[已解决]求助 这是怎么回事啊，怎么解决

白泽、

import urllib.request
import os

def url_open(url):
   
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36 Edg/98.0.1108.62')
    response = urllib.request.urlopen(url)
    html = response.read()
    return html

def get_page(url):
   
    html = url_open(url).decode('utf-8')
   

    a = html.find('current-comment-page')+23
    b = html.find(']',a)

    return html[a:b]

def find_imgs(url):
   
    html = url_open(url).decode('utf-8')
    img_addrs = []

    a = html.find('img src=')

    while a != -1:
        b = html.find('.jpg',a,a+255)
        if b != -1:
            img_addrs.append(html[a+9:b+4])
        else:
            b = a + 9

        a = html.find('img src=',b)
    return img_addrs

def save_imgs(folder,img_addrs):
    for each in img_addrs:
        filename = each.split('/')[-1]
        with open(folder,'wb') as f:
            img = url_open(each)
            f.write(img)

def download_mm(folder='OOXX',pages=10):
   
    os.mkdir(folder)
    os.chdir(folder)

    url ='http://jiandan.net/girl/'
    page_num = int(get_page(url))

    for i in range(pages):
        page_num -= i
        page_url = url+str(page_num)+'#commen'
        img_addrs = find_imgs(page_url)
        save_imgs(folder,img_addrs)

if __name__ == '__main__':
    download_mm()

最佳答案

月排行榜 / 总排行榜

isdkz

2022-3-4 20:53:20

1. 
   
2. import urllib.request
   
3. import os
   
4. 
   
5. def url_open(url):
   
6.    
   
7.     req = urllib.request.Request(url)
   
8.     req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36 Edg/98.0.1108.62')
   
9.     response = urllib.request.urlopen(url)
   
10.     html = response.read()
    
11.     return html
    
12. 
    
13. def get_page(url):
    
14.    
    
15.     html = url_open(url).decode('utf-8')
    
16.    
    
17. 
    
18.     a = html.find('current-comment-page')+23
    
19.     b = html.find(']',a)
    
20. 
    
21.     return html[a:b]
    
22. 
    
23. def find_imgs(url):
    
24.    
    
25.     html = url_open(url).decode('utf-8')
    
26.     img_addrs = []
    
27. 
    
28.     a = html.find('img src=')
    
29. 
    
30.     while a != -1:
    
31.         b = html.find('.jpg',a,a+255)
    
32.         if b != -1:
    
33.             img_addrs.append(html[a+9:b+4])
    
34.         else:
    
35.             b = a + 9
    
36. 
    
37.         a = html.find('img src=',b)
    
38.     return img_addrs
    
39. 
    
40. def save_imgs(folder,img_addrs):
    
41.     for each in img_addrs:
    
42.         print(each)
    
43.         filename = each.split('/')[-1]
    
44.         with open(filename,'wb') as f:         # 这里改成 filename
    
45. 
    
46.             img = url_open("http:" + each)     # 这里加个 http:
    
47.             f.write(img)
    
48. 
    
49. def download_mm(folder='OOXX',pages=10):
    
50.     if not os.path.exists(folder):               # 这里先判断一下指定的文件夹是否存在，不存在再新建
    
51.         os.mkdir(folder)
    
52.     os.chdir(folder)
    
53. 
    
54.     url ='http://jiandan.net/girl/'
    
55.     page_num = int(get_page(url))
    
56. 
    
57.     for i in range(pages):
    
58.         page_num -= i
    
59.         page_url = url+str(page_num)+'#commen'
    
60.         img_addrs = find_imgs(page_url)
    
61.         save_imgs(folder, img_addrs)      
    
62. 
    
63. if __name__ == '__main__':
    
64.     download_mm()

复制代码

跳转到最佳答案楼层

isdkz

占楼

isdkz

1. 
   
2. import urllib.request
   
3. import os
   
4. 
   
5. def url_open(url):
   
6.    
   
7.     req = urllib.request.Request(url)
   
8.     req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36 Edg/98.0.1108.62')
   
9.     response = urllib.request.urlopen(url)
   
10.     html = response.read()
    
11.     return html
    
12. 
    
13. def get_page(url):
    
14.    
    
15.     html = url_open(url).decode('utf-8')
    
16.    
    
17. 
    
18.     a = html.find('current-comment-page')+23
    
19.     b = html.find(']',a)
    
20. 
    
21.     return html[a:b]
    
22. 
    
23. def find_imgs(url):
    
24.    
    
25.     html = url_open(url).decode('utf-8')
    
26.     img_addrs = []
    
27. 
    
28.     a = html.find('img src=')
    
29. 
    
30.     while a != -1:
    
31.         b = html.find('.jpg',a,a+255)
    
32.         if b != -1:
    
33.             img_addrs.append(html[a+9:b+4])
    
34.         else:
    
35.             b = a + 9
    
36. 
    
37.         a = html.find('img src=',b)
    
38.     return img_addrs
    
39. 
    
40. def save_imgs(folder,img_addrs):
    
41.     for each in img_addrs:
    
42.         print(each)
    
43.         filename = each.split('/')[-1]
    
44.         with open(filename,'wb') as f:         # 这里改成 filename
    
45. 
    
46.             img = url_open("http:" + each)     # 这里加个 http:
    
47.             f.write(img)
    
48. 
    
49. def download_mm(folder='OOXX',pages=10):
    
50.     if not os.path.exists(folder):               # 这里先判断一下指定的文件夹是否存在，不存在再新建
    
51.         os.mkdir(folder)
    
52.     os.chdir(folder)
    
53. 
    
54.     url ='http://jiandan.net/girl/'
    
55.     page_num = int(get_page(url))
    
56. 
    
57.     for i in range(pages):
    
58.         page_num -= i
    
59.         page_url = url+str(page_num)+'#commen'
    
60.         img_addrs = find_imgs(page_url)
    
61.         save_imgs(folder, img_addrs)      
    
62. 
    
63. if __name__ == '__main__':
    
64.     download_mm()

复制代码

白泽、

isdkz 发表于 2022-3-4 20:53

谢谢大佬！！！