Mirrors/gallery-dl
1
0
Fork 0
mirror of https://github.com/mikf/gallery-dl.git synced 2025-01-31 11:41:35 +01:00
Code Issues Releases Wiki Activity

[imagechest] simplify code (#750)

Browse Source
This commit is contained in:
Mike Fährmann 2020-05-18 19:11:26 +02:00
parent ece73b5b2a
commit ab11b1c896
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88
2 changed files with 9 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
docs/supportedsites.rst
View File

@ -53,6 +53,7 @@ Hitomi.la https://hitomi.la/ Galleries, Tag Searches
Hypnohub https://hypnohub.net/ Pools, Popular Images, Posts, Tag Searches
Idol Complex https://idol.sankakucomplex.com/ Pools, Posts, Tag Searches Optional
ImageBam http://www.imagebam.com/ Galleries, individual Images
ImageChest https://imgchest.com/ Galleries
ImageFap https://imagefap.com/ Galleries, individual Images, User Profiles
ImgBB https://imgbb.com/ Albums, individual Images, User Profiles Optional
imgbox https://imgbox.com/ Galleries, individual Images

34
gallery_dl/extractor/imagechest.py
View File

@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2014-2020 Leonid "Bepis" Pavel
# Copyright 2020 Leonid "Bepis" Pavel
#
# 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
@ -10,15 +10,12 @@
from .common import GalleryExtractor
from .. import text, exception
import re
class ImagechestGalleryExtractor(GalleryExtractor):
"""Extractor for image galleries from imgchest.com"""
category = "imagechest"
root = "https://imgchest.com"
pattern = r"(?:https?://)?(?:www\.)?imgchest\.com/p/([A-Za-z0-9]{11})"
test = (
("https://imgchest.com/p/3na7kr3by8d", {
@ -29,38 +26,23 @@ class ImagechestGalleryExtractor(GalleryExtractor):
)
def __init__(self, match):
self.gallery_id = match.group(1)
url = self.root + "/p/" + self.gallery_id
GalleryExtractor.__init__(self, match, url)
def metadata(self, page):
"""Return a dict with general metadata"""
if "Sorry, but the page you requested could not be found." in page:
raise exception.NotFoundError("gallery")
title_match = re.search(
r'<meta property="og:title" content="([^"]+)"/>',
page)
title = title_match.group(1).strip()
return {
"gallery_id": self.gallery_id,
"title": text.unescape(title)
"title": text.unescape(text.extract(
page, 'property="og:title" content="', '"')[0].strip())
}
def images(self, page):
"""Return a list of all (image-url, metadata)-tuples"""
image_keys = re.findall(
r'<meta property="og:image" content="([^"]+)"/>',
page)
for imgurl in image_keys:
data = text.nameext_from_url(imgurl)
yield imgurl, data
return [
(url, None)
for url in text.extract_iter(
page, 'property="og:image" content="', '"')
]