python截取url参数_Python爬行一个页面的时候如何提取带有参数的url呢？

[Python] 纯文本查看 复制代码#coding = utf-8

import re

import requests

import time

from bs4 import BeautifulSoup as asp

import random

headeraa = {'User-Agent': 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)',}

hansb = open('urllist.txt','r')

hanssb = hansb.readlines()

hansb.close()

print hanssb

for urllists in hanssb:

urllistx = urllists.strip('\n')

print urllistx

time.sleep(3)

try:

sss5 = []

han = requests.get(url=urllistx,headers=headeraa,timeout=10)

print han.status_code

print han.content

soup = asp(han.content)

hrefs = soup.find_all(href=re.compile(r'asp?'))#寻找a标签，带href中带有ASP？

for href in hrefs:

href = href.get('href')

print '========================='

print href

# zhzhzh = open('zzzzz.txt','a+') #开始写入

# zhzhzh.write(urllists + href + '\n')

sss5.append(href)

# zhzhzh.close()

except:

print 'connect time out'

print sss5

sss4 = random.sample(sss5,3)

print '---------------'

print sss4

print '---------------'