]> gitweb @ CieloNegro.org - youtube-dl.git/blob - youtube_dl/extractor/funimation.py
[ard] Improve _VALID_URL (closes #25134) (#25198)
[youtube-dl.git] / youtube_dl / extractor / funimation.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import random
5 import string
6
7 from .common import InfoExtractor
8 from ..compat import compat_HTTPError
9 from ..utils import (
10     determine_ext,
11     int_or_none,
12     js_to_json,
13     ExtractorError,
14     urlencode_postdata
15 )
16
17
18 class FunimationIE(InfoExtractor):
19     _VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/shows/[^/]+/(?P<id>[^/?#&]+)'
20
21     _NETRC_MACHINE = 'funimation'
22     _TOKEN = None
23
24     _TESTS = [{
25         'url': 'https://www.funimation.com/shows/hacksign/role-play/',
26         'info_dict': {
27             'id': '91144',
28             'display_id': 'role-play',
29             'ext': 'mp4',
30             'title': '.hack//SIGN - Role Play',
31             'description': 'md5:b602bdc15eef4c9bbb201bb6e6a4a2dd',
32             'thumbnail': r're:https?://.*\.jpg',
33         },
34         'params': {
35             # m3u8 download
36             'skip_download': True,
37         },
38     }, {
39         'url': 'https://www.funimation.com/shows/attack-on-titan-junior-high/broadcast-dub-preview/',
40         'info_dict': {
41             'id': '210051',
42             'display_id': 'broadcast-dub-preview',
43             'ext': 'mp4',
44             'title': 'Attack on Titan: Junior High - Broadcast Dub Preview',
45             'thumbnail': r're:https?://.*\.(?:jpg|png)',
46         },
47         'params': {
48             # m3u8 download
49             'skip_download': True,
50         },
51     }, {
52         'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/drop-impact/simulcast/',
53         'only_matching': True,
54     }]
55
56     def _login(self):
57         username, password = self._get_login_info()
58         if username is None:
59             return
60         try:
61             data = self._download_json(
62                 'https://prod-api-funimationnow.dadcdigital.com/api/auth/login/',
63                 None, 'Logging in', data=urlencode_postdata({
64                     'username': username,
65                     'password': password,
66                 }))
67             self._TOKEN = data['token']
68         except ExtractorError as e:
69             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
70                 error = self._parse_json(e.cause.read().decode(), None)['error']
71                 raise ExtractorError(error, expected=True)
72             raise
73
74     def _real_initialize(self):
75         self._login()
76
77     def _real_extract(self, url):
78         display_id = self._match_id(url)
79         webpage = self._download_webpage(url, display_id)
80
81         def _search_kane(name):
82             return self._search_regex(
83                 r"KANE_customdimensions\.%s\s*=\s*'([^']+)';" % name,
84                 webpage, name, default=None)
85
86         title_data = self._parse_json(self._search_regex(
87             r'TITLE_DATA\s*=\s*({[^}]+})',
88             webpage, 'title data', default=''),
89             display_id, js_to_json, fatal=False) or {}
90
91         video_id = title_data.get('id') or self._search_regex([
92             r"KANE_customdimensions.videoID\s*=\s*'(\d+)';",
93             r'<iframe[^>]+src="/player/(\d+)',
94         ], webpage, 'video_id', default=None)
95         if not video_id:
96             player_url = self._html_search_meta([
97                 'al:web:url',
98                 'og:video:url',
99                 'og:video:secure_url',
100             ], webpage, fatal=True)
101             video_id = self._search_regex(r'/player/(\d+)', player_url, 'video id')
102
103         title = episode = title_data.get('title') or _search_kane('videoTitle') or self._og_search_title(webpage)
104         series = _search_kane('showName')
105         if series:
106             title = '%s - %s' % (series, title)
107         description = self._html_search_meta(['description', 'og:description'], webpage, fatal=True)
108
109         try:
110             headers = {}
111             if self._TOKEN:
112                 headers['Authorization'] = 'Token %s' % self._TOKEN
113             sources = self._download_json(
114                 'https://www.funimation.com/api/showexperience/%s/' % video_id,
115                 video_id, headers=headers, query={
116                     'pinst_id': ''.join([random.choice(string.digits + string.ascii_letters) for _ in range(8)]),
117                 })['items']
118         except ExtractorError as e:
119             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
120                 error = self._parse_json(e.cause.read(), video_id)['errors'][0]
121                 raise ExtractorError('%s said: %s' % (
122                     self.IE_NAME, error.get('detail') or error.get('title')), expected=True)
123             raise
124
125         formats = []
126         for source in sources:
127             source_url = source.get('src')
128             if not source_url:
129                 continue
130             source_type = source.get('videoType') or determine_ext(source_url)
131             if source_type == 'm3u8':
132                 formats.extend(self._extract_m3u8_formats(
133                     source_url, video_id, 'mp4',
134                     m3u8_id='hls', fatal=False))
135             else:
136                 formats.append({
137                     'format_id': source_type,
138                     'url': source_url,
139                 })
140         self._sort_formats(formats)
141
142         return {
143             'id': video_id,
144             'display_id': display_id,
145             'title': title,
146             'description': description,
147             'thumbnail': self._og_search_thumbnail(webpage),
148             'series': series,
149             'season_number': int_or_none(title_data.get('seasonNum') or _search_kane('season')),
150             'episode_number': int_or_none(title_data.get('episodeNum')),
151             'episode': episode,
152             'season_id': title_data.get('seriesId'),
153             'formats': formats,
154         }