Last active
June 2, 2019 15:37
-
-
Save bhanuraja/278c884fde7caafd260d9850ae98973c to your computer and use it in GitHub Desktop.
Python script for merging PDF files using PyPDF2
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 os | |
import re | |
from PyPDF2 import PdfFileMerger | |
loc = r"C:\Users\Bhanuraja\Downloads\Compressed\java" | |
merger = PdfFileMerger() | |
# get the list of all files in the specified directory | |
a = os.listdir(loc) | |
b = [] | |
for a in os.listdir(loc): | |
if a.endswith('.pdf')&(a!='output.pdf'): | |
print(loc+"\\"+a)#creating absolute path for pdf file | |
b.append(a)# store only pdf files names on the current directory | |
#function for getting numbers from pdf files | |
def get_int(text):#return the integer in the file name | |
return int(re.search("\d+",str(text)).group()) | |
b = sorted(b,key=get_int)# sorting based on the numbers in file names | |
for c in b:# now merging all the pdf files using merger | |
merger.append(loc+"\\"+c) | |
file = open(loc+"\\"+"output.pdf","w")#for creating file you can also manually create empty pdf file | |
file.close() | |
merger.write(loc+"\\"+"output.pdf") | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment