]>
Commit | Line | Data |
---|---|---|
1 | import re | |
2 | ||
3 | from .common import InfoExtractor | |
4 | from ..compat import compat_urlparse | |
5 | from ..utils import ( | |
6 | get_element_by_class, | |
7 | urlencode_postdata, | |
8 | ) | |
9 | ||
10 | ||
11 | class NJPWWorldIE(InfoExtractor): | |
12 | _VALID_URL = r'https?://(front\.)?njpwworld\.com/p/(?P<id>[a-z0-9_]+)' | |
13 | IE_DESC = '新日本プロレスワールド' | |
14 | _NETRC_MACHINE = 'njpwworld' | |
15 | ||
16 | _TESTS = [{ | |
17 | 'url': 'http://njpwworld.com/p/s_series_00155_1_9/', | |
18 | 'info_dict': { | |
19 | 'id': 's_series_00155_1_9', | |
20 | 'ext': 'mp4', | |
21 | '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', | |
22 | 'tags': list, | |
23 | }, | |
24 | 'params': { | |
25 | 'skip_download': True, # AES-encrypted m3u8 | |
26 | }, | |
27 | 'skip': 'Requires login', | |
28 | }, { | |
29 | 'url': 'https://front.njpwworld.com/p/s_series_00563_16_bs', | |
30 | 'info_dict': { | |
31 | 'id': 's_series_00563_16_bs', | |
32 | 'ext': 'mp4', | |
33 | '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)', | |
34 | '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"], | |
35 | }, | |
36 | 'params': { | |
37 | 'skip_download': True, | |
38 | }, | |
39 | }] | |
40 | ||
41 | _LOGIN_URL = 'https://front.njpwworld.com/auth/login' | |
42 | ||
43 | def _perform_login(self, username, password): | |
44 | # Setup session (will set necessary cookies) | |
45 | self._request_webpage( | |
46 | 'https://njpwworld.com/', None, note='Setting up session') | |
47 | ||
48 | webpage, urlh = self._download_webpage_handle( | |
49 | self._LOGIN_URL, None, | |
50 | note='Logging in', errnote='Unable to login', | |
51 | data=urlencode_postdata({'login_id': username, 'pw': password}), | |
52 | headers={'Referer': 'https://front.njpwworld.com/auth'}) | |
53 | # /auth/login will return 302 for successful logins | |
54 | if urlh.geturl() == self._LOGIN_URL: | |
55 | self.report_warning('unable to login') | |
56 | return False | |
57 | ||
58 | return True | |
59 | ||
60 | def _real_extract(self, url): | |
61 | video_id = self._match_id(url) | |
62 | ||
63 | webpage = self._download_webpage(url, video_id) | |
64 | ||
65 | formats = [] | |
66 | for kind, vid in re.findall(r'if\s+\(\s*imageQualityType\s*==\s*\'([^\']+)\'\s*\)\s*{\s*video_id\s*=\s*"(\d+)"', webpage): | |
67 | player_path = '/intent?id=%s&type=url' % vid | |
68 | player_url = compat_urlparse.urljoin(url, player_path) | |
69 | formats += self._extract_m3u8_formats( | |
70 | player_url, video_id, 'mp4', 'm3u8_native', m3u8_id=kind, fatal=False, quality=int(kind == 'high')) | |
71 | ||
72 | tag_block = get_element_by_class('tag-block', webpage) | |
73 | tags = re.findall( | |
74 | r'<a[^>]+class="tag-[^"]+"[^>]*>([^<]+)</a>', tag_block | |
75 | ) if tag_block else None | |
76 | ||
77 | return { | |
78 | 'id': video_id, | |
79 | 'title': get_element_by_class('article-title', webpage) or self._og_search_title(webpage), | |
80 | 'formats': formats, | |
81 | 'tags': tags, | |
82 | } |