lol forgot the request is still for yt

Reviewed-on: lolcat/4get#67

.dockerignore

@@ -0,0 +1 @@
+.git

Dockerfile

@@ -1,10 +1,9 @@
-FROM alpine:latest
+FROM alpine:3.21
 WORKDIR /var/www/html/4get
 
 RUN apk update && apk upgrade
-RUN apk add php apache2-ssl php83-fileinfo php83-openssl php83-iconv php83-common php83-dom php83-sodium php83-curl curl php83-pecl-apcu php83-apache2 imagemagick php83-pecl-imagick php-mbstring imagemagick-webp imagemagick-jpeg
+RUN apk add php apache2-ssl php84-fileinfo php84-openssl php84-iconv php84-common php84-dom php84-sodium php84-curl curl php84-pecl-apcu php84-apache2 imagemagick php84-pecl-imagick php84-mbstring imagemagick-webp imagemagick-jpeg
 
-COPY ./docker/apache/ /etc/apache2/
 COPY . .
 
 RUN chmod 777 /var/www/html/4get/icons
@@ -14,4 +13,5 @@ EXPOSE 443
 
 ENV FOURGET_PROTO=http
 
-CMD  ["./docker/docker-entrypoint.sh"]
+ENTRYPOINT  ["./docker/docker-entrypoint.sh"]
+CMD ["start"]

README.md

@@ -9,9 +9,11 @@ https://4get.ca/about
 ## Official instance
 https://4get.ca , or visit the official instance list: https://4get.ca/instances
 
+_NOT to be confused with 4get.ch, 4get.lol and friends! I **don't** host these._
+
 ## Totally unbiased comparison between alternatives
 
-|                            | 4get                    | searx(ng) | libreY      | araa      | hearch            |
+|                            | 4get                    | searx(ng) | libreY      | araa      | hearch.co         |
 |----------------------------|-------------------------|-----------|-------------|-----------|-------------------|
 | RAM usage                  | 200-400mb~              | 2GB~      | 200-400mb~  | 2GB~      | idk               |
 | Does it suck               | no (debunked by snopes) | yes       | yes         | a little  | better than searx |
@@ -23,36 +25,37 @@ https://4get.ca , or visit the official instance list: https://4get.ca/instances
 3. Bot protection that *actually* filters out the bots (when configured)
 4. Interface doesn't require javascript
 5. Favicon fetcher with caching support & image proxy
-6. Bunch of other shit
+6. Bunch of other shits
 
-tl;dr the best way to actually browse for shit.
+tl;dr 4get is the best way to browse for shit.
 
 # Supported websites
 
-| Web        | Images       | Videos     | News       | Music      | Autocompleter |
-|------------|--------------|------------|------------|------------|---------------|
-| DuckDuckGo | DuckDuckGo   | YouTube    | DuckDuckGo | Soundcloud | Brave         |
-| Brave      | Brave        | DuckDuckGo | Brave      |            | DuckDuckGo    |
-| Yandex     | Yandex       | Brave      | Google     |            | Yandex        |
-| Google     | Google       | Yandex     | Startpage  |            | Google        |
-| Startpage  | Startpage    | Google     | Qwant      |            | Startpage     |
-| Qwant      | Qwant        | Startpage  | Mojeek     |            | Kagi          |
-| Ghostery   | Yep          | Qwant      |            |            | Qwant         |
-| Yep        | Solofield    | Solofield  |            |            | Ghostery      |
-| Greppr     | Imgur        |            |            |            | Yep           |
-| Crowdview  | FindThatMeme |            |            |            | Marginalia    |
-| Mwmbl      |              |            |            |            | YouTube       |
-| Mojeek     |              |            |            |            | Soundcloud    |
-| Solofield  |              |            |            |            |               |
-| Marginalia |              |            |            |            |               |
-| wiby       |              |            |            |            |               |
-| Curlie     |              |            |            |            |               |
+| Web        | Images       | Videos       | News       | Music      | Autocompleter |
+|------------|--------------|--------------|------------|------------|---------------|
+| DuckDuckGo | DuckDuckGo   | YouTube      | DuckDuckGo | Soundcloud | Brave         |
+| Brave      | Brave        | Sepia Search | Brave      |            | DuckDuckGo    |
+| Yandex     | Yandex       | DuckDuckGo   | Google     |            | Yandex        |
+| Google     | Google       | Brave        | Startpage  |            | Google        |
+| Startpage  | Startpage    | Yandex       | Qwant      |            | Startpage     |
+| Qwant      | Qwant        | Google       | Mojeek     |            | Kagi          |
+| Ghostery   | Yep          | Startpage    | Baidu      |            | Qwant         |
+| Yep        | Baidu        | Qwant        |            |            | Ghostery      |
+| Greppr     | Pinterest    | Baidu        |            |            | Yep           |
+| Crowdview  | 500px        | Coc Coc      |            |            | Marginalia    |
+| Mwmbl      | VSCO         |              |            |            | YouTube       |
+| Mojeek     | Imgur        |              |            |            | Soundcloud    |
+| Baidu      | FindThatMeme |              |            |            |               |
+| Coc Coc    |              |              |            |            |               |
+| Marginalia |              |              |            |            |               |
+| wiby       |              |              |            |            |               |
+| Curlie     |              |              |            |            |               |
 
 # Installation
 Refer to the <a href="https://git.lolcat.ca/lolcat/4get/src/branch/master/docs/">documentation index</a>. I recommend following the <a href="https://git.lolcat.ca/lolcat/4get/src/branch/master/docs/apache2.md">apache2 guide</a>.
 
 ## Contact
-Shit breaks all the time but I repair it all the time too... Email me here: <b>will (at) lolcat.ca</b> or create an issue.
+Shit breaks all the time but I repair it all the time too. Email me here: <b>will (at) lolcat.ca</b> or create an issue.
 
 ## License
 AGPL

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

@@ -100,7 +100,6 @@ class config{
 		"https://4get.sijh.net",
 		"https://4get.hbubli.cc",
 		"https://4get.plunked.party",
-		"https://4get.seitan-ayoub.lol",
 		"https://4get.etenie.pl",
 		"https://4get.lunar.icu",
 		"https://4get.dcs0.hu",
@@ -119,7 +118,7 @@ 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:141.0) Gecko/20100101 Firefox/141.0";
 	
 	// Proxy pool assignments for each scraper
 	// false = Use server's raw IP
@@ -129,8 +128,12 @@ class config{
 	const PROXY_BRAVE = false;
 	const PROXY_FB = false; // facebook
 	const PROXY_GOOGLE = false;
+	const PROXY_GOOGLE_API = false;
+	const PROXY_GOOGLE_CSE = false;
 	const PROXY_STARTPAGE = false;
 	const PROXY_QWANT = false;
+	const PROXY_BAIDU = false;
+	const PROXY_COCCOC = false;
 	const PROXY_GHOSTERY = false;
 	const PROXY_MARGINALIA = false;
 	const PROXY_MOJEEK = false;
@@ -140,8 +143,13 @@ class config{
 	const PROXY_WIBY = false;
 	const PROXY_CURLIE = false;
 	const PROXY_YT = false; // youtube
+	const PROXY_SEPIASEARCH = false;
 	const PROXY_YEP = false;
 	const PROXY_PINTEREST = false;
+	const PROXY_SANKAKUCOMPLEX = false;
+	const PROXY_FLICKR = false;
+	const PROXY_FIVEHPX = false;
+	const PROXY_VSCO = false;
 	const PROXY_SEZNAM = false;
 	const PROXY_NAVER = false;
 	const PROXY_GREPPR = false;
@@ -157,6 +165,9 @@ class config{
 	// Scraper-specific parameters
 	//
 	
+	// GOOGLE CSE & GOOGLE API
+	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.

docker-compose.yaml

@@ -6,14 +6,15 @@ services:
     image: luuul/4get:latest
     restart: unless-stopped
     environment:
+      - FOURGET_PROTO=http
       - FOURGET_SERVER_NAME=4get.ca
+      - FOURGET_INSTANCES=https://4get.ca
 
     ports:
       - "80:80"
       - "443:443"
 
-    volumes:
-      - /etc/letsencrypt/live/domain.tld:/etc/4get/certs
-      # mount custom banners and captcha
-      - ./banners:/var/www/html/4get/banner
-      - ./captcha:/var/www/html/4get/data/captcha
+    # volumes:
+    # - /etc/letsencrypt/live/domain.tld:/etc/4get/certs # mount ssl
+    # - ./banners:/var/www/html/4get/banner # mount custom banners
+    # - ./captcha:/var/www/html/4get/data/captcha # mount captcha images

docker/apache/http/conf.d/ssl.conf

@@ -0,0 +1 @@
+# intentionally blank

docker/docker-entrypoint.sh

@@ -8,18 +8,27 @@ FOURGET_PROTO="${FOURGET_PROTO#\"}"
 # make lowercase
 FOURGET_PROTO=`echo $FOURGET_PROTO | awk '{print tolower($0)}'`
 
+FOURGET_SRC='/var/www/html/4get'
+
+mkdir -p /etc/apache2
 
 if [ "$FOURGET_PROTO" = "https" ]; then
         echo "Using https configuration"
-        cp /etc/apache2/https.conf /etc/apache2/httpd.conf
+        cp -r ${FOURGET_SRC}/docker/apache/https/httpd.conf /etc/apache2
+        cp -r ${FOURGET_SRC}/docker/apache/https/conf.d/* /etc/apache2/conf.d
+
 else
         echo "Using http configuration"
-        cp /etc/apache2/http.conf /etc/apache2/httpd.conf
+        cp -r ${FOURGET_SRC}/docker/apache/http/httpd.conf /etc/apache2
+        cp -r ${FOURGET_SRC}/docker/apache/http/conf.d/* /etc/apache2/conf.d
 fi
 
 php ./docker/gen_config.php
 
-
-echo "4get is running"
-exec httpd -DFOREGROUND
+if [ "$@" = "start" ]; then
+        echo "4get is running"
+        exec httpd -DFOREGROUND
+else 
+        exec "$@"
+fi
 

docs/nginx.md

@@ -1,103 +1,194 @@
-# Install on NGINX
+<h1 align=center>Installation of 4get in NGINX</h1>
 
->I do NOT recommend following this guide, only follow this if you *really* need to use nginx. I recommend you use the apache2 steps instead.
+<div align=right>
 
-Login as root.
+> NOTE: As the previous version stated, it is better to follow the <a href="https://git.lolcat.ca/lolcat/4get/src/branch/master/docs/apache2.md">Apache2 guide</a> instead of the Nginx one.
 
-Create a file in `/etc/nginx/sites-avaliable/` called `4get.conf` or any name you want and put this into the file:
+> NOTE: This is going to guess that you're using either a <abbr title="(Arch Linux, Artix Linux, Endeavouros, etc...) ">Arch-based system</abbr> or a <abbr title="(Debian, Ubuntu, Devuan, etc...)">Debian-based system</abbr>, although you can still follow it with minor issues.
 
-```
-server {
-    # DO YOU REALLY NEED TO LOG SEARCHES?
-    access_log /dev/null;
-    error_log /dev/null;
-    # Change this if you have 4get in other folder.
-    root /var/www/4get;
-    # Change yourdomain by your domain lol
-    server_name www.yourdomain.com yourdomain.com;
+</div>
 
-    location @php {
-        try_files $uri.php $uri/index.php =404;
-                # Change the unix socket address if it's different for you.
-        fastcgi_pass unix:/var/run/php-fpm/php-fpm.sock;
-        fastcgi_index index.php;
-                # Change this to `fastcgi_params` if you use a debian based distro.
-        include fastcgi.conf;
-        fastcgi_intercept_errors on;
-    }
+1. Login as root.
+2. Upgrade your system:
+   * On Arch-based, run `pacman -Syu`.
+   * On Debian-based, run `apt update`, then `apt upgrade`.
+3. Install the following dependencies:
+   * `git`: So you can clone <a href="https://git.lolcat.ca/lolcat/4get">this</a> repository.
+   * `nginx`: So you can run Nginx.
+   * `php-fpm`: This is what allows Nginx to run *(and show)* PHP files.
+   * `php-imagick`, `imagemagick`: Image manipulation.
+   * `php-apcu`: Caching module.
+   * `php-curl`, `curl`:  Transferring data with URLs.
+   * `php-mbstring`: String utils.
+   * `certbot`, `certbot-nginx`: ACME client. Used to create SSL certificates.
+     * In Arch-based distributions:
+       * `pacman -S nginx certbot php-imagick certbot-nginx imagemagick curl php-apcu git`
+     * In Debian-based distributions:
+       * `apt install php-mbstring nginx certbot-nginx certbot php-imagick imagemagick php-curl curl php-apcu git`
 
-    location / {
-        try_files $uri @php;
-    }
+<div align=right>
 
-    location ~* ^(.*)\.php$ {
-        return 301 $1;
-    }
+> IMPORTANT: `php-curl`, `php-mbstring` might be a Debian-only package, but this needs further fact checking.
 
+> IMPORTANT: If having issues with `php-apcu` or `libsodium`, go to [^1].
+
+</div>
+
+4. `cd` to `/etc/nginx` and make the `conf.d/` directory if it doesn't exist:
+   * Again, this guesses you're logged in as root.
+   ```sh
+   cd /etc/nginx
+   ls -l conf.d/ # If ls shows conf.d, then it means it exists.
+   # If it does not, run:
+   mkdir conf.d
+   ```
+5. Make a file inside `conf.d/` called `4get.conf` and place the following content:
+   * First run `touch conf.d/4get.conf` then `nano conf.d/4get.conf` to open the nano editor: *(Install it if it is not, or use another editor.)*
+    ```sh
+    server {
+        access_log /dev/null; # Search log file. Do you really need to?
+        error_log /dev/null;  # Error log file.
+
+        # Change this if you have 4get in another folder.
+        root /var/www/4get;
+        # Change 'yourdomain' to your domain.
+        server_name www.yourdomain.com yourdomain.com;
+        # Port to listen to.
         listen 80;
-}
-```
 
-That is a very basic config so you will need to adapt it to your needs in case you have a more complicated nginx configuration. Anyways, you can see a real world example [here](https://git.zzls.xyz/Fijxu/etc-configs/src/branch/selfhost/nginx/sites-available/4get.zzls.xyz.conf)
+        location @php {
+            try_files $uri.php $uri/index.php =404;
+            # Change the unix socket address if it's different for you.
+            fastcgi_pass unix:/var/run/php-fpm/php-fpm.sock;
+            fastcgi_index index.php;
+            # Change this to `fastcgi_params` if you use a debian based distribution.
+            include fastcgi.conf;
+            fastcgi_intercept_errors on;
+        }
 
-After you save the file you will need to do a symlink of the `4get.conf` file to `/etc/nignx/sites-enabled/`, you can do it with this command: 
+        location / {
+            try_files $uri @php;
+        }
 
-```sh
-ln -s /etc/nginx/sites-available/4get.conf /etc/nginx/sites-available/4get.conf
-```
+        location ~* ^(.*)\.php$ {
+            return 301 $1;
+        }
 
-Now test the nginx config with `nginx -t`, if it says that everything is good, restart nginx using `systemctl restart nginx`
-
-# Encryption setup
-
-Generate a certificate for the domain using:
-
-```sh
-certbot --nginx --key-type ecdsa -d www.yourdomain.com -d yourdomain.com
-```
-(Remember to install the nginx certbot plugin!!!)
-
-After doing that certbot should deploy the certificate automatically into your 4get nginx config file. It should be ready to use at that point.
-
-# Tor setup on NGINX
-
-Important Note: Tor onion addresses are significantly longer than traditional domain names. Before proceeding with Nginx configuration, ensure you increase the `server_names_hash_bucket_size` value in your `nginx.conf` file. This setting in your Nginx configuration controls the internal data structure used to manage multiple server names (hostnames) associated with your web server. Each hostname requires a certain amount of memory within this structure. If the size is insufficient, Nginx will encounter errors.
-
-1. Open your `nginx.conf` file (that is under `/etc/nginx/nginx.conf`).
-2. Find the line containing `# server_names_hash_bucket_size 64;`.
-3. Uncomment the line and adjust the value. Start with 64, but if you encounter issues, incrementally increase it (e.g., 128, 256) until it accommodates your configuration.
-
-Open your current 4get NGINX config (that is under `/etc/nginx/sites-available/`) and append this to the end of the file:
-
-```
-server {
-	access_log /dev/null;
-	error_log /dev/null;
-
-    listen 80;
-    server_name <youronionaddress>;
-    root /var/www/4get;
-
-    location @php {
-        try_files $uri.php $uri/index.php =404;
-        # Change the unix socket address if it's different for you.
-        fastcgi_pass unix:/var/run/php-fpm/php-fpm.sock;
-        fastcgi_index index.php;
-        # Change this to `fastcgi_params` if you use a debian based distro.
-        include fastcgi.conf;
-        fastcgi_intercept_errors on;
     }
+    ```
+    * The above is a very basic configuration and thus will need tweaking to your personal needs. It should still work as-is, though. A 'real world' example is present in [^2].
+    * After saving the file, check that the `nginx.conf` file inside the main directory includes files inside `conf.d/`:
+      * It should be inside the the http block: *(The following is an example! Don't just Copy and Paste it!)*
+      ```sh
+      http {
+        include       mime.types;
+        include       conf.d/*.conf; 
+        types_hash_max_size 4096;
+        # ...
+      }
+      ```
+    * Now, test your configuration with `nginx -t`, if it says that everything is good, restart *(or start)* the Nginx daemon:
+      * This depends on the init manager, most distributions use `systemd`, but it's better practice to include most.
+      ```sh
+      # systemd
+      systemctl stop nginx
+      systemctl start nginxt
+      # or
+      systemctl restart nginx
+
+      # openrc
+      rc-service nginx stop
+      rc-service nginx start
+      # or
+      rc-service nginx restart
+
+      # runit
+      sv down nginx
+      sv up nginx
+      # or
+      sv restart nginx
+
+      # s6
+      s6-rc -d change nginx
+      s6-rc -u change nginx
+      # or
+      s6-svc -r /run/service/nginx
+
+      # dinit
+      dinitctl stop nginx
+      dinitctl start nginx
+      # or
+      dinitctl restart nginx
+      ```
+6. Clone the repository to `/var/www`:
+   * `git clone --depth 1 https://git.lolcat.ca/lolcat/4get 4get` - It clones the repository with the depth of one commit *(so it takes less time to download)* and saves the cloned repository as '4get'.
+7. That should be it! There are some extra steps you can take, but it really just depends on you.
+
+<h2 align=center>Encryption setup</h2>
+
+1. Generate a certificate for the domain you're using with:
+   * Note that `certbot-nginx` is needed.
+    ```sh
+    certbot --nginx --key-type ecdsa -d www.yourdomain.com -d yourdomain.com
+    ```
+2. After that, certbot will deploy the certificate automatically to your 4get conf file; It should be ready to use from there.
+
+<h2 align=center>Tor Setup</h2>
+
+<div align=right>
+
+> IMPORTANT: Tor onion addresses are very long compared to traditional domains, so, Before doing anything, edit `nginx.conf` and increase <abbr title="This setting in your Nginx configuration controls the internal data structure used to manage multiple server names (hostnames) associated with your web server. Each hostname requires a certain amount of memory within this structure. If the size is insufficient, Nginx will encounter errors."><code>server_names_hash_bucket_size</code></abbr> to your needs.
+
+</div>
+
+1. `cd` to `/etc/nginx` *(if you haven't)* and open your `nginx.conf` file.
+2. Find the line containing `# server_names_hash_bucket_size 64;` inside said file.
+3. Uncomment the line and adjust the value; start with 64, but if you encounter issues, incrementally increase it *(e.g., 128, 256)* until it accommodates your configuration.
+4. Open *(or duplicate the configuration)* and edit it:
+   * Example configuration, again:
+    ```sh
+    server {
+        access_log /dev/null; # Search log file. Do you really need to?
+        error_log /dev/null;  # Error log file.
+
+        # Change this if you have 4get in another folder.
+        root /var/www/4get;
+        # Change 'onionadress.onion' to your onion link.
+        server_name onionadress.onion;
+        # Port to listen to.
+        listen 80;
+
+        location @php {
+            try_files $uri.php $uri/index.php =404;
+            # Change the unix socket address if it's different for you.
+            fastcgi_pass unix:/var/run/php-fpm/php-fpm.sock;
+            fastcgi_index index.php;
+            # Change this to `fastcgi_params` if you use a debian based distribution.
+            include fastcgi.conf;
+            fastcgi_intercept_errors on;
+        }
+
+        location / {
+            try_files $uri @php;
+        }
+
+        location ~* ^(.*)\.php$ {
+            return 301 $1;
+        }
 
-    location / {
-        try_files $uri @php;
     }
+    ```
+    A real world example is present in [^2].
+5. Once done, check the configuration with `nginx -t`. If everything's fine and dandy, refer to <a href="https://git.lolcat.ca/lolcat/4get/src/branch/master/docs/tor.md">the Tor guide</a> to setup your onion site.
 
-    location ~* ^(.*)\.php$ {
-        return 301 $1;
-    }
-}
-```
+<h2 align=center>Other important things</h2>
 
-Obviously replace `<youronionaddress>` by the onion address of `/var/lib/tor/4get/hostname` and then check if the nginx config is valid with `nginx -t` if yes, then restart the nginx service and try opening the onion address into the Tor Browser. You can see a real world example [here](https://git.zzls.xyz/Fijxu/etc-configs/src/branch/selfhost/nginx/sites-available/4get.zzls.xyz.conf)
+1. <a href="https://git.lolcat.ca/lolcat/4get/src/branch/master/docs/configure.md">Configuration guide</a>: Things to do after setup.
+2. <a href="https://git.lolcat.ca/lolcat/4get/src/branch/master/docs/apache2.md">Apache2 guide</a>: Fallback to this if you couldn't get something to work, or you don't know something.
 
-Once you did the above, refer to <a href="https://git.lolcat.ca/lolcat/4get/src/branch/master/docs/tor.md">this tor guide</a> to setup your onionsite.
+<h2 align=center>Known issues</h2>
+
+1. https://git.lolcat.ca/lolcat/4get/issues
+
+[^1]: lolcat/4get#40, If having issues with `libsodium`, or `php-apcu`.
+[^2]: <a href="https://git.nadeko.net/Fijxu/etc-configs/src/branch/selfhost/nginx/conf.d/4get.conf">git.nadeko.net</a> nadeko.net's 4get instance configuration.

favicon.php

@@ -15,7 +15,12 @@ class favicon{
 		
 		header("Content-Type: image/png");
 		
-		if(substr_count($url, "/") !== 2){
+		if(
+			preg_match(
+				'/^https?:\/\/[A-Za-z0-9.-]+$/',
+				$url
+			) === 0
+		){
 			
 			header("X-Error: Only provide the protocol and domain");
 			$this->defaulticon();

lib/anubis.php

@@ -0,0 +1,100 @@
+<?php
+
+//
+// Reference
+// https://github.com/TecharoHQ/anubis/blob/ecc716940e34ebe7249974f2789a99a2c7115e4e/web/js/proof-of-work.mjs
+//
+
+class anubis{
+	
+	public function __construct(){
+		
+		include_once "fuckhtml.php";
+		$this->fuckhtml = new fuckhtml();
+	}
+	
+	public function scrape($html){
+		
+		$this->fuckhtml->load($html);
+		
+		$script =
+			$this->fuckhtml
+			->getElementById(
+				"anubis_challenge",
+				"script"
+			);
+		
+		if($script === false){
+			
+			throw new Exception("Failed to scrape anubis challenge data");
+		}
+		
+		$script =
+			json_decode(
+				$this->fuckhtml
+				->getTextContent(
+					$script
+				),
+				true
+			);
+		
+		if($script === null){
+			
+			throw new Exception("Failed to decode anubis challenge data");
+		}
+		
+		if(
+			!isset($script["challenge"]) ||
+			!isset($script["rules"]["difficulty"]) ||
+			!is_int($script["rules"]["difficulty"]) ||
+			!is_string($script["challenge"])
+		){
+			
+			throw new Exception("Found invalid challenge data");
+		}
+		
+		return $this->rape($script["challenge"], $script["rules"]["difficulty"]);
+	}
+	
+	private function is_valid_hash($hash, $difficulty){
+		
+		for ($i=0; $i<$difficulty; $i++) {
+			
+			$index = (int)floor($i / 2);
+			$nibble = $i % 2;
+			
+			$byte = ord($hash[$index]);
+			$nibble = ($byte >> ($nibble === 0 ? 4 : 0)) & 0x0f;
+			
+			if($nibble !== 0){
+				return false;
+			}
+		}
+		
+		return true;
+	}
+	
+	public function rape($data, $difficulty = 5){
+		
+		$nonce = 0;
+		
+		while(true){
+			
+			$hash_binary = hash("sha256", $data . $nonce, true);
+			
+			if($this->is_valid_hash($hash_binary, $difficulty)){
+				
+				$hash_hex = bin2hex($hash_binary);
+				
+				return [
+					"response" => $hash_hex,
+					//"data" => $data,
+					//"difficulty" => $difficulty,
+					"nonce" => $nonce
+				];
+			}
+			
+			$nonce++;
+		}
+	}
+}

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 +939,8 @@ class frontend{
 						"brave" => "Brave",
 						"yandex" => "Yandex",
 						"google" => "Google",
+						//"google_api" => "Google API",
+						"google_cse" => "Google CSE",
 						"startpage" => "Startpage",
 						"qwant" => "Qwant",
 						"ghostery" => "Ghostery",
@@ -947,7 +949,9 @@ class frontend{
 						"crowdview" => "Crowdview",
 						"mwmbl" => "Mwmbl",
 						"mojeek" => "Mojeek",
-						"solofield" => "Solofield",
+						"baidu" => "Baidu",
+						"coccoc" => "Cốc Cốc",
+						//"solofield" => "Solofield",
 						"marginalia" => "Marginalia",
 						"wiby" => "wiby",
 						"curlie" => "Curlie"
@@ -963,13 +967,19 @@ class frontend{
 						"yandex" => "Yandex",
 						"brave" => "Brave",
 						"google" => "Google",
+						"google_cse" => "Google CSE",
 						"startpage" => "Startpage",
 						"qwant" => "Qwant",
 						"yep" => "Yep",
-						"solofield" => "Solofield",
-						//"pinterest" => "Pinterest",
+						"baidu" => "Baidu",
+						//"solofield" => "Solofield",
+						"pinterest" => "Pinterest",
+						"flickr" => "Flickr",
+						"fivehpx" => "500px",
+						"vsco" => "VSCO",
 						"imgur" => "Imgur",
-						"ftm" => "FindThatMeme"
+						"ftm" => "FindThatMeme",
+						//"sankakucomplex" => "SankakuComplex"
 					]
 				];
 				break;
@@ -979,6 +989,7 @@ class frontend{
 					"display" => "Scraper",
 					"option" => [
 						"yt" => "YouTube",
+						"sepiasearch" => "Sepia Search",
 						//"fb" => "Facebook videos",
 						"ddg" => "DuckDuckGo",
 						"brave" => "Brave",
@@ -986,7 +997,9 @@ class frontend{
 						"google" => "Google",
 						"startpage" => "Startpage",
 						"qwant" => "Qwant",
-						"solofield" => "Solofield"
+						"baidu" => "Baidu",
+						"coccoc" => "Cốc Cốc"
+						//"solofield" => "Solofield"
 					]
 				];
 				break;
@@ -1001,7 +1014,8 @@ class frontend{
 						"startpage" => "Startpage",
 						"qwant" => "Qwant",
 						"yep" => "Yep",
-						"mojeek" => "Mojeek"
+						"mojeek" => "Mojeek",
+						"baidu" => "Baidu"
 					]
 				];
 				break;

lib/fuckhtml.php

@@ -240,12 +240,13 @@ class fuckhtml{
 	public function getElementsByFuzzyAttributeValue(string $name, string $value, $collection = null){
 		
 		$elems = $this->getElementsByAttributeName($name, $collection);
+		
 		$value =
 			explode(
 				" ",
 				trim(
 					preg_replace(
-						'/ +/',
+						'/\s+/',
 						" ",
 						$value
 					)
@@ -258,7 +259,18 @@ class fuckhtml{
 			
 			foreach($elem["attributes"] as $attrib_name => $attrib_value){
 				
-				$attrib_value = explode(" ", $attrib_value);
+				$attrib_value =
+					explode(
+						" ",
+						trim(
+							preg_replace(
+								'/\s+/',
+								" ",
+								$attrib_value
+							)
+						)
+					);
+				
 				$ac = count($attrib_value);
 				$nc = count($value);
 				$cr = 0;
@@ -381,6 +393,8 @@ class fuckhtml{
 		$json_out = null;
 		$last_char = null;
 		
+		$keyword_check = null;
+		
 		for($i=0; $i<strlen($json); $i++){
 			
 			switch($json[$i]){
@@ -396,6 +410,7 @@ class fuckhtml{
 						
 						$bracket = false;
 						$is_close_bracket = true;
+						
 					}else{
 						
 						if($bracket === false){
@@ -429,6 +444,31 @@ 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 +538,85 @@ 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;
+			}
+		}
+	}
 }

proxy.php

@@ -34,22 +34,46 @@ try{
 		)
 	){
 		
-		if(
-			!isset($image["query"]) ||
-			!isset($image["path"]) ||
-			$image["path"] != "/th"
-		){
+		if(!isset($image["path"])){
 			
-			header("X-Error: Invalid bing image path");
+			header("X-Error: Missing bing image path");
 			$proxy->do404();
 			die();
 		}
 		
-		parse_str($image["query"], $str);
-		
-		if(!isset($str["id"])){
+		//
+		// get image ID
+		// formations:
+		// https://tse2.mm.bing.net/th/id/OIP.3yLBkUPn8EXA1wlhWP2BHwHaE3
+		// https://tse2.mm.bing.net/th?id=OIP.3yLBkUPn8EXA1wlhWP2BHwHaE3
+		//
+		$id = null;
+		if(isset($image["query"])){
 			
-			header("X-Error: Missing bing ID");
+			parse_str($image["query"], $str);
+			
+			if(isset($str["id"])){
+				
+				$id = $str["id"];
+			}
+		}
+		
+		if($id === null){
+			
+			$id = explode("/th/id/", $image["path"], 2);
+			
+			if(count($id) !== 2){
+				
+				// malformed
+				return $url;
+			}
+			
+			$id = $id[1];
+		}
+		
+		if(is_array($id)){
+			
+			header("X-Error: Missing bing id parameter");
 			$proxy->do404();
 			die();
 		}
@@ -63,7 +87,7 @@ try{
 			case "cover": $req = "&w=207&h=270&p=0&qlt=90"; break;
 		}
 		
-		$proxy->stream_linear_image("https://" . $image["host"] . "/th?id=" . urlencode($str["id"]) . $req, "https://www.bing.com");
+		$proxy->stream_linear_image("https://" . $image["host"] . "/th?id=" . rawurlencode($id) . $req, "https://www.bing.com");
 		die();
 	}
 	

scraper/brave.php

@@ -210,6 +210,63 @@ class brave{
 		return $data;
 	}
 	
+	private function get_js(){
+		
+		$script_disc =
+			$this->fuckhtml
+			->getElementsByTagName(
+				"script"
+			);
+		
+		$data = null;
+		foreach($script_disc as &$discs){
+			
+			if(
+				preg_match(
+					'/kit\.start\(/',
+					$discs["innerHTML"]
+				)
+			){
+				
+				$data =
+					explode(
+						"data:",
+						$discs["innerHTML"],
+						2
+					);
+				
+				if(count($data) !== 2){
+					
+					throw new Exception("Failed to split up data field");
+				}
+				
+				$data = $data[1];
+				break;
+			}
+		}
+		
+		if($data === null){
+			
+			throw new Exception("Could not grep JavaScript object");
+		}
+		
+		$data =
+			$this->fuckhtml
+			->parseJsObject(
+				$this->fuckhtml
+				->extract_json(
+					$data
+				)
+			);
+		
+		if($data === null){
+			
+			throw new Exception("Failed to decode JavaScript object");
+		}
+		
+		return $data;
+	}
+	
 	public function web($get){
 		
 		if($get["npt"]){
@@ -293,8 +350,8 @@ class brave{
 		/*
 		$handle = fopen("scraper/brave.html", "r");
 		$html = fread($handle, filesize("scraper/brave.html"));
-		fclose($handle);
-		*/
+		fclose($handle);*/
+		
 		
 		try{
 			$html =
@@ -346,7 +403,7 @@ class brave{
 			
 			$nextpage =
 				$this->fuckhtml
-				->getElementsByClassName("btn", "a");
+				->getElementsByClassName("button", "a");
 			
 			if(count($nextpage) !== 0){
 				
@@ -382,45 +439,9 @@ class brave{
 			}
 		}
 		
+		// do some magic
 		$this->fuckhtml->load($html);
-		
-		$script_disc =
-			$this->fuckhtml
-			->getElementsByTagName(
-				"script"
-			);
-		
-		$grep = [];
-		foreach($script_disc as $discs){
-			
-			preg_match(
-				'/const data ?= ?(\[{.*}]);/',
-				$discs["innerHTML"],
-				$grep
-			);
-			
-			if(isset($grep[1])){
-				
-				break;
-			}
-		}
-		
-		if(!isset($grep[1])){
-			
-			throw new Exception("Could not grep JavaScript object");
-		}
-		
-		$data =
-			$this->fuckhtml
-			->parseJsObject(
-				$grep[1]
-			);
-		unset($grep);
-		
-		if($data === null){
-			
-			throw new Exception("Failed to decode JavaScript object");
-		}
+		$data = $this->get_js();
 		
 		if(
 			isset($data[2]["data"]["title"]) &&
@@ -663,7 +684,10 @@ 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"] =
 						$result["location"]["rating"]["ratingValue"] . "/" .
@@ -671,13 +695,19 @@ class brave{
 						number_format($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"];
@@ -1160,23 +1190,8 @@ class brave{
 				$proxy
 			);
 		
-		preg_match(
-			'/const data ?= ?(\[{.*}]);/',
-			$html,
-			$json
-		);
-		
-		if(!isset($json[1])){
-			
-			throw new Exception("Failed to grep javascript object");
-		}
-		
-		$json = $this->fuckhtml->parseJsObject($json[1], true);
-		
-		if($json === null){
-			
-			throw new Exception("Failed to parse javascript object");
-		}
+		$this->fuckhtml->load($html);
+		$json = $this->get_js();
 		
 		foreach(
 			$json[1]["data"]["body"]["response"]["news"]["results"]
@@ -1258,22 +1273,8 @@ class brave{
 		$html = fread($handle, filesize("scraper/brave-image.html"));
 		fclose($handle);*/
 		
