# -*- coding: ISO-8859-1 -*-
require 'open-uri'
require 'uri'
html = open('http://www.265.com/').read(2000000)
END_CHARS = %{.,'?!:;}
puts URI.extract(html, ['http']).collect { |u| END_CHARS.index(u[-1]) ? u.chop : u }
?
?
运行结果：
http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd http://www.w3.org/1999/xhtml http://www.google.com.hk/search?hl=zh-CN&q=%E7%94%B5%E5%BD%B1&btnG=Google+%E6%90%9C%E7%B4%A2&meta=&aq=f&oq=&client=aff-avalanche http://google.com.hk/webhp?hl=zh-cn&tab=Aw http://www.google.cn/imghp?hl=zh-cn&tab=Ai http://video.google.cn/?hl=zh-cn&tab=Av http://ditu.google.cn/maps?hl=zh-cn&tab=Al http://news.google.cn/nwshp?hl=zh-cn&tab=An http://www.google.cn/music?hl=zh-cn&tab=AU http://www.google.cn/prdhp?hl=zh-cn&tab=Af http://www.google.com.hk/intl/zh-CN/options/ http://www.google.cn/music?client=aff-avalanche&channel=textlink http://www.265.com/images/googlemusic.gif http://www.google.cn/search?hl=zh-CN&client=aff-avalanche&forid=1&channel=logo&q= http://www.google.com.hk/search?hl=zh-CN&q= http://www.365rili.com/ http://www.boc.cn/cn/common/whpj.html http://www.google.com.hk/finance?client=aff-a&hl=zh-CN http://jipiao.kuxun.cn/?fromid=Kgbw-S1134381-T1137511 http://huoche.kuxun.cn/?fromid=Kgbw-S1134381-T1076521 http://www.lottery.gov.cn/ http://www.zhcw.com/ http://www.google.com.hk/search?hl=zh-CN&q=%E7%94%B5%E5%BD%B1&btnG=Google+%E6%90%9C%E7%B4%A2&meta=&aq=f&oq=&client=aff-avalanche http://www.google.com.hk/dictionary http://www.google.com.hk/intl/zh-CN/help/features.html http://www.google.com.hk/intl/zh-CN/mobile/maps/ http://www.chashouji.com/ http://product.cheshi.com/price.html http://fund.eastmoney.com/fund.html http://www.google.com.hk/search?hl=zh-CN&q= http://www.google.com.hk/search?hl=zh-CN&q= http://download.tech.qq.com/soft/17/21/index.shtml http://www.google.com.hk/search?hl=zh-CN&newwindow=1&safe=strict&q=%E8%B0%B7%E6%AD%8C%E9%87%91%E5%B1%B1%E8%AF%8D%E9%9C%B8&aq=f&aqi=&aql=&oq=&gs_rfai= http://www.uusee.tv/ http://earth.google.com/intl/zh-CN/ http://www.360.cn http://www.kuaikuai.cn/h/down/kk_game/?channel=57_1 http://www.flashget.com/cn/download.htm http://www.ppstream.com/download.html http://pstatic.xunlei.com/about/product/down_xl5.htm http://www.google.com/ime/pinyin/ http://toolbar.google.com/T4/intl/zh-CN/ http://www.kuwo.cn/ http://www.rising.com.cn/ http://www.maxthon.cn/ http://www.stockstar.com/cfg http://www.QVOD.com http://feixin.10086.cn/download/ http://www.gw.com.cn/download/level1/index.htm http://www.google.com.hk/search?q=%E6%9A%B4%E9%A3%8E%E5%BD%B1%E9%9F%B33.6+%E6%99%BA%E8%83%BD%E9%AB%98%E6%B8%85%E7%89%88&hl=zh-CN&source=billboard_site&cd=12200098&cad=5&ie=utf8 http://www.google.com/chrome?hl=zh-cn http://www.mosh.cn/beijing http://www.wooha.com/?WT.mc_id=new265 http://www.qunar.com/ http://www.abang.com/ http://www.yihaodian.com/product/index.do?tracker_type=9&tracker_u=1949358 http://www.izhufu.com/ http://www.docin.com http://bai.sohu.com http://www.daodao.com/?m=12347 http://www.gong1chuang1.com http://www.mpdaogou.com/ http://www.aibaimm.cn/ http://www.bankrate.com.cn/ http://www.5925car.com/ http://www.miui.com/ http://www.trends.com.cn/ http://www.m18.com/ http://www.0-6.com/ http://www.chilema.cn/default.aspx http://www.51mike.com/ http://www.265.com/Youxi_Wangyou/Remen_Youxizhuanti_All.html#609 http://www.265.com/Youxi_Wangyou/Remen_Youxizhuanti_All.html#352 http://www.265.com/Youxi_Wangyou/Remen_Youxizhuanti_All.html#1134 http://www.265.com/Youxi_Wangyou/Remen_Youxizhuanti_All.html#1371 http://www.265.com/Youxi_Wangyou/Remen_Youxizhuanti_All.html#963 http://www.265.com/Youxi_Wangyou/Remen_Youxizhuanti_All.html#1372 http://www.265.com/Youxi_Wangyou/Remen_Youxizhuanti_All.html#1373 http://www.265.com/Youxi_Wangyou/Remen_Youxizhuanti_All.html#1437 http://www.265.com/Youxi_Wangyou/Remen_Youxizhuanti_All.html#1374 http://www.265.com/Youxi_Wangyou/Remen_Youxizhuanti_All.html#355 http://www.265.com/Youxi_Wangyou/Remen_Youxizhuanti_All.html#1438 http://www.265.com/Youxi_Wangyou/Remen_Youxizhuanti_All.html#957 http://www.265.com/Youxi_Wangyou/Remen_Youxizhuanti_All.html#1417 http://www.265.com/Youxi_Wangyou/Remen_Youxizhuanti_All.html#1376 http://www.265.com/Youxi_Wangyou/Remen_Youxizhuanti_All.html#958 http://www.265.com/Youxi_Wangyou/Remen_Youxizhuanti_All.html#1378 http://www.265.com/Youxi_Wangyou/Remen_Youxizhuanti_All.html#1135 http://www.265.com/Youxi_Wangyou/Remen_Youxizhuanti_All.html#1377 http://www.265.com/Youxi_Wangyou/index.html#196 http://www.265.com/Youxi_Wangyou/index.html#195 http://www.google.com.hk/webhp?client=aff-avalanche http://www.baidu.com/ http://www.qq.com/ http://www.163.com/ http://cn.msn.com/ http://www.tom.com/ http://www.china.com/ http://www.sina.com.cn/ http://www.sohu.com/ http://cn.yahoo.com/ http://www.51job.com/ http://www.renren.com/ http://www.mop.com/ http://www.chinamobile.com/ http://www.ifeng.com/ http://www.eastmoney.com/ http://www.people.com.cn/ http://www.xinhuanet.com/ http://www.ctrip.com/ http://www.360.cn/ http://www.soufun.com/ http://www.cctv.com/ http://www.zaobao.com/ http://www.xunlei.com/ http://58.com/ http://www.icbc.com.cn/ http://www.kaixin001.com/ http://www.4399.com/ http://www.jrj.com.cn/ http://www.hexun.com/ http://www.gov.cn/ http://china.alibaba.com/?cosite=265dh&location=alihomepage_dh http://www.taobao.com/ http://www.zol.com.cn http://www.zhcw.com/ http://www.autohome.com.cn/ http://www.youku.com http://www.tudou.com/ http://www.jiayuan.com/ http://www.dangdang.com/ http://www.tianya.cn/ http://www.51.com/?fromsite=265_1 http://news.google.com.hk/news/search?pz=1&cf=all&ned=cn&hl=zh-CN&q=%E6%B2%BB%E5%A0%B5&source=265.com', http://news.google.com.hk/news/more?pz=1&cf=all&ned=cn&cf=all&ncl=dVZ221HiynUgGMMdPA7YVmSj8eZRM&source=265.com', http://news.google.com.hk/news/more?pz=1&cf=all&ned=cn&cf=all&ncl=dlDTKEYmgUS-GKMcA1iendnuqffNM&source=265.com', http://blogsearch.google.com.hk/blogsearch/story?hl=zh-cn&num=10&topic=e&bcid=1651226638&bc_lang=zh-CN&source=265.com', http://blogsearch.google.com.hk/blogsearch/story?hl=zh-cn&topic=fe&bcid=1651764651&bc_lang=zh-CN&source=265.com', http://blogsearch.google.com.hk/blogsearch/story?hl=zh-cn&num=10&topic=fe&bcid=1651435361&bc_lang=zh-CN&source=265.com', http://blogsearch.google.com.hk/blogsearch/story?hl=zh-cn&num=10&topic=fe&bcid=1650340552&bc_lang=zh-CN&source=265.com', http://blogsearch.google.com.hk/blogsearch/story?hl=zh-cn&num=10&topic=fe&bcid=1651458816&bc_lang=zh-CN&source=265.com', http://blogsearch.google.com.hk/blogsearch/story?hl=zh-cn&topic=l&bcid=1651766213&bc_lang=zh-CN&source=265.com', http://news.google.com.hk/news/more?pz=1&cf=all&ned=cn&cf=all&ncl=dZkub0JsW0461gMDeDdtdN4qp-pMM&source=265.com', http://news.google.com.hk/news/search?pz=1&cf=all&ned=cn&hl=zh-CN&q=%E5%85%AC%E5%8A%A1%E5%91%98%E5%B7%A5%E8%B5%84&source=265.com', http://news.google.com.hk/news/more?pz=1&cf=all&ned=cn&cf=all&ncl=dQhOS-yAc2hsqbMejJ2S82D9XA0CM&source=265.com', http://news.google.com.hk/news/search?pz=1&cf=all&ned=cn&hl=zh-CN&q=%E5%BC%A0%E9%9B%A8%E7%BB%AE&source=265.com', http://www.17173.com http://games.sina.com.cn/ http://www.duowan.com/ http://game.zol.com.cn http://tl.sohu.com/ http://aion.sdo.com/project/index/index.htm http://t.mop.com http://www.onlinedown.net/ http://www.skycn.com/ http://www.crsky.com http://xiazai.zol.com.cn http://tech.sina.com.cn/down/ http://www.mydown.com/ http://www.qidian.com/ http://www.readnovel.com/ http://www.xxsy.net/ http://www.hongxiu.com/ http://www.jjwxc.net/ http://book.sina.com.cn/ http://www.xs8.cn/ http://military.china.com/zh_cn/ http://mil.news.sina.com.cn/ http://www.tiexue.net/ http://mil.huanqiu.com/ http://www.xinhuanet.com/mil/ http://junshi.xilu.com/ http://sports.sina.com.cn/ http://sports.sohu.com/ http://sports.163.com/ http://sports.tom.com/ http://china.nba.com/ http://www.hoopchina.com/ http://www.zhibo8.com/ http://www.google.cn/music/homepage?client=aff-avalanche http://www.1ting.com/ http://www.haoting.com/ http://www.qq163.com/ http://www.aiting.com http://www.520music.com/ http://youku.com http://tudou.com http://www.ku6.com/ http://www.6.cn http://www.joy.cn/ http://video.sina.com.cn/ http://tv.sohu.com/ http://www.google.com.hk/finance?client=aff-a&hl=zh-CN http://www.jrj.com.cn/ http://eastmoney.com/ http://www.stockstar.com/ http://www.cnfol.com/ http://hexun.com/ http://finance.qq.com/ http://people.com.cn/ http://xinhuanet.com/ http://www.chinanews.com.cn/ http://news.sina.com.cn/ http://news.google.com.hk/news?ned=cn&client=aff-avalanche http://www.china.com.cn http://news.ifeng.com http://www.tianya.cn http://www.qihoo.com http://www.xici.net http://www.daqi.com http://www.dianping.com http://dzh.mop.com http://laiba.tianya.cn http://blog.sina.com.cn/ http://www.bokee.com/ http://blog.163.com/ http://blog.sohu.com/ http://hi.baidu.com http://qzone.qq.com/ http://www.jiayuan.com/ http://www.marry5.com/ http://www.baihe.com/ http://www.zhenai.com/ http://www.ipart.cn/ http://www.wealink.com/ http://www.myspace.cn/ http://www.lol99.com/ http://www.4399.com/ http://www.7k7k.com/ http://www.51mole.com/ http://www.yx007.com/ http://www.3839.com/ http://www.xiaoyouxi.com/ http://www.91wan.com/ http://mail.163.com/ http://mail.cn.yahoo.com http://mail.sohu.com http://www.hotmail.com/ http://www.gmail.com/ http://www.126.com/ http://mail.sina.com.cn/ http://www.39.net/ http://www.xywy.com/ http://www.haodf.com/ http://health.sohu.com/ http://www.fx120.net/ http://www.fh21.com.cn/ http://www.jxdyf.com/ http://www.pclady.com.cn http://eladies.sina.com.cn/ http://women.sohu.com/ http://lady.163.com/ http://www.lady8844.com/ http://www.zdface.com/ http://www.yoka.com/ http://www.icbc.com.cn/index.jsp http://www.boc.cn/ http://www.ccb.com/portal/cn/home/index.html http://www.abchina.com/ http://www.bankcomm.com/ http://www.cmbchina.com/ http://www.cib.com.cn/ http://finance.sina.com.cn/fund/ http://fund.jrj.com.cn/ http://www.1234567.com.cn/ http://www.chinaamc.com/ http://www.jsfund.cn/ http://www.gffunds.com.cn/ http://autohome.com.cn/ http://www.pcauto.com.cn/ http://www.xcar.com.cn/ http:///www.chinacars.com http://www.cheshi.com/ http://www.bitauto.com/ http://www.che168.com/ http://www.51job.com/ http://zhaopin.com/ http://chinahr.com/ http://www.yingjiesheng.com/ http://www.cjol.com/ http://www.528.com.cn/ http://taobao.com/ http://union.360buy.com/union_default.aspx?union_Id=163 http://www.amazon.cn/ http://www.dangdang.com/ http://www.google.com.hk/products?client=aff-avalanche http://www.newegg.com.cn?cm_mmc=265com-_-265com-_-265com-_-1110 http://58.com http://www.55bbs.com/ http://www.anjuke.com/ http://www.koubei.com/ http://www.ci123.com/ http://www.yaolan.com/ http://www.aibangtuan.com/ http://house.sina.com.cn/ http://www.google.com.hk/webhp?client=aff-avalanche http://www.baidu.com/ http://one.cn.yahoo.com/ http://ditu.google.com/maps?client=aff-avalanche http://www.google.com.hk/products?client=aff-avalanche http://www.google.cn/music?client=aff-avalanche http://video.google.com.hk/?client=aff-avalanche http://images.google.com.hk/images?client=aff-avalanche http://news.google.com.hk/nwshp?client=aff-avalanche http://www.265.com/');return(false) http://www.265.com http://www.google.cn/intl/zh-CN/about.html http://www.265.com http://www.miibeian.gov.cn/
?
相关文章
