ddg hotfix

Reviewed-on: lolcat/4get#41

api.txt

@@ -1,10 +1,17 @@
-                        __ __             __
-                       / // / ____ ____  / /_
-                      / // /_/ __ `/ _ \/ __/
-                     /__  __/ /_/ /  __/ /_ 
-                       /_/  \__, /\___/\__/
-                           /____/         
-
+                   44
+                 4444444      44   
+                 44444444   44444       444
+                 44444444  444444    444444444
+                  44444   44444444  444444444
+                         444444444   4444444
+                        4444444444    444444
+                      4444444444444
+                    444444444444444444
+                       444444444444444
+                          44444444
+                          4444
+                           44
+                 
            + Welcome to the 4get API documentation +
 
 + Terms of use

data/config.php

@@ -119,7 +119,7 @@ class config{
 	
 	// Default user agent to use for scraper requests. Sometimes ignored to get specific webpages
 	// Changing this might break things.
-	const USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:129.0) Gecko/20100101 Firefox/129.0";
+	const USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:133.0) Gecko/20100101 Firefox/133.0";
 	
 	// Proxy pool assignments for each scraper
 	// false = Use server's raw IP
@@ -129,6 +129,7 @@ class config{
 	const PROXY_BRAVE = false;
 	const PROXY_FB = false; // facebook
 	const PROXY_GOOGLE = false;
+	const PROXY_GOOGLE_CSE = false;
 	const PROXY_STARTPAGE = false;
 	const PROXY_QWANT = false;
 	const PROXY_GHOSTERY = false;
@@ -157,6 +158,9 @@ class config{
 	// Scraper-specific parameters
 	//
 	
+	// GOOGLE CSE
+	const GOOGLE_CX_ENDPOINT = "d4e68b99b876541f0";
+	
 	// MARGINALIA
 	// Use "null" to default out to HTML scraping OR specify a string to
 	// use the API (Eg: "public"). API has less filters.

lib/backend.php

@@ -75,6 +75,7 @@ class backend{
 				break;
 			
 			case "socks5_hostname":
+			case "socks5h":
 			case "socks5a":
 				curl_setopt($curlproc, CURLOPT_PROXYTYPE, CURLPROXY_SOCKS5_HOSTNAME);
 				curl_setopt($curlproc, CURLOPT_PROXY, $address . ":" . $port);

lib/frontend.php

@@ -838,10 +838,10 @@ class frontend{
 		}
 		
 		$payload .=
-				'<a href="https://webcache.googleusercontent.com/search?q=cache:' . $urlencode . '" class="list" target="_BLANK"><img src="/favicon?s=https://google.com" alt="go">Google cache</a>' .
 				'<a href="https://web.archive.org/web/' . $urlencode . '" class="list" target="_BLANK"><img src="/favicon?s=https://archive.org" alt="ar">Archive.org</a>' .
 				'<a href="https://archive.ph/newest/' . htmlspecialchars($link) . '" class="list" target="_BLANK"><img src="/favicon?s=https://archive.is" alt="ar">Archive.is</a>' .
 				'<a href="https://ghostarchive.org/search?term=' . $urlencode . '" class="list" target="_BLANK"><img src="/favicon?s=https://ghostarchive.org" alt="gh">Ghostarchive</a>' .
+				'<a href="https://arquivo.pt/wayback/' . htmlspecialchars($link) . '" class="list" target="_BLANK"><img src="/favicon?s=https://arquivo.pt" alt="ar">Arquivo.pt</a>' .
 				'<a href="https://www.bing.com/search?q=url%3A' . $urlencode . '" class="list" target="_BLANK"><img src="/favicon?s=https://bing.com" alt="bi">Bing cache</a>' .
 				'<a href="https://megalodon.jp/?url=' . $urlencode . '" class="list" target="_BLANK"><img src="/favicon?s=https://megalodon.jp" alt="me">Megalodon</a>' .
 			'</div>';
@@ -939,6 +939,7 @@ class frontend{
 						"brave" => "Brave",
 						"yandex" => "Yandex",
 						"google" => "Google",
+						"google_cse" => "Google CSE",
 						"startpage" => "Startpage",
 						"qwant" => "Qwant",
 						"ghostery" => "Ghostery",
@@ -963,6 +964,7 @@ class frontend{
 						"yandex" => "Yandex",
 						"brave" => "Brave",
 						"google" => "Google",
+						"google_cse" => "Google CSE",
 						"startpage" => "Startpage",
 						"qwant" => "Qwant",
 						"yep" => "Yep",

lib/fuckhtml.php

@@ -381,6 +381,8 @@ class fuckhtml{
 		$json_out = null;
 		$last_char = null;
 		
