مشكل مع الدالة file_get_contents

[zamile28]

كل الطرق المجربة فوق تعمل فقط يبدو الشروق غير موجود مرة يظهر ومرة يختفي عندهم مشاكل بالسرفر

[apitos]

بعد تتبع الاخطاء تمكنت من الحصول على نتيجة سوى ان حروفها ليست مفهومة.

هكذا :

xœì}ÙrW–à3ù×ДHµEì+7lËSÕm«<¶ª—©®@$€$™b g&DI튰J,†#&æibž:\*›-‰¦%ÙÅz­Ÿ�û±¿dÎ9wÉ›@€iz¦h‹2ï~Ï=çܳ.¾õþ¯ß»ù/_gk~ÛfÿæÝõKÍe2ÿTx/“yÿæûìŸyó£Y.e7]£ãY¾åt;“¹~#ÅRk¾ßÏd666Ò…´ã®fn~’¹ƒmå°²ø8çk5Ó-¿•Zž^¤ï´íŽ·”ÐL®V«ñÚ)fÕ¥”Ù™ûͧ)¬1zвܥ”ëÛÐæ4ƒŸéÅ·ææ Ø¢×t­®Ou{ƪ¹”ºeÜ6øÃóÜf¨Ó¶Ùê4vþe\sÕ2áwÇèÙ~¦m®Óõæ¦ofŒ”4ït N+}ËK1ÿnZöÍ;~Fk~™-føÇe67·<=µ¸f-üÛ0<“­¹æJ¨w³¹æ¸NoÝéØVǤA®‘I±Öñ-ß6áÃTçèQÿuÿàhëè
ë?…?<Ù9Ú>z¯éÿÅŒ,¾Ø6}ƒa/sæg=ëöRê=§ã›î&:Åšü›=.ôk®®gúK=e®*º§f:Fæ¹jÂJ¸‹s¾ÕÖÛÈy¢4L`¹¦½”òLÃm®É%2º]ÛjRÝŒÓ5;ümËäËOß¾ƒ;=êÒ`ŸRéîZ:ÁI/¥†­ ÿO¦×6½5ÓôC»Ùô¼ÑG㯙mÓË�b½L×î­Zz×±í4µ]™Éwé[ÍuÓ=¯ÞZ-õ¶ÙéÉ

[zamile28]

إليك هذه تجربة كاملة وهي ناجحة جدا جلب الإفتتاحية ووضعها في ملف نصي

<?php
/**
* See <a href="http://www.bin-co.com/php/scripts/load/
" title="http://www.bin-co.com/php/scripts/load/
" rel="nofollow">http://www.bin-co.com/php/scripts/load/
</a> * Version : 1.00.A
*/
function load($url,$options=array('method'=>'get','return_info'=>false)) {
    $url_parts = parse_url($url);
    $info = array(//Currently only supported by curl.
        'http_code'    => 200
    );
    $response = '';

    $send_header = array(
        'Accept' => 'text/*',
        'User-Agent' => 'BinGet/1.00.A (<a href="http://www.bin-co.com/php/scripts/load/" title="http://www.bin-co.com/php/scripts/load/" rel="nofollow">http://www.bin-co.com/php/scripts/load/</a>)'
    );

    ///////////////////////////// Curl /////////////////////////////////////
    //If curl is available, use curl to get the data.
    if(function_exists("curl_init")
                and (!(isset($options['use']) and $options['use'] == 'fsocketopen'))) { //Don't user curl if it is specifically stated to user fsocketopen in the options
        if(isset($options['method']) and $options['method'] == 'post') {
            $page = $url_parts['scheme'] . '://' . $url_parts['host'] . $url_parts['path'];
        } else {
            $page = $url;
        }

        $ch = curl_init($url_parts['host']);

        curl_setopt($ch, CURLOPT_URL, $page);
        curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); //Just return the data - not print the whole thing.
        curl_setopt($ch, CURLOPT_HEADER, true); //We need the headers
        curl_setopt($ch, CURLOPT_NOBODY, false); //The content - if true, will not download the contents
        if(isset($options['method']) and $options['method'] == 'post' and $url_parts['query']) {
            curl_setopt($ch, CURLOPT_POST, true);
            curl_setopt($ch, CURLOPT_POSTFIELDS, $url_parts['query']);
        }
        //Set the headers our spiders sends
        curl_setopt($ch, CURLOPT_USERAGENT, $send_header['User-Agent']); //The Name of the UserAgent we will be using ;)
        $custom_headers = array("Accept: " . $send_header['Accept'] );
        if(isset($options['modified_since']))
            array_push($custom_headers,"If-Modified-Since: ".gmdate('D, d M Y H:i:s \G\M\T',strtotime($options['modified_since'])));
        curl_setopt($ch, CURLOPT_HTTPHEADER, $custom_headers);

        curl_setopt($ch, CURLOPT_COOKIEJAR, "cookie.txt"); //If ever needed...
        curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 0);
        curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, FALSE);

        if(isset($url_parts['user']) and isset($url_parts['pass'])) {
            $custom_headers = array("Authorization: Basic ".base64_encode($url_parts['user'].':'.$url_parts['pass']));
            curl_setopt($ch, CURLOPT_HTTPHEADER, $custom_headers);
        }

