urllib.request基本使用用法

（1）基本用法

    url = "http://www.baidu.com/"# 获取response对象response = urllib.request.urlopen(url)# 读取内容 bytes类型data = response.read()# 转化为字符串str_data = data.decode("utf-8")# 字符串转化为bytesstr_name = "baidu"bytes_name =str_name.encode("utf-8")

（2）url参数中含有汉字的需要转译

    url = "http://www.baidu.com/s?wd="name = "python中含有汉字"final_url = url + name#网址里面包含了汉字;ascii是没有汉字的;url转译#将包含汉字的网址进行转译encode_new_url = urllib.parse.quote(final_url,safe=string.printable)# 使用代码发送网络请求response = urllib.request.urlopen(encode_new_url)print(response)#读取内容data = response.read().decode()#保存到本地with open("02-encode.html","w",encoding="utf-8")as f:f.write(data)

（3）传入字典类型的参数

    url = "http://www.baidu.com/s?"params = {"wd":"中文","key":"zhang","value":"san"}# 字典类型转译成参数str_params = urllib.parse.urlencode(params)final_url = url + str_params# 将带有中文的url 转译成计算机可以识别的urlend_url = urllib.parse.quote(final_url,safe=string.printable)response = urllib.request.urlopen(end_url)data = response.read().decode("utf-8")print(data)

（4）添加header

第一种添加header的方式

    url = "https://www.baidu.com"# 添加请求头的信息headers = {# 浏览器的版本'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36','name':'chen'}# 创建请求对象request = urllib.request.Request(url, headers=headers)

第二种添加header的方式：动态添加

    url = "https://www.baidu.com"# 创建请求对象request = urllib.request.Request(url)# 动态添加请求头信息request.add_header("User-Agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36")# 请求网络数据response = urllib.request.urlopen(request)data = response.read().decode("utf-8")# 获取到完整的urlfinal_url = request.get_full_url()print(final_url)with open("baidu.html", "w", encoding="utf-8") as f:f.write(data)# 获取请求头的信息request_headers = request.headersprint(request_headers)user_agent = request.get_header('User-agent')print(user_agent)# 响应头print(response.headers)

（5）使用代理

    url = 'https://www.cnblogs.com/chenshy'# 添加代理proxy = {'http': '119.102.25.91:9999'}# 代理处理器proxy_handler = urllib.request.ProxyHandler(proxy)# 创建自己的openeropener = urllib.request.build_opener(proxy_handler)# 拿着代理ip发送请求data = opener.open(url).read().decode("utf-8")print(data)

(6) cookie

a.在头部添加cookie

    url = 'https://www.yaozh.com/member/'headers = {'User_Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36','Cookie':'acw_tc=707c9fd115550786016938465e492bb70702a65dacd78c0969a841171ddf8d; PHPSESSID=t4rb1af4vmks8gete5oqfd6ub7; _ga=GA1.2.521923122.1555078606; _gid=GA1.2.523976398.1555078606; Hm_lvt_65968db3ac154c3089d7f9a4cbb98c94=1555078606; MEIQIA_VISIT_ID=1JlnZOkmbJhJwfRjhyv0gTMf14i; MEIQIA_EXTRA_TRACK_ID=1JlnZL47AayFGs373mZAapsuPKv; yaozh_logintime=1555078687; yaozh_user=729821%09lifelover; yaozh_userId=729821; _gat=1; Hm_lpvt_65968db3ac154c3089d7f9a4cbb98c94=1555078691; yaozh_uidhas=1; yaozh_mylogin=1555078693; acw_tc=707c9fd115550786016938465e492bb70702a65dacd78c0969a841171ddf8d; MEIQIA_VISIT_ID=1JlnZOkmbJhJwfRjhyv0gTMf14i; MEIQIA_EXTRA_TRACK_ID=1JlnZL47AayFGs373mZAapsuPKv'}request = urllib.request.Request(url,headers=headers)response = urllib.request.urlopen(request)data = response.read().decode('utf-8')print(data)

b.登录之后获取cookie ,cookiejar的使用

import urllib.request
from http import cookiejar
from urllib import parsedef login():# 1.代码登录 获取cookie 带着cookies请求个人中心url = 'https://www.yaozh.com/login'# 登录的参数login_form_data = {'username':  'lifelover','pwd': 'chen19960319','formhash': 'F456373F7B','backurl': 'https%3A%2F%2Fwww.yaozh.com%2F'}# 发送登录请求cook_jar =  cookiejar.CookieJar()cookie_handler = urllib.request.HTTPCookieProcessor(cook_jar)opener = urllib.request.build_opener(cookie_handler)# 带着参数，发送post请求headers = {'User_Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36'}# 1.需要转译,转码  2.需要byte类型login_str = urllib.parse.urlencode(login_form_data).encode('utf-8')request = urllib.request.Request(url,headers=headers,data=login_str)# 如果登录成功，cookiejar自动保存cookieresponse = opener.open(request)# 带着cookie请求个人中心center = 'https://www.yaozh.com/member/'center_request = urllib.request.Request(center,headers=headers)response = opener.open(center_request)data = response.read().decode('utf-8')with open('test.html','w',encoding='utf-8') as f:f.write(data)