youtube_dl/extractor/jpopsukitv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     unified_strdate,
   8 )
   9
  10
  11 class JpopsukiIE(InfoExtractor):
  12     IE_NAME = 'jpopsuki.tv'
  13     _VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/(?:category/)?video/[^/]+/(?P<id>\S+)'
  14
  15     _TEST = {
  16         'url': 'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771',
  17         'md5': '88018c0c1a9b1387940e90ec9e7e198e',
  18         'info_dict': {
  19             'id': '00be659d23b0b40508169cdee4545771',
  20             'ext': 'mp4',
  21             'title': 'ayumi hamasaki - evolution',
  22             'description': 'Release date: 2001.01.31\r\n浜崎あゆみ - evolution',
  23             'thumbnail': 'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg',
  24             'uploader': 'plama_chan',
  25             'uploader_id': '404',
  26             'upload_date': '20121101'
  27         }
  28     }
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32
  33         webpage = self._download_webpage(url, video_id)
  34
  35         video_url = 'http://www.jpopsuki.tv' + self._html_search_regex(
  36             r'<source src="(.*?)" type', webpage, 'video url')
  37
  38         video_title = self._og_search_title(webpage)
  39         description = self._og_search_description(webpage)
  40         thumbnail = self._og_search_thumbnail(webpage)
  41         uploader = self._html_search_regex(
  42             r'<li>from: <a href="/user/view/user/(.*?)/uid/',
  43             webpage, 'video uploader', fatal=False)
  44         uploader_id = self._html_search_regex(
  45             r'<li>from: <a href="/user/view/user/\S*?/uid/(\d*)',
  46             webpage, 'video uploader_id', fatal=False)
  47         upload_date = unified_strdate(self._html_search_regex(
  48             r'<li>uploaded: (.*?)</li>', webpage, 'video upload_date',
  49             fatal=False))
  50         view_count_str = self._html_search_regex(
  51             r'<li>Hits: ([0-9]+?)</li>', webpage, 'video view_count',
  52             fatal=False)
  53         comment_count_str = self._html_search_regex(
  54             r'<h2>([0-9]+?) comments</h2>', webpage, 'video comment_count',
  55             fatal=False)
  56
  57         return {
  58             'id': video_id,
  59             'url': video_url,
  60             'title': video_title,
  61             'description': description,
  62             'thumbnail': thumbnail,
  63             'uploader': uploader,
  64             'uploader_id': uploader_id,
  65             'upload_date': upload_date,
  66             'view_count': int_or_none(view_count_str),
  67             'comment_count': int_or_none(comment_count_str),
  68         }