urllib 基本用法

基本爬虫

import urllib.request as req
import urllib.parse as parse
import ssl
import json
import time
ssl._create_default_https_context = ssl._create_unverified_context
url = 'https://api-yqzy.mrnaive.com/?s=App.MyUser.GetUserList'
# 打开一个 URL , 获得一个 URL 资源
data = {
    'sign': 'cf1cbd2e142667516d34d570a616ce4b',
    'page': 1,
    'pageNum': 5,
}
head = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 '
                  'Safari/537.36'
}
while True:
    # 将Unicode 资源编码成 utf-8
    dataRes = parse.urlencode(data).encode('utf-8')
    # request 对象
    requestObj = req.Request(url, dataRes, headers = head)
    openReq = req.urlopen(requestObj)
    # 返回的内容 , 将指定编码解码成 Unicode , 同时将json 转换成字典
    res = json.loads(openReq.read().decode('utf-8'))
    print(requestObj.headers)
    print('结果:', res)
    #
    print('返回的类型:', type(res))
    # 访问地址
    print('访问地址:', openReq.geturl())
    # 响应头
    print('服务器信息:', openReq.info())
    # http 状态码
    print('http 状态码', openReq.getcode())
    time.sleep(1)