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

#创建threading.Thread的子类来包装一个线程对象
#coding:utf-8
import threading
import time

class timer(threading.Thread):
    def __init__(self, num, interval):
        threading.Thread.__init__(self)
        self.thread_num = num
        self.interval = interval
        self.thread_stop = False
        
    #Overwrite run() method, put what you want the thread do here
    def run(self):
        while not self.thread_stop:
            print 'Thread object(%d), Time:%s
' %(self.thread_num, time.ctime())
            time.sleep(self.interval)
    def stop(self):
        self.thread_stop = True

def test():
    thread_one = timer(0,1)
    thread_two = timer(2,4)
    thread_one.start()
    thread_two.start()
    time.sleep(5)
    thread_one.stop()
    thread_two.stop()
    return

if __name__ == '__main__':
    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：

#coding:utf-8
import urllib2,random
import threading,time
import sys

#创建线程
class newthread(threading.Thread):
    def __init__(self, startp, end, request):
        threading.Thread.__init__(self)
        self.startp = startp
        self.end = end
        self.request = request
    def run(self):
        #注意使用类的变量时加上self
        self.request.headers['Range'] = 'bytes=%s-%s' %(self.startp, self.end)
        f = urllib2.urlopen(self.request)
        content = f.read()
        write_con(content, self.startp)

#写入本地文件
def write_con(content, position):
    f = open("a.html","r+")
    f.seek(position)
    f.write(content)
    f.close()

#获取下载的文件长度
def get_file_size(request):    
    #request.add_header('Accept_encoding','gzip')

    f = urllib2.urlopen(request)
    #print f.headers.values()
    con_len =  f.headers['content-length']
    return con_len

#分割文件进行随机下载
def multi_download(con_len, request):    
    i = 0    
    #获取文件分块大小
    j = int(con_len) / 10
    #获取无重复随机数
    lst = ['0','1','2','3','4','5','6','7','8','9']
    while i < 10:
        value = random.choice(list(lst))
        r = int(value)
        print r
        start = r*j 
        end = (r+1) * j-1
        if r == 9:
            end = con_len
        nth = newthread(start, end, request)
        nth.start()
    
        i = i+1
        lst.remove(value)    

#读取文件
def read_html():
    f = open('a.html', 'r+')
    print f.read()
    f.close()

if __name__ == '__main__':
    #获取下载链接
    url = sys.argv[1]
    handler = urllib2.HTTPHandler()
    request = urllib2.Request(url)
    #获取文件大小
    con_len = get_file_size(request)
    #多线程下载
    multi_download(con_len, request)
    #读取文件
    read_html()