-		preg_match(
-			'/const data = (\[{.*}\]);/',
-			$html,
-			$json
-		);
-		
-		if(!isset($json[1])){
-			
-			throw new Exception("Failed to get data object");
-		}
-		
-		$json =
-			$this->fuckhtml
-			->parseJsObject(
-				$json[1]
-			);
+		$this->fuckhtml->load($html);
+		$json = $this->get_js();
 		
 		foreach(
 			$json[1]
@@ -1403,22 +1404,8 @@ class brave{
 		$html = fread($handle, filesize("scraper/brave-video.html"));
 		fclose($handle);*/
 		
-		preg_match(
-			'/const data = (\[{.*}\]);/',
-			$html,
-			$json
-		);
-		
-		if(!isset($json[1])){
-			
-			throw new Exception("Failed to get data object");
-		}
-		
-		$json =
-			$this->fuckhtml
-			->parseJsObject(
-				$json[1]
-			);
+		$this->fuckhtml->load($html);
+		$json = $this->get_js();
 		
 		foreach(
 			$json
@@ -1790,42 +1777,57 @@ class brave{
 		
 		$nextpage =
 			$this->fuckhtml
-			->getElementsByClassName("btn", "a");
+			->getElementById(
+				"pagination",
+				"div"
+			);
 		
-		if(count($nextpage) !== 0){
+		if($nextpage){
+			
+			$this->fuckhtml->load($nextpage);
 			
 			$nextpage =
-				$nextpage[count($nextpage) - 1];
-			
-			if(
-				strtolower(
-					$this->fuckhtml
-					->getTextContent(
-						$nextpage
-					)
-				) == "next"
-			){
-				
-				preg_match(
-					'/offset=([0-9]+)/',
-					$this->fuckhtml->getTextContent($nextpage["attributes"]["href"]),
-					$nextpage
+				$this->fuckhtml
+				->getElementsByClassName(
+					"button",
+					"a"
 				);
+			
+			if(count($nextpage) !== 0){
 				
-				return
-					$this->backend->store(
-						json_encode(
-							[
-								"q" => $q,
-								"offset" => (int)$nextpage[1],
-								"nsfw" => $nsfw,
-								"country" => $country,
-								"spellcheck" => $spellcheck
-							]
-						),
-						$page,
-						$proxy
+				$nextpage =
+					$nextpage[count($nextpage) - 1];
+				
+				if(
+					strtolower(
+						$this->fuckhtml
+						->getTextContent(
+							$nextpage
+						)
+					) == "next"
+				){
+					
+					preg_match(
+						'/offset=([0-9]+)/',
+						$this->fuckhtml->getTextContent($nextpage["attributes"]["href"]),
+						$nextpage
 					);
+					
+					return
+						$this->backend->store(
+							json_encode(
+								[
+									"q" => $q,
+									"offset" => (int)$nextpage[1],
+									"nsfw" => $nsfw,
+									"country" => $country,
+									"spellcheck" => $spellcheck
+								]
+							),
+							$page,
+							$proxy
+						);
+				}
 			}
 		}
 		

scraper/coccoc.php

@@ -0,0 +1,672 @@
+<?php
+
+class coccoc{
+	
+	public function __construct(){
+		
+		include "lib/backend.php";
+		$this->backend = new backend("coccoc");
+		
+		include "lib/fuckhtml.php";
+		$this->fuckhtml = new fuckhtml();
+	}
+	
+	
+	private function get($proxy, $url, $get = []){
+		
+		$curlproc = curl_init();
+		
+		if($get !== []){
+			$get = http_build_query($get);
+			$url .= "?" . $get;
+		}
+		
+		curl_setopt($curlproc, CURLOPT_URL, $url);
+		
+		// http2 bypass
+		curl_setopt($curlproc, CURLOPT_HTTP_VERSION, CURL_HTTP_VERSION_2_0);
+		
+		curl_setopt($curlproc, CURLOPT_HTTPHEADER, [
+			"Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
+			"Accept-Language: en-US,en;q=0.5",
+			"Accept-Encoding: gzip, deflate, br, zstd",
+			"DNT: 1",
+			"Sec-GPC: 1",
+			"Connection: keep-alive",
+			//"Cookie: _contentAB_15040_vi=V-06_01; split_test_search=new_search; uid=L_bauXyZBY1B; vid=uCVQJQSTgb9QGT3o; ls=1753742684; serp_version=29223843/7621a70; savedS=direct",
+			"Upgrade-Insecure-Requests: 1",
+			"Sec-Fetch-Dest: document",
+			"Sec-Fetch-Mode: navigate",
+			"Sec-Fetch-Site: cross-site",
+			"Priority: u=0, i"
+		]);
+		
+		$this->backend->assign_proxy($curlproc, $proxy);
+		
+		curl_setopt($curlproc, CURLOPT_ENCODING, ""); // default encoding
+		
+		curl_setopt($curlproc, CURLOPT_RETURNTRANSFER, true);
+		curl_setopt($curlproc, CURLOPT_SSL_VERIFYHOST, 2);
+		curl_setopt($curlproc, CURLOPT_SSL_VERIFYPEER, true);
+		curl_setopt($curlproc, CURLOPT_CONNECTTIMEOUT, 30);
+		curl_setopt($curlproc, CURLOPT_TIMEOUT, 30);
+		
+		$data = curl_exec($curlproc);
+		
+		if(curl_errno($curlproc)){
+			throw new Exception(curl_error($curlproc));
+		}
+		
+		curl_close($curlproc);
+		return $data;
+	}
+	
+	public function getfilters($pagetype){
+		
+		return [
+			"nsfw" => [
+				"display" => "NSFW",
+				"option" => [
+					"yes" => "Yes", // nsfw by default????
+					"no" => "No" // &safe=1
+				]
+			],
+			"time" => [
+				"display" => "Time posted",
+				"option" => [
+					"any" => "Any time",
+					"1w" => "1 week ago",
+					"2w" => "2 weeks ago",
+					"1m" => "1 month ago",
+					"3m" => "3 months ago",
+					"6m" => "6 months ago",
+					"1Y" => "1 year ago"
+				]
+			],
+			"filter" => [
+				"display" => "Remove duplicates",
+				"option" => [
+					"no" => "No",
+					"yes" => "Yes" // &filter=0
+				]
+			]
+		];
+	}
+	
+	public function web($get){
+		
+		if($get["npt"]){
+			
+			[$query, $proxy] =
+				$this->backend->get(
+					$get["npt"],
+					"web"
+				);
+			
+			$query = json_decode($query, true);
+		}else{
+			
+			$proxy = $this->backend->get_ip();
+			
+			$query = [
+				"query" => $get["s"]
+			];
+			
+			// add filters
+			if($get["nsfw"] == "no"){
+				
+				$query["safe"] = 1;
+			}
+			
+			if($get["time"] != "any"){
+				
+				$query["tbs"] = $get["time"];
+			}
+			
+			if($get["filter"] == "yes"){
+				
+				$query["filter"] = 0;
+			}
+		}
+		
+		try{
+			
+			$html =
+				$this->get(
+					$proxy,
+					"https://coccoc.com/search",
+					$query
+				);
+		}catch(Exception $error){
+			
+			throw new Exception("Failed to get search page");
+		}
+		//$html = file_get_contents("scraper/coccoc.html");
+		
+		
+		$html = explode("window.composerResponse", $html, 2);
+		
+		if(count($html) !== 2){
+			
+			throw new Exception("Failed to grep window.composerResponse");
+		}
+		
+		$html =
+			json_decode(
+				$this->fuckhtml
+				->extract_json(
+					ltrim($html[1], " =")
+				),
+				true
+			);
+		
+		if($html === null){
+			
+			throw new Exception("Failed to decode JSON");
+		}
+		
+		if(!isset($html["search"]["search_results"])){
+			
+			throw new Exception("Coc Coc did not return a search_results object");
+		}
+		
+		$out = [
+			"status" => "ok",
+			"spelling" => [
+				"type" => "no_correction",
+				"using" => null,
+				"correction" => null
+			],
+			"npt" => null,
+			"answer" => [],
+			"web" => [],
+			"image" => [],
+			"video" => [],
+			"news" => [],
+			"related" => []
+		];
+		
+		// word correction
+		foreach($html["top"] as $element){
+			
+			if(isset($element["spellChecker"][0]["query"])){
+				
+				$out["spelling"] = [
+					"type" => "not_many",
+					"using" => $html["search"]["query"],
+					"correction" => $element["spellChecker"][0]["query"]
+				];
+			}
+		}
+		
+		foreach($html["search"]["search_results"] as $result){
+			
+			if(isset($result["type"])){
+				
+				switch($result["type"]){
+					
+					//
+					// Related searches
+					//
+					case "related_queries":
+						$out["related"] = $result["queries"];
+						continue 2;
+					
+					//
+					// Videos
+					//
+					case "video_hits":
+						foreach($result["results"] as $video){
+							
+							if(
+								isset($video["image_url"]) &&
+								!empty($video["image_url"])
+							){
+								
+								$thumb = [
+									"ratio" => "16:9",
+									"url" => $video["image_url"]
+								];
+							}else{
+								
+								$thumb = [
+									"ratio" => null,
+									"url" => null
+								];
+							}
+							
+							$out["video"][] = [
+								"title" =>
+									$this->titledots(
+										$this->fuckhtml
+										->getTextContent(
+											$video["title"]
+										)
+									),
+								"description" => null,
+								"author" => [
+									"name" => $video["uploader"],
+									"url" => null,
+									"avatar" => null
+								],
+								"date" => (int)$video["date"],
+								"duration" => (int)$video["duration"],
+								"views" => null,
+								"thumb" => $thumb,
+								"url" => $video["url"]
+							];
+						}
+						continue 2;
+				}
+			}
+			
+			if(
+				!isset($result["title"]) ||
+				!isset($result["url"])
+			){
+				
+				// should not happen
+				continue;
+			}
+			
+			if(isset($result["rich"]["data"]["image_url"])){
+				
+				$thumb = [
+					"url" => $result["rich"]["data"]["image_url"],
+					"ratio" => "16:9"
+				];
+			}else{
+				
+				$thumb = [
+					"url" => null,
+					"ratio" => null
+				];
+			}
+			
+			$sublinks = [];
+			
+			if(isset($result["rich"]["data"]["linked_docs"])){
+				
+				foreach($result["rich"]["data"]["linked_docs"] as $sub){
+					
+					$sublinks[] = [
+						"title" =>
+							$this->titledots(
+								$this->fuckhtml
+								->getTextContent(
+									$sub["title"]
+								)
+							),
+						"description" =>
+							$this->titledots(
+								$this->fuckhtml
+								->getTextContent(
+									$sub["content"]
+								)
+							),
+						"date" => null,
+						"url" => $sub["url"]
+					];
+				}
+			}
+			
+			// get date
+			if(isset($result["date"])){
+				
+				$date = (int)$result["date"];
+			}else{
+				
+				$date = null;
+			}
+			
+			// probe for metadata
+			$table = [];
+			
+			if(isset($result["rich"]["data"]["rating"])){
+				
+				$table["Rating"] = $result["rich"]["data"]["rating"];
+				
+				if(isset($result["rich"]["data"]["num_rating"])){
+					
+					$table["Rating"] .= " (" . number_format($result["rich"]["data"]["num_rating"]) . " ratings)";
+				}
+			}
+			
+			if(isset($result["rich"]["data"]["views"])){
+				
+				$table["Views"] = number_format($result["rich"]["data"]["views"]);
+			}
+			
+			if(isset($result["rich"]["data"]["duration"])){
+				
+				$table["Duration"] = $this->int2hms($result["rich"]["data"]["duration"]);
+			}
+			
+			if(isset($result["rich"]["data"]["channel_name"])){
+				
+				$table["Author"] = $result["rich"]["data"]["channel_name"];
+			}
+			
+			if(isset($result["rich"]["data"]["video_quality"])){
+				
+				$table["Quality"] = $result["rich"]["data"]["video_quality"];
+			}
+			
+			if(isset($result["rich"]["data"]["category"])){
+				
+				$table["Category"] = $result["rich"]["data"]["category"];
+			}
+			
+			$out["web"][] = [
+				"title" =>
+					$this->titledots(
+						$this->fuckhtml
+						->getTextContent(
+							$result["title"]
+						)
+					),
+				"description" =>
+					$this->titledots(
+						$this->fuckhtml
+						->getTextContent(
+							$result["content"]
+						)
+					),
+				"url" => $result["url"],
+				"date" => $date,
+				"type" => "web",
+				"thumb" => $thumb,
+				"sublink" => $sublinks,
+				"table" => $table
+			];
+		}
+		
+		//
+		// Get wikipedia head
+		//
+		if(isset($html["right"])){
+			
+			foreach($html["right"] as $wiki){
+				
+				$description = [];
+				
+				if(isset($wiki["short_intro"])){
+					
+					$description[] =
+						[
+							"type" => "quote",
+							"value" => $wiki["short_intro"],
+						];
+				}
+				
+				if(isset($wiki["intro"])){
+					
+					$description[] =
+						[
+							"type" => "text",
+							"value" => $wiki["intro"],
+						];
+				}
+				
+				// get table elements
+				$table = [];
+				
+				if(isset($wiki["fields"])){
+					
+					foreach($wiki["fields"] as $element){
+						
+						$table[$element["title"]] = implode(", ", $element["value"]);
+					}
+				}
+				
+				// get sublinks
+				$sublinks = [];
+				
+				if(isset($wiki["website"])){
+					
+					if(
+						preg_match(
+							'/^http/',
+							$wiki["website"]
+						) === 0
+					){
+						
+						$sublinks["Website"] = "https://" . $wiki["website"];
+					}else{
+						
+						$sublinks["Website"] = $wiki["website"];
+					}
+				}
+				
+				foreach($wiki["profiles"] as $sitename => $url){
+					
+					$sitename = explode("_", $sitename);
+					$sitename = ucfirst($sitename[count($sitename) - 1]);
+					
+					$sublinks[$sitename] = $url;
+				}
+				
+				$out["answer"][] = [
+					"title" =>
+						$this->titledots(
+							$wiki["title"]
+						),
+					"description" => $description,
+					"url" => null,
+					"thumb" => isset($wiki["image"]["contentUrl"]) ? $wiki["image"]["contentUrl"] : null,
+					"table" => $table,
+					"sublink" => $sublinks
+				];
+			}
+		}
+		
+		// get next page
+		if((int)$html["search"]["page"] < (int)$html["search"]["max_page"]){
+			
+			// https://coccoc.com/composer?_=1754021153532&p=0&q=zbabduiqwhduwqhdnwq&reqid=bwcAs00q&s=direct&apiV=1
+			// ^json endpoint, but we can just do &page=2 lol
+			
+			if(!isset($query["page"])){
+				
+				$query["page"] = 2;
+			}else{
+				
+				$query["page"]++;
+			}
+			
+			$out["npt"] =
+				$this->backend
+				->store(
+					json_encode($query),
+					"web",
+					$proxy
+				);
+		}
+		
+		return $out;
+	}
+	
+	public function video($get){
+		
+		//$html = file_get_contents("scraper/coccoc.html");
+		if($get["npt"]){
+			
+			[$query, $proxy] =
+				$this->backend->get(
+					$get["npt"],
+					"videos"
+				);
+			
+			$query = json_decode($query, true);
+		}else{
+			
+			$proxy = $this->backend->get_ip();
+			
+			$query = [
+				"query" => $get["s"],
+				"tbm" => "vid"
+			];
+			
+			// add filters
+			if($get["nsfw"] == "no"){
+				
+				$query["safe"] = 1;
+			}
+			
+			if($get["time"] != "any"){
+				
+				$query["tbs"] = $get["time"];
+			}
+			
+			if($get["filter"] == "yes"){
+				
+				$query["filter"] = 0;
+			}
+		}
+		
+		try{
+			
+			$html =
+				$this->get(
+					$proxy,
+					"https://coccoc.com/search",
+					$query
+				);
+		}catch(Exception $error){
+			
+			throw new Exception("Failed to get search page");
+		}
+		
+		$html = explode("window.composerResponse", $html, 2);
+		
+		if(count($html) !== 2){
+			
+			throw new Exception("Failed to grep window.composerResponse");
+		}
+		
+		$html =
+			json_decode(
+				$this->fuckhtml
+				->extract_json(
+					ltrim($html[1], " =")
+				),
+				true
+			);
+		
+		if($html === null){
+			
+			throw new Exception("Failed to decode JSON");
+		}
+		
+		$out = [
+			"status" => "ok",
+			"npt" => null,
+			"video" => [],
+			"author" => [],
+			"livestream" => [],
+			"playlist" => [],
+			"reel" => []
+		];
+		
+		if(!isset($html["search_video"]["search_results"])){
+			
+			if(isset($html["search_video"]["error"]["title"])){
+				
+				if($html["search_video"]["error"]["title"] == "Không tìm thấy kết quả nào"){
+					
+					return $out;
+				}
+				
+				throw new Exception("Coc Coc returned an error: " . $html["search_video"]["error"]["title"]);
+			}
+			
+			throw new Exception("Coc Coc did not supply a search_results object");
+		}
+		
+		foreach($html["search_video"]["search_results"] as $video){
+			
+			if(isset($video["rich"]["data"]["image_url"])){
+				
+				$thumb = [
+					"ratio" => "16:9",
+					"url" => $video["rich"]["data"]["image_url"]
+				];
+			}else{
+				
+				$thumb = [
+					"ratio" => null,
+					"url" => null
+				];
+			}
+			
+			$out["video"][] = [
+				"title" =>
+					$this->titledots(
+						$this->fuckhtml
+						->getTextContent(
+							$video["title"]
+						)
+					),
+				"description" =>
+					$this->titledots(
+						$this->fuckhtml
+						->getTextContent(
+							$video["content"]
+						)
+					),
+				"author" => [
+					"name" => 
+						isset($video["rich"]["data"]["channel_name"]) ?
+							$video["rich"]["data"]["channel_name"] : null,
+					"url" => null,
+					"avatar" => null
+				],
+				"date" =>
+					isset($video["date"]) ?
+						$video["date"] : null,
+				"duration" =>
+					isset($video["rich"]["data"]["duration"]) ?
+						(int)$video["rich"]["data"]["duration"] : null,
+				"views" => null,
+				"thumb" => $thumb,
+				"url" => $video["url"]
+			];
+		}
+		
+		// get next page
+		if((int)$html["search_video"]["page"] < (int)$html["search_video"]["max_page"]){
+			
+			if(!isset($query["page"])){
+				
+				$query["page"] = 2;
+			}else{
+				
+				$query["page"]++;
+			}
+			
+			$out["npt"] =
+				$this->backend
+				->store(
+					json_encode($query),
+					"videos",
+					$proxy
+				);
+		}
+		
+		return $out;
+	}
+	
+	private function titledots($title){
+		
+		return trim($title, " .\t\n\r\0\x0B…");
+	}
+	
+	private function int2hms($seconds){
+		
+		$hours = floor($seconds / 3600);
+		$minutes = floor(($seconds % 3600) / 60);
+		$seconds = $seconds % 60;
+		
+		return sprintf("%02d:%02d:%02d", $hours, $minutes, $seconds);
+	}
+}

