Java 提取链接内容及标题

String httpTag= "<a\\b([^>]+)(.*?)</a>";
//String linkHref= "(?:HREF\\s*=\\s*(?:\")([^\"]*)\"|'([^']*)'|([^'\">\\s]+))";
String linkHref= "HREF\\s*=\\s*(?:\"([^\"]*)\"|'([^']*)'|([^'\">\\s]+))";
// String linkHref= "(<a[\\s+]*([^> h]|h(?!ref\b))*href[\\s+]*=[\\s+]*[( '|\ ")]?)([^(\\s+| '|\ ")]*)([^> ]*> ) ";
String linkTitle ="(?:>)(.*)(?:</a>$)";

pathHtml=ie.frame(id,"main").div(id,"PathPanel").html().toString();
//println("LINK is : "+pathHtml);

pattern = Pattern.compile(httpTag, Pattern.CASE_INSENSITIVE);
matcher = pattern.matcher(pathHtml);

while (matcher.find())
{
// int start = matcher.start();
// int end = matcher.end();
// String pureUrl = pathHtml.substring(start, end);
// System.out.println(" match Str is : "+pureUrl);
// println("1: "+matcher.group().length());
// println("2 : "+matcher.groupCount());
// println("22555 --> "+matcher.group(2));
lastLinkHtml=matcher.group();

}
println("Link content: "+lastLinkHtml);
patternCon = Pattern.compile(linkHref, Pattern.CASE_INSENSITIVE);
//patternCon = Pattern.compile(linkTitle, Pattern.CASE_INSENSITIVE);
matcherCon = patternCon.matcher(lastLinkHtml);

while (matcherCon.find())
{
// int start = matcherCon.start();
// int end = matcherCon.end();
// String pureUrl = pathHtml.substring(start, end);

linkValue=matcherCon.group(1);

}
println("link value is: "+linkValue);

importjava.util.regex.*;


publicclassRegExpParseHTML{

/**
*@paramargs
*/
publicstaticvoidmain(String[]args){
//TODOAuto-generatedmethodstub
Stringhtml="<ahref=\"http://www.autohome.com.cn/780/\"style=\"text-decoration:none;\"target=\"_blank\"title=\"[D]大众UP频道\">[D]大众UP频道</a>";
Stringhref=parseHref(html);
System.out.println(href);
}

publicstaticStringparseHref(Stringhtml)
{
Stringregex="<a[\\s]+href[\\s]*=[\\s]*\"([^<\"]+)\"";
//Stringregex="[^.]";
Patternp=Pattern.compile(regex,Pattern.CASE_INSENSITIVE);

Matcherm=p.matcher(html);

StringBufferret=newStringBuffer();
while(m.find())
{
ret.append(m.group(1));
}

returnret.toString();
}



}

查看原文

痴人硕梦-->Aerchi