Need little help convertig fopen to curl please

[pilotcap232]

Hello, my current host has disabled fopen for security purposes, I have a search escript wich now it wont work, I will appreciate if someone can convert this file to use if with curl instead for fopen.
Thank you in advanced, any help will be much appreciated.

<?
	//DMOZ
	$DELAY = 5;
	$DMOZ_URL = "http://search.dmoz.org/cgi-bin/search?";
	$TRY_CONNECTIONS = 20;
	$SEARCHFEED_URL = "http://www.searchfeed.com/rd/feed/XMLFeed.jsp?";
	$RAGING_URL = "http://www.altavista.com/web/res_text?avkw=xytx&amb=txt&kls=0&kgs=0";
	//microseconds
	$TRY_PAUSE = 5;

function Pause($delay = 10){
	$ts = explode(" ", microtime());
	$start_t = $ts[0] + $ts[1]*1000;
	do{
		$ts = explode(" ", microtime());
		$c_t = $ts[0] + $ts[1]*1000;
	}while(($c_t - $start_t)<=$delay);
}	


function GetDMOZResults(&$results, $ss, $start = 1, $num = 1){
	global $DMOZ_URL;
	global $TRY_CONNECTIONS, $TRY_PAUSE;
	$results = array(
							"0" => array(
							"title"=>"",
							"link"=>"",
							"summary"=>"",
							"category"=>""
						 )
	);
	$link = $DMOZ_URL."search=".urlencode($ss)."&start=".$start;

	$cc = 1;
	while(!($fh = @fopen($link, 'r'))){
		if($cc==$TRY_CONNECTIONS) break;
		$cc++;
		Pause($TRY_PAUSE);
	}
	if($fh)
	{
		$buff = "";
		$tmp = "";
		$tmp_arr = array();
		while($buff = fread($fh, 256)){
			$tmp.=$buff;
		}
		fclose($fh);
                   	$sc = 0;
		if(preg_match("/Open Directory Sites.*?(\d+?)\)/", $tmp, $m1)){
			$sc = $m1[1];
                    }        
		$tmp = preg_replace("/^.*Open Directory Sites/", "", $tmp);
		$tmp = preg_replace("/<img.*?>/", "", $tmp);
		$count = 1;
		if(preg_match_all("/<li>(<a href=\"http:.*?)(?:<li>|<\/ol>)/s", $tmp, $matches)){
			foreach($matches[1] as $st){
				if($count<=$num&&$count<=$sc){
                                    if(preg_match("/^<a href=\"(.*?)\">(.*?)<\/a>(.*?)<br>.*?<a href=\".*?\">(.*?)<\/a>/s", $st, $m2)){
						$linkurl = $m2[1];
						$title = $m2[2];
						$summary = $m2[3];
						$category = $m2[4];
					}
//						print $count." - ".$title."<hr>";
						$results[$count] = array(
							"title"=>$title,
							"link"=>$linkurl,
							"summary"=>$summary,
							"category"=>$category
						);
						$count++;
					}else{
						break;
					}
				}
				return $sc;
			}else return "";
		}else{
			return "";
		}
	}


function PPCParseRecord_External($type, $record, $counter, $page, $rpp, $hs, $ss, $rest){
	global $PPC_RESULTS_PART, $CLICK_SCRIPT, $CLICK_TARGET, $MAIN_URL;

		$tmp = ReadTemplate($PPC_RESULTS_PART);
		$shl = "";
		if($rest=="dmoz"||$rest=="msn"){
			if(preg_match("/(http:\/\/(?:[-\w]\.?)+\/??)/", $record["link"], $mm)){
				$shl = $mm[1];
				$cat = $record["category"];
			}
		}elseif($rest=="revenue"){
			$shl = $record["category"];
			$cat = "n/a";
		}

		$vars = array(
				"logo"=>"",
				"counter"=>$counter,
				"id"=>"",
				"title"=>"<a href=\"".$record["link"]."\" target=\"_blank\">".$record["title"]."</a>",
				"summary"=>($hs==0?stripslashes($record["summary"]):"").($record["bid"]!=""?"<br><i>Bid: ".$record["bid"]."</i>":""),
				"link"=>$shl,
				"category"=>$cat
		);
		return ParseTemplate($tmp, $vars);

}

//END OF DMOZ





//SEARCHFEED XML FEEDS
	function GetSearchFeedResults(&$results, $ss, $start = 1, $num = 1){
		global $SEARCHFEED_URL, $TRY_CONNECTIONS, $TRY_PAUSE;
		global $SEARCHFEED_CID;
		$results = array(
								"0" => array(
								"title"=>"",
								"link"=>"",
								"summary"=>"",
								"category"=>"",
								"bid"=>""
							 )
		);
		//$SEARCHFEED_CID = GetSettings("searchfeed_id");
		$link = $SEARCHFEED_URL."cat=".urlencode($ss)."&pID=".$SEARCHFEED_CID."&IP=".getenv("REMOTE_ADDR")."&page=".($start)."&nl=".$num;
		$cc = 1;
		while(!($fh = @fopen($link, 'r'))){
			if($cc==$TRY_CONNECTIONS) break;
			$cc++;
			Pause($TRY_PAUSE);
		}
		if($fh)
		{
			$buff = "";
			$tmp = "";
			$tmp_arr = array();
			while($buff = fread($fh, 256)){
				$tmp.=$buff;
			}
			fclose($fh);
/*
							print "SF working...<hr>";
							$ft = fopen("temp2.txt","a");
							fwrite($ft, "\n\n$link\n\n");
							fwrite($ft, $tmp);
							fclose($ft);
*/
			$sc = $num;
			$count = 1;
			if(preg_match("/<Listings>(.*)<\/Listings>/is", $tmp, $matches)){
				$recs = $matches[1];
					if(preg_match("/<Count>(.*?)<\/Count>/is", $recs, $m1)){
						$sc = $m1[1];
					}
					if(preg_match_all("/<Listing>(.*?)<\/Listing>/is", $recs, $m1)){
						foreach($m1[1] as $tt){
							if(preg_match("/<URI>\s*(.*)\s*<\/URI>/is", $tt, $m2)){
								$linkurl = $m2[1];
							}
							if(preg_match("/<URL>\s*(.*)\s*<\/URL>/is", $tt, $m2)){
								$category = $m2[1];
							}
							if(preg_match("/<Title>\s*<!\[CDATA\[(.*)\]\]>\s*<\/Title>/is", $tt, $m2)){
								$title = $m2[1];
							}
							if(preg_match("/<Description>\s*<!\[CDATA\[(.*)\]\]>\s*<\/Description>/is", $tt, $m2)){
								$summary = $m2[1];
							}
							if(preg_match("/<Bid>\s*(.*)\s*<\/Bid>/is", $tt, $m2)){
								$bid = $m2[1];
							}
/*
							$ft = fopen("temp.txt","a");
							fwrite($ft, "$title\n$summary\n$linkurl\n$category\n$bid\n---------------------------\n");
							fclose($ft);
*/
							$results[$count] = array(
								"title"=>$title,
								"link"=>$linkurl,
								"summary"=>$summary,
								"category"=>$category,
								"bid"=>$bid
							);
							$count++;
						}
					}
				return $sc;
			}else return "";
		}else{
			return "";
		}
	}
//END OF SEARCHFEEDS XML FEEDS

//RAGING FEEDS

function GetRAGINGResults(&$results, $ss, $start = 1, $num = 1){
	global $RAGING_URL;
	global $TRY_CONNECTIONS, $TRY_PAUSE;
	$results = array(
							"0" => array(
							"title"=>"",
							"link"=>"",
							"summary"=>"",
							"category"=>""
						 )
	);
  //		$link = $RAGING_URL."&q=".urlencode($ss)."&stq=".$start;
	$link = "http://www.altavista.com/web/results?q=".urlencode($ss)."&stq=".$start;

