X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fgoldenmoustache.py;h=0fb5097244a6218afca0a0908448127f74073b77;hb=1058f56e96316e778ed74ad008949c634a582e84;hp=c25d2e779878410b57d4c3d149652b22f12e454a;hpb=b868c972d1c1bc7978e4afee51da3322abb6cc6d;p=youtube-dl diff --git a/youtube_dl/extractor/goldenmoustache.py b/youtube_dl/extractor/goldenmoustache.py index c25d2e779..0fb509724 100644 --- a/youtube_dl/extractor/goldenmoustache.py +++ b/youtube_dl/extractor/goldenmoustache.py @@ -1,16 +1,11 @@ from __future__ import unicode_literals -import re from .common import InfoExtractor -from ..utils import ( - parse_duration, - int_or_none, -) class GoldenMoustacheIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?goldenmoustache\.com/(?P[\w-]+)-(?P\d+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.goldenmoustache.com/suricate-le-poker-3700/', 'md5': '0f904432fa07da5054d6c8beb5efb51a', 'info_dict': { @@ -18,26 +13,30 @@ class GoldenMoustacheIE(InfoExtractor): 'ext': 'mp4', 'title': 'Suricate - Le Poker', 'description': 'md5:3d1f242f44f8c8cb0a106f1fd08e5dc9', - 'thumbnail': 'md5:fd41386bc1f932552622da4a7e9a7242', + 'thumbnail': 're:^https?://.*\.jpg$', } - } + }, { + 'url': 'http://www.goldenmoustache.com/le-lab-tout-effacer-mc-fly-et-carlito-55249/', + 'md5': '27f0c50fb4dd5f01dc9082fc67cd5700', + 'info_dict': { + 'id': '55249', + 'ext': 'mp4', + 'title': 'Le LAB - Tout Effacer (Mc Fly et Carlito)', + 'description': 'md5:9b7fbf11023fb2250bd4b185e3de3b2a', + 'thumbnail': 're:^https?://.*\.(?:png|jpg)$', + } + }] 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'(.*?) - Golden Moustache', webpage, 'title') - - thumbnail = self._html_search_meta('og:image', webpage, 'thumbnail') - - description = self._html_search_meta('og:description', webpage, 'description') - - view_count = int_or_none(self._html_search_regex( - r'(\d+)\s*VUES', webpage, 'view count', fatal=False)) + video_url = self._html_search_regex( + r'data-src-type="mp4" data-src="([^"]+)"', webpage, 'video URL') + title = self._html_search_regex( + r'(.*?)(?: - Golden Moustache)?', webpage, 'title') + thumbnail = self._og_search_thumbnail(webpage) + description = self._og_search_description(webpage) return { 'id': video_id, @@ -46,5 +45,4 @@ class GoldenMoustacheIE(InfoExtractor): 'title': title, 'description': description, 'thumbnail': thumbnail, - 'view_count': view_count, }