单线程爬虫：

import re

import requests

import time

url_EB = 'http://www.amazon.com/gp/search/other/ref=sr_sa_p_4?me=A22XNR713HGDVG&rh=n%3A9063592011%2Ck%3Aprojector&bbn=9063592011&keywords=projector&pickerToList=brandtextbin&ie=UTF8&qid=1461902521'

headers_EB = {'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.86 Safari/537.36'}

url_AML = '''https://www.amazon.com/gp/search/other/ref=sr_sa_p_4?me=A3UJI9WWE6PRP5&rh=i%3Amerchant-items

&pickerToList=brandtextbin&ie=UTF8&qid=1461899728'''

headers_AML ={'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.86 Safari/537.36'}

url_DL= 'https://www.amazon.com/gp/search/other/ref=sr_sa_p_4?me=AS7ZU4MN0FPOY&rh=i%3Amerchant-items&pickerToList=brandtextbin&ie=UTF8&qid=1461901862'

headers_DL = {'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.86 Safari/537.36'}

name = {'a':'ExclusiveBulbs',

        'b':'Amazing Lamps',

        'c':'Dynamic Lamps'}

# listing_count = re.findall('<span class="narrowValue">(.*?)</span',data.text)

# f = dict(map(lambda x,y:[x,y],store_name,listing_count))

#

# for k,v in f.items():

#     print(k,v)

def foo_one(url,headers,name):

    print('--------------------------开始爬去{0}at{1}---------------------------'.format(name,time.ctime()))

    response = requests.get(url,headers=headers)

    store_name = re.findall('<span class="refinementLink">(.*?)</span><span class="narrowValue">(.*?)</span',response.text)

    for i in store_name:

        print(i)

    print('--------------------------爬去完毕at{}----------------------------'.format(time.ctime()))

    time.sleep(1)

if __name__ == '__main__':

    foo_one(url_EB,headers_EB,name['a'])

    foo_one(url_AML,headers_AML,name['b'])

    foo_one(url_DL,headers_DL,name['c'])

输出：00:25:33开始，00:26:02结束 耗时29秒

--------------------------开始爬去ExclusiveBulbsatSat Apr 30 00:25:33 2016---------------------------

('A.Shine', ' (97)')

('AmpacElectronics', ' (1,644)')

('AuraBeam', ' (33,084)')

('AWO', ' (1,206)')

('Battery1inc', ' (694)')

('Comoze Lamps', ' (6,172)')

('Compatible Lamp', ' (317)')

('Corgi Lamps', ' (2,124)')

('CTLAMP', ' (3,499)')

('Dell', ' (191)')

('Diamond Lamps', ' (966)')

('Dynamic', ' (4)')

('Eiki', ' (460)')

('ePharos', ' (2,592)')

('Epson', ' (1,456)')

('EREPLACEMENT', ' (115)')

('eReplacements', ' (814)')

('eWo's', ' (120)')

('eWorldlamp', ' (354)')

('FI Lamps', ' (5,707)')

('FL Projector Lamp For Mitsubishi', ' (1)')

('For Epson', ' (3)')

('Generic', ' (9,769)')

('Good Lamp', ' (819)')

('HCDZ', ' (2,746)')

('Hitachi', ' (935)')

('IET Lamps', ' (2,144)')

('InFocus', ' (44)')

('JVC', ' (326)')

('KCL', ' (3,781)')

('Lampedia', ' (618)')

('Lutema', ' (1,956)')

('Mitsubishi', ' (1,006)')

('Mogobe', ' (1,335)')

('MyProjectorLamps', ' (473)')

('NEC', ' (446)')

('Nec Computers', ' (13)')

('Optoma', ' (956)')

('Osram Sylvania', ' (78)')

('Panasonic', ' (820)')

('Philips', ' (7,502)')

('Powerwarehouse', ' (9,971)')

('Projector Lamps World', ' (112)')

('Pureglare', ' (369)')

('Samsung', ' (1,078)')

('Sharp', ' (426)')

