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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import js_to_json
   8
   9
  10 class SportBoxEmbedIE(InfoExtractor):
  11     _VALID_URL = r'https?://news\.sportbox\.ru/vdl/player(?:/[^/]+/|\?.*?\bn?id=)(?P<id>\d+)'
  12     _TESTS = [{
  13         'url': 'http://news.sportbox.ru/vdl/player/ci/211355',
  14         'info_dict': {
  15             'id': '211355',
  16             'ext': 'mp4',
  17             'title': 'В Новороссийске прошел детский турнир «Поле славы боевой»',
  18             'thumbnail': r're:^https?://.*\.jpg$',
  19         },
  20         'params': {
  21             # m3u8 download
  22             'skip_download': True,
  23         },
  24     }, {
  25         'url': 'http://news.sportbox.ru/vdl/player?nid=370908&only_player=1&autostart=false&playeri=2&height=340&width=580',
  26         'only_matching': True,
  27     }]
  28
  29     @staticmethod
  30     def _extract_urls(webpage):
  31         return re.findall(
  32             r'<iframe[^>]+src="(https?://news\.sportbox\.ru/vdl/player[^"]+)"',
  33             webpage)
  34
  35     def _real_extract(self, url):
  36         video_id = self._match_id(url)
  37
  38         webpage = self._download_webpage(url, video_id)
  39
  40         formats = []
  41
  42         def cleanup_js(code):
  43             # desktop_advert_config contains complex Javascripts and we don't need it
  44             return js_to_json(re.sub(r'desktop_advert_config.*', '', code))
  45
  46         jwplayer_data = self._parse_json(self._search_regex(
  47             r'(?s)player\.setup\(({.+?})\);', webpage, 'jwplayer settings'), video_id,
  48             transform_source=cleanup_js)
  49
  50         hls_url = jwplayer_data.get('hls_url')
  51         if hls_url:
  52             formats.extend(self._extract_m3u8_formats(
  53                 hls_url, video_id, ext='mp4', m3u8_id='hls'))
  54
  55         rtsp_url = jwplayer_data.get('rtsp_url')
  56         if rtsp_url:
  57             formats.append({
  58                 'url': rtsp_url,
  59                 'format_id': 'rtsp',
  60             })
  61
  62         self._sort_formats(formats)
  63
  64         title = jwplayer_data['node_title']
  65         thumbnail = jwplayer_data.get('image_url')
  66
  67         return {
  68             'id': video_id,
  69             'title': title,
  70             'thumbnail': thumbnail,
  71             'formats': formats,
  72         }