        $response = curl_exec($ch);
        $info = curl_getinfo($ch); //Some information on the fetch
        curl_close($ch);

    //////////////////////////////////////////// FSockOpen //////////////////////////////
    } else { //If there is no curl, use fsocketopen
        if(isset($url_parts['query'])) {
            if(isset($options['method']) and $options['method'] == 'post')
                $page = $url_parts['path'];
            else
                $page = $url_parts['path'] . '?' . $url_parts['query'];
        } else {
            $page = $url_parts['path'];
        }

        $fp = fsockopen($url_parts['host'], 80, $errno, $errstr, 30);
        if ($fp) {
            $out = '';
            if(isset($options['method']) and $options['method'] == 'post' and isset($url_parts['query'])) {
                $out .= "POST $page HTTP/1.1\r\n";
            } else {
                $out .= "GET $page HTTP/1.0\r\n"; //HTTP/1.0 is much easier to handle than HTTP/1.1
            }
            $out .= "Host: $url_parts[host]\r\n";
            $out .= "Accept: $send_header[Accept]\r\n";
            $out .= "User-Agent: {$send_header['User-Agent']}\r\n";
            if(isset($options['modified_since']))
                $out .= "If-Modified-Since: ".gmdate('D, d M Y H:i:s \G\M\T',strtotime($options['modified_since'])) ."\r\n";

            $out .= "Connection: Close\r\n";

            //HTTP Basic Authorization support
            if(isset($url_parts['user']) and isset($url_parts['pass'])) {
                $out .= "Authorization: Basic ".base64_encode($url_parts['user'].':'.$url_parts['pass']) . "\r\n";
            }

            //If the request is post - pass the data in a special way.
            if(isset($options['method']) and $options['method'] == 'post' and $url_parts['query']) {
                $out .= "(anti-spam-(anti-spam-(anti-spam-(anti-spam-(anti-spam-content-type:))))) application/x-www-form-urlencoded\r\n";
                $out .= 'Content-Length: ' . strlen($url_parts['query']) . "\r\n";
                $out .= "\r\n" . $url_parts['query'];
            }
            $out .= "\r\n";

            fwrite($fp, $out);
            while (!feof($fp)) {
                $response .= fgets($fp, 128);
            }
            fclose($fp);
        }
    }

    //Get the headers in an associative array
    $headers = array();

    if($info['http_code'] == 404) {
        $body = "";
        $headers['Status'] = 404;
    } else {
        //Seperate header and content
        $separator_position = strpos($response,"\r\n\r\n");
        $header_text = substr($response,0,$separator_position);
        $body = substr($response,$separator_position+4);

        foreach(explode("\n",$header_text) as $line) {
            $parts = explode(": ",$line);
            if(count($parts) == 2) $headers[$parts[0]] = chop($parts[1]);
        }
    }

    if($options['return_info']) return array('headers' => $headers, 'body' => $body, 'info' => $info);
    return $body;
}

//$contents = load('http://www.echoroukonline.com/ara/national/76746.html');


 function between($string, $start, $end)
{
    $out    = explode($start, $string);

    if(isset($out[1]))
    {
        $string = explode($end, $out[1]);
        return $string[0];
    }

    return '';
}
/*
 function get_top()
{
    $open   = load('http://www.echoroukonline.com/ara/national/76746.html');

    $code   = between($open, '<div id="meme_rubrique_int">', '</div>');

    return $code;
}
echo get_top();
 */
 
  function get_top()
{
    $open   = load('http://www.echoroukonline.com/ara/editorial/index.1.html');

    $code   = between($open, '<div id="category_right_col_int">', '<div id="box_pagination">');

    return $code;
}
//echo get_top();


$key =  get_top().''. "\r\n";
$sitemap_file    = fopen('echoroukonline.txt','w+');
fwrite($sitemap_file, $key);
fclose($sitemap_file);
?>

[apitos]

اهلا اخي zamile28.

الكود يعمل ولكنه يجلب كل الافتتاحيات وليس الافتتاحية الاخيرة فقط.

قمت بتجريب عدة اكواد واستقرت تجاربي على هذا الكود.

