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_url = 'http://client.expotv.com/video/config/%s/%s' % (
  37             video_id, player_key)
  38         config = self._download_json(
  39             config_url, video_id,
  40             note='Downloading video configuration')
  41
  42         formats = [{
  43             'url': fcfg['file'],
  44             'height': int_or_none(fcfg.get('height')),
  45             'format_note': fcfg.get('label'),
  46             'ext': self._search_regex(
  47                 r'filename=.*\.([a-z0-9_A-Z]+)&', fcfg['file'],
  48                 'file extension', default=None),
  49         } for fcfg in config['sources']]
  50         self._sort_formats(formats)
  51
  52         title = self._og_search_title(webpage)
  53         description = self._og_search_description(webpage)
  54         thumbnail = config.get('image')
  55         view_count = int_or_none(self._search_regex(
  56             r'<h5>Plays: ([0-9]+)</h5>', webpage, 'view counts'))
  57         uploader = self._search_regex(
  58             r'<div class="reviewer">\s*<img alt="([^"]+)"', webpage, 'uploader',
  59             fatal=False)
  60         upload_date = unified_strdate(self._search_regex(
  61             r'<h5>Reviewed on ([0-9/.]+)</h5>', webpage, 'upload date',
  62             fatal=False))
  63
  64         return {
  65             'id': video_id,
  66             'formats': formats,
  67             'title': title,
  68             'description': description,
  69             'view_count': view_count,
  70             'thumbnail': thumbnail,
  71             'uploader': uploader,
  72             'upload_date': upload_date,
  73         }