+		$keyword_check = null;
+		
 		for($i=0; $i<strlen($json); $i++){
 			
 			switch($json[$i]){
@@ -396,6 +398,7 @@ class fuckhtml{
 						
 						$bracket = false;
 						$is_close_bracket = true;
+						
 					}else{
 						
 						if($bracket === false){
@@ -429,6 +432,31 @@ class fuckhtml{
 				$is_close_bracket === false
 			){
 				
+				// do keyword check
+				$keyword_check .= $json[$i];
+				
+				if(in_array($json[$i], [":", "{"])){
+					
+					$keyword_check = substr($keyword_check, 0, -1);
+					
+					if(
+						preg_match(
+							'/function|array|return/i',
+							$keyword_check
+						)
+					){
+						
+						$json_out =
+							preg_replace(
+								'/[{"]*' . preg_quote($keyword_check, "/") . '$/',
+								"",
+								$json_out
+							);
+					}
+					
+					$keyword_check = null;
+				}
+				
 				// here we know we're not iterating over a quoted string
 				switch($json[$i]){
 					
@@ -498,4 +526,85 @@ class fuckhtml{
 				$string
 			);
 	}
+	
+	public function extract_json($json){
+		
+		$len = strlen($json);
+		$array_level = 0;
+		$object_level = 0;
+		$in_quote = null;
+		$start = null;
+		
+		for($i=0; $i<$len; $i++){
+			
+			switch($json[$i]){
+				
+				case "[":
+					if($in_quote === null){
+						
+						$array_level++;
+						if($start === null){
+							
+							$start = $i;
+						}
+					}
+					break;
+				
+				case "]":
+					if($in_quote === null){
+						
+						$array_level--;
+					}
+					break;
+				
+				case "{":
+					if($in_quote === null){
+						
+						$object_level++;
+						if($start === null){
+							
+							$start = $i;
+						}
+					}
+					break;
+				
+				case "}":
+					if($in_quote === null){
+						
+						$object_level--;
+					}
+					break;
+				
+				case "\"":
+				case "'":
+					if(
+						$i !== 0 &&
+						$json[$i - 1] !== "\\"
+					){
+						// found a non-escaped quote
+						
+						if($in_quote === null){
+							
+							// open quote
+							$in_quote = $json[$i];
+						}elseif($in_quote === $json[$i]){
+							
+							// close quote
+							$in_quote = null;
+						}
+					}
+					break;
+			}
+			
+			if(
+				$start !== null &&
+				$array_level === 0 &&
+				$object_level === 0
+			){
+				
+				return substr($json, $start, $i - $start + 1);
+				break;
+			}
+		}
+	}
 }

scraper/brave.php

@@ -293,8 +293,8 @@ class brave{
 		/*
 		$handle = fopen("scraper/brave.html", "r");
 		$html = fread($handle, filesize("scraper/brave.html"));
-		fclose($handle);
-		*/
+		fclose($handle);*/
+		
 		
 		try{
 			$html =
@@ -410,10 +410,20 @@ class brave{
 			throw new Exception("Could not grep JavaScript object");
 		}
 		
+		$data =
+			rtrim(
+				preg_replace(
+					'/\(Array\(0\)\)\).*$/',
+					"",
+					$grep[1]
+				),
+				" ]"
+			) . "]";
+		
 		$data =
 			$this->fuckhtml
 			->parseJsObject(
-				$grep[1]
+				$data
 			);
 		unset($grep);
 		
@@ -663,7 +673,10 @@ class brave{
 					$table["Address"] = $result["location"]["postal_address"]["displayAddress"];
 				}
 				
-				if(isset($result["location"]["rating"])){
+				if(
+					isset($result["location"]["rating"]) &&
+					$result["location"]["rating"] != "void 0"
+				){
 					
 					$table["Rating"] =
 						$result["location"]["rating"]["ratingValue"] . "/" .
@@ -671,13 +684,19 @@ class brave{
 						number_format($result["location"]["rating"]["reviewCount"]) . " votes)";
 				}
 				
-				if(isset($result["location"]["contact"]["telephone"])){
+				if(
+					isset($result["location"]["contact"]["telephone"]) &&
+					$result["location"]["contact"]["telephone"] != "void 0"
+				){
 					
 					$table["Phone number"] =
 						$result["location"]["contact"]["telephone"];
 				}
 				
-				if(isset($result["location"]["price_range"])){
+				if(
+					isset($result["location"]["price_range"]) &&
+					$result["location"]["price_range"] != "void 0"
+				){
 					
 					$table["Price"] =
 						$result["location"]["price_range"];

scraper/ftm.php

@@ -136,7 +136,7 @@ class ftm{
 				"source" => [
 					[
 						"url" =>
-							"https://findthatmeme.us-southeast-1.linodeobjects.com/" .
+							"https://s3.thehackerblog.com/findthatmeme/" .
 							$thumb,
 						"width" => null,
 						"height" => null

scraper/marginalia.php

@@ -220,6 +220,7 @@ class marginalia{
 			"related" => []
 		];
 		
