欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页  >  php教程

PHP采集程序中常用的函数

程序员文章站 2022-04-07 09:19:06
...
函数描述及例子 PHP采集程序中常用的函数 查询关键字 PHP采集程序中常用的函数
//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;$i",">",$txt); 
        $txt = preg_replace("/[\r\n]{1,}/isU","
\r\n",$txt); 
        return $txt; 
}
//清除HTML标记 
function ClearHtml($str){ 
        $str = str_replace('','>',$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('/"\' ]+)["|\']?\s*[^>]*>([^>]+)/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) { 
        $table = preg_replace("']*?>'si",'"',$table); 
        $table = str_replace("",'",',$table); 
        $table = str_replace("","{tr}",$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) { 
        $table = preg_replace("']*?>'si","",$table); 
        $table = preg_replace("']*?>'si","",$table); 
        $table = preg_replace("'[^>\s+href=["|\']?([^>[^>[^>
]*?>'si","",$table); $table = str_replace("","{tr}",$table); $table = str_replace("","{td}",$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 $match[1]; } 函数描述及例子 PHP采集程序中常用的函数 查询关键字 PHP采集程序中常用的函数 ",">",$txt); $txt = preg_replace("/[\r\n]{1,}/isU"," \r\n",$txt); return $txt; } //清除HTML标记 function ClearHtml($str){ $str = str_replace('','>',$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('/"\' ]+)["|\']?\s*[^>]*>([^>]+)/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) { $table = preg_replace("' ]*?>'si",'"',$table); $table = str_replace("",'",',$table); $table = str_replace("","{tr}",$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) { $table = preg_replace("']*?>'si","",$table); $table = preg_replace("']*?>'si","",$table); $table = preg_replace("'[^>[^>
]*?>'si","",$table); $table = str_replace("","{tr}",$table); $table = str_replace("","{td}",$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]; }
[^>
[^>[^>\s+href=["|\']?([^>