searchanddisplace-ingest/storage/scripts/parse-pdf.py

import pdftotext,json,sys, getopt

def main(argv):
   inputfile = ''
   outputfile = ''
   try:
      opts, args = getopt.getopt(argv,"hi:o:",["ifile=","ofile="])
   except getopt.GetoptError:
      print('parse-pdf.py -i <inputfile> -o <outputfile>')
      sys.exit(2)
   for opt, arg in opts:
      if opt == '-h':
         print('parse-pdf.py -i <inputfile> -o <outputfile>')
         sys.exit()
      elif opt in ("-i", "--ifile"):
         inputfile = arg
      elif opt in ("-o", "--ofile"):
         outputfile = arg

  # Load your PDF
   with open(inputfile, "rb") as file:
        pdf = pdftotext.PDF(file)
   outFile = open(outputfile,'w',encoding='UTF-8')
   outFile.write("\n\n".join(pdf))
   outFile.close()

if __name__ == "__main__":
   main(sys.argv[1:])