From 60833abcc6942275491a60e81f169d38fc2e70ed Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Mon, 9 Nov 2015 02:29:33 +0100
Subject: [PATCH] [sankaku] re-enable extractor

---
 gallery_dl/extractor/__init__.py |  1 +
 gallery_dl/extractor/sankaku.py  | 98 +++++++++++++++++++++++---------
 2 files changed, 73 insertions(+), 26 deletions(-)

diff --git a/gallery_dl/extractor/__init__.py b/gallery_dl/extractor/__init__.py
index 3571efca..f16596a9 100644
--- a/gallery_dl/extractor/__init__.py
+++ b/gallery_dl/extractor/__init__.py
@@ -37,6 +37,7 @@ modules = [
     "powermanga",
     "redhawkscans",
     "safebooru",
+    "sankaku",
     "yandere",
 ]
 
diff --git a/gallery_dl/extractor/sankaku.py b/gallery_dl/extractor/sankaku.py
index ad110e2b..0b719663 100644
--- a/gallery_dl/extractor/sankaku.py
+++ b/gallery_dl/extractor/sankaku.py
@@ -1,35 +1,81 @@
-from .common import AsyncExtractor
-from ..util import filename_from_url
+# -*- coding: utf-8 -*-
 
-class Extractor(AsyncExtractor):
+# Copyright 2014, 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 https://chan.sankakucomplex.com/"""
+
+from .common import Extractor, Message
+from .. import text
+import os.path
+
+info = {
+    "category": "sankaku",
+    "extractor": "SankakuExtractor",
+    "directory": ["{category}", "{tags}"],
+    "filename": "{category}_{id}_{md5}.{extension}",
+    "pattern": [
+        r"(?:https?://)?chan\.sankakucomplex\.com/\?tags=([^&]+)",
+    ],
+}
+
+class SankakuExtractor(Extractor):
 
     url = "https://chan.sankakucomplex.com/"
 
-    def __init__(self, match, config):
-        AsyncExtractor.__init__(self, config)
-        self.tags      = match.group(1)
-        self.category  = "sankaku"
-        self.directory = self.tags.replace("/", "_")
-        self.enable_useragent()
+    def __init__(self, match):
+        Extractor.__init__(self)
+        self.tags = text.unquote(match.group(1))
+        self.session.headers["User-Agent"] = (
+            "Mozilla/5.0 Gecko/20100101 Firefox/40.0"
+        )
 
-    def images(self):
-        needle = ' src="//c.sankakucomplex.com/data/preview/'
-        params = {"tags": self.tags, "page":1}
+    def items(self):
+        yield Message.Version, 1
+        data = self.get_job_metadata()
+        yield Message.Directory, data
+        for image in self.get_images():
+            data.update(image)
+            yield Message.Url, image["file-url"], data
+
+    def get_job_metadata(self):
+        """Collect metadata for extractor-job"""
+        return {
+            "category": info["category"],
+            "tags": self.tags,
+        }
+
+    def get_images(self):
+        image = {}
+        params = {
+            "tags": self.tags,
+            "page": 1,
+        }
         while True:
-            text  = self.request(self.url, params=params).text
-            print(text)
-            return
-            pos   = 0
-            found = 0
+            pos = 0
+            count = 0
+            page = self.request(self.url, params=params).text
             while True:
-                try:
-                    url, pos = self.extract(text, needle, '"', pos)
-                    found += 1
-                    print("https://cs.sankakucomplex.com/data/" + url)
-                    yield ("https://cs.sankakucomplex.com/data/" + url,
-                           "%s_%s" % (self.category, filename_from_url(url)))
-                except:
+                image["id"], pos = text.extract(page,
+                    '<span class="thumb blacklisted" id=p', '>', pos)
+                if not image["id"]:
                     break
-            if found == 0:
-                break
+                url , pos = text.extract(page, ' src="//c.sankakucomplex.com/', '"', pos)
+                tags, pos = text.extract(page, ' title="', '"', pos)
+                self.get_image_metadata(image, url)
+                count += 1
+                yield image
+            if count < 20:
+                return
             params["page"] += 1
+
+    @staticmethod
+    def get_image_metadata(image, url):
+        image["file-url"] = "https://cs.sankakucomplex.com/data/" + url[13:]
+        filename = text.filename_from_url(url)
+        name, ext = os.path.splitext(filename)
+        image["name"] = image["md5"] = name
+        image["extension"] = ext[1:]