X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/feb5020b37d7d3ba4005a8bac6f4efece4ce4b8c..76d85602f8a22ca3817c3a86f4f0e8969c0b02a9:/youtube_dl/extractor/wimp.py diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index b9c3b13..e4f50e6 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -1,36 +1,49 @@ -import re -import base64 +from __future__ import unicode_literals from .common import InfoExtractor +from .youtube import YoutubeIE class WimpIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?wimp\.com/([^/]+)/' - _TEST = { - u'url': u'http://www.wimp.com/deerfence/', - u'file': u'deerfence.flv', - u'md5': u'8b215e2e0168c6081a1cf84b2846a2b5', - u'info_dict': { - u"title": u"Watch Till End: Herd of deer jump over a fence." + _VALID_URL = r'http://(?:www\.)?wimp\.com/(?P[^/]+)/' + _TESTS = [{ + 'url': 'http://www.wimp.com/maruexhausted/', + 'md5': 'ee21217ffd66d058e8b16be340b74883', + 'info_dict': { + 'id': 'maruexhausted', + '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) - title = self._search_regex(r'',webpage, 'video title') - thumbnail_url = self._search_regex(r'', webpage,'video thumbnail') - googleString = self._search_regex("googleCode = '(.*?)'", webpage, 'file url') - googleString = base64.b64decode(googleString).decode('ascii') - final_url = self._search_regex('","(.*?)"', googleString,'final video url') - ext = final_url.rpartition(u'.')[2] - - return [{ - 'id': video_id, - 'url': final_url, - 'ext': ext, - 'title': title, - 'thumbnail': thumbnail_url, - }] + video_url = self._search_regex( + [r"[\"']file[\"']\s*[:,]\s*[\"'](.+?)[\"']", r"videoId\s*:\s*[\"']([^\"']+)[\"']"], + webpage, 'video URL') + if YoutubeIE.suitable(video_url): + self.to_screen('Found YouTube video') + return { + '_type': 'url', + 'url': video_url, + 'ie_key': YoutubeIE.ie_key(), + } + return { + 'id': video_id, + 'url': video_url, + 'title': self._og_search_title(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + 'description': self._og_search_description(webpage), + }