ولكن فيه مشكلتين :

1 - حين استعمل طريقة العرض هاته لا احصل على شيء :

echo '
<div class="unit">
    <a href="{$sUrl2}">{$aTitles}</a>
    <div>{$aMetas}</div>
    <div>{$aDescriptions}</div>
</div>';

echo '</div>'; 

2 - وحين استعمل هذه الطريقة احصل على نص ولكن الحروف غير مفهومة بتاتا :

echo "<br />".$aTitles."<br />".$aMetas."<br />".$aDescriptions."<br />"; 

الكود كاملا :

<?php
set_time_limit(0);

$sUrl = 'http://www.echoroukonline.com/ara/editorial/index.1.html';
$sUrlSrc = getWebsiteContent($sUrl,0);

// Load the source
$dom = new DOMDocument("UTF-8");
@$dom->loadHTML($sUrlSrc);

$xpath = new DomXPath($dom);

// ===================================      step 1 - links:

$vRes = $xpath->query("/html/body/div/div[2]/div/div[2]/div[4]/div/div/div/h2/a");

// ===================================      step 2 - titles:

$aLinks = $vRes->item(0)->getAttribute("href");

echo "<br />aLinks : ".$aLinks."<br />";
$sUrl2 = 'http://www.echoroukonline.com/ara/'.$aLinks;

echo "<br />sUrl2 : ".$sUrl2."<br />";
$sUrlSrc2 = getWebsiteContent($sUrl2,1);

@$dom->loadHTML($sUrlSrc2);
$xpath = new DomXPath($dom);

// ===================================      step 3 - titles:

$vRes = $xpath->query(".//*[@id='article_holder']/h1");
$aTitles= $vRes->item(0)->nodeValue;

// ===================================      step 4 - Metas:

$vRes = $xpath->query(".//*[@class='article_metadata']");
$aMetas= $vRes->item(0)->nodeValue;

//====================================      step 5 - descriptions:

$vRes = $xpath->query(utf8_encode(".//*[@id='article_body']"));
$aDescriptions= $vRes->item(0)->nodeValue;

//=============================

echo '<link href="css/styles.css" type="text/css" rel="stylesheet"/><div class="main">';
echo '<h1>Using xpath for dom html</h1>';

//echo "<br />".$aTitles."<br />".$aMetas."<br />".$aDescriptions."<br />";

echo '
<div class="unit">
    <a href="{$sUrl2}">{$aTitles}</a>
    <div>{$aMetas}</div>
    <div>{$aDescriptions}</div>
</div>';

echo '</div>';

// this function will return page content using caches (we will load original sources not more than once per hour)
function getWebsiteContent($sUrl,$f=0) {
    // our folder with cache files
    $sCacheFolder = 'cache/';

    // cache filename
    if ($f==0) {
    $sFilename = 'ech-'.date('YmdHi').'.html';
    } else {
    $sFilename = 'eftch-'.date('YmdHi').'.html';
    }
    
    if (! file_exists($sCacheFolder.$sFilename)) {
        $ch = curl_init($sUrl);
        $fp = fopen($sCacheFolder.$sFilename, 'w');
        curl_setopt($ch, CURLOPT_FILE, $fp);
        curl_setopt($ch, CURLOPT_HEADER, 0);
        curl_setopt($ch, CURLOPT_HTTPHEADER, Array('User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.15) Gecko/20080623 Firefox/2.0.0.15'));
        curl_exec($ch);
        curl_close($ch);
        fclose($fp);
    }
    //return file_get_contents($sCacheFolder.$sFilename);
    return file_get_contents_utf8($sCacheFolder.$sFilename);
    
}
function file_get_contents_utf8($fn) {
     $content = file_get_contents($fn);
      return mb_convert_encoding($content, 'UTF-8',
          mb_detect_encoding($content, 'UTF-8, ISO-8859-1', true));
}

?>

شكراً.

[zamile28]

رغبة في مساعدتك قمت بعدة تجارب والنتيجة النهائية هذه

تعرض اي جزء من الإفتتاحية

<?php
/**
* See <a href="http://www.bin-co.com/php/scripts/load/
" title="http://www.bin-co.com/php/scripts/load/
" rel="nofollow">http://www.bin-co.com/php/scripts/load/
</a> * Version : 1.00.A
*/
function load($url,$options=array('method'=>'get','return_info'=>false)) {
    $url_parts = parse_url($url);
    $info = array(//Currently only supported by curl.
        'http_code'    => 200
    );
    $response = '';

    $send_header = array(
        'Accept' => 'text/*',
        'User-Agent' => 'BinGet/1.00.A (<a href="http://www.bin-co.com/php/scripts/load/" title="http://www.bin-co.com/php/scripts/load/" rel="nofollow">http://www.bin-co.com/php/scripts/load/</a>)'
    );

    ///////////////////////////// Curl /////////////////////////////////////
    //If curl is available, use curl to get the data.
    /*
    if(function_exists("curl_init")
                and (!(isset($options['use']) and $options['use'] == 'fsocketopen'))) { //Don't user curl if it is specifically stated to user fsocketopen in the options
        if(isset($options['method']) and $options['method'] == 'post') {
            $page = $url_parts['scheme'] . '://' . $url_parts['host'] . $url_parts['path'];
        } else {
            $page = $url;
        }

