java网页页面抓取标题和正文心得.docx;」OException;」nputStreamReader;.MalformedURLException;.URL;;;;,;,;lassWebContent{/***读取一个网页全部内容*/publicStringgetOneHtml(finalStringhtmlurl)throwslOException{URLurl;Stringtemp;finalStringBuffersb=newStringBuffer();try{url=newURL(htmlurl);finalBufferedReaderin二newBufferedReader(newInputStreamReader((),nutf-8H));〃读取网页全部内容while((temp=())!=null){(temp);}();}catch(finalMalformedURLExceptionme){("你输入的URL格式有问题!请仔细输入”);();throwme;}catch(finallOExceptione)();throwe;}();}/******@******@return获得网页标题*/publicStringgetTitle(finalStrings){Stringregex;Stringtitle=finalList<Strilist=newArrayList<String>();regex="<title>.*?</title>";finalPatternpa=pilejregex,);finalMatcherma=(s);while(()){(());}for(inti=0;i<();i++){title=title+(i);}returnoutTag(title);}/******@******@return获得链接*/publicList<String>getLink(finalStrings){Stringregex;finalUst<String>list=newArrayList<String>();regex=H<a[A>]*href=(\"(rV]*)\n|\'([叫]*)\'l(L\\s>]*))F>]*>(.*?)v/a>“;finalPatternpa=pilefregex,);finalMatcherma=(s);while(())(
java网页页面抓取标题和正文心得 来自淘豆网m.daumloan.com转载请标明出处.
