and move 'hentaifox' support to this module as well
This commit is contained in:
Mike Fährmann
@@ -68,7 +68,6 @@ modules = [
|
||||
"hentai2read",
|
||||
"hentaicosplays",
|
||||
"hentaifoundry",
|
||||
"hentaifox",
|
||||
"hentaihand",
|
||||
"hentaihere",
|
||||
"hentainexus",
|
||||
|
||||
@@ -1,119 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright 2019-2023 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://hentaifox.com/"""
|
||||
|
||||
from .common import GalleryExtractor, Extractor, Message
|
||||
from .. import text, util
|
||||
|
||||
|
||||
class HentaifoxBase():
|
||||
"""Base class for hentaifox extractors"""
|
||||
category = "hentaifox"
|
||||
root = "https://hentaifox.com"
|
||||
|
||||
|
||||
class HentaifoxGalleryExtractor(HentaifoxBase, GalleryExtractor):
|
||||
"""Extractor for image galleries on hentaifox.com"""
|
||||
pattern = r"(?:https?://)?(?:www\.)?hentaifox\.com(/gallery/(\d+))"
|
||||
example = "https://hentaifox.com/gallery/12345/"
|
||||
|
||||
def __init__(self, match):
|
||||
GalleryExtractor.__init__(self, match)
|
||||
self.gallery_id = match.group(2)
|
||||
|
||||
@staticmethod
|
||||
def _split(txt):
|
||||
return [
|
||||
text.remove_html(tag.partition(">")[2], "", "")
|
||||
for tag in text.extract_iter(
|
||||
txt, "class='tag_btn", "<span class='t_badge")
|
||||
]
|
||||
|
||||
def metadata(self, page):
|
||||
extr = text.extract_from(page)
|
||||
split = self._split
|
||||
|
||||
return {
|
||||
"gallery_id": text.parse_int(self.gallery_id),
|
||||
"parody" : split(extr(">Parodies:" , "</ul>")),
|
||||
"characters": split(extr(">Characters:", "</ul>")),
|
||||
"tags" : split(extr(">Tags:" , "</ul>")),
|
||||
"artist" : split(extr(">Artists:" , "</ul>")),
|
||||
"group" : split(extr(">Groups:" , "</ul>")),
|
||||
"type" : text.remove_html(extr(">Category:", "<span")),
|
||||
"title" : text.unescape(extr(
|
||||
'id="gallery_title" value="', '"')),
|
||||
"language" : "English",
|
||||
"lang" : "en",
|
||||
}
|
||||
|
||||
def images(self, page):
|
||||
cover, pos = text.extract(page, '<img src="', '"')
|
||||
data , pos = text.extract(page, "$.parseJSON('", "');", pos)
|
||||
path = "/".join(cover.split("/")[3:-1])
|
||||
|
||||
result = []
|
||||
append = result.append
|
||||
extmap = {"j": "jpg", "p": "png", "g": "gif"}
|
||||
urlfmt = ("/" + path + "/{}.{}").format
|
||||
|
||||
server1 = "https://i.hentaifox.com"
|
||||
server2 = "https://i2.hentaifox.com"
|
||||
|
||||
for num, image in util.json_loads(data).items():
|
||||
ext, width, height = image.split(",")
|
||||
path = urlfmt(num, extmap[ext])
|
||||
append((server1 + path, {
|
||||
"width" : width,
|
||||
"height" : height,
|
||||
"_fallback": (server2 + path,),
|
||||
}))
|
||||
|
||||
return result
|
||||
|
||||
|
||||
class HentaifoxSearchExtractor(HentaifoxBase, Extractor):
|
||||
"""Extractor for search results and listings on hentaifox.com"""
|
||||
subcategory = "search"
|
||||
pattern = (r"(?:https?://)?(?:www\.)?hentaifox\.com"
|
||||
r"(/(?:parody|tag|artist|character|search|group)/[^/?%#]+)")
|
||||
example = "https://hentaifox.com/tag/TAG/"
|
||||
|
||||
def __init__(self, match):
|
||||
Extractor.__init__(self, match)
|
||||
self.path = match.group(1)
|
||||
|
||||
def items(self):
|
||||
for gallery in self.galleries():
|
||||
yield Message.Queue, gallery["url"], gallery
|
||||
|
||||
def galleries(self):
|
||||
num = 1
|
||||
|
||||
while True:
|
||||
url = "{}{}/pag/{}/".format(self.root, self.path, num)
|
||||
page = self.request(url).text
|
||||
|
||||
for info in text.extract_iter(
|
||||
page, 'class="g_title"><a href="', '</a>'):
|
||||
url, _, title = info.partition('">')
|
||||
|
||||
yield {
|
||||
"url" : text.urljoin(self.root, url),
|
||||
"gallery_id": text.parse_int(
|
||||
url.strip("/").rpartition("/")[2]),
|
