Java读取html中所有img标签的src值

原理：利用正则匹配进行查找

直接上代码

--------------------------------------------------------------------------------------------------------------------------------------

public  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;
	}