mirror of
https://github.com/mikf/gallery-dl.git
synced 2024-11-24 03:32:33 +01:00
127 lines
4.6 KiB
Python
127 lines
4.6 KiB
Python
# -*- coding: utf-8 -*-
|
|
|
|
# Copyright 2019-2020 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.
|
|
|
|
"""Extractors for https://hentainexus.com/"""
|
|
|
|
from .common import GalleryExtractor, Extractor, Message
|
|
from .. import text, util
|
|
import json
|
|
|
|
|
|
class HentainexusGalleryExtractor(GalleryExtractor):
|
|
"""Extractor for image galleries on hentainexus.com"""
|
|
category = "hentainexus"
|
|
root = "https://hentainexus.com"
|
|
pattern = (r"(?i)(?:https?://)?(?:www\.)?hentainexus\.com"
|
|
r"/(?:view|read)/(\d+)")
|
|
test = (
|
|
("https://hentainexus.com/view/5688", {
|
|
"url": "746d0043e20030f1171aae5ea113176607302517",
|
|
"keyword": "5e5bb4b1553b1c6e126b198f9ae017a1a5d0a5ad",
|
|
}),
|
|
("https://hentainexus.com/read/5688"),
|
|
)
|
|
|
|
def __init__(self, match):
|
|
self.gallery_id = match.group(1)
|
|
url = "{}/view/{}".format(self.root, self.gallery_id)
|
|
GalleryExtractor.__init__(self, match, url)
|
|
|
|
def metadata(self, page):
|
|
rmve = text.remove_html
|
|
extr = text.extract_from(page)
|
|
data = {
|
|
"gallery_id" : text.parse_int(self.gallery_id),
|
|
"tags" : extr('"og:description" content="', '"').split(", "),
|
|
"thumbnail" : extr('"og:image" content="', '"'),
|
|
"title" : extr('<h1 class="title">', '</h1>'),
|
|
"artist" : rmve(extr('viewcolumn">Artist</td>' , '</td>')),
|
|
"book" : rmve(extr('viewcolumn">Book</td>' , '</td>')),
|
|
"circle" : rmve(extr('viewcolumn">Circle</td>' , '</td>')),
|
|
"event" : rmve(extr('viewcolumn">Event</td>' , '</td>')),
|
|
"language" : rmve(extr('viewcolumn">Language</td>' , '</td>')),
|
|
"magazine" : rmve(extr('viewcolumn">Magazine</td>' , '</td>')),
|
|
"parody" : rmve(extr('viewcolumn">Parody</td>' , '</td>')),
|
|
"publisher" : rmve(extr('viewcolumn">Publisher</td>' , '</td>')),
|
|
"description": rmve(extr('viewcolumn">Description</td>', '</td>')),
|
|
}
|
|
data["lang"] = util.language_to_code(data["language"])
|
|
data["type"] = "Doujinshi" if 'doujin' in data["tags"] else "Manga"
|
|
data["title_conventional"] = self.join_title(
|
|
data["event"],
|
|
data["circle"],
|
|
data["artist"],
|
|
data["title"],
|
|
data["parody"],
|
|
data["book"],
|
|
data["magazine"],
|
|
)
|
|
return data
|
|
|
|
@staticmethod
|
|
def join_title(event, circle, artist, title, parody, book, magazine):
|
|
jt = ''
|
|
if event:
|
|
jt += '({}) '.format(event)
|
|
if circle:
|
|
jt += '[{} ({})] '.format(circle, artist)
|
|
else:
|
|
jt += '[{}] '.format(artist)
|
|
jt += title
|
|
if parody.lower() != 'original work':
|
|
jt += ' ({})'.format(parody)
|
|
if book:
|
|
jt += ' ({})'.format(book)
|
|
if magazine:
|
|
jt += ' ({})'.format(magazine)
|
|
return jt
|
|
|
|
def images(self, page):
|
|
url = "{}/read/{}".format(self.root, self.gallery_id)
|
|
extr = text.extract_from(self.request(url).text)
|
|
urls = extr("initReader(", "]") + "]"
|
|
return [(url, None) for url in json.loads(urls)]
|
|
|
|
|
|
class HentainexusSearchExtractor(Extractor):
|
|
"""Extractor for search results on hentainexus.com"""
|
|
category = "hentainexus"
|
|
subcategory = "search"
|
|
root = "https://hentainexus.com"
|
|
pattern = (r"(?i)(?:https?://)?(?:www\.)?hentainexus\.com"
|
|
r"(?:/page/\d+)?/?(?:\?(q=[^/?#]+))?$")
|
|
test = (
|
|
("https://hentainexus.com/?q=tag:%22heart+pupils%22%20tag:group", {
|
|
"pattern": HentainexusGalleryExtractor.pattern,
|
|
"count": ">= 50",
|
|
}),
|
|
("https://hentainexus.com/page/3?q=tag:%22heart+pupils%22"),
|
|
)
|
|
|
|
def __init__(self, match):
|
|
Extractor.__init__(self, match)
|
|
self.params = text.parse_query(match.group(1))
|
|
|
|
def items(self):
|
|
yield Message.Version, 1
|
|
params = self.params
|
|
path = "/"
|
|
|
|
while path:
|
|
page = self.request(self.root + path, params=params).text
|
|
extr = text.extract_from(page)
|
|
data = {"_extractor": HentainexusGalleryExtractor}
|
|
|
|
while True:
|
|
gallery_id = extr('<a href="/view/', '"')
|
|
if not gallery_id:
|
|
break
|
|
yield Message.Queue, self.root + "/view/" + gallery_id, data
|
|
|
|
path = extr('class="pagination-next" href="', '"')
|