Variables outside the function

Question

I am using the code below to read Pdfs with the Tkinter interface:

import io
from pdfminer.converter import TextConverter
from pdfminer.pdfinterp import PDFPageInterpreter
from pdfminer.pdfinterp import PDFResourceManager
from pdfminer.pdfpage import PDFPage
from tkinter import *
from tkinter import filedialog

janela = Tk()
janela.geometry('800x600')
janela.title('Envio de Email automatizado')
inserepdf = Label(janela, text='Buscar pdf')
inserepdf.pack()


def abrirArquivo():
    arquivo = filedialog.askopenfilename()


botaoAbrir = Button(janela, text="Abrir Arquivo", command=abrirArquivo)
botaoAbrir.pack()


def extract_text_from_pdf(pdf_path):
    resource_manager = PDFResourceManager()
    fake_file_handle = io.StringIO()
    converter = TextConverter(resource_manager, fake_file_handle)
    page_interpreter = PDFPageInterpreter(resource_manager, converter)
    with open(arquivo, 'rb') as fh:
        for page in PDFPage.get_pages(fh,
                                      caching=True,
                                      check_extractable=True):
            page_interpreter.process_page(page)
        text = fake_file_handle.getvalue()
    # close open handles
    converter.close()
    fake_file_handle.close()

    if text:
        return text


if __name__ == '__main__':
    texto = str(extract_text_from_pdf(''))

    print(texto.split())

janela.mainloop()

However, I cannot make the program read the imported pdf in the open function File() , informs that the file variable does not exist, but I could not define it as global or nonlocal, and I do not know how to use the variable within the extract_text_from_pdf(pdf_path) function. If you can help me, I’d really appreciate it.

Answer 1

This is happening because the variable is declared in the function as a local variable, for you to use this variable elsewhere you have to leave this variable global, to use a variable global within a function, it is necessary to declare it as global within that function so:

arquivo=""
def abrirArquivo():
    global arquivo
    arquivo = filedialog.askopenfilename()

def extract_text_from_pdf(pdf_path):
    global arquivo
    resource_manager = PDFResourceManager()
    fake_file_handle = io.StringIO()
    converter = TextConverter(resource_manager, fake_file_handle)
    page_interpreter = PDFPageInterpreter(resource_manager, converter)
    with open(arquivo, 'rb') as fh:
        for page in PDFPage.get_pages(fh,
                                      caching=True,
                                      check_extractable=True):
            page_interpreter.process_page(page)
        text = fake_file_handle.getvalue()
    # close open handles
    converter.close()
    fake_file_handle.close()

    if text:
        return text