('Shopforbattery', ' (2,510)')

('SMART BOARD', ' (66)')

('Sony', ' (990)')

('TVLampsforless', ' (14)')

('Unknown', ' (722)')

--------------------------爬去完毕atSat Apr 30 00:25:57 2016----------------------------

--------------------------开始爬去Amazing LampsatSat Apr 30 00:25:58 2016---------------------------

('AWO', ' (1)')

('Comoze Lamps', ' (2)')

('DNGO', ' (8)')

('Electrified', ' (9)')

('ELECTRIFIED', ' (10)')

('Electrified Discounters', ' (5)')

('ELECTRIFIED LAMPS', ' (1,177)')

('ELECTRIFIED PRINTHEAD', ' (24)')

('ELECTRIFIED PRINTHEADS', ' (2)')

('FI Lamps', ' (2)')

('Generic', ' (34)')

('GloWatt', ' (1)')

('KCL', ' (1)')

('OEM', ' (1)')

('Powerwarehouse', ' (7)')

('SKU', ' (5)')

('Top Lamp', ' (1)')

('Unknown', ' (1)')

('USOM', ' (3)')

--------------------------爬去完毕atSat Apr 30 00:26:00 2016----------------------------

--------------------------开始爬去Dynamic LampsatSat Apr 30 00:26:01 2016---------------------------

('Battery1inc', ' (85)')

('BenQ', ' (237)')

('Buslink', ' (31)')

('Calumet', ' (2)')

('Comoze Lamps', ' (405)')

('CTLAMP', ' (615)')

('Dell', ' (82)')

('Divine Lighting', ' (36)')

('DNGO', ' (63)')

('Dynamic', ' (4)')

('Eiko', ' (140)')

('Electrified', ' (2)')

('ELECTRIFIED LAMPS', ' (24)')

('Electronix Xpress', ' (418)')

('ePharos', ' (502)')

('Epson', ' (631)')

('eReplacements', ' (119)')

('FI Lamps', ' (505)')

('FL Projector Lamp For Mitsubishi', ' (1)')

('G-lamps', ' (43)')

('GE', ' (248)')

('GE Lighting', ' (152)')

('General Electric', ' (53)')

('Generic', ' (1,671)')

('Genie', ' (101)')

('GLAMPS', ' (2)')

('Impact', ' (7)')

('Industrial Lighting Solutions', ' (9)')

('KCL', ' (280)')

('Kodak', ' (1)')

('Lampedia', ' (63)')

('M-Wave', ' (830)')

('Mitsubishi', ' (406)')

('Mitsubishi DLP TV Bulbs', ' (29)')

('Mocpinc', ' (10)')

('MyProjectorLamps', ' (344)')

('Nec', ' (19)')

('Optoma', ' (161)')

('Osram', ' (1,295)')

('Panasonic', ' (245)')

('Philips', ' (988)')

('Powerwarehouse', ' (239)')

('Projector Lamps World', ' (45)')

('Pureglare', ' (107)')

('Samsung', ' (323)')

('ShopJimmy', ' (3)')

('Sony', ' (141)')

('Sylvania', ' (115)')

('Technical Precision', ' (10)')

('Unknown', ' (167)')

('Welch Allyn Compatible', ' (1)')

--------------------------爬去完毕atSat Apr 30 00:26:02 2016----------------------------

多线程：00：32:37开始00:32:39结束 耗时2秒

import re

import requests

import threading

import time

from time import ctime,sleep

url_EB = 'http://www.amazon.com/gp/search/other/ref=sr_sa_p_4?me=A22XNR713HGDVG&rh=n%3A9063592011%2Ck%3Aprojector&bbn=9063592011&keywords=projector&pickerToList=brandtextbin&ie=UTF8&qid=1461902521'

headers_EB = {'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.86 Safari/537.36'}

url_AML = '''https://www.amazon.com/gp/search/other/ref=sr_sa_p_4?me=A3UJI9WWE6PRP5&rh=i%3Amerchant-items

