查找image标签里的url
public class test2 {
public static void main(String[] args) {
System.out.println(test2.getImgSrc("<img style=\"\" src=\"http://103.37.148.131:33**/talking_main_picture/2016.5/1F4DD7F4_A6A7_497C_932C_7A2A79B5AD15.jpg\" height=\"200\" width=\"320\">"));
}
public static final Pattern PATTERN = Pattern.compile("<img\\s+(?:[^>]*)src\\s*=\\s*([^>]+)", Pattern.CASE_INSENSITIVE | Pattern.MULTILINE);
public static List getImgSrc(String html) {
Matcher matcher = PATTERN.matcher(html);
List list = new ArrayList();
while (matcher.find()) {
String group = matcher.group(1);
if (group == null) {
continue;
}
// 这里可能还需要更复杂的判断,用以处理src="...."内的一些转义符
if (group.startsWith("'")) {
list.add(group.substring(1, group.indexOf("'", 1)));
} else if (group.startsWith("\"")) {
list.add(group.substring(1, group.indexOf("\"", 1)));
} else {
list.add(group.split("\\s")[0]);
}
}
return list;
}
}

浙公网安备 33010602011771号