爬虫爬取美图录的套图【可以自动生成对应文件夹】

huole

1. import urllib.request
   
2. import os
   
3. import re
   
4. import random
   
5. 
   
6. def url_open(url):
   
7.     headers = {
   
8.         'Referer': 'https://www.meitulu.com/',
   
9.         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.162 Safari/537.36'
   
10.     }
    
11.     req = urllib.request.Request(url, headers=headers)
    
12.     response = urllib.request.urlopen(req)
    
13.     html = response.read().decode('utf-8')
    
14.     return html
    
15. 
    
16. 
    
17. def get_album(url):
    
18.     html = url_open(url)
    
19.     album1 = re.findall(r'https://www.meitulu.com/item/\d{1,5}.html', html)
    
20.     album = set(album1)
    
21.     #print(album)
    
22.     return album
    
23. 
    
24. def get_img_addrs(each,pages):
    
25.     html1 = url_open(each)
    
26.     img_1 = set(re.findall(r'https://mtl.gzhuibei.com/images/img/\d{1,5}/1.jpg', html1))
    
27.     #print(str(img_1)[2:-7])
    
28.     img_addrs = []
    
29.     for i in range(1,pages):
    
30.         addrs = str(img_1)[2:-7] + str(i) + '.jpg'
    
31.         img_addrs.append(addrs)
    
32.     #print(img_addrs)
    
33.     return img_addrs
    
34. 
    
35. def find_pages(each):
    
36.     html1 = url_open(each)
    
37.     title_add1 = re.search(r'<h1>', html1)
    
38.     title_add2 = re.search(r'</h1>', html1)
    
39.     # print(title_add1.span(),title_add2.span())
    
40.     title = html1[title_add1.span()[1]:title_add2.span()[0]]
    
41.     p = re.findall(r'图片数量： \d\d 张', html1)
    
42.     print(title,p)
    
43.     page = re.findall(r'\d\d', str(p))
    
44.     #print(page)
    
45.     page.append('1')
    
46.     pages = int(max(page))
    
47.     return pages,title
    
48. 
    
49. 
    
50. urllist = ['https://www.meitulu.com/','https://www.meitulu.com/t/yingsihui-wings/','https://www.meitulu.com/t/bomb.tv/','https://www.meitulu.com/t/wpb-net/',
    
51.            'https://www.meitulu.com/t/qingdouke/','https://www.meitulu.com/t/tuigirl/','https://www.meitulu.com/t/xiuren/','https://www.meitulu.com/t/1371/',
    
52.            'https://www.meitulu.com/t/imiss/','https://www.meitulu.com/t/dianannan/','https://www.meitulu.com/t/youwuguan/','https://www.meitulu.com/t/yunvlang/']
    
53. url = random.choice(urllist)
    
54. path = 'D:\python\learn'
    
55. 
    
56. album = get_album(url)
    
57. for each in album:
    
58. 
    
59.     count = 1
    
60.     pages,title = find_pages(each)
    
61.     folder = title
    
62.     os.chdir('D:\python\learn')
    
63.     os.mkdir(folder)
    
64.     os.chdir(folder)
    
65.     img_addrs = get_img_addrs(each,pages)
    
66.     for each1 in img_addrs:
    
67.         headers = {
    
68.             'Referer': 'https://www.meitulu.com/',
    
69.             'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.162 Safari/537.36'
    
70.         }
    
71.         req2 = urllib.request.Request(each1, headers=headers)
    
72.         response2 = urllib.request.urlopen(req2)
    
73.         mm_img = response2.read()
    
74. 
    
75.         filename = str(count)+'.jpg'
    
76.         print('下载第' + str(count) + '张图片')
    
77.         with open(filename, 'wb') as f:
    
78.             f.write(mm_img)
    
79.             count += 1
    

复制代码

huole

第62行要改成自己代码文件存在的文件夹路径

丶小小少年

大哥请收下我的膝盖