X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ffunnyordie.py;h=8c5ffc9e84cec305e9fc813a6366b360b7e36230;hb=d6712378e73951bede475569c887a1ac73f660a9;hp=1b93c104fd0847d8580ec89f974241e83c40c1f7;hpb=aab8874c55803a12be3299fe4ba890c2de264d68;p=youtube-dl diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py index 1b93c104f..8c5ffc9e8 100644 --- a/youtube_dl/extractor/funnyordie.py +++ b/youtube_dl/extractor/funnyordie.py @@ -4,13 +4,14 @@ import json import re from .common import InfoExtractor +from ..utils import ExtractorError class FunnyOrDieIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?Pembed|videos)/(?P[0-9a-f]+)(?:$|[?#/])' + _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?Pembed|articles|videos)/(?P[0-9a-f]+)(?:$|[?#/])' _TESTS = [{ 'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version', - 'md5': 'f647e9e90064b53b6e046e75d0241fbd', + 'md5': 'bcd81e0c4f26189ee09be362ad6e6ba9', 'info_dict': { 'id': '0732f586d7', 'ext': 'mp4', @@ -20,14 +21,16 @@ class FunnyOrDieIE(InfoExtractor): }, }, { 'url': 'http://www.funnyordie.com/embed/e402820827', - 'md5': '0e0c5a7bf45c52b95cd16aa7f28be0b6', 'info_dict': { 'id': 'e402820827', 'ext': 'mp4', 'title': 'Please Use This Song (Jon Lajoie)', - 'description': 'md5:2ed27d364f5a805a6dba199faaf6681d', + 'description': 'Please use this to sell something. www.jonlajoie.com', 'thumbnail': 're:^http:.*\.jpg$', }, + }, { + 'url': 'http://www.funnyordie.com/articles/ebf5e34fc8/10-hours-of-walking-in-nyc-as-a-man', + 'only_matching': True, }] def _real_extract(self, url): @@ -36,23 +39,48 @@ 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="(.*?)"', r'src="([^>]*?)" type=\'video/mp4\''], - webpage, 'video URL', flags=re.DOTALL) + links = re.findall(r']+src=(["\'])(?P.+?/master\.m3u8[^"\']*)\1', + webpage, 'm3u8 url', group='url') + + formats = [] + + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) + + bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)[,/]', m3u8_url)] + bitrates.sort() + + for bitrate in bitrates: + for link in links: + formats.append({ + 'url': self._proto_relative_url('%s%d.%s' % (link[0], bitrate, link[1])), + 'format_id': '%s-%d' % (link[1], bitrate), + 'vbr': bitrate, + }) + + subtitles = {} + for src, src_lang in re.findall(r'