Question

我正在尝试创建一个剪贴簿，该剪贴簿可以进入网站并从房地产基金下载包含资产负债表的XML文件。

使用下面的代码，我输入一个特定基金的网站，文档编号为07000400000146（位于URL的末尾），使用网站上的搜索栏过滤文档，然后单击以使用下载表格中的第一个文档XPath。

driver.get('https://fnet.bmfbovespa.com.br/fnet/publico/abrirGerenciadorDocumentosCVM?cnpjFundo=07000400000146')
driver.find_element_by_css_selector(f'input[type="search"]').click()
driver.find_element_by_css_selector(f'input[type="search"]').send_keys('informe mensal')
time.sleep(1)
driver.find_element_by_xpath('//*[@id="tblDocumentosEnviados"]/tbody/tr[1]/td[10]/div/a[2]/i').click()

如何在“数据引用”列中创建一个布尔表达式以发现行是03/2020还是02/2020还是01/2020，然后下载每个对应日期的所有可用文件？

Answer 1

您可以尝试使用datelist=[ '03/2020','02/2020','01/2020']这样的列表，并使用xpath选项检查网页上的日期是否可用。如果可用的日期，则单击并下载，否则将没有可用的日期。使用try..except块。忽略sleep()使用WebDriverWait（）

from selenium import webdriver
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait

driver=webdriver.Chrome()
driver.get('https://fnet.bmfbovespa.com.br/fnet/publico/abrirGerenciadorDocumentosCVM?cnpjFundo=07000400000146')
driver.find_element_by_css_selector('input[type="search"]').click()
driver.find_element_by_css_selector('input[type="search"]').send_keys('informe mensal')
datelist=[ '03/2020','02/2020','01/2020']
for dates in datelist:
    try:
       WebDriverWait(driver,5).until(EC.element_to_be_clickable((By.XPATH,"//table[@id='tblDocumentosEnviados']//td[text()='"+ dates + "']/following-sibling::td[5]//a[@title='Download do Documento']"))).click()
       print('file downloaded with dates available ' + dates)
    except:
       print("No such dates available " + dates)

这将在控制台上打印出来。

No such dates available 03/2020
file downloaded with dates available 02/2020
file downloaded with dates available 01/2020

状态为Ativo

的更新代码

driver.get('https://fnet.bmfbovespa.com.br/fnet/publico/abrirGerenciadorDocumentosCVM?cnpjFundo=07000400000146')
driver.find_element_by_css_selector('input[type="search"]').click()
driver.find_element_by_css_selector('input[type="search"]').send_keys('informe mensal')
datelist=[ '03/2020','02/2020','01/2020']
for dates in datelist:
    try:
       WebDriverWait(driver,5).until(EC.element_to_be_clickable((By.XPATH,"//table[@id='tblDocumentosEnviados']//td[text()='"+ dates +"']/following-sibling::td[.//span[text()='Ativo']]/following-sibling::td//a[@title='Download do Documento']"))).click()
       print('file downloaded with dates available ' + dates)
    except:
       print("No such dates available " + dates)

Answer 2

请尝试下面的代码下载pdf

driver.get('https://fnet.bmfbovespa.com.br/fnet/publico/abrirGerenciadorDocumentosCVM?cnpjFundo=07000400000146')
driver.maximize_window()
wait = WebDriverWait(driver, 20)
elemnt=wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, 'label > input')))
elemnt.send_keys('informe mensal')

mylist=[ '03/2020','02/2020','01/2020']
for list in mylist:
button = WebDriverWait(driver, 5).until(EC.element_to_be_clickable((By.XPATH,
                                                                    "//td[text()='" + list + "']//following-sibling::td//a[@title='Download do Documento']")))
driver.execute_script("arguments[0].click();", button);

如何使用硒验证表格元素并单击其他元素

2 个答案: