split_pages.py

from PyPDF2 import PdfWriter, PdfReader
import glob
import os.path
INPUT_DIR = "data"
OUTPUT_DIR="data_proc"
files = glob.glob(INPUT_DIR+"/*.pdf")
for f in files:
    basename = os.path.basename(f)
    basename = basename[:-4]
    print (basename)
    current_output_dir = OUTPUT_DIR+"/"+basename
    os.makedirs(current_output_dir, exist_ok=True)
    inputpdf = PdfReader(open(f, "rb"))

    for i in range(len(inputpdf.pages)):
        output = PdfWriter()
        output.add_page(inputpdf.pages[i])
        with open("%s/sesja%03d.pdf" % (current_output_dir,i), "wb") as outputStream:
            output.write(outputStream)