Python 爬取淘帖里的帖子标题（1）

qiuyouzhi

Python 爬取淘帖里的帖子标题

1. from requests import get
   
2. from bs4 import BeautifulSoup as BS
   
3. 
   
4. def get_Tz(res):
   
5.     soup = BS(res.text, "html.parser")
   
6.     targ = soup.find_all("a",class_="xst", target="_blank")
   
7.     for each in targ:
   
8.         print(each.text)
   
9.         #print(each['title'])
   
10.         print(each['href'])
    
11. 
    
12. def get_Tz_write(res, f):
    
13.     soup = BS(res.text, "html.parser")
    
14.     targ = soup.find_all("a",class_="xst", target="_blank")
    
15.     for each in targ:
    
16.         f.write(each.text)
    
17.         f.write(each['href'])
    
18.         f.write('\n')
    
19. 
    
20. def main():
    
21.     n = int(input("请输入要下载的次数："))
    
22.     f = open("淘帖.txt", "w")
    
23. 
    
24.     for i in range(1,n):
    
25.         url = "https://fishc.com.cn/forum.php?mod=collection&action=view&ctid=%d" % i
    
26.         res = get(url)
    
27.         get_Tz_write(res, f)
    
28.     f.close()
    
29. 
    
30. if __name__ == "__main__":
    
31.     main()

复制代码

有时候会报错，是正常现象，重新运行就好

不要爬太多哦~