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]+)(?:$|[?#/])' _TESTS = [{ 'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version', 'md5': 'bcd81e0c4f26189ee09be362ad6e6ba9', 'info_dict': { 'id': '0732f586d7', 'ext': 'mp4', 'title': 'Heart-Shaped Box: Literal Video Version', 'description': 'md5:ea09a01bc9a1c46d9ab696c01747c338', 'thumbnail': 're:^http:.*\.jpg$', }, }, { 'url': 'http://www.funnyordie.com/embed/e402820827', 'md5': '29f4c5e5a61ca39dfd7e8348a75d0aad', '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$', }, }] 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'