&pickerToList=brandtextbin&ie=UTF8&qid=1461899728'''

headers_AML ={'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.86 Safari/537.36'}

url_DL= 'https://www.amazon.com/gp/search/other/ref=sr_sa_p_4?me=AS7ZU4MN0FPOY&rh=i%3Amerchant-items&pickerToList=brandtextbin&ie=UTF8&qid=1461901862'

headers_DL = {'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.86 Safari/537.36'}

name = {'a':'ExclusiveBulbs',

        'b':'Amazing Lamps',

        'c':'Dynamic Lamps'}

# listing_count = re.findall('<span class="narrowValue">(.*?)</span',data.text)

# f = dict(map(lambda x,y:[x,y],store_name,listing_count))

#

# for k,v in f.items():

#     print(k,v)

def foo_one(url,headers,name):

    print('--------------------------开始爬去{0}at{1}---------------------------'.format(name,time.ctime()))

    response = requests.get(url,headers=headers)

    store_name = re.findall('<span class="refinementLink">(.*?)</span><span class="narrowValue">(.*?)</span',response.text)

    for i in store_name:

        print(i)

    print('--------------------------爬去完毕{0}at{1}----------------------------'.format(name,time.ctime()))

threads = []

t1 = threading.Thread(target=foo_one,args=(url_EB,headers_EB,name['a']))

threads.append(t1)

t2 = threading.Thread(target=foo_one,args=(url_AML,headers_AML,name['b']))

threads.append(t2)

t3 = threading.Thread(target=foo_one,args=(url_DL,headers_DL,name['c']))

threads.append(t3)

if __name__ == '__main__':

    for t in threads:

        t.setDaemon(True)

        t.start()

    t.join()

    print ("all over %s" %ctime())

输出：

--------------------------开始爬去ExclusiveBulbsatSat Apr 30 00:32:37 2016---------------------------

--------------------------开始爬去Amazing LampsatSat Apr 30 00:32:37 2016---------------------------

--------------------------开始爬去Dynamic LampsatSat Apr 30 00:32:37 2016---------------------------

('A.Shine', ' (97)')

('AmpacElectronics', ' (1,645)')

('AuraBeam', ' (33,088)')

('AWO', ' (1,209)')

('Battery1inc', ' (694)')

('Comoze Lamps', ' (6,172)')

('Compatible Lamp', ' (317)')

('Corgi Lamps', ' (2,123)')

('CTLAMP', ' (3,501)')

('Dell', ' (191)')

('Diamond Lamps', ' (966)')

('Dynamic', ' (4)')

('Eiki', ' (457)')

('ePharos', ' (2,592)')

('Epson', ' (1,456)')

('EREPLACEMENT', ' (115)')

('eReplacements', ' (813)')

('eWo's', ' (120)')

('eWorldlamp', ' (354)')

('FI Lamps', ' (5,710)')

('FL Projector Lamp For Mitsubishi', ' (1)')

('For Epson', ' (3)')

('Generic', ' (9,771)')

('Good Lamp', ' (819)')

('HCDZ', ' (2,748)')

('Hitachi', ' (935)')

('IET Lamps', ' (2,137)')

('InFocus', ' (44)')

('JVC', ' (326)')

('KCL', ' (3,783)')

('Lampedia', ' (618)')

('Lutema', ' (1,955)')

('Mitsubishi', ' (1,006)')

('Mogobe', ' (1,336)')

('MyProjectorLamps', ' (473)')

('NEC', ' (450)')

('Nec Computers', ' (13)')

('Optoma', ' (956)')

('Osram Sylvania', ' (78)')

('Panasonic', ' (820)')

('Philips', ' (7,502)')

('Powerwarehouse', ' (9,972)')

('Projector Lamps World', ' (112)')

('Pureglare', ' (369)')

('Samsung', ' (1,078)')

('Sharp', ' (426)')

('Shopforbattery', ' (2,511)')

('SMART BOARD', ' (66)')

('Sony', ' (990)')

