google web, videos and news, various other fixes

README.md

@@ -23,6 +23,7 @@ https://4get.ca
 	- DuckDuckGo
 	- Brave
 	- Yandex
+	- Google
 	- Mojeek
 	- Marginalia
 	- wiby
@@ -41,10 +42,12 @@ https://4get.ca
 	- DuckDuckgo
 	- Brave
 	- Yandex
+	- Google
 
 4. News
 	- DuckDuckGo
 	- Brave
+	- Google
 	- Mojeek
 
 5. Music
@@ -61,7 +64,7 @@ https://4get.ca
 	- YouTube
 	- SoundCloud
 
-More scrapers are coming soon. I currently want to add Google web/video/news search, HackerNews (durr orange site!!) and Qwant. A shopping and files tab is also in my todo list.
+More scrapers are coming soon. I currently want to add HackerNews (durr orange site!!), Qwant, Yep and other garbage. A shopping, files, tab and more music scrapers are also on my todo list.
 
 # Installation
 This section is still to-do. You will need to figure shit out for some of the apache2 and nginx stuff. Everything else should be OK.
@@ -190,6 +193,41 @@ services:
 
 Replace relevant values and start with `docker-compose up -d`
 
+## Install on Caddy
+
+1. Install dependencies:
+
+`sudo apt install caddy php8.2-dom php8.2-imagick imagemagick php8.2-curl curl php8.2-apcu git`
+
+2. Clone this repository where you want to host this from:
+
+`cd /var/www && sudo git clone https://git.konakona.moe/diowo/4get`
+
+3. Set permission on the `icons` directory inside `4get`
+
+`cd /var/www/4get/ && sudo chmod 777 -R icons/`
+
+4. Add an entry for 4get on your Caddyfile at `/etc/caddy/Caddyfile`
+
+```sh
+4get.konakona.moe {
+    root * /var/www/4get
+    file_server
+    encode gzip
+    php_fastcgi unix//var/run/php/php8.2-fpm.sock {
+        index index.php
+    }
+    redir /{path}.php{query} 301
+    try_files {path} {path}.php
+}
+```
+
+Caddy deals with SSL certificates automatically so you don't have to mess with anything. Also if needed, a sample of my Caddyfile can be found [here](https://git.konakona.moe/diowo/misc/src/branch/master/etc/caddy/Caddyfile).
+
+5. Restart Caddy
+
+`sudo systemctl restart caddy`
+
 # Encryption setup
 I'm schizoid (as you should) so I'm gonna setup 4096bit key encryption. To complete this step, you need a domain or subdomain in your possession. Make sure that the DNS shit for your domain has propagated properly before continuing, because certbot is a piece of shit that will error out the ass once you reach 5 attempts under an hour.
 

ami4get.php

@@ -5,8 +5,8 @@ header("Access-Control-Allow-Origin: *");
 
 include "data/config.php";
 
-$bot_requests = apcu_fetch("captcha");
 $real_requests = apcu_fetch("real_requests");
+$bot_requests = apcu_fetch("captcha_gen");
 
 echo json_encode(
 	[

api.txt

@@ -68,8 +68,8 @@
 
 
 + Get the next page of results
-    All API responses come with an array index named "nextpage". To get
-    the next page of results, you must make another API call with &npt.
+    All API responses come with an array index named "npt". To get the
+    next page of results, you must make another API call with &npt.
     
     Example ::
         

api/v1/web.php

@@ -39,7 +39,9 @@ if(
 }
 
 try{
-	echo json_encode(
+	
+	echo
+		json_encode(
 			$scraper->web($get),
 			JSON_UNESCAPED_UNICODE | JSON_UNESCAPED_SLASHES
 		);

data/config.php

@@ -5,7 +5,7 @@ class config{
 	// any parameters.
 	
