pdf.py

from pathlib import Path

import textract
import numpy as np
import re


def main(_file):
    text = textract.process(_file, method="pdfminer")
    with open("%s.csv" % Path(_file).name[: -len(Path(_file).suffix)], "w+") as _file:
        # find orders and DNIs
        coords = re.compile(r"\d?\.?\d+\.+\d+\,\d{2}")                                                                                                                                                               
        results = re.findall(coords, text.decode())
        if results:
            _file.write("|".join(results))


if __name__ == "__main__":
    _file = "c://home/1598615.pdf"
    main(_file)