PHP 采集程序中常用的函數

復制代碼 代碼如下:
//獲得當前的腳本網址
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;
}

//把全角數字轉為半角數字
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標記
function Text2Html($txt)
{
$txt = str_replace(” “,”　”,$txt);
$txt = str_replace(”<”,”<”,$txt);
$txt = str_replace(”>”,”>”,$txt);
$txt = preg_replace(”/[\r\n]{1,}/isU”,”<br/>\r\n”,$txt);
return $txt;
}

//清除HTML標記
function ClearHtml($str)
{
$str = str_replace('<','<',$str);
$str = str_replace('>','>',$str);
return $str;
}

//相對路徑轉化成絕對路徑
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 $new_content;
}
//取得所有鏈接
function get_all_url($code){
preg_match_all('/<a\s+href=[”|\']?([^>”\' ]+)[”|\']?\s*[^>]*>([^>]+)<\/a>/i',$code,$arr);
return array('name'=>$arr[2],'url'=>$arr[1]);
}

//獲取指定標記中的內容
function get_tag_data($str, $start, $end)
{
if ( $start == ” || $end == ” )
{
return;
}
$str = explode($start, $str);
$str = explode($end, $str[1]);
return $str[0];
}

//HTML表格的每行轉為CSV格式數組
function get_tr_array($table)
{
$table = preg_replace(”‘<td[^>]*?>'si”,'”‘,$table);
$table = str_replace(”</td>”,'”,',$table);
$table = str_replace(”</tr>”,”{tr}”,$table);
//去掉 HTML 標記
$table = preg_replace(”‘<[\/\!]*?[^<>]*?>'si”,””,$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;
}

//將HTML表格的每行每列轉為數組，采集表格數據
function 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 標記
$table = preg_replace(”‘<[\/\!]*?[^<>]*?>'si”,””,$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單詞 $distinct=true 去除重復
function split_en_str($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];
}