From 3ebb7d1874e61f6f06c9e670b9106f07e8f265ac Mon Sep 17 00:00:00 2001 From: cyian-1756 Date: Sun, 17 Jun 2018 15:55:57 -0400 Subject: [PATCH] Started work on Picstatio ripper --- .../ripme/ripper/rippers/PicstatioRipper.java | 82 +++++++++++++++++++ 1 file changed, 82 insertions(+) create mode 100644 src/main/java/com/rarchives/ripme/ripper/rippers/PicstatioRipper.java diff --git a/src/main/java/com/rarchives/ripme/ripper/rippers/PicstatioRipper.java b/src/main/java/com/rarchives/ripme/ripper/rippers/PicstatioRipper.java new file mode 100644 index 00000000..29c71a08 --- /dev/null +++ b/src/main/java/com/rarchives/ripme/ripper/rippers/PicstatioRipper.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 PicstatioRipper extends AbstractHTMLRipper { + + public PicstatioRipper(URL url) throws IOException { + super(url); + } + + private String getFullSizedImageFromURL(String fileName) { + try { + return Http.url("https://www.picstatio.com/wallpaper/" + fileName + "/download").get().select("p.text-center > a").attr("href"); + } catch (IOException e) { + e.printStackTrace(); + return null; + } + } + + @Override + public String getHost() { + return "picstatio"; + } + + @Override + public String getDomain() { + return "picstatio.com"; + } + + @Override + public String getGID(URL url) throws MalformedURLException { + Pattern p = Pattern.compile("https?://www.picstatio.com/([a-zA-Z1-9_-]*)/?$"); + Matcher m = p.matcher(url.toExternalForm()); + if (m.matches()) { + return m.group(1); + } + throw new MalformedURLException("Expected picstatio URL format: " + + "www.picstatio.com//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 { + if (doc.select("a.next_page") != null) { + return Http.url("https://www.picstatio.com" + doc.select("a.next_page").attr("href")).get(); + } + throw new IOException("No more pages"); + } + + @Override + public List getURLsFromPage(Document doc) { + List result = new ArrayList<>(); + for (Element e : doc.select("img.img")) { + String imageName = e.parent().attr("href"); + LOGGER.info(getFullSizedImageFromURL(imageName.split("/")[2])); + result.add(getFullSizedImageFromURL(imageName.split("/")[2])); + } + return result; + } + + @Override + public void downloadURL(URL url, int index) { + addURLToDownload(url, getPrefix(index)); + } +} \ No newline at end of file