diff options
| author | Philipp Hagemeister <phihag@phihag.de> | 2014-11-12 15:36:59 +0100 |
|---|---|---|
| committer | Philipp Hagemeister <phihag@phihag.de> | 2014-11-12 15:36:59 +0100 |
| commit | 5ccaddf5b150fc113f5b423f6d2f8b7e9a30cc83 (patch) | |
| tree | b596e19c5468cac9aff341bc12b9eccbcddc489d | |
| parent | 0b201a3134e9b343e2791f2686f1a34f737007a4 (diff) | |
| download | youtube-dl-5ccaddf5b150fc113f5b423f6d2f8b7e9a30cc83.tar.xz | |
[goldenmoustache] Simplify (#4128)
| -rw-r--r-- | youtube_dl/extractor/goldenmoustache.py | 24 |
1 files changed, 11 insertions, 13 deletions
diff --git a/youtube_dl/extractor/goldenmoustache.py b/youtube_dl/extractor/goldenmoustache.py index c25d2e779..f2e231bf4 100644 --- a/youtube_dl/extractor/goldenmoustache.py +++ b/youtube_dl/extractor/goldenmoustache.py @@ -18,26 +18,24 @@ class GoldenMoustacheIE(InfoExtractor): 'ext': 'mp4', 'title': 'Suricate - Le Poker', 'description': 'md5:3d1f242f44f8c8cb0a106f1fd08e5dc9', - 'thumbnail': 'md5:fd41386bc1f932552622da4a7e9a7242', + 'thumbnail': 're:^https?://.*\.jpg$', + 'view_count': int, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - video_url = self._html_search_regex(r'data-src-type="mp4" data-src="([^"]+)"', webpage, 'video URL') - - title = self._html_search_regex(r'<title>(.*?) - Golden Moustache</title>', webpage, 'title') - - thumbnail = self._html_search_meta('og:image', webpage, 'thumbnail') - - description = self._html_search_meta('og:description', webpage, 'description') - + video_url = self._html_search_regex( + r'data-src-type="mp4" data-src="([^"]+)"', webpage, 'video URL') + title = self._html_search_regex( + r'<title>(.*?) - Golden Moustache</title>', webpage, 'title') + thumbnail = self._og_search_thumbnail(webpage) + description = self._og_search_description(webpage) view_count = int_or_none(self._html_search_regex( - r'<strong>(\d+)</strong>\s*VUES</span>', webpage, 'view count', fatal=False)) + r'<strong>([0-9]+)</strong>\s*VUES</span>', + webpage, 'view count', fatal=False)) return { 'id': video_id, |