diff --git a/ocr_pyflow b/ocr_pyflow
index 3bb6bde..4ad3fc8 100755
--- a/ocr_pyflow
+++ b/ocr_pyflow
@@ -249,6 +249,20 @@ class OCRWorkflow(WorkflowRunner):
                 pdf_merge_jobs.append(self.addTask(label="pdf_merge_job_-_%i" % (pdf_merge_job_number), command=cmd, dependencies=tesseract_jobs, nCores=1, memMb=4096))
 
 
+        ###
+        # Task "pdf_to_txt_jobs":
+        # Dependencies: pdf_merge_jobs
+        ###
+        pdf_to_txt_jobs = []
+        pdf_to_txt_job_number = 0
+        if self.pdf:
+            for job in self.pdfImageJobs["images"] + self.pdfImageJobs["pdf"]:
+                pdf_to_txt_job_number += 1
+                cmd = "pdftotext -raw %s" % (
+                    os.path.join(job["output_dir"], os.path.basename(job["path"].rsplit(".", 1)[0] + ".pdf")))
+                pdf_merge_jobs.append(self.addTask(label="pdf_to_txt_job_-_%i" % (pdf_to_txt_job_number), command=cmd, dependencies=pdf_merge_jobs, nCores=1, memMb=4096))
+
+
         ###
         # Task "move_hocr_job": move hocr files from <output_dir>/tmp/tesseract to <output_dir>/hocr_files
         # Dependencies: tesseract_jobs
@@ -340,4 +354,4 @@ def main():
 
 
 if __name__ == "__main__":
-    main()
\ No newline at end of file
+    main()