python批量爬取xml文件

Posted 2022-07-29

1.网站链接：

https://www.cnvd.org.cn/shareData/list

2.需要下载的页面文件：

3.该页面需要登陆，然后批量下载共享漏洞文件，我们就通过cookie来实现。

#!/usr/bin/env python
# -*- coding: utf-8 -*-

"""
Date: 2019-08-17
Author: Bob
Description: python爬取xml文件
"""

import requests
from bs4 import BeautifulSoup

def cnvd_spider():
    url = ‘https://www.cnvd.org.cn/shareData/list?max=240&offset=0‘

    headers = 
        "Cookie": "__jsluid_s=65d5e7902f04498e89b16e93fb010b3c; __jsluid_h=1ab428e655aee36ac3c9835db29b6714; JSESSIONID=91BB91B37543D365AA64895EDFCD828F; __jsl_clearance=1566003116.655|0|CYPFsKirGYBG12qtoOrS5Kq1rM0%3D",
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/76.0.3809.100 Safari/537.36",
    

    html = requests.get(url=url, headers=headers).text
    soup = BeautifulSoup(html, ‘lxml‘)
    links = soup.find_all(‘a‘, attrs=‘title‘: ‘下载xml‘)

    for link in links:
        url = ‘https://www.cnvd.org.cn‘ + link.get(‘href‘)
        file_name = link.get_text()
        html_data = requests.get(url=url, headers=headers)
        with open(file_name, ‘w‘) as f:
            f.write(html_data.content)

if __name__ == ‘__main__‘:
    cnvd_spider()