From bbc78ef67f24a222dcdd6adef97b61e4feec1f00 Mon Sep 17 00:00:00 2001
From: kas-luthor <kas-luthor@users.noreply.github.com>
Date: Thu, 26 Nov 2015 22:18:24 +0100
Subject: [PATCH] added ripper for xbooru.com removed license header for paheal
 ripper added percent sign to url matching for paheal ripper

---
 .../ripme/ripper/rippers/PahealRipper.java    |  8 +-
 .../ripme/ripper/rippers/XbooruRipper.java    | 83 +++++++++++++++++++
 2 files changed, 84 insertions(+), 7 deletions(-)
 create mode 100644 src/main/java/com/rarchives/ripme/ripper/rippers/XbooruRipper.java

diff --git a/src/main/java/com/rarchives/ripme/ripper/rippers/PahealRipper.java b/src/main/java/com/rarchives/ripme/ripper/rippers/PahealRipper.java
index 16591eb1..520914a8 100644
--- a/src/main/java/com/rarchives/ripme/ripper/rippers/PahealRipper.java
+++ b/src/main/java/com/rarchives/ripme/ripper/rippers/PahealRipper.java
@@ -1,9 +1,3 @@
-/*
- * To change this license header, choose License Headers in Project Properties.
- * To change this template file, choose Tools | Templates
- * and open the template in the editor.
- */
-
 package com.rarchives.ripme.ripper.rippers;
 
 import com.rarchives.ripme.ripper.AbstractHTMLRipper;
@@ -92,7 +86,7 @@ public class PahealRipper extends AbstractHTMLRipper{
 	@Override
 	public String getGID(URL url) throws MalformedURLException {
 		if(gidPattern==null)
-			gidPattern=Pattern.compile("^https?://(www\\.)?rule34\\.paheal\\.net/post/list/([a-zA-Z0-9$_.+!*'(),-]+)(/.*)?(#.*)?$");
+			gidPattern=Pattern.compile("^https?://(www\\.)?rule34\\.paheal\\.net/post/list/([a-zA-Z0-9$_.+!*'(),%-]+)(/.*)?(#.*)?$");
 		
 		Matcher m = gidPattern.matcher(url.toExternalForm());
 		if(m.matches())
diff --git a/src/main/java/com/rarchives/ripme/ripper/rippers/XbooruRipper.java b/src/main/java/com/rarchives/ripme/ripper/rippers/XbooruRipper.java
new file mode 100644
index 00000000..dcdf54f5
--- /dev/null
+++ b/src/main/java/com/rarchives/ripme/ripper/rippers/XbooruRipper.java
@@ -0,0 +1,83 @@
+
+package com.rarchives.ripme.ripper.rippers;
+
+import com.rarchives.ripme.ripper.AbstractHTMLRipper;
+import com.rarchives.ripme.utils.Http;
+import com.rarchives.ripme.utils.Utils;
+import java.io.IOException;
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
+
+/**
+ *
+ * @author
+ */
+public class XbooruRipper extends AbstractHTMLRipper{
+	private Pattern gidPattern=null;
+
+	public XbooruRipper(URL url) throws IOException {
+		super(url);
+	}
+
+	@Override
+	public String getDomain() {
+		return "xbooru.com";
+	}
+
+	@Override
+	public String getHost() {
+		return "xbooru";
+	}
+	
+	private String getPage(int num) throws MalformedURLException{
+		return "http://xbooru.com/index.php?page=dapi&s=post&q=index&pid="+num+"&tags="+getGID(url);
+	}
+
+	@Override
+	public Document getFirstPage() throws IOException {
+		return Http.url(getPage(0)).get();
+	}
+
+	@Override
+	public Document getNextPage(Document doc) throws IOException {
+		int offset=Integer.parseInt(doc.getElementsByTag("posts").first().attr("offset"));
+		int num=Integer.parseInt(doc.getElementsByTag("posts").first().attr("count"));
+		
+		if(offset+100>num)
+			return null;
+		
+		return Http.url(getPage(offset/100+1)).get();
+	}
+
+	@Override
+	public List<String> getURLsFromPage(Document page) {
+		List<String> res=new ArrayList<String>(100);
+		for(Element e:page.getElementsByTag("post"))
+			res.add(e.attr("file_url")+"#"+e.attr("id"));
+		return res;
+	}
+
+	@Override
+	public void downloadURL(URL url, int index) {
+		addURLToDownload(url,Utils.getConfigBoolean("download.save_order",true)?url.getRef()+"-":"");
+	}
+
+	@Override
+	public String getGID(URL url) throws MalformedURLException {
+		if(gidPattern==null)
+			gidPattern=Pattern.compile("^https?://(www\\.)?xbooru\\.com/(index.php)?.*([?&]tags=([a-zA-Z0-9$_.+!*'(),%-]+))(\\&|(#.*)?$)");
+		
+		Matcher m = gidPattern.matcher(url.toExternalForm());
+		if(m.matches())
+			return m.group(4);
+		
+		throw new MalformedURLException("Expected xbooru.com URL format: xbooru.com - got "+url+" instead");
+	}
+	
+}