网络爬虫函数封装不会的可以来copy

    <!-- 爬虫远代码 没问题可以copy -->

from urllib import request,parse
from urllib.error import  HTTPError,URLError

#需求：post(url,form)
#需求：get(url,headers)

def get(url,headers=None):
    return urlrequests(url,headers=headers)
def post(url,form,headers=None):
    return urlrequests(url,form,headers=headers)

#封装爬虫页面
# 判断获取方式,有表单式POST，没有是GET

#1. 传入url
#2. user_agent
#3. headers
#4. 定义Request
#5. urlopen
#6. 返回byte数组
def urlrequests(url,form=None,headers=None):
    user_agent="Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36"

    if headers ==None:
        headers={
            'User-Agent':user_agent
        }
    html_bytes=b""
    try:
        if form:
            # POST
            form_str = parse.urlencode(form)
            # print(form_str)
            # 2.2 转换成bytes
            form_bytes = form_str.encode('utf-8')
            req = request.Request(url, data=form_bytes, headers=headers)
        else:
            #GET
            req=request.Request(url,headers=headers)
        response=request.urlopen(req)
        html_bytes=response.read().decode('utf-8')

    except HTTPError as e:
        pritn(e)
    except URLError as e:
        pritn(e)

    return html_bytes

if __name__=="__main__":

    # url 地址 本文为百度，hao123  自己可以换
    
    #百度翻译 单词
    # url = 'http://fanyi.baidu.com/sug'
    # form = {
    #     'kw': '呵呵'
    # }
    # html_bytes = post(url, form=form)
    # print(html_bytes)

    # hao 123 网页爬去
    url = 'https://www.hao123.com/'
    html_byte = get(url)
    print(html_byte)