 	// 4get version. Please keep this updated
-	const VERSION = 5;
+	const VERSION = 6;
 	
 	// Will be shown pretty much everywhere.
 	const SERVER_NAME = "4get";
@@ -56,14 +56,22 @@ class config{
 	const INSTANCES = [
 		"https://4get.ca",
 		"https://4get.zzls.xyz",
+		"https://4getus.zzls.xyz",
 		"https://4get.silly.computer",
 		"https://4g.opnxng.com",
-		"https://4get.konakona.moe"
+		"https://4get.konakona.moe",
+		"https://4get.lvkaszus.pl",
+		"https://4g.ggtyler.dev",
+		"https://4get.perennialte.ch",
+		"https://4get.sihj.net",
+		"https://4get.hbubli.cc",
+		"https://4get.plunked.party",
+		"https://4get.seitan-ayoub.lol"
 	];
 	
 	// 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:109.0) Gecko/20100101 Firefox/119.0";
+	const USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/120.0";
 	
 	// Proxy pool assignments for each scraper
 	// false = Use server's raw IP

lib/captcha_gen.php

@@ -7,6 +7,7 @@ class captcha{
 		// check if we want captcha
 		if(config::BOT_PROTECTION !== 1){
 			
+			apcu_inc("real_requests");
 			if($output === true){
 				$frontend->loadheader(
 					$get,
@@ -45,6 +46,8 @@ class captcha{
 				}else{
 					
 					// the cookie is OK! dont die() and give results
+					apcu_inc("real_requests");
+					
 					if($output === true){
 						$frontend->loadheader(
 							$get,
@@ -175,6 +178,8 @@ class captcha{
 				
 				apcu_inc($key, 1, $stupid, 86400);
 				
+				apcu_inc("real_requests");
+				
 				setcookie(
 					"pass",
 					$key,

lib/frontend.php

@@ -25,7 +25,7 @@ class frontend{
 		
 		if($theme != "Dark"){
 			
-			$replacements["style"] = '<link rel="stylesheet" href="/static/themes/' . $theme . '.css?v' . config::VERSION . '">';
+			$replacements["style"] = '<link rel="stylesheet" href="/static/themes/' . rawurlencode($theme) . '.css?v' . config::VERSION . '">';
 		}else{
 			
 			$replacements["style"] = "";
@@ -84,6 +84,8 @@ class frontend{
 		){
 			
 			// bot detected !!
+			apcu_inc("captcha_gen");
+			
 			$this->drawerror(
 				"Tshh, blocked!",
 				'You were blocked from viewing this page. If you wish to scrape data from 4get, please consider running <a href="https://git.lolcat.ca/lolcat/4get" rel="noreferrer nofollow">your own 4get instance</a> or using <a href="/api.txt">the API</a>.',
@@ -889,7 +891,7 @@ class frontend{
 						"ddg" => "DuckDuckGo",
 						"brave" => "Brave",
 						"yandex" => "Yandex",
-						//"google" => "Google",
+						"google" => "Google",
 						"mojeek" => "Mojeek",
 						"marginalia" => "Marginalia",
 						"wiby" => "wiby"
@@ -921,8 +923,8 @@ class frontend{
 						//"fb" => "Facebook videos",
 						"ddg" => "DuckDuckGo",
 						"brave" => "Brave",
-						"yandex" => "Yandex"
-						//"google" => "Google"
+						"yandex" => "Yandex",
+						"google" => "Google"
 					]
 				];
 				break;
@@ -933,7 +935,7 @@ class frontend{
 					"option" => [
 						"ddg" => "DuckDuckGo",
 						"brave" => "Brave",
-						//"google" => "Google",
+						"google" => "Google",
 						"mojeek" => "Mojeek"
 					]
 				];

lib/fuckhtml.php

@@ -15,7 +15,7 @@ class fuckhtml{
 			
 			if(!isset($html["innerHTML"])){
 				
-				throw new Exception("(load) Supplied array doesn't contain a innerHTML index");
+				throw new Exception("(load) Supplied array doesn't contain an innerHTML index");
 			}
 			$html = $html["innerHTML"];
 		}
@@ -35,6 +35,11 @@ class fuckhtml{
 		$this->strlen = strlen($this->html);
 	}
 	
+	public function getloadedhtml(){
+		
+		return $this->html;
+	}
+	
 	public function getElementsByTagName(string $tagname){
 		
 		$out = [];
@@ -46,7 +51,7 @@ class fuckhtml{
 		
 		if($tagname == "*"){
 			
-			$tagname = '[^\/<>\s]+';
+			$tagname = '[A-Za-z0-9._-]+';
 		}else{
 			
 			$tagname = preg_quote(strtolower($tagname));
@@ -126,7 +131,7 @@ class fuckhtml{
 			}
 		);
 		
-		// computer the indent level for each element
+		// compute the indent level for each element
 		$level = [];
 		$count = count($out);
 		
