_ 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     _NETRC_MACHINE = 'animeondemand'
  21     _TESTS = [{
  22         'url': 'https://www.anime-on-demand.de/anime/161',
  23         'info_dict': {
  24             'id': '161',
  25             'title': 'Grimgar, Ashes and Illusions (OmU)',
  26             'description': 'md5:6681ce3c07c7189d255ac6ab23812d31',
  27         },
  28         'playlist_mincount': 4,
  29     }, {
  30         # Film wording is used instead of Episode
  31         'url': 'https://www.anime-on-demand.de/anime/39',
  32         'only_matching': True,
  33     }]
  34
  35     def _login(self):
  36         (username, password) = self._get_login_info()
  37         if username is None:
  38             return
  39
  40         login_page = self._download_webpage(
  41             self._LOGIN_URL, None, 'Downloading login page')
  42
  43         login_form = self._form_hidden_inputs('new_user', login_page)
  44
  45         login_form.update({
  46             'user[login]': username,
  47             'user[password]': password,
  48         })
  49
  50         post_url = self._search_regex(
  51             r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
  52             'post url', default=self._LOGIN_URL, group='url')
  53
  54         if not post_url.startswith('http'):
  55             post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
  56
  57         request = sanitized_Request(
  58             post_url, urlencode_postdata(encode_dict(login_form)))
  59         request.add_header('Referer', self._LOGIN_URL)
  60
  61         response = self._download_webpage(
  62             request, None, 'Logging in as %s' % username)
  63
  64         if all(p not in response for p in ('>Logout<', 'href="/users/sign_out"')):
  65             error = self._search_regex(
  66                 r'<p class="alert alert-danger">(.+?)</p>',
  67                 response, 'error', default=None)
  68             if error:
  69                 raise ExtractorError('Unable to login: %s' % error, expected=True)
  70             raise ExtractorError('Unable to log in')
  71
  72     def _real_initialize(self):
  73         self._login()
  74
  75     def _real_extract(self, url):
  76         anime_id = self._match_id(url)
  77
  78         webpage = self._download_webpage(url, anime_id)
  79
  80         if 'data-playlist=' not in webpage:
  81             self._download_webpage(
  82                 self._APPLY_HTML5_URL, anime_id,
  83                 'Activating HTML5 beta', 'Unable to apply HTML5 beta')
  84             webpage = self._download_webpage(url, anime_id)
  85
  86         csrf_token = self._html_search_meta(
  87             'csrf-token', webpage, 'csrf token', fatal=True)
  88
  89         anime_title = self._html_search_regex(
  90             r'(?s)<h1[^>]+itemprop="name"[^>]*>(.+?)</h1>',
  91             webpage, 'anime name')
  92         anime_description = self._html_search_regex(
  93             r'(?s)<div[^>]+itemprop="description"[^>]*>(.+?)</div>',
  94             webpage, 'anime description', default=None)
  95
  96         entries = []
  97
  98         for episode_html in re.findall(r'(?s)<h3[^>]+class="episodebox-title".+?>Episodeninhalt<', webpage):
  99             m = re.search(
 100                 r'class="episodebox-title"[^>]+title="(?:Episode|Film)\s*(?P<number>\d+)\s*-\s*(?P<title>.+?)"', episode_html)
 101             if not m:
 102                 continue
 103
 104             episode_number = int(m.group('number'))
 105             episode_title = m.group('title')
 106             video_id = 'episode-%d' % episode_number
 107
 108             common_info = {
 109                 'id': video_id,
 110                 'series': anime_title,
 111                 'episode': episode_title,
 112                 'episode_number': episode_number,
 113             }
 114
 115             formats = []
 116
 117             playlist_url = self._search_regex(
 118                 r'data-playlist=(["\'])(?P<url>.+?)\1',
 119                 episode_html, 'data playlist', default=None, group='url')
 120             if playlist_url:
 121                 request = sanitized_Request(
 122                     compat_urlparse.urljoin(url, playlist_url),
 123                     headers={
 124                         'X-Requested-With': 'XMLHttpRequest',
 125                         'X-CSRF-Token': csrf_token,
 126                         'Referer': url,
 127                         'Accept': 'application/json, text/javascript, */*; q=0.01',
 128                     })
 129
 130                 playlist = self._download_json(
 131                     request, video_id, 'Downloading playlist JSON', fatal=False)
 132                 if playlist:
 133                     playlist = playlist['playlist'][0]
 134                     title = playlist['title']
 135                     description = playlist.get('description')
 136                     for source in playlist.get('sources', []):
 137                         file_ = source.get('file')
 138                         if file_ and determine_ext(file_) == 'm3u8':
 139                             formats = self._extract_m3u8_formats(
 140                                 file_, video_id, 'mp4',
 141                                 entry_protocol='m3u8_native', m3u8_id='hls')
 142
 143             if formats:
 144                 f = common_info.copy()
 145                 f.update({
 146                     'title': title,
 147                     'description': description,
 148                     'formats': formats,
 149                 })
 150                 entries.append(f)
 151
 152             m = re.search(
 153                 r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>Teaser<',
 154                 episode_html)
 155             if m:
 156                 f = common_info.copy()
 157                 f.update({
 158                     'id': '%s-teaser' % f['id'],
 159                     'title': m.group('title'),
 160                     'url': compat_urlparse.urljoin(url, m.group('href')),
 161                 })
 162                 entries.append(f)
 163
 164         return self.playlist_result(entries, anime_id, anime_title, anime_description)