Added user support to SmuttyRipper

This commit is contained in:
cyian-1756 2018-05-06 06:27:41 -04:00
parent 2d1e648bd1
commit 66bba724f9

View File

@ -3,24 +3,19 @@ package com.rarchives.ripme.ripper.rippers;
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;
import com.rarchives.ripme.ripper.AlbumRipper;
import com.rarchives.ripme.ui.RipStatusMessage.STATUS;
import com.rarchives.ripme.ripper.AbstractHTMLRipper;
import com.rarchives.ripme.utils.Http;
/**
* Appears to be broken as of 2015-02-11.
* Generating large image from thumbnail requires replacing "/m/" with something else:
* -> Sometimes "/b/"
* -> Sometimes "/p/"
* No way to know without loading the image page.
*/
public class SmuttyRipper extends AlbumRipper {
public class SmuttyRipper extends AbstractHTMLRipper {
private static final String DOMAIN = "smutty.com",
HOST = "smutty";
@ -29,6 +24,16 @@ public class SmuttyRipper extends AlbumRipper {
super(url);
}
@Override
public String getHost() {
return "smutty";
}
@Override
public String getDomain() {
return "smutty.com";
}
@Override
public boolean canRip(URL url) {
return (url.getHost().endsWith(DOMAIN));
@ -40,69 +45,57 @@ public class SmuttyRipper extends AlbumRipper {
}
@Override
public void rip() throws IOException {
int page = 0;
String url, tag = getGID(this.url);
boolean hasNextPage = true;
while (hasNextPage) {
public List<String> getURLsFromPage(Document doc) {
List<String> results = new ArrayList<>();
for (Element image : doc.select("a.l > img")) {
if (isStopped()) {
break;
}
page++;
url = "http://smutty.com/h/" + tag + "/?q=%23" + tag + "&page=" + page + "&sort=date&lazy=1";
this.sendUpdate(STATUS.LOADING_RESOURCE, url);
logger.info(" Retrieving " + url);
Document doc;
try {
doc = Http.url(url)
.ignoreContentType()
.get();
} catch (IOException e) {
if (e.toString().contains("Status=404")) {
logger.info("No more pages to load");
} else {
logger.warn("Exception while loading " + url, e);
}
break;
}
for (Element image : doc.select("a.l > img")) {
if (isStopped()) {
break;
}
String imageUrl = image.attr("src");
String imageUrl = image.attr("src");
// Construct direct link to image based on thumbnail
StringBuilder sb = new StringBuilder();
String[] fields = imageUrl.split("/");
for (int i = 0; i < fields.length; i++) {
if (i == fields.length - 2 && fields[i].equals("m")) {
fields[i] = "b";
}
sb.append(fields[i]);
if (i < fields.length - 1) {
sb.append("/");
}
// Construct direct link to image based on thumbnail
StringBuilder sb = new StringBuilder();
String[] fields = imageUrl.split("/");
for (int i = 0; i < fields.length; i++) {
if (i == fields.length - 2 && fields[i].equals("m")) {
fields[i] = "b";
}
sb.append(fields[i]);
if (i < fields.length - 1) {
sb.append("/");
}
imageUrl = sb.toString();
addURLToDownload(new URL("http:" + imageUrl));
}
if (doc.select("#next").size() == 0) {
break; // No more pages
}
// Wait before loading next page
try {
Thread.sleep(1000);
} catch (InterruptedException e) {
logger.error("[!] Interrupted while waiting to load next album:", e);
break;
}
imageUrl = sb.toString();
results.add("http:" + imageUrl);
}
waitForThreads();
return results;
}
@Override
public String getHost() {
return HOST;
public Document getNextPage(Document doc) throws IOException {
Element elem = doc.select("a.next").first();
if (elem == null) {
throw new IOException("No more pages");
}
String nextPage = elem.attr("href");
// Some times this returns a empty string
// This for stops that
if (nextPage.equals("")) {
throw new IOException("No more pages");
}
else {
return Http.url("https://smutty.com" + nextPage).get();
}
}
@Override
public Document getFirstPage() throws IOException {
// "url" is an instance field of the superclass
return Http.url(url).get();
}
public void downloadURL(URL url, int index) {
addURLToDownload(url, getPrefix(index));
}
@Override
@ -117,6 +110,12 @@ public class SmuttyRipper extends AlbumRipper {
if (m.matches()) {
return m.group(1).replace("%23", "");
}
p = Pattern.compile("^https?://smutty.com/user/([a-zA-Z0-9\\-_]+)/?$");
m = p.matcher(url.toExternalForm());
if (m.matches()) {
return m.group(1);
}
throw new MalformedURLException("Expected tag in URL (smutty.com/h/tag and not " + url);
}