Python网络urlllib库详解常用的使用操作最全-CSDN博客

本文链接：https://blog.csdn.net/qq_42988748/article/details/100060384

本文详细介绍Python中使用urllib库进行HTTP请求的方法，包括GET和POST请求、处理响应、下载图片、设置代理、管理Cookie及URL解析等关键操作。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

py2和py3使用区别
在这里插入图片描述

最简单的请求方式urlopen

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

import urllib.request

response = urllib.request.urlopen('http://www.baidu.com')
print(response.read().decode('utf-8'))

查看状态码,响应头

import urllib.request

response = urllib.request.urlopen('https://www.python.org')
print(response.status)
print(response.getheaders())
print(response.getheader('Server'))

get请求

def Getmethod(url):
    headers = {
        'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)',
    }
    requst = urllib.request.Request(url,headers=headers)
    response = urllib.request.urlopen(requst)
    status = response.status
    response = response.read().decode('GBK')
    print(status)

post请求

def Postmethod(url):
    url = 'http://httpbin.org/post'
    headers = {
        'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)',
        'Host': 'httpbin.org'
    }
    dict = {
        'name': 'Germey'
    }
    data = bytes(urllib.parse.urlencode(dict), encoding='utf8')
    req = urllib.request.Request(url=url, data=data, headers=headers, method='POST')
    response = urllib.request.urlopen(req)
    print(response.read().decode('utf-8'))

下载图片

def Download_Picture(img):
    # file = urllib.request.urlopen(img['url'])/
    path = img['name'] + '.jpg'
    urllib.request.urlretrieve(img['url'],path)
    print('下载成功: {}'.format(path))

使用代理

import urllib.request

proxy_handler = urllib.request.ProxyHandler({
    'http': 'http://127.0.0.1:9743',
    'https': 'https://127.0.0.1:9743'
})
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)
response = 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'))

URL解析

from urllib.parse import urlencode

params = {
    'name': 'germey',
    'age': 22
}
base_url = 'http://www.baidu.com?'
url = base_url + urlencode(params)
print(url)
##http://www.baidu.com?name=germey&age=22