scraper/fivehpx.php

@@ -0,0 +1,262 @@
+<?php
+
+class fivehpx{
+	
+	public function __construct(){
+		
+		include "lib/backend.php";
+		$this->backend = new backend("fivehpx");
+		
+		include "lib/fuckhtml.php";
+		$this->fuckhtml = new fuckhtml();
+	}
+	
+	public function getfilters($page){
+		
+		return [
+			"sort" => [
+				"display" => "Sort",
+				"option" => [
+					"relevance" => "Relevance",
+					"pulse" => "Pulse",
+					"newest" => "Newest"
+				]
+			]
+		];
+	}
+	
+	private function get($proxy, $url, $get = [], $post_data = null){
+		
+		$curlproc = curl_init();
+		
+		if($get !== []){
+			$get = http_build_query($get);
+			$url .= "?" . $get;
+		}
+		
+		curl_setopt($curlproc, CURLOPT_URL, $url);
+		
+		curl_setopt($curlproc, CURLOPT_ENCODING, ""); // default encoding
+		
+		if($post_data === null){
+			
+			curl_setopt($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",
+				"Sec-GPC: 1",
+				"Connection: keep-alive",
+				"Upgrade-Insecure-Requests: 1",
+				"Sec-Fetch-Dest: document",
+				"Sec-Fetch-Mode: navigate",
+				"Sec-Fetch-Site: same-origin",
+				"Sec-Fetch-User: ?1",
+				"Priority: u=0, i",
+				"TE: trailers"]
+			);
+		}else{
+			
+			curl_setopt($curlproc, CURLOPT_HTTPHEADER,
+				["User-Agent: " . config::USER_AGENT,
+				"Accept: */*",
+				"Accept-Language: en-US,en;q=0.5",
+				"Accept-Encoding: gzip",
+				"Referer: https://500px.com/",
+				"content-type: application/json",
+				//"x-csrf-token: undefined",
+				"x-500px-source: Search",
+				"Content-Length: " . strlen($post_data),
+				"Origin: https://500px.com",
+				"DNT: 1",
+				"Sec-GPC: 1",
+				"Connection: keep-alive",
+				// "Cookie: _pin_unauth, _fbp, _sharedID, _sharedID_cst",
+				"Sec-Fetch-Dest: empty",
+				"Sec-Fetch-Mode: cors",
+				"Sec-Fetch-Site: same-site",
+				"Priority: u=4",
+				"TE: trailers"]
+			);
+						
+			// set post data
+			curl_setopt($curlproc, CURLOPT_POST, true);
+			curl_setopt($curlproc, CURLOPT_POSTFIELDS, $post_data);
+		}
+		
+		curl_setopt($curlproc, CURLOPT_RETURNTRANSFER, true);
+		curl_setopt($curlproc, CURLOPT_SSL_VERIFYHOST, 2);
+		curl_setopt($curlproc, CURLOPT_SSL_VERIFYPEER, true);
+		curl_setopt($curlproc, CURLOPT_CONNECTTIMEOUT, 30);
+		curl_setopt($curlproc, CURLOPT_TIMEOUT, 30);
+		
+		// http2 bypass
+		curl_setopt($curlproc, CURLOPT_HTTP_VERSION, CURL_HTTP_VERSION_2_0);
+		
+		$this->backend->assign_proxy($curlproc, $proxy);
+		
+		$data = curl_exec($curlproc);
+		
+		if(curl_errno($curlproc)){
+			
+			throw new Exception(curl_error($curlproc));
+		}
+		
+		curl_close($curlproc);
+		return $data;
+	}
+	
+	public function image($get){
+		
+		if($get["npt"]){
+			
+			[$pagination, $proxy] =
+				$this->backend->get(
+					$get["npt"], "images"
+				);
+			
+			$pagination = json_decode($pagination, true);
+			$search = $pagination["search"];
+			
+		}else{
+			
+			$search = $get["s"];
+			if(strlen($search) === 0){
+				
+				throw new Exception("Search term is empty!");
+			}
+			
+			$proxy = $this->backend->get_ip();
+			$pagination = [
+				"sort" => strtoupper($get["sort"]),
+				"search" => $search,
+				"filters" => [],
+				"nlp" => false,
+			];
+		}
+		
+		try{
+			
+			$json =
+				$this->get(
+					$proxy,
+					"https://api.500px.com/graphql",
+					[],
+					json_encode([
+						"operationName" => "PhotoSearchPaginationContainerQuery",
+						"variables" => $pagination,
+						"query" =>
+							'query PhotoSearchPaginationContainerQuery(' .
+							(isset($pagination["cursor"]) ? '$cursor: String, ' : "") .
+							'$sort: PhotoSort, $search: String!, $filters: [PhotoSearchFilter!], $nlp: Boolean) {  ...PhotoSearchPaginationContainer_query_1vzAZD} fragment PhotoSearchPaginationContainer_query_1vzAZD on Query { photoSearch(sort: $sort, first: 100, ' .
+							(isset($pagination["cursor"]) ? 'after: $cursor, ' : "") .
+							'search: $search, filters: $filters, nlp: $nlp) { edges { node { id legacyId canonicalPath name description width height images(sizes: [33, 36]) { size url id } } } totalCount pageInfo { endCursor hasNextPage } }}'
+					])
+				);
+		}catch(Exception $error){
+			
+			throw new Exception("Failed to fetch graphQL object");
+		}
+		
+		$json = json_decode($json, true);
+		
+		if($json === null){
+			
+			throw new Exception("Failed to decode graphQL object");
+		}
+		
+		if(isset($json["errors"][0]["message"])){
+			
+			throw new Exception("500px returned an API error: " . $json["errors"][0]["message"]);
+		}
+		
+		if(!isset($json["data"]["photoSearch"]["edges"])){
+			
+			throw new Exception("No edges returned by API");
+		}
+		
+		$out = [
+			"status" => "ok",
+			"npt" => null,
+			"image" => []
+		];
+		
+		foreach($json["data"]["photoSearch"]["edges"] as $image){
+			
+			$image = $image["node"];
+			$title =
+				trim(
+					$this->fuckhtml
+					->getTextContent(
+						$image["name"]
+					) . ": " .
+					$this->fuckhtml
+					->getTextContent(
+						$image["description"]
+					)
+					, " :"
+				);
+			
+			$small = $this->image_ratio(600, $image["width"], $image["height"]);
+			$large = $this->image_ratio(2048, $image["width"], $image["height"]);
+			
+			$out["image"][] = [
+				"title" => $title,
+				"source" => [
+					[
+						"url" => $image["images"][1]["url"],
+						"width" => $large[0],
+						"height" => $large[1]
+					],
+					[
+						"url" => $image["images"][0]["url"],
+						"width" => $small[0],
+						"height" => $small[1]
+					]
+				],
+				"url" => "https://500px.com" . $image["canonicalPath"]
+			];
+		}
+		
+		// get NPT token
+		if($json["data"]["photoSearch"]["pageInfo"]["hasNextPage"] === true){
+			
+			$out["npt"] =
+				$this->backend->store(
+					json_encode([
+						"cursor" => $json["data"]["photoSearch"]["pageInfo"]["endCursor"],
+						"search" => $search,
+						"sort" => $pagination["sort"],
+						"filters" => [],
+						"nlp" => false
+					]),
+					"images",
+					$proxy
+				);
+		}
+			
+		return $out;
+	}
+	
+	private function image_ratio($longest_edge, $width, $height){
+		
+		$ratio = [
+			$longest_edge / $width,
+			$longest_edge / $height
+		];
+		
+		if($ratio[0] < $ratio[1]){
+			
+			$ratio = $ratio[0];
+		}else{
+			
+			$ratio = $ratio[1];
+		}
+		
+		return [
+			floor($width * $ratio),
+			floor($height * $ratio)
+		];
+	}
+}

scraper/flickr.php

@@ -0,0 +1,415 @@
+<?php
+
+class flickr{
+	
+	const req_web = 0;
+	const req_xhr = 1;
+	
+	public function __construct(){
+		
+		include "lib/backend.php";
+		$this->backend = new backend("flickr");
+		
+		include "lib/fuckhtml.php";
+		$this->fuckhtml = new fuckhtml();
+	}
+	
+	public function getfilters($page){
+		
+		return [
+			"nsfw" => [
+				"display" => "NSFW",
+				"option" => [
+					"yes" => "Yes",
+					"maybe" => "Maybe",
+					"no" => "No",
+				]
+			],
+			"sort" => [
+				"display" => "Sort by",
+				"option" => [
+					"relevance" => "Relevance",
+					"date-posted-desc" => "Newest uploads",
+					"date-posted-asc" => "Oldest uploads",
+					"date-taken-desc" => "Newest taken",
+					"date-taken-asc" => "Oldest taken",
+					"interestingness-desc" => "Interesting"
+				]
+			],
+			"color" => [
+				"display" => "Color",
+				"option" => [
+					"any" => "Any color",
+					// color_codes=
+					"0" => "Red",
+					"1" => "Brown",
+					"2" => "Orange",
+					"b" => "Pink",
+					"4" => "Yellow",
+					"3" => "Golden",
+					"5" => "Lime",
+					"6" => "Green",
+					"7" => "Sky blue",
+					"8" => "Blue",
+					"9" => "Purple",
+					"a" => "Hot pink",
+					"c" => "White",
+					"d" => "Gray",
+					"e" => "Black",
+					// styles= override
+					"blackandwhite" => "Black & white",
+				]
+			],
+			"style" => [ // styles=
+				"display" => "Style",
+				"option" => [
+					"any" => "Any style",
+					"depthoffield" => "Depth of field",
+					"minimalism" => "Minimalism",
+					"pattern" => "Patterns"
+				]
+			],
+			"license" => [
+				"display" => "License",
+				"option" => [
+					"any" => "Any license",
+					"1,2,3,4,5,6,9,11,12,13,14,15,16" => "All creative commons",
+					"4,5,6,9,10,11,12,13" => "Commercial use allowed",
+					"1,2,4,5,9,10,11,12,14,15" => "Modifications allowed",
+					"4,5,9,10,11,12" => "Commercial use & mods allowed",
+					"7,9,10" => "No known copyright restrictions",
+					"8" => "U.S Government works"
+				]
+			]
+		];
+	}
+	
+	private function get($proxy, $url, $get = [], $reqtype){
+		
+		$curlproc = curl_init();
+		
+		if($get !== []){
+			$get = http_build_query($get);
+			$url .= "?" . $get;
+		}
+		
+		curl_setopt($curlproc, CURLOPT_URL, $url);
+		
+		curl_setopt($curlproc, CURLOPT_ENCODING, ""); // default encoding
+		
+		if($reqtype === flickr::req_web){
+			
+			curl_setopt($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",
+				"Sec-GPC: 1",
+				"Connection: keep-alive",
+				"Upgrade-Insecure-Requests: 1",
+				"Sec-Fetch-Dest: document",
+				"Sec-Fetch-Mode: navigate",
+				"Sec-Fetch-Site: same-origin",
+				"Sec-Fetch-User: ?1",
+				"Priority: u=0, i",
+				"TE: trailers"]
+			);
+		}else{
+			
+			curl_setopt($curlproc, CURLOPT_HTTPHEADER,
+				["User-Agent: " . config::USER_AGENT,
+				"Accept: */*",
+				"Accept-Language: en-US,en;q=0.5",
+				"Accept-Encoding: gzip",
+				"Origin: https://www.flickr.com",
+				"DNT: 1",
+				"Sec-GPC: 1",
+				"Connection: keep-alive",
+				"Referer: https://www.flickr.com/",
+				// Cookie:
+				"Sec-Fetch-Dest: empty",
+				"Sec-Fetch-Mode: cors",
+				"Sec-Fetch-Site: same-site",
+				"TE: trailers"]
+			);
+		}
+		
+		curl_setopt($curlproc, CURLOPT_RETURNTRANSFER, true);
+		curl_setopt($curlproc, CURLOPT_SSL_VERIFYHOST, 2);
+		curl_setopt($curlproc, CURLOPT_SSL_VERIFYPEER, true);
+		curl_setopt($curlproc, CURLOPT_CONNECTTIMEOUT, 30);
+		curl_setopt($curlproc, CURLOPT_TIMEOUT, 30);
+		
+		// http2 bypass
+		curl_setopt($curlproc, CURLOPT_HTTP_VERSION, CURL_HTTP_VERSION_2_0);
+		
+		$this->backend->assign_proxy($curlproc, $proxy);
+		
+		$data = curl_exec($curlproc);
+		
+		if(curl_errno($curlproc)){
+			
+			throw new Exception(curl_error($curlproc));
+		}
+		
+		curl_close($curlproc);
+		return $data;
+	}
+	
+	public function image($get){
+		
+		if($get["npt"]){
+			
+			[$filters, $proxy] =
+				$this->backend->get(
+					$get["npt"], "images"
+				);
+			
+			$filters = json_decode($filters, true);
+			
+			// Workaround for the future, if flickr deprecates &page argument on html page
+			/*
+			try{
+				
+				$json =
+					$this->get(
+						$proxy,
+						"https://api.flickr.com/services/rest",
+						[
+							"sort" => $data["sort"],
+							"parse_tags" => 1,
+							// url_s,url_n,url_w,url_m,url_z,url_c,url_l,url_h,url_k,url_3k,url_4k,url_5k,url_6k,url_o
+							"extras" => "can_comment,can_print,count_comments,count_faves,description,isfavorite,license,media,needs_interstitial,owner_name,path_alias,realname,rotation,url_sq,url_q,url_t,url_s,url_n,url_w,url_m,url_z,url_c,url_l",
+							"per_page" => 100,
+							"page" => $data["page"],
+							"lang" => "en-US",
+							"text" => $data["search"],
+							"viewerNSID" => "",
+							"method" => "flickr.photos.search",
+							"csrf" => "",
+							"api_key" => $data["api_key"],
+							"format" => "json",
+							"hermes" => 1,
+							"hermesClient" => 1,
+							"reqId" => $data["reqId"],
+							"nojsoncallback" => 1
+						]
+					);
+			}catch(Exception $error){
+				
+				throw new Exception("Failed to fetch JSON");
+			}*/
+			
+		}else{
+			
+			if(strlen($get["s"]) === 0){
+				
+				throw new Exception("Search term is empty!");
+			}
+			
+			$proxy = $this->backend->get_ip();
+						
+			// compute filters
+			$filters = [
+				"page" => 1,
+				"sort" => $get["sort"]
+			];
+			
+			if($get["style"] != "any"){
+				
+				$filters["styles"] = $get["style"];
+			}
+			
+			if($get["color"] != "any"){
+				
+				if($get["color"] != "blackandwhite"){
+					
+					$filters["color_codes"] = $get["color"];
+				}else{
+					
+					$filters["styles"] = "blackandwhite";
+				}
+			}
+			
+			if($get["license"] != "any"){
+				
+				$filters["license"] = $get["license"];
+			}
+			
+			switch($get["nsfw"]){
+				
+				case "yes": $filters["safe_search"] = 0; break;
+				case "maybe": $filters["safe_search"] = 2; break;
+				case "no": $filters["safe_search"] = 1; break;
+			}
+		}
+		
+		$get_params = [
+			"text" => $get["s"],
+			"per_page" => 50,
+			// scrape highest resolution
+			"extras" => "url_s,url_n,url_w,url_m,url_z,url_c,url_l,url_h,url_k,url_3k,url_4k,url_5k,url_6k,url_o",
+			"view_all" => 1
+		];
+		
+		$get_params = array_merge($get_params, $filters);
+		
+		$html =
+			$this->get(
+				$proxy,
+				"https://www.flickr.com/search/",
+				$get_params,
+				flickr::req_web
+			);
+		
+		// @TODO
+		// get api_key and reqId, if flickr deprecates &page
+		
+		$this->fuckhtml->load($html);
+		
+		//
+		// get response JSON
+		//
+		$scripts =
+			$this->fuckhtml
+			->getElementsByClassName(
+				"modelExport",
+				"script"
+			);
+		
+		$found = false;
+		foreach($scripts as $script){
+			
+			$json =	
+				preg_split(
+					'/modelExport: ?/',
+					$script["innerHTML"],
+					2
+				);
+			
+			if(count($json) !== 0){
+				
+				$found = true;
+				$json = $json[1];
+				break;
+			}
+		}
+		
+		if($found === false){
+			
+			throw new Exception("Failed to grep JSON");
+		}
+		
+		$json =
+			json_decode(
+				$this->fuckhtml
+				->extract_json(
+					$json
+				),
+				true
+			);
+		
+		if($json === null){
+			
+			throw new Exception("Failed to decode JSON");
+		}
+		
+		$out = [
+			"status" => "ok",
+			"npt" => null,
+			"image" => []
+		];
+		
+		if(!isset($json["main"]["search-photos-lite-models"][0]["data"]["photos"]["data"]["_data"])){
+			
+			throw new Exception("Failed to access data object");
+		}
+		
+		foreach($json["main"]["search-photos-lite-models"][0]["data"]["photos"]["data"]["_data"] as $image){
+			
+			if(!isset($image["data"])){
+				
+				// flickr likes to gives us empty array objects
+				continue;
+			}
+			
+			$image = $image["data"];
+			
+			$title = [];
+			
+			if(isset($image["title"])){
+				
+				$title[] =
+					$this->fuckhtml
+					->getTextContent(
+						$image["title"]
+					);
+			}
+			
+			if(isset($image["description"])){
+				
+				$title[] =
+					$this->fuckhtml
+					->getTextContent(
+						str_replace(
+							"\n",
+							" ",
+							$image["description"]
+						)
+					);
+			}
+			
+			$title = implode(": ", $title);
+			
+			$sources = array_values($image["sizes"]["data"]);
+			
+			$suitable_sizes = ["n", "m", "w", "s"];
+			
+			$thumb = &$sources[0]["data"];
+			foreach($suitable_sizes as $testing_size){
+				
+				if(isset($image["sizes"]["data"][$testing_size])){
+					
+					$thumb = &$image["sizes"]["data"][$testing_size]["data"];
+					break;
+				}
+			}
+			
+			$og = &$sources[count($sources) - 1]["data"];
+			
+			$out["image"][] = [
+				"title" => $title,
+				"source" => [
+					[
+						"url" => "https:" . $og["displayUrl"],
+						"width" => (int)$og["width"],
+						"height" => (int)$og["height"]
+					],
+					[
+						"url" => "https:" . $thumb["displayUrl"],
+						"width" => (int)$thumb["width"],
+						"height" => (int)$thumb["height"]
+					]
+				],
+				"url" => "https://www.flickr.com/photos/" . $image["ownerNsid"] . "/" . $image["id"] . "/"
+			];
+		}
+		
+		$total_items = (int)$json["main"]["search-photos-lite-models"][0]["data"]["photos"]["data"]["totalItems"];
+		
+		if(($filters["page"]) * 50 < $total_items){
+			
+			$filters["page"]++;
+			
+			$out["npt"] =
+				$this->backend->store(
+					json_encode($filters),
+					"images",
+					$proxy
+				);
+		}
+		
+		return $out;
+	}
+}

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/imgur.php

@@ -182,6 +182,23 @@ class imgur{
 			throw new Exception("Failed to fetch HTML");
 		}
 		
+		$json = json_decode($html, true);
+		
+		if($json){
+			
+			// {"data":{"error":"Imgur is temporarily over capacity. Please try again later."},"success":false,"status":403}
+			
+			if(isset($json["data"]["error"])){
+				
+				if(stripos($json["data"]["error"], "capacity")){
+					
+					throw new Exception("Imgur IP blocked this 4get instance or request proxy. Try again");
+				}
+			}
+			
+			throw new Exception("Imgur returned an unknown error (IP ban?)");
+		}
+		
 		$this->fuckhtml->load($html);
 		
 		$posts =
@@ -197,7 +214,14 @@ class imgur{
 			
 			$image =
 				$this->fuckhtml
-				->getElementsByTagName("img")[0];
+				->getElementsByTagName("img");
+			
+			if(count($image) === 0){
+				
+				continue;
+			}
+			
+			$image = $image[0];
 			
 			$image_url = "https:" . substr($this->fuckhtml->getTextContent($image["attributes"]["src"]), 0, -5);
 			

scraper/marginalia.php

@@ -3,7 +3,10 @@
 class marginalia{
 	public function __construct(){
 		
-		include "lib/fuckhtml.php";
+		include "lib/anubis.php";
+		$this->anubis = new anubis();
+		
+		include_once "lib/fuckhtml.php";
 		$this->fuckhtml = new fuckhtml();
 		
 		include "lib/backend.php";
@@ -102,7 +105,40 @@ class marginalia{
 		);
 	}
 	
-	private function get($proxy, $url, $get = []){
+	private function get($proxy, $url, $get = [], $get_cookies = 1){
+		
+		$curlproc = curl_init();
+		
+		switch($get_cookies){
+			
+			case 0:
+				$cookies = "";
+				$cookies_tmp = [];
+				curl_setopt($curlproc, CURLOPT_HEADERFUNCTION, function($curlproc, $header) use (&$cookies_tmp){
+					
+					$length = strlen($header);
+					
+					$header = explode(":", $header, 2);
+					
+					if(trim(strtolower($header[0])) == "set-cookie"){
+						
+						$cookie_tmp = explode("=", trim($header[1]), 2);
+						
+						$cookies_tmp[trim($cookie_tmp[0])] =
+							explode(";", $cookie_tmp[1], 2)[0];
+					}
+					
+					return $length;
+				});
+				break;
+			
+			case 1:
+				$cookies = "";
+				break;
+			
+			default:
+				$cookies = "Cookie: " . $get_cookies;
+		}
 		
 		$headers = [
 			"User-Agent: " . config::USER_AGENT,
@@ -110,6 +146,7 @@ class marginalia{
 			"Accept-Language: en-US,en;q=0.5",
 			"Accept-Encoding: gzip",
 			"DNT: 1",
+			$cookies,
 			"Connection: keep-alive",
 			"Upgrade-Insecure-Requests: 1",
 			"Sec-Fetch-Dest: document",
@@ -118,8 +155,6 @@ class marginalia{
 			"Sec-Fetch-User: ?1"
 		];
 		
-		$curlproc = curl_init();
-		
 		if($get !== []){
 			$get = http_build_query($get);
 			$url .= "?" . $get;
@@ -145,7 +180,19 @@ class marginalia{
 			throw new Exception(curl_error($curlproc));
 		}
 		
-		curl_close($curlproc);
+		if($get_cookies === 0){
+			
+			$cookie = [];
+			
+			foreach($cookies_tmp as $key => $value){
+				
+				$cookie[] = $key . "=" . $value;
+			}
+			
+			curl_close($curlproc);
+			return implode(";", $cookie);
+		}
+		
 		return $data;
 	}
 	
@@ -220,13 +267,14 @@ class marginalia{
 			"related" => []
 		];
 		
+		// API scraper
 		if(config::MARGINALIA_API_KEY !== null){
 			
 			try{
 				$json =
 					$this->get(
 						$this->backend->get_ip(), // no nextpage
-						"https://api.marginalia.nu/" . config::MARGINALIA_API_KEY . "/search/" . urlencode($search),
+						"https://api.marginalia-search.com/" . config::MARGINALIA_API_KEY . "/search/" . urlencode($search),
 						[
 							"count" => 20
 						]
@@ -263,34 +311,114 @@ 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 $v){
+		//
+		// Bypass anubis check
+		//
+		/*
+		if(($anubis_key = apcu_fetch("marginalia_cookie")) === false){
 			
-			if($get[$v] == "yes"){
-				
-				switch($v){
+			try{
+				$html =
+					$this->get(
+						$proxy,
+						"https://old-search.marginalia.nu/search",
+						[
+							"query" => $search
+						]
+					);
 					
-					case "adtech": $params["adtech"] = "reduce"; break;
-					case "recent": $params["recent"] = "recent"; break;
-					case "adtech": $params["searchTitle"] = "title"; break;
+			}catch(Exception $error){
+				
+				throw new Exception("Failed to get anubis challenge");
+			}
+			
+			try{
+				
+				$anubis_data = $this->anubis->scrape($html);
+			}catch(Exception $error){
+				
+				throw new Exception($error);
+			}
+			
+			// send anubis response & get cookies
+			// https://old-search.marginalia.nu/.within.website/x/cmd/anubis/api/pass-challenge?response=0000018966b086834f738bacba6031028adb5aa875974ead197a8b75778baf3a&nonce=39947&redir=https%3A%2F%2Fold-search.marginalia.nu%2F&elapsedTime=1164
+			
+			try{
+				
+				$anubis_key =
+					$this->get(
+						$proxy,
+						"https://old-search.marginalia.nu/.within.website/x/cmd/anubis/api/pass-challenge",
+						[
+							"response" => $anubis_data["response"],
+							"nonce" => $anubis_data["nonce"],
+							"redir" => "https://old-search.marginalia.nu/",
+							"elapsedTime" => random_int(1000, 2000)
+						],
+						0
+					);
+			}catch(Exception $error){
+				
+				throw new Exception("Failed to submit anubis challenge");
+			}
+			
+			apcu_store("marginalia_cookie", $anubis_key);
+		}*/
+		
+		if($get["npt"]){
+			
+			[$params, $proxy] =
+				$this->backend->get(
+					$get["npt"],
+					"web"
+				);
+			
+			try{
+				$html =
+					$this->get(
+						$proxy,
+						"https://old-search.marginalia.nu/search?" . $params,
+						[],
+						//$anubis_key
+					);
+			}catch(Exception $error){
+				
+				throw new Exception("Failed to get HTML");
+			}
+			
+		}else{
+			$params = [
+				"query" => $search
+			];
+			
+			foreach(["adtech", "recent", "intitle"] as $v){
+				
+				if($get[$v] == "yes"){
+					
+					switch($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://old-search.marginalia.nu/search",
+						$params,
+						//$anubis_key
+					);
+			}catch(Exception $error){
+				
+				throw new Exception("Failed to get HTML");
+			}
 		}
 		
 		$this->fuckhtml->load($html);
@@ -387,6 +515,65 @@ 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]
+							)
 						);
 				}
 			}

scraper/pinterest.php

@@ -13,31 +13,104 @@ class pinterest{
 		return [];
 	}
 	
-	private function get($proxy, $url, $get = []){
+	private function get($proxy, $url, $get = [], &$cookies, $header_data_post = null){
 		
 		$curlproc = curl_init();
 		
-		if($get !== []){
+		if($header_data_post === null){
+			
+			// handling GET
+						
+			// extract cookies
+			$cookies_tmp = [];
+			curl_setopt($curlproc, CURLOPT_HEADERFUNCTION, function($curlproc, $header) use (&$cookies_tmp){
+				
+				$length = strlen($header);
+				
+				$header = explode(":", $header, 2);
+				
+				if(trim(strtolower($header[0])) == "set-cookie"){
+					
+					$cookie_tmp = explode("=", trim($header[1]), 2);
+					
+					$cookies_tmp[trim($cookie_tmp[0])] =
+						explode(";", $cookie_tmp[1], 2)[0];
+				}
+				
+				return $length;
+			});
+			
+			curl_setopt($curlproc, CURLOPT_HTTPHEADER,
+				["User-Agent: " . config::USER_AGENT,
+				"Accept: application/json, text/javascript, */*, q=0.01",
+				"Accept-Language: en-US,en;q=0.5",
+				"Accept-Encoding: gzip",
+				"Referer: https://ca.pinterest.com/",
+				"X-Requested-With: XMLHttpRequest",
+				"X-APP-VERSION: 78f8764",
+				"X-Pinterest-AppState: active",
+				"X-Pinterest-Source-Url: /",
+				"X-Pinterest-PWS-Handler: www/index.js",
+				"screen-dpr: 1",
+				"is-preload-enabled: 1",
+				"DNT: 1",
+				"Sec-GPC: 1",
+				"Sec-Fetch-Dest: empty",
+				"Sec-Fetch-Mode: cors",
+				"Sec-Fetch-Site: same-origin",
+				"Connection: keep-alive",
+				"Alt-Used: ca.pinterest.com",
+				"Priority: u=0",
+				"TE: trailers"]
+			);
+			
+			if($get !== []){
+				$get = http_build_query($get);
+				$url .= "?" . $get;
+			}
+		}else{
+			
+			// handling POST (pagination)
 			$get = http_build_query($get);
-			$url .= "?" . $get;
+			
+			curl_setopt($curlproc, CURLOPT_HTTPHEADER,
+				["User-Agent: " . config::USER_AGENT,
+				"Accept: application/json, text/javascript, */*, q=0.01",
+				"Accept-Language: en-US,en;q=0.5",
+				"Accept-Encoding: gzip",
+				"Content-Type: application/x-www-form-urlencoded",
+				"Content-Length: " . strlen($get),
+				"Referer: https://ca.pinterest.com/",
+				"X-Requested-With: XMLHttpRequest",
+				"X-APP-VERSION: 78f8764",
+				"X-CSRFToken: " . $cookies["csrf"],
+				"X-Pinterest-AppState: active",
+				"X-Pinterest-Source-Url: /search/pins/?rs=ac&len=2&q=" . urlencode($header_data_post) . "&eq=" . urlencode($header_data_post),
+				"X-Pinterest-PWS-Handler: www/search/[scope].js",
+				"screen-dpr: 1",
+				"is-preload-enabled: 1",
+				"Origin: https://ca.pinterest.com",
+				"DNT: 1",
+				"Sec-GPC: 1",
+				"Sec-Fetch-Dest: empty",
+				"Sec-Fetch-Mode: cors",
+				"Sec-Fetch-Site: same-origin",
+				"Connection: keep-alive",
+				"Alt-Used: ca.pinterest.com",
+				"Cookie: " . $cookies["cookie"],
+				"TE: trailers"]
+			);
+			
+			curl_setopt($curlproc, CURLOPT_POST, true);
+			curl_setopt($curlproc, CURLOPT_POSTFIELDS, $get);
 		}
 		
 		curl_setopt($curlproc, CURLOPT_URL, $url);
 		
 		curl_setopt($curlproc, CURLOPT_ENCODING, ""); // default encoding
-		curl_setopt($curlproc, CURLOPT_HTTPHEADER,
-			["User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:107.0) Gecko/20100101 Firefox/110.0",
-			"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: none",
-			"Sec-Fetch-User: ?1"]
-		);
+		
+		// http2 bypass
+		curl_setopt($curlproc, CURLOPT_HTTP_VERSION, CURL_HTTP_VERSION_2_0);
 		
 		curl_setopt($curlproc, CURLOPT_RETURNTRANSFER, true);
 		curl_setopt($curlproc, CURLOPT_SSL_VERIFYHOST, 2);
@@ -54,6 +127,26 @@ class pinterest{
 			throw new Exception(curl_error($curlproc));
 		}
 		
+		if($header_data_post === null){
+			
+			if(!isset($cookies_tmp["csrftoken"])){
+				
+				throw new Exception("Failed to grep CSRF token");
+			}
+			
+			$cookies = "";
+			
+			foreach($cookies_tmp as $cookie_name => $cookie_value){
+				
+				$cookies .= $cookie_name . "=" . $cookie_value . "; ";
+			}
+			
+			$cookies = [
+				"csrf" => $cookies_tmp["csrftoken"],
+				"cookie" => rtrim($cookies, " ;")
+			];
+		}
+		
 		curl_close($curlproc);
 		return $data;
 	}
@@ -62,17 +155,68 @@ class pinterest{
 		
 		if($get["npt"]){
 			
-			// @TODO
-			// post data for next page
-			$data = [
-				"source_url" => "/search/pins/?q=" . urlencode($search) . "&rs=typed",
-				"data" =>
-					json_encode(
+			[$data, $proxy] =
+				$this->backend->get(
+					$get["npt"], "images"
+				);
+			
+			$data = json_decode($data, true);
+			
+			$search = $data["q"];
+			$cookies = $data["cookies"];
+			
+			try{
+				$json =
+					$this->get(
+						$proxy,
+						"https://ca.pinterest.com/resource/BaseSearchResource/get/",
 						[
-							// {"options":{"applied_filters":null,"appliedProductFilters":"---","article":null,"auto_correction_disabled":false,"corpus":null,"customized_rerank_type":null,"domains":null,"filters":null,"journey_depth":null,"page_size":null,"price_max":null,"price_min":null,"query_pin_sigs":null,"query":"higurashi","redux_normalize_feed":true,"rs":"typed","scope":"pins","selected_one_bar_modules":null,"source_id":null,"source_module_id":null,"top_pin_id":null,"bookmarks":["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"]},"context":{}}
-						]
+							"source_url" => "/search/pins/?q=" . urlencode($search) . "&rs=typed",
+							"data" => json_encode(
+								[
+									"options" => [
+										"applied_unified_filters" => null,
+										"appliedProductFilters" => "---",
+										"article" => null,
+										"auto_correction_disabled" => false,
+										"corpus" => null,
+										"customized_rerank_type" => null,
+										"domains" => null,
+										"dynamicPageSizeExpGroup" => null,
+										"filters" => null,
+										"journey_depth" => null,
+										"page_size" => null,
+										"price_max" => null,
+										"price_min" => null,
+										"query_pin_sigs" => null,
+										"query" => $data["q"],
+										"redux_normalize_feed" => true,
+										"request_params" => null,
+										"rs" => "typed",
+										"scope" => "pins",
+										"selected_one_bar_modules" => null,
+										"source_id" => null,
+										"source_module_id" => null,
+										"source_url" => "/search/pins/?q=" . urlencode($search) . "&rs=typed",
+										"top_pin_id" => null,
+										"top_pin_ids" => null,
+										"bookmarks" => [
+											$data["bookmark"]
+										]
+									],
+									"context" => []
+								],
+								JSON_UNESCAPED_SLASHES
+							)
+						],
+						$cookies,
+						$search
 					);
-			];
+				
+			}catch(Exception $error){
+				
+				throw new Exception("Failed to fetch JSON");
+			}
 			
