yt_dlp/extractor/expotv.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     unified_strdate,
   5 )
   6
   7
   8 class ExpoTVIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])'
  10     _TEST = {
  11         'url': 'http://www.expotv.com/videos/reviews/3/40/NYX-Butter-lipstick/667916',
  12         'md5': 'fe1d728c3a813ff78f595bc8b7a707a8',
  13         'info_dict': {
  14             'id': '667916',
  15             'ext': 'mp4',
  16             'title': 'NYX Butter Lipstick Little Susie',
  17             'description': 'Goes on like butter, but looks better!',
  18             'thumbnail': r're:^https?://.*\.jpg$',
  19             'uploader': 'Stephanie S.',
  20             'upload_date': '20150520',
  21             'view_count': int,
  22         }
  23     }
  24
  25     def _real_extract(self, url):
  26         video_id = self._match_id(url)
  27
  28         webpage = self._download_webpage(url, video_id)
  29         player_key = self._search_regex(
  30             r'<param name="playerKey" value="([^"]+)"', webpage, 'player key')
  31         config = self._download_json(
  32             'http://client.expotv.com/video/config/%s/%s' % (video_id, player_key),
  33             video_id, 'Downloading video configuration')
  34
  35         formats = []
  36         for fcfg in config['sources']:
  37             media_url = fcfg.get('file')
  38             if not media_url:
  39                 continue
  40             if fcfg.get('type') == 'm3u8':
  41                 formats.extend(self._extract_m3u8_formats(
  42                     media_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls'))
  43             else:
  44                 formats.append({
  45                     'url': media_url,
  46                     'height': int_or_none(fcfg.get('height')),
  47                     'format_id': fcfg.get('label'),
  48                     'ext': self._search_regex(
  49                         r'filename=.*\.([a-z0-9_A-Z]+)&', media_url,
  50                         'file extension', default=None) or fcfg.get('type'),
  51                 })
  52
  53         title = self._og_search_title(webpage)
  54         description = self._og_search_description(webpage)
  55         thumbnail = config.get('image')
  56         view_count = int_or_none(self._search_regex(
  57             r'<h5>Plays: ([0-9]+)</h5>', webpage, 'view counts'))
  58         uploader = self._search_regex(
  59             r'<div class="reviewer">\s*<img alt="([^"]+)"', webpage, 'uploader',
  60             fatal=False)
  61         upload_date = unified_strdate(self._search_regex(
  62             r'<h5>Reviewed on ([0-9/.]+)</h5>', webpage, 'upload date',
  63             fatal=False), day_first=False)
  64
  65         return {
  66             'id': video_id,
  67             'formats': formats,
  68             'title': title,
  69             'description': description,
  70             'view_count': view_count,
  71             'thumbnail': thumbnail,
  72             'uploader': uploader,
  73             'upload_date': upload_date,
  74         }