Adding better exception for when blocked by bot protection

youtube_transcript_api/_api.py

@@ -16,7 +16,7 @@
 
 class YouTubeTranscriptApi(object):
  @classmethod
- def list_transcripts(cls, video_id, proxies=None, cookies=None):
+ def list_transcripts(cls, video_id, proxies=None, cookies=None, verify=True):
  """
  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
@@ -61,13 +61,16 @@ def list_transcripts(cls, video_id, proxies=None, cookies=None):
  :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
+ :param verify: SSL Verification default. Will make your application vulnerable to man-in-the-middle (MitM) attacks.
+ :type verify: bool
  :return: the list of available transcripts
  :rtype TranscriptList:
  """
  with requests.Session() as http_client:
  if cookies:
  http_client.cookies = cls._load_cookies(cookies, video_id)
  http_client.proxies = proxies if proxies else {}
+ http_client.verify = verify
  return TranscriptListFetcher(http_client).fetch(video_id)
 
  @classmethod

youtube_transcript_api/_errors.py

@@ -77,6 +77,10 @@ class TranscriptsDisabled(CouldNotRetrieveTranscript):
  CAUSE_MESSAGE = 'Subtitles are disabled for this video'
 
 
+class BotRestricted(CouldNotRetrieveTranscript):
+ CAUSE_MESSAGE = 'Login required because video is restricted by bot detection system'
+
+
 class NoTranscriptAvailable(CouldNotRetrieveTranscript):
  CAUSE_MESSAGE = 'No transcripts are available for this video'
 

youtube_transcript_api/_transcripts.py

@@ -16,6 +16,7 @@
 from ._html_unescaping import unescape
 from ._errors import (
  VideoUnavailable,
+ BotRestricted,
  TooManyRequests,
  YouTubeRequestFailed,
  NoTranscriptFound,
@@ -58,6 +59,8 @@ def _extract_captions_json(self, html, video_id):
  raise TooManyRequests(video_id)
  if '"playabilityStatus":' not in html:
  raise VideoUnavailable(video_id)
+ if '"playabilityStatus":' in html and '"Sign in to confirm you’re not a bot"' in html:
+ raise BotRestricted(video_id)
 
  raise TranscriptsDisabled(video_id)