Last active
October 6, 2023 10:48
-
-
Save tecoholic/e44f727f77c74e50f4d70ff10539350b to your computer and use it in GitHub Desktop.
Python script to replace an image file in the PDF
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
import sys | |
import os | |
from PIL import Image | |
# Include the \n to ensure extact match and avoid partials from 111, 211... | |
OBJECT_ID = "\n11 0 obj" | |
def replace_image(filepath, new_image): | |
f = open(filepath, "r") | |
contents = f.read() | |
f.close() | |
image = Image.open(new_image) | |
width, height = image.size | |
length = os.path.getsize(new_image) | |
start = contents.find(OBJECT_ID) | |
stream = contents.find("stream", start) | |
image_beginning = stream + 7 | |
# Process the metadata and update with new image's details | |
meta = contents[start: image_beginning] | |
meta = meta.split("\n") | |
new_meta = [] | |
for item in meta: | |
if "/Width" in item: | |
new_meta.append("/Width {0}".format(width)) | |
elif "/Height" in item: | |
new_meta.append("/Height {0}".format(height)) | |
elif "/Length" in item: | |
new_meta.append("/Length {0}".format(length)) | |
else: | |
new_meta.append(item) | |
new_meta = "\n".join(new_meta) | |
# Find the end location | |
image_end = contents.find("endstream", stream) - 1 | |
# read the image | |
f = open(new_image, "r") | |
new_image_data = f.read() | |
f.close() | |
# recreate the PDF file with the new_sign | |
with open(filepath, "wb") as f: | |
f.write(contents[:start]) | |
f.write("\n") | |
f.write(new_meta) | |
f.write(new_image_data) | |
f.write(contents[image_end:]) | |
if __name__ == "__main__": | |
if len(sys.argv) == 3: | |
replace_image(sys.argv[1], sys.argv[2]) | |
else: | |
print("Usage: python process.py <pdfile> <new_image>") |
You will have to inspect the PDF in a text editor
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
How to find that object id