import requests
import re
import os
import time
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.125 Safari/537.36'}
name = '切割机'
num = 0
x =10 #input('您要爬取几张呢?,输入1等于60张图片。')
for i in range(int(x)):
name_1 =r'D:\object\PycharmProjects\aiproess\speader\bauduword\imgs'#图片保存地址
url = 'https://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word='+name+'&pn='+str(i*30)
res = requests.get(url,headers=headers)
htlm_1 = res.content.decode()
a = re.findall('"objURL":"(.*?)",',htlm_1)
if not os.path.exists(name_1):
os.makedirs(name_1)
for b in a:
num = num +1
try:
img = requests.get(b)
except Exception as e:
print('第'+str(num)+'张图片无法下载------------')
print(str(e))
continue
f = open(name_1+'/'+name+str(num)+'.jpg','ab')
print('---------正在下载第'+str(num)+'张图片----------')
f.write(img.content)
f.close()
print('下载完成')
电脑系统是windows10
<切割机>就是我们要爬取的关键字,图片保存<D:\object\PycharmProjects\aiproess\speader\bauduword\imgs>地址注意按自己需要更改
注意别爬取太多,会被封的!