#http://nedbatchelder.com/blog/200712/extracting_jpgs_from_pdfs.html
# jp2 version
import sys,os

filename = sys.argv[1]
filenamebody = filename[0:filename.rindex(".")]
os.mkdir(filenamebody)
pdf = file(filename, "rb").read()

startmark = "\x00\x00\x00\x0c\x6a\x50\x20\x20\x0d\x0a\x87\x0a\x00"
startfix = 0
endmark = "\xff\xd9"
endfix = 2
i = 0

njpg = 0
while True:
	istream = pdf.find("stream", i)
	if istream < 0:
		break
	istart = pdf.find(startmark, istream, istream+20)
	if istart < 0:
		i = istream+20
		continue
	iend = pdf.find("endstream", istart)
	if iend < 0:
		raise Exception("Didn't find end of stream!")
	iend = pdf.find(endmark, iend-20)
	if iend < 0:
		raise Exception("Didn't find end of JP2!")

	istart += startfix
	iend += endfix
	print "JP2 %d from %d to %d" % (njpg, istart, iend)
	jpg = pdf[istart:iend]
	jpgfile = file(filenamebody + "/%03d.jp2" % njpg, "wb")
	jpgfile.write(jpg)
	jpgfile.close()

	njpg += 1
	i = iend
if njpg == 0 :
	os.rmdir(filenamebody)