extract the text from a webpage using jericho html parser in clojure

extract-text.clj

;; lein dep: [net.htmlparser.jericho/jericho-html "3.1"]
(ns foo.preprocess
  (:import 
   [java.io File BufferedInputStream FileInputStream]
   [net.htmlparser.jericho Source TextExtractor]))

  (def filename "data/raw-html/cosmetiquemedspa.com/index.html")
  (def file (java.io.File. filename))
  (def source (Source. (BufferedInputStream. (FileInputStream. file))))
  (def tex (TextExtractor. source))
  (.toString tex)