_ Git - youtube-dl/blob - youtube_dl/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?://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     _TEST = {
  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': '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
  33     def _real_initialize(self):
  34         self._login()
  35
  36     def _login(self):
  37         username, password = self._get_login_info()
  38         # No authentication to be performed
  39         if not username:
  40             return True
  41
  42         webpage, urlh = self._download_webpage_handle(
  43             'https://njpwworld.com/auth/login', None,
  44             note='Logging in', errnote='Unable to login',
  45             data=urlencode_postdata({'login_id': username, 'pw': password}))
  46         # /auth/login will return 302 for successful logins
  47         if urlh.geturl() == 'https://njpwworld.com/auth/login':
  48             self.report_warning('unable to login')
  49             return False
  50
  51         return True
  52
  53     def _real_extract(self, url):
  54         video_id = self._match_id(url)
  55
  56         webpage = self._download_webpage(url, video_id)
  57
  58         formats = []
  59         for player_url, kind in re.findall(r'<a[^>]+href="(/player[^"]+)".+?<img[^>]+src="[^"]+qf_btn_([^".]+)', webpage):
  60             player_url = compat_urlparse.urljoin(url, player_url)
  61
  62             player_page = self._download_webpage(
  63                 player_url, video_id, note='Downloading player page')
  64
  65             entries = self._parse_html5_media_entries(
  66                 player_url, player_page, video_id, m3u8_id='hls-%s' % kind,
  67                 m3u8_entry_protocol='m3u8_native',
  68                 preference=2 if 'hq' in kind else 1)
  69             formats.extend(entries[0]['formats'])
  70
  71         self._sort_formats(formats)
  72
  73         post_content = get_element_by_class('post-content', webpage)
  74         tags = re.findall(
  75             r'<li[^>]+class="tag-[^"]+"><a[^>]*>([^<]+)</a></li>', post_content
  76         ) if post_content else None
  77
  78         return {
  79             'id': video_id,
  80             'title': self._og_search_title(webpage),
  81             'formats': formats,
  82             'tags': tags,
  83         }