ImgScroll/src/main/java/com/rarchives/ripme/ripper/rippers/HbrowseRipper.java

68 lines
2.1 KiB
Java
Raw Normal View History

2017-10-17 06:02:44 +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.Arrays;
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 HbrowseRipper extends AbstractHTMLRipper {
public HbrowseRipper(URL url) throws IOException {
super(url);
}
@Override
public String getHost() {
return "hbrowse";
}
@Override
public String getDomain() {
return "hbrowse.com";
}
@Override
public String getGID(URL url) throws MalformedURLException {
Pattern p = Pattern.compile("http://www.hbrowse.com/\\d+/([a-zA-Z0-9]*)");
Matcher m = p.matcher(url.toExternalForm());
if (m.matches()) {
return m.group(1);
}
throw new MalformedURLException("Expected hbrowse.com URL format: " +
"hbrowse.com/ID/COMICID - got " + url + " instead");
}
@Override
public Document getFirstPage() throws IOException {
// "url" is an instance field of the superclass
Document tempDoc = Http.url(url).get();
return Http.url(tempDoc.select("td[id=pageTopHome] > a[title=view thumbnails (top)]").attr("href")).get();
}
@Override
public List<String> getURLsFromPage(Document doc) {
List<String> result = new ArrayList<String>();
for (Element el : doc.select("table > tbody > tr > td > a > img")) {
String imageURL = el.attr("src").replace("/zzz", "");
result.add(imageURL);
}
return result;
}
@Override
public void downloadURL(URL url, int index) {
addURLToDownload(url, getPrefix(index));
}
}