]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/iwara.py
debian/control: Remove trailing whitespace at EOF.
[youtubedl] / youtube_dl / extractor / iwara.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..compat import compat_urllib_parse_urlparse
6 from ..utils import (
7 int_or_none,
8 mimetype2ext,
9 remove_end,
10 )
11
12
13 class IwaraIE(InfoExtractor):
14 _VALID_URL = r'https?://(?:www\.|ecchi\.)?iwara\.tv/videos/(?P<id>[a-zA-Z0-9]+)'
15 _TESTS = [{
16 'url': 'http://iwara.tv/videos/amVwUl1EHpAD9RD',
17 # md5 is unstable
18 'info_dict': {
19 'id': 'amVwUl1EHpAD9RD',
20 'ext': 'mp4',
21 'title': '【MMD R-18】ガールフレンド carry_me_off',
22 'age_limit': 18,
23 },
24 }, {
25 'url': 'http://ecchi.iwara.tv/videos/Vb4yf2yZspkzkBO',
26 'md5': '7e5f1f359cd51a027ba4a7b7710a50f0',
27 'info_dict': {
28 'id': '0B1LvuHnL-sRFNXB1WHNqbGw4SXc',
29 'ext': 'mp4',
30 'title': '[3D Hentai] Kyonyu × Genkai × Emaki Shinobi Girls.mp4',
31 'age_limit': 18,
32 },
33 'add_ie': ['GoogleDrive'],
34 }, {
35 'url': 'http://www.iwara.tv/videos/nawkaumd6ilezzgq',
36 # md5 is unstable
37 'info_dict': {
38 'id': '6liAP9s2Ojc',
39 'ext': 'mp4',
40 'age_limit': 18,
41 'title': '[MMD] Do It Again Ver.2 [1080p 60FPS] (Motion,Camera,Wav+DL)',
42 'description': 'md5:590c12c0df1443d833fbebe05da8c47a',
43 'upload_date': '20160910',
44 'uploader': 'aMMDsork',
45 'uploader_id': 'UCVOFyOSCyFkXTYYHITtqB7A',
46 },
47 'add_ie': ['Youtube'],
48 }]
49
50 def _real_extract(self, url):
51 video_id = self._match_id(url)
52
53 webpage, urlh = self._download_webpage_handle(url, video_id)
54
55 hostname = compat_urllib_parse_urlparse(urlh.geturl()).hostname
56 # ecchi is 'sexy' in Japanese
57 age_limit = 18 if hostname.split('.')[0] == 'ecchi' else 0
58
59 video_data = self._download_json('http://www.iwara.tv/api/video/%s' % video_id, video_id)
60
61 if not video_data:
62 iframe_url = self._html_search_regex(
63 r'<iframe[^>]+src=([\'"])(?P<url>[^\'"]+)\1',
64 webpage, 'iframe URL', group='url')
65 return {
66 '_type': 'url_transparent',
67 'url': iframe_url,
68 'age_limit': age_limit,
69 }
70
71 title = remove_end(self._html_search_regex(
72 r'<title>([^<]+)</title>', webpage, 'title'), ' | Iwara')
73
74 formats = []
75 for a_format in video_data:
76 format_id = a_format.get('resolution')
77 height = int_or_none(self._search_regex(
78 r'(\d+)p', format_id, 'height', default=None))
79 formats.append({
80 'url': a_format['uri'],
81 'format_id': format_id,
82 'ext': mimetype2ext(a_format.get('mime')) or 'mp4',
83 'height': height,
84 'width': int_or_none(height / 9.0 * 16.0 if height else None),
85 'quality': 1 if format_id == 'Source' else 0,
86 })
87
88 self._sort_formats(formats)
89
90 return {
91 'id': video_id,
92 'title': title,
93 'age_limit': age_limit,
94 'formats': formats,
95 }