cns selenium

selenium.py

import os
from datetime import date
from time import sleep
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.webdriver import WebDriver
from openpyxl import Workbook

class DownloadCNJDDocuments:
    def __init__(self) -> None:
        self.downloadFilepath = os.path.join(os.getcwd(), 'documents')
        self.cnj_url = 'https://www.cnj.jus.br/corregedoria/justica_aberta/?'
        self.chrome = self._new_chrome_browser(headless=False, downloadPath=self.downloadFilepath)
    
    def execute(self) -> None:
        self._access_url(self.cnj_url)
        self._access_extrajudicial_services()
        self._search_cns()
        self._download_pdf()
        self.chrome.quit()

    def _access_url(self, url) -> None:
        self.chrome.get(url)
    
    def _access_extrajudicial_services(self) -> None:
        anchor = self.chrome.find_element(By.LINK_TEXT, "Clique aqui")
        anchor.click()
    
    def _search_cns(self) -> None:
        input = self.chrome.find_element(By.ID, "COD_IDENTIFICACAO_UNICA")
        input.send_keys("02.675-7")
        submit_button = self.chrome.find_element(By.CSS_SELECTOR, 'button[type="submit"]')
        submit_button.click()
    
    def _generate_excel_spreadsheet(self) -> None:
        # Encontre a linha (tr) específica da tabela usando seu id
        tr = self.chrome.find_element(By.ID, "8124")
        # Crie um novo arquivo Excel e adicione uma planilha
        workbook = Workbook()
        planilha = workbook.active
        # Encontre todas as linhas da tabela usando um seletor CSS ou XPATH
        linhas = tr.find_elements(By.TAG_NAME,"tr")
        # Itere sobre as linhas da tabela e adicione-as como linhas na planilha
        for linha in linhas:
            celulas = linha.find_elements(By.TAG_NAME,"td")
            linha_dados = []
            # Itere sobre as células da linha e adicione-as como valores nas colunas da planilha
            for celula in celulas:
                linha_dados.append(celula.text)
            planilha.append(linha_dados)
        # Salve o arquivo Excel
        workbook.save(filename="tabela.xlsx")
    
    def _download_pdf(self) -> None:
        cns_link = self.chrome.find_element(By.CSS_SELECTOR, 'img[src="html/img/produtividade.png"]')
        cns_link.click()
        cns_link.click()
        download_pdf_link = self.chrome.find_element(By.CSS_SELECTOR, 'a>strong')
        download_pdf_link.click()
        sleep(2)
        self._rename_downloaded_file()

    
    def _rename_downloaded_file(self) -> None:
        old_file = os.path.join(self.downloadFilepath, 'out.php')
        new_file = os.path.join(self.downloadFilepath, f'{date.today().strftime("%d-%m-%Y")}-cns.pdf')
        os.rename(old_file, new_file)
    
    def _new_chrome_browser(self, headless=True, downloadPath=None) -> WebDriver:
        """ Helper function that creates a new Selenium browser """
        options = webdriver.ChromeOptions()
        if headless:
            options.add_argument('headless')
        if downloadPath is not None:
            prefs = {}
            is_download_folder_exist = os.path.isdir(downloadPath)
            if not is_download_folder_exist:
                os.makedirs(downloadPath)
            prefs["profile.default_content_settings.popups"] = 0
            prefs["download.default_directory"] = downloadPath
            prefs["plugins.always_open_pdf_externally"] = True
            options.add_experimental_option("prefs", prefs)
        browser = webdriver.Chrome(options=options)
        browser.implicitly_wait(3)
        return browser


if __name__ == '__main__':
    app = DownloadCNJDDocuments()
    app.execute()