我正在尝试从以下网站下载 PDF:http://esaj.tjsp.jus.br/cjsg/getArquivo.do?conversationId=&cdAcordao=16548741
所以,我做的第一件事是创建一个 time.sleep 来手动解决 reCAPTCHA (我不确定是否可以自动执行此操作)。之后,我希望下载开始。然而,什么也没有发生。
下面是我的代码:
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
import time
if __name__ == "__main__":
url = "http://esaj.tjsp.jus.br/cjsg/getArquivo.do?conversationId=&cdAcordao=16548741"
service = Service(executable_path='./chromedriver.exe')
options = webdriver.ChromeOptions()
options.add_experimental_option('prefs', {
'download.default_directory': 'C:\\Users\....',
'download.prompt_for_download': False,
"download.directory_upgrade": True,
'plugins.always_open_pdf_externally': True})
driver = webdriver.Chrome(service=service, options=options)
try:
driver.get(url)
print('Acesso')
time.sleep(180)
print('Sucesso!')
driver.implicitly_wait(10)
print('Download concluido...')
driver.quit()
except Exception as e:
print(f"Ocorreu um erro: {e}")
driver.quit()