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