Created
July 11, 2019 23:49
-
-
Save shentonfreude/d1db383556f7f7512bc22b0376f116da to your computer and use it in GitHub Desktop.
Extracts the JPG image from a PDF *scan* and saves to a file; adapted for Python3 from Ned Batchelder's py2 code
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
# Extract jpg's from pdf's. Quick and dirty. | |
# Adapted from https://nedbatchelder.com/blog/200712/extracting_jpgs_from_pdfs.html | |
import sys | |
pdf = open(sys.argv[1], "rb").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("Did not find end of stream!") | |
iend = pdf.find(endmark, iend - 20) | |
if iend < 0: | |
raise Exception("Did not find end of JPG!") | |
istart += startfix | |
iend += endfix | |
print("JPG %d from %d to %d" % (njpg, istart, iend)) | |
jpg = pdf[istart:iend] | |
jpgfile = open("jpg%d.jpg" % njpg, "wb") | |
jpgfile.write(jpg) | |
jpgfile.close() | |
njpg += 1 | |
i = iend |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment