php进行html网页字数统计实例

统计前先把html标签去掉，变成纯文本形式
<?php 
    $a="<p>欢迎来到羊窝网：</p>
    <p>这是笑望书的博客，博客地址是www.yangwo.net</p>
    <p>博客采用的typecho程序建的，很简洁的程序，是我喜欢的类型<p>
    <p>给张有趣的图片你吧<img src=\"http://www.yangwo.net/usr/uploads/2010/04/4189455239.jpg\" alt=\"有趣的图片\" /></p>";

$search = array ("'<script[^>]*?>.*?</script>'si",  // 去掉 javascript
                 "'<[\/\!]*?[^<>]*?>'si",           // 去掉 HTML 标记
                 "'([\r\n])[\s]+'",                 // 去掉空白字符
                 "'&(quot|#34);'i",                 // 替换 HTML 实体
                 "'&(amp|#38);'i",
                 "'&(lt|#60);'i",
                 "'&(gt|#62);'i",
                 "'&(nbsp|#160);'i",
                 "'&(iexcl|#161);'i",
                 "'&(cent|#162);'i",
                 "'&(pound|#163);'i",
                 "'&(copy|#169);'i",
                 "'&#(\d+);'e");                    // 作为 PHP 代码运行

$replace = array ("",
                  "",
                  "\\1",
                  "\"",
                  "&",
                  "<",
                  ">",
                  " ",
                  chr(161),
                  chr(162),
                  chr(163),
                  chr(169),
                  "chr(\\1)");

$b = preg_replace ($search, $replace, $a);
$b = str_replace(" ","",$b); //去掉空格
echo $b."<br />"; //输出处理后的纯文本内容
$str_number=mb_strlen($b,'UTF-8');//用mb_strlen函数进行字数统计,记得指定编码类型，这里是utf-8
echo $str_number."<br />";//输出字数统计结果
if($str_number<500) {
    echo "字数不足200字！";
} else {
    echo "字数不少于200字！";
}
?>