Merge pull request #588 from cyian-1756/ehentaiTagSkip

Can now blacklist nhentai tags

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

@@ -2,6 +2,7 @@ package com.rarchives.ripme.ripper.rippers;
 
 import com.rarchives.ripme.ripper.AbstractHTMLRipper;
 import com.rarchives.ripme.ripper.DownloadThreadPool;
+import com.rarchives.ripme.ui.RipStatusMessage;
 import com.rarchives.ripme.utils.Http;
 import com.rarchives.ripme.utils.Utils;
 import org.jsoup.nodes.Document;
@@ -64,6 +65,39 @@ public class NhentaiRipper extends AbstractHTMLRipper {
         return "nhentai" + title;
     }
 
+    private List<String> getTags(Document doc) {
+        List<String> tags = new ArrayList<>();
+        for (Element tag : doc.select("a.tag")) {
+            tags.add(tag.attr("href").replaceAll("/tag/", "").replaceAll("/", ""));
+        }
+        return tags;
+    }
+
+    /**
+     * Checks for blacklisted tags on page. If it finds one it returns it, if not it return null
+     *
+     * @param doc
+     * @return String
+     */
+    public String checkTags(Document doc, String[] blackListedTags) {
+        // If the user hasn't blacklisted any tags we return false;
+        if (blackListedTags == null) {
+            return null;
+        }
+        logger.info("Blacklisted tags " + blackListedTags[0]);
+        List<String> tagsOnPage = getTags(doc);
+        for (String tag : blackListedTags) {
+            for (String pageTag : tagsOnPage) {
+                // We replace all dashes in the tag with spaces because the tags we get from the site are separated using
+                // dashes
+                if (tag.trim().toLowerCase().equals(pageTag.replaceAll("-", " ").toLowerCase())) {
+                    return tag;
+                }
+            }
+        }
+        return null;
+    }
+
     @Override
     public String getGID(URL url) throws MalformedURLException {
         // Ex: https://nhentai.net/g/159174/
@@ -82,6 +116,13 @@ public class NhentaiRipper extends AbstractHTMLRipper {
         if (firstPage == null) {
             firstPage = Http.url(url).get();
         }
+
+        String blacklistedTag = checkTags(firstPage, Utils.getConfigStringArray("nhentai.blacklist.tags"));
+        if (blacklistedTag != null) {
+            sendUpdate(RipStatusMessage.STATUS.DOWNLOAD_WARN, "Skipping " + url.toExternalForm() + " as it " +
+                    "contains the blacklisted tag \"" + blacklistedTag + "\"");
+            return null;
+        }
         return firstPage;
     }
 

src/main/java/com/rarchives/ripme/utils/Utils.java

@@ -92,6 +92,16 @@ public class Utils {
     public static String getConfigString(String key, String defaultValue) {
         return config.getString(key, defaultValue);
     }
+
+    public static String[] getConfigStringArray(String key) {
+        String[] s = config.getStringArray(key);
+        if (s.length == 0) {
+            return null;
+        } else {
+            return s;
+        }
+    }
+
     public static int getConfigInteger(String key, int defaultValue) {
         return config.getInt(key, defaultValue);
     }

src/test/java/com/rarchives/ripme/tst/ripper/rippers/NhentaiRipperTest.java

@@ -0,0 +1,33 @@
+package com.rarchives.ripme.tst.ripper.rippers;
+
+import java.io.IOException;
+import java.net.URL;
+
+import com.rarchives.ripme.ripper.rippers.NhentaiRipper;
+
+public class NhentaiRipperTest extends RippersTest {
+    public void testRip() throws IOException {
+        NhentaiRipper ripper = new NhentaiRipper(new URL("https://nhentai.net/g/233295/"));
+        testRipper(ripper);
+    }
+
+    public void testGetGID()  throws IOException {
+        NhentaiRipper ripper = new NhentaiRipper(new URL("https://nhentai.net/g/233295/"));
+        assertEquals("233295", ripper.getGID(new URL("https://nhentai.net/g/233295/")));
+    }
+
+    // Test the tag black listing
+    public void testTagBlackList()  throws IOException {
+        URL url = new URL("https://nhentai.net/g/233295/");
+        NhentaiRipper ripper = new NhentaiRipper(url);
+        // Test multiple blacklisted tags
+        String[] tags = {"test", "one", "blowjob"};
+        String blacklistedTag = ripper.checkTags(ripper.getFirstPage(), tags);
+        assertEquals("blowjob", blacklistedTag);
+
+        // test tags with spaces in them
+        String[] tags2 = {"test", "one", "sole female"};
+        blacklistedTag = ripper.checkTags(ripper.getFirstPage(), tags2);
+        assertEquals("sole female", blacklistedTag);
+    }
+}