_ Git - youtube-dl/blob - youtube_dl/extractor/jpopsukitv.py

   1 import re
   2 from ..utils import unified_strdate
   3 from .common import InfoExtractor
   4
   5
   6 class JpopsukiIE(InfoExtractor):
   7     IE_NAME = u'jpopsuki.tv'
   8     _VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/video/(.*?)/(?P<id>\S+)'
   9
  10     _TEST = {
  11         u'url': u'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771',
  12         u'md5': u'88018c0c1a9b1387940e90ec9e7e198e',
  13         u'file': u'00be659d23b0b40508169cdee4545771.mp4',
  14         u'info_dict': {
  15             u'id': u'00be659d23b0b40508169cdee4545771',
  16             u'title': u'ayumi hamasaki - evolution',
  17             'description': u'Release date: 2001.01.31\r 浜崎あゆみ - evolution',
  18             'thumbnail': u'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg',
  19             'uploader': u'plama_chan',
  20             'uploader_id': u'404',
  21             'upload_date': u'20121101'
  22         }
  23     }
  24
  25     def _real_extract(self, url):
  26         mobj = re.match(self._VALID_URL, url)
  27         video_id = mobj.group('id')
  28
  29         webpage = self._download_webpage(url, video_id)
  30
  31         video_url = 'http://www.jpopsuki.tv' + self._html_search_regex(
  32             r'<source src="(.*?)" type', webpage, u'video url')
  33
  34         video_title = self._html_search_regex(
  35             r'<meta name="og:title" content="(.*?)" />', webpage, u'video title')
  36         description = self._html_search_regex(
  37             r'<meta name="og:description" content="(.*?)" />', webpage, u'video description', flags=re.DOTALL)
  38         thumbnail = self._html_search_regex(
  39             r'<meta name="og:image" content="(.*?)" />', webpage, u'video thumbnail')
  40         uploader = self._html_search_regex(
  41             r'<li>from: <a href="/user/view/user/(.*?)/uid/', webpage, u'video uploader')
  42         uploader_id = self._html_search_regex(
  43             r'<li>from: <a href="/user/view/user/\S*?/uid/(\d*)', webpage, u'video uploader_id')
  44         upload_date = self._html_search_regex(
  45             r'<li>uploaded: (.*?)</li>', webpage, u'video upload_date')
  46         if upload_date is not None:
  47             upload_date = unified_strdate(upload_date)
  48         view_count = self._html_search_regex(
  49             r'<li>Hits: (\d*?)</li>', webpage, u'video view_count')
  50         comment_count = self._html_search_regex(
  51             r'<h2>(\d*?) comments</h2>', webpage, u'video comment_count')
  52
  53         return {
  54             'id': video_id,
  55             'url': video_url,
  56             'title': video_title,
  57             'description': description,
  58             'thumbnail': thumbnail,
  59             'uploader': uploader,
  60             'uploader_id': uploader_id,
  61             'upload_date': upload_date,
  62             'view_count': view_count,
  63             'comment_count': comment_count,
  64         }