Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tvplayer.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_HTTPError
   6 from ..utils import (
   7     extract_attributes,
   8     urlencode_postdata,
   9     ExtractorError,
  10 )
  11
  12
  13 class TVPlayerIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?tvplayer\.com/watch/(?P<id>[^/?#]+)'
  15     _TEST = {
  16         'url': 'http://tvplayer.com/watch/bbcone',
  17         'info_dict': {
  18             'id': '89',
  19             'ext': 'mp4',
  20             'title': r're:^BBC One [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  21         },
  22         'params': {
  23             # m3u8 download
  24             'skip_download': True,
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         display_id = self._match_id(url)
  30         webpage = self._download_webpage(url, display_id)
  31
  32         current_channel = extract_attributes(self._search_regex(
  33             r'(<div[^>]+class="[^"]*current-channel[^"]*"[^>]*>)',
  34             webpage, 'channel element'))
  35         title = current_channel['data-name']
  36
  37         resource_id = self._search_regex(
  38             r'resourceId\s*=\s*"(\d+)"', webpage, 'resource id')
  39         platform = self._search_regex(
  40             r'platform\s*=\s*"([^"]+)"', webpage, 'platform')
  41         token = self._search_regex(
  42             r'token\s*=\s*"([^"]+)"', webpage, 'token', default='null')
  43         validate = self._search_regex(
  44             r'validate\s*=\s*"([^"]+)"', webpage, 'validate', default='null')
  45
  46         try:
  47             response = self._download_json(
  48                 'http://api.tvplayer.com/api/v2/stream/live',
  49                 resource_id, headers={
  50                     'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
  51                 }, data=urlencode_postdata({
  52                     'service': 1,
  53                     'platform': platform,
  54                     'id': resource_id,
  55                     'token': token,
  56                     'validate': validate,
  57                 }))['tvplayer']['response']
  58         except ExtractorError as e:
  59             if isinstance(e.cause, compat_HTTPError):
  60                 response = self._parse_json(
  61                     e.cause.read().decode(), resource_id)['tvplayer']['response']
  62                 raise ExtractorError(
  63                     '%s said: %s' % (self.IE_NAME, response['error']), expected=True)
  64             raise
  65
  66         formats = self._extract_m3u8_formats(response['stream'], resource_id, 'mp4')
  67         self._sort_formats(formats)
  68
  69         return {
  70             'id': resource_id,
  71             'display_id': display_id,
  72             'title': self._live_title(title),
  73             'formats': formats,
  74             'is_live': True,
  75         }