轉自:
http://www.java265.com/JavaJingYan/202205/16534860003509.html
實作思路:
隻需定義相應的正規表達式
如:提取文本,隻需下列的正規表達式
String regx = "(<.+?>)|(</.+?>)";
private static Pattern p_image= Pattern.compile("<img.*src\\s*=\\s*(.*?)[^>]*?>",Pattern.CASE_INSENSITIVE);
private static Pattern r_image=Pattern.compile("src\\s*=\\s*\"?(.*?)(\"|>|\\s+)");
/**
* 提取富文本中純文字
*/
public static String getText(String richText) {
String regx = "(<.+?>)|(</.+?>)";
Matcher matcher = Pattern.compile(regx).matcher(richText);
while (matcher.find()) {
// 替換圖檔
richText = matcher.replaceAll("").replace(" ", "");
}
return richText;
}
/**
* 提取富文本中圖檔位址
*/
public static List<String> getImgStr(String richText) {
List<String> list = new ArrayList<>();
Matcher pMatcher = pImage.matcher(richText);
while (pMatcher.find()) {
// 得到<img />資料
String img = pMatcher.group();
// 比對<img>中的src資料
Matcher rMatcher = rImage.matcher(img);
while (rMatcher.find()) {
list.add(rMatcher.group(1));
}
}
return list;
}
private static Pattern p_image= Pattern.compile("<img.*src\\s*=\\s*(.*?)[^>]*?>",Pattern.CASE_INSENSITIVE);
private static Pattern r_image=Pattern.compile("src\\s*=\\s*\"?(.*?)(\"|>|\\s+)");
/**
* 提取富文本中純文字
*/
public static String getText(String richText) {
String regx = "(<.+?>)|(</.+?>)";
Matcher matcher = Pattern.compile(regx).matcher(richText);
while (matcher.find()) {
// 替換圖檔
richText = matcher.replaceAll("").replace(" ", "");
}
return richText;
}
/**
* 提取富文本中圖檔位址
*/
public static List<String> getImgStr(String richText) {
List<String> list = new ArrayList<>();
Matcher pMatcher = pImage.matcher(richText);
while (pMatcher.find()) {
// 得到<img />資料
String img = pMatcher.group();
// 比對<img>中的src資料
Matcher rMatcher = rImage.matcher(img);
while (rMatcher.find()) {
list.add(rMatcher.group(1));
}
}
return list;
}