堆糖爬虫

shiyouroc

因为，本人能力问题爬图片不能怕全。
而且，也没有多线程。

1. from urllib.request import *
   
2. import random
   
3. import os
   
4. from urllib.error import *
   
5. import re
   
6. import time
   
7. f_img = []
   
8. url = input('请输入网址')
   
9. head ={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.5112.48 Safari/537.36 Edg/104.0.1293.25'}
   
10. html = None
    
11. 
    
12. def get_html(url):
    
13.     global html
    
14.     url =url
    
15.     head ={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.5112.48 Safari/537.36 Edg/104.0.1293.25'}
    
16.     req = Request(url,None,head)
    
17.     response = urlopen(req)
    
18.     html = response.read().decode('utf-8')
    
19.    
    
20. 
    
21. 
    
22. def find_img():
    
23.     global html
    
24.     global f_img
    
25.    
    
26.     while True:
    
27.         
    
28.         
    
29.         xx = re.search(r'data-iid="" src="*"',html)
    
30.         yy = re.search(r'thumb\.400_0\.jpg" height',html)
    
31.         
    
32.         if yy == None:
    
33.             break;
    
34.         else:
    
35.             xxx = str(yy)
    
36.             xxx = xxx[24:28]
    
37.             yyy = str(xx)
    
38.             yyy = yyy[30:34]
    
39.             yyy = int(yyy)
    
40.             xxx = int(xxx)
    
41.             xxx = xxx+15
    
42.             y = html[yyy:xxx]
    
43.             print(y)
    
44.             savemm(y,y)
    
45.             html = html[xxx:]
    
46. 
    
47. def savemm(url,y):
    
48.     y = url[50:86]
    
49.     y = y+str(time.time())
    
50.     y = y+'.jpg'
    
51.     try:
    
52.         url = url
    
53.         iplist = ['58.221.154.46:9091','112.14.40.137:9091','223.94.85.131:9091','120.237.144.200:9091','183.222.217.168:9091','123.180.189.135:9091','222.179.155.90:9091','183.239.62.251:9091','221.181.238.59:9091','112.14.40.137:9091','59.56.142.185:9091','222.77.85.15:9091']
    
54.         head ={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.5112.48 Safari/537.36 Edg/104.0.1293.25'}
    
55.         x = random.choice(iplist)
    
56.         proxy_support = ProxyHandler({'http':x})
    
57.         opener = build_opener(proxy_support)
    
58.         opener.addheaders = [('User-Agent', 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.65 Safari/537.36')]
    
59.         install_opener(opener)
    
60.         response = urlopen(url)
    
61.         html = response.read()
    
62.         
    
63.         with open(y,'wb') as f:
    
64.             f.write(html)
    
65.             f.close()
    
66.     except:
    
67.         savemm(url,y)
    
68.         
    
69.         
    
70.    
    
71.         
    
72. 
    
73. get_html(url)
    
74. 
    
75. find_img()
    

复制代码