aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/animeondemand.py
blob: 00ce684d1c9811ef3ba885194c23fd012d935b6b (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
    determine_ext,
    extract_attributes,
    ExtractorError,
    url_or_none,
    urlencode_postdata,
    urljoin,
)


class AnimeOnDemandIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?anime-on-demand\.de/anime/(?P<id>\d+)'
    _LOGIN_URL = 'https://www.anime-on-demand.de/users/sign_in'
    _APPLY_HTML5_URL = 'https://www.anime-on-demand.de/html5apply'
    _NETRC_MACHINE = 'animeondemand'
    # German-speaking countries of Europe
    _GEO_COUNTRIES = ['AT', 'CH', 'DE', 'LI', 'LU']
    _TESTS = [{
        # jap, OmU
        'url': 'https://www.anime-on-demand.de/anime/161',
        'info_dict': {
            'id': '161',
            'title': 'Grimgar, Ashes and Illusions (OmU)',
            'description': 'md5:6681ce3c07c7189d255ac6ab23812d31',
        },
        'playlist_mincount': 4,
    }, {
        # Film wording is used instead of Episode, ger/jap, Dub/OmU
        'url': 'https://www.anime-on-demand.de/anime/39',
        'only_matching': True,
    }, {
        # Episodes without titles, jap, OmU
        'url': 'https://www.anime-on-demand.de/anime/162',
        'only_matching': True,
    }, {
        # ger/jap, Dub/OmU, account required
        'url': 'https://www.anime-on-demand.de/anime/169',
        'only_matching': True,
    }, {
        # Full length film, non-series, ger/jap, Dub/OmU, account required
        'url': 'https://www.anime-on-demand.de/anime/185',
        'only_matching': True,
    }, {
        # Flash videos
        'url': 'https://www.anime-on-demand.de/anime/12',
        'only_matching': True,
    }]

    def _login(self):
        username, password = self._get_login_info()
        if username is None:
            return

        login_page = self._download_webpage(
            self._LOGIN_URL, None, 'Downloading login page')

        if '>Our licensing terms allow the distribution of animes only to German-speaking countries of Europe' in login_page:
            self.raise_geo_restricted(
                '%s is only available in German-speaking countries of Europe' % self.IE_NAME)

        login_form = self._form_hidden_inputs('new_user', login_page)

        login_form.update({
            'user[login]': username,
            'user[password]': password,
        })

        post_url = self._search_regex(
            r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
            'post url', default=self._LOGIN_URL, group='url')

        if not post_url.startswith('http'):
            post_url = urljoin(self._LOGIN_URL, post_url)

        response = self._download_webpage(
            post_url, None, 'Logging in',
            data=urlencode_postdata(login_form), headers={
                'Referer': self._LOGIN_URL,
            })

        if all(p not in response for p in ('>Logout<', 'href="/users/sign_out"')):
            error = self._search_regex(
                r'<p[^>]+\bclass=(["\'])(?:(?!\1).)*\balert\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</p>',
                response, 'error', default=None, group='error')
            if error:
                raise ExtractorError('Unable to login: %s' % error, expected=True)
            raise ExtractorError('Unable to log in')

    def _real_initialize(self):
        self._login()

    def _real_extract(self, url):
        anime_id = self._match_id(url)

        webpage = self._download_webpage(url, anime_id)

        if 'data-playlist=' not in webpage:
            self._download_webpage(
                self._APPLY_HTML5_URL, anime_id,
                'Activating HTML5 beta', 'Unable to apply HTML5 beta')
            webpage = self._download_webpage(url, anime_id)

        csrf_token = self._html_search_meta(
            'csrf-token', webpage, 'csrf token', fatal=True)

        anime_title = self._html_search_regex(
            r'(?s)<h1[^>]+itemprop="name"[^>]*>(.+?)</h1>',
            webpage, 'anime name')
        anime_description = self._html_search_regex(
            r'(?s)<div[^>]+itemprop="description"[^>]*>(.+?)</div>',
            webpage, 'anime description', default=None)

        entries = []

        def extract_info(html, video_id, num=None):
            title, description = [None] * 2
            formats = []

            for input_ in re.findall(
                    r'<input[^>]+class=["\'].*?streamstarter[^>]+>', html):
                attributes = extract_attributes(input_)
                title = attributes.get('data-dialog-header')
                playlist_urls = []
                for playlist_key in ('data-playlist', 'data-otherplaylist', 'data-stream'):
                    playlist_url = attributes.get(playlist_key)
                    if isinstance(playlist_url, compat_str) and re.match(
                            r'/?[\da-zA-Z]+', playlist_url):
                        playlist_urls.append(attributes[playlist_key])
                if not playlist_urls:
                    continue

                lang = attributes.get('data-lang')
                lang_note = attributes.get('value')

