maven.xml

<repository>
  <id>boilerpipe-m2-repo</id>
  <url>https://boilerpipe.googlecode.com/svn/repo/</url>
</repository>

<dependency>
  <groupId>de.l3s.boilerpipe</groupId>
  <artifactId>boilerpipe</artifactId>
  <version>1.2.0</version>
</dependency>

<dependency>
  <groupId>net.sourceforge.nekohtml</groupId>
  <artifactId>nekohtml</artifactId>
  <version>1.9.15</version>
</dependency>

<dependency>
  <groupId>xerces</groupId>
  <artifactId>xercesImpl</artifactId>
  <version>2.9.1</version>
</dependency>

project.clj

;; All this jazz is necessary because Boilerpipe developer likes optional dependencies
;; but never documents them. 
[net.sourceforge.nekohtml/nekohtml "1.9.15"]
[xerces/xercesImpl                 "2.9.1"]
[de.l3s.boilerpipe/boilerpipe      "1.2.0"]