直接上代码:
public List<String> getImgStr(String htmlStr) {
List<String> list = Lists.newArrayList();
String regEx_img = "<img.*src\\s*=\\s*(.*?)[^>]*?>";
Pattern p_image = Pattern.compile(regEx_img, Pattern.CASE_INSENSITIVE);
Matcher m_image = p_image.matcher(htmlStr);
String img = "";
while (m_image.find()) {
// 得到<img />数据
img = m_image.group();
// 匹配<img>中的src数据
Matcher m = Pattern.compile("src\\s*=\\s*\"?(.*?)(\"|>|\\s+)").matcher(img);
while (m.find()) {
list.add(m.group(1));
}
}
return list;
}