 		}else{
 			
@@ -81,27 +225,45 @@ class pinterest{
 				
 				throw new Exception("Search term is empty!");
 			}
+						
+			// https://ca.pinterest.com/resource/BaseSearchResource/get/?source_url=%2Fsearch%2Fpins%2F%3Feq%3Dhigurashi%26etslf%3D5966%26len%3D2%26q%3Dhigurashi%2520when%2520they%2520cry%26rs%3Dac&data=%7B%22options%22%3A%7B%22applied_unified_filters%22%3Anull%2C%22appliedProductFilters%22%3A%22---%22%2C%22article%22%3Anull%2C%22auto_correction_disabled%22%3Afalse%2C%22corpus%22%3Anull%2C%22customized_rerank_type%22%3Anull%2C%22domains%22%3Anull%2C%22dynamicPageSizeExpGroup%22%3Anull%2C%22filters%22%3Anull%2C%22journey_depth%22%3Anull%2C%22page_size%22%3Anull%2C%22price_max%22%3Anull%2C%22price_min%22%3Anull%2C%22query_pin_sigs%22%3Anull%2C%22query%22%3A%22higurashi%20when%20they%20cry%22%2C%22redux_normalize_feed%22%3Atrue%2C%22request_params%22%3Anull%2C%22rs%22%3A%22ac%22%2C%22scope%22%3A%22pins%22%2C%22selected_one_bar_modules%22%3Anull%2C%22source_id%22%3Anull%2C%22source_module_id%22%3Anull%2C%22source_url%22%3A%22%2Fsearch%2Fpins%2F%3Feq%3Dhigurashi%26etslf%3D5966%26len%3D2%26q%3Dhigurashi%2520when%2520they%2520cry%26rs%3Dac%22%2C%22top_pin_id%22%3Anull%2C%22top_pin_ids%22%3Anull%7D%2C%22context%22%3A%7B%7D%7D&_=1736116313987
+			// source_url=%2Fsearch%2Fpins%2F%3Feq%3Dhigurashi%26etslf%3D5966%26len%3D2%26q%3Dhigurashi%2520when%2520they%2520cry%26rs%3Dac
+			// &data=%7B%22options%22%3A%7B%22applied_unified_filters%22%3Anull%2C%22appliedProductFilters%22%3A%22---%22%2C%22article%22%3Anull%2C%22auto_correction_disabled%22%3Afalse%2C%22corpus%22%3Anull%2C%22customized_rerank_type%22%3Anull%2C%22domains%22%3Anull%2C%22dynamicPageSizeExpGroup%22%3Anull%2C%22filters%22%3Anull%2C%22journey_depth%22%3Anull%2C%22page_size%22%3Anull%2C%22price_max%22%3Anull%2C%22price_min%22%3Anull%2C%22query_pin_sigs%22%3Anull%2C%22query%22%3A%22higurashi%20when%20they%20cry%22%2C%22redux_normalize_feed%22%3Atrue%2C%22request_params%22%3Anull%2C%22rs%22%3A%22ac%22%2C%22scope%22%3A%22pins%22%2C%22selected_one_bar_modules%22%3Anull%2C%22source_id%22%3Anull%2C%22source_module_id%22%3Anull%2C%22source_url%22%3A%22%2Fsearch%2Fpins%2F%3Feq%3Dhigurashi%26etslf%3D5966%26len%3D2%26q%3Dhigurashi%2520when%2520they%2520cry%26rs%3Dac%22%2C%22top_pin_id%22%3Anull%2C%22top_pin_ids%22%3Anull%7D%2C%22context%22%3A%7B%7D%7D
+			// &_=1736116313987
+			
+			$source_url = "/search/pins/?q=" . urlencode($search) . "&rs=" . urlencode($search);
 			
 			$filter = [
-				"source_url" => "/search/pins/?q=" . urlencode($search),
+				"source_url" => $source_url,
 				"rs" => "typed",
 				"data" =>
 					json_encode(
 						[
 							"options" => [
-								"article" => null,
-								"applied_filters" => null,
+								"applied_unified_filters" => null,
 								"appliedProductFilters" => "---",
-								"auto_correction_disabled" => false,
+								"article" => null,
 								"corpus" => null,
 								"customized_rerank_type" => null,
+								"domains" => null,
+								"dynamicPageSizeExpGroup" => null,
 								"filters" => null,
-								"query" => $search,
+								"journey_depth" => null,
+								"page_size" => null,
+								"price_max" => null,
+								"price_min" => null,
 								"query_pin_sigs" => null,
+								"query" => $search,
 								"redux_normalize_feed" => true,
-								"rs" => "typed",
+								"request_params" => null,
+								"rs" => "ac",
 								"scope" => "pins", // pins, boards, videos, 
-								"source_id" => null
+								"selected_one_bar_modules" => null,
+								"source_id" => null,
+								"source_module_id" => null,
+								"source_url" => $source_url,
+								"top_pin_id" => null,
+								"top_pin_ids" => null
 							],
 							"context" => []
 						]
@@ -110,24 +272,26 @@ class pinterest{
 			];
 			
 			$proxy = $this->backend->get_ip();
-		}
-		
-		try{
-			$json =
-				json_decode(
+			$cookies = [];
+			
+			try{
+				$json =
 					$this->get(
 						$proxy,
-						"https://www.pinterest.ca/resource/BaseSearchResource/get/",
-						$filter
-					),
-					true
-				);
-			
-		}catch(Exception $error){
-			
-			throw new Exception("Failed to fetch JSON");
+						"https://ca.pinterest.com/resource/BaseSearchResource/get/",
+						$filter,
+						$cookies,
+						null
+					);
+				
+			}catch(Exception $error){
+				
+				throw new Exception("Failed to fetch JSON");
+			}
 		}
 		
+		$json = json_decode($json, true);
+		
 		if($json === null){
 			
 			throw new Exception("Failed to decode JSON");
@@ -139,6 +303,60 @@ class pinterest{
 			"image" => []
 		];
 		
+		if(
+			!isset(
+				$json["resource_response"]
+				["status"]
+			)
+		){
+			
+			throw new Exception("Unknown API failure");
+		}
+		
+		if($json["resource_response"]["status"] != "success"){
+			
+			$status = "Got non-OK response: " . $json["resource_response"]["status"];
+			
+			if(
+				isset(
+					$json["resource_response"]["message"]
+				)
+			){
+				
+				$status .= " - " . $json["resource_response"]["message"];
+			}
+			
+			throw new Exception($status);
+		}
+		
+		if(
+			isset(
+				$json["resource_response"]["sensitivity"]
+				["notices"][0]["description"]["text"]
+			)
+		){
+			
+			throw new Exception(
+				"Pinterest returned a notice: " .
+				$json["resource_response"]["sensitivity"]["notices"][0]["description"]["text"]
+			);
+		}
+		
+		// get NPT
+		if(isset($json["resource_response"]["bookmark"])){
+			
+			$out["npt"] =
+				$this->backend->store(
+					json_encode([
+						"q" => $search,
+						"bookmark" => $json["resource_response"]["bookmark"],
+						"cookies" => $cookies
+					]),
+					"images",
+					$proxy
+				);
+		}
+		
 		foreach(
 			$json
 			["resource_response"]
@@ -150,6 +368,7 @@ class pinterest{
 			switch($item["type"]){
 				
 				case "pin":
+				case "board":
 					
 					/*
 						Handle image object
@@ -206,42 +425,15 @@ class pinterest{
 								"height" => (int)$thumb["height"]
 							]
 						],
-						"url" => "https://www.pinterest.com/pin/" . $item["id"]
+						"url" =>
+							$item["link"] === null ?
+							"https://ca.pinterest.com/pin/" . $item["id"] :
+							$item["link"]
 					];
 					break;
-				
-				case "board":
-					if(isset($item["cover_pin"]["image_url"])){
-						
-						$image = [
-							"url" => $item["cover_pin"]["image_url"],
-							"width" => (int)$item["cover_pin"]["size"][0],
-							"height" => (int)$item["cover_pin"]["size"][1]
-						];
-					}elseif(isset($item["image_cover_url_hd"])){
-						/*
-						$image = [
-							"url" => 
-							"width" => null,
-							"height" => null
-						];*/
-					}
-					break;
 			}
 		}
 		
 		return $out;
 	}
-	
-	private function getfullresimage($image, $has_og){
-		
-		$has_og = $has_og ? "1200x" : "originals";
-		
-		return
-			preg_replace(
-				'/https:\/\/i\.pinimg\.com\/[^\/]+\//',
-				"https://i.pinimg.com/" . $has_og . "/",
-				$image
-			);
-	}
 }

scraper/qwant.php

@@ -410,10 +410,7 @@ class qwant{
 					"thumb" =>
 						$answer["data"]["result"]["thumbnail"]["landscape"] == null ?
 						null :
-						$this->unshitimage(
-							$answer["data"]["result"]["thumbnail"]["landscape"],
-							false
-						),
+						$this->unshitimage($answer["data"]["result"]["thumbnail"]["landscape"]),
 					"table" => [],
 					"sublink" => []
 				];
@@ -770,7 +767,7 @@ class qwant{
 			}else{
 				
 				$thumb = [
-					"url" => $this->unshitimage($video["thumbnail"], false),
+					"url" => $this->unshitimage($video["thumbnail"]),
 					"ratio" => "16:9"
 				];
 			}
@@ -870,7 +867,7 @@ class qwant{
 			}else{
 				
 				$thumb = [
-					"url" => $this->unshitimage($news["media"][0]["pict_big"]["url"], false),
+					"url" => $this->unshitimage($news["media"][0]["pict_big"]["url"]),
 					"ratio" => "16:9"
 				];
 			}
@@ -920,18 +917,77 @@ class qwant{
 		return trim($text, ". ");
 	}
 	
-	private function unshitimage($url, $is_bing = true){
+	private function unshitimage($url){
 		
 		// https://s1.qwant.com/thumbr/0x0/8/d/f6de4deb2c2b12f55d8bdcaae576f9f62fd58a05ec0feeac117b354d1bf5c2/th.jpg?u=https%3A%2F%2Fwww.bing.com%2Fth%3Fid%3DOIP.vvDWsagzxjoKKP_rOqhwrQAAAA%26w%3D160%26h%3D160%26c%3D7%26pid%3D5.1&q=0&b=1&p=0&a=0
-		parse_str(parse_url($url)["query"], $parts);
+		// https://s2.qwant.com/thumbr/474x289/7/f/412d13b3fe3a03eb2b89633c8e88b609b7d0b93cdd9a5e52db3c663e41e65e/th.jpg?u=https%3A%2F%2Ftse.mm.bing.net%2Fth%3Fid%3DOIP.9Tm_Eo6m7V7ltN19mxduDgHaEh%26pid%3DApi&q=0&b=1&p=0&a=0
 		
-		if($is_bing){
-			$parse = parse_url($parts["u"]);
-			parse_str($parse["query"], $parts);
+		$image = parse_url($url);
+		
+		if(
+			!isset($image["host"]) ||
+			!isset($image["query"])
+		){
 			
-			return "https://" . $parse["host"] . "/th?id=" . urlencode($parts["id"]);
+			// cant do anything
+			return $url;
 		}
 		
-		return $parts["u"];
+		$id = null;
+		
+		if(
+			preg_match(
+				'/s[0-9]+\.qwant\.com$/',
+				$image["host"]
+			)
+		){
+			
+			parse_str($image["query"], $str);
+			
+			// we're being served a proxy URL
+			if(isset($str["u"])){
+				
+				$bing_url = $str["u"];
+			}else{
+				
+				// give up
+				return $url;
+			}
+		}
+		
+		// parse bing URL
+		$id = null;
+		$image = parse_url($bing_url);
+		
+		if(isset($image["query"])){
+			
+			parse_str($image["query"], $str);
+			
+			if(isset($str["id"])){
+				
+				$id = $str["id"];
+			}
+		}
+		
+		if($id === null){
+			
+			$id = explode("/th/id/", $image["path"], 2);
+			
+			if(count($id) !== 2){
+				
+				// malformed
+				return $url;
+			}
+			
+			$id = $id[1];
+		}
+		
+		if(is_array($id)){
+			
+			// fuck off, let proxy.php deal with it
+			return $url;
+		}
+		
+		return "https://" . $image["host"] . "/th?id=" . rawurlencode($id);
 	}
 }

