From b1ed146c3b964bb1d66a82fd8d27efbd95308403 Mon Sep 17 00:00:00 2001 From: cyian-1756 Date: Mon, 4 Sep 2017 22:03:27 -0400 Subject: [PATCH 1/2] Added cfake.com ripper --- .../ripme/ripper/rippers/CfakeRipper.java | 95 +++++++++++++++++++ 1 file changed, 95 insertions(+) create mode 100644 src/main/java/com/rarchives/ripme/ripper/rippers/CfakeRipper.java diff --git a/src/main/java/com/rarchives/ripme/ripper/rippers/CfakeRipper.java b/src/main/java/com/rarchives/ripme/ripper/rippers/CfakeRipper.java new file mode 100644 index 00000000..03e8a636 --- /dev/null +++ b/src/main/java/com/rarchives/ripme/ripper/rippers/CfakeRipper.java @@ -0,0 +1,95 @@ +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 CfakeRipper extends AbstractHTMLRipper { + + public CfakeRipper(URL url) throws IOException { + super(url); + } + + @Override + public String getHost() { + return "cfake"; + } + + @Override + public String getDomain() { + return "cfake.com"; + } + + @Override + public String getGID(URL url) throws MalformedURLException { + Pattern p = Pattern.compile("https?://cfake\\.com/picture/([a-zA-Z1-9_-]*)/\\d+/?$"); + Matcher m = p.matcher(url.toExternalForm()); + if (m.matches()) { + return m.group(1); + } + throw new MalformedURLException("Expected cfake URL format: " + + "cfake.com/picture/MODEL/ID - 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 { + // Find next page + String nextUrl = ""; + // We use comic-nav-next to the find the next page + Element elem = doc.select("td > div.next > a").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 == "") { + return null; + } + else { + return Http.url("http://cfake.com" + nextPage).get(); + } + } + + @Override + public List getURLsFromPage(Document doc) { + List result = new ArrayList(); + for (Element el : doc.select("table.display > tbody > tr > td > table > tbody > tr > td > a")) { + if (el.attr("href").contains("upload")) { + return result; + } else { + String imageSource = el.select("img").attr("src"); + // We remove the .md from images so we download the full size image + // not the thumbnail ones + imageSource = imageSource.replace("thumbs", "photos"); + result.add("http://cfake.com" + imageSource); + } + } + return result; + } + + @Override + public void downloadURL(URL url, int index) { + addURLToDownload(url, getPrefix(index)); + } + + + } From f643172cef7020ee5681e459c9e7a11c9bfb2d1a Mon Sep 17 00:00:00 2001 From: cyian-1756 Date: Tue, 5 Sep 2017 14:37:48 -0400 Subject: [PATCH 2/2] Removed extra newlines --- .../java/com/rarchives/ripme/ripper/rippers/CfakeRipper.java | 2 -- 1 file changed, 2 deletions(-) diff --git a/src/main/java/com/rarchives/ripme/ripper/rippers/CfakeRipper.java b/src/main/java/com/rarchives/ripme/ripper/rippers/CfakeRipper.java index 03e8a636..f50956c6 100644 --- a/src/main/java/com/rarchives/ripme/ripper/rippers/CfakeRipper.java +++ b/src/main/java/com/rarchives/ripme/ripper/rippers/CfakeRipper.java @@ -90,6 +90,4 @@ public class CfakeRipper extends AbstractHTMLRipper { public void downloadURL(URL url, int index) { addURLToDownload(url, getPrefix(index)); } - - }