X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ffunnyordie.py;h=f85e7de1496b07848e19b491b7ef5312652a0d7c;hb=4c76aa06665621c7689938afd7bbdbc797b5c7ea;hp=f2928b5fecb68df5429a90ca079faac6faf93bb2;hpb=6334794f2a8cc289bbb1e23c493fddcc7e488b00;p=youtube-dl diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py index f2928b5fe..f85e7de14 100644 --- a/youtube_dl/extractor/funnyordie.py +++ b/youtube_dl/extractor/funnyordie.py @@ -1,10 +1,14 @@ from __future__ import unicode_literals -import json import re from .common import InfoExtractor -from ..utils import ExtractorError +from ..utils import ( + ExtractorError, + float_or_none, + int_or_none, + unified_timestamp, +) class FunnyOrDieIE(InfoExtractor): @@ -17,7 +21,11 @@ class FunnyOrDieIE(InfoExtractor): 'ext': 'mp4', 'title': 'Heart-Shaped Box: Literal Video Version', 'description': 'md5:ea09a01bc9a1c46d9ab696c01747c338', - 'thumbnail': 're:^http:.*\.jpg$', + 'thumbnail': r're:^http:.*\.jpg$', + 'uploader': 'DASjr', + 'timestamp': 1317904928, + 'upload_date': '20111006', + 'duration': 318.3, }, }, { 'url': 'http://www.funnyordie.com/embed/e402820827', @@ -26,7 +34,9 @@ class FunnyOrDieIE(InfoExtractor): 'ext': 'mp4', 'title': 'Please Use This Song (Jon Lajoie)', 'description': 'Please use this to sell something. www.jonlajoie.com', - 'thumbnail': 're:^http:.*\.jpg$', + 'thumbnail': r're:^http:.*\.jpg$', + 'timestamp': 1398988800, + 'upload_date': '20140502', }, 'params': { 'skip_download': True, @@ -58,8 +68,7 @@ class FunnyOrDieIE(InfoExtractor): m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) source_formats = list(filter( - lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple', - m3u8_formats)) + lambda f: f.get('vcodec') != 'none', m3u8_formats)) bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)(?=[,/])', m3u8_url)] bitrates.sort() @@ -101,15 +110,53 @@ class FunnyOrDieIE(InfoExtractor): 'url': 'http://www.funnyordie.com%s' % src, }] - post_json = self._search_regex( - r'fb_post\s*=\s*(\{.*?\});', webpage, 'post details') - post = json.loads(post_json) + timestamp = unified_timestamp(self._html_search_meta( + 'uploadDate', webpage, 'timestamp', default=None)) + + uploader = self._html_search_regex( + r']+\bclass=["\']channel-preview-name[^>]+>(.+?)