2018-04-14 00:33:31 +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 com.rarchives.ripme.ripper.AbstractHTMLRipper;
|
|
|
|
import com.rarchives.ripme.utils.Http;
|
|
|
|
|
2018-04-14 00:55:19 +02:00
|
|
|
public class BlackbrickroadofozRipper extends AbstractHTMLRipper {
|
2018-04-14 00:33:31 +02:00
|
|
|
|
2018-04-14 00:55:19 +02:00
|
|
|
public BlackbrickroadofozRipper(URL url) throws IOException {
|
2018-04-14 00:33:31 +02:00
|
|
|
super(url);
|
|
|
|
}
|
|
|
|
|
|
|
|
@Override
|
|
|
|
public String getHost() {
|
2018-04-14 00:52:38 +02:00
|
|
|
return "blackbrickroadofoz";
|
2018-04-14 00:33:31 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
@Override
|
|
|
|
public String getDomain() {
|
2018-04-14 00:52:38 +02:00
|
|
|
return "blackbrickroadofoz.com";
|
2018-04-14 00:33:31 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
@Override
|
|
|
|
public String getGID(URL url) throws MalformedURLException {
|
|
|
|
Pattern p = Pattern.compile("https?://www.blackbrickroadofoz.com/comic/([a-zA-Z0-9_-]*)/?$");
|
|
|
|
Matcher m = p.matcher(url.toExternalForm());
|
|
|
|
if (m.matches()) {
|
|
|
|
return m.group(1);
|
|
|
|
}
|
|
|
|
throw new MalformedURLException("Expected blackbrickroadofoz URL format: " +
|
|
|
|
"www.blackbrickroadofoz.com/comic/PAGE - got " + url + " instead");
|
|
|
|
}
|
|
|
|
|
|
|
|
@Override
|
|
|
|
public Document getFirstPage() throws IOException {
|
|
|
|
// "url" is an instance field of the superclass
|
|
|
|
return Http.url(url).get();
|
|
|
|
}
|
|
|
|
|
|
|
|
@Override
|
|
|
|
public Document getNextPage(Document doc) throws IOException {
|
2018-04-14 00:52:38 +02:00
|
|
|
sleep(1000);
|
|
|
|
Element elem = doc.select("div[id=topnav] > nav.cc-nav > a.cc-next").first();
|
2018-04-14 00:33:31 +02:00
|
|
|
if (elem == null) {
|
|
|
|
throw new IOException("No more pages");
|
|
|
|
}
|
|
|
|
String nextPage = elem.attr("href");
|
2018-04-19 17:35:36 +02:00
|
|
|
return Http.url(nextPage).get();
|
|
|
|
|
2018-04-14 00:33:31 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
@Override
|
|
|
|
public List<String> getURLsFromPage(Document doc) {
|
|
|
|
List<String> result = new ArrayList<>();
|
2018-04-14 00:52:38 +02:00
|
|
|
Element elem = doc.select("div[id=cc-comicbody] > a > img[id=cc-comic]").first();
|
|
|
|
// The site doesn't return properly encoded urls we replace all spaces ( ) with %20
|
|
|
|
result.add(elem.attr("src").replaceAll(" ", "%20"));
|
2018-04-14 00:33:31 +02:00
|
|
|
|
|
|
|
return result;
|
|
|
|
}
|
|
|
|
|
|
|
|
@Override
|
|
|
|
public void downloadURL(URL url, int index) {
|
|
|
|
addURLToDownload(url, getPrefix(index));
|
|
|
|
}
|
|
|
|
}
|