网络爬虫

import urllib2

response = urllib2.urlopen("http://www.baidu.com")
html = response.read()
print(html)

# coding:utf-8
import re  
# import requests  
import sys  
import codecs
#python2
import urllib2

#设置编码  
reload(sys)  
sys.setdefaultencoding(‘utf-8‘)  
#获得系统编码格式  
type = sys.getfilesystemencoding()  

# response = urllib2.urlopen("http://www.baidu.com")
req=urllib2.Request("http://www.baidu.com")
response=urllib2.urlopen(req)
html = response.read().decode(‘utf-8‘).encode(type)  
print(html)

# coding:utf-8

import sys
import urllib2
# 设置编码  
reload(sys)  
sys.setdefaultencoding(‘utf-8‘)  
# 获得系统编码格式  
type = sys.getfilesystemencoding()  

url = "http://www.baidu.com"
user_agent = "Mozilla/5.0(compatible;MSIE9.0;WindowsNT6.1;Trident/5.0;"

headers={
    ‘User-Agent‘:user_agent
}
req=urllib2.Request(url,headers=headers)
response = urllib2.urlopen(req)
html=response.read().decode("utf-8").encode(type)
print(html)

import re

pattern = re.compile("\d+\.\d+")

s1="1.234 dsa frwr 4235.324 432423"
rs = pattern.findall(s1)
print(rs)