('TVLampsforless', ' (14)')

('Unknown', ' (722)')

--------------------------爬去完毕ExclusiveBulbsatSat Apr 30 00:32:38 2016----------------------------

('Battery1inc', ' (85)')

('BenQ', ' (237)')

('Buslink', ' (31)')

('Calumet', ' (2)')

('Comoze Lamps', ' (405)')

('CTLAMP', ' (615)')

('Dell', ' (82)')

('Divine Lighting', ' (36)')

('DNGO', ' (63)')

('Dynamic', ' (4)')

('Eiko', ' (140)')

('Electrified', ' (2)')

('ELECTRIFIED LAMPS', ' (24)')

('Electronix Xpress', ' (418)')

('ePharos', ' (502)')

('Epson', ' (631)')

('eReplacements', ' (119)')

('FI Lamps', ' (505)')

('FL Projector Lamp For Mitsubishi', ' (1)')

('G-lamps', ' (43)')

('GE', ' (248)')

('GE Lighting', ' (152)')

('General Electric', ' (53)')

('Generic', ' (1,671)')

('Genie', ' (101)')

('GLAMPS', ' (2)')

('Impact', ' (7)')

('Industrial Lighting Solutions', ' (9)')

('KCL', ' (280)')

('Kodak', ' (1)')

('Lampedia', ' (63)')

('M-Wave', ' (830)')

('Mitsubishi', ' (406)')

('Mitsubishi DLP TV Bulbs', ' (29)')

('Mocpinc', ' (10)')

('MyProjectorLamps', ' (344)')

('Nec', ' (19)')

('Optoma', ' (161)')

('Osram', ' (1,295)')

('Panasonic', ' (245)')

('Philips', ' (988)')

('Powerwarehouse', ' (239)')

('Projector Lamps World', ' (45)')

('Pureglare', ' (107)')

('Samsung', ' (323)')

('ShopJimmy', ' (3)')

('Sony', ' (141)')

('Sylvania', ' (115)')

('Technical Precision', ' (10)')

('Unknown', ' (167)')

('Welch Allyn Compatible', ' (1)')

--------------------------爬去完毕Dynamic LampsatSat Apr 30 00:32:39 2016----------------------------

all over Sat Apr 30 00:32:39 2016

　　

单线程爬虫VS多线程爬虫的效率对比的更多相关文章

  1. 【Python爬虫实战】多线程爬虫---糗事百科段子爬取

    多线程爬虫:即程序中的某些程序段并行执行,合理地设置多线程,可以让爬虫效率更高糗事百科段子普通爬虫和多线程爬虫分析该网址链接得出:https://www.qiushibaike.com/8hr/pag ...

  2. Java 多线程爬虫及分布式爬虫架构探索

    这是 Java 爬虫系列博文的第五篇,在上一篇 Java 爬虫服务器被屏蔽,不要慌,咱们换一台服务器 中,我们简单的聊反爬虫策略和反反爬虫方法,主要针对的是 IP 被封及其对应办法.前面几篇文章我们把 ...

  3. Java 多线程爬虫及分布式爬虫架构

    这是 Java 爬虫系列博文的第五篇,在上一篇 Java 爬虫服务器被屏蔽,不要慌,咱们换一台服务器 中,我们简单的聊反爬虫策略和反反爬虫方法,主要针对的是 IP 被封及其对应办法.前面几篇文章我们把 ...

  4. python多线程爬虫设计及实现示例

    爬虫的基本步骤分为:获取,解析,存储.假设这里获取和存储为io密集型(访问网络和数据存储),解析为cpu密集型.那么在设计多线程爬虫时主要有两种方案:第一种方案是一个线程完成三个步骤,然后运行多个线程 ...

  5. 抓包分析、多线程爬虫及xpath学习

    1.抓包分析 1.1 Fiddler安装及基本操作 由于很多网站采用的是HTTPS协议,而fiddler默认不支持HTTPS,先通过设置使fiddler能抓取HTTPS网站,过程可参考(https:/ ...

