python学习（七）

得到不重复的随机数字的方法，如下所示，建立一个列表，将需要生成的随机数字放在列表中，然后随机选出一个，同时将选出的数字移出列表：

lst = ['0','1','2','3','4','5','6','7','8','9']
value = random.choice(list(lst))
r = int(value)
lst.remove(value)

多线程下载

先来学习一下多线程的创建方式，我们创建threading.Thread的子类来包装一个线程对象

 1 #创建threading.Thread的子类来包装一个线程对象
 2 #coding:utf-8
 3 import threading
 4 import time
 5 
 6 class timer(threading.Thread):
 7     def __init__(self, num, interval):
 8         threading.Thread.__init__(self)
 9         self.thread_num = num
10         self.interval = interval
11         self.thread_stop = False
12         
13     #Overwrite run() method, put what you want the thread do here
14     def run(self):
15         while not self.thread_stop:
16             print 'Thread object(%d), Time:%s
' %(self.thread_num, time.ctime())
17             time.sleep(self.interval)
18     def stop(self):
19         self.thread_stop = True
20 
21 def test():
22     thread_one = timer(0,1)
23     thread_two = timer(2,4)
24     thread_one.start()
25     thread_two.start()
26     time.sleep(5)
27     thread_one.stop()
28     thread_two.stop()
29     return
30 
31 if __name__ == '__main__':
32     test()

多线程下载

我们把需要下载的文件分成10部分，每部分起一个线程进行下载，具体代码如下：

 1 #coding:utf-8
 2 import urllib2,random
 3 import threading,time
 4 import sys
 5 
 6 #创建线程
 7 class newthread(threading.Thread):
 8     def __init__(self, startp, end, request):
 9         threading.Thread.__init__(self)
10         self.startp = startp
11         self.end = end
12         self.request = request
13     def run(self):
14         #注意使用类的变量时加上self
15         self.request.headers['Range'] = 'bytes=%s-%s' %(self.startp, self.end)
16         f = urllib2.urlopen(self.request)
17         content = f.read()
18         write_con(content, self.startp)
19 
20 #写入本地文件
21 def write_con(content, position):
22     f = open("a.html","r+")
23     f.seek(position)
24     f.write(content)
25     f.close()
26 
27 #获取下载的文件长度
28 def get_file_size(request):    
29     #request.add_header('Accept_encoding','gzip')
30 
31     f = urllib2.urlopen(request)
32     #print f.headers.values()
33     con_len =  f.headers['content-length']
34     return con_len
35 
36 #分割文件进行随机下载
37 def multi_download(con_len, request):    
38     i = 0    
39     #获取文件分块大小
40     j = int(con_len) / 10
41     #获取无重复随机数
42     lst = ['0','1','2','3','4','5','6','7','8','9']
43     while i < 10:
44         value = random.choice(list(lst))
45         r = int(value)
46         print r
47         start = r*j 
48         end = (r+1) * j-1
49         if r == 9:
50             end = con_len
51         nth = newthread(start, end, request)
52         nth.start()
53     
54         i = i+1
55         lst.remove(value)    
56 
57 #读取文件
58 def read_html():
59     f = open('a.html', 'r+')
60     print f.read()
61     f.close()
62 
63 if __name__ == '__main__':
64     #获取下载链接
65     url = sys.argv[1]
66     handler = urllib2.HTTPHandler()
67     request = urllib2.Request(url)
68     #获取文件大小
69     con_len = get_file_size(request)
70     #多线程下载
71     multi_download(con_len, request)
72     #读取文件
73     read_html()