Raphaël G. Git Repositories - youtubedl/blob - 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     url_or_none,
  11 )
  12
  13
  14 class IwaraIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.|ecchi\.)?iwara\.tv/videos/(?P<id>[a-zA-Z0-9]+)'
  16     _TESTS = [{
  17         'url': 'http://iwara.tv/videos/amVwUl1EHpAD9RD',
  18         # md5 is unstable
  19         'info_dict': {
  20             'id': 'amVwUl1EHpAD9RD',
  21             'ext': 'mp4',
  22             'title': '【MMD R-18】ガールフレンド carry_me_off',
  23             'age_limit': 18,
  24         },
  25     }, {
  26         'url': 'http://ecchi.iwara.tv/videos/Vb4yf2yZspkzkBO',
  27         'md5': '7e5f1f359cd51a027ba4a7b7710a50f0',
  28         'info_dict': {
  29             'id': '0B1LvuHnL-sRFNXB1WHNqbGw4SXc',
  30             'ext': 'mp4',
  31             'title': '[3D Hentai] Kyonyu × Genkai × Emaki Shinobi Girls.mp4',
  32             'age_limit': 18,
  33         },
  34         'add_ie': ['GoogleDrive'],
  35     }, {
  36         'url': 'http://www.iwara.tv/videos/nawkaumd6ilezzgq',
  37         # md5 is unstable
  38         'info_dict': {
  39             'id': '6liAP9s2Ojc',
  40             'ext': 'mp4',
  41             'age_limit': 18,
  42             'title': '[MMD] Do It Again Ver.2 [1080p 60FPS] (Motion,Camera,Wav+DL)',
  43             'description': 'md5:590c12c0df1443d833fbebe05da8c47a',
  44             'upload_date': '20160910',
  45             'uploader': 'aMMDsork',
  46             'uploader_id': 'UCVOFyOSCyFkXTYYHITtqB7A',
  47         },
  48         'add_ie': ['Youtube'],
  49     }]
  50
  51     def _real_extract(self, url):
  52         video_id = self._match_id(url)
  53
  54         webpage, urlh = self._download_webpage_handle(url, video_id)
  55
  56         hostname = compat_urllib_parse_urlparse(urlh.geturl()).hostname
  57         # ecchi is 'sexy' in Japanese
  58         age_limit = 18 if hostname.split('.')[0] == 'ecchi' else 0
  59
  60         video_data = self._download_json('http://www.iwara.tv/api/video/%s' % video_id, video_id)
  61
  62         if not video_data:
  63             iframe_url = self._html_search_regex(
  64                 r'<iframe[^>]+src=([\'"])(?P<url>[^\'"]+)\1',
  65                 webpage, 'iframe URL', group='url')
  66             return {
  67                 '_type': 'url_transparent',
  68                 'url': iframe_url,
  69                 'age_limit': age_limit,
  70             }
  71
  72         title = remove_end(self._html_search_regex(
  73             r'<title>([^<]+)</title>', webpage, 'title'), ' | Iwara')
  74
  75         formats = []
  76         for a_format in video_data:
  77             format_uri = url_or_none(a_format.get('uri'))
  78             if not format_uri:
  79                 continue
  80             format_id = a_format.get('resolution')
  81             height = int_or_none(self._search_regex(
  82                 r'(\d+)p', format_id, 'height', default=None))
  83             formats.append({
  84                 'url': self._proto_relative_url(format_uri, 'https:'),
  85                 'format_id': format_id,
  86                 'ext': mimetype2ext(a_format.get('mime')) or 'mp4',
  87                 'height': height,
  88                 'width': int_or_none(height / 9.0 * 16.0 if height else None),
  89                 'quality': 1 if format_id == 'Source' else 0,
  90             })
  91
  92         self._sort_formats(formats)
  93
  94         return {
  95             'id': video_id,
  96             'title': title,
  97             'age_limit': age_limit,
  98             'formats': formats,
  99         }