updated version of submission + layer

slifty · Jun 27, 2014 · 04d90c7 · 04d90c7
1 parent 8a5eb72
commit 04d90c7
Show file tree

Hide file tree

Showing 50 changed files with 17,176 additions and 1,040 deletions.
diff --git a/api/external/get_external.php b/api/external/get_external.php
@@ -0,0 +1,39 @@
+<?php
+	/* GET THE CONTENT OF THE WEB PAGE */
+	$url = $_GET['url'];
+
+	// Cookie Jar
+	$ckfile = tempnam ("/tmp", "CURLCOOKIE");
+
+	// Clean the URL
+	$url = isset($_GET['url'])?$_GET['url']:"";
+	$url = substr($url,0,7) == "http://"?$url:"http://".$url;
+	$url = getFinalUrl($url);
+
+	// CURL
+	$ch = curl_init();
+	curl_setopt( $ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; rv:1.7.3) Gecko/20041001 Firefox/0.10.1" );
+	curl_setopt($ch,CURLOPT_URL,$url);
+	curl_setopt ($ch, CURLOPT_COOKIEJAR, $ckfile); 
+	curl_setopt($ch, CURLOPT_ENCODING, 'UTF-8');
+	curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);
+	$html = curl_exec($ch);
+	$content_type = curl_getinfo($ch, CURLINFO_CONTENT_TYPE);
+	$data = 'data:'.$content_type.';base64,'.base64_encode($html);
+	curl_close($ch);
+
+
+	/* EXTRACT THE TEXT */
+	$Readability     = new Readability($html); // default charset is utf-8
+	$readabilityData = $Readability->getContent(); // throws an exception when no suitable content is found
+
+	$collectionJSON = '{
+		"html": '.DBConn::clean($readabilityData['content']).'
+	}';
+
+	$callback = $_REQUEST['callback'];
+	if($callback)
+		echo($callback.'('.$collectionJSON.');');
+	else
+		echo($collectionJSON);
+?>
diff --git a/api/layers/get_layers.php b/api/layers/get_layers.php
@@ -1,14 +1,14 @@
 <?php
 	$collectionJSON = "";
 	$layer = Layer::getObject($_REQUEST['l']);
-	$callback = $_REQUEST['callback'];
 
 	if($layer->getItemID() == $layer) {
 		$collectionJSON = $layer->toJSON();
 	}
 
 	$collectionJSON = $layer->toJSON();
 
+	$callback = $_REQUEST['callback'];
 	if($callback)
 		echo($callback.'('.$collectionJSON.');');
 	else

diff --git a/api/layers/post_layers.php b/api/layers/post_layers.php
@@ -19,7 +19,7 @@
 		$question->save();
 
 		$statement = new Statement();
-		$statement->setContent($contributionData['statement']);
+		$statement->setContent($contributionData['content']);
 		$statement->setContext($contributionData['context']);
 		$statement->setContributionID($contribution->getItemID());
 		$statement->save();
@@ -31,7 +31,69 @@
 		$argument->save();
 	}
 