        $ch = curl_init($url_parts['host']);

        curl_setopt($ch, CURLOPT_URL, $page);
        curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); //Just return the data - not print the whole thing.
        curl_setopt($ch, CURLOPT_HEADER, true); //We need the headers
        curl_setopt($ch, CURLOPT_NOBODY, false); //The content - if true, will not download the contents
        if(isset($options['method']) and $options['method'] == 'post' and $url_parts['query']) {
            curl_setopt($ch, CURLOPT_POST, true);
            curl_setopt($ch, CURLOPT_POSTFIELDS, $url_parts['query']);
        }
        //Set the headers our spiders sends
        curl_setopt($ch, CURLOPT_USERAGENT, $send_header['User-Agent']); //The Name of the UserAgent we will be using ;)
        $custom_headers = array("Accept: " . $send_header['Accept'] );
        if(isset($options['modified_since']))
            array_push($custom_headers,"If-Modified-Since: ".gmdate('D, d M Y H:i:s \G\M\T',strtotime($options['modified_since'])));
        curl_setopt($ch, CURLOPT_HTTPHEADER, $custom_headers);

        curl_setopt($ch, CURLOPT_COOKIEJAR, "cookie.txt"); //If ever needed...
        curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 0);
        curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, FALSE);

        if(isset($url_parts['user']) and isset($url_parts['pass'])) {
            $custom_headers = array("Authorization: Basic ".base64_encode($url_parts['user'].':'.$url_parts['pass']));
            curl_setopt($ch, CURLOPT_HTTPHEADER, $custom_headers);
        }

        $response = curl_exec($ch);
        $info = curl_getinfo($ch); //Some information on the fetch
        curl_close($ch);

    //////////////////////////////////////////// FSockOpen //////////////////////////////

     } else { //If there is no curl, use fsocketopen
     
     */
        if(isset($url_parts['query'])) {
            if(isset($options['method']) and $options['method'] == 'post')
                $page = $url_parts['path'];
            else
                $page = $url_parts['path'] . '?' . $url_parts['query'];
        } else {
            $page = $url_parts['path'];
        }

        $fp = fsockopen($url_parts['host'], 80, $errno, $errstr, 30);
        //  $fp = fopen($url_parts['host'], 80, $errno, $errstr, 30);
        if ($fp) {
            $out = '';
            if(isset($options['method']) and $options['method'] == 'post' and isset($url_parts['query'])) {
                $out .= "POST $page HTTP/1.1\r\n";
            } else {
                $out .= "GET $page HTTP/1.0\r\n"; //HTTP/1.0 is much easier to handle than HTTP/1.1
            }
            $out .= "Host: $url_parts[host]\r\n";
            $out .= "Accept: $send_header[Accept]\r\n";
            $out .= "User-Agent: {$send_header['User-Agent']}\r\n";
            if(isset($options['modified_since']))
                $out .= "If-Modified-Since: ".gmdate('D, d M Y H:i:s \G\M\T',strtotime($options['modified_since'])) ."\r\n";

            $out .= "Connection: Close\r\n";

            //HTTP Basic Authorization support
            if(isset($url_parts['user']) and isset($url_parts['pass'])) {
                $out .= "Authorization: Basic ".base64_encode($url_parts['user'].':'.$url_parts['pass']) . "\r\n";
            }

            //If the request is post - pass the data in a special way.
            if(isset($options['method']) and $options['method'] == 'post' and $url_parts['query']) {
                $out .= "(anti-spam-(anti-spam-(anti-spam-content-type:))) application/x-www-form-urlencoded\r\n";
                $out .= 'Content-Length: ' . strlen($url_parts['query']) . "\r\n";
                $out .= "\r\n" . $url_parts['query'];
            }
            $out .= "\r\n";

            fwrite($fp, $out);
            while (!feof($fp)) {
                $response .= fgets($fp, 128);
            }
            fclose($fp);
        }
  //  }

    //Get the headers in an associative array
    $headers = array();

    if($info['http_code'] == 404) {
        $body = "";
        $headers['Status'] = 404;
    } else {
        //Seperate header and content
        $separator_position = strpos($response,"\r\n\r\n");
        $header_text = substr($response,0,$separator_position);
        $body = substr($response,$separator_position+4);

        foreach(explode("\n",$header_text) as $line) {
            $parts = explode(": ",$line);
            if(count($parts) == 2) $headers[$parts[0]] = chop($parts[1]);
        }
    }

    if($options['return_info']) return array('headers' => $headers, 'body' => $body, 'info' => $info);
    return $body;
}

//$contents = load('http://www.echoroukonline.com/ara/national/76746.html');


 function between($string, $start, $end)
{
    $out    = explode($start, $string);

    if(isset($out[1]))
    {
        $string = explode($end, $out[1]);
        return $string[0];
    }

    return '';
}
/*
 function get_top()
{
    $open   = load('http://www.echoroukonline.com/ara/national/76746.html');

    $code   = between($open, '<div id="meme_rubrique_int">', '</div>');

    return $code;
}
echo get_top();
 */
/*
  function get_top()
{
    $open   = load('http://www.echoroukonline.com/ara/editorial/index.1.html');

    $code   = between($open, '<div id="category_right_col_int">', '<div id="box_pagination">');

    return $code;
}
*/
//echo get_top();
  $open   = load('http://www.echoroukonline.com/ara/editorial/index.1.html');

