yt_dlp/extractor/njpwworld.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     get_element_by_class,
  10     urlencode_postdata,
  11 )
  12
  13
  14 class NJPWWorldIE(InfoExtractor):
  15     _VALID_URL = r'https?://(front\.)?njpwworld\.com/p/(?P<id>[a-z0-9_]+)'
  16     IE_DESC = '新日本プロレスワールド'
  17     _NETRC_MACHINE = 'njpwworld'
  18
  19     _TESTS = [{
  20         'url': 'http://njpwworld.com/p/s_series_00155_1_9/',
  21         'info_dict': {
  22             'id': 's_series_00155_1_9',
  23             'ext': 'mp4',
  24             'title': '闘強導夢2000 2000年1月4日 東京ドーム 第9試合 ランディ・サベージ VS リック・スタイナー',
  25             'tags': list,
  26         },
  27         'params': {
  28             'skip_download': True,  # AES-encrypted m3u8
  29         },
  30         'skip': 'Requires login',
  31     }, {
  32         'url': 'https://front.njpwworld.com/p/s_series_00563_16_bs',
  33         'info_dict': {
  34             'id': 's_series_00563_16_bs',
  35             'ext': 'mp4',
  36             'title': 'WORLD TAG LEAGUE 2020 & BEST OF THE SUPER Jr.27 2020年12月6日 福岡・福岡国際センター バックステージコメント（字幕あり）',
  37             'tags': ["福岡・福岡国際センター", "バックステージコメント", "2020", "20年代"],
  38         },
  39         'params': {
  40             'skip_download': True,
  41         },
  42     }]
  43
  44     _LOGIN_URL = 'https://front.njpwworld.com/auth/login'
  45
  46     def _perform_login(self, username, password):
  47         # Setup session (will set necessary cookies)
  48         self._request_webpage(
  49             'https://njpwworld.com/', None, note='Setting up session')
  50
  51         webpage, urlh = self._download_webpage_handle(
  52             self._LOGIN_URL, None,
  53             note='Logging in', errnote='Unable to login',
  54             data=urlencode_postdata({'login_id': username, 'pw': password}),
  55             headers={'Referer': 'https://front.njpwworld.com/auth'})
  56         # /auth/login will return 302 for successful logins
  57         if urlh.geturl() == self._LOGIN_URL:
  58             self.report_warning('unable to login')
  59             return False
  60
  61         return True
  62
  63     def _real_extract(self, url):
  64         video_id = self._match_id(url)
  65
  66         webpage = self._download_webpage(url, video_id)
  67
  68         formats = []
  69         for kind, vid in re.findall(r'if\s+\(\s*imageQualityType\s*==\s*\'([^\']+)\'\s*\)\s*{\s*video_id\s*=\s*"(\d+)"', webpage):
  70             player_path = '/intent?id=%s&type=url' % vid
  71             player_url = compat_urlparse.urljoin(url, player_path)
  72             formats += self._extract_m3u8_formats(
  73                 player_url, video_id, 'mp4', 'm3u8_native', m3u8_id=kind, fatal=False, quality=int(kind == 'high'))
  74
  75         self._sort_formats(formats)
  76
  77         tag_block = get_element_by_class('tag-block', webpage)
  78         tags = re.findall(
  79             r'<a[^>]+class="tag-[^"]+"[^>]*>([^<]+)</a>', tag_block
  80         ) if tag_block else None
  81
  82         return {
  83             'id': video_id,
  84             'title': get_element_by_class('article-title', webpage) or self._og_search_title(webpage),
  85             'formats': formats,
  86             'tags': tags,
  87         }