yt_dlp/extractor/pyvideo.py

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