youtube_dl/extractor/expotv.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6     unified_strdate,
   7 )
   8
   9
  10 class ExpoTVIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])'
  12     _TEST = {
  13         'url': 'http://www.expotv.com/videos/reviews/3/40/NYX-Butter-lipstick/667916',
  14         'md5': 'fe1d728c3a813ff78f595bc8b7a707a8',
  15         'info_dict': {
  16             'id': '667916',
  17             'ext': 'mp4',
  18             'title': 'NYX Butter Lipstick Little Susie',
  19             'description': 'Goes on like butter, but looks better!',
  20             'thumbnail': r're:^https?://.*\.jpg$',
  21             'uploader': 'Stephanie S.',
  22             'upload_date': '20150520',
  23             'view_count': int,
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29
  30         webpage = self._download_webpage(url, video_id)
  31         player_key = self._search_regex(
  32             r'<param name="playerKey" value="([^"]+)"', webpage, 'player key')
  33         config = self._download_json(
  34             'http://client.expotv.com/video/config/%s/%s' % (video_id, player_key),
  35             video_id, 'Downloading video configuration')
  36
  37         formats = []
  38         for fcfg in config['sources']:
  39             media_url = fcfg.get('file')
  40             if not media_url:
  41                 continue
  42             if fcfg.get('type') == 'm3u8':
  43                 formats.extend(self._extract_m3u8_formats(
  44                     media_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls'))
  45             else:
  46                 formats.append({
  47                     'url': media_url,
  48                     'height': int_or_none(fcfg.get('height')),
  49                     'format_id': fcfg.get('label'),
  50                     'ext': self._search_regex(
  51                         r'filename=.*\.([a-z0-9_A-Z]+)&', media_url,
  52                         'file extension', default=None) or fcfg.get('type'),
  53                 })
  54         self._sort_formats(formats)
  55
  56         title = self._og_search_title(webpage)
  57         description = self._og_search_description(webpage)
  58         thumbnail = config.get('image')
  59         view_count = int_or_none(self._search_regex(
  60             r'<h5>Plays: ([0-9]+)</h5>', webpage, 'view counts'))
  61         uploader = self._search_regex(
  62             r'<div class="reviewer">\s*<img alt="([^"]+)"', webpage, 'uploader',
  63             fatal=False)
  64         upload_date = unified_strdate(self._search_regex(
  65             r'<h5>Reviewed on ([0-9/.]+)</h5>', webpage, 'upload date',
  66             fatal=False), day_first=False)
  67
  68         return {
  69             'id': video_id,
  70             'formats': formats,
  71             'title': title,
  72             'description': description,
  73             'view_count': view_count,
  74             'thumbnail': thumbnail,
  75             'uploader': uploader,
  76             'upload_date': upload_date,
  77         }