Funciones de uso común en programas de colección PHP

//获得当前的脚本网址
función get_php_url(){
if(!empty($_SERVER["REQUEST_URI"])){
$scriptName = $_SERVER["REQUEST_URI"];
$nowurl = $scriptName;
}demás{
$scriptName = $_SERVER["PHP_SELF"];
if(empty($_SERVER["QUERY_STRING"])) $nowurl = $scriptName;
else $nowurl = $scriptName."?".$_SERVER["QUERY_STRING"];
}
devolver $nowurl;
}
//把全角数字转为半角数字
función GetAlabNum($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);
si($fnum=="") $fnum=0;
devolver $fnum;
}
//去除HTML标记
función Texto2Html($txt){
$txt = str_replace(" "," ",$txt);
$txt = str_replace("<","&lt;",$txt);
$txt = str_replace(">","&gt;",$txt);
$txt = preg_replace("/[rn]{1,}/isU","<br/>rn",$txt);
devolver $texto;
}

//清除HTML标记
función ClearHtml($cadena){
$cadena = str_replace('<','&lt;',$cadena);
$cadena = str_replace('>','&gt;',$cadena);
devolver $cadena;
}
//相对路径转化成绝对路径
función relativa_a_absoluta($contenido, $feed_url) {
preg_match('/(http|https|ftp):///', $feed_url, $protocolo);
$server_url = preg_replace("/(http|https|ftp|noticias):///", "", $feed_url);
$server_url = preg_replace("//.*/", "", $server_url);

si ($servidor_url == '') {
devolver $contenido;
}

if (isset($protocolo[0])) {
$new_content = preg_replace('/href="//', 'href="'.$protocol[0].$server_url.'/', $content);
$new_content = preg_replace('/src="//', 'src="'.$protocol[0].$server_url.'/', $new_content);
} demás {
$nuevo_contenido = $contenido;
}
devolver $nuevo_contenido;
}
//取得所有链接
función get_all_url($código){
preg_match_all('/<as+href=["|']?([^>"' ]+)["|']?s*[^>]*>([^>]+ )</a>/i',$código,$arr);
return array('nombre'=>$arr[2],'url'=>$arr[1]);
}

//获取指定标记中的内容
función get_tag_data($cadena, $inicio, $fin){
si ( $inicio == '' || $fin == '' ){
devolver;
}
$cadena = explotar($inicio, $cadena);
$cadena = explotar($end, $cadena[1]);
devolver $cadena[0];
}
//HTML 表格的每行转为CSV格式数组
función get_tr_array($tabla) {
$table = preg_replace("'<td[^>]*?>'si",'"',$table);
$tabla = str_replace("</td>",'",',$tabla);
$tabla = str_replace("</tr>","{tr}",$tabla);
//去掉 HTML 标记
$table = preg_replace("'<[/!]*?[^<>]*?>'si","",$table);
//去掉空白字符
$tabla = preg_replace("'([rn])[s]+'","",$tabla);
$tabla = str_replace(" ","",$tabla);
$tabla = str_replace(" ","",$tabla);

$tabla = explotar(",{tr}",$tabla);
array_pop($tabla);
devolver $tabla;
}

//将HTML表格的每行每列转为数组，采集表格数据
función get_td_array($tabla) {
$table = preg_replace("'<table[^>]*?>'si","",$table);
$table = preg_replace("'<tr[^>]*?>'si","",$table);
$table = preg_replace("'<td[^>]*?>'si","",$table);
$tabla = str_replace("</tr>","{tr}",$tabla);
$tabla = str_replace("</td>","{td}",$tabla);
//去掉 HTML 标记
$table = preg_replace("'<[/!]*?[^<>]*?>'si","",$table);
//去掉空白字符
$tabla = preg_replace("'([rn])[s]+'","",$tabla);
$tabla = str_replace(" ","",$tabla);
$tabla = str_replace(" ","",$tabla);

$tabla = explotar('{tr}', $tabla);
array_pop($tabla);
foreach ($tabla como $clave=>$tr) {
$td = explotar('{td}', $tr);
array_pop($td);
$td_array[] = $td;
}
devolver $td_array;
}

//返回字符串中的所有单词 $distinct=true 去除重复
función split_en_str($cadena,$distinct=true) {
preg_match_all('/([a-zA-Z]+)/',$str,$match);
si ($distinto == verdadero) {
$partido[1] = array_unique($partido[1]);
}
ordenar($coincidencia[1]);
devolver $partido[1];
}