X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fgametrailers.py;h=c3f031d9cd4341184cc3b70eea77c1f360a1a3c6;hb=9f0ee2a3883ec6f6fdccba90085cb925aaa2f617;hp=33e59e82c47f10d37c0004de073757568d25347b;hpb=825e0984e27f0c626c4d072066e0c9cae9069704;p=youtube-dl diff --git a/youtube_dl/extractor/gametrailers.py b/youtube_dl/extractor/gametrailers.py index 33e59e82c..c3f031d9c 100644 --- a/youtube_dl/extractor/gametrailers.py +++ b/youtube_dl/extractor/gametrailers.py @@ -1,59 +1,62 @@ -import re +from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( - compat_urllib_parse, - - ExtractorError, + int_or_none, + parse_age_limit, + url_basename, ) + class GametrailersIE(InfoExtractor): - _VALID_URL = r'http://www.gametrailers.com/(?Pvideos|reviews|full-episodes)/(?P.*?)/(?P.*)' + _VALID_URL = r'http://www\.gametrailers\.com/videos/view/[^/]+/(?P<id>.+)' + + _TEST = { + 'url': 'http://www.gametrailers.com/videos/view/gametrailers-com/116437-Just-Cause-3-Review', + 'md5': 'f28c4efa0bdfaf9b760f6507955b6a6a', + 'info_dict': { + 'id': '2983958', + 'ext': 'mp4', + 'display_id': '116437-Just-Cause-3-Review', + 'title': 'Just Cause 3 - Review', + 'description': 'It\'s a lot of fun to shoot at things and then watch them explode in Just Cause 3, but should there be more to the experience than that?', + }, + } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - video_id = mobj.group('id') - video_type = mobj.group('type') - webpage = self._download_webpage(url, video_id) - if video_type == 'full-episodes': - mgid_re = r'data-video="(?P<mgid>mgid:.*?)"' - else: - mgid_re = r'data-contentId=\'(?P<mgid>mgid:.*?)\'' - mgid = self._search_regex(mgid_re, webpage, u'mgid') - data = compat_urllib_parse.urlencode({'uri': mgid, 'acceptMethods': 'fms'}) - - info_page = self._download_webpage('http://www.gametrailers.com/feeds/mrss?' + data, - video_id, u'Downloading video info') - links_webpage = self._download_webpage('http://www.gametrailers.com/feeds/mediagen/?' + data, - video_id, u'Downloading video urls info') - - self.report_extraction(video_id) - info_re = r'''<title><!\[CDATA\[(?P<title>.*?)\]\]>.* - .*?)\]\]>.* - .* - (?P.*?).* - ''' - - m_info = re.search(info_re, info_page, re.VERBOSE|re.DOTALL) - if m_info is None: - raise ExtractorError(u'Unable to extract video info') - video_title = m_info.group('title') - video_description = m_info.group('description') - video_thumb = m_info.group('thumb') - - m_urls = list(re.finditer(r'(?P.*)', links_webpage)) - if m_urls is None or len(m_urls) == 0: - raise ExtractorError(u'Unable to extract video url') - # They are sorted from worst to best quality - video_url = m_urls[-1].group('url') - - return {'url': video_url, - 'id': video_id, - 'title': video_title, - # Videos are actually flv not mp4 - 'ext': 'flv', - 'thumbnail': video_thumb, - 'description': video_description, - } + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + title = self._html_search_regex( + r'(.+?)\|', webpage, 'title').strip() + embed_url = self._proto_relative_url( + self._search_regex( + r'src=\'(//embed.gametrailers.com/embed/[^\']+)\'', webpage, + 'embed url'), + scheme='http:') + video_id = url_basename(embed_url) + embed_page = self._download_webpage(embed_url, video_id) + embed_vars_json = self._search_regex( + r'(?s)var embedVars = (\{.*?\})\s*</script>', embed_page, + 'embed vars') + info = self._parse_json(embed_vars_json, video_id) + + formats = [] + for media in info['media']: + if media['mediaPurpose'] == 'play': + formats.append({ + 'url': media['uri'], + 'height': media['height'], + 'width:': media['width'], + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'formats': formats, + 'thumbnail': info.get('thumbUri'), + 'description': self._og_search_description(webpage), + 'duration': int_or_none(info.get('videoLengthInSeconds')), + 'age_limit': parse_age_limit(info.get('audienceRating')), + }