爬虫初级之get,post函数简单封装

最新推荐文章于 2024-03-14 18:40:12 发布

SpringWaterDuckEgg

最新推荐文章于 2024-03-14 18:40:12 发布

阅读量376

点赞数

文章标签：爬虫

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

#a.get(url,headers=None)
def get(rul,headers=None):
    return urlrequests(url,headers=headers)
#b.post(url,form,headers=None)
def post(url,form,headers=None)  :
    return urlrequests(url,form,headers=headers)

#传入URL
#user_agent
#headers
#定义REQUEST
#URLOPEN
#返回byte数组
def urlrequests(url,form=None,headers=None):
    user_agent = 'Mozilla/5.0 (Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
    if headers == None:
        headers = {
            'User-Agent':user_agent
        }
    html_bytes = b''
    try:
        if form:
            # 2.1 转换成tr类型，然后在转换成bytes 类型
            form_str = parse.urlencode(form)
            # print(form_str)
            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/sug'
    # form = {
    #     'kw':'呵呵'
    # }
    # html_bytes = post(url,form=form)
    # print(html_bytes.decode('utf-8'))

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