// $result= file_get_contents('http://www.echoroukonline.com/ara/editorial/index.1.html');
 
preg_match_all('#<div class="short_holder_rubrique">(.+?)</div>#smi',  $open,$echoroukonline);
$editorial1=strip_tags($echoroukonline[1][0]);
$editorial2=strip_tags($echoroukonline[1][1]);
$editorial3=strip_tags($echoroukonline[1][2]);
$editorial4=strip_tags($echoroukonline[1][3]);
echo"<br>";
echo $editorial1;
echo"<br>";
echo $editorial2;
echo"<br>";
echo $editorial3;
echo"<br>";
echo $editorial4;
echo"<br>";
/*
$key =  get_top().''. "\r\n";
$sitemap_file    = fopen('echoroukonline.txt','w+');
fwrite($sitemap_file, $key);
fclose($sitemap_file);
*/
 // ### Checks for presence of the cURL extension.
//function _iscurlinstalled() {
//    if  (in_array  ('curl', get_loaded_extensions())) {
//        return true;
//    }
//    else{
    //    return false;
//    }
//}

//Sample usage:

//if (_iscurlinstalled()) echo "cURL is installed"; else echo "cURL is NOT installed";

?>

اعرض اي خبر بالطريقة هذه حسب الترتيب اطن هناك 11 يعني الاخيرة

$editorial11=strip_tags($echoroukonline[1][11]); 

خبرني إذا نجحت

[apitos]

اهلا اخي زميل وبارك الله فيك على مد يد المساعدة،

هناك نتائج ولكن اظن ان الدالة fsockopen ليست متوفرة في كل السيرفرات.

كما اني اريد محتوى آخر افتتاحية تم اضافتها.

وحتى آخر كود قمت بوضعه يعمل جيدا الا ان فيه مشكلة ظهور الحروف العربية كما اسلفت.

[zamile28]

الطريقة التي اعطيتك فوق تعمل ب curl و fsockopen

فقط إفتح اعلي الاكواد /* ليعمل curl اغلقتها لان لا تعمل عندي
جرب هذه خفيفة وسريعة في جلب اخر مقال

للعلم احيانا هماك تسع مقالات في الإفتتاحية واحيانا هناك عشرة فقط غير الرقم حسب العدد ارجو انك فهمت

<?php
header("(anti-spam-content-type:) text/html; charset=utf-8");
 function getHtmlCodeViaCurl($url){
        $userAgent=array();
        $userAgent[]="Opera/9.50 (Windows NT 5.1; U; en)";
        $userAgent[]="Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.13 (KHTML, like Gecko) Version/3.1 Safari/525.13";
        $userAgent[]="Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; FDM; MEGAUPLOAD 1.0; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30)";
        $userAgent[]="Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.12) Gecko/20080201 Firefox/2.0.0.12";
        $userAgent[]="Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; FDM; MEGAUPLOAD 1.0; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30)";
        $userAgent[]="Mozilla/5.0 (Windows; U; Windows NT 5.1; en) AppleWebKit/522.15.5 (KHTML, like Gecko) Version/3.0.3 Safari/522.15.5";
        $total1=count($userAgent)-1;
        $rand1=rand(0,$total1);


        $curl = curl_init() or die("FATAL ERROR: cURL support is not found on this server.");
        curl_setopt($curl, CURLOPT_USERAGENT, $userAgent[$rand1]);
        curl_setopt($curl, CURLOPT_URL, $url);
        curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
        curl_setopt($curl, CURLOPT_TIMEOUT, 20);
        return curl_exec($curl);
    }

$url = 'http://www.echoroukonline.com/ara/editorial/index.1.html';
$open =  getHtmlCodeViaCurl($url);

preg_match_all('#<div class="short_holder_rubrique">(.+?)</div>#smi', $open,$echoroukonline);

$editorial9=strip_tags($echoroukonline[1][9]);

echo"<br>";
echo $editorial9;
echo"<br>";


 ?>

[apitos]

اهلا اخي زميل28،

هذا الرابط يحوي قاءمة مختصرة لمواضيع الافتتاحيات :

http://www.echoroukonline.com/ara/editorial/index.1.html

ولكن اريد الحصول على الموضوع كاملا لاخر افتتاحية تم اضافتها ويكون رابطها هكذا :

http://www.echoroukonline.com/ara/editorial/77456.html

شكراً.