+		// API scraper
 		if(config::MARGINALIA_API_KEY !== null){
 			
 			try{
@@ -263,34 +264,57 @@ class marginalia{
 			return $out;
 		}
 		
-		// no more cloudflare!! Parse html by default
-		$params = [
-			"query" => $search
-		];
+		// HTML parser
+		$proxy = $this->backend->get_ip();
 		
-		foreach(["adtech", "recent", "intitle"] as $v){
+		if($get["npt"]){
 			
-			if($get[$v] == "yes"){
+			[$params, $proxy] =
+				$this->backend->get(
+					$get["npt"],
+					"web"
+				);
+			
+			try{
+				$html =
+					$this->get(
+						$proxy,
+						"https://search.marginalia.nu/search?" . $params
+					);
+			}catch(Exception $error){
 				
-				switch($v){
+				throw new Exception("Failed to get HTML");
+			}
+			
+		}else{
+			$params = [
+				"query" => $search
+			];
+			
+			foreach(["adtech", "recent", "intitle"] as $v){
+				
+				if($get[$v] == "yes"){
 					
-					case "adtech": $params["adtech"] = "reduce"; break;
-					case "recent": $params["recent"] = "recent"; break;
-					case "adtech": $params["searchTitle"] = "title"; break;
+					switch($v){
+						
+						case "adtech": $params["adtech"] = "reduce"; break;
+						case "recent": $params["recent"] = "recent"; break;
+						case "adtech": $params["searchTitle"] = "title"; break;
+					}
 				}
 			}
-		}
-		
-		try{
-			$html =
-				$this->get(
-					$this->backend->get_ip(),
-					"https://search.marginalia.nu/search",
-					$params
-				);
-		}catch(Exception $error){
 			
-			throw new Exception("Failed to get HTML");
+			try{
+				$html =
+					$this->get(
+						$proxy,
+						"https://search.marginalia.nu/search",
+						$params
+					);
+			}catch(Exception $error){
+				
+				throw new Exception("Failed to get HTML");
+			}
 		}
 		
 		$this->fuckhtml->load($html);
@@ -387,6 +411,65 @@ class marginalia{
 			];
 		}
 		
+		// get next page
+		$this->fuckhtml->load($html);
+		
+		$pagination =
+			$this->fuckhtml
+			->getElementsByAttributeValue(
+				"aria-label",
+				"pagination",
+				"nav"
+			);
+		
+		if(count($pagination) === 0){
+			
+			// no pagination
+			return $out;
+		}
+		
+		$this->fuckhtml->load($pagination[0]);
+		
+		$pages =
+			$this->fuckhtml
+			->getElementsByClassName(
+				"page-link",
+				"a"
+			);
+		
+		$found_current_page = false;
+		
+		foreach($pages as $page){
+			
+			if(
+				stripos(
+					$page["attributes"]["class"],
+					"active"
+				) !== false
+			){
+				
+				$found_current_page = true;
+				continue;
+			}
+			
+			if($found_current_page){
+				
+				// we found current page index, and we iterated over
+				// the next page <a>
+				
+				$out["npt"] =
+					$this->backend->store(
+						parse_url(
+							$page["attributes"]["href"],
+							PHP_URL_QUERY
+						),
+						"web",
+						$proxy
+					);
+				break;
+			}
+		}
+		
 		return $out;
 	}
 }

scraper/mojeek.php

@@ -701,9 +701,11 @@ class mojeek{
 				if(count($thumb) === 2){
 					
 					$answer["thumb"] =
-						$this->fuckhtml
-						->getTextContent(
-							$thumb[1]
+						urldecode(
+							$this->fuckhtml
+							->getTextContent(
+								$thumb[1]
+							)
 						);
 				}
 			}

settings.php

@@ -133,6 +133,10 @@ $settings = [
 						"value" => "google",
 						"text" => "Google"
 					],
+					[
+						"value" => "google_cse",
+						"text" => "Google CSE"
+					],
 					[
 						"value" => "startpage",
 						"text" => "Startpage"
@@ -203,6 +207,10 @@ $settings = [
 						"value" => "google",
 						"text" => "Google"
 					],
+					[
+						"value" => "google_cse",
+						"text" => "Google CSE"
+					],
 					[
 						"value" => "startpage",
 						"text" => "Startpage"

static/themes/Gore's shitty theme.css

@@ -16,6 +16,7 @@
 
 body{
 	padding:15px 4% 40px;
+	margin:unset;
 }
 
 h1,h2,h3,h4,h5,h6{