From a32f253112032f4b17d6d6c634358599bad4851b Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 4 Nov 2014 23:04:12 +0100 Subject: [PATCH] [gamespot] Modernize --- youtube_dl/extractor/gamespot.py | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py index 3d67b9d602..908a8b2c96 100644 --- a/youtube_dl/extractor/gamespot.py +++ b/youtube_dl/extractor/gamespot.py @@ -13,7 +13,7 @@ from ..utils import ( 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/videos/arma-3-community-guide-sitrep-i/2300-6410818/', 'md5': 'b2a30deaa8654fcccd43713a6b6a4825', @@ -26,10 +26,10 @@ class GameSpotIE(InfoExtractor): } 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, '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 @@ -41,7 +41,8 @@ class GameSpotIE(InfoExtractor): 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({ @@ -52,8 +53,9 @@ 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), }