Merge pull request #462 from cyian-1756/sinfest

Added Sinfest ripper
This commit is contained in:
cyian-1756 2018-03-12 11:41:04 -04:00 committed by GitHub
commit 6968a52c41
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 93 additions and 0 deletions

View File

@ -0,0 +1,80 @@
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 SinfestRipper extends AbstractHTMLRipper {
public SinfestRipper(URL url) throws IOException {
super(url);
}
@Override
public String getHost() {
return "sinfest";
}
@Override
public String getDomain() {
return "sinfest.net";
}
@Override
public String getGID(URL url) throws MalformedURLException {
Pattern p = Pattern.compile("https?://sinfest.net/view.php\\?date=([0-9-]*)/?");
Matcher m = p.matcher(url.toExternalForm());
if (m.matches()) {
return m.group(1);
}
throw new MalformedURLException("Expected sinfest URL format: " +
"sinfest.net/view.php?date=XXXX-XX-XX/ - 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 {
Element elem = doc.select("td.style5 > a > img").last();
logger.info(elem.parent().attr("href"));
if (elem == null || elem.parent().attr("href").equals("view.php?date=")) {
throw new IOException("No more pages");
}
String nextPage = elem.parent().attr("href");
// Some times this returns a empty string
// This for stops that
if (nextPage == "") {
return null;
}
else {
return Http.url("http://sinfest.net/" + nextPage).get();
}
}
@Override
public List<String> getURLsFromPage(Document doc) {
List<String> result = new ArrayList<>();
Element elem = doc.select("tbody > tr > td > img").last();
result.add("http://sinfest.net/" + elem.attr("src"));
return result;
}
@Override
public void downloadURL(URL url, int index) {
addURLToDownload(url, getPrefix(index));
}
}

View File

@ -0,0 +1,13 @@
package com.rarchives.ripme.tst.ripper.rippers;
import java.io.IOException;
import java.net.URL;
import com.rarchives.ripme.ripper.rippers.SinfestRipper;
public class SinfestRipperTest extends RippersTest {
public void testRip() throws IOException {
SinfestRipper ripper = new SinfestRipper(new URL("http://sinfest.net/view.php?date=2000-01-17"));
testRipper(ripper);
}
}