Python自动化下载指定公开页面文件-CSDN博客

本文链接：https://blog.csdn.net/weixin_61092302/article/details/138576286

示例代码如下，但你拿到本地之需要做两件事才能运行

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
import time

# 设置Selenium WebDriver
driver_path = r'C:\Users\……\chromedriver-win64\chromedriver-win64\chromedriver.exe'  # 替换为您的ChromeDriver路径
url = 'https://data.sh.gov.cn/view/detail/index.html?type=cp&&id=AB6002012300'  # 替换为实际的下载页面URL

service = Service(executable_path=driver_path)   
# 初始化WebDriver
driver = webdriver.Chrome(service=service)

try:
    # 打开下载页面
    driver.get(url)
    
    # 等待页面加载完成，这里设置了最长等待时间为10秒
    time.sleep(1)
    

    download_button = driver.find_element(By.CSS_SELECTOR, 'span.filebase.xlsx.docType00xlsx')
    download_button.click()
 
    
    
    # 等待文件下载完成。这里需要根据实际情况设置等待时间或检查下载状态
    time.sleep(1)
    
finally:
    # 关闭浏览器
    driver.quit()

print("Download end!")

1. 需要先下载模拟点击浏览器的软