[Core Java] Using Regular Expression to extract anchor from html

String htmlLine = "What We Know Aboutâ¦Health Literacy?   [PDF-2.54MB]

";
                     htmlLine += "What We Know Aboutâ¦Health Literacy?   [PDF-2.54MB]

";
                     htmlLine += "What We Know Aboutâ¦Health Literacy?   [PDF-2.54MB]

";
                     htmlLine += "What We Know Aboutâ¦Health Literacy?   [PDF-2.54MB]

";
                     String expr ="]*)>"      // Element Detail - Group1
                            + "([^<]+)"       // Element Data   - Group2
                            + ""; 
                     Pattern patt = Pattern.compile(expr, Pattern.DOTALL | Pattern.UNIX_LINES);
                     Matcher m = patt.matcher(htmlLine);
                     List anchors =new ArrayList();
                     
                     while(m.find())
                     {
                           anchors.add(""+m.group(2)+"");
                     }
                     
                     //get external Links
                     String hrefExpr = "href=\""
                            + "([^\"]+)"      
                            + "\"[^>]*>"      
                            + "([^<]+)"; 
                     patt = Pattern.compile(hrefExpr, Pattern.DOTALL | Pattern.UNIX_LINES);
                     for(String anchor : anchors){
                           if(anchor.contains("href") || anchor.contains("HREF")){
                                  m = patt.matcher(anchor);
                                  while(m.find())
                                  {
                                         String href = m.group(1);
                                         if(!href.contains(".gov") && !href.contains("localhost")){
                                                System.out.println(anchor);
                                         }
                                  }
                           }
                     }