diff --git a/warcbase-core/src/main/scala/org/warcbase/spark/matchbox/ExtractLinks.scala b/warcbase-core/src/main/scala/org/warcbase/spark/matchbox/ExtractLinks.scala
index 43e0aeb..a0313a4 100644
--- a/warcbase-core/src/main/scala/org/warcbase/spark/matchbox/ExtractLinks.scala
+++ b/warcbase-core/src/main/scala/org/warcbase/spark/matchbox/ExtractLinks.scala
@@ -1,59 +1,62 @@
 /*
  * Warcbase: an open-source platform for managing web archives
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
  * You may obtain a copy of the License at
  *
  *     http://www.apache.org/licenses/LICENSE-2.0
  *
  * Unless required by applicable law or agreed to in writing, software
  * distributed under the License is distributed on an "AS IS" BASIS,
  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
 
 package org.warcbase.spark.matchbox
 
 import java.io.IOException
 
 import org.jsoup.Jsoup
 import org.jsoup.select.Elements
 
 import scala.collection.mutable
 
 /**
   * UDF for extracting links from a webpage given the HTML content (using Jsoup).
-  *
   */
 object ExtractLinks {
   /**
     * @param src the src link.
     * @param html the content from which links are to be extracted.
     * @param base an optional base URI.
     *
     * Returns a sequence of (source, target, anchortext)
     */
   def apply(src: String, html: String, base: String = ""): Seq[(String, String, String)] = {
-    if (html.isEmpty) return Nil
     try {
       val output = mutable.MutableList[(String, String, String)]()
+
+      // Basic input checking, return empty list if we fail.
+      if (src == null) return output
+      if (html.isEmpty) return output
+
       val doc = Jsoup.parse(html)
       val links: Elements = doc.select("a[href]")
       val it = links.iterator()
       while (it.hasNext) {
         val link = it.next()
         if (base.nonEmpty) link.setBaseUri(base)
         val target = link.attr("abs:href")
         if (target.nonEmpty) {
           output += ((src, target, link.text))
         }
       }
       output
     } catch {
       case e: Exception =>
         throw new IOException("Caught exception processing input ", e);
     }
   }
 }
diff --git a/warcbase-core/src/main/scala/org/warcbase/spark/matchbox/StringUtils.scala b/warcbase-core/src/main/scala/org/warcbase/spark/matchbox/StringUtils.scala
index 5904dc6..710e031 100644
--- a/warcbase-core/src/main/scala/org/warcbase/spark/matchbox/StringUtils.scala
+++ b/warcbase-core/src/main/scala/org/warcbase/spark/matchbox/StringUtils.scala
@@ -1,27 +1,28 @@
 /*
  * Warcbase: an open-source platform for managing web archives
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
  * You may obtain a copy of the License at
  *
  *     http://www.apache.org/licenses/LICENSE-2.0
  *
  * Unless required by applicable law or agreed to in writing, software
  * distributed under the License is distributed on an "AS IS" BASIS,
  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
 
 package org.warcbase.spark.matchbox
 
 object StringUtils {
 
   implicit class WWWLink(s: String) {
     def removePrefixWWW(): String = {
+      if (s == null) return null
       s.replaceAll("^\\s*www\\.", "")
     }
   }
 
 }