X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fwimp.py;h=041ff6c555123d44c97bc63810d2aa7903ec069e;hb=9f0ee2a3883ec6f6fdccba90085cb925aaa2f617;hp=79fd53e0c8e85daae8efd86b70dc1302c1c0a629;hpb=da362979887b163d09d67c84c788fa16d921e4bc;p=youtube-dl diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index 79fd53e0c..041ff6c55 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -1,29 +1,49 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor +from .youtube import YoutubeIE class WimpIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?wimp\.com/([^/]+)/' - _TEST = { + _VALID_URL = r'http://(?:www\.)?wimp\.com/(?P[^/]+)' + _TESTS = [{ 'url': 'http://www.wimp.com/maruexhausted/', - 'md5': 'f1acced123ecb28d9bb79f2479f2b6a1', + 'md5': 'ee21217ffd66d058e8b16be340b74883', 'info_dict': { 'id': 'maruexhausted', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Maru is exhausted.', 'description': 'md5:57e099e857c0a4ea312542b684a869b8', } - } + }, { + 'url': 'http://www.wimp.com/clowncar/', + 'md5': '4e2986c793694b55b37cf92521d12bb4', + 'info_dict': { + 'id': 'clowncar', + 'ext': 'mp4', + 'title': 'It\'s like a clown car.', + 'description': 'md5:0e56db1370a6e49c5c1d19124c0d2fb2', + }, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + youtube_id = self._search_regex( + r"videoId\s*:\s*[\"']([0-9A-Za-z_-]{11})[\"']", + webpage, 'video URL', default=None) + if youtube_id: + return { + '_type': 'url', + 'url': youtube_id, + 'ie_key': YoutubeIE.ie_key(), + } + video_url = self._search_regex( - r's1\.addVariable\("file",\s*"([^"]+)"\);', webpage, 'video URL') + r']+>\s*]+src=(["\'])(?P.+?)\1', + webpage, 'video URL', group='url') return { 'id': video_id, @@ -31,4 +51,4 @@ class WimpIE(InfoExtractor): 'title': self._og_search_title(webpage), 'thumbnail': self._og_search_thumbnail(webpage), 'description': self._og_search_description(webpage), - } \ No newline at end of file + }