2014-07-20 10:31:45 +02:00
|
|
|
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 org.jsoup.select.Elements;
|
|
|
|
|
|
|
|
import com.rarchives.ripme.ripper.AbstractHTMLRipper;
|
|
|
|
import com.rarchives.ripme.utils.Http;
|
|
|
|
|
|
|
|
public class BcfakesRipper extends AbstractHTMLRipper {
|
|
|
|
|
|
|
|
public BcfakesRipper(URL url) throws IOException {
|
|
|
|
super(url);
|
|
|
|
}
|
|
|
|
|
|
|
|
@Override
|
|
|
|
public String getHost() {
|
|
|
|
return "bcfakes";
|
|
|
|
}
|
|
|
|
@Override
|
|
|
|
public String getDomain() {
|
|
|
|
return "bcfakes.com";
|
|
|
|
}
|
|
|
|
|
|
|
|
@Override
|
|
|
|
public String getGID(URL url) throws MalformedURLException {
|
|
|
|
Pattern p;
|
|
|
|
Matcher m;
|
|
|
|
|
|
|
|
p = Pattern.compile("^https?://[wm.]*bcfakes.com/celebritylist/([a-zA-Z0-9\\-_]+).*$");
|
|
|
|
m = p.matcher(url.toExternalForm());
|
|
|
|
if (m.matches()) {
|
|
|
|
return m.group(1);
|
|
|
|
}
|
|
|
|
|
|
|
|
throw new MalformedURLException(
|
|
|
|
"Expected bcfakes gallery format: "
|
|
|
|
+ "http://www.bcfakes.com/celebritylist/name"
|
|
|
|
+ " Got: " + url);
|
|
|
|
}
|
2017-05-10 00:22:55 +02:00
|
|
|
|
2014-07-20 10:31:45 +02:00
|
|
|
@Override
|
|
|
|
public Document getFirstPage() throws IOException {
|
|
|
|
return Http.url(url).get();
|
|
|
|
}
|
2017-05-10 00:22:55 +02:00
|
|
|
|
2014-07-20 10:31:45 +02:00
|
|
|
@Override
|
|
|
|
public Document getNextPage(Document doc) throws IOException {
|
|
|
|
// Find next page
|
|
|
|
Elements hrefs = doc.select("a.next");
|
|
|
|
if (hrefs.size() == 0) {
|
|
|
|
throw new IOException("No more pages");
|
|
|
|
}
|
|
|
|
String nextUrl = "http://www.bcfakes.com" + hrefs.first().attr("href");
|
|
|
|
sleep(500);
|
|
|
|
return Http.url(nextUrl).get();
|
|
|
|
}
|
2017-05-10 00:22:55 +02:00
|
|
|
|
2014-07-20 10:31:45 +02:00
|
|
|
@Override
|
|
|
|
public List<String> getURLsFromPage(Document doc) {
|
2017-10-24 16:33:28 +02:00
|
|
|
List<String> imageURLs = new ArrayList<>();
|
2014-07-20 10:31:45 +02:00
|
|
|
for (Element thumb : doc.select("div.ngg-gallery-thumbnail > a > img")) {
|
|
|
|
String imageURL = thumb.attr("src");
|
|
|
|
imageURL = imageURL.replace("thumbs/thumbs_", "");
|
|
|
|
imageURLs.add(imageURL);
|
|
|
|
}
|
|
|
|
return imageURLs;
|
|
|
|
}
|
|
|
|
|
|
|
|
@Override
|
|
|
|
public void downloadURL(URL url, int index) {
|
|
|
|
addURLToDownload(url, getPrefix(index));
|
|
|
|
}
|
|
|
|
|
|
|
|
}
|