3 from ..utils import unified_strdate
4 from .common import InfoExtractor
7 class JpopsukiIE(InfoExtractor):
8 IE_NAME = u'jpopsuki.tv'
9 _VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/video/(.*?)/(?P<id>\S+)'
12 u'url': u'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771',
13 u'md5': u'88018c0c1a9b1387940e90ec9e7e198e',
14 u'file': u'00be659d23b0b40508169cdee4545771.mp4',
16 u'id': u'00be659d23b0b40508169cdee4545771',
17 u'title': u'ayumi hamasaki - evolution',
18 'description': u'Release date: 2001.01.31\r 浜崎あゆみ - evolution',
19 'thumbnail': u'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg',
20 'uploader': u'plama_chan',
21 'uploader_id': u'404',
22 'upload_date': u'20121101'
26 def _real_extract(self, url):
27 mobj = re.match(self._VALID_URL, url)
28 video_id = mobj.group('id')
30 webpage = self._download_webpage(url, video_id)
32 video_url = 'http://www.jpopsuki.tv' + self._html_search_regex(
33 r'<source src="(.*?)" type', webpage, u'video url')
35 video_title = self._html_search_regex(
36 r'<meta name="og:title" content="(.*?)" />', webpage, u'video title')
37 description = self._html_search_regex(
38 r'<meta name="og:description" content="(.*?)" />', webpage, u'video description', flags=re.DOTALL)
39 thumbnail = self._html_search_regex(
40 r'<meta name="og:image" content="(.*?)" />', webpage, u'video thumbnail')
41 uploader = self._html_search_regex(
42 r'<li>from: <a href="/user/view/user/(.*?)/uid/', webpage, u'video uploader')
43 uploader_id = self._html_search_regex(
44 r'<li>from: <a href="/user/view/user/\S*?/uid/(\d*)', webpage, u'video uploader_id')
45 upload_date = self._html_search_regex(
46 r'<li>uploaded: (.*?)</li>', webpage, u'video upload_date')
47 if upload_date is not None:
48 upload_date = unified_strdate(upload_date)
49 view_count = self._html_search_regex(
50 r'<li>Hits: (\d*?)</li>', webpage, u'video view_count')
51 comment_count = self._html_search_regex(
52 r'<h2>(\d*?) comments</h2>', webpage, u'video comment_count')
58 'description': description,
59 'thumbnail': thumbnail,
61 'uploader_id': uploader_id,
62 'upload_date': upload_date,
63 'view_count': view_count,
64 'comment_count': comment_count,