Created
January 6, 2019 18:26
-
-
Save ionox0/aac0068eb990b919e017a1edb673e8c6 to your computer and use it in GitHub Desktop.
Simple python script to find and replace text within a PDF
This file contains hidden or 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 re | |
import sys | |
import zlib | |
# Module to find and replace text in PDF files | |
# | |
# Usage: | |
# python pdf_replace.py <input_filename> <text_to_find> <text_to_replace> <output_filename> | |
# | |
# @author Ionox0 | |
input_filename = sys.argv[1] | |
text_to_find = sys.argv[2] | |
text_to_replace = sys.argv[3] | |
output_filename sys.argv[4] | |
pdf = open(input_filename, "rb").read() | |
# Create a copy of the PDF content to make edits to | |
pdf_copy = pdf[0:] | |
# Search for stream objects with text to replace | |
stream = re.compile(r'.*?FlateDecode.*?stream(.*?)endstream', re.S) | |
for s in stream.findall(pdf): | |
s = s.strip('\r\n') | |
try: | |
text = zlib.decompress(s) | |
if text_to_find in text: | |
print('Found match:') | |
print(text) | |
text = text.replace(text_to_find, text_to_replace) | |
pdf_copy = pdf_copy.replace(s, zlib.compress(text)) | |
except: | |
pass | |
with open(output_filename, 'wb') as out: | |
out.write(pdf_copy) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment