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);

 

1. import java.util.regex.*;  
2.   
3.   
4. public class RegExpParseHTML {  
5.   
6.     /** 
7.      * @param args 
8.      */  
9.     public static void main(String[] args) {  
10.         // TODO Auto-generated method stub  
11.         String html = "<a href=\"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>";  
12.         String href = parseHref(html);  
13.         System.out.println(href);  
14.     }  
15.   
16.     public static String parseHref(String html)  
17.     {  
18.         String regex = "<a[\\s]+href[\\s]*=[\\s]*\"([^<\"]+)\"";  
19.         //String regex = "[^.]";  
20.         Pattern p = Pattern.compile(regex, Pattern.CASE_INSENSITIVE);  
21.           
22.         Matcher m = p.matcher(html);  
23.           
24.         StringBuffer ret = new StringBuffer();  
25.         while(m.find())  
26.         {  
27.             ret.append(m.group(1));  
28.         }  
29.           
30.         return ret.toString();  
31.     }  
32.   
33.       
34.           
35. }  

 

查看原文

 

痴人硕梦-->Aerchi