initial commit. basic ripper skeleton. long ways to go
This commit is contained in:
4pr0n
commit
db9a87595e
|
|
@ -0,0 +1,26 @@
|
|||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<classpath>
|
||||
<classpathentry kind="src" output="target/classes" path="src/main/java">
|
||||
<attributes>
|
||||
<attribute name="optional" value="true"/>
|
||||
<attribute name="maven.pomderived" value="true"/>
|
||||
</attributes>
|
||||
</classpathentry>
|
||||
<classpathentry kind="src" output="target/test-classes" path="src/test/java">
|
||||
<attributes>
|
||||
<attribute name="optional" value="true"/>
|
||||
<attribute name="maven.pomderived" value="true"/>
|
||||
</attributes>
|
||||
</classpathentry>
|
||||
<classpathentry kind="con" path="org.eclipse.jdt.launching.JRE_CONTAINER/org.eclipse.jdt.internal.debug.ui.launcher.StandardVMType/J2SE-1.5">
|
||||
<attributes>
|
||||
<attribute name="maven.pomderived" value="true"/>
|
||||
</attributes>
|
||||
</classpathentry>
|
||||
<classpathentry kind="con" path="org.eclipse.m2e.MAVEN2_CLASSPATH_CONTAINER">
|
||||
<attributes>
|
||||
<attribute name="maven.pomderived" value="true"/>
|
||||
</attributes>
|
||||
</classpathentry>
|
||||
<classpathentry kind="output" path="target/classes"/>
|
||||
</classpath>
|
||||
|
|
@ -0,0 +1,23 @@
|
|||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<projectDescription>
|
||||
<name>ripme</name>
|
||||
<comment></comment>
|
||||
<projects>
|
||||
</projects>
|
||||
<buildSpec>
|
||||
<buildCommand>
|
||||
<name>org.eclipse.jdt.core.javabuilder</name>
|
||||
<arguments>
|
||||
</arguments>
|
||||
</buildCommand>
|
||||
<buildCommand>
|
||||
<name>org.eclipse.m2e.core.maven2Builder</name>
|
||||
<arguments>
|
||||
</arguments>
|
||||
</buildCommand>
|
||||
</buildSpec>
|
||||
<natures>
|
||||
<nature>org.eclipse.jdt.core.javanature</nature>
|
||||
<nature>org.eclipse.m2e.core.maven2Nature</nature>
|
||||
</natures>
|
||||
</projectDescription>
|
||||
|
|
@ -0,0 +1,46 @@
|
|||
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
|
||||
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
|
||||
<modelVersion>4.0.0</modelVersion>
|
||||
<groupId>com.rarchives.ripme</groupId>
|
||||
<artifactId>ripme</artifactId>
|
||||
<packaging>jar</packaging>
|
||||
<version>1.0-SNAPSHOT</version>
|
||||
<name>ripme</name>
|
||||
<url>http://maven.apache.org</url>
|
||||
<dependencies>
|
||||
<dependency>
|
||||
<groupId>junit</groupId>
|
||||
<artifactId>junit</artifactId>
|
||||
<version>3.8.1</version>
|
||||
<scope>test</scope>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<!-- jsoup HTML parser library @ http://jsoup.org/ -->
|
||||
<groupId>org.jsoup</groupId>
|
||||
<artifactId>jsoup</artifactId>
|
||||
<version>1.7.3</version>
|
||||
</dependency>
|
||||
<dependency>
|
||||
<groupId>org.json</groupId>
|
||||
<artifactId>json</artifactId>
|
||||
<version>20140107</version>
|
||||
</dependency>
|
||||
</dependencies>
|
||||
<build>
|
||||
<plugins>
|
||||
<plugin>
|
||||
<artifactId>maven-assembly-plugin</artifactId>
|
||||
<configuration>
|
||||
<archive>
|
||||
<manifest>
|
||||
<mainClass>fully.qualified.MainClass</mainClass>
|
||||
</manifest>
|
||||
</archive>
|
||||
<descriptorRefs>
|
||||
<descriptorRef>jar-with-dependencies</descriptorRef>
|
||||
</descriptorRefs>
|
||||
</configuration>
|
||||
</plugin>
|
||||
</plugins>
|
||||
</build>
|
||||
</project>
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
package com.rarchives.ripme;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.net.URL;
|
||||
|
||||
import com.rarchives.ripme.ripper.rippers.ImagefapRipper;
|
||||
|
||||
/**
|
||||
*
|
||||
*/
|
||||
public class App {
|
||||
public static void main( String[] args ) throws IOException {
|
||||
URL url = new URL("http://www.imagefap.com/pictures/4117023/Mirror-flat-stomach-small-firm-tits");
|
||||
System.out.println("URL: " + url.toExternalForm());
|
||||
ImagefapRipper ir = new ImagefapRipper(url);
|
||||
System.out.println("Ripping");
|
||||
ir.rip();
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,24 @@
|
|||
package com.rarchives.ripme.ripper;
|
||||
|
||||
import java.net.MalformedURLException;
|
||||
import java.net.URL;
|
||||
|
||||
public abstract class AbstractRipper implements RipperInterface {
|
||||
|
||||
protected URL url;
|
||||
|
||||
public AbstractRipper(URL url) throws MalformedURLException {
|
||||
// Ensure that the inheriting class can rip this URL.
