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
|
# -*- coding: utf-8 -*-
# Copyright 2022-2023 Mike Fährmann
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation.
"""Extractors for https://bunkr.si/"""
from .common import Extractor
from .lolisafe import LolisafeAlbumExtractor
from .. import text, config, exception
import random
if config.get(("extractor", "bunkr"), "tlds"):
BASE_PATTERN = (
r"(?:bunkr:(?:https?://)?([^/?#]+)|"
r"(?:https?://)?(?:app\.)?(bunkr+\.\w+))"
)
else:
BASE_PATTERN = (
r"(?:bunkr:(?:https?://)?([^/?#]+)|"
r"(?:https?://)?(?:app\.)?(bunkr+"
r"\.(?:s[kiu]|c[ir]|fi|p[hks]|ru|la|is|to|a[cx]"
r"|black|cat|media|red|site|ws|org)))"
)
DOMAINS = [
"bunkr.ac",
"bunkr.ci",
"bunkr.cr",
"bunkr.fi",
"bunkr.ph",
"bunkr.pk",
"bunkr.ps",
"bunkr.si",
"bunkr.sk",
"bunkr.ws",
"bunkr.black",
"bunkr.red",
"bunkr.media",
"bunkr.site",
]
LEGACY_DOMAINS = {
"bunkr.ax",
"bunkr.cat",
"bunkr.ru",
"bunkrr.ru",
"bunkr.su",
"bunkrr.su",
"bunkr.la",
"bunkr.is",
"bunkr.to",
}
CF_DOMAINS = set()
class BunkrAlbumExtractor(LolisafeAlbumExtractor):
"""Extractor for bunkr.si albums"""
category = "bunkr"
root = "https://bunkr.si"
pattern = BASE_PATTERN + r"/a/([^/?#]+)"
example = "https://bunkr.si/a/ID"
def __init__(self, match):
LolisafeAlbumExtractor.__init__(self, match)
domain = self.groups[0] or self.groups[1]
if domain not in LEGACY_DOMAINS:
self.root = "https://" + domain
def request(self, url, **kwargs):
kwargs["allow_redirects"] = False
while True:
try:
response = Extractor.request(self, url, **kwargs)
if response.status_code < 300:
return response
# redirect
url = response.headers["Location"]
root, path = self._split(url)
if root not in CF_DOMAINS:
continue
self.log.debug("Redirect to known CF challenge domain '%s'",
root)
except exception.HttpError as exc:
if exc.status != 403:
raise
# CF challenge
root, path = self._split(url)
CF_DOMAINS.add(root)
self.log.debug("Added '%s' to CF challenge domains", root)
try:
DOMAINS.remove(root.rpartition("/")[2])
except ValueError:
pass
else:
if not DOMAINS:
raise exception.StopExtraction(
"All Bunkr domains require solving a CF challenge")
# select alternative domain
root = "https://" + random.choice(DOMAINS)
self.log.debug("Trying '%s' as fallback", root)
url = root + path
def fetch_album(self, album_id):
# album metadata
page = self.request(self.root + "/a/" + album_id).text
title, size = text.split_html(text.extr(
page, "<h1", "</span>").partition(">")[2])
if "&" in title:
title = title.replace(
"<", "<").replace(">", ">").replace("&", "&")
# files
items = list(text.extract_iter(page, "<!-- item -->", "<!-- -->"))
return self._extract_files(items), {
"album_id" : album_id,
"album_name" : title,
"album_size" : text.extr(size, "(", ")"),
"count" : len(items),
}
def _extract_files(self, items):
for item in items:
try:
url = text.extr(item, ' href="', '"')
file = self._extract_file(text.unescape(url))
info = text.split_html(item)
file["name"] = info[0]
file["size"] = info[2]
file["date"] = text.parse_datetime(
info[-1], "%H:%M:%S %d/%m/%Y")
yield file
except exception.StopExtraction:
raise
except Exception as exc:
self.log.error("%s: %s", exc.__class__.__name__, exc)
self.log.debug("", exc_info=exc)
def _extract_file(self, webpage_url):
response = self.request(webpage_url)
page = response.text
file_url = (text.extr(page, '<source src="', '"') or
text.extr(page, '<img src="', '"'))
if not file_url:
webpage_url = text.unescape(text.rextract(
page, ' href="', '"', page.rindex("Download"))[0])
response = self.request(webpage_url)
file_url = text.rextract(response.text, ' href="', '"')[0]
return {
"file" : text.unescape(file_url),
"_http_headers" : {"Referer": response.url},
"_http_validate": self._validate,
}
def _validate(self, response):
if response.history and response.url.endswith("/maintenance-vid.mp4"):
self.log.warning("File server in maintenance mode")
return False
return True
def _split(self, url):
pos = url.index("/", 8)
return url[:pos], url[pos:]
class BunkrMediaExtractor(BunkrAlbumExtractor):
"""Extractor for bunkr.si media links"""
subcategory = "media"
directory_fmt = ("{category}",)
pattern = BASE_PATTERN + r"(/[vid]/[^/?#]+)"
example = "https://bunkr.si/v/FILENAME"
def fetch_album(self, album_id):
try:
file = self._extract_file(self.root + album_id)
except Exception as exc:
self.log.error("%s: %s", exc.__class__.__name__, exc)
return (), {}
return (file,), {
"album_id" : "",
"album_name" : "",
"album_size" : -1,
"description": "",
"count" : 1,
}
|
