Regex Function to remove Double Extension-CodePudding

I have written a code to convert multiple pdf files to .txt file. The code works pretty fine but the major issue I am having is that while having an extension I am getting double extension meaning "companyA.pdf" to "companyA.pdf.txt". I am not really sure where I am making a mistake. Following is the code :

'''

import os
import re
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from io import StringIO

pdf_folder_path = os.getcwd()                               #Get the path of the current folder
text_folder_path = os.getcwd()   '/'   'text_folder'        #Notation of path is mac specification. For windows'/'To'\'Correct to.

os.makedirs(text_folder_path, exist_ok=True)
pdf_file_name = os.listdir(pdf_folder_path)

#name is a PDF file (ends.pdf) returns TRUE, otherwise FALSE is returned.

def pdf_checker(name):
    pdf_regex = re.compile(r'. \.pdf')
    if pdf_regex.search(str(name)):
        return True
    else:
        return False

#Convert PDF to text file
def convert_pdf_to_txt(path, txtname, buf=True):
    rsrcmgr = PDFResourceManager()
    if buf:
        outfp = StringIO()
    else:
        outfp = file(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 = outfp.getvalue()
        make_new_text_file = open(text_folder_path   '/'   path   '.txt', 'w')
        make_new_text_file.write(text)
        make_new_text_file.close()
    outfp.close()

#Get the pdf file name in the folder and list it
for name in pdf_file_name:
    if pdf_checker(name):
        convert_pdf_to_txt(name, name   '.txt')     # pdf_Use checker and TRUE (end is.For pdf) proceed to conversion)
    else:
        pass                                        #Pass if not a PDF file

'''

CodePudding user response：

What I recommend is running a regex to remove .pdf when the name string ends with it, like so:

if pdf_checker(name):
    newName = re.sub(r'\.pdf$', '.txt', name)
    convert_pdf_to_txt(name, newName)

Then replace this line:

make_new_text_file = open(text_folder_path   '/'   path   '.txt', 'w')

With the following:

make_new_text_file = open(text_folder_path   '/'   txtname, 'w')