Added motherless support, various unit test changes
Motherless ripper gets images and videos. Unit tests have flag to avoid downloading content on every execution.
This commit is contained in:
4pr0n
parent
4a47cc650e
commit
76d27fd199
@ -14,8 +14,16 @@ public class DownloadThreadPool {
|
||||
private ExecutorService threadPool = null;
|
||||
|
||||
public DownloadThreadPool() {
|
||||
initialize("Main");
|
||||
}
|
||||
|
||||
public DownloadThreadPool(String threadPoolName) {
|
||||
initialize(threadPoolName);
|
||||
}
|
||||
|
||||
private void initialize(String threadPoolName) {
|
||||
int threads = Utils.getConfigInteger("threads.size", 10);
|
||||
logger.debug("Initializing thread pool with " + threads + " threads");
|
||||
logger.debug("Initializing " + threadPoolName + " thread pool with " + threads + " threads");
|
||||
threadPool = Executors.newFixedThreadPool(threads);
|
||||
}
|
||||
|
||||
|
||||
@ -143,6 +143,9 @@ public class ImgurRipper extends AbstractRipper {
|
||||
}
|
||||
}
|
||||
|
||||
// TODO If album is empty, use this to check for cached images:
|
||||
// http://i.rarchives.com/search.cgi?cache=http://imgur.com/a/albumID
|
||||
// At the least, get the thumbnails.
|
||||
logger.info("[!] Falling back to elemental retrieval method");
|
||||
|
||||
// Fall back to parsing HTML elements
|
||||
|
||||
@ -0,0 +1,111 @@
|
||||
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.apache.log4j.Logger;
|
||||
import org.jsoup.Jsoup;
|
||||
import org.jsoup.nodes.Document;
|
||||
import org.jsoup.nodes.Element;
|
||||
|
||||
import com.rarchives.ripme.ripper.AbstractRipper;
|
||||
import com.rarchives.ripme.ripper.DownloadThreadPool;
|
||||
|
||||
public class MotherlessRipper extends AbstractRipper {
|
||||
|
||||
private static final String DOMAIN = "motherless.com",
|
||||
HOST = "motherless";
|
||||
private static final Logger logger = Logger.getLogger(MotherlessRipper.class);
|
||||
private static final String USER_AGENT =
|
||||
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.7; rv:27.0) Gecko/20100101 Firefox/27.0";
|
||||
|
||||
private DownloadThreadPool motherlessThreadPool;
|
||||
|
||||
public MotherlessRipper(URL url) throws IOException {
|
||||
super(url);
|
||||
motherlessThreadPool = new DownloadThreadPool();
|
||||
}
|
||||
|
||||
@Override
|
||||
public boolean canRip(URL url) {
|
||||
return url.getHost().endsWith(DOMAIN);
|
||||
}
|
||||
|
||||
@Override
|
||||
public String getHost() {
|
||||
return HOST;
|
||||
}
|
||||
|
||||
@Override
|
||||
public URL sanitizeURL(URL url) throws MalformedURLException {
|
||||
String gid = getGID(url);
|
||||
URL newURL = new URL("http://motherless.com/G" + gid);
|
||||
logger.debug("Sanitized URL from " + url + " to " + newURL);
|
||||
return newURL;
|
||||
}
|
||||
|
||||
@Override
|
||||
public String getGID(URL url) throws MalformedURLException {
|
||||
Pattern p = Pattern.compile("^https?://(www\\.)?motherless\\.com/G([A-Z0-9]{6,8}).*$");
|
||||
Matcher m = p.matcher(url.toExternalForm());
|
||||
if (!m.matches()) {
|
||||
throw new MalformedURLException("Expected URL format: http://motherless.com/GXXXXXXXX");
|
||||
}
|
||||
return m.group(m.groupCount());
|
||||
}
|
||||
|
||||
@Override
|
||||
public void rip() throws IOException {
|
||||
int index = 0;
|
||||
logger.info("[ ] Retrieving " + this.url.toExternalForm());
|
||||
Document doc = Jsoup.connect(this.url.toExternalForm())
|
||||
.userAgent(USER_AGENT)
|
||||
.get();
|
||||
for (Element thumb : doc.select("div.thumb a.img-container")) {
|
||||
URL url = new URL("http://" + DOMAIN + thumb.attr("href"));
|
||||
index += 1;
|
||||
// Create thread for finding image at "url" page
|
||||
MotherlessImageThread mit = new MotherlessImageThread(url, index);
|
||||
motherlessThreadPool.addThread(mit);
|
||||
}
|
||||
motherlessThreadPool.waitForThreads();
|
||||
waitForThreads();
|
||||
}
|
||||
|
