微博内容正则表达式匹配链接, 话题标签与@用户

需要找出微博正文中的链接(主要为http链接)，话题标签(#内容#)，@用户，用正则表达式解决之，暂时找到的方案如下

1. 链接

正则表达式

(?:^|[\\W])((ht|f)tp(s?):\\/\\/|www\\.)(([\\w\\-]+\\.){1,}?([\\w\\-.~]+\\/?)*[\\p{Alnum}.,%_=?&#\\-+()\\[\\]\\*$~@!:/{};']*)

Java程序示例

/**
* URL正则表达式
*/
private static final Pattern urlPattern = Pattern.compile(
"(?:^|[\\W])((ht|f)tp(s?):\\/\\/|www\\.)"
+ "(([\\w\\-]+\\.){1,}?([\\w\\-.~]+\\/?)*"
+ "[\\p{Alnum}.,%_=?&#\\-+()\\[\\]\\*$~@!:/{};']*)",
Pattern.CASE_INSENSITIVE | Pattern.MULTILINE | Pattern.DOTALL);
/**
* 去掉文本中URLs
* @param text
* @return
*/
public static String removeURLs(String text){
Matcher matcher;
String newTweet = text.trim();
String cleanedText="";
while(!newTweet.equals(cleanedText)){
cleanedText=newTweet;
matcher = urlPattern.matcher(cleanedText);
newTweet = matcher.replaceAll("");
newTweet =newTweet.trim();
}
return cleanedText;
}

/**
* 获得文本中URL列表
* @param originalString
* @return
*/
public static List<String> getURLs(String originalString){
List<String> urlsSet=new ArrayList<String>();
Matcher matcher = urlPattern.matcher(originalString);
while (matcher.find()) {
int matchStart = matcher.start(1);
int matchEnd = matcher.end();
String tmpUrl=originalString.substring(matchStart,matchEnd);
urlsSet.add(tmpUrl);
// now you have the offsets of a URL match
originalString=originalString.replace(tmpUrl,"");
matcher = urlPattern.matcher(originalString);
}
return urlsSet;
}

2. 话题标签

正则表达式

#[^#]+#

Java程序示例

/**
* Hashtag正则表达式
*/
// private static final Pattern hashtagPattern =
//    Pattern.compile("(?:^|\\s|[\\p{Punct}&&[^/]])(#[\\p{L}0-9-_]+)");
private static final Pattern hashtagPattern =
Pattern.compile("#[^#]+#");
private static String removeHashtags(String text){
Matcher matcher;
String newTweet = text.trim();
String cleanedText="";
while(!newTweet.equals(cleanedText)){
cleanedText=newTweet;
matcher = hashtagPattern.matcher(cleanedText);
newTweet = matcher.replaceAll("");
newTweet =newTweet.trim();
}
return cleanedText;
}

public static List<String> getHashtags(String originalString){
List<String> hashtagSet=new ArrayList<String>();
Matcher matcher = hashtagPattern.matcher(originalString);
while (matcher.find()) {
//            int matchStart = matcher.start(1);
int matchStart = matcher.start();
int matchEnd = matcher.end();
String tmpHashtag=originalString.substring(matchStart,matchEnd);
hashtagSet.add(tmpHashtag);
originalString=originalString.replace(tmpHashtag,"");
matcher = hashtagPattern.matcher(originalString);
}
return hashtagSet;
}

3. @用户

正则表达式

@[\u4e00-\u9fa5a-zA-Z0-9_-]{2,30}

Java程序示例

/**
* 用户@正则表达式
* 新浪微博中的用户名格式为是“4-30个字符，支持英文、数字、"_"或减号”,
* 也就是说，支持中文、字母、数字、下划线及减号，并且是4到30个字符（这里暂且认为汉字为一个字符）
* 那么在写匹配的表达式的时候就可以这么来写:    @[\u4e00-\u9fa5a-zA-Z0-9_-]{4,30}
*/
// private static final Pattern usermentionPattern =
//      Pattern.compile("(?:^|\\s|[\\p{Punct}&&[^/]])(@[\\p{L}0-9-_]+)");
private static final Pattern usermentionPattern =
Pattern.compile("@[\u4e00-\u9fa5a-zA-Z0-9_-]{2,30}");
public static String removeUserMentions(String text){
Matcher matcher;
String newTweet = text.trim();
String cleanedText="";
while(!newTweet.equals(cleanedText)){
cleanedText=newTweet;
matcher = usermentionPattern.matcher(cleanedText);
newTweet = matcher.replaceAll("");
newTweet =newTweet.trim();
}
return cleanedText;
}

public static List<String> getUsermentions(String originalString){
List<String> usermentionsSet=new ArrayList<String>();
Matcher matcher = usermentionPattern.matcher(originalString);
while (matcher.find()) {
//            int matchStart = matcher.start(1);
int matchStart = matcher.start();
int matchEnd = matcher.end();
String tmpUsermention=originalString.substring(matchStart,matchEnd);
usermentionsSet.add(tmpUsermention);
originalString=originalString.replace(tmpUsermention,"");
matcher = usermentionPattern.matcher(originalString);
}
return usermentionsSet;
}