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
|
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urllib_request
from ..utils import (
clean_html,
determine_ext,
encode_dict,
sanitized_Request,
ExtractorError,
urlencode_postdata
)
class FunimationIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?funimation\.com/shows/[^/]+/videos/official/(?P<id>[^?]+)'
_TEST = {
'url': 'http://www.funimation.com/shows/air/videos/official/breeze',
'info_dict': {
'id': 'AIRENG0001',
'title': 'Air - 1 - Breeze ',
'ext': 'mp4',
'thumbnail': 'http://www.funimation.com/admin/uploads/default/recap_thumbnails/7555590/home_spotlight/AIR0001.jpg',
'description': 'Travelling puppeteer Yukito arrives in a small town where he hopes to earn money through the magic of his puppets. When a young girl named Misuzu lures him to her home with the promise of food, his life changes forever. ',
}
}
def _download_webpage(self, url_or_request, video_id, note='Downloading webpage'):
HEADERS = {
'User-Agent': 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0',
}
if isinstance(url_or_request, compat_urllib_request.Request):
for header, value in HEADERS.items():
url_or_request.add_header(header, value)
else:
url_or_request = sanitized_Request(url_or_request, headers=HEADERS)
response = super(FunimationIE, self)._download_webpage(url_or_request, video_id, note)
return response
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
data = urlencode_postdata(encode_dict({
'email_field': username,
'password_field': password,
}))
login_request = sanitized_Request('http://www.funimation.com/login', data, headers={
'Content-Type': 'application/x-www-form-urlencoded'
})
login = self._download_webpage(
login_request, None, 'Logging in as %s' % username)
if re.search(r'<meta property="og:url" content="http://www.funimation.com/login"/>', login) is not None:
raise ExtractorError('Unable to login, wrong username or password.', expected=True)
def _real_initialize(self):
self._login()
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
items = self._parse_json(
self._search_regex(
r'var\s+playersData\s*=\s*(\[.+?\]);\n',
webpage, 'players data'),
display_id)[0]['playlist'][0]['items']
item = next(item for item in items if item.get('itemAK') == display_id)
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',
}
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
errors = []
formats = []
for video in item['videoSet']:
auth_token = video.get('authToken')
if not auth_token:
continue
funimation_id = video.get('FUNImationID') or video.get('videoId')
if not auth_token.startswith('?'):
auth_token = '?%s' % auth_token
for quality in ('sd', 'hd', 'hd1080'):
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':
m3u8_formats = self._extract_m3u8_formats(
format_url + auth_token, display_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id=funimation_id or 'hls', fatal=False)
if m3u8_formats:
formats.extend(m3u8_formats)
else:
formats.append({
'url': format_url + auth_token,
})
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)
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,
}
|
