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     determine_ext,
   9     int_or_none,
  10     js_to_json,
  11     merge_dicts,
  12 )
  13
  14
  15 class SportBoxIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:news\.sportbox|matchtv)\.ru/vdl/player(?:/[^/]+/|\?.*?\bn?id=)(?P<id>\d+)'
  17     _TESTS = [{
  18         'url': 'http://news.sportbox.ru/vdl/player/ci/211355',
  19         'info_dict': {
  20             'id': '109158',
  21             'ext': 'mp4',
  22             'title': 'В Новороссийске прошел детский турнир «Поле славы боевой»',
  23             'description': 'В Новороссийске прошел детский турнир «Поле славы боевой»',
  24             'thumbnail': r're:^https?://.*\.jpg$',
  25             'duration': 292,
  26             'view_count': int,
  27             'timestamp': 1426237001,
  28             'upload_date': '20150313',
  29         },
  30         'params': {
  31             # m3u8 download
  32             'skip_download': True,
  33         },
  34     }, {
  35         'url': 'http://news.sportbox.ru/vdl/player?nid=370908&only_player=1&autostart=false&playeri=2&height=340&width=580',
  36         'only_matching': True,
  37     }, {
  38         'url': 'https://news.sportbox.ru/vdl/player/media/193095',
  39         'only_matching': True,
  40     }, {
  41         'url': 'https://news.sportbox.ru/vdl/player/media/109158',
  42         'only_matching': True,
  43     }, {
  44         'url': 'https://matchtv.ru/vdl/player/media/109158',
  45         'only_matching': True,
  46     }]
  47
  48     @staticmethod
  49     def _extract_urls(webpage):
  50         return re.findall(
  51             r'<iframe[^>]+src="(https?://(?:news\.sportbox|matchtv)\.ru/vdl/player[^"]+)"',
  52             webpage)
  53
  54     def _real_extract(self, url):
  55         video_id = self._match_id(url)
  56
  57         webpage = self._download_webpage(url, video_id)
  58
  59         sources = self._parse_json(
  60             self._search_regex(
  61                 r'(?s)playerOptions\.sources(?:WithRes)?\s*=\s*(\[.+?\])\s*;\s*\n',
  62                 webpage, 'sources'),
  63             video_id, transform_source=js_to_json)
  64
  65         formats = []
  66         for source in sources:
  67             src = source.get('src')
  68             if not src:
  69                 continue
  70             if determine_ext(src) == 'm3u8':
  71                 formats.extend(self._extract_m3u8_formats(
  72                     src, video_id, 'mp4', entry_protocol='m3u8_native',
  73                     m3u8_id='hls', fatal=False))
  74             else:
  75                 formats.append({
  76                     'url': src,
  77                 })
  78         self._sort_formats(formats)
  79
  80         player = self._parse_json(
  81             self._search_regex(
  82                 r'(?s)playerOptions\s*=\s*({.+?})\s*;\s*\n', webpage,
  83                 'player options', default='{}'),
  84             video_id, transform_source=js_to_json)
  85         media_id = player['mediaId']
  86
  87         info = self._search_json_ld(webpage, media_id, default={})
  88
  89         view_count = int_or_none(self._search_regex(
  90             r'Просмотров\s*:\s*(\d+)', webpage, 'view count', default=None))
  91
  92         return merge_dicts(info, {
  93             'id': media_id,
  94             'title': self._og_search_title(webpage, default=None) or media_id,
  95             'thumbnail': player.get('poster'),
  96             'duration': int_or_none(player.get('duration')),
  97             'view_count': view_count,
  98             'formats': formats,
  99         })