Add yuvutu.com ripper.

This commit is contained in:
rephormat 2018-01-12 19:24:40 -06:00
parent c070f154f4
commit f7ae0e8d96
2 changed files with 152 additions and 0 deletions

View File

@ -0,0 +1,70 @@
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.AbstractHTMLRipper;
import com.rarchives.ripme.utils.Http;
public class YuvutuRipper extends AbstractHTMLRipper {
private static final String DOMAIN = "yuvutu.com",
HOST = "yuvutu";
public YuvutuRipper(URL url) throws IOException {
super(url);
}
@Override
public String getHost() {
return HOST;
}
@Override
public String getDomain() {
return DOMAIN;
}
@Override
public boolean canRip(URL url) {
Pattern p = Pattern.compile("^http://www\\.yuvutu\\.com/modules\\.php\\?name=YuGallery&action=view&set_id=([0-9]+)$");
Matcher m = p.matcher(url.toExternalForm());
return m.matches();
}
@Override
public String getGID(URL url) throws MalformedURLException {
Pattern p = Pattern.compile("^http://www\\.yuvutu\\.com/modules\\.php\\?name=YuGallery&action=view&set_id=([0-9]+)$");
Matcher m = p.matcher(url.toExternalForm());
if (m.matches()) {
return m.group(1);
}
throw new MalformedURLException("Expected yuvutu.com URL format: " +
"yuvutu.com/modules.php?name=YuGallery&action=view&set_id=albumid - got " + url + "instead");
}
@Override
public Document getFirstPage() throws IOException {
return Http.url(url).get();
}
@Override
public List<String> getURLsFromPage(Document doc) {
List<String> imageURLs = new ArrayList<>();
for (Element thumb : doc.select("div#galleria > a > img")) {
String image = thumb.attr("src");
imageURLs.add(image);
}
return imageURLs;
}
@Override
public void downloadURL(URL url, int index) {
addURLToDownload(url, getPrefix(index));
}
}

View File

@ -0,0 +1,82 @@
package com.rarchives.ripme.ripper.rippers.video;
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.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import com.rarchives.ripme.ripper.VideoRipper;
import com.rarchives.ripme.utils.Http;
public class YuvutuRipper extends VideoRipper {
private static final String HOST = "yuvutu";
public YuvutuRipper(URL url) throws IOException {
super(url);
}
@Override
public String getHost() {
return HOST;
}
@Override
public boolean canRip(URL url) {
Pattern p = Pattern.compile("^http://www\\.yuvutu\\.com/video/[0-9]+/(.*)$");
Matcher m = p.matcher(url.toExternalForm());
return m.matches();
}
@Override
public URL sanitizeURL(URL url) throws MalformedURLException {
return url;
}
@Override
public String getGID(URL url) throws MalformedURLException {
Pattern p = Pattern.compile("^http://www\\.yuvutu\\.com/video/[0-9]+/(.*)$");
Matcher m = p.matcher(url.toExternalForm());
if (m.matches()) {
return m.group(1);
}
throw new MalformedURLException(
"Expected yuvutu format:"
+ "yuvutu.com/video/####"
+ " Got: " + url);
}
@Override
public void rip() throws IOException {
logger.info("Retrieving " + this.url);
Document doc = Http.url(url).get();
Element iframe = doc.select("iframe").first();
String iframeSrc = iframe.attr("src");
if (iframeSrc != null) {
doc = Http.url("http://www.yuvutu.com" + iframeSrc).get();
} else {
throw new IOException("Could not find iframe code at " + url);
}
Elements script = doc.select("script");
if (script.size() == 0) {
throw new IOException("Could not find script code at " + url);
}
Pattern p = Pattern.compile("file: \"(.*?)\"");
for (Element element : script) {
Matcher m = p.matcher(element.data());
if (m.find()){
String vidUrl = m.group(1);
addURLToDownload(new URL(vidUrl), HOST + "_" + getGID(this.url));
}
}
waitForThreads();
}
}