                for playlist_url in playlist_urls:
                    kind = self._search_regex(
                        r'videomaterialurl/\d+/([^/]+)/',
                        playlist_url, 'media kind', default=None)
                    format_id_list = []
                    if lang:
                        format_id_list.append(lang)
                    if kind:
                        format_id_list.append(kind)
                    if not format_id_list and num is not None:
                        format_id_list.append(compat_str(num))
                    format_id = '-'.join(format_id_list)
                    format_note = ', '.join(filter(None, (kind, lang_note)))
                    item_id_list = []
                    if format_id:
                        item_id_list.append(format_id)
                    item_id_list.append('videomaterial')
                    playlist = self._download_json(
                        urljoin(url, playlist_url), video_id,
                        'Downloading %s JSON' % ' '.join(item_id_list),
                        headers={
                            'X-Requested-With': 'XMLHttpRequest',
                            'X-CSRF-Token': csrf_token,
                            'Referer': url,
                            'Accept': 'application/json, text/javascript, */*; q=0.01',
                        }, fatal=False)
                    if not playlist:
                        continue
                    stream_url = url_or_none(playlist.get('streamurl'))
                    if stream_url:
                        rtmp = re.search(
                            r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+/))(?P<playpath>mp[34]:.+)',
                            stream_url)
                        if rtmp:
                            formats.append({
                                'url': rtmp.group('url'),
                                'app': rtmp.group('app'),
                                'play_path': rtmp.group('playpath'),
                                'page_url': url,
                                'player_url': 'https://www.anime-on-demand.de/assets/jwplayer.flash-55abfb34080700304d49125ce9ffb4a6.swf',
                                'rtmp_real_time': True,
                                'format_id': 'rtmp',
                                'ext': 'flv',
                            })
                            continue
                    start_video = playlist.get('startvideo', 0)
                    playlist = playlist.get('playlist')
                    if not playlist or not isinstance(playlist, list):
                        continue
                    playlist = playlist[start_video]
                    title = playlist.get('title')
                    if not title:
                        continue
                    description = playlist.get('description')
                    for source in playlist.get('sources', []):
                        file_ = source.get('file')
                        if not file_:
                            continue
                        ext = determine_ext(file_)
                        format_id_list = [lang, kind]
                        if ext == 'm3u8':
                            format_id_list.append('hls')
                        elif source.get('type') == 'video/dash' or ext == 'mpd':
                            format_id_list.append('dash')
                        format_id = '-'.join(filter(None, format_id_list))
                        if ext == 'm3u8':
                            file_formats = self._extract_m3u8_formats(
                                file_, video_id, 'mp4',
                                entry_protocol='m3u8_native', m3u8_id=format_id, fatal=False)
                        elif source.get('type') == 'video/dash' or ext == 'mpd':
                            continue
                            file_formats = self._extract_mpd_formats(
                                file_, video_id, mpd_id=format_id, fatal=False)
                        else:
                            continue
                        for f in file_formats:
                            f.update({
                                'language': lang,
                                'format_note': format_note,
                            })
                        formats.extend(file_formats)

            return {
                'title': title,
                'description': description,
                'formats': formats,
            }

        def extract_entries(html, video_id, common_info, num=None):
            info = extract_info(html, video_id, num)

            if info['formats']:
                self._sort_formats(info['formats'])
                f = common_info.copy()
                f.update(info)
                entries.append(f)

            # Extract teaser/trailer only when full episode is not available
            if not info['formats']:
                m = re.search(
                    r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>(?P<kind>Teaser|Trailer)<',
                    html)
                if m:
                    f = common_info.copy()
                    f.update({
                        'id': '%s-%s' % (f['id'], m.group('kind').lower()),
                        'title': m.group('title'),
                        'url': urljoin(url, m.group('href')),
                    })
                    entries.append(f)

        def extract_episodes(html):
            for num, episode_html in enumerate(re.findall(
                    r'(?s)<h3[^>]+class="episodebox-title".+?>Episodeninhalt<', html), 1):
                episodebox_title = self._search_regex(
                    (r'class="episodebox-title"[^>]+title=(["\'])(?P<title>.+?)\1',
                     r'class="episodebox-title"[^>]+>(?P<title>.+?)<'),
                    episode_html, 'episodebox title', default=None, group='title')
                if not episodebox_title:
                    continue

                episode_number = int(self._search_regex(
                    r'(?:Episode|Film)\s*(\d+)',
                    episodebox_title, 'episode number', default=num))
                episode_title = self._search_regex(
                    r'(?:Episode|Film)\s*\d+\s*-\s*(.+)',
                    episodebox_title, 'episode title', default=None)

                video_id = 'episode-%d' % episode_number

                common_info = {
                    'id': video_id,
                    'series': anime_title,
                    'episode': episode_title,
                    'episode_number': episode_number,
                }

                extract_entries(episode_html, video_id, common_info)

        def extract_film(html, video_id):
            common_info = {
                'id': anime_id,
                'title': anime_title,
                'description': anime_description,
            }
            extract_entries(html, video_id, common_info)

        extract_episodes(webpage)

        if not entries:
            extract_film(webpage, anime_id)

        return self.playlist_result(entries, anime_id, anime_title, anime_description)