||||
"title" : text.unescape(title),
|
||||
"_extractor": HentaifoxGalleryExtractor,
|
||||
}
|
||||
|
||||
pos = page.find(">Next<")
|
||||
url = text.rextract(page, "href=", ">", pos)[0]
|
||||
if pos == -1 or "/pag" not in url:
|
||||
return
|
||||
num += 1
|
||||
@@ -22,10 +22,15 @@ class ImhentaiExtractor(BaseExtractor):
|
||||
|
||||
while True:
|
||||
page = self.request(url).text
|
||||
|
||||
pos = page.find('class="ranking_list"')
|
||||
if pos >= 0:
|
||||
page = page[:pos]
|
||||
|
||||
extr = text.extract_from(page)
|
||||
|
||||
while True:
|
||||
gallery_id = extr('<a href="/gallery/', '"')
|
||||
gallery_id = extr('href="/gallery/', '"')
|
||||
if gallery_id == prev:
|
||||
continue
|
||||
if not gallery_id:
|
||||
@@ -57,6 +62,18 @@ BASE_PATTERN = ImhentaiExtractor.update({
|
||||
"root": "https://hentairox.com",
|
||||
"pattern": r"(?:www\.)?hentairox\.com",
|
||||
},
|
||||
"hentaifox": {
|
||||
"root": "https://hentaifox.com",
|
||||
"pattern": r"(?:www\.)?hentaifox\.com",
|
||||
},
|
||||
"hentaienvy": {
|
||||
"root": "https://hentaienvy.com",
|
||||
"pattern": r"(?:www\.)?hentaienvy\.com",
|
||||
},
|
||||
"hentaizap": {
|
||||
"root": "https://hentaizap.com",
|
||||
"pattern": r"(?:www\.)?hentaizap\.com",
|
||||
},
|
||||
})
|
||||
|
||||
|
||||
@@ -72,17 +89,20 @@ class ImhentaiGalleryExtractor(ImhentaiExtractor, GalleryExtractor):
|
||||
|
||||
def metadata(self, page):
|
||||
extr = text.extract_from(page)
|
||||
title = extr("<h1>", "<")
|
||||
title_alt = extr('class="subtitle">', "<")
|
||||
end = "</li>" if extr('<ul class="galleries_info', ">") else "</ul>"
|
||||
|
||||
data = {
|
||||
"gallery_id": text.parse_int(self.gallery_id),
|
||||
"title" : text.unescape(extr("<h1>", "<")),
|
||||
"title_alt" : text.unescape(extr('class="subtitle">', "<")),
|
||||
"parody" : self._split(extr(">Parodies", "</li>")),
|
||||
"character" : self._split(extr(">Characters", "</li>")),
|
||||
"tags" : self._split(extr(">Tags", "</li>")),
|
||||
"artist" : self._split(extr(">Artists", "</li>")),
|
||||
"group" : self._split(extr(">Groups", "</li>")),
|
||||
"language" : self._split(extr(">Languages", "</li>")),
|
||||
"title" : text.unescape(title),
|
||||
"title_alt" : text.unescape(title_alt),
|
||||
"parody" : self._split(extr(">Parodies", end)),
|
||||
"character" : self._split(extr(">Characters", end)),
|
||||
"tags" : self._split(extr(">Tags", end)),
|
||||
"artist" : self._split(extr(">Artists", end)),
|
||||
"group" : self._split(extr(">Groups", end)),
|
||||
"language" : self._split(extr(">Languages", end)),
|
||||
"type" : extr("href='/category/", "/"),
|
||||
}
|
||||
|
||||
@@ -94,10 +114,12 @@ class ImhentaiGalleryExtractor(ImhentaiExtractor, GalleryExtractor):
|
||||
def _split(self, html):
|
||||
results = []
|
||||
for tag in text.extract_iter(html, ">", "</a>"):
|
||||
tag = tag.partition(" <span class='badge'>")[0]
|
||||
if "<" in tag:
|
||||
tag = text.remove_html(tag)
|
||||
badge = ("badge'>" in tag or "class='badge" in tag)
|
||||
tag = text.remove_html(tag)
|
||||
if badge:
|
||||
tag = tag.rpartition(" ")[0]
|
||||
results.append(tag)
|
||||
results.sort()
|
||||
return results
|
||||
|
||||
def images(self, page):
|
||||
@@ -132,9 +154,9 @@ class ImhentaiTagExtractor(ImhentaiExtractor):
|
||||
class ImhentaiSearchExtractor(ImhentaiExtractor):
|
||||
"""Extractor for imhentai search results"""
|
||||
subcategory = "search"
|
||||
pattern = BASE_PATTERN + r"/search/?\?([^#]+)"
|
||||
pattern = BASE_PATTERN + r"/search(/?\?[^#]+|/[^/?#]+/?)"
|
||||
example = "https://imhentai.xxx/search/?key=QUERY"
|
||||
|
||||
def items(self):
|
||||
url = self.root + "/search/?" + self.groups[-1]
|
||||
url = self.root + "/search" + self.groups[-1]
|
||||
return self._pagination(url)
|
||||
|
||||
Reference in New Issue
Block a user