Python多线程下载文件实例代码

发布时间:2020-09-07编辑:脚本学堂
本文介绍了python多线程下载文件的一例代码,python实现简单的多线程下载,各个线程将自己下载的文件块保存为临时文件,所有线程都完成后,再将这些临时文件按顺序聚合写入到最终的一个文件中。

python实现多线程下载文件

实现多线程下载,注意几点:
1,文件的大小:可以从reponse header中提取,如“Content-Length:911”表示大小是911字节
2,任务拆分:指定各个线程下载的文件的哪一块,可以通过request header中添加“Range: bytes=300-400”(表示下载300~400byte的内容).
注意,可以请求的文件的range是[0, size-1]字节的。
3,下载文件的聚合:各个线程将自己下载的文件块保存为临时文件,所有线程都完成后,再将这些临时文件按顺序聚合写入到最终的一个文件中。

代码:
 

复制代码 代码示例:

#!/usr/bin/python
# -*- coding: utf-8 -*-
# filename: paxel.py
# FROM: http://jb200.com/code/view/58/full/
# Jay modified it a little and save for further potential usage.

'''It is a multi-thread downloading tool

    It was developed following axel.
        Author: volans
        E-mail: volansw [at] gmail.com
'''

import sys
import os
import time
import urllib
from threading import Thread

# in case you want to use http_proxy
local_proxies = {'http': 'http://131.139.58.200:8080'}

class AxelPython(Thread, urllib.FancyURLopener):
    '''Multi-thread downloading class.

        run() is a vitural method of Thread.
    '''
    def __init__(self, threadname, url, filename, ranges=0, proxies={}):
        Thread.__init__(self, name=threadname)
        urllib.FancyURLopener.__init__(self, proxies)
        self.name = threadname
        self.url = url
        self.filename = filename
        self.ranges = ranges
        self.downloaded = 0

    def run(self):
        '''vertual function in Thread'''
        try:
            self.downloaded = os.path.getsize(self.filename)
        except OSError:
            #print 'never downloaded'
            self.downloaded = 0

        # rebuild start poind
        self.startpoint = self.ranges[0] + self.downloaded

        # This part is completed
        if self.startpoint >= self.ranges[1]:
            print 'Part %s has been downloaded over.' % self.filename
            return

        self.oneTimeSize = 16384  # 16kByte/time
        print 'task %s will download from %d to %d' % (self.name, self.startpoint, self.ranges[1])

        self.addheader("Range", "bytes=%d-%d" % (self.startpoint, self.ranges[1]))
        self.urlhandle = self.open(self.url)

        data = self.urlhandle.read(self.oneTimeSize)
        while data:
            filehandle = open(self.filename, 'ab+')
            filehandle.write(data)
            filehandle.close()

            self.downloaded += len(data)
            #print "%s" % (self.name)
            #progress = u'r...'

            data = self.urlhandle.read(self.oneTimeSize)

def GetUrlFileSize(url, proxies={}):
    urlHandler = urllib.urlopen(url, proxies=proxies)
    headers = urlHandler.info().headers
    length = 0
    for header in headers:
        if header.find('Length') != -1:
            length = header.split(':')[-1].strip()
            length = int(length)
    return length

def SpliteBlocks(totalsize, blocknumber):
    blocksize = totalsize / blocknumber
    ranges = []
    for i in range(0, blocknumber - 1):
        ranges.append((i * blocksize, i * blocksize + blocksize - 1))
    ranges.append((blocksize * (blocknumber - 1), totalsize - 1))

    return ranges

def islive(tasks):
    for task in tasks:
        if task.isAlive():
            return True
    return False

def paxel(url, output, blocks=6, proxies=local_proxies):
    ''' paxel
    '''
    size = GetUrlFileSize(url, proxies)
    ranges = SpliteBlocks(size, blocks)

    threadname = ["thread_%d" % i for i in range(0, blocks)]
    filename = ["tmpfile_%d" % i for i in range(0, blocks)]

    tasks = []
    for i in range(0, blocks):
        task = AxelPython(threadname[i], url, filename[i], ranges[i])
        task.setDaemon(True)
        task.start()
        tasks.append(task)

    time.sleep(2)
    while islive(tasks):
        downloaded = sum([task.downloaded for task in tasks])
        process = downloaded / float(size) * 100
        show = u'rFilesize:%d Downloaded:%d Completed:%.2f%%' % (size, downloaded, process)
        sys.stdout.write(show)
        sys.stdout.flush()
        time.sleep(0.5)

    filehandle = open(output, 'wb+')
    for i in filename:
        f = open(i, 'rb')
        filehandle.write(f.read())
        f.close()
        try:
            os.remove(i)
            pass
        except:
            pass

    filehandle.close()

if __name__ == '__main__':
    url = 'http://dldir1.qq.com/qqfile/QQforMac/QQ_V3.1.1.dmg'
    output = 'download.file'
    paxel(url, output, blocks=4, proxies={})