PHP采集程序中常用的函数-php手册-php.cn

PHP采集程序中常用的函数
WBOY
Lepaskan： 2016-06-13 10:59:21
asal
1240 orang telah melayarinya
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;$i<=9;$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); 
        $txt = str_replace("<","<",$txt); 
        $txt = str_replace(">",">",$txt); 
        $txt = preg_replace("/[\r\n]{1,}/isU","
\r\n",$txt); 
        return $txt; 
}
//清除HTML标记 
function ClearHtml($str){ 
        $str = str_replace(&#39;<&#39;,&#39;<&#39;,$str); 
        $str = str_replace(&#39;>&#39;,&#39;>&#39;,$str); 
        return $str; 
} 
//相对路径转化成绝对路径 
function relative_to_absolute($content, $feed_url) { 
    preg_match(&#39;/(http|https|ftp):\/\//&#39;, $feed_url, $protocol); 
    $server_url = preg_replace("/(http|https|ftp|news):\/\//", "", $feed_url); 
    $server_url = preg_replace("/\/.*/", "", $server_url);
    if ($server_url == &#39;&#39;) { 
        return $content; 
    }
    if (isset($protocol[0])) { 
        $new_content = preg_replace(&#39;/href="\//&#39;, &#39;href="&#39;.$protocol[0].$server_url.&#39;/&#39;, $content); 
        $new_content = preg_replace(&#39;/src="\//&#39;, &#39;src="&#39;.$protocol[0].$server_url.&#39;/&#39;, $new_content); 
    } else { 
        $new_content = $content; 
    } 
    return $new_content; 
} 
//取得所有链接 
function get_all_url($code){ 
        preg_match_all(&#39;/"\&#39; ]+)["|\&#39;]?\s*[^>]*>([^>]+)<\/a>/i&#39;,$code,$arr); 
        return array(&#39;name&#39;=>$arr[2],&#39;url&#39;=>$arr[1]); 
}
//获取指定标记中的内容 
function get_tag_data($str, $start, $end){ 
        if ( $start == &#39;&#39; || $end == &#39;&#39; ){ 
               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) { 
        $table = preg_replace("&#39;<td[^>]*?>&#39;si",&#39;"&#39;,$table); 
        $table = str_replace("",&#39;",&#39;,$table); 
        $table = str_replace("","{tr}",$table); 
        //去掉 HTML 标记 
        $table = preg_replace("&#39;<[\/\!]*?[^<>]*?>&#39;si","",$table); 
        //去掉空白字符 
        $table = preg_replace("&#39;([\r\n])[\s]+&#39;","",$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) { 
        $table = preg_replace("&#39;<table[^>]*?>&#39;si","",$table); 
        $table = preg_replace("&#39;<tr[^>]*?>&#39;si","",$table); 
        $table = preg_replace("&#39;<td[^>]*?>&#39;si","",$table); 
        $table = str_replace("","{tr}",$table); 
        $table = str_replace("","{td}",$table); 
        //去掉 HTML 标记 
        $table = preg_replace("&#39;<[\/\!]*?[^<>]*?>&#39;si","",$table); 
        //去掉空白字符 
        $table = preg_replace("&#39;([\r\n])[\s]+&#39;","",$table); 
        $table = str_replace(" ","",$table); 
        $table = str_replace(" ","",$table); 
        
        $table = explode(&#39;{tr}&#39;, $table); 
        array_pop($table); 
        foreach ($table as $key=>$tr) { 
                $td = explode(&#39;{td}&#39;, $tr); 
                array_pop($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,$distinct=true) { 
        preg_match_all(&#39;/([a-zA-Z]+)/&#39;,$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
<!--?
//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); 
        $txt = str_replace("<","<",$txt); 
        $txt = str_replace("-->",">",$txt); 
        $txt = preg_replace("/[\r\n]{1,}/isU","
\r\n",$txt); 
        return $txt; 
}
//清除HTML标记 
function ClearHtml($str){ 
        $str = str_replace(&#39;<&#39;,&#39;<&#39;,$str); 
        $str = str_replace(&#39;>&#39;,&#39;>&#39;,$str); 
        return $str; 
} 
//相对路径转化成绝对路径 
function relative_to_absolute($content, $feed_url) { 
    preg_match(&#39;/(http|https|ftp):\/\//&#39;, $feed_url, $protocol); 
    $server_url = preg_replace("/(http|https|ftp|news):\/\//", "", $feed_url); 
    $server_url = preg_replace("/\/.*/", "", $server_url);
    if ($server_url == &#39;&#39;) { 
        return $content; 
    }
    if (isset($protocol[0])) { 
        $new_content = preg_replace(&#39;/href="\//&#39;, &#39;href="&#39;.$protocol[0].$server_url.&#39;/&#39;, $content); 
        $new_content = preg_replace(&#39;/src="\//&#39;, &#39;src="&#39;.$protocol[0].$server_url.&#39;/&#39;, $new_content); 
    } else { 
        $new_content = $content; 
    } 
    return $new_content; 
} 
//取得所有链接 
function get_all_url($code){ 
        preg_match_all(&#39;/"\&#39; ]+)["|\&#39;]?\s*[^>]*>([^>]+)<\/a>/i&#39;,$code,$arr); 
        return array(&#39;name&#39;=>$arr[2],&#39;url&#39;=>$arr[1]); 
}
//获取指定标记中的内容 
function get_tag_data($str, $start, $end){ 
        if ( $start == &#39;&#39; || $end == &#39;&#39; ){ 
               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) { 
        $table = preg_replace("&#39;<td[^>]*?>&#39;si",&#39;"&#39;,$table); 
        $table = str_replace("",&#39;",&#39;,$table); 
        $table = str_replace("","{tr}",$table); 
        //去掉 HTML 标记 
        $table = preg_replace("&#39;<[\/\!]*?[^<>]*?>&#39;si","",$table); 
        //去掉空白字符 
        $table = preg_replace("&#39;([\r\n])[\s]+&#39;","",$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) { 
        $table = preg_replace("&#39;<table[^>]*?>&#39;si","",$table); 
        $table = preg_replace("&#39;<tr[^>]*?>&#39;si","",$table); 
        $table = preg_replace("&#39;<td[^>]*?>&#39;si","",$table); 
        $table = str_replace("","{tr}",$table); 
        $table = str_replace("","{td}",$table); 
        //去掉 HTML 标记 
        $table = preg_replace("&#39;<[\/\!]*?[^<>]*?>&#39;si","",$table); 
        //去掉空白字符 
        $table = preg_replace("&#39;([\r\n])[\s]+&#39;","",$table); 
        $table = str_replace(" ","",$table); 
        $table = str_replace(" ","",$table); 
        
        $table = explode(&#39;{tr}&#39;, $table); 
        array_pop($table); 
        foreach ($table as $key=>$tr) { 
                $td = explode(&#39;{td}&#39;, $tr); 
                array_pop($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,$distinct=true) { 
        preg_match_all(&#39;/([a-zA-Z]+)/&#39;,$str,$match); 
        if ($distinct == true) { 
                $match[1] = array_unique($match[1]); 
        } 
        sort($match[1]); 
        return $match[1]; 
}
 
</td[^></tr[^></table[^></td[^></a\s+href=["|\&#39;]?([^></td[^></tr[^></table[^></td[^></a\s+href=["|\&#39;]?([^>
Salin selepas log masuk