[zamile28]

ساعطيك المفتاح والباقي عليك

هذه لجلب اخر مقال بالإفتتاحية
غير عدل كما تشاء

<?php
header("(anti-spam-content-type:) text/html; charset=utf-8");
function load($url,$options=array('method'=>'get','return_info'=>false)) {
    $url_parts = parse_url($url);
    $info = array(//Currently only supported by curl.
        'http_code'    => 200
    );
    $response = '';

    $send_header = array(
        'Accept' => 'text/*',
        'User-Agent' => 'BinGet/1.00.A (<a href="http://www.bin-co.com/php/scripts/load/" title="http://www.bin-co.com/php/scripts/load/" rel="nofollow">http://www.bin-co.com/php/scripts/load/</a>)'
    );

    ///////////////////////////// Curl /////////////////////////////////////
    //If curl is available, use curl to get the data.

    if(function_exists("curl_init")
                and (!(isset($options['use']) and $options['use'] == 'fsocketopen'))) { //Don't user curl if it is specifically stated to user fsocketopen in the options
        if(isset($options['method']) and $options['method'] == 'post') {
            $page = $url_parts['scheme'] . '://' . $url_parts['host'] . $url_parts['path'];
        } else {
            $page = $url;
        }

        $ch = curl_init($url_parts['host']);

        curl_setopt($ch, CURLOPT_URL, $page);
        curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); //Just return the data - not print the whole thing.
        curl_setopt($ch, CURLOPT_HEADER, true); //We need the headers
        curl_setopt($ch, CURLOPT_NOBODY, false); //The content - if true, will not download the contents
        if(isset($options['method']) and $options['method'] == 'post' and $url_parts['query']) {
            curl_setopt($ch, CURLOPT_POST, true);
            curl_setopt($ch, CURLOPT_POSTFIELDS, $url_parts['query']);
        }
        //Set the headers our spiders sends
        curl_setopt($ch, CURLOPT_USERAGENT, $send_header['User-Agent']); //The Name of the UserAgent we will be using ;)
        $custom_headers = array("Accept: " . $send_header['Accept'] );
        if(isset($options['modified_since']))
            array_push($custom_headers,"If-Modified-Since: ".gmdate('D, d M Y H:i:s \G\M\T',strtotime($options['modified_since'])));
        curl_setopt($ch, CURLOPT_HTTPHEADER, $custom_headers);

        curl_setopt($ch, CURLOPT_COOKIEJAR, "cookie.txt"); //If ever needed...
        curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 0);
        curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, FALSE);

        if(isset($url_parts['user']) and isset($url_parts['pass'])) {
            $custom_headers = array("Authorization: Basic ".base64_encode($url_parts['user'].':'.$url_parts['pass']));
            curl_setopt($ch, CURLOPT_HTTPHEADER, $custom_headers);
        }

        $response = curl_exec($ch);
        $info = curl_getinfo($ch); //Some information on the fetch
        curl_close($ch);

    //////////////////////////////////////////// FSockOpen //////////////////////////////

     } else { //If there is no curl, use fsocketopen


        if(isset($url_parts['query'])) {
            if(isset($options['method']) and $options['method'] == 'post')
                $page = $url_parts['path'];
            else
                $page = $url_parts['path'] . '?' . $url_parts['query'];
        } else {
            $page = $url_parts['path'];
        }

        $fp = fsockopen($url_parts['host'], 80, $errno, $errstr, 30);
        //  $fp = fopen($url_parts['host'], 80, $errno, $errstr, 30);
        if ($fp) {
            $out = '';
            if(isset($options['method']) and $options['method'] == 'post' and isset($url_parts['query'])) {
                $out .= "POST $page HTTP/1.1\r\n";
            } else {
                $out .= "GET $page HTTP/1.0\r\n"; //HTTP/1.0 is much easier to handle than HTTP/1.1
            }
            $out .= "Host: $url_parts[host]\r\n";
            $out .= "Accept: $send_header[Accept]\r\n";
            $out .= "User-Agent: {$send_header['User-Agent']}\r\n";
            if(isset($options['modified_since']))
                $out .= "If-Modified-Since: ".gmdate('D, d M Y H:i:s \G\M\T',strtotime($options['modified_since'])) ."\r\n";

            $out .= "Connection: Close\r\n";

            //HTTP Basic Authorization support
            if(isset($url_parts['user']) and isset($url_parts['pass'])) {
                $out .= "Authorization: Basic ".base64_encode($url_parts['user'].':'.$url_parts['pass']) . "\r\n";
            }

            //If the request is post - pass the data in a special way.
            if(isset($options['method']) and $options['method'] == 'post' and $url_parts['query']) {
                $out .= "(anti-spam-content-type:) application/x-www-form-urlencoded\r\n";
                $out .= 'Content-Length: ' . strlen($url_parts['query']) . "\r\n";
                $out .= "\r\n" . $url_parts['query'];
            }
            $out .= "\r\n";

            fwrite($fp, $out);
            while (!feof($fp)) {
                $response .= fgets($fp, 128);
            }
            fclose($fp);
        }
    }

