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
|
# -*- coding: utf-8 -*-
# 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://everia.club"""
from .common import Extractor, Message
from .. import text
BASE_PATTERN = r"(?:https?://)?everia\.club"
class EveriaExtractor(Extractor):
category = "everia"
root = "https://everia.club"
def items(self):
data = {"_extractor": EveriaPostExtractor}
for url in self.posts():
yield Message.Queue, url, data
def posts(self):
return self._pagination(self.groups[0])
def _pagination(self, path, params=None, pnum=1):
find_posts = text.re(r'thumbnail">\s*<a href="([^"]+)').findall
while True:
if pnum == 1:
url = f"{self.root}{path}/"
else:
url = f"{self.root}{path}/page/{pnum}/"
response = self.request(url, params=params, allow_redirects=False)
if response.status_code >= 300:
return
yield from find_posts(response.text)
pnum += 1
class EveriaPostExtractor(EveriaExtractor):
subcategory = "post"
directory_fmt = ("{category}", "{title}")
archive_fmt = "{post_url}_{num}"
pattern = rf"{BASE_PATTERN}(/\d{{4}}/\d{{2}}/\d{{2}}/[^/?#]+)"
example = "https://everia.club/0000/00/00/TITLE"
def items(self):
url = self.root + self.groups[0] + "/"
page = self.request(url).text
content = text.extr(page, 'itemprop="text">', "<h3")
urls = text.re(r'img.*?lazy-src="([^"]+)').findall(content)
data = {
"title": text.unescape(
text.extr(page, 'itemprop="headline">', "</h")),
"tags": list(text.extract_iter(page, 'rel="tag">', "</a>")),
"post_url": text.unquote(url),
"post_category": text.extr(
page, "post-in-category-", " ").capitalize(),
"count": len(urls),
}
yield Message.Directory, "", data
for data["num"], url in enumerate(urls, 1):
url = text.unquote(url)
yield Message.Url, url, text.nameext_from_url(url, data)
class EveriaTagExtractor(EveriaExtractor):
subcategory = "tag"
pattern = rf"{BASE_PATTERN}(/tag/[^/?#]+)"
example = "https://everia.club/tag/TAG"
class EveriaCategoryExtractor(EveriaExtractor):
subcategory = "category"
pattern = rf"{BASE_PATTERN}(/category/[^/?#]+)"
example = "https://everia.club/category/CATEGORY"
class EveriaDateExtractor(EveriaExtractor):
subcategory = "date"
pattern = (rf"{BASE_PATTERN}"
rf"(/\d{{4}}(?:/\d{{2}})?(?:/\d{{2}})?)(?:/page/\d+)?/?$")
example = "https://everia.club/0000/00/00"
class EveriaSearchExtractor(EveriaExtractor):
subcategory = "search"
pattern = rf"{BASE_PATTERN}/(?:page/\d+/)?\?s=([^&#]+)"
example = "https://everia.club/?s=SEARCH"
def posts(self):
params = {"s": self.groups[0]}
return self._pagination("", params)
|
