1
0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-26 04:32:51 +01:00
gallery-dl/gallery_dl/extractor/nhentai.py
2015-10-28 12:08:27 +01:00

71 lines
2.4 KiB
Python

# -*- 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://nhentai.net/"""
from .common import Extractor, Message
from .. import text
import json
info = {
"category": "nhentai",
"extractor": "NhentaiExtractor",
"directory": ["{category}", "{gallery-id} {title}"],
"filename": "{category}_{gallery-id}_{num:>03}.{extension}",
"pattern": [
r"(?:https?://)?(?:www\.)?nhentai\.net/g/(\d+)",
],
}
class NhentaiExtractor(Extractor):
def __init__(self, match):
Extractor.__init__(self)
self.gid = match.group(1)
def items(self):
ginfo = self.get_gallery_info()
data = self.get_job_metadata(ginfo)
urlbase = "http:{}galleries/{}/".format(ginfo["media_url"], data["media-id"])
extdict = {"j": "jpg", "p": "png", "g": "gif"}
yield Message.Version, 1
yield Message.Directory, data
for num, image in enumerate(ginfo["images"]["pages"], 1):
ext = extdict.get(image["t"], "jpg")
data["num"] = num
data["width"] = image["w"]
data["height"] = image["h"]
data["extension"] = ext
yield Message.Url, "{}{}.{}".format(urlbase, num, ext), data
def get_gallery_info(self):
"""Extract and return gallery-info"""
page = self.request("http://nhentai.net/g/" + self.gid + "/1/").text
media_url, pos = text.extract(page, "nhentai.reader({\n\t\t\tmedia_url: '", "'")
json_data, pos = text.extract(page, "gallery: ", ",\n", pos)
json_dict = json.loads(json_data)
json_dict["media_url"] = media_url
return json_dict
def get_job_metadata(self, ginfo):
"""Collect metadata for extractor-job"""
title_en = ginfo["title"].get("english", "")
title_ja = ginfo["title"].get("japanese", "")
return {
"category": info["category"],
"gallery-id": self.gid,
"upload-date": ginfo["upload_date"],
"media-id": ginfo["media_id"],
"favorites": ginfo["num_favorites"],
"scanlator": ginfo["scanlator"],
"count": ginfo["num_pages"],
"title": title_en or title_ja,
"title-en": title_en,
"title-ja": title_ja,
}