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 DatwinRipper extends AbstractHTMLRipper { public DatwinRipper(URL url) throws IOException { super(url); } @Override public String getHost() { return "datwin"; } @Override public String getDomain() { return "datw.in"; } @Override public String getGID(URL url) throws MalformedURLException { Pattern p = Pattern.compile("^.*datw.in/([a-zA-Z0-9\\-_]+).*$"); Matcher m = p.matcher(url.toExternalForm()); if (m.matches()) { return m.group(1); } throw new MalformedURLException( "Expected datw.in gallery formats: " + "datw.in/..." + " Got: " + url); } @Override public Document getFirstPage() throws IOException { return Http.url(url).get(); } @Override public List getURLsFromPage(Document doc) { List imageURLs = new ArrayList(); for (Element thumb : doc.select("img.attachment-thumbnail")) { String image = thumb.attr("src"); image = image.replaceAll("-\\d{1,3}x\\d{1,3}", ""); imageURLs.add(image); } return imageURLs; } @Override public void downloadURL(URL url, int index) { addURLToDownload(url, getPrefix(index)); } }