使用正则表达式及
串操作
抽取网页信息实现代码如下: /* 去script */
public
String trimScript(String content) { String regEx = "<script[^>]*>[^<]+</script>";
Pattern p = Pattern.compile(regEx);
Matcher m = p.matcher(content);
String result = content;
(m.find
) { result = m.replaceAll("");
}
result; }
/* 去除注释*/
public
String trimComment(String content) { String regEx = "<!--[^-]*-->";
Pattern p = Pattern.compile(regEx);
Matcher m = p.matcher(content);
String result = content;
(m.find) { result = m.replaceAll("");
}
result; }
/* 去除标签 */
public
String trimTag(String content) { String regEx = "<[^>]+>";
Pattern p = Pattern.compile(regEx);
Matcher m = p.matcher(content);
String result = content;
(m.find) { result = m.replaceAll("");
}
result = result.replace(" ", "").replace(">", "").replace(
">", "");
result; }
/* 根据起始位置和结束位置
截取串 */ public
String subString(String start, String end, String content) { 
iStart = content.indexOf(start); iEnd = content.indexOf(end); (iStart < iEnd) { content.sub
(iStart, iEnd); }
null; }
最新评论