from __future__ import unicode_literals import json import re from .common import InfoExtractor from ..utils import ExtractorError class FunnyOrDieIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?Pembed|articles|videos)/(?P[0-9a-f]+)(?:$|[?#/])' _TESTS = [{ 'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version', 'md5': 'c26b9ee0e1ca138c12071f59572ba9c7', 'info_dict': { 'id': '0732f586d7', 'ext': 'mp4', 'title': 'Heart-Shaped Box: Literal Video Version', 'description': 'md5:ea09a01bc9a1c46d9ab696c01747c338', 'thumbnail': 're:^http:.*\.jpg$', }, }, { 'url': 'http://www.funnyordie.com/embed/e402820827', 'info_dict': { 'id': 'e402820827', 'ext': 'mp4', 'title': 'Please Use This Song (Jon Lajoie)', '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): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) links = re.findall(r']+src=(["\'])(?P.+?/master\.m3u8[^"\']*)\1', webpage, 'm3u8 url', group='url') formats = [] 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, }) self._check_formats(formats, video_id) formats.extend(self._extract_m3u8_formats( m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) subtitles = {} for src, src_lang in re.findall(r'