return another transcript object print(transcript.translate('en').fetch()) # you can also directly filter for the language you are looking for, using the transcript list transcript = transcript_list.find_transcript(['de', 'en']) # or just filter for manually created transcripts transcript = transcript_list.find_manually_created_transcript(['de', 'en']) # or automatically generated ones transcript = transcript_list.find_generated_transcript(['de', 'en']) :param video_id: the youtube video id :type video_id: str :param proxies: a dictionary mapping of http and https proxies to be used for the network requests :type proxies: {'http': str, 'https': str} - http://docs.python-requests.org/en/master/user/advanced/#proxies :param cookies: a string of the path to a text file containing youtube authorization cookies :type cookies: str :return: the list of available transcripts :rtype TranscriptList: zh`list_transcripts` is deprecated and will be removed in a future version. Use the `list` method instead!Nhttphttps)http_url https_url)rr) warningswarnDeprecationWarning isinstancer r getrrr1)clsr,r&rrytt_apis rlist_transcriptsz%YouTubeTranscriptApi.list_transcriptss~f   -   ';/& 1$[[0GKK   .  (C(G*GG(  7G < _Y ' U':U ; []  r+)NNN)enF)NN)rNFNNF)rNNNF)__name__ __module__ __qualname__rrrrr r r*rboolrr3rr1 classmethodrArKrCr+rrrs37.2)- VeD#I./V{+Vg& VD$+$)   C= "    23-3- 3-jE&E&N"!7*7*r! * * r+r)r:pathlibrtypingrrrhttp.cookiejarrrrequestsr r&r r _transcriptsr rr_errorsrrrrrrUr+rr\sL,,64RR5)eD#I.)3C)[ [ r+