]> asedeno.scripts.mit.edu Git - youtube-dl.git/blob - youtube_dl/extractor/njpwworld.py
Support more deeply nested ptmd_path with test, update tests
[youtube-dl.git] / 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?://(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 _real_initialize(self):
47         self._login()
48
49     def _login(self):
50         username, password = self._get_login_info()
51         # No authentication to be performed
52         if not username:
53             return True
54
55         # Setup session (will set necessary cookies)
56         self._request_webpage(
57             'https://njpwworld.com/', None, note='Setting up session')
58
59         webpage, urlh = self._download_webpage_handle(
60             self._LOGIN_URL, None,
61             note='Logging in', errnote='Unable to login',
62             data=urlencode_postdata({'login_id': username, 'pw': password}),
63             headers={'Referer': 'https://front.njpwworld.com/auth'})
64         # /auth/login will return 302 for successful logins
65         if urlh.geturl() == self._LOGIN_URL:
66             self.report_warning('unable to login')
67             return False
68
69         return True
70
71     def _real_extract(self, url):
72         video_id = self._match_id(url)
73
74         webpage = self._download_webpage(url, video_id)
75
76         formats = []
77         for kind, vid in re.findall(r'if\s+\(\s*imageQualityType\s*==\s*\'([^\']+)\'\s*\)\s*{\s*video_id\s*=\s*"(\d+)"', webpage):
78             player_path = '/intent?id=%s&type=url' % vid
79             player_url = compat_urlparse.urljoin(url, player_path)
80             formats.append({
81                 'url': player_url,
82                 'format_id': kind,
83                 'ext': 'mp4',
84                 'protocol': 'm3u8',
85                 'quality': 2 if kind == 'high' else 1,
86             })
87
88         self._sort_formats(formats)
89
90         tag_block = get_element_by_class('tag-block', webpage)
91         tags = re.findall(
92             r'<a[^>]+class="tag-[^"]+"[^>]*>([^<]+)</a>', tag_block
93         ) if tag_block else None
94
95         return {
96             'id': video_id,
97             'title': get_element_by_class('article-title', webpage) or self._og_search_title(webpage),
98             'formats': formats,
99             'tags': tags,
100         }