采集规则：部分内容截取，然后得到集合(正则和逻辑两种)

import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class Test {
private static String REGEX = "<a href=\"\\w*\"/>";
private static String INPUT = "aabbsdasdaiqo<a href=\"xxx\"/>sasdadsa<a href=\"eee\"/>sdasadpqwo<a href=\"ggg\"/>||wxwdqwq<a href=\"bbb\"/>...";

public static void main(String[] args) {
List<String> list = new ArrayList<String>();

Pattern p = Pattern.compile(REGEX);
Matcher m = p.matcher(INPUT);

while (m.find()) {
String tmp = m.group();
list.add(tmp.substring(tmp.indexOf('"') + 1, tmp.lastIndexOf('"')));
}

printList(list);
}

private static void printList(List<String> list) {
for (String i : list) {
System.out.println(i);
}
}
}

import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;

public class mytest {
public static List getArrByStr(String str){
ArrayList list = new ArrayList();

String[] arr = str.split("<a");

for(int i=1;i<arr.length;i++){
int startPosTemp = arr[i].indexOf("href=\"");
int startPos = startPosTemp + 6;

StringBuffer sb = new StringBuffer();
for(int j=startPos;j<arr[i].length();j++){
if(arr[i].charAt(j) != '\"'){
sb.append(arr[i].charAt(j));
}else{
list.add(sb.toString());
break;
}
}
}

return list;
}
public static void main(String[] args) {
String text = "aabbsdasdaiqo<a href=\"xxx\"/>sasdadsa<a href=\"eee\"/>sdasadpqwo<a href=\"ggg\"/>||wxwdqwq<a href=\"bbb\"/>";
List list = getArrByStr(text);
for(Iterator it = list.iterator();it.hasNext();){
String strTemp = (String)it.next();
System.out.println(strTemp);
}

}
}