Added support for the command line program pdftotext from the poppler-utils packages to extract text from PDF documents without doing OCR

2011-04-15 23:59:52 -04:00
parent 73a52293e8
commit eaaaa5b645
5 changed files with 49 additions and 13 deletions
--- a/apps/ocr/exceptions.py
+++ b/apps/ocr/exceptions.py
@@ -1,2 +1,10 @@
 class AlreadyQueued(Exception):
    pass
+
+
+class TesseractError(Exception):
+    pass
+    
+    
+class PdftotextError(Exception):
+    pass