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
|
# -*- coding: utf-8 -*-
# Copyright 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://vipergirls.to/"""
from .common import Extractor, Message
from .. import text, util, exception
from ..cache import cache
from xml.etree import ElementTree
BASE_PATTERN = r"(?:https?://)?(?:www\.)?vipergirls\.to"
class VipergirlsExtractor(Extractor):
"""Base class for vipergirls extractors"""
category = "vipergirls"
root = "https://vipergirls.to"
request_interval = 0.5
request_interval_min = 0.2
cookies_domain = ".vipergirls.to"
cookies_names = ("vg_userid", "vg_password")
def _init(self):
domain = self.config("domain")
if domain:
pos = domain.find("://")
if pos >= 0:
self.root = domain.rstrip("/")
self.cookies_domain = "." + domain[pos+1:].strip("/")
else:
domain = domain.strip("/")
self.root = "https://" + domain
self.cookies_domain = "." + domain
else:
self.root = "https://viper.click"
self.cookies_domain = ".viper.click"
def items(self):
self.login()
root = self.posts()
forum_title = root[1].attrib["title"]
thread_title = root[2].attrib["title"]
like = self.config("like")
if like:
user_hash = root[0].get("hash")
if len(user_hash) < 16:
self.log.warning("Login required to like posts")
like = False
posts = root.iter("post")
if self.page:
util.advance(posts, (text.parse_int(self.page[5:]) - 1) * 15)
for post in posts:
images = list(post)
data = post.attrib
data["forum_title"] = forum_title
data["thread_id"] = self.thread_id
data["thread_title"] = thread_title
data["post_id"] = data.pop("id")
data["post_num"] = data.pop("number")
data["post_title"] = data.pop("title")
data["count"] = len(images)
del data["imagecount"]
yield Message.Directory, data
if images:
for data["num"], image in enumerate(images, 1):
yield Message.Queue, image.attrib["main_url"], data
if like:
self.like(post, user_hash)
def login(self):
if self.cookies_check(self.cookies_names):
return
username, password = self._get_auth_info()
if username:
self.cookies_update(self._login_impl(username, password))
@cache(maxage=90*86400, keyarg=1)
def _login_impl(self, username, password):
self.log.info("Logging in as %s", username)
url = "{}/login.php?do=login".format(self.root)
data = {
"vb_login_username": username,
"vb_login_password": password,
"do" : "login",
"cookieuser" : "1",
}
response = self.request(url, method="POST", data=data)
if not response.cookies.get("vg_password"):
raise exception.AuthenticationError()
return {cookie.name: cookie.value
for cookie in response.cookies}
def like(self, post, user_hash):
url = self.root + "/post_thanks.php"
params = {
"do" : "post_thanks_add",
"p" : post.get("id"),
"securitytoken": user_hash,
}
with self.request(url, params=params, allow_redirects=False):
pass
class VipergirlsThreadExtractor(VipergirlsExtractor):
"""Extractor for vipergirls threads"""
subcategory = "thread"
pattern = (BASE_PATTERN +
r"/threads/(\d+)(?:-[^/?#]+)?(/page\d+)?(?:$|#|\?(?!p=))")
example = "https://vipergirls.to/threads/12345-TITLE"
def __init__(self, match):
VipergirlsExtractor.__init__(self, match)
self.thread_id, self.page = match.groups()
def posts(self):
url = "{}/vr.php?t={}".format(self.root, self.thread_id)
return ElementTree.fromstring(self.request(url).text)
class VipergirlsPostExtractor(VipergirlsExtractor):
"""Extractor for vipergirls posts"""
subcategory = "post"
pattern = (BASE_PATTERN +
r"/threads/(\d+)(?:-[^/?#]+)?\?p=\d+[^#]*#post(\d+)")
example = "https://vipergirls.to/threads/12345-TITLE?p=23456#post23456"
def __init__(self, match):
VipergirlsExtractor.__init__(self, match)
self.thread_id, self.post_id = match.groups()
self.page = 0
def posts(self):
url = "{}/vr.php?p={}".format(self.root, self.post_id)
return ElementTree.fromstring(self.request(url).text)
|