@@ -314,7 +319,7 @@ class fuckhtml{
 			
 			if(!isset($html["innerHTML"])){
 				
-				throw new Exception("(getTextContent) Supplied array doesn't contain a innerHTML index");
+				throw new Exception("(getTextContent) Supplied array doesn't contain an innerHTML index");
 			}
 			$html = $html["innerHTML"];
 		}
@@ -441,4 +446,27 @@ class fuckhtml{
 		
 		return json_decode($json_out, true);
 	}
+	
+	public function parseJsString($string){
+		
+		return
+			preg_replace_callback(
+				'/\\\u[A-Fa-f0-9]{4}|\\\x[A-Fa-f0-9]{2}/',
+				function($match){
+					
+					if($match[0][1] == "u"){
+						
+						return json_decode('"' . $match[0] . '"');
+					}else{
+						
+						return mb_convert_encoding(
+							stripcslashes($match[0]),
+							"utf-8",
+							"windows-1252"
+						);
+					}
+				},
+				$string
+			);
+	}
 }

robots.txt

@@ -24,5 +24,5 @@
 
 User-agent: *
 Disallow:
-host: 4get.ca
-sitemap: https://4get.ca/sitemap.xml
+Host: 4get.ca
+Sitemap: https://4get.ca/sitemap

scraper/brave.php

@@ -857,7 +857,9 @@ class brave{
 					// parse ratings
 					if(
 						isset($info["ratings"]) &&
-						$info["ratings"] != "void 0"
+						$info["ratings"] != "void 0" &&
+						is_array($info["ratings"]) &&
+						count($info["ratings"]) !== 0
 					){
 						
 						$description[] = [
@@ -1183,7 +1185,7 @@ class brave{
 				"title" => $news["title"],
 				"author" => null,
 				"description" => $news["description"],
-				"date" => !isset($news["age"]) || $news["age"] == "void 0" ? null : strtotime($news["age"]),
+				"date" => !isset($news["age"]) || $news["age"] == "void 0" || $news["age"] == "null" ? null : strtotime($news["age"]),
 				"thumb" => $thumb,
 				"url" => $news["url"]
 			];

scraper/ddg.php

@@ -545,8 +545,6 @@ class ddg{
 	
 	public function web($get){
 		
-		$proxy = null;
-		
 		if($get["npt"]){
 			
 			[$jsgrep, $proxy] = $this->backend->get($get["npt"], "web");

scraper/mojeek.php

@@ -608,7 +608,7 @@ class mojeek{
 						$this->fuckhtml
 						->getTextContent(
 							$this->fuckhtml
-							->getElementsByClassName("i", "p")[1]
+							->getElementsByClassName("i", "p")[0]
 						)
 					);
 				

scraper/sc.php

@@ -229,7 +229,7 @@ class sc{
 		
 		if($json === null){
 			
-			throw new Exception("Failed to decode JSON");
+			throw new Exception("Failed to decode JSON. Did the keys set in data/config.php expire?");
 		}
 		
 		$out = [

settings.php

@@ -117,10 +117,10 @@ $settings = [
 						"value" => "yandex",
 						"text" => "Yandex"
 					],
-					/*[
+					[
 						"value" => "google",
 						"text" => "Google"
-					],*/
+					],
 					[
 						"value" => "mojeek",
 						"text" => "Mojeek"
@@ -192,11 +192,11 @@ $settings = [
 					[
 						"value" => "yandex",
 						"text" => "Yandex"
-					]/*,
+					],
 					[
 						"value" => "google",
 						"text" => "Google"
-					]*/
+					]
 				]
 			],
 			[
@@ -211,10 +211,10 @@ $settings = [
 						"value" => "brave",
 						"text" => "Brave"
 					],
-					/*[
+					[
 						"value" => "google",
 						"text" => "Google"
-					],*/
+					],
 					[
 						"value" => "mojeek",
 						"text" => "Mojeek"
@@ -434,20 +434,33 @@ $left .=
 	'</div>' .
 	'<div class="settings-submit">' .
 		'<input type="submit" value="Update settings!">' .
-		'<a href="../">&lt; Return to front page</a>' .
+		'<a href="../">&lt; Go back</a>' .
 	'</div>' .
 	'</form>';
 
