【Python】python3中urllib爬虫开发

import urllib.request
from http import cookiejar
url =‘http://www.baidu.com‘

print("First Method")

response1 = urllib.request.urlopen(url)
#返回状态码
print(response1.getcode())
print(len(response1.read()))

print("Second Method")
request = urllib.request.Request(url)
request.add_header("uese-agent","Mazilla/5.0")
response2 = urllib.request.urlopen(url)
#返回状态码
print(response2.getcode())
print(len(response2.read()))

print("Third Method")
#声明一个CookieJar对象实例来保存cookie
cj = cookiejar.CookieJar()
#利用urllib.request库的HTTPCookieProcessor对象来创建cookie处理器,也就CookieHandler
handler = urllib.request.HTTPCookieProcessor(cj)
#通过CookieHandler创建opener
opener = urllib.request.build_opener(handler)
#此处的open方法同urllib.request的urlopen方法，也可以传入request
response3 = opener.open(url)
#返回状态码
print(response3.getcode())
print(response3.read())