-	$collectionJSON = $layer->toJSON();
+	// Is there a URL?
+	if($_REQUEST['url']) {
+		// Cookie Jar
+		$ckfile = tempnam ("/tmp", "CURLCOOKIE");
+
+		// Clean the URL
+		$url = isset($_REQUEST['url'])?$_REQUEST['url']:"";
+		$url = substr($url,0,7) == "http://"?$url:"http://".$url;
+		$url = getFinalUrl($url);
+
+		// CURL
+		$ch = curl_init();
+		curl_setopt( $ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; rv:1.7.3) Gecko/20041001 Firefox/0.10.1" );
+		curl_setopt($ch,CURLOPT_URL,$url);
+		curl_setopt ($ch, CURLOPT_COOKIEJAR, $ckfile); 
+		curl_setopt($ch, CURLOPT_ENCODING, 'UTF-8');
+		curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);
+		$html = curl_exec($ch);
+		$content_type = curl_getinfo($ch, CURLINFO_CONTENT_TYPE);
+		$data = 'data:'.$content_type.';base64,'.base64_encode($html);
+		curl_close($ch);
+
+		// Remove all meta tags
+		$html = preg_replace('/\<\s*meta[^>]*>/i',"", $html);
+
+		// Remove all iframes (force a "noscript" environment)
+		$html = preg_replace('/\<\s*iframe[^>]*?>.*?\<\s*\/iframe[^>]*?>/is',"", $html);
+
+		// Remove all scripts (force a "noscript" environment)
+		$html = preg_replace('/<\s*script[^>]*>.*?<\s*\/script[^>]*?>/is',"", $html);
+		$html = preg_replace('/<\s*noscript[^>]*>/i',"", $html);
+
+		$data = preg_replace('/src=\".*\"(.*)dest_src=\"(.*)\"/i',"src=\"\\2\" \\1", $data);
+		$data = preg_replace('/dest_src=\"(.*)\"(.*)src=\".*\"/i',"src=\"\\1\" \\2", $data);
+
+		// General Image Fixes
+		$html = preg_replace('/src=\"\/(.*?)\"/i', "src=\"".$url_base."/\\1\"", $html);
+		$html = preg_replace('/src=\'\/(.*?)\'/i', "src='".$url_base."/\\1'", $html);
+
+		// General Link Fixes
+		$html = preg_replace('/href=\"\/(.*?)\"/i', "href=\"".$url_base."/\\1\"", $html);
+		$html = preg_replace('/href=\'\/(.*?)\'/i', "href='".$url_base."/\\1'", $html);
+
+		// CSS Link Fixes
+		$html = preg_replace('/\<link(.*?)text\/css(.*?)src\=(.*?)\/\>/i', "<link\\1text/css\\2href=\\3/>", $html);
+	} elseif ($_REQUEST['text']) {
+		$html = "<html><head></head><body>".str_replace("\n","<br />",$_REQUEST['text'])."</body></html>";
+	}
+	$script = "
+	
+	<script src='".$BASE_DIRECTORY."js/goggles.js'></script><script>truthGoggles({server: '".$GOGGLES_DIRECTORY."',layerId: ".$layer->getItemID()."});</script>";
+
+
+	$html = preg_replace('/<\s*\/\s*head[^>]*>/', $script."</head>", $html);
+
+	$guid = uniqid("");
+	$file = fopen($_SERVER['DOCUMENT_ROOT'].$BASE_DIRECTORY."layers/".$guid.".html","w");
+	fwrite($file, $html);
+
+	$collectionJSON = '{
+		"layer": '.$layer->toJSON().',
+		"url": "'.$BASE_DIRECTORY."layers/".$guid.'"
+	}';
 
 	if(isset($jsonp) && $jsonp)
 		echo($callback.'('.$collectionJSON.');');

diff --git a/includes/engine/helpers/helpers.php b/includes/engine/helpers/helpers.php
@@ -0,0 +1,45 @@
+<?php
+	function getFinalUrl( $url, $timeout = 5 ) {
+	    $url = str_replace( "&amp;", "&", urldecode(trim($url)) );
+
+	    $cookie = tempnam ("/tmp", "CURLCOOKIE");
+	    $ch = curl_init();
+	    curl_setopt( $ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows; U; Windows NT 5.1; rv:1.7.3) Gecko/20041001 Firefox/0.10.1" );
+	    curl_setopt( $ch, CURLOPT_URL, $url );
+	    curl_setopt( $ch, CURLOPT_COOKIEJAR, $cookie );
+	    curl_setopt( $ch, CURLOPT_FOLLOWLOCATION, true );
+	    curl_setopt( $ch, CURLOPT_ENCODING, "" );
+	    curl_setopt( $ch, CURLOPT_RETURNTRANSFER, true );
+	    curl_setopt( $ch, CURLOPT_AUTOREFERER, true );
+	    curl_setopt( $ch, CURLOPT_CONNECTTIMEOUT, $timeout );
+	    curl_setopt( $ch, CURLOPT_TIMEOUT, $timeout );
+	    curl_setopt( $ch, CURLOPT_MAXREDIRS, 10 );
+	    $content = curl_exec( $ch );
+	    $response = curl_getinfo( $ch );
+	    curl_close ( $ch );
+
+	    if ($response['http_code'] == 301 || $response['http_code'] == 302)
+	    {
+	        ini_set("user_agent", "Mozilla/5.0 (Windows; U; Windows NT 5.1; rv:1.7.3) Gecko/20041001 Firefox/0.10.1");
+	        $headers = get_headers($response['url']);
+
+	        $location = "";
+	        foreach( $headers as $value )
+	        {
+	            if ( substr( strtolower($value), 0, 9 ) == "location:" )
+	                return get_final_url( trim( substr( $value, 9, strlen($value) ) ) );
+	        }
+	    }
+
+	    if (    preg_match("/window\.location\.replace\('(.*)'\)/i", $content, $value) ||
+	            preg_match("/window\.location\=\"(.*)\"/i", $content, $value)
+	    )
+	    {
+	        return get_final_url ( $value[1] );
+	    }
+	    else
+	    {
+	        return $response['url'];
+	    }
+	}
+?>