youtube_dl/extractor/pyvideo.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_str
   7 from ..utils import int_or_none
   8
   9
  10 class PyvideoIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?pyvideo\.org/(?P<category>[^/]+)/(?P<id>[^/?#&.]+)'
  12
  13     _TESTS = [{
  14         'url': 'http://pyvideo.org/pycon-us-2013/become-a-logging-expert-in-30-minutes.html',
  15         'info_dict': {
  16             'id': 'become-a-logging-expert-in-30-minutes',
  17         },
  18         'playlist_count': 2,
  19     }, {
  20         'url': 'http://pyvideo.org/pygotham-2012/gloriajw-spotifywitherikbernhardsson182m4v.html',
  21         'md5': '5fe1c7e0a8aa5570330784c847ff6d12',
  22         'info_dict': {
  23             'id': '2542',
  24             'ext': 'm4v',
  25             'title': 'Gloriajw-SpotifyWithErikBernhardsson182.m4v',
  26         },
  27     }]
  28
  29     def _real_extract(self, url):
  30         mobj = re.match(self._VALID_URL, url)
  31         category = mobj.group('category')
  32         video_id = mobj.group('id')
  33
  34         entries = []
  35
  36         data = self._download_json(
  37             'https://raw.githubusercontent.com/pyvideo/data/master/%s/videos/%s.json'
  38             % (category, video_id), video_id, fatal=False)
  39
  40         if data:
  41             for video in data['videos']:
  42                 video_url = video.get('url')
  43                 if video_url:
  44                     if video.get('type') == 'youtube':
  45                         entries.append(self.url_result(video_url, 'Youtube'))
  46                     else:
  47                         entries.append({
  48                             'id': compat_str(data.get('id') or video_id),
  49                             'url': video_url,
  50                             'title': data['title'],
  51                             'description': data.get('description') or data.get('summary'),
  52                             'thumbnail': data.get('thumbnail_url'),
  53                             'duration': int_or_none(data.get('duration')),
  54                         })
  55         else:
  56             webpage = self._download_webpage(url, video_id)
  57             title = self._og_search_title(webpage)
  58             media_urls = self._search_regex(
  59                 r'(?s)Media URL:(.+?)</li>', webpage, 'media urls')
  60             for m in re.finditer(
  61                     r'<a[^>]+href=(["\'])(?P<url>http.+?)\1', media_urls):
  62                 media_url = m.group('url')
  63                 if re.match(r'https?://www\.youtube\.com/watch\?v=.*', media_url):
  64                     entries.append(self.url_result(media_url, 'Youtube'))
  65                 else:
  66                     entries.append({
  67                         'id': video_id,
  68                         'url': media_url,
  69                         'title': title,
  70                     })
  71
  72         return self.playlist_result(entries, video_id)