Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/funnyordie.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import ExtractorError
   8
   9
  10 class FunnyOrDieIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?P<type>embed|videos)/(?P<id>[0-9a-f]+)(?:$|[?#/])'
  12     _TESTS = [{
  13         'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version',
  14         'md5': 'bcd81e0c4f26189ee09be362ad6e6ba9',
  15         'info_dict': {
  16             'id': '0732f586d7',
  17             'ext': 'mp4',
  18             'title': 'Heart-Shaped Box: Literal Video Version',
  19             'description': 'md5:ea09a01bc9a1c46d9ab696c01747c338',
  20             'thumbnail': 're:^http:.*\.jpg$',
  21         },
  22     }, {
  23         'url': 'http://www.funnyordie.com/embed/e402820827',
  24         'md5': '29f4c5e5a61ca39dfd7e8348a75d0aad',
  25         'info_dict': {
  26             'id': 'e402820827',
  27             'ext': 'mp4',
  28             'title': 'Please Use This Song (Jon Lajoie)',
  29             'description': 'Please use this to sell something.  www.jonlajoie.com',
  30             'thumbnail': 're:^http:.*\.jpg$',
  31         },
  32     }]
  33
  34     def _real_extract(self, url):
  35         mobj = re.match(self._VALID_URL, url)
  36
  37         video_id = mobj.group('id')
  38         webpage = self._download_webpage(url, video_id)
  39
  40         links = re.findall(r'<source src="([^"]+/v)[^"]+\.([^"]+)" type=\'video', webpage)
  41         if not links:
  42             raise ExtractorError('No media links available for %s' % video_id)
  43
  44         links.sort(key=lambda link: 1 if link[1] == 'mp4' else 0)
  45
  46         bitrates = self._html_search_regex(r'<source src="[^"]+/v,((?:\d+,)+)\.mp4\.csmil', webpage, 'video bitrates')
  47         bitrates = [int(b) for b in bitrates.rstrip(',').split(',')]
  48         bitrates.sort()
  49
  50         formats = []
  51
  52         for bitrate in bitrates:
  53             for link in links:
  54                 formats.append({
  55                     'url': '%s%d.%s' % (link[0], bitrate, link[1]),
  56                     'format_id': '%s-%d' % (link[1], bitrate),
  57                     'vbr': bitrate,
  58                 })
  59
  60         post_json = self._search_regex(
  61             r'fb_post\s*=\s*(\{.*?\});', webpage, 'post details')
  62         post = json.loads(post_json)
  63
  64         return {
  65             'id': video_id,
  66             'title': post['name'],
  67             'description': post.get('description'),
  68             'thumbnail': post.get('picture'),
  69             'formats': formats,
  70         }