|
||||
if (!canRip(url)) {
|
||||
throw new MalformedURLException("Unable to rip url: " + url);
|
||||
}
|
||||
this.url = url;
|
||||
sanitizeURL();
|
||||
}
|
||||
|
||||
public URL getURL() {
|
||||
return url;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,11 @@
|
|||
package com.rarchives.ripme.ripper;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.net.MalformedURLException;
|
||||
import java.net.URL;
|
||||
|
||||
public interface RipperInterface {
|
||||
public void rip() throws IOException;
|
||||
public boolean canRip(URL url);
|
||||
public void sanitizeURL() throws MalformedURLException;
|
||||
}
|
||||
|
|
@ -0,0 +1,68 @@
|
|||
package com.rarchives.ripme.ripper.rippers;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.net.MalformedURLException;
|
||||
import java.net.URL;
|
||||
import java.util.regex.Matcher;
|
||||
import java.util.regex.Pattern;
|
||||
|
||||
import org.jsoup.Jsoup;
|
||||
import org.jsoup.nodes.Document;
|
||||
import org.jsoup.nodes.Element;
|
||||
|
||||
import com.rarchives.ripme.ripper.AbstractRipper;
|
||||
|
||||
public class ImagefapRipper extends AbstractRipper {
|
||||
|
||||
private static final String HOST = "imagefap.com";
|
||||
|
||||
public ImagefapRipper(URL url) throws MalformedURLException {
|
||||
super(url);
|
||||
}
|
||||
|
||||
/**
|
||||
* Reformat given URL into the desired format (all images on single page)
|
||||
*/
|
||||
public void sanitizeURL() throws MalformedURLException {
|
||||
String gid = null;
|
||||
Pattern p = Pattern.compile("^.*imagefap.com/gallery.php?gid=([0-9]{1,}).*$");
|
||||
Matcher m = p.matcher(this.url.toExternalForm());
|
||||
if (m.matches()) {
|
||||
gid = m.group(1);
|
||||
} else {
|
||||
p = Pattern.compile("^.*imagefap.com/pictures/([0-9]{1,}).*$");
|
||||
m = p.matcher(this.url.toExternalForm());
|
||||
if (m.matches()) {
|
||||
gid = m.group(1);
|
||||
}
|
||||
}
|
||||
if (gid == null) {
|
||||
throw new MalformedURLException("Expected imagefap.com gallery formats:"
|
||||
+ "imagefap.com/gallery.php?gid=####... or"
|
||||
+ "imagefap.com/pictures/####...");
|
||||
}
|
||||
this.url = new URL("http://www.imagefap.com/gallery.php?gid=" + gid + "&view=2");
|
||||
}
|
||||
|
||||
public void rip() throws IOException {
|
||||
System.err.println("Connecting to " + this.url.toExternalForm());
|
||||
Document doc = Jsoup.connect(this.url.toExternalForm()).get();
|
||||
for (Element thumb : doc.select("#gallery img")) {
|
||||
if (!thumb.hasAttr("src") || !thumb.hasAttr("width")) {
|
||||
continue;
|
||||
}
|
||||
String image = thumb.attr("src");
|
||||
image = image.replaceAll("http://x.*.fap.to/images/thumb/", "http://fap.to/images/full/");
|
||||
System.err.println(image);
|
||||
}
|
||||
}
|
||||
|
||||
public boolean canRip(URL url) {
|
||||
if (!url.getHost().endsWith(HOST)) {
|
||||
return false;
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,33 @@
|
|||
package com.rarchives.ripme;
|
||||
|
||||
import junit.framework.Test;
|
||||
import junit.framework.TestCase;
|
||||
import junit.framework.TestSuite;
|
||||
|
||||
/**
|
||||
* Unit test for simple App.
|
||||
*/
|
||||
public class AppTest extends TestCase {
|
||||
/**
|
||||
* Create the test case
|
||||
*
|
||||
* @param testName name of the test case
|
||||
*/
|
||||
public AppTest( String testName ) {
|
||||
super( testName );
|
||||
}
|
||||
|
||||
/**
|
||||
* @return the suite of tests being tested
|
||||
*/
|
||||
public static Test suite() {
|
||||
return new TestSuite( AppTest.class );
|
||||
}
|
||||
|
||||
/**
|
||||
* Rigourous Test :-)
|
||||
*/
|
||||
public void testApp() {
|
||||
assertTrue( true );
|
||||
}
|
||||
}
|
||||
Loading…
Reference in New Issue