Converting ZIP archive to PDF document

zip2pdf.py

#!/usr/bin/env python
#-*- coding: utf-8 -*-

import os
import StringIO
import zipfile
import sys
from reportlab.pdfgen import canvas
from reportlab.lib.utils import ImageReader
from pyPdf import pdf
from PIL import Image

def getPageFromImage(filename):
    packet = StringIO.StringIO()
    im = ImageReader(filename)
    w, h = im.getSize()
    can = canvas.Canvas(packet, (w, h))
    can.drawImage(im, 0, 0, width=w, height=h)
    can.save()
    packet.seek(0)
    ip = pdf.PdfFileReader(packet)
    return ip.getPage(0)


if(len(sys.argv) != 2):
    print '1 argument required but %d given' % (len(sys.argv) - 1)
    exit(0)

print 'Processing File:' + sys.argv[1]

f = zipfile.ZipFile(sys.argv[1],"r")
out = pdf.PdfFileWriter()

l = f.namelist()
l.sort()

for name in l:
    utf8name=name.decode('utf-8')
    if not (utf8name.lower().endswith(".jpg")
            or utf8name.lower().endswith(".png")
            or utf8name.lower().endswith(".bmp")
            ):
        continue;
    print "Processing " + utf8name
    pathname = os.path.basename(utf8name)
    data = f.read(name)
    if not os.path.exists(pathname):
        fo = open(pathname, "w")
        fo.write(data)
        fo.close()
        out.addPage(getPageFromImage(pathname))
        os.remove(pathname)

out.write(open(sys.argv[1] + ".pdf", 'wb'))
f.close()