2019-04-25

python内置的http请求库

urllib.request 请求模块

urlib.error  异常处理模块

urllib.parse url解析模块

urllib.robotparser  robots.txt解析模块

相比python2的变化

python2

import urllib2

response = urllib2.urlopen('http://www.biadu.com')

python3

import urllib.request

response = urllib.reqquest.urlopen('http://www.baidu.com')

用法：

urlopen

发送request请求

urllib.request.urlopen(url,data=None,[timeout,]*,cafile-None,cadefault=False,context=None)

get请求

import urllib.request

response = urllib.request.urlopen('http://www.baidu.com')

print(response.read().decode('utf-8'))

post请求

# http://httpbin.org/posthttp测试用网址，以后可用测试使用

import urllib.parse

import urllib.request

data =- bytest(urllib.parse.urlencode({'word':'hello'}),encoding='utf-8')

response = urllib.request.urlopen('http://httpbin.org/post',data=data)

print(response.read())

import urllib.request

response = urllib.request.urlopen('http://httpbin.org/get',timeout=1)

print(response.read())

import socket

import urllib.request

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')

注意： except后边不加冒号

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())

b'{\n  "args": {}, \n  "data": "", \n  "files": {}, \n  "form": {\n    "word": "hello"\n  }, \n  "headers": {\n    "Accept-Encoding": "identity", \n    "Content-Length": "10", \n    "Content-Type": "application/x-www-form-urlencoded", \n    "Host": "httpbin.org", \n    "User-Agent": "Python-urllib/3.7"\n  }, \n  "json": null, \n  "origin": "106.114.219.48, 106.114.219.48", \n  "url": "https://httpbin.org/post"\n}\n'

importurllib.request

response=urllib.request.urlopen('http://httpbin.org/get',timeout=1)

print(response.read())

b'{\n  "args": {}, \n  "headers": {\n    "Accept-Encoding": "identity", \n    "Host": "httpbin.org", \n    "User-Agent": "Python-urllib/3.7"\n  }, \n  "origin": "106.114.219.48, 106.114.219.48", \n  "url": "https://httpbin.org/get"\n}\n'

importsocket

importurllib.request

importurllib.error

try:

response=urllib.request.urlopen('http://httpbin.org/get',timeout=0.1)

excepturllib.error.URLErrorase:

ifisinstance(e.reason,socket.timeout):

print('TIME OUT')

TIME OUT

In [ ]: