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
|
# -*- 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://poipiku.com/"""
from .common import Extractor, Message
from .. import text
BASE_PATTERN = r"(?:https?://)?poipiku\.com"
class PoipikuExtractor(Extractor):
"""Base class for poipiku extractors"""
category = "poipiku"
root = "https://poipiku.com"
directory_fmt = ("{category}", "{user_id} {user_name}")
filename_fmt = "{post_id}_{num}.{extension}"
archive_fmt = "{post_id}_{num}"
request_interval = (0.5, 1.5)
def _init(self):
self.cookies.set(
"LANG", "en", domain="poipiku.com")
self.cookies.set(
"POIPIKU_CONTENTS_VIEW_MODE", "1", domain="poipiku.com")
def items(self):
password = self.config("password", "")
for post_url in self.posts():
parts = post_url.split("/")
if post_url[0] == "/":
post_url = self.root + post_url
page = self.request(post_url).text
extr = text.extract_from(page)
post = {
"post_category": extr("<title>[", "]"),
"count" : text.parse_int(extr("(", " ")),
"post_id" : parts[-1].partition(".")[0],
"user_id" : parts[-2],
"user_name" : text.unescape(extr(
'<h2 class="UserInfoUserName">', '</').rpartition(">")[2]),
"description": text.unescape(extr(
'class="IllustItemDesc" >', '</h1>')),
"_http_headers": {"Referer": post_url},
}
yield Message.Directory, post
post["num"] = 0
while True:
thumb = extr('class="IllustItemThumbImg" src="', '"')
if not thumb:
break
elif thumb.startswith(("//img.poipiku.com/img/", "/img/")):
continue
post["num"] += 1
url = text.ensure_http_scheme(thumb[:-8]).replace(
"//img.", "//img-org.", 1)
yield Message.Url, url, text.nameext_from_url(url, post)
if not extr('ShowAppendFile', '<'):
continue
url = self.root + "/f/ShowAppendFileF.jsp"
headers = {
"Accept" : "application/json, text/javascript, */*; q=0.01",
"X-Requested-With": "XMLHttpRequest",
"Origin" : self.root,
"Referer": post_url,
}
data = {
"UID": post["user_id"],
"IID": post["post_id"],
"PAS": password,
"MD" : "0",
"TWF": "-1",
}
resp = self.request(
url, method="POST", headers=headers, data=data).json()
page = resp["html"]
if (resp.get("result_num") or 0) < 0:
self.log.warning("'%s'", page.replace("<br/>", " "))
for thumb in text.extract_iter(
page, 'class="IllustItemThumbImg" src="', '"'):
post["num"] += 1
url = text.ensure_http_scheme(thumb[:-8]).replace(
"//img.", "//img-org.", 1)
yield Message.Url, url, text.nameext_from_url(url, post)
class PoipikuUserExtractor(PoipikuExtractor):
"""Extractor for posts from a poipiku user"""
subcategory = "user"
pattern = (BASE_PATTERN + r"/(?:IllustListPcV\.jsp\?PG=(\d+)&ID=)?"
r"(\d+)/?(?:$|[?&#])")
example = "https://poipiku.com/12345/"
def __init__(self, match):
PoipikuExtractor.__init__(self, match)
self._page, self.user_id = match.groups()
def posts(self):
url = self.root + "/IllustListPcV.jsp"
params = {
"PG" : text.parse_int(self._page, 0),
"ID" : self.user_id,
"KWD": "",
}
while True:
page = self.request(url, params=params).text
cnt = 0
for path in text.extract_iter(
page, 'class="IllustInfo" href="', '"'):
yield path
cnt += 1
if cnt < 48:
return
params["PG"] += 1
class PoipikuPostExtractor(PoipikuExtractor):
"""Extractor for a poipiku post"""
subcategory = "post"
pattern = BASE_PATTERN + r"/(\d+)/(\d+)"
example = "https://poipiku.com/12345/12345.html"
def __init__(self, match):
PoipikuExtractor.__init__(self, match)
self.user_id, self.post_id = match.groups()
def posts(self):
return ("/{}/{}.html".format(self.user_id, self.post_id),)
|
