merge #4886: [urlgalleries] add 'gallery' extractor (#919, #1184, #2905)

pull/4906/head
Mike Fährmann 10 months ago
commit bf74eb5c46
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88

@ -889,6 +889,12 @@ Consider all sites to be NSFW unless otherwise known.
<td>Files</td>
<td></td>
</tr>
<tr>
<td>Urlgalleries</td>
<td>https://urlgalleries.net/</td>
<td>Galleries</td>
<td></td>
</tr>
<tr>
<td>Vipergirls</td>
<td>https://vipergirls.to/</td>

@ -155,6 +155,7 @@ modules = [
"tumblrgallery",
"twibooru",
"twitter",
"urlgalleries",
"unsplash",
"uploadir",
"urlshortener",

@ -0,0 +1,55 @@
# -*- 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
class UrlgalleriesGalleryExtractor(GalleryExtractor):
"""Base class for Urlgalleries extractors"""
category = "urlgalleries"
root = "urlgalleries.net"
request_interval = (0.5, 1.0)
pattern = r"(?:https?://)(?:(\w+)\.)?urlgalleries\.net/(?:[\w-]+-)?(\d+)"
example = "https://blog.urlgalleries.net/gallery-12345/TITLE"
def __init__(self, match):
self.blog, self.gallery_id = match.groups()
url = "https://{}.urlgalleries.net/porn-gallery-{}/?a=10000".format(
self.blog, self.gallery_id)
GalleryExtractor.__init__(self, match, url)
def items(self):
page = self.request(self.gallery_url).text
imgs = self.images(page)
data = self.metadata(page)
data["count"] = len(imgs)
del page
root = "https://{}.urlgalleries.net".format(self.blog)
yield Message.Directory, data
for data["num"], img in enumerate(imgs, 1):
response = self.request(
root + img, method="HEAD", allow_redirects=False)
yield Message.Queue, response.headers["Location"], 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='", "'"))

@ -0,0 +1,49 @@
# -*- 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.
from gallery_dl.extractor import urlgalleries
__tests__ = (
{
"#url" : "https://photos2q.urlgalleries.net/porn-gallery-7851311/clarice-window-8",
"#category": ("", "urlgalleries", "gallery"),
"#class" : urlgalleries.UrlgalleriesGalleryExtractor,
"#range" : "1-3",
"#urls" : (
"https://fappic.com/x207mqkn2463/4gq1yv.jpg",
"https://fappic.com/q684ua2rp0j9/4gq1xv.jpg",
"https://fappic.com/8vf3n8fgz9po/4gq1ya.jpg",
),
"blog" : "photos2q",
"count" : 39,
"date" : "dt:2023-12-08 13:59:00",
"gallery_id": "7851311",
"num" : range(1, 3),
"title" : "Clarice window 8",
},
{
"#url" : "https://dreamer.urlgalleries.net/7645840",
"#category": ("", "urlgalleries", "gallery"),
"#class" : urlgalleries.UrlgalleriesGalleryExtractor,
"#range" : "1-3",
"#urls" : (
"https://www.fappic.com/vj7up04ny487/AmourAngels-0001.jpg",
"https://www.fappic.com/zfgsmpm36iyv/AmourAngels-0002.jpg",
"https://www.fappic.com/rqpt37rdbwa5/AmourAngels-0003.jpg",
),
"blog" : "Dreamer",
"count" : 105,
"date" : "dt:2020-03-10 21:17:00",
"gallery_id": "7645840",
"num" : range(1, 3),
"title" : "Angelika - Rustic Charm - AmourAngels 2016-09-27",
},
)
Loading…
Cancel
Save