[wallpapercave] add extractor for images (#2205)

pull/2301/head
David Hoppenbrouwers 3 years ago committed by GitHub
parent c661737f36
commit b17e2dcf93
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

@ -787,6 +787,12 @@ Consider all sites to be NSFW unless otherwise known.
<td>Collections, individual Images, Search Results</td>
<td><a href="configuration.rst#extractorwallhavenapi-key">API Key</a></td>
</tr>
<tr>
<td>Wallpaper Cave</td>
<td>https://wallpapercave.com/</td>
<td>individual Images, Search Results</td>
<td></td>
</tr>
<tr>
<td>Warosu</td>
<td>https://warosu.org/</td>

@ -132,6 +132,7 @@ modules = [
"vk",
"vsco",
"wallhaven",
"wallpapercave",
"warosu",
"weasyl",
"webtoons",

@ -0,0 +1,30 @@
# -*- coding: utf-8 -*-
# Copyright 2021 David Hoppenbrouwers
#
# 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://wallpapercave.com/"""
from .common import Extractor, Message
from .. import text
class WallpapercaveImageExtractor(Extractor):
"""Extractor for images on wallpapercave.com"""
category = "wallpapercave"
subcategory = "image"
root = "https://wallpapercave.com"
pattern = r"(?:https?://)?(?:www\.)?wallpapercave\.com"
test = ("https://wallpapercave.com/w/wp10270355", {
"content": "58b088aaa1cf1a60e347015019eb0c5a22b263a6",
})
def items(self):
page = self.request(text.ensure_http_scheme(self.url)).text
for path in text.extract_iter(page, 'class="download" href="', '"'):
image = text.nameext_from_url(path)
yield Message.Directory, image
yield Message.Url, self.root + path, image

@ -111,6 +111,7 @@ CATEGORY_MAP = {
"vk" : "VK",
"vsco" : "VSCO",
"wakarimasen" : "Wakarimasen Archive",
"wallpapercave" : "Wallpaper Cave",
"webtoons" : "Webtoon",
"wikiart" : "WikiArt.org",
"xhamster" : "xHamster",
@ -203,6 +204,9 @@ SUBCATEGORY_MAP = {
"wallhaven": {
"collections": "",
},
"wallpapercave": {
"image": "individual Images, Search Results",
},
"weasyl": {
"journals" : "",
"submissions": "",

Loading…
Cancel
Save