renomeador_n22/renomearN22.py

import PyPDF2
import unicodedata
import os
import re


def create_subfolder_if_not_exists():
    subfolder_name = "notasProcessadas"
    if not os.path.isdir(subfolder_name):
        os.mkdir(subfolder_name)

def extract_num_nota(filename):
    start = filename.rfind("_")
    end = filename.find(".pdf")
    return filename[start+1:end]

def is_pdf(filename):
    return filename[-4:] == ".pdf"

def filter_interesting_lines(lines_array):
    lines_array_res = []
    flag = False
    for line in lines_array:
        if (line.find("TOMADOR DE SERVI") > -1):
            flag = True
        elif line.find("NOTA FISCAL DE SERVI") > -1:
            flag = False
        
        if flag:
            lines_array_res.append(line)
    return lines_array_res

def condition_nome_razao(input_str):
    input_str = input_str.upper()
    return input_str.find("NOME/RAZ") > -1

def format_nome_razao(input_str):
    input_str = input_str[input_str.find(":")+1:].strip().replace(' ', '_')
    input_str = unicodedata.normalize('NFKD', input_str).encode('ascii', 'ignore').decode('ascii')
    input_str = input_str.upper()
    return input_str[:40]


def condition_cpf_cnpj(input_str):
    return input_str.find("CPF/CNPJ") > -1

def string_to_numeric(input_str):
    res = ""
    for char in input_str:
        if char.isnumeric():
            res += char
    return res

def format_cpf_cnpj(input_str):
    pattern=re.search(r'\d{2}\.\d{3}\.\d{3}\/\d{4}\-\d{2}', input_str)
    if pattern != None:
        return string_to_numeric(input_str[pattern.start():pattern.end()])
    else:
        pattern=re.search(r'\d{3}\.\d{3}\.\d{3}\-\d{2}', input_str)
        if pattern != None:
            return string_to_numeric(input_str[pattern.start():pattern.end()])

        



def main():
    create_subfolder_if_not_exists()
    dir_processadas = "notasProcessadas"
    filenames = os.listdir()
    for filename in filenames:
        if (is_pdf(filename)):
            reader = PyPDF2.PdfReader(filename)
            interesting_string_page1 = filter_interesting_lines(reader.pages[0].extract_text().split('\n'))
            num_nota = extract_num_nota(filename)
            for line in interesting_string_page1:
                if (condition_nome_razao(line)):
                    nome_razao = format_nome_razao(line)
                elif condition_cpf_cnpj(line):
                    cpf_cnpj = format_cpf_cnpj(line)
            newFilename = nome_razao + "_" + cpf_cnpj + "_" + num_nota + ".pdf"
            newPlace = os.path.join(dir_processadas, newFilename)
            os.rename(filename, newPlace)
main()