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

74 lines
2.6 KiB
Java
Raw Normal View History

2017-10-16 21:32:04 +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 com.rarchives.ripme.ripper.AbstractHTMLRipper;
import com.rarchives.ripme.utils.Http;
public class HentaiCafeRipper extends AbstractHTMLRipper {
public HentaiCafeRipper(URL url) throws IOException {
2017-10-17 20:11:31 +02:00
super(url);
2017-10-16 21:32:04 +02:00
}
@Override
public String getHost() {
return "hentai";
}
@Override
public String getDomain() {
return "hentai.cafe";
}
@Override
public String getGID(URL url) throws MalformedURLException {
2017-12-29 10:31:36 +01:00
Pattern p = Pattern.compile("https?://hentai\\.cafe/([a-zA-Z0-9_\\-%]*)/?$");
2017-10-16 21:32:04 +02:00
Matcher m = p.matcher(url.toExternalForm());
if (m.matches()) {
return m.group(1);
}
throw new MalformedURLException("Expected hentai.cafe URL format: " +
"hentai.cafe/COMIC - 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("div.last > p > a.x-btn").attr("href")).get();
}
@Override
public Document getNextPage(Document doc) throws IOException {
String nextPageURL = doc.select("div[id=page] > div.inner > a").attr("href");
int totalPages = Integer.parseInt(doc.select("div.panel > div.topbar > div > div.topbar_right > div.tbtitle > div.text").text().replace("", ""));
String[] nextPageURLSplite = nextPageURL.split("/");
// This checks if the next page number is greater than the total number of pages
if (totalPages >= Integer.parseInt(nextPageURLSplite[nextPageURLSplite.length -1])) {
return Http.url(nextPageURL).get();
}
throw new IOException("No more pages");
}
@Override
public List<String> getURLsFromPage(Document doc) {
List<String> result = new ArrayList<>();
2017-10-16 21:32:04 +02:00
result.add(doc.select("div[id=page] > div.inner > a > img.open").attr("src"));
return result;
}
@Override
public void downloadURL(URL url, int index) {
addURLToDownload(url, getPrefix(index));
}
}