爬虫--函数的封装

最新推荐文章于 2024-03-30 18:35:16 发布

J__333

最新推荐文章于 2024-03-30 18:35:16 发布

阅读量345

点赞数

分类专栏：程序人生文章标签：爬虫 python 封装函数

本文链接：https://blog.csdn.net/J__333/article/details/81637672

版权

程序人生专栏收录该内容

14 篇文章 0 订阅

订阅专栏

from urllib import request,parse
from urllib.error import HTTPError,URLError
def get(url,headers=None):
    return urlrequests(url,headers=headers)
def post(url,form,headers=None):
    return urlrequests(url,form,headers=headers)
#1.传入url
#2.uesr_agent
#3.headers
#4.定义Request
#5.urlopen
#6.返回byte数组
def urlrequest == 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'
    # 如果用户需要自行传入headers,则覆盖之前的headers
    if headers == None:
        headers = {
            'User-Agent':user_agent 
        }
    html_bytes = b''
    try:
        if form:
            #POST
            #2.1转化成str
            form_str = parse.urlencode(form)
            #print(form_str)
            #2.2转化成bytes
            form_bytes = form_str.encode('utf-8')
            req = request.Request(url,data=form_bytes,headers=headers)
        else:
            req = request.Request(url,headers=headers)
        response = request.urlopen(req)
        html_bytes = response.read()
    except HTTPError as e:
        print(e)
    except URLError as e:
        print(e)
    return html_bytes
if __name__ == '__main__':
    #url = 'http://fanyi.baidu.com/jjj'
    #form = {
        'kw':'你好'
    }
    #html_bytes = post(url,form=form)
    #print(html_bytes)

    url = 'http://www.baidu.com'
    html_byte = get(url)
    print(html_byte)