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
|
# -*- 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://urlgalleries.net/"""
from .common import GalleryExtractor, Message
from .. import text, exception
class UrlgalleriesGalleryExtractor(GalleryExtractor):
"""Base class for Urlgalleries extractors"""
category = "urlgalleries"
root = "https://urlgalleries.net"
request_interval = (0.5, 1.5)
pattern = r"(?:https?://)(?:(\w+)\.)?urlgalleries\.net/(?:[\w-]+-)?(\d+)"
example = "https://BLOG.urlgalleries.net/gallery-12345/TITLE"
def items(self):
blog, self.gallery_id = self.groups
url = "https://{}.urlgalleries.net/porn-gallery-{}/?a=10000".format(
blog, self.gallery_id)
with self.request(url, allow_redirects=False, fatal=...) as response:
if 300 <= response.status_code < 500:
if response.headers.get("location", "").endswith(
"/not_found_adult.php"):
raise exception.NotFoundError("gallery")
raise exception.HttpError(None, response)
page = response.text
imgs = self.images(page)
data = self.metadata(page)
data["count"] = len(imgs)
root = "https://{}.urlgalleries.net".format(blog)
yield Message.Directory, data
for data["num"], img in enumerate(imgs, 1):
page = self.request(root + img).text
url = text.extr(page, "window.location.href = '", "'")
yield Message.Queue, url, data
def metadata(self, page):
extr = text.extract_from(page)
return {
"gallery_id": self.gallery_id,
"_site": extr(' title="', '"'), # site name
"blog" : text.unescape(extr(' title="', '"')),
"_rprt": extr(' title="', '"'), # report button
"title": text.unescape(extr(' title="', '"').strip()),
"date" : text.parse_datetime(
extr(" images in gallery | ", "<"), "%B %d, %Y %H:%M"),
}
def images(self, page):
imgs = text.extr(page, 'id="wtf"', "</div>")
return list(text.extract_iter(imgs, " href='", "'"))
|
