Reads a PDF file into text

pdf_to_text.py

import subprocess
from typing import List as L


def pdf_to_text(fp: str, strip: bool = True) -> L[str]:
    proc = subprocess.Popen(['pdftotext', '-layout', fp, '-'], stdout=subprocess.PIPE)
    raw_output = proc.communicate()[0].decode()
    if strip:
        res = [i.strip() for i in raw_output.split('\n') if i]
    else:
        res = raw_output.split('\n')
    return res