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
|
# -*- coding: utf-8 -*-
# Copyright 2020-2023 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://kabe-uchiroom.com/"""
from .common import Extractor, Message
from .. import text, exception
class KabeuchiUserExtractor(Extractor):
"""Extractor for all posts of a user on kabe-uchiroom.com"""
category = "kabeuchi"
subcategory = "user"
directory_fmt = ("{category}", "{twitter_user_id} {twitter_id}")
filename_fmt = "{id}_{num:>02}{title:?_//}.{extension}"
archive_fmt = "{id}_{num}"
root = "https://kabe-uchiroom.com"
pattern = r"(?:https?://)?kabe-uchiroom\.com/mypage/?\?id=(\d+)"
example = "https://kabe-uchiroom.com/mypage/?id=12345"
def __init__(self, match):
Extractor.__init__(self, match)
self.user_id = match.group(1)
def items(self):
base = "{}/accounts/upfile/{}/{}/".format(
self.root, self.user_id[-1], self.user_id)
keys = ("image1", "image2", "image3", "image4", "image5", "image6")
for post in self.posts():
if post.get("is_ad") or not post["image1"]:
continue
post["date"] = text.parse_datetime(
post["created_at"], "%Y-%m-%d %H:%M:%S")
yield Message.Directory, post
for key in keys:
name = post[key]
if not name:
break
url = base + name
post["num"] = ord(key[-1]) - 48
yield Message.Url, url, text.nameext_from_url(name, post)
def posts(self):
url = "{}/mypage/?id={}".format(self.root, self.user_id)
response = self.request(url)
if response.history and response.url == self.root + "/":
raise exception.NotFoundError("user")
target_id = text.extr(response.text, 'user_friend_id = "', '"')
return self._pagination(target_id)
def _pagination(self, target_id):
url = "{}/get_posts.php".format(self.root)
data = {
"user_id" : "0",
"target_id" : target_id,
"type" : "uploads",
"sort_type" : "0",
"category_id": "all",
"latest_post": "",
"page_num" : 0,
}
while True:
info = self.request(url, method="POST", data=data).json()
datas = info["datas"]
if not datas or not isinstance(datas, list):
return
yield from datas
last_id = datas[-1]["id"]
if last_id == info["last_data"]:
return
data["latest_post"] = last_id
data["page_num"] += 1
|
