youtube-dl/youtube_dl/extractor/iwara.py
Yen Chi Hsuan 2ab2c0d1f5
[iwara] Add width (closes #11724)
The heuristic is from #11724
2017-02-05 22:30:13 +08:00

96 lines
3.1 KiB
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlparse
from ..utils import (
int_or_none,
mimetype2ext,
remove_end,
)
class IwaraIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.|ecchi\.)?iwara\.tv/videos/(?P<id>[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,
},
}, {
'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'<iframe[^>]+src=([\'"])(?P<url>[^\'"]+)\1',
webpage, 'iframe URL', group='url')
return {
'_type': 'url_transparent',
'url': iframe_url,
'age_limit': age_limit,
}
title = remove_end(self._html_search_regex(
r'<title>([^<]+)</title>', webpage, 'title'), ' | Iwara')
formats = []
for a_format in video_data:
format_id = a_format.get('resolution')
height = int_or_none(self._search_regex(
r'(\d+)p', format_id, 'height', default=None))
formats.append({
'url': a_format['uri'],
'format_id': format_id,
'ext': mimetype2ext(a_format.get('mime')) or 'mp4',
'height': height,
'width': int_or_none(height / 9.0 * 16.0 if height else None),
'quality': 1 if format_id == 'Source' else 0,
})
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'age_limit': age_limit,
'formats': formats,
}