From 6ce181bcfe291d8eac5e628600d27dc7e777dcee Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Wed, 28 Oct 2015 12:08:27 +0100
Subject: [PATCH] add extractor 'nhentai'

---
 gallery_dl/extractor/__init__.py |  1 +
 gallery_dl/extractor/nhentai.py  | 70 ++++++++++++++++++++++++++++++++
 2 files changed, 71 insertions(+)
 create mode 100644 gallery_dl/extractor/nhentai.py

diff --git a/gallery_dl/extractor/__init__.py b/gallery_dl/extractor/__init__.py
index 88509734..a80569f5 100644
--- a/gallery_dl/extractor/__init__.py
+++ b/gallery_dl/extractor/__init__.py
@@ -26,6 +26,7 @@ modules = [
     "imgchili",
     "imgur",
     "mangareader",
+    "nhentai",
     "nijie",
     "powermanga",
     "redhawkscans",
diff --git a/gallery_dl/extractor/nhentai.py b/gallery_dl/extractor/nhentai.py
new file mode 100644
index 00000000..e462b701
--- /dev/null
+++ b/gallery_dl/extractor/nhentai.py
@@ -0,0 +1,70 @@
+# -*- 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,
+        }