下载斗破苍穹爬虫

hkz

新手做的可能代码有点繁杂

1. import requests
   
2. import time
   
3. import re
   
4. 
   
5. headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.7 Safari/537.36'}
   
6. f=open('E:/doupo.txt','a+')
   
7. 
   
8. def get_info(url):
   
9.     res=requests.get(url,headers=headers)
   
10.     if res.status_code==200:
    
11.         contents=re.findall('<p>(.*?)</p>',res.content.decode('utf-8'),re.S)
    
12.         for content in contents:
    
13.             f.write(content+'\n')
    
14.     else:
    
15.         pass
    
16. 
    
17. if __name__=='__main__':
    
18.     urls=['http://www.doupoxs.com/doupocangqiong/{}.html'.format(str(i)) for i in range(2,1665)]
    
19.     for url in urls:
    
20.         get_info(url)
    
21.         time.sleep(1)
    
22.     f.closse()
    
23. 
    
24. #请勿重复运行，程序运行有点慢需要等

复制代码