convert pdf files to text for further parsing

gistfile1.clj

(ns pdf-text-extractor.core
  (:import [com.snowtide.pdf OutputTarget PDFTextStream]))

(defn pdf-to-text [file]
  (let [pdfts (new PDFTextStream file)
        output (new StringBuilder 1024)]
    (.pipe pdfts (new OutputTarget output))
    (.close pdfts)
    output))


(defn -main [& args]
  (println (apply str
                  (interleave (map pdf-to-text args) (repeat "\n------------------------------------\n")))))

gistfile2.txt

(defproject pdf-text-extractor "0.1.0-SNAPSHOT"
  :description "FIXME: write description"
  :url "http://example.com/FIXME"
  :license {:name "Eclipse Public License"
            :url "http://www.eclipse.org/legal/epl-v10.html"}
  :dependencies [[org.clojure/clojure "1.5.1"]
                 [com.snowtide/pdftextstream "2.6.4"]]
  :repositories [["snowtide-releases" "http://maven.snowtide.com/releases"]]
  :main pdf-text-extractor.core)