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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class SoulAnimeWatchingIE(InfoExtractor):
   9     IE_NAME = "soulanime:watching"
  10     IE_DESC = "SoulAnime video"
  11     _TEST = {
  12         'url': 'http://www.soul-anime.net/watching/seirei-tsukai-no-blade-dance-episode-9/',
  13         'md5': '05fae04abf72298098b528e98abf4298',
  14         'info_dict': {
  15             'id': 'seirei-tsukai-no-blade-dance-episode-9',
  16             'ext': 'mp4',
  17             'title': 'seirei-tsukai-no-blade-dance-episode-9',
  18             'description': 'seirei-tsukai-no-blade-dance-episode-9'
  19         }
  20     }
  21     _VALID_URL = r'http://[w.]*soul-anime\.(?P<domain>[^/]+)/watch[^/]*/(?P<id>[^/]+)'
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         video_id = mobj.group('id')
  26         domain = mobj.group('domain')
  27
  28         page = self._download_webpage(url, video_id)
  29
  30         video_url_encoded = self._html_search_regex(
  31             r'<div id="download">[^<]*<a href="(?P<url>[^"]+)"', page, 'url')
  32         video_url = "http://www.soul-anime." + domain + video_url_encoded
  33
  34         vid = self._request_webpage(video_url, video_id)
  35         ext = vid.info().gettype().split("/")[1]
  36
  37         return {
  38             'id': video_id,
  39             'url': video_url,
  40             'ext': ext,
  41             'title': video_id,
  42             'description': video_id
  43         }
  44
  45
  46 class SoulAnimeSeriesIE(InfoExtractor):
  47     IE_NAME = "soulanime:series"
  48     IE_DESC = "SoulAnime Series"
  49
  50     _VALID_URL = r'http://[w.]*soul-anime\.(?P<domain>[^/]+)/anime./(?P<id>[^/]+)'
  51
  52     _EPISODE_REGEX = r'<option value="(/watch[^/]*/[^"]+)">[^<]*</option>'
  53
  54     _TEST = {
  55         'url': 'http://www.soul-anime.net/anime1/black-rock-shooter-tv/',
  56         'info_dict': {
  57             'id': 'black-rock-shooter-tv'
  58         },
  59         'playlist_count': 8
  60     }
  61
  62     def _real_extract(self, url):
  63         mobj = re.match(self._VALID_URL, url)
  64         series_id = mobj.group('id')
  65         domain = mobj.group('domain')
  66
  67         pattern = re.compile(self._EPISODE_REGEX)
  68
  69         page = self._download_webpage(url, series_id, "Downloading series page")
  70         mobj = pattern.findall(page)
  71
  72         entries = [self.url_result("http://www.soul-anime." + domain + obj) for obj in mobj]
  73
  74         return self.playlist_result(entries, series_id)