stitch.py

# need pandoc (if want to support txt), img2pdf (if want to support images) and pdfjoin (for pdfs)
# stitch together txt, images and pdf files in a folder to an out pdf
# filenames must begin with their desired sequence number ie 1_foo.pdf 2_beach.png 4_ending_notes.txt
# there can be gaps in the sequence
import os
import glob

import sys

folder = sys.argv[1] if len(sys.argv)>1 else '.'
out_pdf = sys.argv[2] if len(sys.argv)>2 else 'out.pdf'

pdfs_to_stich = []

for ffn in glob.glob(folder+"/*"):
	fn = os.path.basename(ffn)
	# expecting files of the format 12_foo.jpg
	parts = fn.split("_")
	print(parts)
	if len(parts)<2:
		print(ffn+" skipped")
		continue
	try:
		num = int(parts[0])
	except:
		print(ffn+" skipped")
		continue
		
	ffn_without_ext, ext = os.path.splitext(ffn)
	if ext in [".png", ".jpeg", ".jpg"]:
		target_pdf = ffn_without_ext + '.pdf'
		if os.path.exists(target_pdf):
			print(ffn+" already converted")
			continue
		os.system("img2pdf {} -o {}".format(ffn, target_pdf))
		pdfs_to_stich.append((num, target_pdf))
	elif ext == '.pdf':
		pdfs_to_stich.append((num, ffn))
	elif ext == '.txt':
		target_pdf = ffn_without_ext + '.pdf'
		if os.path.exists(target_pdf):
			print(ffn+" already converted")
			continue
		os.system("pandoc {} -o {}".format(ffn, target_pdf))
		pdfs_to_stich.append((num, target_pdf))
		
	
	else:
		print(ffn+" skipped")

pdfs_to_stich.sort(key=lambda x: x[0])

base_folder = os.path.basename(folder)
out = base_folder+'_'+out_pdf # creates a foo_out.pdf under foo/

cmd = "pdfjoin {} --rotateoversize 'false' --outfile {}".format(" ".join([x[1] for x in pdfs_to_stich]), os.path.join(folder, out))
print("Running cmd: {}".format(cmd))
os.system(cmd)