Added retry logic for downloads, imagearn ripper
This commit is contained in:
parent
569b7fbdc4
commit
25232c0ab3
@ -7,6 +7,7 @@ import java.net.URL;
|
|||||||
|
|
||||||
import org.apache.log4j.Logger;
|
import org.apache.log4j.Logger;
|
||||||
|
|
||||||
|
import com.rarchives.ripme.ripper.rippers.ImagearnRipper;
|
||||||
import com.rarchives.ripme.ripper.rippers.ImagefapRipper;
|
import com.rarchives.ripme.ripper.rippers.ImagefapRipper;
|
||||||
import com.rarchives.ripme.ripper.rippers.ImgurRipper;
|
import com.rarchives.ripme.ripper.rippers.ImgurRipper;
|
||||||
import com.rarchives.ripme.utils.Utils;
|
import com.rarchives.ripme.utils.Utils;
|
||||||
@ -109,6 +110,10 @@ public abstract class AbstractRipper implements RipperInterface {
|
|||||||
AbstractRipper r = new ImgurRipper(url);
|
AbstractRipper r = new ImgurRipper(url);
|
||||||
return r;
|
return r;
|
||||||
} catch (IOException e) { }
|
} catch (IOException e) { }
|
||||||
|
try {
|
||||||
|
AbstractRipper r = new ImagearnRipper(url);
|
||||||
|
return r;
|
||||||
|
} catch (IOException e) { }
|
||||||
throw new Exception("No compatible ripper found");
|
throw new Exception("No compatible ripper found");
|
||||||
}
|
}
|
||||||
}
|
}
|
@ -17,11 +17,13 @@ public class DownloadFileThread extends Thread {
|
|||||||
|
|
||||||
private URL url;
|
private URL url;
|
||||||
private File saveAs;
|
private File saveAs;
|
||||||
|
private int retries;
|
||||||
|
|
||||||
public DownloadFileThread(URL url, File saveAs) {
|
public DownloadFileThread(URL url, File saveAs) {
|
||||||
super();
|
super();
|
||||||
this.url = url;
|
this.url = url;
|
||||||
this.saveAs = saveAs;
|
this.saveAs = saveAs;
|
||||||
|
this.retries = Utils.getConfigInteger("download.retries", 1);
|
||||||
}
|
}
|
||||||
|
|
||||||
public void run() {
|
public void run() {
|
||||||
@ -36,8 +38,11 @@ public class DownloadFileThread extends Thread {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
logger.info("[ ] Downloading file from: " + url);
|
int tries = 0; // Number of attempts to download
|
||||||
|
do {
|
||||||
try {
|
try {
|
||||||
|
logger.info("[ ] Downloading file from: " + url + (tries > 0 ? " Retry #" + tries : ""));
|
||||||
|
tries += 1;
|
||||||
Response response;
|
Response response;
|
||||||
response = Jsoup.connect(url.toExternalForm())
|
response = Jsoup.connect(url.toExternalForm())
|
||||||
.ignoreContentType(true)
|
.ignoreContentType(true)
|
||||||
@ -45,10 +50,15 @@ public class DownloadFileThread extends Thread {
|
|||||||
FileOutputStream out = (new FileOutputStream(saveAs));
|
FileOutputStream out = (new FileOutputStream(saveAs));
|
||||||
out.write(response.bodyAsBytes());
|
out.write(response.bodyAsBytes());
|
||||||
out.close();
|
out.close();
|
||||||
|
break; // Download successful: break out of infinite loop
|
||||||
} catch (IOException e) {
|
} catch (IOException e) {
|
||||||
logger.error("[!] Exception while downloading file: " + url, e);
|
logger.error("[!] Exception while downloading file: " + url + " - " + e.getMessage());
|
||||||
|
}
|
||||||
|
if (tries > this.retries) {
|
||||||
|
logger.error("[!] Exceeded maximum retries (" + this.retries + ") for URL " + url);
|
||||||
return;
|
return;
|
||||||
}
|
}
|
||||||
|
} while (true);
|
||||||
logger.info("[+] Download completed: " + url);
|
logger.info("[+] Download completed: " + url);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -24,6 +24,7 @@ public class DownloadThreadPool {
|
|||||||
}
|
}
|
||||||
|
|
||||||
public void waitForThreads() {
|
public void waitForThreads() {
|
||||||
|
logger.info("[ ] Waiting for threads to finish...");
|
||||||
threadPool.shutdown();
|
threadPool.shutdown();
|
||||||
try {
|
try {
|
||||||
threadPool.awaitTermination(60, TimeUnit.SECONDS);
|
threadPool.awaitTermination(60, TimeUnit.SECONDS);
|
||||||
|
@ -0,0 +1,92 @@
|
|||||||
|
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;
|
||||||
|
|
||||||
|
public class ImagearnRipper extends AbstractRipper {
|
||||||
|
|
||||||
|
private static final String DOMAIN = "imagearn.com",
|
||||||
|
HOST = "imagearn";
|
||||||
|
private static final Logger logger = Logger.getLogger(ImagearnRipper.class);
|
||||||
|
|
||||||
|
public ImagearnRipper(URL url) throws IOException {
