From a05a9689f61b222c5c47cc958c444221da31994b Mon Sep 17 00:00:00 2001 From: cyian-1756 Date: Tue, 31 Oct 2017 21:39:07 -0400 Subject: [PATCH 1/2] Added Porncomix.info ripper --- .../ripme/ripper/rippers/PorncomixRipper.java | 69 +++++++++++++++++++ 1 file changed, 69 insertions(+) create mode 100644 src/main/java/com/rarchives/ripme/ripper/rippers/PorncomixRipper.java diff --git a/src/main/java/com/rarchives/ripme/ripper/rippers/PorncomixRipper.java b/src/main/java/com/rarchives/ripme/ripper/rippers/PorncomixRipper.java new file mode 100644 index 00000000..6ed3e4f9 --- /dev/null +++ b/src/main/java/com/rarchives/ripme/ripper/rippers/PorncomixRipper.java @@ -0,0 +1,69 @@ +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.Arrays; +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 org.jsoup.select.Elements; + +import com.rarchives.ripme.ripper.AbstractHTMLRipper; +import com.rarchives.ripme.utils.Http; + +public class PorncomixRipper extends AbstractHTMLRipper { + + public PorncomixRipper(URL url) throws IOException { + super(url); + } + + @Override + public String getHost() { + return "porncomix"; + } + + @Override + public String getDomain() { + return "porncomix.info"; + } + + @Override + public String getGID(URL url) throws MalformedURLException { + Pattern p = Pattern.compile("https?://www.porncomix.info/([a-zA-Z1-9_-]*)/?$"); + Matcher m = p.matcher(url.toExternalForm()); + if (m.matches()) { + return m.group(1); + } + throw new MalformedURLException("Expected proncomix URL format: " + + "porncomix.info/comic - got " + url + " instead"); + } + + @Override + public Document getFirstPage() throws IOException { + // "url" is an instance field of the superclass + return Http.url(url).get(); + } + + @Override + public List getURLsFromPage(Document doc) { + List result = new ArrayList<>(); + for (Element el : doc.select("div.single-post > div.gallery > dl > dt > a > img")) { + String imageSource = el.attr("data-lazy-src"); + // We remove the .md from images so we download the full size image + // not the thumbnail ones + imageSource = imageSource.replaceAll("-\\d\\d\\dx\\d\\d\\d", ""); + result.add(imageSource); + } + return result; + } + + @Override + public void downloadURL(URL url, int index) { + addURLToDownload(url, getPrefix(index)); + } + } From fec24fc6979a5b1da29b8096f5d94e8f0ecde8a5 Mon Sep 17 00:00:00 2001 From: cyian-1756 Date: Tue, 31 Oct 2017 21:48:05 -0400 Subject: [PATCH 2/2] fixed porncomix.info ripper --- .../com/rarchives/ripme/ripper/rippers/PorncomixRipper.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/main/java/com/rarchives/ripme/ripper/rippers/PorncomixRipper.java b/src/main/java/com/rarchives/ripme/ripper/rippers/PorncomixRipper.java index 6ed3e4f9..cc01ab20 100644 --- a/src/main/java/com/rarchives/ripme/ripper/rippers/PorncomixRipper.java +++ b/src/main/java/com/rarchives/ripme/ripper/rippers/PorncomixRipper.java @@ -34,7 +34,7 @@ public class PorncomixRipper extends AbstractHTMLRipper { @Override public String getGID(URL url) throws MalformedURLException { - Pattern p = Pattern.compile("https?://www.porncomix.info/([a-zA-Z1-9_-]*)/?$"); + Pattern p = Pattern.compile("https?://www.porncomix.info/([a-zA-Z0-9_\\-]*)/?$"); Matcher m = p.matcher(url.toExternalForm()); if (m.matches()) { return m.group(1);