爬虫基本的get获取和post百度翻译

---

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

    #get 方法请求函数
def get(url,hearders=None):
    return urlrequests(url,headers=hearders)


def post(url,form,hearders=None):
    #post 方法函数
    return urlrequests(url,form=form,headers=hearders)






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'
    #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
            #将数据转换位str
            from_str = parse.urlencode(form)
            #转换为bytes
            form_bytes = from_str.encode('utf-8')
            response = request.Request(url,data=form_bytes,headers=headers)
            response = request.urlopen(response)
            #转unicode码方便显示
            res_dict = json.loads(response.read().decode('utf-8'))

            k = [i['k']+i['v'] for i in res_dict['data']]
            return k

                # result_1 = res_dict['data'][0]['k']
            # result = res_dict['data'][0]['v']
            #
            # result = form['kw']+' : '+result_1 + result



        else:
            #GET
            req = request.Request(url,headers=headers)
        response = request.urlopen(req)
        # 转unicode码方便显示
        html_bytes = response.read().decode('utf-8')
    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':'马'
    }
    html_bytes = post(url,form=form)
    for i in html_bytes:
        print(i)



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