scraper/sepiasearch.php

@@ -0,0 +1,541 @@
+<?php
+
+class sepiasearch{
+	
+	public function __construct(){
+		
+		include "lib/backend.php";
+		$this->backend = new backend("sepiasearch");
+	}
+	
+	public function getfilters($page){
+		
+		return [
+			"nsfw" => [
+				"display" => "NSFW",
+				"option" => [
+					"yes" => "Yes", // &sensitiveContent=both
+					"no" => "No" // &sensitiveContent=false
+				]
+			],
+			"language" => [
+				"display" => "Language", // &language=
+				"option" => [
+					"any" => "Any language",
+					"en" => "English",
+					"fr" => "Français",
+					"ar" => "العربية",
+					"ca" => "Català",
+					"cs" => "Čeština",
+					"de" => "Deutsch",
+					"el" => "ελληνικά",
+					"eo" => "Esperanto",
+					"es" => "Español",
+					"eu" => "Euskara",
+					"fa" => "فارسی",
+					"fi" => "Suomi",
+					"gd" => "Gàidhlig",
+					"gl" => "Galego",
+					"hr" => "Hrvatski",
+					"hu" => "Magyar",
+					"is" => "Íslenska",
+					"it" => "Italiano",
+					"ja" => "日本語",
+					"kab" => "Taqbaylit",
+					"nl" => "Nederlands",
+					"no" => "Norsk",
+					"oc" => "Occitan",
+					"pl" => "Polski",
+					"pt" => "Português (Brasil)",
+					"pt-PT" => "Português (Portugal)",
+					"ru" => "Pусский",
+					"sk" => "Slovenčina",
+					"sq" => "Shqip",
+					"sv" => "Svenska",
+					"th" => "ไทย",
+					"tok" => "Toki Pona",
+					"tr" => "Türkçe",
+					"uk" => "украї́нська мо́ва",
+					"vi" => "Tiếng Việt",
+					"zh-Hans" => "简体中文（中国）",
+					"zh-Hant" => "繁體中文（台灣）"
+				]
+			],
+			"type" => [
+				"display" => "Result type", // i handle this
+				"option" => [
+					"videos" => "Videos",
+					"playlists" => "Playlists",
+					"channels" => "Channels"
+				]
+			],
+			"sort" => [
+				"display" => "Sort by",
+				"option" => [
+					"best" => "Best match", // no filter
+					"-publishedAt" => "Newest", // sort=-publishedAt
+					"publishedAt" => "Oldest" // sort=publishedAt
+				]
+			],
+			"newer" => [ // &startDate=2025-07-26T04:00:00.000Z
+				"display" => "Newer than",
+				"option" => "_DATE"
+			],
+			"duration" => [
+				"display" => "Duration",
+				"option" => [
+					"any" => "Any duration",
+					"short" => "Short (0-4mins)", // &durationRange=short
+					"medium" => "Medium (4-10 mins)",
+					"long" => "Long (10+ mins)",
+				]
+			],
+			"category" => [
+				"display" => "Category", // &categoryOneOf[]=
+				"option" => [
+					"any" => "Any category",
+					"1" => "Music",
+					"2" => "Films",
+					"3" => "Vehicles",
+					"4" => "Art",
+					"5" => "Sports",
+					"6" => "Travels",
+					"7" => "Gaming",
+					"8" => "People",
+					"9" => "Comedy",
+					"10" => "Entertainment",
+					"11" => "News & Politics",
+					"12" => "How To",
+					"13" => "Education",
+					"14" => "Activism",
+					"15" => "Science & Technology",
+					"16" => "Animals",
+					"17" => "Kids",
+					"18" => "Food"
+				]
+			],
+			"display" => [
+				"display" => "Display",
+				"option" => [
+					"any" => "Everything",
+					"true" => "Live videos", // &isLive=true
+					"false" => "VODs" // &isLive=false
+				]
+			],
+			"license" => [
+				"display" => "License", // &license=
+				"option" => [
+					"any" => "Any license",
+					"1" => "Attribution",
+					"2" => "Attribution - Share Alike",
+					"3" => "Attribution - No Derivatives",
+					"4" => "Attribution - Non Commercial",
+					"5" => "Attribution - Non Commercial - Share Alike",
+					"6" => "Attribution - Non Commercial - No Derivatives",
+					"7" => "Public Domain Dedication"
+				]
+			]
+		];
+	}
+	
+	private function get($proxy, $url, $get = []){
+		
+		$curlproc = curl_init();
+		
+		if($get !== []){
+			$get = http_build_query($get);
+			$url .= "?" . $get;
+		}
+		
+		curl_setopt($curlproc, CURLOPT_URL, $url);
+		curl_setopt($curlproc, CURLOPT_ENCODING, ""); // default encoding
+		
+		curl_setopt(
+			$curlproc,
+			CURLOPT_HTTPHEADER,
+			["User-Agent: " . config::USER_AGENT,
+			"Accept: application/json, text/plain, */*",
+			"Accept-Language: en-US,en;q=0.5",
+			"Accept-Encoding: gzip, deflate, br, zstd",
+			"DNT: 1",
+			"Sec-GPC: 1",
+			"Connection: keep-alive",
+			"Referer: https://sepiasearch.org/search",
+			"Sec-Fetch-Dest: empty",
+			"Sec-Fetch-Mode: cors",
+			"Sec-Fetch-Site: same-origin",
+			"Priority: u=0",
+			"TE: trailers"]
+		);
+		
+		curl_setopt($curlproc, CURLOPT_RETURNTRANSFER, true);
+		curl_setopt($curlproc, CURLOPT_SSL_VERIFYHOST, 2);
+		curl_setopt($curlproc, CURLOPT_SSL_VERIFYPEER, true);
+		curl_setopt($curlproc, CURLOPT_CONNECTTIMEOUT, 30);
+		curl_setopt($curlproc, CURLOPT_TIMEOUT, 30);
+
+		$this->backend->assign_proxy($curlproc, $proxy);
+		
+		$data = curl_exec($curlproc);
+		
+		if(curl_errno($curlproc)){
+			
+			throw new Exception(curl_error($curlproc));
+		}
+		
+		curl_close($curlproc);
+		return $data;
+	}
+	
+	public function video($get){
+		
+		if($get["npt"]){
+			
+			[$npt, $proxy] =
+				$this->backend
+				->get(
+					$get["npt"],
+					"videos"
+				);
+			
+			$npt = json_decode($npt, true);
+			$type = $npt["type"];
+			$npt = $npt["npt"];
+		}else{
+			
+			$proxy = $this->backend->get_ip();
+						
+			$npt = [
+				"search" => $get["s"],
+				"start" => 0,
+				"count" => 20
+			];
+			
+			if($get["type"] == "videos"){
+				
+				//
+				// Parse video filters
+				//
+				switch($get["nsfw"]){
+					
+					case "yes": $npt["nsfw"] = "both"; break;
+					case "no": $npt["nsfw"] = "false"; break;
+				}
+				
+				$npt["boostLanguages[]"] = "en";
+				if($get["language"] != "any"){
+					
+					$npt["languageOneOf[]"] = $get["language"];
+				}
+				
+				if($get["sort"] != "best"){
+					
+					$npt["sort"] = $get["sort"];
+				}
+				
+				if($get["newer"] !== false){
+					
+					$date = new DateTime("@{$get["newer"]}");
+					$date->setTimezone(new DateTimeZone("UTC"));
+					$formatted = $date->format("Y-m-d\TH:i:s.000\Z");
+					
+					$npt["startDate"] = $formatted;
+				}
+				
+				switch($get["duration"]){
+					
+					case "short":
+						$npt["durationMax"] = 240;
+						break;
+					
+					case "medium":
+						$npt["durationMin"] = 240;
+						$npt["durationMax"] = 600;
+						break;
+					
+					case "long":
+						$npt["durationMin"] = 600;
+						break;
+				}
+				
+				if($get["category"] != "any"){
+					
+					$npt["categoryOneOf[]"] = $get["category"];
+				}
+				
+				if($get["display"] != "any"){
+					
+					$npt["isLive"] = $get["display"];
+				}
+				
+				if($get["license"] != "any"){
+					
+					// typo in license, lol
+					$npt["licenceOneOf[]"] = $get["license"];
+				}
+			}
+			
+			$type = $get["type"];
+		}
+		
+		switch($type){
+			
+			case "videos":
+				$url = "https://sepiasearch.org/api/v1/search/videos";
+				break;
+			
+			case "channels":
+				$url = "https://sepiasearch.org/api/v1/search/video-channels";
+				break;
+			
+			case "playlists":
+				$url = "https://sepiasearch.org/api/v1/search/video-playlists";
+				break;
+		}
+		
+		//$json = file_get_contents("scraper/sepia.json");
+		try{
+			
+			$json =
+				$this->get(
+					$proxy,
+					$url,
+					$npt
+				);
+		}catch(Exception $error){
+			
+			throw new Exception("Failed to fetch JSON");
+		}
+		
+		$json = json_decode($json, true);
+		
+		if($json === null){
+			
+			throw new Exception("Failed to parse JSON");
+		}
+		
+		if(isset($json["errors"])){
+			
+			$msg = [];
+			foreach($json["errors"] as $error){
+				
+				if(isset($error["msg"])){
+					
+					$msg[] = $error["msg"];
+				}
+			}
+			
+			throw new Exception("Sepia Search returned error(s): " . implode(", ", $msg));
+		}
+		
+		if(!isset($json["data"])){
+			
+			throw new Exception("Sepia Search did not return a data object");
+		}
+		
+		$out = [
+			"status" => "ok",
+			"npt" => null,
+			"video" => [],
+			"author" => [],
+			"livestream" => [],
+			"playlist" => [],
+			"reel" => []
+		];
+		
+		
+		switch($get["type"]){
+			
+			case "videos":
+				foreach($json["data"] as $video){
+					
+					if(count($video["account"]["avatars"]) !== 0){
+						
+						$avatar =
+							$video["account"]["avatars"][count($video["account"]["avatars"]) - 1]["url"];
+					}else{
+						
+						$avatar = null;
+					}
+					
+					if($video["thumbnailUrl"] === null){
+						
+						$thumb = [
+							"ratio" => null,
+							"url" => null
+						];
+					}else{
+						
+						$thumb  = [
+							"ratio" => "16:9",
+							"url" => $video["thumbnailUrl"]
+						];
+					}
+					
+					if($video["isLive"]){
+						
+						$append = "livestream";
+					}else{
+						
+						$append = "video";
+					}
+					
+					$out[$append][] = [
+						"title" => $video["name"],
+						"description" =>
+							$this->limitstrlen(
+								$this->titledots(
+									$video["description"]
+								)
+							),
+						"author" => [
+							"name" => $video["account"]["displayName"] . " ({$video["account"]["name"]})",
+							"url" => $video["account"]["url"],
+							"avatar" => $avatar
+						],
+						"date" => strtotime($video["publishedAt"]),
+						"duration" => $video["isLive"] ? "_LIVE" : $video["duration"],
+						"views" => $video["views"],
+						"thumb" => $thumb,
+						"url" => $video["url"]
+					];
+				}
+				break;
+			
+			case "playlists":
+				foreach($json["data"] as $playlist){
+					
+					if(count($playlist["ownerAccount"]["avatars"]) !== 0){
+						
+						$avatar =
+							$playlist["ownerAccount"]["avatars"][count($playlist["ownerAccount"]["avatars"]) - 1]["url"];
+					}else{
+						
+						$avatar = null;
+					}
+					
+					if($playlist["thumbnailUrl"] === null){
+						
+						$thumb = [
+							"ratio" => null,
+							"url" => null
+						];
+					}else{
+						
+						$thumb  = [
+							"ratio" => "16:9",
+							"url" => $playlist["thumbnailUrl"]
+						];
+					}
+					
+					$out["playlist"][] = [
+						"title" => $playlist["displayName"],
+						"description" =>
+							$this->limitstrlen(
+								$this->titledots(
+									$playlist["description"]
+								)
+							),
+						"author" => [
+							"name" => $playlist["ownerAccount"]["displayName"] . " ({$playlist["ownerAccount"]["name"]})",
+							"url" => $playlist["ownerAccount"]["url"],
+							"avatar" => $avatar
+						],
+						"date" => strtotime($playlist["createdAt"]),
+						"duration" => $playlist["videosLength"],
+						"views" => null,
+						"thumb" => $thumb,
+						"url" => $playlist["url"]
+					];
+				}
+				break;
+			
+			case "channels":
+				foreach($json["data"] as $channel){
+					
+					if(count($channel["avatars"]) !== 0){
+						
+						$thumb = [
+							"ratio" => "1:1",
+							"url" => $channel["avatars"][count($channel["avatars"]) - 1]["url"]
+						];
+					}else{
+						
+						$thumb = [
+							"ratio" => null,
+							"url" => null
+						];
+					}
+					
+					$out["author"][] = [
+						"title" => $channel["displayName"] . " ({$channel["name"]})",
+						"followers" => $channel["followersCount"],
+						"description" =>
+							$channel["videosCount"] . " videos. " .
+							$this->limitstrlen(
+								$this->titledots(
+									$channel["description"]
+								)
+							),
+						"thumb" => $thumb,
+						"url" => $channel["url"]
+					];
+				}
+				break;
+		}
+		
+		// get next page
+		if($json["total"] - 20 > $npt["start"]){
+			
+			$npt["start"] += 20;
+			
+			$npt = [
+				"type" => $get["type"],
+				"npt" => $npt
+			];
+			
+			$out["npt"] =
+				$this->backend
+				->store(
+					json_encode($npt),
+					"videos",
+					$proxy
+				);
+		}
+		
+		return $out;
+	}
+	
+	private function titledots($title){
+		
+		$substr = substr($title, -3);
+		
+		if(
+			$substr == "..." ||
+			$substr == "…"
+		){
+			
+			return trim(substr($title, 0, -3), " \n\r\t\v\x00\0\x0B\xc2\xa0");
+		}
+		
+		return trim($title, " \n\r\t\v\x00\0\x0B\xc2\xa0");
+	}
+	
+	private function limitstrlen($text){
+		
+		return
+			explode(
+				"\n",
+				wordwrap(
+					str_replace(
+						["\n\r", "\r\n", "\n", "\r"],
+						" ",
+						$text
+					),
+					300,
+					"\n"
+				),
+				2
+			)[0];
+	}
+}

scraper/startpage.php

@@ -1226,7 +1226,12 @@ class startpage{
 		// get results
 		foreach($json["render"]["presenter"]["regions"]["mainline"] as $category){
 			
-			if($category["display_type"] == "video-youtube"){
+			if(
+				preg_match(
+					'/^video-/i',
+					$category["display_type"]
+				)
+			){
 				
 				foreach($category["results"] as $video){
 					
@@ -1248,7 +1253,7 @@ class startpage{
 					}
 					
 					$out["video"][] = [
-						"title" => $video["title"],
+						"title" => str_replace(["", ""], "", $video["title"]),
 						"description" => $this->limitstrlen($video["description"]),
 						"author" => [
 							"name" => $video["channelTitle"],
@@ -1256,7 +1261,7 @@ class startpage{
 							"avatar" => null
 						],
 						"date" => strtotime($video["publishDate"]),
-						"duration" => $this->hms2int($video["duration"]),
+						"duration" => $this->hms2int($category["display_type"] == "video-youtube" ? $video["duration"] : $video["duration"] / 1000),
 						"views" => (int)$video["viewCount"],
 						"thumb" => $thumb,
 						"url" => $video["clickUrl"]

scraper/vsco.php

@@ -0,0 +1,257 @@
+<?php
+
+class vsco{
+	
+	public function __construct(){
+		
+		include "lib/backend.php";
+		$this->backend = new backend("vsco");
+	}
+	
+	public function getfilters($page){
+		
+		return [];
+	}
+	
+	private function get($proxy, $url, $get = [], $bearer = null){
+		
+		$curlproc = curl_init();
+		
+		if($get !== []){
+			$get_tmp = http_build_query($get);
+			$url .= "?" . $get_tmp;
+		}
+		
+		curl_setopt($curlproc, CURLOPT_URL, $url);
+		
+		curl_setopt($curlproc, CURLOPT_ENCODING, ""); // default encoding
+		
+		if($bearer === null){
+			
+			curl_setopt($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",
+				"Sec-GPC: 1",
+				"Connection: keep-alive",
+				"Upgrade-Insecure-Requests: 1",
+				"Sec-Fetch-Dest: document",
+				"Sec-Fetch-Mode: navigate",
+				"Sec-Fetch-Site: same-origin",
+				"Sec-Fetch-User: ?1",
+				"Priority: u=0, i",
+				"TE: trailers"]
+			);
+		}else{
+			
+			curl_setopt($curlproc, CURLOPT_HTTPHEADER,
+				["User-Agent: " . config::USER_AGENT,
+				"Accept: */*",
+				"Accept-Language: en-US",
+				"Accept-Encoding: gzip",
+				"Referer: https://vsco.co/search/images/" . urlencode($get["query"]),
+				"authorization: Bearer " . $bearer,
+				"content-type: application/json",
+				"x-client-build: 1",
+				"x-client-platform: web",
+				"DNT: 1",
+				"Sec-GPC: 1",
+				"Connection: keep-alive",
+				"Sec-Fetch-Dest: empty",
+				"Sec-Fetch-Mode: cors",
+				"Sec-Fetch-Site: same-origin",
+				"Priority: u=0",
+				"TE: trailers"]
+			);
+		}
+		
+		curl_setopt($curlproc, CURLOPT_RETURNTRANSFER, true);
+		curl_setopt($curlproc, CURLOPT_SSL_VERIFYHOST, 2);
+		curl_setopt($curlproc, CURLOPT_SSL_VERIFYPEER, true);
+		curl_setopt($curlproc, CURLOPT_CONNECTTIMEOUT, 30);
+		curl_setopt($curlproc, CURLOPT_TIMEOUT, 30);
+		
+		// http2 bypass
+		curl_setopt($curlproc, CURLOPT_HTTP_VERSION, CURL_HTTP_VERSION_2_0);
+		
+		$this->backend->assign_proxy($curlproc, $proxy);
+		
+		$data = curl_exec($curlproc);
+		
+		if(curl_errno($curlproc)){
+			
+			throw new Exception(curl_error($curlproc));
+		}
+		
+		curl_close($curlproc);
+		return $data;
+	}
+	
+	public function image($get){
+		
+		if($get["npt"]){
+			
+			[$data, $proxy] =
+				$this->backend->get(
+					$get["npt"], "images"
+				);
+			
+			$data = json_decode($data, true);
+			
+		}else{
+			
+			$search = $get["s"];
+			if(strlen($search) === 0){
+				
+				throw new Exception("Search term is empty!");
+			}
+			
+			$proxy = $this->backend->get_ip();
+			
+			// get bearer token
+			try{
+				
+				$html =
+					$this->get(
+						$proxy,
+						"https://vsco.co/feed"
+					);
+				
+			}catch(Exception $error){
+				
+				throw new Exception("Failed to fetch feed page");
+			}
+			
+			preg_match(
+				'/"tkn":"([A-z0-9]+)"/',
+				$html,
+				$bearer
+			);
+			
+			if(!isset($bearer[1])){
+				
+				throw new Exception("Failed to grep bearer token");
+			}
+			
+			$data = [
+				"pagination" => [
+					"query" => $search,
+					"page" => 0,
+					"size" => 100
+				],
+				"bearer" => $bearer[1]
+			];
+		}
+		
+		try{
+			
+			$json =
+				$this->get(
+					$proxy,
+					"https://vsco.co/api/2.0/search/images",
+					$data["pagination"],
+					$data["bearer"]
+				);
+		}catch(Exception $error){
+			
+			throw new Exception("Failed to fetch JSON");
+		}
+		
+		$json = json_decode($json, true);
+		
+		if($json === null){
+			
+			throw new Exception("Failed to decode JSON");
+		}
+		
+		$out = [
+			"status" => "ok",
+			"npt" => null,
+			"image" => []
+		];
+		
+		if(!isset($json["results"])){
+			
+			throw new Exception("Failed to access results object");
+		}
+		
+		foreach($json["results"] as $image){
+			
+			$image_domain = parse_url("https://" . $image["responsive_url"], PHP_URL_HOST);
+			$thumbnail = explode($image_domain, $image["responsive_url"], 2)[1];
+			
+			if(substr($thumbnail, 0, 3) != "/1/"){
+				
+				$thumbnail =
+					preg_replace(
+						'/^\/[^\/]+/',
+						"",
+						$thumbnail
+					);
+			}
+			
+			$thumbnail = "https://img.vsco.co/cdn-cgi/image/width=480,height=360" . $thumbnail;
+			$size =
+				$this->image_ratio(
+					(int)$image["dimensions"]["width"],
+					(int)$image["dimensions"]["height"]
+				);
+			
+			$out["image"][] = [
+				"title" => $image["description"],
+				"source" => [
+					[
+						"url" => "https://" . $image["responsive_url"],
+						"width" => (int)$image["dimensions"]["width"],
+						"height" => (int)$image["dimensions"]["height"]
+					],
+					[
+						"url" => $thumbnail,
+						"width" => $size[0],
+						"height" => $size[1]
+					]
+				],
+				"url" => "https://" . $image["grid"]["domain"] . "/media/" . $image["imageId"]
+			];
+		}
+		
+		// get NPT
+		$max_page = ceil($json["total"] / 100);
+		$data["pagination"]["page"]++;
+		
+		if($max_page > $data["pagination"]["page"]){
+			
+			$out["npt"] =
+				$this->backend->store(
+					json_encode($data),
+					"images",
+					$proxy
+				);
+		}
+		
+		return $out;
+	}
+	
+	private function image_ratio($width, $height){
+		
+		$ratio = [
+			480 / $width,
+			360 / $height
+		];
+		
+		if($ratio[0] < $ratio[1]){
+			
+			$ratio = $ratio[0];
+		}else{
+			
+			$ratio = $ratio[1];
+		}
+		
+		return [
+			floor($width * $ratio),
+			floor($height * $ratio)
+		];
+	}
+}

scraper/yandex.php

@@ -14,7 +14,7 @@ class yandex{
 		// backend included in the scraper functions
 	}
 	
