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
|
# -*- coding: utf-8 -*-
# Copyright 2025 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://simpcity.cr/"""
from .common import Extractor, Message
from .. import text, exception
BASE_PATTERN = r"(?:https?://)?(?:www\.)?simpcity\.(?:cr|su)"
class SimpcityExtractor(Extractor):
"""Base class for simpcity extractors"""
category = "simpcity"
root = "https://simpcity.cr"
def items(self):
extract_urls = text.re(
r'<(?:a [^>]*?href|iframe [^>]*?src)="([^"]+)').findall
for post in self.posts():
urls = extract_urls(post["content"])
data = {"post": post}
post["count"] = data["count"] = len(urls)
yield Message.Directory, data
for data["num"], url in enumerate(urls, 1):
yield Message.Queue, url, data
def request_page(self, url):
try:
return self.request(url)
except exception.HttpError as exc:
if exc.status == 403 and b">Log in<" in exc.response.content:
msg = text.extr(exc.response.text, "blockMessage--error", "</")
raise exception.AuthRequired(
"'authenticated cookies'", None,
msg.rpartition(">")[2].strip())
raise
def _pagination(self, base, pnum=None):
base = f"{self.root}{base}"
if pnum is None:
url = f"{base}/"
pnum = 1
else:
url = f"{base}/page-{pnum}"
pnum = None
while True:
page = self.request_page(url).text
yield page
if pnum is None or "pageNav-jump--next" not in page:
return
pnum += 1
url = f"{base}/page-{pnum}"
def _pagination_reverse(self, base, pnum=None):
base = f"{self.root}{base}"
url = f"{base}/page-9999" # force redirect to last page
with self.request_page(url) as response:
url = response.url
if url[-1] == "/":
pnum = 1
else:
pnum = text.parse_int(url[url.rfind("-")+1:], 1)
page = response.text
while True:
yield page
pnum -= 1
if pnum > 1:
url = f"{base}/page-{pnum}"
elif pnum == 1:
url = f"{base}/"
else:
return
page = self.request_page(url).text
def _parse_thread(self, page):
schema = self._extract_jsonld(page)["mainEntity"]
author = schema["author"]
stats = schema["interactionStatistic"]
url_t = schema["url"]
url_a = author["url"]
thread = {
"id" : url_t[url_t.rfind(".")+1:-1],
"url" : url_t,
"title": schema["headline"],
"date" : text.parse_datetime(schema["datePublished"]),
"views": stats[0]["userInteractionCount"],
"posts": stats[1]["userInteractionCount"],
"tags" : (schema["keywords"].split(", ")
if "keywords" in schema else ()),
"section" : schema["articleSection"],
"author" : author["name"],
"author_id" : url_a[url_a.rfind(".")+1:-1],
"author_url": url_a,
}
return thread
def _parse_post(self, html):
extr = text.extract_from(html)
post = {
"author": extr('data-author="', '"'),
"id": extr('data-content="post-', '"'),
"author_url": extr('itemprop="url" content="', '"'),
"date": text.parse_datetime(extr('datetime="', '"')),
"content": extr('<div itemprop="text">',
'<div class="js-selectToQuote').strip(),
}
url_a = post["author_url"]
post["author_id"] = url_a[url_a.rfind(".")+1:-1]
return post
class SimpcityPostExtractor(SimpcityExtractor):
subcategory = "post"
pattern = rf"{BASE_PATTERN}/(?:threads/[^/?#]+/post-|posts/)(\d+)"
example = "https://simpcity.cr/threads/TITLE.12345/post-54321"
def posts(self):
post_id = self.groups[0]
url = f"{self.root}/posts/{post_id}/"
page = self.request_page(url).text
pos = page.find(f'data-content="post-{post_id}"')
if pos < 0:
raise exception.NotFoundError("post")
html = text.extract(page, "<article ", "</article>", pos-200)[0]
self.kwdict["thread"] = self._parse_thread(page)
return (self._parse_post(html),)
class SimpcityThreadExtractor(SimpcityExtractor):
subcategory = "thread"
pattern = rf"{BASE_PATTERN}(/threads/(?:[^/?#]+\.)?\d+)(?:/page-(\d+))?"
example = "https://simpcity.cr/threads/TITLE.12345/"
def posts(self):
if (order := self.config("order-posts")) and \
order[0] not in ("d", "r"):
pages = self._pagination(*self.groups)
reverse = False
else:
pages = self._pagination_reverse(*self.groups)
reverse = True
for page in pages:
if "thread" not in self.kwdict:
self.kwdict["thread"] = self._parse_thread(page)
posts = text.extract_iter(page, "<article ", "</article>")
if reverse:
posts = list(posts)
posts.reverse()
for html in posts:
yield self._parse_post(html)
class SimpcityForumExtractor(SimpcityExtractor):
subcategory = "forum"
pattern = rf"{BASE_PATTERN}(/forums/(?:[^/?#]+\.)?\d+)(?:/page-(\d+))?"
example = "https://simpcity.cr/forums/TITLE.123/"
def items(self):
data = {"_extractor": SimpcityThreadExtractor}
for page in self._pagination(*self.groups):
for path in text.extract_iter(page, ' uix-href="', '"'):
yield Message.Queue, f"{self.root}{text.unquote(path)}", data
|
