Python提取站点地图sitemap.xml

站点sitemap.xml内容格式

百度搜索：Xs小屋

Python 3

简单实现，提取URL保存到url.txt文件

import xml.dom.minidom as xmldom
import urllib.request
import xml
#Python 简单实现 提取站点地图 提取到得URL保持到D盘url.txt文件内容中
#2021.10.3
#百度搜索：Xs小屋 微信公众号：Xs小屋

proxy = '127.0.0.1:10809'
proxy_support = urllib.request.ProxyHandler({'http':'http://'+proxy,
                                             'https':'https://'+proxy})

opener = urllib.request.build_opener(proxy_support)

#如有需要取消注释，使用代理
#urllib.request.install_opener(opener)

headers = {
    'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:89.0) Gecko/20100101 Firefox/89.0"
}

##设置站点地图 URL链接
sitemap_url = "https://www.nstns.com/sitemap.xml"


http = urllib.request.Request(url=sitemap_url,headers=headers);

#发送请求
http_run = urllib.request.urlopen(http);


dom = xml.dom.minidom.parse(http_run)

return_xml = dom.documentElement.getElementsByTagName("url")
open("D:\\url.txt", 'w').close()
for url_xml in return_xml:
        url = url_xml.getElementsByTagName("loc")[0]
        a_url = url.firstChild.data        
        #print(a_url)
        file = open("D:\\url.txt",'a',encoding="utf-8")
        file.write(a_url+'\n')
        file.close()
        continue

效果图