KeyArgo
/
youtube-transcript-api
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Added cookies parameter to api class methods

This commit is contained in:
danielcliu 2020-01-15 22:48:00 -08:00
parent edefeeaf1d
commit 02b1978217
1 changed files with 14 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
youtube_transcript_api/_api.py
View File

@ -1,11 +1,15 @@
import requests import requests
try:
import http.cookiejar as cookiejar
except ImportError:
import cookielib as cookiejar
from ._transcripts import TranscriptListFetcher from ._transcripts import TranscriptListFetcher
class YouTubeTranscriptApi(): class YouTubeTranscriptApi():
@classmethod @classmethod
def list_transcripts(cls, video_id, proxies=None): def list_transcripts(cls, video_id, proxies=None, cookies=None):
""" """
Retrieves the list of transcripts which are available for a given video. It returns a `TranscriptList` object 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 which is iterable and provides methods to filter the list of transcripts for specific languages. While iterating
@ -51,12 +55,17 @@ class YouTubeTranscriptApi():
:return: the list of available transcripts :return: the list of available transcripts
:rtype TranscriptList: :rtype TranscriptList:
""" """
print(cookies)
with requests.Session() as http_client: with requests.Session() as http_client:
if cookies:
cj = cookiejar.MozillaCookieJar()
cj.load(cookies)
http_client.cookies = cj
http_client.proxies = proxies if proxies else {} http_client.proxies = proxies if proxies else {}
return TranscriptListFetcher(http_client).fetch(video_id) return TranscriptListFetcher(http_client).fetch(video_id)
@classmethod @classmethod
def get_transcripts(cls, video_ids, languages=('en',), continue_after_error=False, proxies=None): def get_transcripts(cls, video_ids, languages=('en',), continue_after_error=False, proxies=None, cookies=None):
""" """
Retrieves the transcripts for a list of videos. Retrieves the transcripts for a list of videos.
@ -80,7 +89,7 @@ class YouTubeTranscriptApi():
for video_id in video_ids: for video_id in video_ids:
try: try:
data[video_id] = cls.get_transcript(video_id, languages, proxies) data[video_id] = cls.get_transcript(video_id, languages, proxies, cookies)
except Exception as exception: except Exception as exception:
if not continue_after_error: if not continue_after_error:
raise exception raise exception
@ -90,7 +99,7 @@ class YouTubeTranscriptApi():
return data, unretrievable_videos return data, unretrievable_videos
@classmethod @classmethod
def get_transcript(cls, video_id, languages=('en',), proxies=None): def get_transcript(cls, video_id, languages=('en',), proxies=None, cookies=None):
""" """
Retrieves the transcript for a single video. This is just a shortcut for calling:: Retrieves the transcript for a single video. This is just a shortcut for calling::
@ -107,4 +116,4 @@ class YouTubeTranscriptApi():
:return: a list of dictionaries containing the 'text', 'start' and 'duration' keys :return: a list of dictionaries containing the 'text', 'start' and 'duration' keys
:rtype [{'text': str, 'start': float, 'end': float}]: :rtype [{'text': str, 'start': float, 'end': float}]:
""" """
return cls.list_transcripts(video_id, proxies).find_transcript(languages).fetch() return cls.list_transcripts(video_id, proxies, cookies).find_transcript(languages).fetch()