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 (
   8     parse_duration,
   9     parse_iso8601,
  10 )
  11
  12
  13 class SportBoxIE(InfoExtractor):
  14     _VALID_URL = r'https?://news\.sportbox\.ru/Vidy_sporta/(?:[^/]+/)+spbvideo_NI\d+_(?P<display_id>.+)'
  15     _TESTS = [
  16         {
  17             'url': 'http://news.sportbox.ru/Vidy_sporta/Avtosport/Rossijskij/spbvideo_NI483529_Gonka-2-zaezd-Obyedinenniy-2000-klassi-Turing-i-S',
  18             'md5': 'ff56a598c2cf411a9a38a69709e97079',
  19             'info_dict': {
  20                 'id': '80822',
  21                 'ext': 'mp4',
  22                 'title': 'Гонка 2  заезд ««Объединенный 2000»: классы Туринг и Супер-продакшн',
  23                 'description': 'md5:81715fa9c4ea3d9e7915dc8180c778ed',
  24                 'thumbnail': 're:^https?://.*\.jpg$',
  25                 'timestamp': 1411896237,
  26                 'upload_date': '20140928',
  27                 'duration': 4846,
  28             },
  29             'params': {
  30                 # m3u8 download
  31                 'skip_download': True,
  32             },
  33         }, {
  34             'url': 'http://news.sportbox.ru/Vidy_sporta/billiard/spbvideo_NI486287_CHempionat-mira-po-dinamichnoy-piramide-4',
  35             'only_matching': True,
  36         }
  37     ]
  38
  39     def _real_extract(self, url):
  40         mobj = re.match(self._VALID_URL, url)
  41         display_id = mobj.group('display_id')
  42
  43         webpage = self._download_webpage(url, display_id)
  44
  45         video_id = self._search_regex(
  46             r'src="/vdl/player/media/(\d+)"', webpage, 'video id')
  47
  48         player = self._download_webpage(
  49             'http://news.sportbox.ru/vdl/player/media/%s' % video_id,
  50             display_id, 'Downloading player webpage')
  51
  52         hls = self._search_regex(
  53             r"var\s+original_hls_file\s*=\s*'([^']+)'", player, 'hls file')
  54
  55         formats = self._extract_m3u8_formats(hls, display_id, 'mp4')
  56
  57         title = self._html_search_regex(
  58             r'<h1 itemprop="name">([^<]+)</h1>', webpage, 'title')
  59         description = self._html_search_regex(
  60             r'(?s)<div itemprop="description">(.+?)</div>', webpage, 'description', fatal=False)
  61         thumbnail = self._og_search_thumbnail(webpage)
  62         timestamp = parse_iso8601(self._search_regex(
  63             r'<span itemprop="uploadDate">([^<]+)</span>', webpage, 'timestamp', fatal=False))
  64         duration = parse_duration(self._html_search_regex(
  65             r'<meta itemprop="duration" content="PT([^"]+)">', webpage, 'duration', fatal=False))
  66
  67         return {
  68             'id': video_id,
  69             'display_id': display_id,
  70             'title': title,
  71             'description': description,
  72             'thumbnail': thumbnail,
  73             'timestamp': timestamp,
  74             'duration': duration,
  75             'formats': formats,
  76         }