 if(count($_GET) === 0){
 	
+	$code = [];
+	foreach($_COOKIE as $key => $value){
+		
+		$code[] = rawurlencode($key) . "=" . rawurlencode($value);
+	}
+	
+	$code = implode("&", $code);
+	
+	if($code != ""){
+		
+		$code = "?" . $code;
+	}
+	
 	echo
 		$frontend->load(
 			"search.html",
 			[
 				"class" => "",
 				"right-left" =>			
-					'<div class="infobox"><h2>Preference link</h2>Follow this link to auto-apply all cookies. Useful if your browser clears out cookies after a browsing session. Following this link will redirect you to the front page, unless no settings are set.<br><br>' .
-					'<a href="settings' . rtrim("?" . str_replace("; ", "&", $code), "?") . '">Bookmark me!</a>' .
+					'<div class="infobox"><h2>Preference link</h2>Following this link will re-apply all cookies configured here and will redirect you to the front page. Useful if your browser clears out cookies after a browsing session.<br><br>' .
+					'<a href="settings' . $code . '">Bookmark me!</a>' .
 					'</div>',
 				"right-right" => "",
 				"left" => $left

static/serverping.js

@@ -160,6 +160,16 @@ function number_format(int){
 	return new Intl.NumberFormat().format(int);
 }
 
+window.fetch = (function(fetch) {
+	return function(fn, t){
+		const begin = Date.now();
+		return fetch.apply(this, arguments).then(function(response) {
+			response.ping = Date.now() - begin;
+			return response;
+		});
+	};
+})(window.fetch);
+
 // parse initial server list
 fetch_server(window.location.origin);
 
@@ -187,25 +197,24 @@ async function fetch_server(server){
 	list.push(server);
 	
 	var data = null;
-	var ping = new Date().getTime();
 	
 	try{
 		
-		data = await fetch(
+		var payload = await fetch(
 			server + "/ami4get"
 		);
 		
-		if(data.status !== 200){
+		if(payload.status !== 200){
 			
 			// endpoint is not available
 			errors++;
 			div_failedreqs.textContent = number_format(errors);
-			console.warn(server + ": Invalid HTTP code " + data.status);
+			console.warn(server + ": Invalid HTTP code " + payload.status);
 			return;
 		}
 		
-		data = await data.json();
-		data.server.ping = new Date().getTime() - ping;
+		data = await payload.json();
+		data.server.ping = payload.ping;
 		
 	}catch(error){
 		

static/style.css

@@ -499,6 +499,7 @@ h3,h4,h5,h6{
 	text-align:center;
 	display:block;
 	text-align:left;
+	white-space:nowrap;
 }
 
 .favicon-dropdown img{
@@ -1247,6 +1248,11 @@ table tr a:last-child{
 	padding-left:20px;
 }
 
+.instances .go-back{
+	margin-top:17px;
+	display:inline-block;
+}
+
 
 /*
 	Responsive image

template/instances.html

@@ -27,6 +27,7 @@
 			</tbody>
 		</table>
 	</noscript>
+	<a href="../" class="go-back">&lt; Go back</a>
 	<div id="popup-bg"></div>
 	<div class="popup-wrapper">
 		<div class="popup"></div>

web.php

@@ -146,9 +146,17 @@ if(count($results["image"]) !== 0){
 		
 		$right["image"] .=
 			'<a class="image" href="' . htmlspecialchars($image["url"]) . '" rel="noreferrer nofollow" title="' . htmlspecialchars($image["title"]) . '" data-json="' . htmlspecialchars(json_encode($image["source"])) . '" tabindex="-1">' .
-				'<img src="' . $frontend->htmlimage($image["source"][count($image["source"]) - 1]["url"], "square") . '" alt="thumb">' .
-				'<div class="duration">' . $image["source"][0]["width"] . 'x' . $image["source"][0]["height"] . '</div>' .
-			'</a>';
+				'<img src="' . $frontend->htmlimage($image["source"][count($image["source"]) - 1]["url"], "square") . '" alt="thumb">';
+		
+		if(
+			$image["source"][0]["width"] !== null &&
+			$image["source"][0]["height"] !== null
+		){
+			
+			$right["image"] .= '<div class="duration">' . $image["source"][0]["width"] . 'x' . $image["source"][0]["height"] . '</div>';
+		}
+		
+		$right["image"] .= '</a>';
 	}
 	
 	$right["image"] .=