# -*- coding: utf-8 -*-
# Copyright 2018-2019 Mike Fährmann
#
# 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.
"""Extract hentai-manga from https://www.simply-hentai.com/"""
from .common import Extractor, ChapterExtractor, Message
from .. import text, util, exception
class SimplyhentaiGalleryExtractor(ChapterExtractor):
"""Extractor for image galleries from simply-hentai.com"""
category = "simplyhentai"
subcategory = "gallery"
directory_fmt = ("{category}", "{gallery_id} {title}")
filename_fmt = "{category}_{gallery_id}_{page:>03}.{extension}"
archive_fmt = "{image_id}"
pattern = (r"(?:https?://)?(?!videos\.)([\w-]+\.simply-hentai\.com"
r"(?!/(?:album|gifs?|images?|series)(?:/|$))"
r"(?:/(?!(?:page|all-pages)(?:/|\.|$))[^/?]+)+)")
test = (
(("https://original-work.simply-hentai.com"
"/amazon-no-hiyaku-amazon-elixir"), {
"url": "258289249990502c3138719cb89e995a60861e49",
"keyword": "5ea1498a1a902d76d337946910082755d168b941",
}),
("https://www.simply-hentai.com/notfound", {
"exception": exception.GalleryDLException,
}),
# custom subdomain
("https://pokemon.simply-hentai.com/mao-friends-9bc39"),
# www subdomain, two path segments
("https://www.simply-hentai.com/vocaloid/black-magnet"),
)
def __init__(self, match):
url = "https://" + match.group(1)
ChapterExtractor.__init__(self, url)
self.session.headers["Referer"] = url
def get_metadata(self, page):
extr = text.extract
title , pos = extr(page, 'Series', '', pos)
lang , pos = extr(page, 'box-title">Language', '', pos)
chars , pos = extr(page, 'box-title">Characters', '', pos)
tags , pos = extr(page, 'box-title">Tags', '', pos)
artist, pos = extr(page, 'box-title">Artists', '', pos)
date , pos = extr(page, 'Uploaded', '', pos)
lang = text.remove_html(lang) if lang else None
return {
"gallery_id": text.parse_int(gid),
"title": text.unescape(title),
"series": text.remove_html(series),
"characters": ", ".join(text.split_html(chars)),
"tags": text.split_html(tags),
"artist": ", ".join(text.split_html(artist)),
"lang": util.language_to_code(lang),
"language": lang,
"date": text.remove_html(date),
}
def get_images(self, _):
headers = {"Accept": "application/json"}
images = self.request(self.url + "/all-pages", headers=headers).json()
return [
(urls["full"], {"image_id": text.parse_int(image_id)})
for image_id, urls in sorted(images.items())
]
class SimplyhentaiImageExtractor(Extractor):
"""Extractor for individual images from simply-hentai.com"""
category = "simplyhentai"
subcategory = "image"
directory_fmt = ("{category}", "{type}s")
filename_fmt = "{category}_{token}{title:?_//}.{extension}"
archive_fmt = "{token}"
pattern = (r"(?:https?://)?(?:www\.)?(simply-hentai\.com"
r"/(image|gif)/[^/?]+)")
test = (
(("https://www.simply-hentai.com/image"
"/pheromomania-vol-1-kanzenban-isao-3949d8b3-400c-4b6"), {
"url": "0338eb137830ab6f81e5f410d3936ef785d063d9",
"keyword": "0209cc8657c80e2b5fed8f2f3f2aa3a57e2cc8b6",
}),
("https://www.simply-hentai.com/gif/8915dfcf-0b6a-47c", {
"url": "11c060d7ec4dfd0bd105300b6e1fd454674a5af1",
"keyword": "de26851c4eb7a204364ea26943b1581a0fd43da5",
}),
)
def __init__(self, match):
Extractor.__init__(self)
self.url = "https://www." + match.group(1)
self.type = match.group(2)
def items(self):
page = self.request(self.url).text
url_search = 'data-src="' if self.type == "image" else '