X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fgamespot.py;h=d570e3f6a85ca399d81328e3afedee4f98158e5f;hb=010cd3a3eee3b7c0a86424a2cc426cf427dab25f;hp=380ebbe556355b8fc0f49e825fa15433d5180b0b;hpb=c1195541b7c62af7a7c3e6ae802f4412173a61a3;p=youtube-dl diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py index 380ebbe55..d570e3f6a 100644 --- a/youtube_dl/extractor/gamespot.py +++ b/youtube_dl/extractor/gamespot.py @@ -8,27 +8,27 @@ from ..utils import ( compat_urllib_parse, compat_urlparse, unescapeHTML, - get_meta_content, ) class GameSpotIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P\d+)/?' + _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P\d+)/?' _TEST = { - "url": "http://www.gamespot.com/arma-iii/videos/arma-iii-community-guide-sitrep-i-6410818/", - "file": "gs-2300-6410818.mp4", - "md5": "b2a30deaa8654fcccd43713a6b6a4825", - "info_dict": { - "title": "Arma 3 - Community Guide: SITREP I", + 'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/', + 'md5': 'b2a30deaa8654fcccd43713a6b6a4825', + 'info_dict': { + 'id': 'gs-2300-6410818', + 'ext': 'mp4', + 'title': 'Arma 3 - Community Guide: SITREP I', 'description': 'Check out this video where some of the basics of Arma 3 is explained.', } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - page_id = mobj.group('page_id') + page_id = self._match_id(url) webpage = self._download_webpage(url, page_id) - data_video_json = self._search_regex(r'data-video=\'(.*?)\'', webpage, u'data video') + data_video_json = self._search_regex( + r'data-video=["\'](.*?)["\']', webpage, 'data video') data_video = json.loads(unescapeHTML(data_video_json)) # Transform the manifest url to a link to the mp4 files @@ -36,11 +36,12 @@ class GameSpotIE(InfoExtractor): f4m_url = data_video['videoStreams']['f4m_stream'] f4m_path = compat_urlparse.urlparse(f4m_url).path QUALITIES_RE = r'((,\d+)+,?)' - qualities = self._search_regex(QUALITIES_RE, f4m_path, u'qualities').strip(',').split(',') + qualities = self._search_regex(QUALITIES_RE, f4m_path, 'qualities').strip(',').split(',') http_path = f4m_path[1:].split('/', 1)[1] http_template = re.sub(QUALITIES_RE, r'%s', http_path) http_template = http_template.replace('.csmil/manifest.f4m', '') - http_template = compat_urlparse.urljoin('http://video.gamespotcdn.com/', http_template) + http_template = compat_urlparse.urljoin( + 'http://video.gamespotcdn.com/', http_template) formats = [] for q in qualities: formats.append({ @@ -51,8 +52,9 @@ class GameSpotIE(InfoExtractor): return { 'id': data_video['guid'], + 'display_id': page_id, 'title': compat_urllib_parse.unquote(data_video['title']), 'formats': formats, - 'description': get_meta_content('description', webpage), + 'description': self._html_search_meta('description', webpage), 'thumbnail': self._og_search_thumbnail(webpage), }