From d324c5803806e208b8102ce30da5b35a5acc3d64 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Sat, 17 Sep 2016 18:12:37 +0200
Subject: [PATCH] [rule34] add tag- and image-extractor

---
 gallery_dl/extractor/__init__.py  |  1 +
 gallery_dl/extractor/rule34.py    | 45 +++++++++++++++++++++++++++++++
 gallery_dl/extractor/safebooru.py |  1 -
 3 files changed, 46 insertions(+), 1 deletion(-)
 create mode 100644 gallery_dl/extractor/rule34.py

diff --git a/gallery_dl/extractor/__init__.py b/gallery_dl/extractor/__init__.py
index 2ba67bc8..d57d965a 100644
--- a/gallery_dl/extractor/__init__.py
+++ b/gallery_dl/extractor/__init__.py
@@ -54,6 +54,7 @@ modules = [
     "nijie",
     "pinterest",
     "powermanga",
+    "rule34",
     "safebooru",
     "sankaku",
     "seiga",
diff --git a/gallery_dl/extractor/rule34.py b/gallery_dl/extractor/rule34.py
new file mode 100644
index 00000000..f6e21ac9
--- /dev/null
+++ b/gallery_dl/extractor/rule34.py
@@ -0,0 +1,45 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2016 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://rule34.xxx/"""
+
+from . import booru
+
+class Rule34Extractor(booru.XMLBooruExtractor):
+    """Base class for rule34 extractors"""
+    category = "rule34"
+    api_url = "https://rule34.xxx/index.php"
+
+    def setup(self):
+        self.params.update({"page":"dapi", "s":"post", "q":"index"})
+
+    def update_page(self, reset=False):
+        if reset is False:
+            self.params["pid"] += 1
+        else:
+            self.params["pid"] = 0
+
+class Rule34TagExtractor(Rule34Extractor, booru.BooruTagExtractor):
+    """Extractor for images from rule34.xxx based on search-tags"""
+    subcategory = "tag"
+    pattern = [(r"(?:https?://)?(?:www\.)?rule34\.xxx/(?:index\.php)?"
+                r"\?page=post&s=list&tags=([^&]+)")]
+    test = [("http://rule34.xxx/index.php?page=post&s=list&tags=danraku", {
+        "url": "104094495973edfe7e764c8f2dd42017163322aa",
+        "content": "a01768c6f86f32eb7ebbdeb87c30b0d9968d7f97",
+    })]
+
+class Rule34PostExtractor(Rule34Extractor, booru.BooruPostExtractor):
+    """Extractor for single images from rule34.xxx"""
+    subcategory = "post"
+    pattern = [(r"(?:https?://)?(?:www\.)?rule34\.xxx/(?:index\.php)?"
+                r"\?page=post&s=view&id=(\d+)")]
+    test = [("http://rule34.xxx/index.php?page=post&s=view&id=1974854", {
+        "url": "3b1f9817785868d1cd94d5376d20478eed591965",
+        "content": "fd2820df78fb937532da0a46f7af6cefc4dc94be",
+    })]
diff --git a/gallery_dl/extractor/safebooru.py b/gallery_dl/extractor/safebooru.py
index 8248181c..cf9e160c 100644
--- a/gallery_dl/extractor/safebooru.py
+++ b/gallery_dl/extractor/safebooru.py
@@ -12,7 +12,6 @@ from . import booru
 
 class SafebooruExtractor(booru.XMLBooruExtractor):
     """Base class for safebooru extractors"""
-
     category = "safebooru"
     api_url = "http://safebooru.org/index.php"