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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from .youtube import YoutubeIE
   7
   8
   9 class WimpIE(InfoExtractor):
  10     _VALID_URL = r'http://(?:www\.)?wimp\.com/([^/]+)/'
  11     _TESTS = [{
  12         'url': 'http://www.wimp.com/maruexhausted/',
  13         'md5': 'f1acced123ecb28d9bb79f2479f2b6a1',
  14         'info_dict': {
  15             'id': 'maruexhausted',
  16             'ext': 'flv',
  17             'title': 'Maru is exhausted.',
  18             'description': 'md5:57e099e857c0a4ea312542b684a869b8',
  19         }
  20     }, {
  21         # youtube video
  22         'url': 'http://www.wimp.com/clowncar/',
  23         'info_dict': {
  24             'id': 'cG4CEr2aiSg',
  25             'ext': 'mp4',
  26             'title': 'Basset hound clown car...incredible!',
  27             'description': 'md5:8d228485e0719898c017203f900b3a35',
  28             'uploader': 'Gretchen Hoey',
  29             'uploader_id': 'gretchenandjeff1',
  30             'upload_date': '20140303',
  31         },
  32         'add_ie': ['Youtube'],
  33     }]
  34
  35     def _real_extract(self, url):
  36         mobj = re.match(self._VALID_URL, url)
  37         video_id = mobj.group(1)
  38         webpage = self._download_webpage(url, video_id)
  39         video_url = self._search_regex(
  40             [r"[\"']file[\"']\s*[:,]\s*[\"'](.+?)[\"']", r"videoId\s*:\s*[\"']([^\"']+)[\"']"],
  41             webpage, 'video URL')
  42         if YoutubeIE.suitable(video_url):
  43             self.to_screen('Found YouTube video')
  44             return {
  45                 '_type': 'url',
  46                 'url': video_url,
  47                 'ie_key': YoutubeIE.ie_key(),
  48             }
  49
  50         return {
  51             'id': video_id,
  52             'url': video_url,
  53             'title': self._og_search_title(webpage),
  54             'thumbnail': self._og_search_thumbnail(webpage),
  55             'description': self._og_search_description(webpage),
  56         }