	$cc = 1;
	while(!($fh = @fopen($link, 'r'))){
		if($cc==$TRY_CONNECTIONS) break;
		$cc++;
		Pause($TRY_PAUSE);
	}
	if($fh){
		$buff = "";
		$tmp = "";
		$tmp_arr = array();
		while($buff = fread($fh, 256)){
			$tmp.=$buff;
		}
		fclose($fh);
	}
	$sc = 0;
/*
		if(preg_match("/found ([\d\,]+) results\s+<\/a>/i", $tmp, $m1)){
			$sc = $m1[1];
		}
*/
//new		
			if(preg_match("/found (.*?) results/i", $tmp, $m1)){
			$sc = $m1[1];
			$sc = preg_replace("/,/","",$sc);
                 }
//new                 

		$str_pos = strpos($tmp,"found $sc results") + 15; 
		$tmp = substr($tmp,$str_pos);


//		if (preg_match_all("/<a\n*\s+href\s*=\"\/r\?ck_sm=([^\"]*)[^>]*>([^<]*)<\/a><br><\/b><span class=s>(.*)<br>/",$tmp,$array))
		if (preg_match_all("/<br class='lb'><a class='res' href=\'(.*?)\'>(.*?)<\/a><br><span class=s>(.*?)<br>/si",$tmp,$array))
		{
			$i=0;
			while($i<count($array[1]))
			{
 //				$linkurl="http://www.altavista.com/r?ck_sm=".$array[1][$i];
				$linkurl=$array[1][$i];
	             		$title=$array[2][$i]; 
				$summary=$array[3][$i];
				$category = "n/a"; 
				$results[$i+1] = array(
					"title"=>$title,
					"link"=>$linkurl,
					"summary"=>$summary,
					"category"=>$category
				);
				$i++;  

/* echo "$title <br>"; 
echo "$linkurl <br>"; 
echo "$summary <br>"; 
*/				
			}
		}
		return $sc;
	}

?>

[NogDog]

Here's a function you can use to grab the content of a URL:

<?php
function curl_get_contents($url, $timeout=60)
{
   $timeout = abs((int)$timeout);
   $curl = curl_init();
   $opts = array(
      CURLOPT_URL => $url,
      CURLOPT_RETURNTRANSFER => true,
      CURLOPT_TIMEOUT => $timeout
   );
   curl_setopt_array($curl, $opts);
   $result = curl_exec($curl);
   if($result === false)
   {
      user_error(curl_error($curl));
      return false;
   }
   $response = curl_getinfo($curl, CURLINFO_HTTP_CODE);
   if($response != 200)
   {
      user_error("Received HTTP response of $response.");
   }
   return $result;
}

// sample usage:
$test = curl_get_contents('http://www.phpbuilder.com/');
echo "<pre>".htmlentities($test)."</pre>";
?>

[pilotcap232]

thank you for your reply, but still dont know how to incorporate this script with my already existing one to replace fopen to curl.

thank you again

[NogDog]

Basically, stick the curl_get_contents() function definition I supplied somewhere in your script. Then wherever you have this type of thing:

   $cc = 1;
   while(!($fh = @fopen($link, 'r')))
   {
      if($cc == $TRY_CONNECTIONS)
         break;
      $cc++;
      Pause($TRY_PAUSE);
   }
   if($fh)
   {
      $buff = "";
      $tmp = "";
      $tmp_arr = array();
      while($buff = fread($fh, 256))
      {
         $tmp .= $buff;
      }
      fclose($fh);

...replace it with...

$tmp = curl_get_contents($link);
if($tmp !== false) {

[pilotcap232]

thank you, I did what you have told me but no luck, for example , I have set my script to retrieve raging search results and I did the following:
added the function to the script substitute the $url for $link

<?php 
function curl_get_contents($link, $timeout=60) 
{ 
   $timeout = abs((int)$timeout); 
   $curl = curl_init(); 
   $opts = array( 
      CURLOPT_URL => $link, 
      CURLOPT_RETURNTRANSFER => true, 
      CURLOPT_TIMEOUT => $timeout 
   ); 
   curl_setopt_array($curl, $opts); 
   $result = curl_exec($curl); 
   if($result === false) 
   { 
      user_error(curl_error($curl)); 
      return false; 
   } 
   $response = curl_getinfo($curl, CURLINFO_HTTP_CODE); 
   if($response != 200) 
   { 
      user_error("Received HTTP response of $response."); 
   } 
   return $result; 
} 

then replaced the code like this:

