youtube_dl/extractor/discovery.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     parse_duration,
   6     parse_iso8601,
   7 )
   8 from ..compat import compat_str
   9
  10
  11 class DiscoveryIE(InfoExtractor):
  12     _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9_\-]*)(?:\.htm)?'
  13     _TESTS = [{
  14         'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
  15         'info_dict': {
  16             'id': '20769',
  17             'ext': 'mp4',
  18             'title': 'Mission Impossible Outtakes',
  19             'description': ('Watch Jamie Hyneman and Adam Savage practice being'
  20                             ' each other -- to the point of confusing Jamie\'s dog -- and '
  21                             'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s'
  22                             ' back.'),
  23             'duration': 156,
  24             'timestamp': 1303099200,
  25             'upload_date': '20110418',
  26         },
  27         'params': {
  28             'skip_download': True,  # requires ffmpeg
  29         }
  30     }, {
  31         'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mythbusters-the-simpsons',
  32         'info_dict': {
  33             'id': 'mythbusters-the-simpsons',
  34             'title': 'MythBusters: The Simpsons',
  35         },
  36         'playlist_count': 9,
  37     }]
  38
  39     def _real_extract(self, url):
  40         video_id = self._match_id(url)
  41         info = self._download_json(url + '?flat=1', video_id)
  42
  43         video_title = info.get('playlist_title') or info.get('video_title')
  44
  45         entries = [{
  46             'id': compat_str(video_info['id']),
  47             'formats': self._extract_m3u8_formats(
  48                 video_info['src'], video_id, ext='mp4',
  49                 note='Download m3u8 information for video %d' % (idx + 1)),
  50             'title': video_info['title'],
  51             'description': video_info.get('description'),
  52             'duration': parse_duration(video_info.get('video_length')),
  53             'webpage_url': video_info.get('href'),
  54             'thumbnail': video_info.get('thumbnailURL'),
  55             'alt_title': video_info.get('secondary_title'),
  56             'timestamp': parse_iso8601(video_info.get('publishedDate')),
  57         } for idx, video_info in enumerate(info['playlist'])]
  58
  59         return self.playlist_result(entries, video_id, video_title)