aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/funimation.py
blob: 1eb528f31f4b908b8d832cfe1fd4e1647ef74058 (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
# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor
from ..utils import (
    clean_html,
    determine_ext,
    int_or_none,
    sanitized_Request,
    ExtractorError,
    urlencode_postdata
)


class FunimationIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?funimation\.com/shows/[^/]+/videos/(?:official|promotional)/(?P<id>[^/?#&]+)'

    _NETRC_MACHINE = 'funimation'

    _TESTS = [{
        'url': 'http://www.funimation.com/shows/air/videos/official/breeze',
        'info_dict': {
            'id': '658',
            'display_id': 'breeze',
            'ext': 'mp4',
            'title': 'Air - 1 - Breeze',
            'description': 'md5:1769f43cd5fc130ace8fd87232207892',
            'thumbnail': 're:https?://.*\.jpg',
        },
    }, {
        'url': 'http://www.funimation.com/shows/hacksign/videos/official/role-play',
        'info_dict': {
            'id': '31128',
            'display_id': 'role-play',
            'ext': 'mp4',
            'title': '.hack//SIGN - 1 - Role Play',
            'description': 'md5:b602bdc15eef4c9bbb201bb6e6a4a2dd',
            'thumbnail': 're:https?://.*\.jpg',
        },
    }, {
        'url': 'http://www.funimation.com/shows/attack-on-titan-junior-high/videos/promotional/broadcast-dub-preview',
        'info_dict': {
            'id': '9635',
            'display_id': 'broadcast-dub-preview',
            'ext': 'mp4',
            'title': 'Attack on Titan: Junior High - Broadcast Dub Preview',
            'description': 'md5:f8ec49c0aff702a7832cd81b8a44f803',
            'thumbnail': 're:https?://.*\.(?:jpg|png)',
        },
    }]

    def _login(self):
        (username, password) = self._get_login_info()
        if username is None:
            return
        data = urlencode_postdata({
            'email_field': username,
            'password_field': password,
        })
        login_request = sanitized_Request('http://www.funimation.com/login', data, headers={
            'User-Agent': 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0',
            'Content-Type': 'application/x-www-form-urlencoded'
        })
        login_page = self._download_webpage(
            login_request, None, 'Logging in as %s' % username)
        if any(p in login_page for p in ('funimation.com/logout', '>Log Out<')):
            return
        error = self._html_search_regex(
            r'(?s)<div[^>]+id=["\']errorMessages["\'][^>]*>(.+?)</div>',
            login_page, 'error messages', default=None)
        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):
        display_id = self._match_id(url)

        errors = []
        formats = []

        ERRORS_MAP = {
            'ERROR_MATURE_CONTENT_LOGGED_IN': 'matureContentLoggedIn',
            'ERROR_MATURE_CONTENT_LOGGED_OUT': 'matureContentLoggedOut',
            'ERROR_SUBSCRIPTION_LOGGED_OUT': 'subscriptionLoggedOut',
            'ERROR_VIDEO_EXPIRED': 'videoExpired',
            'ERROR_TERRITORY_UNAVAILABLE': 'territoryUnavailable',
            'SVODBASIC_SUBSCRIPTION_IN_PLAYER': 'basicSubscription',
            'SVODNON_SUBSCRIPTION_IN_PLAYER': 'nonSubscription',
            'ERROR_PLAYER_NOT_RESPONDING': 'playerNotResponding',
            'ERROR_UNABLE_TO_CONNECT_TO_CDN': 'unableToConnectToCDN',
            'ERROR_STREAM_NOT_FOUND': 'streamNotFound',
        }

        USER_AGENTS = (
            # PC UA is served with m3u8 that provides some bonus lower quality formats
            ('pc', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0'),
            # Mobile UA allows to extract direct links and also does not fail when
            # PC UA fails with hulu error (e.g.
            # http://www.funimation.com/shows/hacksign/videos/official/role-play)
            ('mobile', 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36'),
        )

        for kind, user_agent in USER_AGENTS:
            request = sanitized_Request(url)
            request.add_header('User-Agent', user_agent)
            webpage = self._download_webpage(
                request, display_id, 'Downloading %s webpage' % kind)

            playlist = self._parse_json(
                self._search_regex(
                    r'var\s+playersData\s*=\s*(\[.+?\]);\n',
                    webpage, 'players data'),
                display_id)[0]['playlist']

            items = next(item['items'] for item in playlist if item.get('items'))
            item = next(item for item in items if item.get('itemAK') == display_id)

            error_messages = {}
            video_error_messages = self._search_regex(
                r'var\s+videoErrorMessages\s*=\s*({.+?});\n',
                webpage, 'error messages', default=None)
            if video_error_messages:
                error_messages_json = self._parse_json(video_error_messages, display_id, fatal=False)
                if error_messages_json:
                    for _, error in error_messages_json.items():
                        type_ = error.get('type')
                        description = error.get('description')
                        content = error.get('content')
                        if type_ == 'text' and description and content:
                            error_message = ERRORS_MAP.get(description)
                            if error_message:
                                error_messages[error_message] = content

            for video in item.get('videoSet', []):
                auth_token = video.get('authToken')
                if not auth_token:
                    continue
                funimation_id = video.get('FUNImationID') or video.get('videoId')
                preference = 1 if video.get('languageMode') == 'dub' else 0
                if not auth_token.startswith('?'):
                    auth_token = '?%s' % auth_token
                for quality, height in (('sd', 480), ('hd', 720), ('hd1080', 1080)):
                    format_url = video.get('%sUrl' % quality)
                    if not format_url:
                        continue
                    if not format_url.startswith(('http', '//')):
                        errors.append(format_url)
                        continue
                    if determine_ext(format_url) == 'm3u8':
                        formats.extend(self._extract_m3u8_formats(
                            format_url + auth_token, display_id, 'mp4', entry_protocol='m3u8_native',
                            preference=preference, m3u8_id='%s-hls' % funimation_id, fatal=False))
                    else:
                        tbr = int_or_none(self._search_regex(
                            r'-(\d+)[Kk]', format_url, 'tbr', default=None))
                        formats.append({
                            'url': format_url + auth_token,
                            'format_id': '%s-http-%dp' % (funimation_id, height),
                            'height': height,
                            'tbr': tbr,
                            'preference': preference,
                        })

        if not formats and errors:
            raise ExtractorError(
                '%s returned error: %s'
                % (self.IE_NAME, clean_html(error_messages.get(errors[0], errors[0]))),
                expected=True)

        self._sort_formats(formats)

        title = item['title']
        artist = item.get('artist')
        if artist:
            title = '%s - %s' % (artist, title)
        description = self._og_search_description(webpage) or item.get('description')
        thumbnail = self._og_search_thumbnail(webpage) or item.get('posterUrl')
        video_id = item.get('itemId') or display_id

        return {
            'id': video_id,
            'display_id': display_id,
            'title': title,
            'description': description,
            'thumbnail': thumbnail,
            'formats': formats,
        }