 //		$link = $RAGING_URL."&q=".urlencode($ss)."&stq=".$start;
 		$link = "http://www.altavista.com/web/results?q=".urlencode($ss)."&stq=".$start;

	$tmp = curl_get_contents($link); 
if($tmp !== false) { 

	}
	$sc = 0;
/*
		if(preg_match("/found ([\d\,]+) results\s+<\/a>/i", $tmp, $m1)){
			$sc = $m1[1];
		}
*/
//new		
			if(preg_match("/found (.*?) results/i", $tmp, $m1)){
			$sc = $m1[1];
			$sc = preg_replace("/,/","",$sc);
                 }
//new                 

		$str_pos = strpos($tmp,"found $sc results") + 15; 
		$tmp = substr($tmp,$str_pos);


//		if (preg_match_all("/<a\n*\s+href\s*=\"\/r\?ck_sm=([^\"]*)[^>]*>([^<]*)<\/a><br><\/b><span class=s>(.*)<br>/",$tmp,$array))
		if (preg_match_all("/<br class='lb'><a class='res' href=\'(.*?)\'>(.*?)<\/a><br><span class=s>(.*?)<br>/si",$tmp,$array))
		{
			$i=0;
			while($i<count($array[1]))
			{
 //				$linkurl="http://www.altavista.com/r?ck_sm=".$array[1][$i];
				$linkurl=$array[1][$i];
	             		$title=$array[2][$i]; 
				$summary=$array[3][$i];
				$category = "n/a"; 
				$results[$i+1] = array(
					"title"=>$title,
					"link"=>$linkurl,
					"summary"=>$summary,
					"category"=>$category
				);
				$i++;  

/* echo "$title <br>"; 
echo "$linkurl <br>"; 
echo "$summary <br>"; 
*/				
			}
		}
		return $sc;
	}

?>

but no luck, just a blank page

I am still prety noob at coding, any other siggestion will be well appreciated, thansk again

[NogDog]

See how this works:

<?php
//DMOZ
$DELAY = 5;
$DMOZ_URL = "http://search.dmoz.org/cgi-bin/search?";
$TRY_CONNECTIONS = 20;
$SEARCHFEED_URL = "http://www.searchfeed.com/rd/feed/XMLFeed.jsp?";
$RAGING_URL = "http://www.altavista.com/web/res_text?avkw=xytx&amb=txt&kls=0&kgs=0";
//microseconds
$TRY_PAUSE = 5;

/**
 * Replacement function for fetching text via cURL
 */
function curl_get_contents($url, $timeout = 60)
{
   $timeout = abs((int)$timeout);
   $curl = curl_init();
   $opts = array(CURLOPT_URL => $url, CURLOPT_RETURNTRANSFER => true,
      CURLOPT_TIMEOUT => $timeout);
   curl_setopt_array($curl, $opts);
   $result = curl_exec($curl);
   if($result === false)
   {
      user_error(curl_error($curl));
      return false;
   }
   $response = curl_getinfo($curl, CURLINFO_HTTP_CODE);
   if($response != 200)
   {
      user_error("Received HTTP response of $response.");
   }
   return $result;
}

function Pause($delay = 10)
{
   $ts = explode(" ", microtime());
   $start_t = $ts[0] + $ts[1] * 1000;
   do
   {
      $ts = explode(" ", microtime());
      $c_t = $ts[0] + $ts[1] * 1000;
   } while(($c_t - $start_t) <= $delay);
}

function GetDMOZResults(&$results, $ss, $start = 1, $num = 1)
{
   global $DMOZ_URL;
   global $TRY_CONNECTIONS, $TRY_PAUSE;
   $results = array("0" => array("title" => "", "link" => "", "summary" => "",
      "category" => ""));
   $link = $DMOZ_URL . "search=" . urlencode($ss) . "&start=" . $start;

