Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/jpopsukitv.py

   1 # coding=utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     int_or_none,
   9     unified_strdate,
  10 )
  11
  12
  13 class JpopsukiIE(InfoExtractor):
  14     IE_NAME = 'jpopsuki.tv'
  15     _VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/video/(.*?)/(?P<id>\S+)'
  16
  17     _TEST = {
  18         'url': 'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771',
  19         'md5': '88018c0c1a9b1387940e90ec9e7e198e',
  20         'file': '00be659d23b0b40508169cdee4545771.mp4',
  21         'info_dict': {
  22             'id': '00be659d23b0b40508169cdee4545771',
  23             'title': 'ayumi hamasaki - evolution',
  24             'description': 'Release date: 2001.01.31\r\n浜崎あゆみ - evolution',
  25             'thumbnail': 'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg',
  26             'uploader': 'plama_chan',
  27             'uploader_id': '404',
  28             'upload_date': '20121101'
  29         }
  30     }
  31
  32     def _real_extract(self, url):
  33         mobj = re.match(self._VALID_URL, url)
  34         video_id = mobj.group('id')
  35
  36         webpage = self._download_webpage(url, video_id)
  37
  38         video_url = 'http://www.jpopsuki.tv' + self._html_search_regex(
  39             r'<source src="(.*?)" type', webpage, 'video url')
  40
  41         video_title = self._og_search_title(webpage)
  42         description = self._og_search_description(webpage)
  43         thumbnail = self._og_search_thumbnail(webpage)
  44         uploader = self._html_search_regex(
  45             r'<li>from: <a href="/user/view/user/(.*?)/uid/',
  46             webpage, 'video uploader', fatal=False)
  47         uploader_id = self._html_search_regex(
  48             r'<li>from: <a href="/user/view/user/\S*?/uid/(\d*)',
  49             webpage, 'video uploader_id', fatal=False)
  50         upload_date = self._html_search_regex(
  51             r'<li>uploaded: (.*?)</li>', webpage, 'video upload_date',
  52             fatal=False)
  53         if upload_date is not None:
  54             upload_date = unified_strdate(upload_date)
  55         view_count_str = self._html_search_regex(
  56             r'<li>Hits: ([0-9]+?)</li>', webpage, 'video view_count',
  57             fatal=False)
  58         comment_count_str = self._html_search_regex(
  59             r'<h2>([0-9]+?) comments</h2>', webpage, 'video comment_count',
  60             fatal=False)
  61
  62         return {
  63             'id': video_id,
  64             'url': video_url,
  65             'title': video_title,
  66             'description': description,
  67             'thumbnail': thumbnail,
  68             'uploader': uploader,
  69             'uploader_id': uploader_id,
  70             'upload_date': upload_date,
  71             'view_count': int_or_none(view_count_str),
  72             'comment_count': int_or_none(comment_count_str),
  73         }