Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/thvideo.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     unified_strdate
   9 )
  10
  11
  12 class THVideoIE(InfoExtractor):
  13     _VALID_URL = r'http://(?:www\.)?thvideo\.tv/(?:v/th|mobile\.php\?cid=)(?P<id>[0-9]+)'
  14     _TEST = {
  15         'url': 'http://thvideo.tv/v/th1987/',
  16         'md5': 'fa107b1f73817e325e9433505a70db50',
  17         'info_dict': {
  18             'id': '1987',
  19             'ext': 'mp4',
  20             'title': '【动画】秘封活动记录 ～ The Sealed Esoteric History.分镜稿预览',
  21             'display_id': 'th1987',
  22             'thumbnail': 'http://thvideo.tv/uploadfile/2014/0722/20140722013459856.jpg',
  23             'description': '社团京都幻想剧团的第一个东方二次同人动画作品「秘封活动记录 ～ The Sealed Esoteric History.」 本视频是该动画第一期的分镜草稿...',
  24             'upload_date': '20140722'
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30
  31         # extract download link from mobile player page
  32         webpage_player = self._download_webpage(
  33             'http://thvideo.tv/mobile.php?cid=%s-0' % (video_id),
  34             video_id, note='Downloading video source page')
  35         video_url = self._html_search_regex(
  36             r'<source src="(.*?)" type', webpage_player, 'video url')
  37
  38         # extract video info from main page
  39         webpage = self._download_webpage(
  40             'http://thvideo.tv/v/th%s' % (video_id), video_id)
  41         title = self._og_search_title(webpage)
  42         display_id = 'th%s' % video_id
  43         thumbnail = self._og_search_thumbnail(webpage)
  44         description = self._og_search_description(webpage)
  45         upload_date = unified_strdate(self._html_search_regex(
  46             r'span itemprop="datePublished" content="(.*?)">', webpage,
  47             'upload date', fatal=False))
  48
  49         return {
  50             'id': video_id,
  51             'ext': 'mp4',
  52             'url': video_url,
  53             'title': title,
  54             'display_id': display_id,
  55             'thumbnail': thumbnail,
  56             'description': description,
  57             'upload_date': upload_date
  58         }
  59
  60
  61 class THVideoPlaylistIE(InfoExtractor):
  62     _VALID_URL = r'http?://(?:www\.)?thvideo\.tv/mylist(?P<id>[0-9]+)'
  63     _TEST = {
  64         'url': 'http://thvideo.tv/mylist2',
  65         'info_dict': {
  66             'id': '2',
  67             'title': '幻想万華鏡',
  68         },
  69         'playlist_mincount': 23,
  70     }
  71
  72     def _real_extract(self, url):
  73         playlist_id = self._match_id(url)
  74
  75         webpage = self._download_webpage(url, playlist_id)
  76         list_title = self._html_search_regex(
  77             r'<h1 class="show_title">(.*?)<b id', webpage, 'playlist title',
  78             fatal=False)
  79
  80         entries = [
  81             self.url_result('http://thvideo.tv/v/th' + id, 'THVideo')
  82             for id in re.findall(r'<dd><a href="http://thvideo.tv/v/th(\d+)/" target=', webpage)]
  83
  84         return self.playlist_result(entries, playlist_id, list_title)