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 ..compat import compat_urlparse
   8 from ..utils import (
   9     unified_strdate,
  10 )
  11
  12
  13 class SportBoxIE(InfoExtractor):
  14     _VALID_URL = r'https?://news\.sportbox\.ru/(?:[^/]+/)+spbvideo_NI\d+_(?P<display_id>.+)'
  15     _TESTS = [{
  16         'url': 'http://news.sportbox.ru/Vidy_sporta/Avtosport/Rossijskij/spbvideo_NI483529_Gonka-2-zaezd-Obyedinenniy-2000-klassi-Turing-i-S',
  17         'md5': 'ff56a598c2cf411a9a38a69709e97079',
  18         'info_dict': {
  19             'id': '80822',
  20             'ext': 'mp4',
  21             'title': 'Гонка 2  заезд ««Объединенный 2000»: классы Туринг и Супер-продакшн',
  22             'description': 'md5:3d72dc4a006ab6805d82f037fdc637ad',
  23             'thumbnail': 're:^https?://.*\.jpg$',
  24             'upload_date': '20140928',
  25         },
  26         'params': {
  27             # m3u8 download
  28             'skip_download': True,
  29         },
  30     }, {
  31         'url': 'http://news.sportbox.ru/Vidy_sporta/billiard/spbvideo_NI486287_CHempionat-mira-po-dinamichnoy-piramide-4',
  32         'only_matching': True,
  33     }, {
  34         'url': 'http://news.sportbox.ru/video/no_ads/spbvideo_NI536574_V_Novorossijske_proshel_detskij_turnir_Pole_slavy_bojevoj?ci=211355',
  35         'only_matching': True,
  36     }]
  37
  38     def _real_extract(self, url):
  39         mobj = re.match(self._VALID_URL, url)
  40         display_id = mobj.group('display_id')
  41
  42         webpage = self._download_webpage(url, display_id)
  43
  44         player = self._search_regex(
  45             r'src="/?(vdl/player/[^"]+)"', webpage, 'player')
  46
  47         title = self._html_search_regex(
  48             [r'"nodetitle"\s*:\s*"([^"]+)"', r'class="node-header_{1,2}title">([^<]+)'],
  49             webpage, 'title')
  50         description = self._og_search_description(webpage) or self._html_search_meta(
  51             'description', webpage, 'description')
  52         thumbnail = self._og_search_thumbnail(webpage)
  53         upload_date = unified_strdate(self._html_search_meta(
  54             'dateCreated', webpage, 'upload date'))
  55
  56         return {
  57             '_type': 'url_transparent',
  58             'url': compat_urlparse.urljoin(url, '/%s' % player),
  59             'display_id': display_id,
  60             'title': title,
  61             'description': description,
  62             'thumbnail': thumbnail,
  63             'upload_date': upload_date,
  64         }
  65
  66
  67 class SportBoxEmbedIE(InfoExtractor):
  68     _VALID_URL = r'https?://news\.sportbox\.ru/vdl/player(?:/[^/]+/|\?.*?\bn?id=)(?P<id>\d+)'
  69     _TESTS = [{
  70         'url': 'http://news.sportbox.ru/vdl/player/ci/211355',
  71         'info_dict': {
  72             'id': '211355',
  73             'ext': 'mp4',
  74             'title': 'В Новороссийске прошел детский турнир «Поле славы боевой»',
  75             'thumbnail': 're:^https?://.*\.jpg$',
  76         },
  77         'params': {
  78             # m3u8 download
  79             'skip_download': True,
  80         },
  81     }, {
  82         'url': 'http://news.sportbox.ru/vdl/player?nid=370908&only_player=1&autostart=false&playeri=2&height=340&width=580',
  83         'only_matching': True,
  84     }]
  85
  86     @staticmethod
  87     def _extract_urls(webpage):
  88         return re.findall(
  89             r'<iframe[^>]+src="(https?://news\.sportbox\.ru/vdl/player[^"]+)"',
  90             webpage)
  91
  92     def _real_extract(self, url):
  93         video_id = self._match_id(url)
  94
  95         webpage = self._download_webpage(url, video_id)
  96
  97         hls = self._search_regex(
  98             r"sportboxPlayer\.jwplayer_common_params\.file\s*=\s*['\"]([^'\"]+)['\"]",
  99             webpage, 'hls file')
 100
 101         formats = self._extract_m3u8_formats(hls, video_id, 'mp4')
 102
 103         title = self._search_regex(
 104             r'sportboxPlayer\.node_title\s*=\s*"([^"]+)"', webpage, 'title')
 105
 106         thumbnail = self._search_regex(
 107             r'sportboxPlayer\.jwplayer_common_params\.image\s*=\s*"([^"]+)"',
 108             webpage, 'thumbnail', default=None)
 109
 110         return {
 111             'id': video_id,
 112             'title': title,
 113             'thumbnail': thumbnail,
 114             'formats': formats,
 115         }