Extract the text from a webpage using jericho html parser in clojure. Run with 'lein one-off extract-text.clj filename.html'

extract-text.clj

#_(defdeps [[net.htmlparser.jericho/jericho-html "3.1"]])
 
(ns foo.preprocess
  (:import [java.io File BufferedInputStream FileInputStream]
           [net.htmlparser.jericho Source TextExtractor HTMLElementName]))

(defn my-text-extractor [source]
  (proxy [TextExtractor] [source]
    (excludeElement [tag]
      (= (.getName tag) HTMLElementName/PRE))))

(defn -main [fname]
  (let [file (java.io.File. fname)
        source (Source. (BufferedInputStream. (FileInputStream. file)))
        tex (my-text-extractor source)]
    (println (str tex))))

(apply -main *command-line-args*)