X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fdiscoverygo.py;h=9e7b14a7d594e5fbb145aab0521bc4f8250305a6;hb=HEAD;hp=d14de8f006f3c68963f77e405ea8e98114690bed;hpb=70497994707b6bcbd6c0ecc3fb1073be4d75d970;p=youtube-dl diff --git a/youtube_dl/extractor/discoverygo.py b/youtube_dl/extractor/discoverygo.py index d14de8f00..9e7b14a7d 100644 --- a/youtube_dl/extractor/discoverygo.py +++ b/youtube_dl/extractor/discoverygo.py @@ -3,14 +3,15 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( + determine_ext, extract_attributes, ExtractorError, int_or_none, parse_age_limit, remove_end, unescapeHTML, + url_or_none, ) @@ -27,41 +28,9 @@ class DiscoveryGoBaseIE(InfoExtractor): velocitychannel )go\.com/%s(?P[^/?#&]+)''' - -class DiscoveryGoIE(DiscoveryGoBaseIE): - _VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % r'(?:[^/]+/)+' - _TEST = { - 'url': 'https://www.discoverygo.com/love-at-first-kiss/kiss-first-ask-questions-later/', - 'info_dict': { - 'id': '57a33c536b66d1cd0345eeb1', - 'ext': 'mp4', - 'title': 'Kiss First, Ask Questions Later!', - 'description': 'md5:fe923ba34050eae468bffae10831cb22', - 'duration': 2579, - 'series': 'Love at First Kiss', - 'season_number': 1, - 'episode_number': 1, - 'age_limit': 14, - }, - } - - def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - - container = extract_attributes( - self._search_regex( - r'(]+class=["\']video-player-container[^>]+>)', - webpage, 'video container')) - - video = self._parse_json( - container.get('data-video') or container.get('data-json'), - display_id) - + def _extract_video_info(self, video, stream, display_id): title = video['name'] - stream = video.get('stream') if not stream: if video.get('authenticated') is True: raise ExtractorError( @@ -100,12 +69,15 @@ class DiscoveryGoIE(DiscoveryGoBaseIE): captions = stream.get('captions') if isinstance(captions, list): for caption in captions: - subtitle_url = caption.get('fileUrl') - if (not subtitle_url or not isinstance(subtitle_url, compat_str) or - not subtitle_url.startswith('http')): + subtitle_url = url_or_none(caption.get('fileUrl')) + if not subtitle_url or not subtitle_url.startswith('http'): continue lang = caption.get('fileLang', 'en') - subtitles.setdefault(lang, []).append({'url': subtitle_url}) + ext = determine_ext(subtitle_url) + subtitles.setdefault(lang, []).append({ + 'url': subtitle_url, + 'ext': 'ttml' if ext == 'xml' else ext, + }) return { 'id': video_id, @@ -123,6 +95,43 @@ class DiscoveryGoIE(DiscoveryGoBaseIE): } +class DiscoveryGoIE(DiscoveryGoBaseIE): + _VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % r'(?:[^/]+/)+' + _GEO_COUNTRIES = ['US'] + _TEST = { + 'url': 'https://www.discoverygo.com/bering-sea-gold/reaper-madness/', + 'info_dict': { + 'id': '58c167d86b66d12f2addeb01', + 'ext': 'mp4', + 'title': 'Reaper Madness', + 'description': 'md5:09f2c625c99afb8946ed4fb7865f6e78', + 'duration': 2519, + 'series': 'Bering Sea Gold', + 'season_number': 8, + 'episode_number': 6, + 'age_limit': 14, + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + container = extract_attributes( + self._search_regex( + r'(]+class=["\']video-player-container[^>]+>)', + webpage, 'video container')) + + video = self._parse_json( + container.get('data-video') or container.get('data-json'), + display_id) + + stream = video.get('stream') + + return self._extract_video_info(video, stream, display_id) + + class DiscoveryGoPlaylistIE(DiscoveryGoBaseIE): _VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % '' _TEST = {