机器学习——小白学习Linux（二）爬取并保存图片

 1 import requests
 2 import re
 3 from urllib import request
 4 
 5 
 6 #模拟浏览器获取图片链接
 7 def Get_PIC_list(keyword,max_page):
 8     all_picture_list = []
 9     for page in range(max_page):
10         page = page *30
11         url = ‘https://image.baidu.com/search/flip?tn=baiduimage&ie=utf-8&word={}&pn={}‘.format(keyword, page)
12         html = requests.get(url).content.decode(‘utf-8‘)
13         picture_list = re.findall(‘{"thumbURL":"(.*?)",‘,html)
14         all_picture_list.extend(picture_list)
15 
16     all_picture_list = set(all_picture_list)
17     download_picture(all_picture_list)
18 
19 #下载图片
20 def download_picture(all_picture_list):
21     for i,pic_url in enumerate(all_picture_list):
22         print(i)
23         string = ‘picture/{}.jpg‘.format(str(i + 1))
24         request.urlretrieve(pic_url, string)
25 
26 #开始函数
27 def start():
28     keyword = ‘美食照片‘
29     max_page = 2
30     Get_PIC_list(keyword,max_page)
31 
32 
33 if __name__ == ‘__main__‘:
34     start()