PHP采集程序中常用的函数

//获取当前的脚本网址
函数 get_php_url(){
if(!empty($_SERVER["REQUEST_URI"])){
$scriptName = $_SERVER["REQUEST_URI"];
$nowurl = $scriptName;
}别的{
$scriptName = $_SERVER["PHP_SELF"];
if(空($_SERVER["QUERY_STRING"])) $nowurl = $scriptName;
否则 $nowurl = $scriptName."?".$_SERVER["QUERY_STRING"];
}
返回$nowurl；
}
// 把全角数字转为半角数字
函数 GetAlabNum($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=="") $fnum=0;
返回$fnum；
}
// 增加HTML标记
函数 Text2Html($txt){
$txt = str_replace(" "," ",$txt);
$txt = str_replace("<","<",$txt);
$txt = str_replace(">",">",$txt);
$txt = preg_replace("/[rn]{1,}/isU","<br/>rn",$txt);
返回$txt；
}

//清除HTML标记
函数 ClearHtml($str){
$str = str_replace('<','<',$str);
$str = str_replace('>','>',$str);
返回$str；
}
//相对路径转化成绝对路径
函数relative_to_absolute($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);

如果（$server_url == ''）{
返回$内容；
}

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);
} 别的 {
$新内容=$内容；
}
返回$new_content；
}
//获取所有链接
函数 get_all_url($code){
preg_match_all('/<as+href=["|']?([^>"' ]+)["|']?s*[^>]*>([^>]+ )</a>/i',$code,$arr);
返回数组('name'=>$arr[2],'url'=>$arr[1]);
}

//获取指定标记中的内容
函数 get_tag_data($str, $start, $end){
if ( $start == '' || $end == '' ){
返回;
}
$str = 爆炸($start, $str);
$str = 爆炸($end, $str[1]);
返回$str[0]；
}
//HTML表格的每行转为CSV格式阵列
函数 get_tr_array($table) {
$table = preg_replace("'<td[^>]*?>'si",'"',$table);
$table = str_replace("</td>",'",',$table);
$table = str_replace("</tr>","{tr}",$table);
// 删除 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);

$表 = 爆炸(",{tr}",$表);
array_pop($表);
返回$表；
}

//将HTML表格的每行每列转为批量，采集表格数据
函数 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);
// 删除 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);

$table=explode('{tr}',$table);
array_pop($表);
foreach ($table as $key=>$tr) {
$td = 爆炸('{td}', $tr);
array_pop($td);
$td_array[] = $td;
}
返回$td_array；
}

//返回字符串中的所有单词 $distinct=true 去掉重复
函数 split_en_str($str,$distinct=true) {
preg_match_all('/([a-zA-Z]+)/',$str,$match);
如果（$distinct == true）{
$match[1] = array_unique($match[1]);
}
排序($match[1]);
返回$match[1]；
}