python3爬虫 url管理器

import urllib.request   #python3中将urllib2拆分为了urllib.request、urllib.error、urllib.response等
import http.cookiejar

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

print("第一种方法")
response1 = urllib.request.urlopen(url)
print(response1.getcode())  #打印response1的状态码看是否请求成功, 200表示请求成功
print(len(response1.read())) #打印返回网页内容长度

print("第二种方法")
request = urllib.request.Request(url)
request.add_header("user-agent", "Mozilla/5.0") #模拟浏览器访问
request2 = urllib.request.urlopen(request)
print(request2.getcode())
print(len(request2.read()))

print("第三种方法")
cj = http.cookiejar.CookieJar()
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj)) #在请求对象中添加cookie
urllib.request.install_opener(opener)
request3 = urllib.request.urlopen(url)
print(request3.getcode())
print(len(request3.read()))
原文地址:https://www.cnblogs.com/lsy-ai/p/5666163.html