[已解决]爬百度贴吧图片,为啥只生成一个文件夹

起风了番茄

1. import urllib.request
   
2. import re
   
3. import os
   
4. def open_url(url):
   
5.     req =urllib.request.Request(url)
   
6.     req.add_header('User-Agent',' Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.74 Safari/537.36 Edg/99.0.1150.46')
   
7.     page = urllib.request.urlopen(req)
   
8.     html = page.read().decode('utf-8')
   
9.     return html
   
10. 
    
11. def get_img(html):
    
12.     p = r'<img class="BDE_Image".*?src="([^"]*\.jpg)".*?>'
    
13.     imglist = re.findall(p,html)
    
14. 
    
15.     try:
    
16.         os.mkdir('NewPics')
    
17.     except FileExistsError:
    
18.         pass
    
19.     os.chdir("NewPics")
    
20.     for each in imglist:
    
21.         filename = each.split("/")[-1]
    
22.         urllib.request.urlretrieve(each,filename,None)
    
23. 
    
24. if __name__ == '__main__':
    
25.     url = 'https://tieba.baidu.com/p/7766911770'
    
26.     get_img(open_url(url))

复制代码

最佳答案

月排行榜 / 总排行榜

isdkz

2022-3-24 18:59:38

正则表达式不对：

1. import urllib.request
   
2. import re
   
3. import os
   
4. def open_url(url):
   
5.     req =urllib.request.Request(url)
   
6.     req.add_header('User-Agent',' Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.74 Safari/537.36 Edg/99.0.1150.46')
   
7.     page = urllib.request.urlopen(req)
   
8.     html = page.read().decode('utf-8')
   
9.     return html
   
10. 
    
11. def get_img(html):
    
12.     p = r'<img class="BDE_Image".*?src="([^"]*\.jpg)[^"]*".*?>'        # 修改了正则表达式
    
13.     imglist = re.findall(p,html)
    
14. 
    
15.     try:
    
16.         os.mkdir('NewPics')
    
17.     except FileExistsError:
    
18.         pass
    
19.     os.chdir("NewPics")
    
20.     for each in imglist:
    
21.         filename = each.split("/")[-1]
    
22.         urllib.request.urlretrieve(each,filename,None)
    
23. 
    
24. if __name__ == '__main__':
    
25.     url = 'https://tieba.baidu.com/p/7766911770'
    
26.     get_img(open_url(url))

复制代码

跳转到最佳答案楼层

isdkz

正则表达式不对：

1. import urllib.request
   
2. import re
   
3. import os
   
4. def open_url(url):
   
5.     req =urllib.request.Request(url)
   
6.     req.add_header('User-Agent',' Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.74 Safari/537.36 Edg/99.0.1150.46')
   
7.     page = urllib.request.urlopen(req)
   
8.     html = page.read().decode('utf-8')
   
9.     return html
   
10. 
    
11. def get_img(html):
    
12.     p = r'<img class="BDE_Image".*?src="([^"]*\.jpg)[^"]*".*?>'        # 修改了正则表达式
    
13.     imglist = re.findall(p,html)
    
14. 
    
15.     try:
    
16.         os.mkdir('NewPics')
    
17.     except FileExistsError:
    
18.         pass
    
19.     os.chdir("NewPics")
    
20.     for each in imglist:
    
21.         filename = each.split("/")[-1]
    
22.         urllib.request.urlretrieve(each,filename,None)
    
23. 
    
24. if __name__ == '__main__':
    
25.     url = 'https://tieba.baidu.com/p/7766911770'
    
26.     get_img(open_url(url))

复制代码

起风了番茄

isdkz 发表于 2022-3-24 18:59
正则表达式不对：

老哥我那个悬赏是跟这个题一样的,你能去答一下,悬赏结算给你吗?

isdkz

起风了番茄 发表于 2022-3-24 19:19
老哥我那个悬赏是跟这个题一样的,你能去答一下,悬赏结算给你吗?

那谢谢啦！