_ 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         # Episodes without titles
  35         'url': 'https://www.anime-on-demand.de/anime/162',
  36         'only_matching': True,
  37     }]
  38
  39     def _login(self):
  40         (username, password) = self._get_login_info()
  41         if username is None:
  42             return
  43
  44         login_page = self._download_webpage(
  45             self._LOGIN_URL, None, 'Downloading login page')
  46
  47         login_form = self._form_hidden_inputs('new_user', login_page)
  48
  49         login_form.update({
  50             'user[login]': username,
  51             'user[password]': password,
  52         })
  53
  54         post_url = self._search_regex(
  55             r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
  56             'post url', default=self._LOGIN_URL, group='url')
  57
  58         if not post_url.startswith('http'):
  59             post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
  60
  61         request = sanitized_Request(
  62             post_url, urlencode_postdata(encode_dict(login_form)))
  63         request.add_header('Referer', self._LOGIN_URL)
  64
  65         response = self._download_webpage(
  66             request, None, 'Logging in as %s' % username)
  67
  68         if all(p not in response for p in ('>Logout<', 'href="/users/sign_out"')):
  69             error = self._search_regex(
  70                 r'<p class="alert alert-danger">(.+?)</p>',
  71                 response, 'error', default=None)
  72             if error:
  73                 raise ExtractorError('Unable to login: %s' % error, expected=True)
  74             raise ExtractorError('Unable to log in')
  75
  76     def _real_initialize(self):
  77         self._login()
  78
  79     def _real_extract(self, url):
  80         anime_id = self._match_id(url)
  81
  82         webpage = self._download_webpage(url, anime_id)
  83
  84         if 'data-playlist=' not in webpage:
  85             self._download_webpage(
  86                 self._APPLY_HTML5_URL, anime_id,
  87                 'Activating HTML5 beta', 'Unable to apply HTML5 beta')
  88             webpage = self._download_webpage(url, anime_id)
  89
  90         csrf_token = self._html_search_meta(
  91             'csrf-token', webpage, 'csrf token', fatal=True)
  92
  93         anime_title = self._html_search_regex(
  94             r'(?s)<h1[^>]+itemprop="name"[^>]*>(.+?)</h1>',
  95             webpage, 'anime name')
  96         anime_description = self._html_search_regex(
  97             r'(?s)<div[^>]+itemprop="description"[^>]*>(.+?)</div>',
  98             webpage, 'anime description', default=None)
  99
 100         entries = []
 101
 102         for num, episode_html in enumerate(re.findall(
 103                 r'(?s)<h3[^>]+class="episodebox-title".+?>Episodeninhalt<', webpage)):
 104             episodebox_title = self._search_regex(
 105                 (r'class="episodebox-title"[^>]+title="(.+?)"',
 106                  r'class="episodebox-title"[^>]+>(.+?)<'),
 107                 webpage, 'episodebox title', default=None)
 108             if not episodebox_title:
 109                 continue
 110
 111             episode_number = int(self._search_regex(
 112                 r'^(?:Episode|Film)\s*(\d+)',
 113                 episodebox_title, 'episode number', default=num))
 114             episode_title = self._search_regex(
 115                 r'(?:Episode|Film)\s*\d+\s*-\s*(?P<title>.+?)',
 116                 episodebox_title, 'episode title', default=None)
 117
 118             video_id = 'episode-%d' % episode_number
 119
 120             common_info = {
 121                 'id': video_id,
 122                 'series': anime_title,
 123                 'episode': episode_title,
 124                 'episode_number': episode_number,
 125             }
 126
 127             formats = []
 128
 129             playlist_url = self._search_regex(
 130                 r'data-playlist=(["\'])(?P<url>.+?)\1',
 131                 episode_html, 'data playlist', default=None, group='url')
 132             if playlist_url:
 133                 request = sanitized_Request(
 134                     compat_urlparse.urljoin(url, playlist_url),
 135                     headers={
 136                         'X-Requested-With': 'XMLHttpRequest',
 137                         'X-CSRF-Token': csrf_token,
 138                         'Referer': url,
 139                         'Accept': 'application/json, text/javascript, */*; q=0.01',
 140                     })
 141
 142                 playlist = self._download_json(
 143                     request, video_id, 'Downloading playlist JSON', fatal=False)
 144                 if playlist:
 145                     playlist = playlist['playlist'][0]
 146                     title = playlist['title']
 147                     description = playlist.get('description')
 148                     for source in playlist.get('sources', []):
 149                         file_ = source.get('file')
 150                         if file_ and determine_ext(file_) == 'm3u8':
 151                             formats = self._extract_m3u8_formats(
 152                                 file_, video_id, 'mp4',
 153                                 entry_protocol='m3u8_native', m3u8_id='hls')
 154
 155             if formats:
 156                 f = common_info.copy()
 157                 f.update({
 158                     'title': title,
 159                     'description': description,
 160                     'formats': formats,
 161                 })
 162                 entries.append(f)
 163
 164             m = re.search(
 165                 r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>Teaser<',
 166                 episode_html)
 167             if m:
 168                 f = common_info.copy()
 169                 f.update({
 170                     'id': '%s-teaser' % f['id'],
 171                     'title': m.group('title'),
 172                     'url': compat_urlparse.urljoin(url, m.group('href')),
 173                 })
 174                 entries.append(f)
 175
 176         return self.playlist_result(entries, anime_id, anime_title, anime_description)