scraper/sc.php

@@ -6,9 +6,6 @@ class sc{
 		
 		include "lib/backend.php";
 		$this->backend = new backend("sc");
-		
-		include "lib/fuckhtml.php";
-		$this->fuckhtml = new fuckhtml();
 	}
 	
 	public function getfilters($page){
@@ -28,7 +25,7 @@ class sc{
 		];
 	}
 	
-	private function get($proxy, $url, $get = [], $web_req = false){
+	private function get($proxy, $url, $get = []){
 		
 		$curlproc = curl_init();
 		
@@ -40,42 +37,19 @@ class sc{
 		curl_setopt($curlproc, CURLOPT_URL, $url);
 		
 		curl_setopt($curlproc, CURLOPT_ENCODING, ""); // default encoding
-		
+		curl_setopt($curlproc, CURLOPT_HTTPHEADER,
-		// use http2
+			["User-Agent: " . config::USER_AGENT,
-		curl_setopt($curlproc, CURLOPT_HTTP_VERSION, CURL_HTTP_VERSION_2_0);
+			"Accept: application/json, text/javascript, */*; q=0.01",
-		
+			"Accept-Language: en-US,en;q=0.5",
-		if($web_req === false){
+			"Accept-Encoding: gzip",
-			
+			"Referer: https://soundcloud.com/",
-			curl_setopt($curlproc, CURLOPT_HTTPHEADER,
+			"Origin: https://soundcloud.com",
-				["User-Agent: " . config::USER_AGENT,
+			"DNT: 1",
-				"Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8",
+			"Connection: keep-alive",
-				"Accept-Language: en-US,en;q=0.5",
+			"Sec-Fetch-Dest: empty",
-				"Accept-Encoding: gzip",
+			"Sec-Fetch-Mode: cors",
-				"Referer: https://soundcloud.com/",
+			"Sec-Fetch-Site: same-site"]
-				"Origin: https://soundcloud.com",
+		);
-				"DNT: 1",
-				"Connection: keep-alive",
-				"Sec-Fetch-Dest: empty",
-				"Sec-Fetch-Mode: cors",
-				"Sec-Fetch-Site: same-site"]
-			);
-		}else{
-			
-			curl_setopt($curlproc, CURLOPT_HTTPHEADER,
-				["User-Agent: " . config::USER_AGENT,
-				"Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8",
-				"Accept-Language: en-US,en;q=0.5",
-				"Accept-Encoding: gzip",
-				"DNT: 1",
-				"Connection: keep-alive",
-				"Upgrade-Insecure-Requests: 1",
-				"Sec-Fetch-Dest: document",
-				"Sec-Fetch-Mode: navigate",
-				"Sec-Fetch-Site: cross-site",
-				"Priority: u=1",
-				"TE: trailers"]
-			);
-		}
 		
 		curl_setopt($curlproc, CURLOPT_RETURNTRANSFER, true);
 		curl_setopt($curlproc, CURLOPT_SSL_VERIFYHOST, 2);
@@ -422,47 +396,13 @@ class sc{
 		
 		$token = apcu_fetch("sc_token");
 		
-		if($token !== false){
+		if($token === false){
-			
-			return $token;
-		}
-		
-		// search through all javascript components on the main page
-		try{
-			$html =
-				$this->get(
-					$proxy,
-					"https://soundcloud.com",
-					[]
-				);
-		}catch(Exception $error){
-			
-			throw new Exception("Failed to fetch front page");
-		}
-		
-		$this->fuckhtml->load($html);
-		
-		$scripts =
-			$this->fuckhtml
-			->getElementsByTagName(
-				"script"
-			);
-		
-		foreach($scripts as $script){
-			
-			if(
-				!isset($script["attributes"]["src"]) ||
-				strpos($script["attributes"]["src"], "sndcdn.com") === false
-			){
-				
-				continue;
-			}
 			
 			try{
 				$js =
 					$this->get(
 						$proxy,
-						$script["attributes"]["src"],
+						"https://a-v2.sndcdn.com/assets/0-a901c1e0.js",
 						[]
 					);
 			}catch(Exception $error){
@@ -476,15 +416,16 @@ class sc{
 				$token
 			);
 			
-			if(isset($token[1])){
+			if(!isset($token[1])){
 				
-				apcu_store("sc_token", $token[1]);
+				throw new Exception("Failed to get search token");
-				return $token[1];
-				break;
 			}
+			
+			apcu_store("sc_token", $token[1]);
+			return $token[1];
 		}
 		
-		throw new Exception("Did not find a Soundcloud token in the Javascript blobs");
+		return $token;
 	}
 	
 	private function limitstrlen($text){