   $tmp = curl_get_contents($link);
   if($tmp !== false)
   {
      $sc = 0;
      if(preg_match("/Open Directory Sites.*?(\d+?)\)/", $tmp, $m1))
      {
         $sc = $m1[1];
      }
      $tmp = preg_replace("/^.*Open Directory Sites/", "", $tmp);
      $tmp = preg_replace("/<img.*?>/", "", $tmp);
      $count = 1;
      if(preg_match_all("/<li>(<a href=\"http:.*?)(?:<li>|<\/ol>)/s", $tmp, $matches))
      {
         foreach($matches[1] as $st)
         {
            if($count <= $num && $count <= $sc)
            {
               if(preg_match("/^<a href=\"(.*?)\">(.*?)<\/a>(.*?)<br>.*?<a href=\".*?\">(.*?)<\/a>/s",
                  $st, $m2))
               {
                  $linkurl = $m2[1];
                  $title = $m2[2];
                  $summary = $m2[3];
                  $category = $m2[4];
               }
               //						print $count." - ".$title."<hr>";
               $results[$count] = array("title" => $title, "link" => $linkurl, "summary" => $summary,
                  "category" => $category);
               $count++;
            }
            else
            {
               break;
            }
         }
         return $sc;
      }
      else
         return "";
   }
   else
   {
      return "";
   }
}


function PPCParseRecord_External($type, $record, $counter, $page, $rpp, $hs, $ss,
   $rest)
{
   global $PPC_RESULTS_PART, $CLICK_SCRIPT, $CLICK_TARGET, $MAIN_URL;

   $tmp = ReadTemplate($PPC_RESULTS_PART);
   $shl = "";
   if($rest == "dmoz" || $rest == "msn")
   {
      if(preg_match("/(http:\/\/(?:[-\w]\.?)+\/??)/", $record["link"], $mm))
      {
         $shl = $mm[1];
         $cat = $record["category"];
      }
   } elseif($rest == "revenue")
   {
      $shl = $record["category"];
      $cat = "n/a";
   }

   $vars = array("logo" => "", "counter" => $counter, "id" => "", "title" =>
      "<a href=\"" . $record["link"] . "\" target=\"_blank\">" . $record["title"] .
      "</a>", "summary" => ($hs == 0 ? stripslashes($record["summary"]) : "") . ($record["bid"] !=
      "" ? "<br><i>Bid: " . $record["bid"] . "</i>" : ""), "link" => $shl, "category" =>
      $cat);
   return ParseTemplate($tmp, $vars);

}

//END OF DMOZ


//SEARCHFEED XML FEEDS
function GetSearchFeedResults(&$results, $ss, $start = 1, $num = 1)
{
   global $SEARCHFEED_URL, $TRY_CONNECTIONS, $TRY_PAUSE;
   global $SEARCHFEED_CID;
   $results = array("0" => array("title" => "", "link" => "", "summary" => "",
      "category" => "", "bid" => ""));
   //$SEARCHFEED_CID = GetSettings("searchfeed_id");
   $link = $SEARCHFEED_URL . "cat=" . urlencode($ss) . "&pID=" . $SEARCHFEED_CID .
      "&IP=" . getenv("REMOTE_ADDR") . "&page=" . ($start) . "&nl=" . $num;

