youtube_dl/extractor/howstuffworks.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class HowStuffWorksIE(InfoExtractor):
   7     _VALID_URL = r'https?://[\da-z-]+\.howstuffworks\.com/(?:[^/]+/)*\d+-(?P<id>.+?)-video\.htm'
   8     _TESTS = [
   9         {
  10             'url': 'http://adventure.howstuffworks.com/39521-deadliest-catch-nautical-collision-video.htm',
  11             'info_dict': {
  12                 'id': '553475',
  13                 'ext': 'mp4',
  14                 'title': 'Deadliest Catch: Nautical Collision',
  15                 'description': 'Check out this clip to get an exclusive look at the Deadliest Catch crew back in action.',
  16                 'thumbnail': 'http://s.hswstatic.com/gif/videos/480x360/39521.jpg',
  17             },
  18         },
  19         {
  20             'url': 'http://adventure.howstuffworks.com/7199-survival-zone-food-and-water-in-the-savanna-video.htm',
  21             'info_dict': {
  22                 'id': '453464',
  23                 'ext': 'mp4',
  24                 'title': 'Survival Zone: Food and Water In the Savanna',
  25                 'description': 'Learn how to find both food and water while trekking in the African savannah. In this video from the Discovery Channel.',
  26                 'thumbnail': 'http://s.hswstatic.com/gif/videos/480x360/7199.jpg',
  27             },
  28         },
  29         {
  30             'url': 'http://entertainment.howstuffworks.com/arts/34476-time-warp-fire-breathing-disaster-video.htm',
  31             'info_dict': {
  32                 'id': '487036',
  33                 'ext': 'mp4',
  34                 'title': 'Time Warp: Fire-Breathing Disaster',
  35                 'description': 'Fire-breathers are safe from flames when they angle their heads up as they blow -- see what would happen if they looked down instead. Check out this clip from Discovery\'s "Time Warp" series to learn more.',
  36                 'thumbnail': 'http://s.hswstatic.com/gif/videos/480x360/34476.jpg',
  37             },
  38         },
  39     ]
  40
  41     def _extract_clip_info(self, key, clip_info, name=None, **kargs):
  42         if name is None:
  43             name = key
  44         return self._html_search_regex(
  45             r"\s*%s\s*: '?([^'\n]*[^'\n,])" % key, clip_info, name, **kargs)
  46
  47     def _real_extract(self, url):
  48         display_id = self._match_id(url)
  49         webpage = self._download_webpage(url, display_id)
  50         clip_info = self._search_regex('(?s)var clip = {(.*?)};', webpage, 'clip info')
  51         video_id = self._extract_clip_info('content_id', clip_info, 'video id')
  52         formats = []
  53         m3u8_url = self._extract_clip_info('m3u8', clip_info, 'm3u8 url', default=None)
  54         if m3u8_url is not None:
  55             formats += self._extract_m3u8_formats(m3u8_url , video_id, 'mp4')
  56         mp4 = self._parse_json(
  57             self._extract_clip_info(
  58                 'mp4', clip_info, 'formats').replace('},]','}]'), video_id)
  59         for video in mp4:
  60             formats.append({
  61                 'url': video['src'],
  62                 'format_id': video['bitrate'],
  63                 'tbr': int(video['bitrate'].rstrip('k')),
  64             })
  65         self._sort_formats(formats)
  66
  67         return {
  68             'id': video_id,
  69             'display_id': display_id,
  70             'title': self._extract_clip_info('clip_title', clip_info, 'title'),
  71             'description': self._extract_clip_info('caption', clip_info, 'description', fatal=False),
  72             'thumbnail': self._extract_clip_info('video_still_url', clip_info, 'thumbnail'),
  73             'duration': self._extract_clip_info('duration', clip_info),
  74             'formats': formats,
  75         }