Fonctions couramment utilisées dans les programmes de collecte PHP

//获得当前的脚本网址
fonction get_php_url(){
si(!empty($_SERVER["REQUEST_URI"])){
$scriptName = $_SERVER["REQUEST_URI"];
$nowurl = $scriptName ;
}autre{
$scriptName = $_SERVER["PHP_SELF"];
if(empty($_SERVER["QUERY_STRING"])) $nowurl = $scriptName;
sinon $nowurl = $scriptName."?".$_SERVER["QUERY_STRING"];
}
renvoie $nowurl ;
}
//把全角数字转为半角数字
fonction GetAlabNum($fnum){
$nums = array("０","１","２","３","４","５","６","７","８","９");
$fnums = "0123456789" ;
pour($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;
renvoie $fnum ;
}
//去除HTML标记
fonction Text2Html($txt){
$txt = str_replace(" "," ",$txt);
$txt = str_replace("<","&lt;",$txt);
$txt = str_replace(">","&gt;",$txt);
$txt = preg_replace("/[rn]{1,}/isU","<br/>rn",$txt);
renvoie $txt ;
}

//清除HTML标记
fonction ClearHtml($str){
$str = str_replace('<','&lt;',$str);
$str = str_replace('>','&gt;',$str);
retourner $ str ;
}
//相对路径转化成绝对路径
fonction 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);

si ($server_url == '') {
renvoie $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);
} autre {
$nouveau_content = $contenu ;
}
renvoie $new_content ;
}
//取得所有链接
fonction get_all_url($code){
preg_match_all('/<as+href=["|']?([^>"' ]+)["|']?s*[^>]*>([^>]+ )</a>/i',$code,$arr);
return array('name'=>$arr[2],'url'=>$arr[1]);
}

//获取指定标记中的内容
fonction get_tag_data($str, $start, $end){
si ( $start == '' || $end == '' ){
retour;
}
$str = exploser($start, $str);
$str = exploser($end, $str[1]);
renvoie $str[0] ;
}
// Version HTML relative aux fichiers CSV
fonction get_tr_array($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
$table = preg_replace("'([rn])[s]+'","",$table);
$table = str_replace(" ","",$table);
$table = str_replace(" ","",$table);

$table = exploser(",{tr}",$table);
array_pop($table);
retourner $table;
}

//L'utilisation du HTML dans les pages Web
fonction 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
$table = preg_replace("'([rn])[s]+'","",$table);
$table = str_replace(" ","",$table);
$table = str_replace(" ","",$table);

$table = exploser('{tr}', $table);
array_pop($table);
foreach ($table comme $key=>$tr) {
$td = exploser('{td}', $tr);
array_pop($td);
$td_array[] = $td;
}
renvoie $td_array ;
}

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