macOS-pdf2txt.py

#!/usr/bin/python
# coding: utf-8

########## Install dependencies
#sudo -H /usr/bin/pip3 install pyobjc-core pyobjc-framework-Cocoa pyobjc-framework-Quartz

########## Usage example
#/usr/bin/python3 ./macOS-pdf2txt.py ./input.pdf

import os, sys
from Quartz import PDFDocument
from CoreFoundation import (NSURL, NSString)
NSUTF8StringEncoding = 4

def pdf2txt():
    for filename in sys.argv[1:]:
        #inputfile =filename.decode('utf-8') #python2
        inputfile = filename #pyhton3
        shortName = os.path.splitext(filename)[0]
        pdfURL = NSURL.fileURLWithPath_(inputfile)
        pdfDoc = PDFDocument.alloc().initWithURL_(pdfURL)
        if pdfDoc :
            pdfString = NSString.stringWithString_(pdfDoc.string())
            if len(pdfString) < 4096:
                outputfile = str(shortName) + str("-ERR.txt")
            else:
                outputfile = str(shortName) + str("-OK.txt")
            print("Writing " + str(outputfile))
            pdfString.writeToFile_atomically_encoding_error_(outputfile, True, NSUTF8StringEncoding, None)

if __name__ == "__main__":
   pdf2txt()