Created
July 26, 2012 14:49
Revisions
-
jackrusher created this gist
Jul 26, 2012 .There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode charactersOriginal file line number Diff line number Diff line change @@ -0,0 +1,15 @@ (ns pdfbox.core (:import [org.apache.pdfbox.pdmodel PDDocument] [org.apache.pdfbox.util PDFMarkedContentExtractor TextPosition] [java.util ArrayList])) (defn parse-pdf [filename] (let [pages (.getAllPages (.getDocumentCatalog (PDDocument/load filename))) textpool (ArrayList.) extract-text (proxy [PDFMarkedContentExtractor] [] (processTextPosition [text] (.add textpool text)))] (doseq [page pages] (when-let [contents (.getStream (.getContents page))] (.processStream extract-text page (.findResources page) contents))) textpool))