Added ripper for Erofus.com

src/main/java/com/rarchives/ripme/ripper/rippers/ErofusRipper.java

@@ -0,0 +1,134 @@
+package com.rarchives.ripme.ripper.rippers;
+
+import com.rarchives.ripme.ripper.AbstractHTMLRipper;
+import com.rarchives.ripme.ui.RipStatusMessage;
+import com.rarchives.ripme.utils.Http;
+import org.json.JSONObject;
+import org.jsoup.Connection;
+import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
+import org.jsoup.select.Elements;
+
+import java.io.IOException;
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.util.ArrayList;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+public class ErofusRipper extends AbstractHTMLRipper {
+
+    private Document albumDoc = null;
+    private Map<String,String> cookies = new HashMap<>();
+    // TODO put up a wiki page on using maps to store titles
+    // the map for storing the title of each album when downloading sub albums
+    private Map<URL,String> urlTitles = new HashMap<>();
+
+    private Boolean rippingSubalbums = false;
+
+    public ErofusRipper(URL url) throws IOException {
+        super(url);
+    }
+
+    @Override
+    public boolean hasASAPRipping() {
+        return true;
+    }
+
+    @Override
+    public String getHost() {
+        return "erofus";
+    }
+
+    @Override
+    public String getDomain() {
+        return "erofus.com";
+    }
+
+    @Override
+    public String getGID(URL url) throws MalformedURLException {
+        Pattern p = Pattern.compile("^https://www.erofus.com/comics/([a-zA-Z0-9\\-_]+).*$");
+        Matcher m = p.matcher(url.toExternalForm());
+        if (!m.matches()) {
+            throw new MalformedURLException("Expected URL format: http://www.8muses.com/index/category/albumname, got: " + url);
+        }
+        return m.group(m.groupCount());
+    }
+
+    @Override
+    public Document getFirstPage() throws IOException {
+        if (albumDoc == null) {
+            Connection.Response resp = Http.url(url).response();
+            cookies.putAll(resp.cookies());
+            albumDoc = resp.parse();
+        }
+        return albumDoc;
+    }
+
+    @Override
+    public List<String> getURLsFromPage(Document page) {
+        LOGGER.info(page);
+        List<String> imageURLs = new ArrayList<>();
+        int x = 1;
+        if (pageContainsImages(page)) {
+            LOGGER.info("Page contains images");
+            imageURLs.addAll(ripAlbum(page));
+        } else {
+            // This contains the thumbnails of all images on the page
+            Elements pageImages = page.select("a.a-click");
+            for (Element pageLink : pageImages) {
+                if (super.isStopped()) break;
+                if (pageLink.attr("href").contains("comics")) {
+                    String subUrl = "https://erofus.com" + pageLink.attr("href");
+                    try {
+                        LOGGER.info("Retrieving " + subUrl);
+                        sendUpdate(RipStatusMessage.STATUS.LOADING_RESOURCE, subUrl);
+                        Document subPage = Http.url(subUrl).get();
+                        List<String> subalbumImages = getURLsFromPage(subPage);
+                    } catch (IOException e) {
+                        LOGGER.warn("Error while loading subalbum " + subUrl, e);
+                    }
+                }
+                if (isThisATest()) break;
+            }
+        }
+
+
+        return imageURLs;
+    }
+
+    public List<String> ripAlbum(Document page) {
+        int x = 1;
+        List<String> imageURLs = new ArrayList<>();
+        Elements thumbs = page.select("a.a-click > div.thumbnail > img");
+        for (Element thumb : thumbs) {
+            String image = "https://www.erofus.com" + thumb.attr("src").replaceAll("thumb", "medium");
+            imageURLs.add(image);
+            try {
+                addURLToDownload(new URL(image), getPrefix(x));
+            } catch (MalformedURLException e) {
+                LOGGER.info(e.getMessage());
+            }
+            x++;
+        }
+        return imageURLs;
+    }
+
+    private boolean pageContainsImages(Document page) {
+        Elements pageImages = page.select("a.a-click");
+        for (Element pageLink : pageImages) {
+            if (pageLink.attr("href").contains("/pic/")) {
+                return true;
+            }
+        }
+        return false;
+    }
+
+    @Override
+    public void downloadURL(URL url, int index) {
+        addURLToDownload(url, getPrefix(index), "", this.url.toExternalForm(), cookies);
+    }
+}