2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..compat import compat_urlparse
15 class NJPWWorldIE(InfoExtractor):
16 _VALID_URL = r'https?://njpwworld\.com/p/(?P<id>[a-z0-9_]+)'
17 IE_DESC = '新日本プロレスワールド'
18 _NETRC_MACHINE = 'njpwworld'
21 'url': 'http://njpwworld.com/p/s_series_00155_1_9/',
23 'id': 's_series_00155_1_9',
25 'title': '第9試合 ランディ・サベージ vs リック・スタイナー',
29 'skip_download': True, # AES-encrypted m3u8
31 'skip': 'Requires login',
34 def _real_initialize(self):
38 username, password = self._get_login_info()
39 # No authentication to be performed
43 webpage, urlh = self._download_webpage_handle(
44 'https://njpwworld.com/auth/login', None,
45 note='Logging in', errnote='Unable to login',
46 data=urlencode_postdata({'login_id': username, 'pw': password}),
47 headers={'Referer': 'https://njpwworld.com/auth'})
48 # /auth/login will return 302 for successful logins
49 if urlh.geturl() == 'https://njpwworld.com/auth/login':
50 self.report_warning('unable to login')
55 def _real_extract(self, url):
56 video_id = self._match_id(url)
58 webpage = self._download_webpage(url, video_id)
61 for mobj in re.finditer(r'<a[^>]+\bhref=(["\'])/player.+?[^>]*>', webpage):
62 player = extract_attributes(mobj.group(0))
63 player_path = player.get('href')
66 kind = self._search_regex(
67 r'(low|high)$', player.get('class') or '', 'kind',
69 player_url = compat_urlparse.urljoin(url, player_path)
70 player_page = self._download_webpage(
71 player_url, video_id, note='Downloading player page')
72 entries = self._parse_html5_media_entries(
73 player_url, player_page, video_id, m3u8_id='hls-%s' % kind,
74 m3u8_entry_protocol='m3u8_native')
75 kind_formats = entries[0]['formats']
76 for f in kind_formats:
77 f['quality'] = 2 if kind == 'high' else 1
78 formats.extend(kind_formats)
80 self._sort_formats(formats)
82 post_content = get_element_by_class('post-content', webpage)
84 r'<li[^>]+class="tag-[^"]+"><a[^>]*>([^<]+)</a></li>', post_content
85 ) if post_content else None
89 'title': self._og_search_title(webpage),