python爬虫基础函数的封装

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

封装get（）请求

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

封装post（）请求

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

定义一个 urlrquests 函数

def urlrequests(url,form = None,headers = None):
    #发送请求头
    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heakers，则覆盖之前的heakers
    if headers == None:
        headers = {
            'User-Agent':user_agent
        }
    html_bytes = b''
    try:
        if form:
            #post
            #转换成str
            form_str = parse.urlencode(form)
            #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:
        print(e)
    except URLError as e:
        print(e)

    return html_bytes

if __name__ == '__main__':

#1. 传入url

 #url = 'http://fanyi.baidu.com/sug'
 # url = 'http://www.baidu.com'
             ...
             ...
             ...

#2. user_agent

#3. headers

#4. 定义Request

#5. urlopen

#6. 返回byte数组

url = 'http://fanyi.baidu.com/sug'
    form = {
        'kw':'美味的'
    }
    req = urlrequests(url,form=form)
    req_dict = json.loads(req)['data'][0]['v']
    print(req_dict)


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