||||
/**
|
||||
* Helper class to find and download images found on "image" pages
|
||||
*/
|
||||
private class MotherlessImageThread extends Thread {
|
||||
private URL url;
|
||||
private int index;
|
||||
|
||||
public MotherlessImageThread(URL url, int index) {
|
||||
super();
|
||||
this.url = url;
|
||||
this.index = index;
|
||||
}
|
||||
|
||||
@Override
|
||||
public void run() {
|
||||
try {
|
||||
Document doc = Jsoup.connect(this.url.toExternalForm())
|
||||
.userAgent(USER_AGENT)
|
||||
.get();
|
||||
Pattern p = Pattern.compile("^.*__fileurl = '([^']{1,})';.*$", Pattern.DOTALL);
|
||||
Matcher m = p.matcher(doc.outerHtml());
|
||||
if (m.matches()) {
|
||||
String file = m.group(1);
|
||||
addURLToDownload(new URL(file), String.format("%03d_", index));
|
||||
} else {
|
||||
logger.warn("[!] could not find '__fileurl' at " + url);
|
||||
}
|
||||
} catch (IOException e) {
|
||||
logger.error("[!] Exception while loading/parsing " + this.url, e);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
@ -55,6 +55,9 @@ public class ImgurRipperTest extends RippersTest {
|
||||
}
|
||||
|
||||
public void testImgurAlbums() throws IOException {
|
||||
if (!DOWNLOAD_CONTENT) {
|
||||
return;
|
||||
}
|
||||
List<URL> contentURLs = new ArrayList<URL>();
|
||||
// URLs that should return more than 1 image
|
||||
contentURLs.add(new URL("http://imgur.com/a/hqJIu")); // Vertical layout
|
||||
|
||||
@ -10,6 +10,9 @@ import com.rarchives.ripme.ripper.rippers.InstagramRipper;
|
||||
public class InstagramRipperTest extends RippersTest {
|
||||
|
||||
public void testInstagramAlbums() throws IOException {
|
||||
if (!DOWNLOAD_CONTENT) {
|
||||
return;
|
||||
}
|
||||
List<URL> contentURLs = new ArrayList<URL>();
|
||||
contentURLs.add(new URL("http://instagram.com/feelgoodincc#"));
|
||||
for (URL url : contentURLs) {
|
||||
|
||||
@ -0,0 +1,36 @@
|
||||
package com.rarchives.ripme.tst.ripper.rippers;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.net.URL;
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
|
||||
import com.rarchives.ripme.ripper.rippers.MotherlessRipper;
|
||||
|
||||
public class MotherlessRipperTest extends RippersTest {
|
||||
|
||||
public void testMotherlessAlbums() throws IOException {
|
||||
if (!DOWNLOAD_CONTENT) {
|
||||
return;
|
||||
}
|
||||
List<URL> contentURLs = new ArrayList<URL>();
|
||||
|
||||
// Image album
|
||||
contentURLs.add(new URL("http://motherless.com/G4DAA18D"));
|
||||
// Video album
|
||||
contentURLs.add(new URL("http://motherless.com/GFD0F537"));
|
||||
|
||||
for (URL url : contentURLs) {
|
||||
try {
|
||||
MotherlessRipper ripper = new MotherlessRipper(url);
|
||||
ripper.rip();
|
||||
assert(ripper.getWorkingDir().listFiles().length > 1);
|
||||
deleteDir(ripper.getWorkingDir());
|
||||
} catch (Exception e) {
|
||||
e.printStackTrace();
|
||||
fail("Error while ripping URL " + url + ": " + e.getMessage());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
@ -6,6 +6,9 @@ import junit.framework.TestCase;
|
||||
|
||||
public class RippersTest extends TestCase {
|
||||
|
||||
// Flag for avoiding downloading content with every unit test
|
||||
public final boolean DOWNLOAD_CONTENT = false;
|
||||
|
||||
public void testNothing() {
|
||||
// Avoid complaints about no test cases in this file.
|
||||
assert(true);
|
||||
|
||||
@ -10,6 +10,9 @@ import com.rarchives.ripme.ripper.rippers.TwitterRipper;
|
||||
public class TwitterRipperTest extends RippersTest {
|
||||
|
||||
public void testTwitterAlbums() throws IOException {
|
||||
if (!DOWNLOAD_CONTENT) {
|
||||
return;
|
||||
}
|
||||
List<URL> contentURLs = new ArrayList<URL>();
|
||||
//contentURLs.add(new URL("https://twitter.com/danngamber01/media"));
|
||||
contentURLs.add(new URL("https://twitter.com/search?q=from%3Apurrbunny%20filter%3Aimages&src=typd"));
|
||||
|
||||
Loading…
Reference in New Issue
Block a user