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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_urlparse
   7 from ..utils import (
   8     determine_ext,
   9     encode_dict,
  10     ExtractorError,
  11     sanitized_Request,
  12     urlencode_postdata,
  13 )
  14
  15
  16 class AnimeOnDemandIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?anime-on-demand\.de/anime/(?P<id>\d+)'
  18     _LOGIN_URL = 'https://www.anime-on-demand.de/users/sign_in'
  19     _APPLY_HTML5_URL = 'https://www.anime-on-demand.de/html5apply'
  20     _TEST = {
  21         'url': 'https://www.anime-on-demand.de/anime/161',
  22         'info_dict': {
  23             'id': '161',
  24             'title': 'Grimgar, Ashes and Illusions (OmU)',
  25             'description': 'md5:6681ce3c07c7189d255ac6ab23812d31',
  26         },
  27         'playlist_mincount': 4,
  28     }
  29
  30     def _login(self):
  31         (username, password) = self._get_login_info()
  32         if username is None:
  33             return
  34
  35         login_page = self._download_webpage(
  36             self._LOGIN_URL, None, 'Downloading login page')
  37
  38         login_form = self._form_hidden_inputs('new_user', login_page)
  39
  40         login_form.update({
  41             'user[login]': username,
  42             'user[password]': password,
  43         })
  44
  45         post_url = self._search_regex(
  46             r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
  47             'post url', default=self._LOGIN_URL, group='url')
  48
  49         if not post_url.startswith('http'):
  50             post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
  51
  52         request = sanitized_Request(
  53             post_url, urlencode_postdata(encode_dict(login_form)))
  54         request.add_header('Referer', self._LOGIN_URL)
  55
  56         response = self._download_webpage(
  57             request, None, 'Logging in as %s' % username)
  58
  59         if all(p not in response for p in ('>Logout<', 'href="/users/sign_out"')):
  60             error = self._search_regex(
  61                 r'<p class="alert alert-danger">(.+?)</p>',
  62                 response, 'error', default=None)
  63             if error:
  64                 raise ExtractorError('Unable to login: %s' % error, expected=True)
  65             raise ExtractorError('Unable to log in')
  66
  67     def _real_initialize(self):
  68         self._login()
  69
  70     def _real_extract(self, url):
  71         anime_id = self._match_id(url)
  72
  73         webpage = self._download_webpage(url, anime_id)
  74
  75         if 'data-playlist=' not in webpage:
  76             self._download_webpage(
  77                 self._APPLY_HTML5_URL, anime_id,
  78                 'Activating HTML5 beta', 'Unable to apply HTML5 beta')
  79             webpage = self._download_webpage(url, anime_id)
  80
  81         csrf_token = self._html_search_meta(
  82             'csrf-token', webpage, 'csrf token', fatal=True)
  83
  84         anime_title = self._html_search_regex(
  85             r'(?s)<h1[^>]+itemprop="name"[^>]*>(.+?)</h1>',
  86             webpage, 'anime name')
  87         anime_description = self._html_search_regex(
  88             r'(?s)<div[^>]+itemprop="description"[^>]*>(.+?)</div>',
  89             webpage, 'anime description', default=None)
  90
  91         entries = []
  92
  93         for episode_html in re.findall(r'(?s)<h3[^>]+class="episodebox-title".+?>Episodeninhalt<', webpage):
  94             m = re.search(
  95                 r'class="episodebox-title"[^>]+title="Episode (?P<number>\d+) - (?P<title>.+?)"', episode_html)
  96             if not m:
  97                 continue
  98
  99             episode_number = int(m.group('number'))
 100             episode_title = m.group('title')
 101             video_id = 'episode-%d' % episode_number
 102
 103             common_info = {
 104                 'id': video_id,
 105                 'series': anime_title,
 106                 'episode': episode_title,
 107                 'episode_number': episode_number,
 108             }
 109
 110             formats = []
 111
 112             playlist_url = self._search_regex(
 113                 r'data-playlist=(["\'])(?P<url>.+?)\1',
 114                 episode_html, 'data playlist', default=None, group='url')
 115             if playlist_url:
 116                 request = sanitized_Request(
 117                     compat_urlparse.urljoin(url, playlist_url),
 118                     headers={
 119                         'X-Requested-With': 'XMLHttpRequest',
 120                         'X-CSRF-Token': csrf_token,
 121                         'Referer': url,
 122                         'Accept': 'application/json, text/javascript, */*; q=0.01',
 123                     })
 124
 125                 playlist = self._download_json(
 126                     request, video_id, 'Downloading playlist JSON', fatal=False)
 127                 if playlist:
 128                     playlist = playlist['playlist'][0]
 129                     title = playlist['title']
 130                     description = playlist.get('description')
 131                     for source in playlist.get('sources', []):
 132                         file_ = source.get('file')
 133                         if file_ and determine_ext(file_) == 'm3u8':
 134                             formats = self._extract_m3u8_formats(
 135                                 file_, video_id, 'mp4',
 136                                 entry_protocol='m3u8_native', m3u8_id='hls')
 137
 138             if formats:
 139                 f = common_info.copy()
 140                 f.update({
 141                     'title': title,
 142                     'description': description,
 143                     'formats': formats,
 144                 })
 145                 entries.append(f)
 146
 147             m = re.search(
 148                 r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>Teaser<',
 149                 episode_html)
 150             if m:
 151                 f = common_info.copy()
 152                 f.update({
 153                     'id': '%s-teaser' % f['id'],
 154                     'title': m.group('title'),
 155                     'url': compat_urlparse.urljoin(url, m.group('href')),
 156                 })
 157                 entries.append(f)
 158
 159         return self.playlist_result(entries, anime_id, anime_title, anime_description)