github/gallery-dl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[simplyhentai] fix extraction

Browse Source
This commit is contained in:
Mike Fährmann
2021-04-25 01:47:51 +02:00
parent ba8180b5e6
commit d900edfcfb
1 changed files with 8 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
gallery_dl/extractor/simplyhentai.py
View File

@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
# Copyright 2018-2019 Mike Fährmann # Copyright 2018-2021 Mike Fährmann
# #
# This program is free software; you can redistribute it and/or modify # 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 # it under the terms of the GNU General Public License version 2 as
@@ -16,9 +16,9 @@ class SimplyhentaiGalleryExtractor(GalleryExtractor):
"""Extractor for image galleries from simply-hentai.com""" """Extractor for image galleries from simply-hentai.com"""
category = "simplyhentai" category = "simplyhentai"
archive_fmt = "{image_id}" archive_fmt = "{image_id}"
pattern = (r"(?:https?://)?(?!videos\.)([\w-]+\.simply-hentai\.com" pattern = (r"(?:https?://)?(?!videos\.)([\w-]+\.)?simply-hentai\.com"
r"(?!/(?:album|gifs?|images?|series)(?:/|$))" r"(?!/(?:album|gifs?|images?|series)(?:/|$))"
r"(?:/(?!(?:page|all-pages)(?:/|\.|$))[^/?#]+)+)") r"((?:/(?!(?:page|all-pages)(?:/|\.|$))[^/?#]+)+)")
test = ( test = (
(("https://original-work.simply-hentai.com" (("https://original-work.simply-hentai.com"
"/amazon-no-hiyaku-amazon-elixir"), { "/amazon-no-hiyaku-amazon-elixir"), {
@@ -35,7 +35,10 @@ class SimplyhentaiGalleryExtractor(GalleryExtractor):
) )
def __init__(self, match): def __init__(self, match):
url = "https://" + match.group(1) subdomain, path = match.groups()
if subdomain and subdomain not in ("www.", "old."):
path = "/" + subdomain.rstrip(".") + path
url = "https://old.simply-hentai.com" + path
GalleryExtractor.__init__(self, match, url) GalleryExtractor.__init__(self, match, url)
self.session.headers["Referer"] = url self.session.headers["Referer"] = url
@@ -43,7 +46,6 @@ class SimplyhentaiGalleryExtractor(GalleryExtractor):
extr = text.extract_from(page) extr = text.extract_from(page)
split = text.split_html split = text.split_html
self.gallery_url = extr('<link rel="canonical" href="', '"')
title = extr('<meta property="og:title" content="', '"') title = extr('<meta property="og:title" content="', '"')
image = extr('<meta property="og:image" content="', '"') image = extr('<meta property="og:image" content="', '"')
if not title: if not title:
@@ -99,7 +101,7 @@ class SimplyhentaiImageExtractor(Extractor):
def __init__(self, match): def __init__(self, match):
Extractor.__init__(self, match) Extractor.__init__(self, match)
self.page_url = "https://www." + match.group(1) self.page_url = "https://old." + match.group(1)
self.type = match.group(2) self.type = match.group(2)
def items(self): def items(self):