|
||||||
|
super(url);
|
||||||
|
}
|
||||||
|
|
||||||
|
public boolean canRip(URL url) {
|
||||||
|
if (!url.getHost().endsWith(DOMAIN)) {
|
||||||
|
return false;
|
||||||
|
}
|
||||||
|
return true;
|
||||||
|
}
|
||||||
|
|
||||||
|
public URL sanitizeURL(URL url) throws MalformedURLException {
|
||||||
|
Pattern p = Pattern.compile("^.*imagearn.com/{1,}image.php\\?id=[0-9]{1,}.*$");
|
||||||
|
Matcher m = p.matcher(url.toExternalForm());
|
||||||
|
if (m.matches()) {
|
||||||
|
// URL points to imagearn *image*, not gallery
|
||||||
|
try {
|
||||||
|
url = getGalleryFromImage(url);
|
||||||
|
} catch (Exception e) {
|
||||||
|
logger.error("[!] " + e.getMessage(), e);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return url;
|
||||||
|
}
|
||||||
|
|
||||||
|
private URL getGalleryFromImage(URL url) throws IOException {
|
||||||
|
Document doc = Jsoup.connect(url.toExternalForm()).get();
|
||||||
|
for (Element link : doc.select("a[href~=^gallery\\.php.*$]")) {
|
||||||
|
logger.info("LINK: " + link.toString());
|
||||||
|
if (link.hasAttr("href")
|
||||||
|
&& link.attr("href").contains("gallery.php")) {
|
||||||
|
url = new URL("http://imagearn.com/" + link.attr("href"));
|
||||||
|
logger.info("[!] Found gallery from given link: " + url);
|
||||||
|
return url;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
throw new IOException("Failed to find gallery at URL " + url);
|
||||||
|
}
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public void rip() throws IOException {
|
||||||
|
int index = 0;
|
||||||
|
logger.info("[ ] Retrieving " + this.url.toExternalForm());
|
||||||
|
Document doc = Jsoup.connect(url.toExternalForm()).get();
|
||||||
|
for (Element thumb : doc.select("img.border")) {
|
||||||
|
String image = thumb.attr("src");
|
||||||
|
image = image.replaceAll("thumbs[0-9]*\\.imagearn\\.com/", "img.imagearn.com/imags/");
|
||||||
|
index += 1;
|
||||||
|
addURLToDownload(new URL(image), String.format("%03d_", index));
|
||||||
|
}
|
||||||
|
threadPool.waitForThreads();
|
||||||
|
}
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public String getHost() {
|
||||||
|
return HOST;
|
||||||
|
}
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public String getGID(URL url) throws MalformedURLException {
|
||||||
|
Pattern p = Pattern.compile("^.*imagearn.com/{1,}gallery.php\\?id=([0-9]{1,}).*$");
|
||||||
|
Matcher m = p.matcher(url.toExternalForm());
|
||||||
|
if (m.matches()) {
|
||||||
|
return m.group(1);
|
||||||
|
}
|
||||||
|
throw new MalformedURLException(
|
||||||
|
"Expected imagearn.com gallery formats: "
|
||||||
|
+ "imagearn.com/gallery.php?id=####..."
|
||||||
|
+ " Got: " + url);
|
||||||
|
}
|
||||||
|
}
|
@ -71,17 +71,11 @@ public class ImagefapRipper extends AbstractRipper {
|
|||||||
"http://x.*.fap.to/images/thumb/",
|
"http://x.*.fap.to/images/thumb/",
|
||||||
"http://fap.to/images/full/");
|
"http://fap.to/images/full/");
|
||||||
index += 1;
|
index += 1;
|
||||||
processURL(new URL(image), String.format("%03d_", index));
|
addURLToDownload(new URL(image), String.format("%03d_", index));
|
||||||
}
|
}
|
||||||
logger.info("[ ] Waiting for threads to finish...");
|
|
||||||
threadPool.waitForThreads();
|
threadPool.waitForThreads();
|
||||||
}
|
}
|
||||||
|
|
||||||
public void processURL(URL url, String prefix) {
|
|
||||||
logger.debug("Found URL: " + url);
|
|
||||||
addURLToDownload(url, prefix);
|
|
||||||
}
|
|
||||||
|
|
||||||
public boolean canRip(URL url) {
|
public boolean canRip(URL url) {
|
||||||
if (!url.getHost().endsWith(DOMAIN)) {
|
if (!url.getHost().endsWith(DOMAIN)) {
|
||||||
return false;
|
return false;
|
||||||
|
@ -75,7 +75,6 @@ public class ImgurRipper extends AbstractRipper {
|
|||||||
// TODO Get all albums by user
|
// TODO Get all albums by user
|
||||||
break;
|
break;
|
||||||
}
|
}
|
||||||
logger.info("[ ] Waiting for threads to finish...");
|
|
||||||
threadPool.waitForThreads();
|
threadPool.waitForThreads();
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -1,2 +1,3 @@
|
|||||||
threads.size = 5
|
threads.size = 5
|
||||||
file.overwrite = false
|
file.overwrite = false
|
||||||
|
download.retries = 3
|
Loading…
Reference in New Issue
Block a user