#! /usr/bin/env python
#
# A dubious script that extracts all the visible text portion from a
# PDF file and spits it onto stdout
#
from re import findall, sub
from sys import stdout, argv
from pdffile import PDFFile

for filename in argv[1:]:
   f = PDFFile()
   f.load_file(filename)
   print f.Security
   count = f.Root['Pages']['Count'].value()
   for page in range(0, count):
	kid = f.Root['Pages']['Kids'][page]
	data = kid['Contents'].value()._stream.read(65536)
	for g in findall(r'\(((\\.|[^)])*)\)', data):
	    stdout.write(sub(r'\\(.)', r'\1', g[0]))
	stdout.write('\n')