当前位置: 首页 > 图文教程 > 网络编程 > PHP > PHP采集程序中常用的函数

PHP
php ignore_user_abort与register_shutdown_function 使用方法
PHP写MySQL数据 实现代码
phpmyadmin 访问被拒绝的真实原因
PHP 程序员也要学会使用“异常”
php MYSQL 数据备份类
PHP 类型转换函数intval
php 图像函数大举例(非原创)
PHP 输出缓存详解
PHP COOKIE设置为浏览器进程
ie6 动态缩略图不显示的原因
php 将bmp图片转为jpg等其他任意格式的图片
discuz7 phpMysql操作类
一个php Mysql类 可以参考学习熟悉下
php 分页函数multi() discuz
学习discuz php 引入文件的方法DISCUZ_ROOT
php fckeditor 调用的函数
mysql 性能的检查和优化方法
PHP 高级课程笔记 面向对象
PHP 多进程 解决难题
php 404错误页面实现代码

PHP采集程序中常用的函数


出处:互联网   整理: 软晨网(RuanChen.com)   发布: 2009-08-14   浏览: 202 ::
收藏到网摘: n/a

以下为引用的内容:

//获得当前的脚本网址
function get_php_url(){
        if(!empty($_SERVER["REQUEST_URI"])){
                $scriptName = $_SERVER["REQUEST_URI"];
                $nowurl = $scriptName;
        }else{
                $scriptName = $_SERVER["PHP_SELF"];
                if(empty($_SERVER["QUERY_STRING"])) $nowurl = $scriptName;
                else $nowurl = $scriptName."?".$_SERVER["QUERY_STRING"];
        }
        return $nowurl;
}
//把全角数字转为半角数字
function GetAlabNum($fnum){
        $nums = array("0","1","2","3","4","5","6","7","8","9");
        $fnums = "0123456789";
        for($i=0;$i<=9;$i++) $fnum = str_replace($nums[$i],$fnums[$i],$fnum);
        $fnum = ereg_replace("[^0-9\.]|^0{1,}","",$fnum);
        if($fnum=="") $fnum=0;
        return $fnum;
}
//去除HTML标记
function Text2Html($txt){
        $txt = str_replace("  "," ",$txt);
        $txt = str_replace("<","&lt;",$txt);
        $txt = str_replace(">","&gt;",$txt);
        $txt = preg_replace("/[\r\n]{1,}/isU","<br/>\r\n",$txt);
        return $txt;
}

//清除HTML标记
function ClearHtml($str){
        $str = str_replace('<','&lt;',$str);
        $str = str_replace('>','&gt;',$str);
        return $str;
}
//相对路径转化成绝对路径
function relative_to_absolute($content, $feed_url) {
    preg_match('/(http|https|ftp):\/\//', $feed_url, $protocol);
    $server_url = preg_replace("/(http|https|ftp|news):\/\//", "", $feed_url);
    $server_url = preg_replace("/\/.*/", "", $server_url);

    if ($server_url == '') {
        return $content;
    }

    if (isset($protocol[0])) {
        $new_content = preg_replace('/href="\//', 'href="'.$protocol[0].$server_url.'/', $content);
        $new_content = preg_replace('/src="\//', 'src="'.$protocol[0].$server_url.'/', $new_content);
    } else {
        $new_content = $content;
    }
    return $new_content;
}
//取得所有链接
function get_all_url($code){
        preg_match_all('/<a\s+href=["|\']?([^>"\' ]+)["|\']?\s*[^>]*>([^>]+)<\/a>/i',$code,$arr);
        return array('name'=>$arr[2],'url'=>$arr[1]);
}

//获取指定标记中的内容
function get_tag_data($str, $start, $end){
        if ( $start == '' || $end == '' ){
               return;
        }
        $str = explode($start, $str);
        $str = explode($end, $str[1]);
        return $str[0];
}
//HTML表格的每行转为CSV格式数组
function get_tr_array($table) {
        $table = preg_replace("'<td[^>]*?>'si",'"',$table);
        $table = str_replace("</td>",'",',$table);
        $table = str_replace("</tr>","{tr}",$table);
        //去掉 HTML 标记
        $table = preg_replace("'<[\/\!]*?[^<>]*?>'si","",$table);
        //去掉空白字符
        $table = preg_replace("'([\r\n])[\s]+'","",$table);
        $table = str_replace(" ","",$table);
        $table = str_replace(" ","",$table);

        $table = explode(",{tr}",$table);
        array_pop($table);
        return $table;
}

//将HTML表格的每行每列转为数组,采集表格数据
function get_td_array($table) {
        $table = preg_replace("'<table[^>]*?>'si","",$table);
        $table = preg_replace("'<tr[^>]*?>'si","",$table);
        $table = preg_replace("'<td[^>]*?>'si","",$table);
        $table = str_replace("</tr>","{tr}",$table);
        $table = str_replace("</td>","{td}",$table);
        //去掉 HTML 标记
        $table = preg_replace("'<[\/\!]*?[^<>]*?>'si","",$table);
        //去掉空白字符
        $table = preg_replace("'([\r\n])[\s]+'","",$table);
        $table = str_replace(" ","",$table);
        $table = str_replace(" ","",$table);
      
        $table = explode('{tr}', $table);
        array_pop($table);
        foreach ($table as $key=>$tr) {
                $td = explode('{td}', $tr);
                array_pop($td);
            $td_array[] = $td;
        }
        return $td_array;
}

//返回字符串中的所有单词 $distinct=true 去除重复
function split_en_str($str,$distinct=true) {
        preg_match_all('/([a-zA-Z]+)/',$str,$match);
        if ($distinct == true) {
                $match[1] = array_unique($match[1]);
        }
        sort($match[1]);
        return $match[1];
}