-	private function get($proxy, $url, $get = [], $nsfw){
+	private function get($proxy, $url, $get = [], $nsfw, $get_cookie = 1){
 		
 		$curlproc = curl_init();
 		
@@ -25,19 +25,55 @@ class yandex{
 		
 		curl_setopt($curlproc, CURLOPT_URL, $url);
 		
+		// extract "i" cookie
+		if($get_cookie === 0){
+			
+			$cookies_tmp = [];
+			curl_setopt($curlproc, CURLOPT_HEADERFUNCTION, function($curlproc, $header) use (&$cookies_tmp){
+				
+				$length = strlen($header);
+				
+				$header = explode(":", $header, 2);
+				
+				if(trim(strtolower($header[0])) == "set-cookie"){
+					
+					$cookie_tmp = explode("=", trim($header[1]), 2);
+					
+					$cookies_tmp[trim($cookie_tmp[0])] =
+						explode(";", $cookie_tmp[1], 2)[0];
+				}
+				
+				return $length;
+			});
+		}
+		
 		switch($nsfw){
 			case "yes": $nsfw = "0"; break;
 			case "maybe": $nsfw = "1"; break;
 			case "no": $nsfw = "2"; break;
 		}
 		
+		switch($get_cookie){
+			
+			case 0:
+				$cookie = "";
+				break;
+			
+			case 1:
+				$cookie = "Cookie: yp=" . (time() - 4000033) . ".szm.1:1920x1080:876x1000#" . time() . ".sp.family:" . $nsfw;
+				break;
+			
+			default:
+				$cookie = "Cookie: i=" . $get_cookie;
+		}
+		
 		$headers =
 			["User-Agent: " . config::USER_AGENT,
 			"Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8",
 			"Accept-Encoding: gzip",
 			"Accept-Language: en-US,en;q=0.5",
 			"DNT: 1",
-			"Cookie: yp=1716337604.sp.family%3A{$nsfw}#1685406411.szm.1:1920x1080:1920x999",
+			$cookie,
 			"Referer: https://yandex.com/images/search",
 			"Connection: keep-alive",
 			"Upgrade-Insecure-Requests: 1",
@@ -59,6 +95,17 @@ class yandex{
 		
 		$data = curl_exec($curlproc);
 		
+		if($get_cookie === 0){
+			
+			if(isset($cookies_tmp["i"])){
+				
+				return $cookies_tmp["i"];
+			}else{
+				
+				throw new Exception("Failed to get Yandex clearance cookie");
+			}
+		}
+		
 		if(curl_errno($curlproc)){
 			
 			throw new Exception(curl_error($curlproc));
@@ -217,6 +264,23 @@ class yandex{
 		// https://yandex.com/search/site/?text=minecraft&web=1&frame=1&v=2.0&searchid=3131712
 		// &within=777&from_day=26&from_month=8&from_year=2023&to_day=26&to_month=8&to_year=2023
 		
+		// get clearance cookie
+		if(($cookie = apcu_fetch("yandexweb_cookie")) === false){
+			
+			$proxy = $this->backend->get_ip();
+			
+			$cookie =
+				$this->get(
+					$proxy,
+					"https://yandex.ru/support2/smart-captcha/ru/",
+					[],
+					false,
+					0
+				);
+			
+			apcu_store("yandexweb_cookie", $cookie);
+		}
+		
 		if($get["npt"]){
 			
 			[$npt, $proxy] = $this->backend->get($get["npt"], "web");
@@ -226,7 +290,8 @@ class yandex{
 					$proxy,
 					"https://yandex.com" . $npt,
 					[],
-					"yes"
+					"yes",
+					$cookie
 				);
 		}else{
 			
@@ -236,7 +301,7 @@ class yandex{
 				throw new Exception("Search term is empty!");
 			}
 			
-			$proxy = $this->backend->get_ip();
+			$proxy = !isset($proxy) ? $this->backend->get_ip() : $proxy;
 			$lang = $get["lang"];
 			$older = $get["older"];
 			$newer = $get["newer"];
@@ -283,7 +348,8 @@ class yandex{
 						$proxy,
 						"https://yandex.com/search/site/",
 						$params,
-						"yes"
+						"yes",
+						$cookie
 					);
 			}catch(Exception $error){
 				
@@ -314,6 +380,19 @@ class yandex{
 		
 		$this->fuckhtml->load($html);
 		
+		// Scrape page blocked error
+		$title =
+			$this->fuckhtml
+			->getElementsByTagName("title");
+		
+		if(
+			count($title) !== 0 &&
+			$title[0]["innerHTML"] == "403"
+		){
+			
+			throw new Exception("Yandex blocked this proxy or 4get instance.");
+		}
+		
 		// get nextpage
 		$npt =
 			$this->fuckhtml
@@ -668,7 +747,6 @@ class yandex{
 		foreach($json["blocks"] as $block){
 			
 			$html .= $block["html"];
-			
 			// get next page
 			if(
 				isset($block["params"]["nextPageUrl"]) &&

scraper/yt.php

@@ -1209,15 +1209,16 @@ class yt{
 				
 				$reel =
 					$reel
-					->reelItemRenderer;
+					->shortsLockupViewModel;
 				
 				array_push(
 					$this->out["reel"],
 					[
 						"title" =>
 							$reel
-							->headline
-							->simpleText,
+							->overlayMetadata
+							->primaryText
+							->content,
 						"description" => null,
 						"author" => [
 							"name" => null,
@@ -1225,30 +1226,22 @@ class yt{
 							"avatar" => null
 						],
 						"date" => null,
-						"duration" =>
-							$this->textualtime2int(
-								$reel
-								->accessibility
-								->accessibilityData
-								->label
-							),
-						"views" =>
-							$this->truncatedcount2int(
-								$reel
-								->viewCountText
-								->simpleText
-							),
+						"duration" => null,
+						"views" => null,
 						"thumb" => [
 							"url" =>
 								$reel
 								->thumbnail
-								->thumbnails[0]
+								->sources[0]
 								->url,
 							"ratio" => "9:16"
 						],
 						"url" =>
 							"https://www.youtube.com/watch?v=" .
 							$reel
+							->onTap
+							->innertubeCommand
+							->reelWatchEndpoint
 							->videoId
 					]
 				);

settings.php

@@ -133,6 +133,10 @@ $settings = [
 						"value" => "google",
 						"text" => "Google"
 					],
+					[
+						"value" => "google_cse",
+						"text" => "Google CSE"
+					],
 					[
 						"value" => "startpage",
 						"text" => "Startpage"
@@ -166,8 +170,12 @@ $settings = [
 						"text" => "Mojeek"
 					],
 					[
-						"value" => "solofield",
-						"text" => "Solofield"
+						"value" => "baidu",
+						"text" => "Baidu"
+					],
+					[
+						"value" => "coccoc",
+						"text" => "Cốc Cốc"
 					],
 					[
 						"value" => "marginalia",
@@ -203,6 +211,10 @@ $settings = [
 						"value" => "google",
 						"text" => "Google"
 					],
+					[
+						"value" => "google_cse",
+						"text" => "Google CSE"
+					],
 					[
 						"value" => "startpage",
 						"text" => "Startpage"
@@ -216,13 +228,25 @@ $settings = [
 						"text" => "Yep"
 					],
 					[
-						"value" => "solofield",
-						"text" => "Solofield"
+						"value" => "baidu",
+						"text" => "Baidu"
 					],
-					/*[
+					[
 						"value" => "pinterest",
 						"text" => "Pinterest"
-					],*/
+					],
+					[
+						"value" => "flickr",
+						"text" => "Flickr"
+					],
+					[
+						"value" => "fivehpx",
+						"text" => "500px"
+					],
+					[
+						"value" => "vsco",
+						"text" => "VSCO"
+					],
 					[
 						"value" => "imgur",
 						"text" => "Imgur"
@@ -241,6 +265,10 @@ $settings = [
 						"value" => "yt",
 						"text" => "YouTube"
 					],
+					[
+						"value" => "sepiasearch",
+						"text" => "Sepia Search"
+					],
 					[
 						"value" => "ddg",
 						"text" => "DuckDuckGo"
@@ -266,8 +294,12 @@ $settings = [
 						"text" => "Qwant"
 					],
 					[
-						"value" => "solofield",
-						"text" => "Solofield"
+						"value" => "baidu",
+						"text" => "Baidu"
+					],
+					[
+						"value" => "coccoc",
+						"text" => "Cốc Cốc"
 					]
 				]
 			],
@@ -302,6 +334,10 @@ $settings = [
 					[
 						"value" => "mojeek",
 						"text" => "Mojeek"
+					],
+					[
+						"value" => "baidu",
+						"text" => "Baidu"
 					]
 				]
 			],

static/themes/Gore's shitty theme.css

@@ -1,47 +1,45 @@
 :root{
-	--1d2021: #1d2021;
-	--282828: #282828;
-	--3c3836: #3c3836;
-	--504945: #504945;
-	
+	--1d2021:#1d2021;
+	--282828:#282828;
+	--3c3836:#3c3836;
+	--504945:#504945;
+
 	/* font */
-	--928374: #928374;
-	--a89984: #c9c5bf;
-	--bdae93: #bdae93;
-	--8ec07c: #8ec07c;
-	--ebdbb2: #ebdbb2;
+	--928374:#928374;
+	--a89984:#c9c5bf;
+	--bdae93:#bdae93;
+	--8ec07c:#8ec07c;
+	--ebdbb2:#ebdbb2;
 }
 
-
-
 body{
 	padding:15px 4% 40px;
+	margin:unset;
 }
 
-h1,h2,h3,h4,h5,h6{
+h1, h2, h3, h4, h5, h6{
 	padding:0;
 	margin:0 0 7px 0;
 	line-height:initial;
 	color:var(--bdae93);
 }
 
-h3,h4,h5,h6{
+h3, h4, h5, h6{
 	margin-bottom:14px;
 }
 
 /*
-	Web styles
+  Web styles
 */
 
 .searchbox input[type="submit"]{
 	float:right;
 	cursor:pointer;
 	padding:0 10px;
-  border-left: 1px solid var(--504945);
-  background: #723c0b;
+	border-left:1px solid var(--504945);
+	background:#723c0b;
 }
 
-
 .searchbox input{
 	all:unset;
 	line-height:36px;
@@ -96,7 +94,6 @@ h3,h4,h5,h6{
 	display:inline-block;
 }
 
-
 .tabs .tab.selected{
 	border-bottom:2px solid #fc92a5;
 }
@@ -106,7 +103,7 @@ h3,h4,h5,h6{
 	padding-bottom:12px;
 	padding-top:7px;
 	margin-bottom:7px;
-	background-color:#232525
+	background-color:#232525;
 }
 
 .filters .filter{
@@ -169,7 +166,6 @@ h3,h4,h5,h6{
 	font-size:12px;
 }
 
-
 .web .hover{
 	display:block;
 	text-decoration:none;
@@ -193,16 +189,13 @@ h3,h4,h5,h6{
 	color:#9760b1 !important;
 }
 
-
 .web .text-result .greentext{
 	font-size:14px;
 	color:var(--bdae93);
 }
 
-
 /* favicon */
 
-
 .favicon-dropdown a{
 	text-decoration:none;
 	color:#d3d0c1;
@@ -211,39 +204,33 @@ h3,h4,h5,h6{
 	font-size:13px;
 }
 
-
-.web .favicon img,
-.favicon-dropdown img{
+.web .favicon img, .favicon-dropdown img{
 	margin:3px 7px 0 0;
 	height:16px;
 	font-size:12px;
-	line-height:16px;;
+	line-height:16px;
 	display:block;
 	text-align:left;
 }
 
-
 .web .sublinks{
 	padding:17px 10px;
 	font-size:15px;
 	color:var(--#928374);
 }
 
-
 .web .text-result .sublinks:last-child{
 	padding-bottom:0;
 }
 
-
 /* Wikipedia head */
 .wiki-head{
 	padding:5px;
-	background-color: #322f2b
+	background-color:#322f2b;
 }
 
-
 /*
-	Images tab
+  Images tab
 */
 
 #images{
@@ -257,17 +244,14 @@ h3,h4,h5,h6{
 	float:left;
 }
 
-
-
 #images .image .title{
 	white-space:nowrap;
 	overflow:hidden;
 	margin-bottom:7px;
 	font-weight:bold;
-    color:var(--bdae93);
+	color:var(--bdae93);
 }
 
-
 #popup-status{
 	display:none;
 	position:fixed;
@@ -280,43 +264,59 @@ h3,h4,h5,h6{
 }
 
 /*
-	Settings page
+  Settings page
 */
 
-
 .web .settings-submit a{
 	margin-right:17px;
 	color:#bdae93;
 }
 
+/*
+  Responsive image
+*/
+@media only screen and (max-width:1454px){
+	#images .image-wrapper{
+		width:25%;
+	}
+}
+
+@media only screen and (max-width:1161px){
+	#images .image-wrapper{
+		width:25%;
+	}
+}
+
+@media only screen and (max-width:750px){
+	#images .image-wrapper{
+		width:50%;
+	}
+}
+
+@media only screen and (max-width:450px){
+	#images .image-wrapper{
+		width:100%;
+	}
+}
 
 /*
-	Responsive image
+  Responsive design
 */
-@media only screen and (max-width: 1454px){ #images .image-wrapper{ width:25%; } }
-@media only screen and (max-width: 1161px){ #images .image-wrapper{ width:25%; } }
-@media only screen and (max-width: 750px){ #images .image-wrapper{ width:50%; } }
-@media only screen and (max-width: 450px){ #images .image-wrapper{ width:100%; } }
 
-
-/*
-	Responsive design
-*/
-@media only screen and (max-width: 1550px){
-	
-	
-	.web .left,
+@media only screen and (max-width:1550px){
+.web .left,
 	.searchbox{
 		width:60%;
 	}
-
 }
 
-@media only screen and (max-width: 1000px){
-
+@media only screen and (max-width:1100px){
+.web .left,
+	.searchbox{
+		width:100%;
+	}
 }
 
-    .type{
-    color:var(--bdae93);
-    }
+.type{
+	color:var(--bdae93);
 }

static/themes/Kuuro.css

@@ -0,0 +1,17 @@
+:root{
+	--1d2021: #101010;
+	--282828: #1a1a1a;
+	--3c3836: #1e1e1e;
+	--504945: #232323;
+
+	--928374: #949494;
+	--a89984: #d2d2d2;
+	--bdae93: #d2d2d2;
+	--8ec07c: #99c794;
+	--ebdbb2: #d2d2d2;
+
+	--comment: #5f6364;
+	--default: #cccece;
+	--keyword: #c594c5;
+	--string:  #99c794;
+}

static/themes/Wine.css

@@ -0,0 +1,40 @@
+:root
+{
+        --accent : #f79e98;
+        --1d2021 : #180d0c;
+        --282828 : #180d0c;
+        --3c3836 : #251615;
+        --504945 : #251615;
+        --928374 : var(--accent);
+        --a89984 : #d8c5c4;
+        --bdae93 : #d8c5c4;
+        --8ec07c : var(--accent);
+        --ebdbb2 : #d8c5c4;
+        --comment: #928374;
+        --default: #DCC9BC;
+        --keyword: #F07342;
+        --string : var(--accent);
+        --green  : #959A6B;
+        --yellow : #E39C45;
+        --red    : #CF223E;
+        --white  : var(--a89984);
+        --black  : var(--1d2021);
+        --hover  : #b18884
+}
+
+      a.link, a { color: var(--accent); text-decoration: none; }
+      .searchbox { width: 23%; }
+      .filters filter select { color: #E39C45; }
+      .web .separator::before { color: var(--white) }
+      .searchbox input[type="text"]::placeholder { color: var(--white); }
+      a.link:hover
+      {
+        color: var(--hover);
+        text-shadow: 0 0 .2rem var(--hover);
+      }
+      .code-inline
+      { border-color: var(--default); font-family: monospace;}
+      .home #center a
+      { color: var(--accent); }
+      .home .subtext
+      { color: var(--white); }

web.php

@@ -89,7 +89,7 @@ if($results["spelling"]["type"] != "no_correction"){
 			'&' .
 			$frontend->buildquery($get, true) .
 			'&spellcheck=no">' .
-			$results["spelling"]["correction"] .
+			htmlspecialchars($results["spelling"]["correction"]) .
 			'</a>?' .
 		'</div>';
 }