You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
109 lines
3.5 KiB
109 lines
3.5 KiB
9 years ago
|
# -*- coding: utf-8 -*-
|
||
|
|
|
||
|
|
# Copyright 2015 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 images from http://www.hentai-foundry.com/"""
|
||
|
|
|
||
|
|
from .common import Extractor, Message
|
||
|
|
from .. import text
|
||
|
|
import os.path
|
||
|
|
|
||
|
|
info = {
|
||
|
|
"category": "hentaifoundry",
|
||
|
|
"extractor": "HentaiFoundryExtractor",
|
||
|
|
"directory": ["{category}", "{artist}"],
|
||
|
|
"filename": "{category}_{index}_{title}.{extension}",
|
||
|
|
"pattern": [
|
||
|
|
r"(?:https?://)?(?:www\.)?hentai-foundry\.com/pictures/user/([^/]+)",
|
||
|
|
r"(?:https?://)?(?:www\.)?hentai-foundry\.com/user/([^/]+)/profile",
|
||
|
|
],
|
||
|
|
}
|
||
|
|
|
||
|
|
class HentaiFoundryExtractor(Extractor):
|
||
|
|
|
||
|
|
url_base = "http://www.hentai-foundry.com/pictures/user/"
|
||
|
|
|
||
|
|
def __init__(self, match):
|
||
|
|
Extractor.__init__(self)
|
||
|
|
self.artist = match.group(1)
|
||
|
|
|
||
|
|
def items(self):
|
||
|
|
data, token = self.get_job_metadata()
|
||
|
|
self.set_filters(token)
|
||
|
|
yield Message.Version, 1
|
||
|
|
yield Message.Directory, data
|
||
|
|
for image in self.get_images():
|
||
|
|
image.update(data)
|
||
|
|
yield Message.Url, image["url"], image
|
||
|
|
|
||
|
|
def get_images(self):
|
||
|
|
num = 1
|
||
|
|
while True:
|
||
|
|
pos = 0
|
||
|
|
url = self.url_base + self.artist + "/page/" + str(num)
|
||
|
|
page = self.request(url).text
|
||
|
|
for i in range(25):
|
||
|
|
part, pos = text.extract(page, 'thumbTitle"><a href="/pictures/user/', '"', pos)
|
||
|
|
if not part:
|
||
|
|
return
|
||
|
|
yield self.get_image_metadata(self.url_base + part)
|
||
|
|
num += 1
|
||
|
|
|
||
|
|
def get_job_metadata(self):
|
||
|
|
"""Collect metadata for extractor-job"""
|
||
|
|
page = self.request(self.url_base + self.artist + "?enterAgree=1").text
|
||
|
|
token, pos = text.extract(page, 'hidden" value="', '"')
|
||
|
|
count, pos = text.extract(page, 'class="active" >Pictures (', ')', pos)
|
||
|
|
return {
|
||
|
|
"category": info["category"],
|
||
|
|
"artist": self.artist,
|
||
|
|
"count": count,
|
||
|
|
}, token
|
||
|
|
|
||
|
|
def get_image_metadata(self, url):
|
||
|
|
"""Collect metadata for an image"""
|
||
|
|
page = self.request(url).text
|
||
|
|
index = text.extract(url, '/', '/', len(self.url_base) + len(self.artist))[0]
|
||
|
|
title, pos = text.extract(page, 'Pictures</a> » <span>', '<')
|
||
|
|
url , pos = text.extract(page, '//pictures.hentai-foundry.com', '"', pos)
|
||
|
|
return {
|
||
|
|
"url": "http://pictures.hentai-foundry.com" + url,
|
||
|
|
"index": index,
|
||
|
|
"title": text.unescape(title),
|
||
|
|
"extension": os.path.splitext(url)[1][1:],
|
||
|
|
}
|
||
|
|
|
||
|
|
def set_filters(self, token):
|
||
|
|
formdata = {
|
||
|
|
"YII_CSRF_TOKEN": token,
|
||
|
|
"rating_nudity": 3,
|
||
|
|
"rating_violence": 3,
|
||
|
|
"rating_profanity": 3,
|
||
|
|
"rating_racism": 3,
|
||
|
|
"rating_sex": 3,
|
||
|
|
"rating_spoilers": 3,
|
||
|
|
"rating_yaoi": 1,
|
||
|
|
"rating_yuri": 1,
|
||
|
|
"rating_teen": 1,
|
||
|
|
"rating_guro": 1,
|
||
|
|
"rating_furry": 1,
|
||
|
|
"rating_beast": 1,
|
||
|
|
"rating_male": 1,
|
||
|
|
"rating_female": 1,
|
||
|
|
"rating_futa": 1,
|
||
|
|
"rating_other": 1,
|
||
|
|
"filter_media": "A",
|
||
|
|
"filter_order": "date_new",
|
||
|
|
"filter_type": 0,
|
||
|
|
}
|
||
|
|
self.request("http://www.hentai-foundry.com/site/filters",
|
||
|
|
method="post", data=formdata)
|
||
|
|
|
||
|
|
# enterAgree=1
|
||
|
|
|
||
|
|
#YII_CSRF_TOKEN=388b659daeab4517ea5ca6d93b9253d4c59a12df
|