X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fskysports.py;h=efcbb36a9eb5e6e2cf5884ccea3aa9c505fa8cb3;hb=54fc90aabfb71968f28af68dfe3f7a3544cc2f0b;hp=9dc78c7d2b27748fd2e1c083e7b265448cbff500;hpb=5b6a74856babce30e9e72701259f790322281d3a;p=youtube-dl diff --git a/youtube_dl/extractor/skysports.py b/youtube_dl/extractor/skysports.py index 9dc78c7d2..efcbb36a9 100644 --- a/youtube_dl/extractor/skysports.py +++ b/youtube_dl/extractor/skysports.py @@ -2,18 +2,24 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import ( + extract_attributes, + smuggle_url, + strip_or_none, + urljoin, +) class SkySportsIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?skysports\.com/watch/video/(?P[0-9]+)' _TEST = { 'url': 'http://www.skysports.com/watch/video/10328419/bale-its-our-time-to-shine', - 'md5': 'c44a1db29f27daf9a0003e010af82100', + 'md5': '77d59166cddc8d3cb7b13e35eaf0f5ec', 'info_dict': { 'id': '10328419', - 'ext': 'flv', - 'title': 'Bale: Its our time to shine', - 'description': 'md5:9fd1de3614d525f5addda32ac3c482c9', + 'ext': 'mp4', + 'title': 'Bale: It\'s our time to shine', + 'description': 'md5:e88bda94ae15f7720c5cb467e777bb6d', }, 'add_ie': ['Ooyala'], } @@ -21,13 +27,23 @@ class SkySportsIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + video_data = extract_attributes(self._search_regex( + r'(]+>)', webpage, 'video data')) + + video_url = 'ooyala:%s' % video_data['data-video-id'] + if video_data.get('data-token-required') == 'true': + token_fetch_options = self._parse_json(video_data.get('data-token-fetch-options', '{}'), video_id, fatal=False) or {} + token_fetch_url = token_fetch_options.get('url') + if token_fetch_url: + embed_token = self._download_webpage(urljoin(url, token_fetch_url), video_id, fatal=False) + if embed_token: + video_url = smuggle_url(video_url, {'embed_token': embed_token.strip('"')}) return { '_type': 'url_transparent', 'id': video_id, - 'url': 'ooyala:%s' % self._search_regex( - r'data-video-id="([^"]+)"', webpage, 'ooyala id'), + 'url': video_url, 'title': self._og_search_title(webpage), - 'description': self._og_search_description(webpage), + 'description': strip_or_none(self._og_search_description(webpage)), 'ie_key': 'Ooyala', }