X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ffunnyordie.py;h=56e079288d7c19a24c8bceead6675ac1be1ed415;hb=1ff7c0f7d804dedb9186490f2d61c773e62650c5;hp=4508f0dfac29a85d86533c2f781414b9b17d10cb;hpb=8d212e604a86da3c924ab15fe8045ab748a8183d;p=youtube-dl diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py index 4508f0dfa..56e079288 100644 --- a/youtube_dl/extractor/funnyordie.py +++ b/youtube_dl/extractor/funnyordie.py @@ -1,18 +1,24 @@ +from __future__ import unicode_literals + +import json import re from .common import InfoExtractor class FunnyOrDieIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P[0-9a-f]+)/.*$' + _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?Pembed|videos)/(?P[0-9a-f]+)(?:$|[?#/])' _TEST = { - u'url': u'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version', - u'file': u'0732f586d7.mp4', - u'md5': u'f647e9e90064b53b6e046e75d0241fbd', - u'info_dict': { - u"description": u"Lyrics changed to match the video. Spoken cameo by Obscurus Lupa (from ThatGuyWithTheGlasses.com). Based on a concept by Dustin McLean (DustFilms.com). Performed, edited, and written by David A. Scott.", - u"title": u"Heart-Shaped Box: Literal Video Version" - } + 'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version', + 'file': '0732f586d7.mp4', + 'md5': 'f647e9e90064b53b6e046e75d0241fbd', + 'info_dict': { + 'description': ('Lyrics changed to match the video. Spoken cameo ' + 'by Obscurus Lupa (from ThatGuyWithTheGlasses.com). Based on a ' + 'concept by Dustin McLean (DustFilms.com). Performed, edited, ' + 'and written by David A. Scott.'), + 'title': 'Heart-Shaped Box: Literal Video Version', + }, } def _real_extract(self, url): @@ -21,14 +27,27 @@ class FunnyOrDieIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - video_url = self._search_regex(r'type: "video/mp4", src: "(.*?)"', - webpage, u'video URL', flags=re.DOTALL) + video_url = self._search_regex( + [r'type="video/mp4" src="(.*?)"', r'src="([^>]*?)" type=\'video/mp4\''], + webpage, 'video URL', flags=re.DOTALL) + + if mobj.group('type') == 'embed': + post_json = self._search_regex( + r'fb_post\s*=\s*(\{.*?\});', webpage, 'post details') + post = json.loads(post_json) + title = post['name'] + description = post.get('description') + thumbnail = post.get('picture') + else: + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = None - info = { + return { 'id': video_id, 'url': video_url, 'ext': 'mp4', - 'title': self._og_search_title(webpage), - 'description': self._og_search_description(webpage), + 'title': title, + 'description': description, + 'thumbnail': thumbnail, } - return [info]