Get text from PDF

core.clj

(ns pdftstr.core
  (:import [com.snowtide.pdf OutputTarget PDFTextStream]))

(defn get-text [filename]
  (with-open [pdfts (PDFTextStream. filename)]
    (let [txt (StringBuilder. 1024)]
      (.pipe pdfts (OutputTarget. txt))
      (str txt))))

(get-text "kalle.pdf")

project.clj

(defproject pdftstr "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 "2.6.2"]]
  :repositories [["snowtide-releases" "http://maven.snowtide.com/releases"]])