X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fpluralsight.py;h=abd08bc285c3c107bd548ddf0ec1c86fe77ecd9a;hb=067aa17edf5a46a8cbc4d6b90864eddf051fa2bc;hp=1257841e4bbcffbae999cd402f9a6c7982a3fb30;hpb=836ef4840f00d7e07c826de23f3a09675dc532d5;p=youtube-dl diff --git a/youtube_dl/extractor/pluralsight.py b/youtube_dl/extractor/pluralsight.py index 1257841e4..abd08bc28 100644 --- a/youtube_dl/extractor/pluralsight.py +++ b/youtube_dl/extractor/pluralsight.py @@ -4,6 +4,7 @@ import collections import json import os import random +import re from .common import InfoExtractor from ..compat import ( @@ -196,7 +197,10 @@ query viewClip { if error: raise ExtractorError('Unable to login: %s' % error, expected=True) - if all(p not in response for p in ('__INITIAL_STATE__', '"currentUser"')): + if all(not re.search(p, response) for p in ( + r'__INITIAL_STATE__', r'["\']currentUser["\']', + # new layout? + r'>\s*Sign out\s*<')): BLOCKED = 'Your account has been blocked due to suspicious activity' if BLOCKED in response: raise ExtractorError( @@ -210,18 +214,26 @@ query viewClip { raise ExtractorError('Unable to log in') - def _get_subtitles(self, author, clip_idx, lang, name, duration, video_id): - captions_post = { - 'a': author, - 'cn': clip_idx, - 'lc': lang, - 'm': name, - } - captions = self._download_json( - '%s/player/retrieve-captions' % self._API_BASE, video_id, - 'Downloading captions JSON', 'Unable to download captions JSON', - fatal=False, data=json.dumps(captions_post).encode('utf-8'), - headers={'Content-Type': 'application/json;charset=utf-8'}) + def _get_subtitles(self, author, clip_idx, clip_id, lang, name, duration, video_id): + captions = None + if clip_id: + captions = self._download_json( + '%s/transcript/api/v1/caption/json/%s/%s' + % (self._API_BASE, clip_id, lang), video_id, + 'Downloading captions JSON', 'Unable to download captions JSON', + fatal=False) + if not captions: + captions_post = { + 'a': author, + 'cn': int(clip_idx), + 'lc': lang, + 'm': name, + } + captions = self._download_json( + '%s/player/retrieve-captions' % self._API_BASE, video_id, + 'Downloading captions JSON', 'Unable to download captions JSON', + fatal=False, data=json.dumps(captions_post).encode('utf-8'), + headers={'Content-Type': 'application/json;charset=utf-8'}) if captions: return { lang: [{ @@ -315,7 +327,7 @@ query viewClip { ) # Some courses also offer widescreen resolution for high quality (see - # https://github.com/rg3/youtube-dl/issues/7766) + # https://github.com/ytdl-org/youtube-dl/issues/7766) widescreen = course.get('supportsWideScreenVideoFormats') is True best_quality = 'high-widescreen' if widescreen else 'high' if widescreen: @@ -376,8 +388,8 @@ query viewClip { # Pluralsight tracks multiple sequential calls to ViewClip API and start # to return 429 HTTP errors after some time (see - # https://github.com/rg3/youtube-dl/pull/6989). Moreover it may even lead - # to account ban (see https://github.com/rg3/youtube-dl/issues/6842). + # https://github.com/ytdl-org/youtube-dl/pull/6989). Moreover it may even lead + # to account ban (see https://github.com/ytdl-org/youtube-dl/issues/6842). # To somewhat reduce the probability of these consequences # we will sleep random amount of time before each call to ViewClip. self._sleep( @@ -413,7 +425,7 @@ query viewClip { # TODO: other languages? subtitles = self.extract_subtitles( - author, clip_idx, 'en', name, duration, display_id) + author, clip_idx, clip.get('clipId'), 'en', name, duration, display_id) return { 'id': clip_id,