read_txt_from_PDF.py

import re
from io import StringIO

from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfinterp import PDFPageInterpreter, PDFResourceManager
from pdfminer.pdfpage import PDFPage

space = re.compile(r"[ 　]+")


def convert_pdf_to_txt(path, txtname, buf=True):
    rsrcmgr = PDFResourceManager()
    if buf:
        outfp = StringIO()
    else:
        outfp = open(txtname, 'w')
    codec = 'utf-8'
    laparams = LAParams()
    laparams.detect_vertical = True
    device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams)
    fp = open(path, 'rb')
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    for page in PDFPage.get_pages(fp):
        interpreter.process_page(page)
    fp.close()
    device.close()
    if buf:
        text = re.sub(space, "", outfp.getvalue())
        return text
    outfp.close()


convert_pdf_to_txt("TEST.pdf", "from_pdf.txt", False)