    //Get the headers in an associative array
    $headers = array();

    if($info['http_code'] == 404) {
        $body = "";
        $headers['Status'] = 404;
    } else {
        //Seperate header and content
        $separator_position = strpos($response,"\r\n\r\n");
        $header_text = substr($response,0,$separator_position);
        $body = substr($response,$separator_position+4);

        foreach(explode("\n",$header_text) as $line) {
            $parts = explode(": ",$line);
            if(count($parts) == 2) $headers[$parts[0]] = chop($parts[1]);
        }
    }

    if($options['return_info']) return array('headers' => $headers, 'body' => $body, 'info' => $info);
    return $body;
}

 function getHtmlCodeViaCurl($url){
        $userAgent=array();
        $userAgent[]="Opera/9.50 (Windows NT 5.1; U; en)";
        $userAgent[]="Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.13 (KHTML, like Gecko) Version/3.1 Safari/525.13";
        $userAgent[]="Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; FDM; MEGAUPLOAD 1.0; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30)";
        $userAgent[]="Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.12) Gecko/20080201 Firefox/2.0.0.12";
        $userAgent[]="Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; FDM; MEGAUPLOAD 1.0; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30)";
        $userAgent[]="Mozilla/5.0 (Windows; U; Windows NT 5.1; en) AppleWebKit/522.15.5 (KHTML, like Gecko) Version/3.0.3 Safari/522.15.5";
        $total1=count($userAgent)-1;
        $rand1=rand(0,$total1);


        $curl = curl_init() or die("FATAL ERROR: cURL support is not found on this server.");
        curl_setopt($curl, CURLOPT_USERAGENT, $userAgent[$rand1]);
        curl_setopt($curl, CURLOPT_URL, $url);
        curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
        curl_setopt($curl, CURLOPT_TIMEOUT, 20);
        return curl_exec($curl);
    }

$url = 'http://www.echoroukonline.com/ara/editorial/index.1.html';
//$open =  getHtmlCodeViaCurl($url);
$open = load($url);
//preg_match_all('#<div class="short_holder_rubrique">(.+?)</div>#smi', $open,$echoroukonline);
//$editorial9=strip_tags($echoroukonline[1][9]);
preg_match_all('#<span class="summary">(.+?)</span>#smi', $open,$echoroukonline);
$editorial9=strip_tags($echoroukonline[1][10]);

preg_match_all('#<span class="visit">(.+?)</span>#smi', $open,$echoroukonline);
$editorialurl=$echoroukonline[1][9];
preg_match("~<a href=\"(.*?)\">~i", $editorialurl, $epiurl);
$editoriallink =$epiurl[1];

echo"<br>";
echo $editorial9;
echo"<br>";
echo $editorialurl;
echo"<br>";
echo "<a href='curl-echorouk2.php?id=".$editoriallink."'>المزيد</a>";
echo"<br>";
 ?>

وهذه لجلب المقال كاملا

<?php
header("(anti-spam-content-type:) text/html; charset=utf-8");
function load($url,$options=array('method'=>'get','return_info'=>false)) {
    $url_parts = parse_url($url);
    $info = array(//Currently only supported by curl.
        'http_code'    => 200
    );
    $response = '';

    $send_header = array(
        'Accept' => 'text/*',
        'User-Agent' => 'BinGet/1.00.A (<a href="http://www.bin-co.com/php/scripts/load/" title="http://www.bin-co.com/php/scripts/load/" rel="nofollow">http://www.bin-co.com/php/scripts/load/</a>)'
    );

    ///////////////////////////// Curl /////////////////////////////////////
    //If curl is available, use curl to get the data.

    if(function_exists("curl_init")
                and (!(isset($options['use']) and $options['use'] == 'fsocketopen'))) { //Don't user curl if it is specifically stated to user fsocketopen in the options
        if(isset($options['method']) and $options['method'] == 'post') {
            $page = $url_parts['scheme'] . '://' . $url_parts['host'] . $url_parts['path'];
        } else {
            $page = $url;
        }

        $ch = curl_init($url_parts['host']);

        curl_setopt($ch, CURLOPT_URL, $page);
        curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); //Just return the data - not print the whole thing.
        curl_setopt($ch, CURLOPT_HEADER, true); //We need the headers
        curl_setopt($ch, CURLOPT_NOBODY, false); //The content - if true, will not download the contents
        if(isset($options['method']) and $options['method'] == 'post' and $url_parts['query']) {
            curl_setopt($ch, CURLOPT_POST, true);
            curl_setopt($ch, CURLOPT_POSTFIELDS, $url_parts['query']);
        }
        //Set the headers our spiders sends
        curl_setopt($ch, CURLOPT_USERAGENT, $send_header['User-Agent']); //The Name of the UserAgent we will be using ;)
        $custom_headers = array("Accept: " . $send_header['Accept'] );
        if(isset($options['modified_since']))
            array_push($custom_headers,"If-Modified-Since: ".gmdate('D, d M Y H:i:s \G\M\T',strtotime($options['modified_since'])));
        curl_setopt($ch, CURLOPT_HTTPHEADER, $custom_headers);

        curl_setopt($ch, CURLOPT_COOKIEJAR, "cookie.txt"); //If ever needed...
        curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 0);
        curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, FALSE);

        if(isset($url_parts['user']) and isset($url_parts['pass'])) {
            $custom_headers = array("Authorization: Basic ".base64_encode($url_parts['user'].':'.$url_parts['pass']));
            curl_setopt($ch, CURLOPT_HTTPHEADER, $custom_headers);
        }

