diff --git a/src/main/java/com/rarchives/ripme/ripper/rippers/BlackbrickroadofozRipper.java b/src/main/java/com/rarchives/ripme/ripper/rippers/BlackbrickroadofozRipper.java new file mode 100644 index 00000000..76340cf9 --- /dev/null +++ b/src/main/java/com/rarchives/ripme/ripper/rippers/BlackbrickroadofozRipper.java @@ -0,0 +1,82 @@ +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 BlackbrickroadofozRipper extends AbstractHTMLRipper { + + public BlackbrickroadofozRipper(URL url) throws IOException { + super(url); + } + + @Override + public String getHost() { + return "blackbrickroadofoz"; + } + + @Override + public String getDomain() { + return "blackbrickroadofoz.com"; + } + + @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 { + sleep(1000); + Element elem = doc.select("div[id=topnav] > nav.cc-nav > a.cc-next").first(); + if (elem == null) { + throw new IOException("No more pages"); + } + String nextPage = elem.attr("href"); + // Some times this returns a empty string + // This for stops that + if (nextPage == "") { + throw new IOException("No more pages"); + } + else { + return Http.url(nextPage).get(); + } + } + + @Override + public List getURLsFromPage(Document doc) { + List result = new ArrayList<>(); + 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")); + + return result; + } + + @Override + public void downloadURL(URL url, int index) { + addURLToDownload(url, getPrefix(index)); + } +} diff --git a/src/test/java/com/rarchives/ripme/tst/ripper/rippers/BlackbrickroadofozRipperTest.java b/src/test/java/com/rarchives/ripme/tst/ripper/rippers/BlackbrickroadofozRipperTest.java new file mode 100644 index 00000000..a3c7d862 --- /dev/null +++ b/src/test/java/com/rarchives/ripme/tst/ripper/rippers/BlackbrickroadofozRipperTest.java @@ -0,0 +1,13 @@ +package com.rarchives.ripme.tst.ripper.rippers; + +import com.rarchives.ripme.ripper.rippers.BlackbrickroadofozRipper; + +import java.io.IOException; +import java.net.URL; + +public class BlackbrickroadofozRipperTest extends RippersTest { + public void testRip() throws IOException { + BlackbrickroadofozRipper ripper = new BlackbrickroadofozRipper(new URL("http://www.blackbrickroadofoz.com/comic/beginning")); + testRipper(ripper); + } +}