urllib/requests基本库的使用

urllib的使用

import urllib.request
#发送请求获取返回结果
response = urllib.request.urlopen("https://www.baidu.com/")
print(type(response))
print(response.status)  #状态码
print(response.getheaders()) #头信息
print(response.getheader('Server')) #服务器
print(response.read().decode('utf-8'))

data参数(模拟表单的提交方式，以POST方式传输数据)

import urllib.parse
import urllib.request

data = bytes(urllib.parse.urlencode({'word':'hello'}),encoding='utf-8')
response = urllib.request.urlopen('http://httpbin.org/post',data=data)
print(response.read().decode('utf-8'))

 timeout参数(设置timeout实现超时处理)

import urllib.request
import socket
import urllib.error

try:
    response = urllib.request.urlopen('http://httpbin.org/get',timeout=0.1)
except urllib.error.URLError as e:
    if isinstance(e.reason,socket.timeout):
        print('Time Out')

Request(urlopen方法可以试下最基本的发起请求，但几个简单的参数不足以构建一个完整的请求，所以利用更强大的Request)

from urllib import request,parse

url = 'http://httpbin.org/post'
headers = {
            'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:58.0) Gecko/20100101 Firefox/58.0',
            'Host':'httpbin.org'
} #请求头

dict = {
    'name':'Germey'
}

data = bytes(parse.urlencode(dict),encoding='utf-8')          #传输的data必须转化为字节类型
req = request.Request(url=url,data=data,headers=headers,method='POST')
response = request.urlopen(req)
print(response.read().decode('utf-8'))