• python多线程threading下载示例


    #coding:utf-8
    
    # windows中测试不通过,下载的图片不完整
    # 通过多线程下载图片
    
    import requests
    import threading
    
    class downloader(object):
        def __init__(self):
            # self.url = 'http://f1.topitme.com/1/eb/96/112730204208796eb1o.jpg'
            # mysql source package
            # self.url = 'http://mirrors.sohu.com/mysql/MySQL-5.6/mysql-5.6.35.tar.gz'
            # yangmi
            self.url = 'https://imgsa.baidu.com/baike/c0%3Dbaike116%2C5%2C5%2C116%2C38/sign=18d31e2c6c380cd7f213aabfc02dc651/2e2eb9389b504fc27dcf5199ecdde71191ef6d9e.jpg'
            
            # self.name = 'mysql-5.6.35.tar.gz'
            self.name = 'yangmi.jpg'
            self.num = 5
    
    
        def get_img(self, r):
            # 获取图片的分段位置,并记录seek值(分段后的起始位置)开始写入系统
            _request = requests.get(self.url, headers = {'Range':'bytes=%s-%s' % r})
            self.fd.seek(r[0])
            self.fd.write(_request.content)
            print 'success %s-%s' % r
    
        def get_range(self):
            r = requests.head(self.url)
            headers = r.headers
            # 获取图片的大小
            image_size = int(headers['Content-Length'])
            # print [image_size]
            # 分为5段(即开启5个线程下载图片)
            offset = image_size / self.num
            print image_size
            range_list = []
    
            # 将图片分为 num(5)段
            for i in range(self.num):
                if i == self.num - 1:
                    range_list.append((offset*i, ''))
                else:
                    range_list.append((offset*i, offset*(i + 1)))
            return range_list
    
    
        def download(self):
            range_list = self.get_range()
            self.fd = open(self.name, 'w')
            n = 0
            ths = []
            # 创建线程
            for r in range_list:
                # self.get_img(r)
                # 开启多线程下载
                th = threading.Thread(target=self.get_img(r), args = r)
                th.start()
                print 'thread%d' % n
                n += 1
                ths.append(th)
                
            # 线程等待
            for r in ths:
                r.join()  
    
            self.fd.close()
            print 'download success'
    
    
    if __name__ == "__main__":
        d = downloader()
        d.download()

    普通分段下载

    #coding:utf-8
    
    # windows中测试不通过,下载的图片不完整
    # 分段下载图片
    import requests
    from decimal import Decimal
    
    class downloader(object):
        def __init__(self):
            self.url = 'https://ss2.baidu.com/6ONYsjip0QIZ8tyhnq/it/u=4241609126,773789288&fm=173&s=E42EB6570862D211C87C4CEE0300A02A&w=500&h=333&img.JPG'
            # yangmi
            # self.url = 'https://imgsa.baidu.com/baike/c0%3Dbaike116%2C5%2C5%2C116%2C38/sign=18d31e2c6c380cd7f213aabfc02dc651/2e2eb9389b504fc27dcf5199ecdde71191ef6d9e.jpg'
            
            self.name = 'bizhi.jpg'
            self.num = 5
    
        
        def get_img(self, r):
            _request = requests.get(self.url, headers = {'Range':'bytes=%s-%s' % r})
            self.fd.seek(r[0])
            self.fd.write(_request.content)
            print 'success %s-%s' % r
    
        def get_range(self):
            r = requests.head(self.url)
            headers = r.headers
            image_size = int(headers['Content-Length'])
            # print [image_size]
            offset = image_size / self.num
            print image_size
            range_list = []
            for i in range(self.num):
                if i == self.num - 1:
                    range_list.append((offset*i, ''))
                else:
                    range_list.append((offset*i, offset*(i + 1)))
            return range_list
    
    
        def download(self):
            range_list = self.get_range()
            self.fd = open(self.name, 'w')
            for r in range_list:
                self.get_img(r)
    
    
    if __name__ == "__main__":
        d = downloader()
        d.download()
  • 相关阅读:
    gdb常用命令
    gdb之watch命令
    gdb之x命令
    python's descriptor II
    MacOSX快捷键
    主题敏感词PageRank
    shell调试选项
    shell输出调试信息
    事务时间如何去掉wasted time
    深刻剖析VuGen脚本录制原理
  • 原文地址:https://www.cnblogs.com/reblue520/p/8042131.html
Copyright © 2020-2023  润新知