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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     HEADRequest,
   8     urlhandle_detect_ext,
   9 )
  10
  11
  12 class SoulAnimeWatchingIE(InfoExtractor):
  13     IE_NAME = "soulanime:watching"
  14     IE_DESC = "SoulAnime video"
  15     _TEST = {
  16         'url': 'http://www.soul-anime.net/watching/seirei-tsukai-no-blade-dance-episode-9/',
  17         'md5': '05fae04abf72298098b528e98abf4298',
  18         'info_dict': {
  19             'id': 'seirei-tsukai-no-blade-dance-episode-9',
  20             'ext': 'mp4',
  21             'title': 'seirei-tsukai-no-blade-dance-episode-9',
  22             'description': 'seirei-tsukai-no-blade-dance-episode-9'
  23         }
  24     }
  25     _VALID_URL = r'http://[w.]*soul-anime\.(?P<domain>[^/]+)/watch[^/]*/(?P<id>[^/]+)'
  26
  27     def _real_extract(self, url):
  28         mobj = re.match(self._VALID_URL, url)
  29         video_id = mobj.group('id')
  30         domain = mobj.group('domain')
  31
  32         page = self._download_webpage(url, video_id)
  33
  34         video_url_encoded = self._html_search_regex(
  35             r'<div id="download">[^<]*<a href="(?P<url>[^"]+)"', page, 'url')
  36         video_url = "http://www.soul-anime." + domain + video_url_encoded
  37
  38         ext_req = HEADRequest(video_url)
  39         ext_handle = self._request_webpage(
  40             ext_req, video_id, note='Determining extension')
  41         ext = urlhandle_detect_ext(ext_handle)
  42
  43         return {
  44             'id': video_id,
  45             'url': video_url,
  46             'ext': ext,
  47             'title': video_id,
  48             'description': video_id
  49         }
  50
  51
  52 class SoulAnimeSeriesIE(InfoExtractor):
  53     IE_NAME = "soulanime:series"
  54     IE_DESC = "SoulAnime Series"
  55
  56     _VALID_URL = r'http://[w.]*soul-anime\.(?P<domain>[^/]+)/anime./(?P<id>[^/]+)'
  57
  58     _EPISODE_REGEX = r'<option value="(/watch[^/]*/[^"]+)">[^<]*</option>'
  59
  60     _TEST = {
  61         'url': 'http://www.soul-anime.net/anime1/black-rock-shooter-tv/',
  62         'info_dict': {
  63             'id': 'black-rock-shooter-tv'
  64         },
  65         'playlist_count': 8
  66     }
  67
  68     def _real_extract(self, url):
  69         mobj = re.match(self._VALID_URL, url)
  70         series_id = mobj.group('id')
  71         domain = mobj.group('domain')
  72
  73         pattern = re.compile(self._EPISODE_REGEX)
  74
  75         page = self._download_webpage(url, series_id, "Downloading series page")
  76         mobj = pattern.findall(page)
  77
  78         entries = [self.url_result("http://www.soul-anime." + domain + obj) for obj in mobj]
  79
  80         return self.playlist_result(entries, series_id)