]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/njpwworld.py
9b5ad5a9f0c38427834fb9e942f018a7aa3c2cbf
[youtubedl] / 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 extract_attributes,
10 get_element_by_class,
11 urlencode_postdata,
12 )
13
14
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'
19
20 _TEST = {
21 'url': 'http://njpwworld.com/p/s_series_00155_1_9/',
22 'info_dict': {
23 'id': 's_series_00155_1_9',
24 'ext': 'mp4',
25 'title': '第9試合 ランディ・サベージ vs リック・スタイナー',
26 'tags': list,
27 },
28 'params': {
29 'skip_download': True, # AES-encrypted m3u8
30 },
31 'skip': 'Requires login',
32 }
33
34 def _real_initialize(self):
35 self._login()
36
37 def _login(self):
38 username, password = self._get_login_info()
39 # No authentication to be performed
40 if not username:
41 return True
42
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 # /auth/login will return 302 for successful logins
48 if urlh.geturl() == 'https://njpwworld.com/auth/login':
49 self.report_warning('unable to login')
50 return False
51
52 return True
53
54 def _real_extract(self, url):
55 video_id = self._match_id(url)
56
57 webpage = self._download_webpage(url, video_id)
58
59 formats = []
60 for mobj in re.finditer(r'<a[^>]+\bhref=(["\'])/player.+?[^>]*>', webpage):
61 player = extract_attributes(mobj.group(0))
62 player_path = player.get('href')
63 if not player_path:
64 continue
65 kind = self._search_regex(
66 r'(low|high)$', player.get('class') or '', 'kind',
67 default='low')
68 player_url = compat_urlparse.urljoin(url, player_path)
69 player_page = self._download_webpage(
70 player_url, video_id, note='Downloading player page')
71 entries = self._parse_html5_media_entries(
72 player_url, player_page, video_id, m3u8_id='hls-%s' % kind,
73 m3u8_entry_protocol='m3u8_native')
74 kind_formats = entries[0]['formats']
75 for f in kind_formats:
76 f['quality'] = 2 if kind == 'high' else 1
77 formats.extend(kind_formats)
78
79 self._sort_formats(formats)
80
81 post_content = get_element_by_class('post-content', webpage)
82 tags = re.findall(
83 r'<li[^>]+class="tag-[^"]+"><a[^>]*>([^<]+)</a></li>', post_content
84 ) if post_content else None
85
86 return {
87 'id': video_id,
88 'title': self._og_search_title(webpage),
89 'formats': formats,
90 'tags': tags,
91 }