   $tmp = curl_get_contents($link);
   if($tmp !== false)
   {
      /*
      print "SF working...<hr>";
      $ft = fopen("temp2.txt","a");
      fwrite($ft, "\n\n$link\n\n");
      fwrite($ft, $tmp);
      fclose($ft);
      */
      $sc = $num;
      $count = 1;
      if(preg_match("/<Listings>(.*)<\/Listings>/is", $tmp, $matches))
      {
         $recs = $matches[1];
         if(preg_match("/<Count>(.*?)<\/Count>/is", $recs, $m1))
         {
            $sc = $m1[1];
         }
         if(preg_match_all("/<Listing>(.*?)<\/Listing>/is", $recs, $m1))
         {
            foreach($m1[1] as $tt)
            {
               if(preg_match("/<URI>\s*(.*)\s*<\/URI>/is", $tt, $m2))
               {
                  $linkurl = $m2[1];
               }
               if(preg_match("/<URL>\s*(.*)\s*<\/URL>/is", $tt, $m2))
               {
                  $category = $m2[1];
               }
               if(preg_match("/<Title>\s*<!\[CDATA\[(.*)\]\]>\s*<\/Title>/is", $tt, $m2))
               {
                  $title = $m2[1];
               }
               if(preg_match("/<Description>\s*<!\[CDATA\[(.*)\]\]>\s*<\/Description>/is", $tt,
                  $m2))
               {
                  $summary = $m2[1];
               }
               if(preg_match("/<Bid>\s*(.*)\s*<\/Bid>/is", $tt, $m2))
               {
                  $bid = $m2[1];
               }
               /*
               $ft = fopen("temp.txt","a");
               fwrite($ft, "$title\n$summary\n$linkurl\n$category\n$bid\n---------------------------\n");
               fclose($ft);
               */
               $results[$count] = array("title" => $title, "link" => $linkurl, "summary" => $summary,
                  "category" => $category, "bid" => $bid);
               $count++;
            }
         }
         return $sc;
      }
      else
         return "";
   }
   else
   {
      return "";
   }
}
//END OF SEARCHFEEDS XML FEEDS

//RAGING FEEDS

function GetRAGINGResults(&$results, $ss, $start = 1, $num = 1)
{
   global $RAGING_URL;
   global $TRY_CONNECTIONS, $TRY_PAUSE;
   $results = array("0" => array("title" => "", "link" => "", "summary" => "",
      "category" => ""));
   //		$link = $RAGING_URL."&q=".urlencode($ss)."&stq=".$start;
   $link = "http://www.altavista.com/web/results?q=" . urlencode($ss) . "&stq=" . $start;

   $tmp = curl_get_contents($link);
   if($tmp !== false)
   {
      return false;
   }
   $sc = 0;
   /*
   if(preg_match("/found ([\d\,]+) results\s+<\/a>/i", $tmp, $m1)){
   $sc = $m1[1];
   }
   */
   //new
   if(preg_match("/found (.*?) results/i", $tmp, $m1))
   {
      $sc = $m1[1];
      $sc = preg_replace("/,/", "", $sc);
   }
   //new
   $str_pos = strpos($tmp, "found $sc results") + 15;
   $tmp = substr($tmp, $str_pos);


   //		if (preg_match_all("/<a\n*\s+href\s*=\"\/r\?ck_sm=([^\"]*)[^>]*>([^<]*)<\/a><br><\/b><span class=s>(.*)<br>/",$tmp,$array))
   if(preg_match_all("/<br class='lb'><a class='res' href=\'(.*?)\'>(.*?)<\/a><br><span class=s>(.*?)<br>/si",
      $tmp, $array))
   {
      $i = 0;
      while($i < count($array[1]))
      {
         //				$linkurl="http://www.altavista.com/r?ck_sm=".$array[1][$i];
         $linkurl = $array[1][$i];
         $title = $array[2][$i];
         $summary = $array[3][$i];
         $category = "n/a";
         $results[$i + 1] = array("title" => $title, "link" => $linkurl, "summary" => $summary,
            "category" => $category);
         $i++;
         /* echo "$title <br>";
         echo "$linkurl <br>"; 
         echo "$summary <br>"; 
         */
      }
   }
   return $sc;
}

?>

[pilotcap232]

no, no luck, still showing a blank page, not even showing the regular header and footer from page.

I think I may need to move the site to another server that support fopen to make it work, lol

Thanks for your input.

[NogDog]

Hmmm...worked OK for me from my PC. :bemused: Of course, there may be other dependencies I'm not aware of, or something broken in the script that calls those functions, etc. With a better understanding of the functional requirements and some code refactoring I'm sure it could work, and probably end up being cleaner and easier to maintain, too. 🙂