3.Python爬虫入门_正则表达式(简单例子)

 1 #2019-11-23
 2 import requests
 3 import time
 4 import re #Python正则表达式库
 5 
 6 if __name__=='__main__':
 7     #海量爬取图片数据
 8     #进入网站(一般商业图片素材公司网站版权保护做得比较好,不容易爬取)
 9     #https://www.pexels.com/(该网站图片免费,易于爬取)
10     #搜索关键词<man>,Chrome按下F12查看源码,发现图片链接
11     url_picture='https://www.pexels.com/search/man/'
12     response=requests.get(url=url_picture)
13     with open('./pexels/man.html',mode='w',encoding='utf-8') as fp:
14         fp.write(response.text)
15         print('网页保存成功!')  #保存的html文件中含有多张图片的url地址
16     
17     #所有的数据
18     #<img srcset="https://images.pexels.com/photos/220453/pexels-photo-220453.jpeg?auto=compress&amp;cs=tinysrgb&amp;dpr=1&amp;w=500 1x, 
19     #https://images.pexels.com/photos/220453/pexels-photo-220453.jpeg?auto=compress&amp;cs=tinysrgb&amp;dpr=2&amp;w=500 2x" 
20     #class="photo-item__img" alt="Man Smiling Behind Wall" data-image-width="3476" data-image-height="5214" 
21     #data-big-src="https://images.pexels.com/photos/220453/pexels-photo-220453.jpeg?auto=compress&amp;cs=tinysrgb&amp;h=750&amp;w=1260" 
22     #data-large-src="https://images.pexels.com/photos/220453/pexels-photo-220453.jpeg?auto=compress&amp;cs=tinysrgb&amp;h=650&amp;w=940" 
23     #data-tiny-src="https://images.pexels.com/photos/220453/pexels-photo-220453.jpeg?auto=compress&amp;cs=tinysrgb&amp;dpr=1&amp;w=500" 
24     #data-tiny-srcset="https://images.pexels.com/photos/220453/pexels-photo-220453.jpeg?auto=compress&amp;cs=tinysrgb&amp;dpr=1&amp;w=500 1x, 
25     #https://images.pexels.com/photos/220453/pexels-photo-220453.jpeg?auto=compress&amp;cs=tinysrgb&amp;dpr=2&amp;w=500 2x" 
26     #src="https://images.pexels.com/photos/220453/pexels-photo-220453.jpeg?auto=compress&amp;cs=tinysrgb&amp;dpr=1&amp;w=500" >
27     
28     #该正则获取小括号内内容 (.*?)  .表示任意字符,*表示匹配多个,?表示遇到"就停下来(非贪婪模式)
29     num_name=1
30     html=response.text
31     pattern_url=r'<img srcset="(.*?)".*?>'  # r'':非转义的原始字符串
32     pattern_img_name=r'pexels-photo-(.*?).jpeg'
33     img_urls=re.findall(pattern_url,html) #得到的是一个list,里面是str元素,这些元素是匹配到的图片url
34     print(img_urls)
35     for img_url in img_urls:
36         response=requests.get(img_url)
37         content=response.content
38         #img_name=re.findall(pattern_img_name,img_url) #该网站srcset内有两条可用的url,所以匹配后会有两条相同的name
39         with open('./Pexels/'+str(num_name)+'.jpg','wb') as fp:
40             fp.write(content)
41             print(str(num_name)+'号图片下载成功!')
42             num_name+=1
43         time.sleep(0.1) #设置时间延迟 1s
44         
45     #Python 文件读写 
46     #open(文件地址,读写方式,编码方式),
47     #读写方式: 
48     #文本'w' 
49     #图片'wb' 
50
posted on 2019-11-23 22:19 Chenjin123 阅读(616) 评论(0) 编辑收藏举报