String html ="<img width=100' height='30' src='aa.jpg'/>";
//这里是修改width的属性为100%
html = html.replaceAll("(<img[^>]*?)\\s+width\\s*=\\s*\\S+","$1 width=100%");
System.out.println(html);
//这里是清除width的属性
html = html.replaceAll("(<img[^>]*?)\\s+width\\s*=\\s*\\S+","$1");
html = html.replaceAll("(<img[^>]*?)\\s+height\\s*=\\s*\\S+","$1");
System.out.println(html);
//这里是移除img标签
html = html.replaceAll("<img[^>]*/>", " ");
System.out.println(html);
//这是截取img标签里的src属性的值,就是图片的路径
public static List<String> getImgSrc(String htmlStr) {
String img = "";
Pattern p_image;
Matcher m_image;
List<String> pics = new ArrayList<String>();
// String regEx_img = "<img.*src=(.*?)[^>]*?>"; //图片链接地址
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()) {
img = img + "," + m_image.group();
// Matcher m =
// Pattern.compile("src=\"?(.*?)(\"|>|\\s+)").matcher(img); //匹配src
Matcher m = Pattern.compile("src\\s*=\\s*\"?(.*?)(\"|>|\\s+)").matcher(img);
while (m.find()) {
pics.add(m.group(1));
}
}
return pics;
}