Images from PDF

[Darrell]

I was playing with pulling images out of PDF files tonight.
Thought I'd share.

--Darrell

import Image, re, zlib, sys

def stripImages(fn):
    buf= open(fn,'rb').read()
    fnS= fn.split(".")[0]
    s =
re.findall("(?s)/XObject\s+/Subtype\s+/Image(.*?)stream\s*\012(.*?)endstream
", buf)
    print len(s)
    for i in s:
        try:
            name = re.findall("(?i)/name\s+/(\w+)",i[0])[0]
            width= re.findall("(?i)/Width\s+(\d+)",i[0])[0]
            height= re.findall("(?i)/Height\s+(\d+)",i[0])[0]
            filter = re.findall("(?i)/filter\s+/(\w+)",i[0])[0]
            colorSpace = re.findall("(?i)/ColorSpace\s+/(\w+)",i[0])[0]
        except IndexError:
            print "Skip:", i[0]
            continue

        print "Found:", name, width, height, filter, colorSpace

        if filter=="FlateDecode":
            im = zlib.decompress(i[1])
            im = Image.fromstring("RGB", (int(width),int(height)), im)
            im.save("%s_%s.jpg"%(fnS,name))
        elif filter == "DCTDecode":
            open("%s_%s.jpg"%(fnS,name),'wb').write(i[1])


stripImages(sys.argv[1])