From 1302f5a0f6788b4c2eb85a272ac0d91ca483cd19 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Sat, 7 Nov 2015 02:32:59 +0100
Subject: [PATCH] [kissmanga] add extractor

---
 gallery_dl/extractor/kissmanga.py | 73 +++++++++++++++++++++++++++++++
 1 file changed, 73 insertions(+)
 create mode 100644 gallery_dl/extractor/kissmanga.py

diff --git a/gallery_dl/extractor/kissmanga.py b/gallery_dl/extractor/kissmanga.py
new file mode 100644
index 00000000..08738301
--- /dev/null
+++ b/gallery_dl/extractor/kissmanga.py
@@ -0,0 +1,73 @@
+# -*- 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 manga pages from http://kissmanga.com/"""
+
+from .common import Extractor, Message
+from .. import text, cloudflare
+import os.path
+import re
+
+info = {
+    "category": "kissmanga",
+    "extractor": "KissmangaExtractor",
+    "directory": ["{category}", "{manga}", "c{chapter:>03} - {title}"],
+    "filename": "{manga}_c{chapter:>03}_{page:>03}.{extension}",
+    "pattern": [
+        r"(?:https?://)?(?:www\.)?kissmanga\.com/Manga/.+/.+\?id=\d+",
+    ],
+}
+
+class KissmangaExtractor(Extractor):
+
+    def __init__(self, match):
+        Extractor.__init__(self)
+        self.url = match.group(0)
+
+    def items(self):
+        cloudflare.bypass_ddos_protection(self.session, "http://kissmanga.com")
+        page = self.request(self.url).text
+        data = self.get_job_metadata(page)
+        imgs = self.get_image_urls(page)
+        data["count"] = len(imgs)
+        yield Message.Version, 1
+        yield Message.Directory, data
+        for num, url in enumerate(imgs, 1):
+            filename = text.unquote(text.filename_from_url(url))
+            name, ext = os.path.splitext(filename)
+            data["page"] = num
+            data["name"] = name
+            data["extension"] = ext[1:]
+            yield Message.Url, url, data
+
+    @staticmethod
+    def get_job_metadata(page):
+        """Collect metadata for extractor-job"""
+        manga, pos = text.extract(page, "Read manga\n", "\n")
+        cinfo, pos = text.extract(page, "", "\n", pos)
+        match = re.match(r"(?:Vol.0*(\d+) )?Ch.0*(\d+)(?:: (.+))", cinfo)
+        return {
+            "category": info["category"],
+            "manga": manga,
+            "volume": match.group(1) or "",
+            "chapter": match.group(2),
+            "title": match.group(3) or "",
+            "lang": "en",
+            "language": "English",
+        }
+
+    @staticmethod
+    def get_image_urls(page):
+        """Extract list of all image-urls for a manga chapter"""
+        pos = 0
+        images = []
+        while True:
+            url, pos = text.extract(page, 'lstImages.push("', '"', pos)
+            if not url:
+                return images
+            images.append(url)