yt_dlp/extractor/pyvideo.py

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