Python 爬虫入门3种方法

 Python 2.0

url = "http://www.baidu.com" 
print '第一种方法' 
response1 = urllib2.urlopen(url) 
print response1.getcode() 
print len(response1.read()) 

print '第二种方法' 
request = urllib2.Request(url) 
request.add_header("user-agent","Mozilla/5.0") 
response2 = urllib2.urlopen(request) 
print response2.getcode() 
print len(response2.read()) 

print '第三种方法' 
cj = cookielib.CookieJar() 
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj)) 
urllib2.install_opener(opener) 
response3 = urllib2.urlopen(url) 
print response3.getcode() 
print cj print 
response3.read()

Python 3.0

第一种方法
import urllib.request
import http.cookiejar

url="http://www.baidu.com"

print('第一种方法：')
response1 = urllib.request.urlopen(url)

print(response1.getcode())
print(len(response1.read()))

print('第二种方法')
request = urllib.request.Request(url)
request.add_header('user-agent','Mozilla/5.0')
response2 =urllib.request.urlopen(request)
print(response1.getcode())
print(len(response2.read()))

print('第三种方法')
cj = http.cookiejar.CookieJar()
opener= urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj))
urllib.request.install_opener(opener)
response3 =urllib.request.urlopen(url)
print(response3.getcode())
print(cj)
print(response3.read())

 

 

 

参考：http://www.imooc.com/article/16363