  6. python爬虫之多线程、多进程+代码示例

    python爬虫之多线程.多进程 使用多进程.多线程编写爬虫的代码能有效的提高爬虫爬取目标网站的效率. 一.什么是进程和线程 引用廖雪峰的官方网站关于进程和线程的讲解: 进程:对于操作系统来说,一个任 ...

  7. c#中@标志的作用 C#通过序列化实现深表复制 细说并发编程-TPL 大数据量下DataTable To List效率对比 【转载】C#工具类：实现文件操作File的工具类 异步多线程 Async .net 多线程 Thread ThreadPool Task .Net 反射学习

    c#中@标志的作用   参考微软官方文档-特殊字符@,地址 https://docs.microsoft.com/zh-cn/dotnet/csharp/language-reference/toke ...

  8. 【python3两小时快速入门】入门笔记03：简单爬虫+多线程爬虫

    作用,之间将目标网页保存金本地 1.爬虫代码修改自网络,目前运行平稳,博主需要的是精准爬取,数据量并不大,暂未加多线程. 2.分割策略是通过查询条件进行分类,循环启动多条线程. 1.单线程简单爬虫(第 ...

  9. Python爬虫进阶 | 多线程

    一.简介 为了提高爬虫程序效率,由于python解释器GIL,导致同一进程中即使有多个线程,实际上也只会有一个线程在运行,但通过request.get发送请求获取响应时有阻塞,所以采用了多线程依然可以 ...

随机推荐

  1. 如何更专业的使用Chrome开发者工具

    顾名思义Chrome开发工具就是一个工具,它允许Web开发人员可以通过浏览器应用程序干预和操作Web页面,也可以通过这个工具调试和测试Web页面或Web应用程序.有了这个工具,你可以做很多有趣的事情: ...

  2. es6 中的 模板字符串

    Template literals are string literals allowing embedded expressions. You can use multi-line strings ...

  3. DataGridView拖动到TreeView

    很多时候我们会有这样的需求:一个窗体中有两个GRID,两个GRID中数据表结构差不多,我们要把一个GRID中的数据加入到另一个GRID中.一般的做法是新增一个导入或导出按钮,选择目标行后,通过按钮来触 ...

  4. Selenium webdriver Java firefox 路径设置问题

    问题: Cannot find firefox binary in PATH. Make sure firefox is installed. 原因:selenium找不到Firefox浏览器. 方法 ...

  5. loadrunner脚本中写入脚本输出log到外部文件,分析参数取值方式

    loadrunner脚本中写入脚本输出log到外部文件,分析参数取值方式 分类: 心得 loadrunner 我的测试 2012-04-01 12:52 2340人阅读 评论(0) 收藏 举报 脚本l ...

  6. iOS 转盘动画效果实现

    代码地址如下:http://www.demodashi.com/demo/11598.html 近期公司项目告一段落,闲来无事,看到山东中国移动客户端有个转盘动画挺酷的.于是试着实现一下,看似简单,可 ...

  7. redis清空部分key

    redis-cli keys "test:job:*" redis-cli keys "test:job:*" |xargs redis-cli del

  8. vue 手动挂载$mount() 获取 $el

    手动挂载$mount() 如果没有挂载的话,没有关联的 DOM 元素.是获取不到$el的. https://vuejs.org/v2/api/#vm-mount var MyComponent = V ...

  9. Netty（一）：初识Netty

    Netty是什么? Netty是由JBOSS提供的一个java开源框架. Netty提供异步的.事件驱动的网络应用程序框架和工具,用以快速开发高性能.高可靠性的网络服务器和客户端程序. 封装了JDK底 ...

  10. 从第三方Launcher授权启动指定APP的设计与实现

    Case 背景: Case要求从第三方Launcher中首次启动指定的应用程序时.弹出对话框提示用户进行授权启动,若用户未授权,则在下次再次启动该应用时依旧弹出对话框提示用户进行授权.直到用户相应用进 ...