爬虫学习第三天，urllib中的handler

Handler

代理

import urllib.request

proxy_handler = urllib.request.ProxyHandler({
    'http': 'http://163.125.255.169:9000',
    'https': 'https://163.125.255.169:9000'
})
opener = urllib.request.build_opener(proxy_handler)
response = opener.open('http://www.baidu.com')
print(response.read())

import urllib.request

proxy_handler = urllib.request.ProxyHandler({
    'http': 'http://58.220.95.35:10174',
    'https': 'https://58.220.95.35:10174'
})
opener = urllib.request.build_opener(proxy_handler)
response = opener.open('http://httpbin.org/get')
print(response.read())

Cookie

import http.cookiejar,urllib.request

cookie = http.cookiejar.CookieJar()
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
resopnse = opener.open('http://www.baidu.com')
for item in cookie:
    print(item.name+"="+item.value)

import http.cookiejar,urllib.request
filename = "cookie.txt"
cookie = http.cookiejar.MozillaCookieJar(filename)
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
cookie.save(ignore_discard=True,ignore_expires=True)

import http.cookiejar,urllib.request
filename = "cookie.txt"
cookie = http.cookiejar.LWPCookieJar(filename)
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
cookie.save(ignore_discard=True,ignore_expires=True)

import http.cookiejar,urllib.request
cookie = http.cookiejar.LWPCookieJar()
cookie.load('cookie.txt',ignore_discard=True,ignore_expires=True)
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
print(response.read().decode('utf-8'))