_ Git - youtube-dl/blob - youtube_dl/extractor/expotv.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     int_or_none,
   8     unified_strdate,
   9 )
  10
  11
  12 class ExpoTVIE(InfoExtractor):
  13     _VALID_URL = r'https?://www\.expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])'
  14     _TEST = {
  15         'url': 'http://www.expotv.com/videos/reviews/1/24/LinneCardscom/17561',
  16         'md5': '2985e6d7a392b2f7a05e0ca350fe41d0',
  17         'info_dict': {
  18             'id': '17561',
  19             'ext': 'mp4',
  20             'upload_date': '20060212',
  21             'title': 'My Favorite Online Scrapbook Store',
  22             'view_count': int,
  23             'description': 'You\'ll find most everything you need at this virtual store front.',
  24             'uploader': 'Anna T.',
  25             'thumbnail': 're:^https?://.*\.jpg$',
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         mobj = re.match(self._VALID_URL, url)
  31         video_id = mobj.group('id')
  32
  33         webpage = self._download_webpage(url, video_id)
  34         player_key = self._search_regex(
  35             r'<param name="playerKey" value="([^"]+)"', webpage, 'player key')
  36         config = self._download_json(
  37                 'http://client.expotv.com/video/config/%s/%s' % (video_id, player_key),
  38                 video_id,
  39                 note='Downloading video configuration')
  40
  41         formats = []
  42         for fcfg in config['sources']:
  43             if fcfg['type'] == 'm3u8':
  44                 formats.extend(self._extract_m3u8_formats(fcfg['file'], video_id))
  45             else:
  46                 formats.append({
  47                     'url': fcfg['file'],
  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]+)&', fcfg['file'],
  52                         'file extension', default=None),
  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))
  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         }