import re from .common import InfoExtractor from ..compat import compat_urllib_parse_urlparse from ..utils import ( int_or_none, mimetype2ext, remove_end, url_or_none, unified_strdate, strip_or_none, ) class IwaraIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.|ecchi\.)?iwara\.tv/videos/(?P[a-zA-Z0-9]+)' _TESTS = [{ 'url': 'http://iwara.tv/videos/amVwUl1EHpAD9RD', # md5 is unstable 'info_dict': { 'id': 'amVwUl1EHpAD9RD', 'ext': 'mp4', 'title': '【MMD R-18】ガールフレンド carry_me_off', 'age_limit': 18, 'thumbnail': 'https://i.iwara.tv/sites/default/files/videos/thumbnails/7951/thumbnail-7951_0001.png', 'uploader': 'Reimu丨Action', 'upload_date': '20150828', 'description': 'md5:1d4905ce48c66c9299c617f08e106e0f', }, }, { 'url': 'http://ecchi.iwara.tv/videos/Vb4yf2yZspkzkBO', 'md5': '7e5f1f359cd51a027ba4a7b7710a50f0', 'info_dict': { 'id': '0B1LvuHnL-sRFNXB1WHNqbGw4SXc', 'ext': 'mp4', 'title': '[3D Hentai] Kyonyu × Genkai × Emaki Shinobi Girls.mp4', 'age_limit': 18, }, 'add_ie': ['GoogleDrive'], }, { 'url': 'http://www.iwara.tv/videos/nawkaumd6ilezzgq', # md5 is unstable 'info_dict': { 'id': '6liAP9s2Ojc', 'ext': 'mp4', 'age_limit': 18, 'title': '[MMD] Do It Again Ver.2 [1080p 60FPS] (Motion,Camera,Wav+DL)', 'description': 'md5:590c12c0df1443d833fbebe05da8c47a', 'upload_date': '20160910', 'uploader': 'aMMDsork', 'uploader_id': 'UCVOFyOSCyFkXTYYHITtqB7A', }, 'add_ie': ['Youtube'], }] def _real_extract(self, url): video_id = self._match_id(url) webpage, urlh = self._download_webpage_handle(url, video_id) hostname = compat_urllib_parse_urlparse(urlh.geturl()).hostname # ecchi is 'sexy' in Japanese age_limit = 18 if hostname.split('.')[0] == 'ecchi' else 0 video_data = self._download_json('http://www.iwara.tv/api/video/%s' % video_id, video_id) if not video_data: iframe_url = self._html_search_regex( r']+src=([\'"])(?P[^\'"]+)\1', webpage, 'iframe URL', group='url') return { '_type': 'url_transparent', 'url': iframe_url, 'age_limit': age_limit, } title = remove_end(self._html_extract_title(webpage), ' | Iwara') thumbnail = self._html_search_regex( r'poster=[\'"]([^\'"]+)', webpage, 'thumbnail', default=None) uploader = self._html_search_regex( r'class="username">([^<]+)', webpage, 'uploader', fatal=False) upload_date = unified_strdate(self._html_search_regex( r'作成日:([^\s]+)', webpage, 'upload_date', fatal=False)) description = strip_or_none(self._search_regex( r'

(.+?(?=