X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/848723ea972c09f28787db91d8c06e98a274ab89..15b1d10671b48df598afd70e17ba21e9e64ac766:/youtube_dl/extractor/funnyordie.py?ds=sidebyside diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py index 7c40e67..a49fc11 100644 --- a/youtube_dl/extractor/funnyordie.py +++ b/youtube_dl/extractor/funnyordie.py @@ -1,24 +1,37 @@ 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/videos/(?P[0-9a-f]+)/.*$' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?Pembed|articles|videos)/(?P[0-9a-f]+)(?:$|[?#/])' + _TESTS = [{ 'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version', - 'file': '0732f586d7.mp4', - 'md5': 'f647e9e90064b53b6e046e75d0241fbd', + 'md5': 'bcd81e0c4f26189ee09be362ad6e6ba9', '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.'), + '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) @@ -26,14 +39,34 @@ 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'