@Component
public class GetImgStrListUils {
public List<String> getImgStrList(String htmlStr) {
List<String> list = new ArrayList<>();
String img = "";
Pattern p_image;
Matcher m_image;
String regEx_img = "<img.*src\\s*=\\s*(.*?)[^>]*?>";
p_image = Pattern.compile
(regEx_img, Pattern.CASE_INSENSITIVE);
m_image = p_image.matcher(htmlStr);
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()) {
String str = m.group(1).substring(30,76);
list.add(str);
}
}
return list;
}
}
因为我们的路径都是固定长度,所以我最后就直接截取了(偷懒了)