from urlparse import urlparse
import urllib

from urllib.parse import urlparse
import urllib.request

# -*- coding:utf-8 -*-
 
from urlparse import urlparse
import urllib
import re
 
# url
source_txt = "E:\\python_Anaconda_code\\url.txt"
# 规则
regular = r'(\w+(%\w\w)+\w+|(%\w\w)+\w+(%\w\w)+|\w+(%\w\w)+|(%\w\w)+\w+|(%\w\w)+|\w+)'
 
# 存放关键字
kw_list = list()
 
# key为要研究网站的host，value为关键字的嫁接标识符
dict = {
 "www.baidu.com": "wd=",
 "news.baidu.com": "word=",
 "www.sogou.com": "query=",
 "tieba.baidu.com": "kw=",
 "wenku.baidu.com": "word=",
 "music.sina.com.cn": "k=",
 "www.haosou.com": "q=",
 "www.lagou.com": "list_",
 "www.chunyuyisheng.com": "query=",
 "s.weibo.com": "weibo/"
}
 
def Main():
 with open(source_txt, 'r') as f_source_txt:
  for url in f_source_txt:
   host = url.split("//")[1].split("/")[0]
   if host in dict:
    flag = dict[host]
    if flag.find("=") != -1:
     query = urlparse(url).query.replace('+', '')
     kw = re.search(flag + regular, query, re.I) # .group(0)
     if kw:
      kw = urllib.unquote(kw.group(0).split(flag)[1])
      print(kw)
    else:
     path = urlparse(url).path.replace('+', '')
     kw = re.search(flag + regular, path.replace("%25", "%"), re.I)
     if kw:
      kw = urllib.unquote(kw.group(0).split(flag)[1])
      print(kw)
if __name__ == '__main__':
 Main()

https://www.baidu.com/s"text-align: center">

如果要研究其他host，可以加到字典dict里。
备注：以上代码和思路仅供参考，如有更好的方法敬请留言！
以上这篇Python解析、提取url关键字的实例详解就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持。