python实现切割url得到域名、协议、主机名等各个字段

    有一个需求就是需要对url进行进一步的划分得到详细的各个字段信息&＃xff0c;下面是简单的实现&＃xff1a;

#!/usr/bin/python
# -*- coding: UTF-8 -*-
&＃39;&＃39;&＃39;
__Author__:沂水寒城
功能: 对URL进行分割&＃xff0c;基于urlparse, publicsuffix, urllib编写
&＃39;&＃39;&＃39;
from urlparse import urlparse
import codecs
from publicsuffix import PublicSuffixList
from urllib import splitport
import redef domain_split(server_domain):&＃39;&＃39;&＃39;server_domain为网站所用服务名&＃43;域名分割域名, 得到前缀(服务名)、主机域名、后缀(顶级域名)输入www.baidu.com&＃xff0c;输出&＃39;www&＃39;, &＃39;baidu&＃39;, &＃39;com&＃39;输入172.31.137.240&＃xff0c;输出&＃39;&＃39;, &＃39;172.31.137.240&＃39;, &＃39;&＃39;&＃39;&＃39;&＃39;PSL_FILE &＃61; codecs.open(&＃39;public_suffix_list.dat&＃39;, encoding&＃61;&＃39;utf8&＃39;)psl &＃61; PublicSuffixList(PSL_FILE)domain &＃61; psl.get_public_suffix(server_domain)# 取域名的第一个字段&＃xff0c;即第一个&＃39;.&＃39;之前的为主机域名, 后面为顶级域名&＃xff0c;前面为所使用的服务if &＃39;.&＃39; in domain:server &＃61; server_domain[:-len(domain)]host &＃61; domain[:domain.index(&＃39;.&＃39;)]top &＃61; domain[domain.index(&＃39;.&＃39;):]hostname &＃61; server &＃43; host &＃43; topelse: # 说明提取域名失败&＃xff0c;例如172.31.137.240等IP形式&＃xff0c;此时全部当作主机域名server &＃61; &＃39;&＃39;host &＃61; server_domaintop &＃61; &＃39;&＃39;hostname &＃61; server_domainreturn server, host, top, hostnamedef url_split_new(url):&＃39;&＃39;&＃39;url分割&＃39;&＃39;&＃39;if not url.startswith(&＃39;http&＃39;): # 补全协议&＃xff0c;否则urlparse出错url &＃61; &＃39;http://&＃39; &＃43; urlparts &＃61; urlparse(url)# 服务&＃43;域名&＃39;www.baidu.api.com.cn&＃39;切分server, host, top, hostname &＃61; domain_split(parts.netloc)host, port &＃61; splitport(host)if port &＃61;&＃61; None: port &＃61; &＃39;&＃39;return {&＃39;protocol&＃39;: parts.scheme, &＃39;hostname&＃39;: hostname, &＃39;path&＃39;: parts.path}if __name__ &＃61;&＃61; &＃39;__main__&＃39;:print url_split_new(&＃39;http://www.baidu.com/&＃39;)print url_split(&＃39;http://www.baidu.com/&＃39;)