爬淘宝店铺MM的头像图片

Posted 2020-10-18 jiangxiaochuan

别的不多说，直接上代码：

 

#!usr/bin/python3
# -*-coding:UTF-8 -*-

import requests
import re
from collections import deque

url=‘‘
header={

    ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/58.0.3029.110 Safari/537.36 Edge/16.16299‘

}
post_data={

}
cookies={}


queue=deque()
set=set()

def Get_one_page(num = 0):

    for i in list(range(1,10000)):
        url=‘https://mm.taobao.com/json/request_top_list.htm?page=‘+str(i)
        print(url,end=‘\t‘)
        try:
            response=requests.get(url,headers=header,verify=False,timeout=2000)
        except:
            continue

        demo=re.compile(‘<img.*?src="(.*?\.[jpgn]{3})".*?>‘,flags=0)
        Img_src_list=re.findall(demo,response.content.decode(‘gbk‘))

        for src in Img_src_list:
            src=‘http:‘+src

            try:
                bin = requests.get(src).content
            except:
                continue
            num += 1
            path = ‘F:\\图片\\淘宝客服图片‘ + ‘\\\\‘ + str(num) + ‘.jpg‘

            with open(path, ‘wb+‘) as fp:
                fp.write(bin)
        print(‘已取得%d张图片‘%num)


if __name__==‘__main__‘:


    Get_one_page()