        $response = curl_exec($ch);
        $info = curl_getinfo($ch); //Some information on the fetch
        curl_close($ch);

    //////////////////////////////////////////// FSockOpen //////////////////////////////

     } else { //If there is no curl, use fsocketopen


        if(isset($url_parts['query'])) {
            if(isset($options['method']) and $options['method'] == 'post')
                $page = $url_parts['path'];
            else
                $page = $url_parts['path'] . '?' . $url_parts['query'];
        } else {
            $page = $url_parts['path'];
        }

        $fp = fsockopen($url_parts['host'], 80, $errno, $errstr, 30);
        //  $fp = fopen($url_parts['host'], 80, $errno, $errstr, 30);
        if ($fp) {
            $out = '';
            if(isset($options['method']) and $options['method'] == 'post' and isset($url_parts['query'])) {
                $out .= "POST $page HTTP/1.1\r\n";
            } else {
                $out .= "GET $page HTTP/1.0\r\n"; //HTTP/1.0 is much easier to handle than HTTP/1.1
            }
            $out .= "Host: $url_parts[host]\r\n";
            $out .= "Accept: $send_header[Accept]\r\n";
            $out .= "User-Agent: {$send_header['User-Agent']}\r\n";
            if(isset($options['modified_since']))
                $out .= "If-Modified-Since: ".gmdate('D, d M Y H:i:s \G\M\T',strtotime($options['modified_since'])) ."\r\n";

            $out .= "Connection: Close\r\n";

            //HTTP Basic Authorization support
            if(isset($url_parts['user']) and isset($url_parts['pass'])) {
                $out .= "Authorization: Basic ".base64_encode($url_parts['user'].':'.$url_parts['pass']) . "\r\n";
            }

            //If the request is post - pass the data in a special way.
            if(isset($options['method']) and $options['method'] == 'post' and $url_parts['query']) {
                $out .= "(anti-spam-content-type:) application/x-www-form-urlencoded\r\n";
                $out .= 'Content-Length: ' . strlen($url_parts['query']) . "\r\n";
                $out .= "\r\n" . $url_parts['query'];
            }
            $out .= "\r\n";

            fwrite($fp, $out);
            while (!feof($fp)) {
                $response .= fgets($fp, 128);
            }
            fclose($fp);
        }
    }

    //Get the headers in an associative array
    $headers = array();

    if($info['http_code'] == 404) {
        $body = "";
        $headers['Status'] = 404;
    } else {
        //Seperate header and content
        $separator_position = strpos($response,"\r\n\r\n");
        $header_text = substr($response,0,$separator_position);
        $body = substr($response,$separator_position+4);

        foreach(explode("\n",$header_text) as $line) {
            $parts = explode(": ",$line);
            if(count($parts) == 2) $headers[$parts[0]] = chop($parts[1]);
        }
    }

    if($options['return_info']) return array('headers' => $headers, 'body' => $body, 'info' => $info);
    return $body;
}
 function getHtmlCodeViaCurl($url){
        $userAgent=array();
        $userAgent[]="Opera/9.50 (Windows NT 5.1; U; en)";
        $userAgent[]="Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.13 (KHTML, like Gecko) Version/3.1 Safari/525.13";
        $userAgent[]="Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; FDM; MEGAUPLOAD 1.0; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30)";
        $userAgent[]="Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.12) Gecko/20080201 Firefox/2.0.0.12";
        $userAgent[]="Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; FDM; MEGAUPLOAD 1.0; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30)";
        $userAgent[]="Mozilla/5.0 (Windows; U; Windows NT 5.1; en) AppleWebKit/522.15.5 (KHTML, like Gecko) Version/3.0.3 Safari/522.15.5";
        $total1=count($userAgent)-1;
        $rand1=rand(0,$total1);


        $curl = curl_init() or die("FATAL ERROR: cURL support is not found on this server.");
        curl_setopt($curl, CURLOPT_USERAGENT, $userAgent[$rand1]);
        curl_setopt($curl, CURLOPT_URL, $url);
        curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
        curl_setopt($curl, CURLOPT_TIMEOUT, 20);
        return curl_exec($curl);
    }
 
$id=$_GET["id"];

$url = "http://www.echoroukonline.com/ara/".$id."";
//$open =  getHtmlCodeViaCurl($url);
$open = load($url);
//preg_match_all('#<div class="short_holder_rubrique">(.+?)</div>#smi', $open,$echoroukonline);
//$editorial9=strip_tags($echoroukonline[1][9]);
 //echo $url;
preg_match('#<div id="article_body">(.+?)</div>#smi', $open,$echoroukonline);
$editorial9=strip_tags($echoroukonline[1]);

echo"<br>";
echo $editorial9;
echo"<br>";


 ?>

تنبيه يجب ان يكون لديك سيرفر محلي انصحك ب appserv

فهو الافضل وشبيه بسيرفر حقيقي.


فعل curl

قم بعدة تجارب ضع مخطط واعمل عليه

[apitos]

حسنا اخي زميل.

شكرا لوقفتك معي وجزاك الله خيراً.