2014-05-26 10:04:42 +02:00
|
|
|
package com.rarchives.ripme.ripper.rippers;
|
|
|
|
|
|
|
|
import java.io.IOException;
|
|
|
|
import java.net.MalformedURLException;
|
|
|
|
import java.net.URL;
|
2014-06-25 11:03:47 +02:00
|
|
|
import java.util.ArrayList;
|
|
|
|
import java.util.List;
|
2014-05-26 10:04:42 +02:00
|
|
|
import java.util.regex.Matcher;
|
|
|
|
import java.util.regex.Pattern;
|
|
|
|
|
|
|
|
import org.jsoup.nodes.Document;
|
2016-04-17 20:52:57 +02:00
|
|
|
import org.jsoup.nodes.Element;
|
2014-05-26 10:04:42 +02:00
|
|
|
import org.jsoup.select.Elements;
|
|
|
|
|
2014-06-25 11:03:47 +02:00
|
|
|
import com.rarchives.ripme.ripper.AbstractHTMLRipper;
|
2014-06-22 02:08:42 +02:00
|
|
|
import com.rarchives.ripme.utils.Http;
|
2014-05-26 10:04:42 +02:00
|
|
|
|
2014-06-25 11:03:47 +02:00
|
|
|
public class VidbleRipper extends AbstractHTMLRipper {
|
2014-05-26 10:04:42 +02:00
|
|
|
|
|
|
|
public VidbleRipper(URL url) throws IOException {
|
|
|
|
super(url);
|
|
|
|
}
|
|
|
|
|
|
|
|
@Override
|
|
|
|
public String getHost() {
|
2014-06-25 11:03:47 +02:00
|
|
|
return "vidble";
|
|
|
|
}
|
|
|
|
@Override
|
|
|
|
public String getDomain() {
|
|
|
|
return "vidble.com";
|
2014-05-26 10:04:42 +02:00
|
|
|
}
|
2017-05-10 00:22:55 +02:00
|
|
|
|
2014-05-26 10:04:42 +02:00
|
|
|
@Override
|
|
|
|
public String getGID(URL url) throws MalformedURLException {
|
|
|
|
Pattern p; Matcher m;
|
|
|
|
|
|
|
|
p = Pattern.compile("^.*vidble.com/album/([a-zA-Z0-9_\\-]+).*$");
|
|
|
|
m = p.matcher(url.toExternalForm());
|
|
|
|
if (m.matches()) {
|
|
|
|
return m.group(1);
|
|
|
|
}
|
|
|
|
throw new MalformedURLException(
|
|
|
|
"Expected vidble.com album format: "
|
|
|
|
+ "vidble.com/album/####"
|
|
|
|
+ " Got: " + url);
|
|
|
|
}
|
|
|
|
|
|
|
|
@Override
|
2014-06-25 11:03:47 +02:00
|
|
|
public Document getFirstPage() throws IOException {
|
|
|
|
return Http.url(url).get();
|
|
|
|
}
|
|
|
|
|
|
|
|
@Override
|
|
|
|
public List<String> getURLsFromPage(Document doc) {
|
|
|
|
return getURLsFromPageStatic(doc);
|
|
|
|
}
|
|
|
|
|
|
|
|
private static List<String> getURLsFromPageStatic(Document doc) {
|
2017-10-24 16:33:28 +02:00
|
|
|
List<String> imageURLs = new ArrayList<>();
|
2016-04-17 20:52:57 +02:00
|
|
|
Elements els = doc.select("#ContentPlaceHolder1_divContent");
|
|
|
|
Elements imgs = els.select("img");
|
|
|
|
for (Element img : imgs) {
|
|
|
|
String src = img.absUrl("src");
|
|
|
|
src = src.replaceAll("_[a-zA-Z]{3,5}", "");
|
2017-05-10 00:22:55 +02:00
|
|
|
|
2016-04-17 20:52:57 +02:00
|
|
|
if (!src.equals("")) {
|
|
|
|
imageURLs.add(src);
|
2014-05-26 10:04:42 +02:00
|
|
|
}
|
|
|
|
}
|
2014-06-25 11:03:47 +02:00
|
|
|
return imageURLs;
|
2016-04-17 20:52:57 +02:00
|
|
|
}
|
2014-05-26 10:04:42 +02:00
|
|
|
|
|
|
|
@Override
|
2014-06-25 11:03:47 +02:00
|
|
|
public void downloadURL(URL url, int index) {
|
|
|
|
addURLToDownload(url, getPrefix(index));
|
2014-05-26 10:04:42 +02:00
|
|
|
}
|
|
|
|
|
2014-06-25 11:03:47 +02:00
|
|
|
public static List<URL> getURLsFromPage(URL url) throws IOException {
|
2017-10-24 16:33:28 +02:00
|
|
|
List<URL> urls = new ArrayList<>();
|
2014-06-25 11:03:47 +02:00
|
|
|
Document doc = Http.url(url).get();
|
|
|
|
for (String stringURL : getURLsFromPageStatic(doc)) {
|
|
|
|
urls.add(new URL(stringURL));
|
|
|
|
}
|
|
|
|
return urls;
|
|
|
|
}
|
2016-04-17 20:52:57 +02:00
|
|
|
}
|