Extracts JPEG images from a PDF.

extract-pdf-jpgs.py

"""
Extracts JPGs from a PDF. Inspired by this StackOverflow post:
https://stackoverflow.com/questions/2693820/extract-images-from-pdf-without-resampling-in-python
"""

import sys

with open(sys.argv[1],"rb") as file:
    file.seek(0)
    pdf = file.read()

startmark = b"\xff\xd8"
startfix = 0
endmark = b"\xff\xd9"
endfix = 2
i = 0

njpg = 0
while True:
    istream = pdf.find(b"stream", i)
    if istream < 0:
        break
    istart = pdf.find(startmark, istream, istream + 20)
    if istart < 0:
        i = istream + 20
        continue
    iend = pdf.find(b"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 JPG!")

    istart += startfix
    iend += endfix
    print("JPG %d from %d to %d" % (njpg, istart, iend))
    jpg = pdf[istart:iend]
    with open("jpg%d.jpg" % njpg, "wb") as jpgfile:
        jpgfile.write(jpg)

    njpg += 1
    i = iend