python写的百度图片爬虫

 1 #/usr/bin/env python
 2 #Guoyabin
 3 #-*- coding:utf-8 -*-
 4 import re,os
 5 import requests
 6 
 7 keyword=input(‘请输入搜索关键词:‘)
 8 os.chdir(‘C:\\Users\\Administrator\\Desktop\\‘)
 9 if os.path.exists(keyword) ==False:
10     os.mkdir(keyword)
11 os.chdir(keyword)
12 
13 page_begin=input(‘从第几页开始搜索,回车从第一页开始:‘)
14 if len(page_begin)==0:
15     baidupn=0
16 else:
17     baidupn=page_begin*20
18 
19 num=1
20 for i in range(50):
21     url=‘https://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8‘
22     payload={‘word‘:keyword,‘pn‘:baidupn}
23     html = requests.get(url,params=payload).text
24     regular=‘"objURL":"(.*?)",‘
25     pic=re.findall(regular,html)
26     baidupn+=20
27 
28     for tu in pic:
29         try:
30             dl=requests.get(tu,timeout=60)
31             #pic_name=os.path.basename(tu).split(‘?‘)[0]
32             pic_name=‘%s%s‘ %(num,‘.jpg‘)
33             with open(pic_name,"wb") as code:
34                 code.write(dl.content)
35                 requests.session().keep_alive = False
36                 dl.close()
37             num+=1
38         except requests.exceptions.ConnectionError:
39             print(‘这张图片下载失败了,图片地址‘,tu)
40             continue