lolcat
/
4get
6
14
Fork 5
Code Issues 24 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

Compare commits

..

No commits in common. "master" and "docker_tor_documentation" have entirely different histories.
master ... docker_tor

49 changed files with 5921 additions and 9152 deletions

1
.dockerignore
View File

@ -1 +0,0 @@
.git

6
.gitignore vendored
View File

@ -1,3 +1,4 @@
<<<<<<< HEAD
lib/test.html
lib/postdata.json
lib/nextpage.json
@ -24,5 +25,8 @@ data/captcha/birds/
data/captcha/fumo_plushies/
data/captcha/minecraft/
!banner/*default*
=======
banner/*
!banner/*default*
>>>>>>> 77293818cd213ec0ad07c573d298fff9cd5b357d
scraper/curlie.html
icons/*

8
Dockerfile
View File

@ -1,9 +1,10 @@
FROM alpine:3.21
FROM alpine:latest
WORKDIR /var/www/html/4get
RUN apk update && apk upgrade
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
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
COPY ./docker/apache/ /etc/apache2/
COPY . .
RUN chmod 777 /var/www/html/4get/icons
@ -13,5 +14,4 @@ EXPOSE 443
ENV FOURGET_PROTO=http
ENTRYPOINT ["./docker/docker-entrypoint.sh"]
CMD ["start"]
CMD ["./docker/docker-entrypoint.sh"]

45
README.md
View File

@ -1,4 +1,4 @@
## <a href="https://4get.ca/donate">Donate to the project here!</a>
[![ko-fi](https://ko-fi.com/img/githubbutton_sm.svg)](https://ko-fi.com/W7W2OZK5H)
# 4get search
**4get** is a proxy search engine that doesn't suck.
@ -6,18 +6,17 @@
## About 4get
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._
## Try it out
https://4get.ca
## Totally unbiased comparison between alternatives
| | 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 |
| Does it work | ye | sometimes | sometimes | sometimes | yes |
| | 4get | searx(ng) | librex | araa |
|----------------------------|-------------------------|-----------|-------------|-----------|
| RAM usage | 200-400mb~ | 2GB~ | 200-400mb~ | 2GB~ |
| Does it suck | no (debunked by snopes) | yes | yes | a little |
| Does it work | ye | sometimes | no | sometimes |
| Did the dev commit suicide | not until my 30s | no | allegedly | no |
## Features
1. Rotating proxies on a per-scraper basis
@ -25,9 +24,9 @@ _NOT to be confused with 4get.ch, 4get.lol and friends! I **don't** host these._
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 shits
6. Bunch of other shit
tl;dr 4get is the best way to browse for shit.
tl;dr the best way to actually browse for shit.
# Supported websites
@ -36,16 +35,13 @@ tl;dr 4get is the best way to browse for shit.
| 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 | Pinterest | | | | Yep |
| Crowdview | 500px | | | | Marginalia |
| Mwmbl | VSCO | | | | YouTube |
| Mojeek | Imgur | | | | Soundcloud |
| Solofield | FindThatMeme | | | | |
| Google | Google | Yandex | Qwant | | Google |
| Qwant | Qwant | Google | Mojeek | | Qwant |
| Yep | Yep | Qwant | | | Yep |
| Greppr | Imgur | | | | Marginalia |
| Crowdview | FindThatMeme | | | | YouTube |
| Mwmbl | | | | | Soundcloud |
| Mojeek | | | | | |
| Marginalia | | | | | |
| wiby | | | | | |
| Curlie | | | | | |
@ -54,7 +50,4 @@ tl;dr 4get is the best way to browse for shit.
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.
## License
AGPL
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.

21
api.txt
View File

@ -1,17 +1,10 @@
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

5
api/v1/ac.php
View File

@ -18,10 +18,7 @@ class autocomplete{
"yep" => "https://api.yep.com/ac/?query={searchTerms}",
"marginalia" => "https://search.marginalia.nu/suggest/?partial={searchTerms}",
"yt" => "https://suggestqueries-clients6.youtube.com/complete/search?client=youtube&q={searchTerms}",
"sc" => "",
"startpage" => "https://www.startpage.com/suggestions?q={searchTerms}&format=opensearch&segment=startpage.defaultffx&lui=english",
"kagi" => "https://kagi.com/api/autosuggest?q={searchTerms}",
"ghostery" => "https://ghosterysearch.com/suggest?q={searchTerms}"
"sc" => ""
];
/*

21
data/config.php
View File

@ -11,7 +11,7 @@ class config{
const SERVER_NAME = "4get";
// Will be shown in <meta> tag on home page
const SERVER_SHORT_DESCRIPTION = "4get is a proxy search engine that doesn't suck.";
const SERVER_SHORT_DESCRIPTION = "They live in our walls!";
// Will be shown in server list ping (null for no description)
const SERVER_LONG_DESCRIPTION = null;
@ -63,14 +63,6 @@ class config{
//"via"
];
// Block SSL ciphers used by CLI tools used for botting
// Basically a primitive version of Cloudflare's browser integrity check
// ** If curl can still access the site (with spoofed headers), please make sure you use the new apache2 config **
// https://git.lolcat.ca/lolcat/4get/docs/apache2.md
const DISALLOWED_SSL = [
// "TLS_AES_256_GCM_SHA384" // used by WGET and CURL
];
// Maximal number of searches per captcha key/pass issued. Counter gets
// reset on every APCU cache clear (should happen once a day).
// Only useful when BOT_PROTECTION is NOT set to 0
@ -119,7 +111,7 @@ 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:134.0) Gecko/20100101 Firefox/134.0";
const USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:127.0) Gecko/20100101 Firefox/127.0";
// Proxy pool assignments for each scraper
// false = Use server's raw IP
@ -129,22 +121,16 @@ class config{
const PROXY_BRAVE = false;
const PROXY_FB = false; // facebook
const PROXY_GOOGLE = false;
const PROXY_GOOGLE_CSE = false;
const PROXY_STARTPAGE = false;
const PROXY_QWANT = false;
const PROXY_GHOSTERY = false;
const PROXY_MARGINALIA = false;
const PROXY_MOJEEK = false;
const PROXY_SC = false; // soundcloud
const PROXY_SPOTIFY = false;
const PROXY_SOLOFIELD = false;
const PROXY_WIBY = false;
const PROXY_CURLIE = false;
const PROXY_YT = false; // youtube
const PROXY_YEP = false;
const PROXY_PINTEREST = false;
const PROXY_FIVEHPX = false;
const PROXY_VSCO = false;
const PROXY_SEZNAM = false;
const PROXY_NAVER = false;
const PROXY_GREPPR = false;
@ -160,9 +146,6 @@ class config{
// Scraper-specific parameters
//
// GOOGLE CSE
const GOOGLE_CX_ENDPOINT = "d4e68b99b876541f0";
// MARGINALIA
// Use "null" to default out to HTML scraping OR specify a string to
// use the API (Eg: "public"). API has less filters.

11
docker-compose.yaml
View File

@ -6,15 +6,14 @@ 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 ssl
# - ./banners:/var/www/html/4get/banner # mount custom banners
# - ./captcha:/var/www/html/4get/data/captcha # mount captcha images
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

0
docker/apache/https/conf.d/ssl.conf → docker/apache/conf.d/ssl.conf
View File

0
docker/apache/http/httpd.conf → docker/apache/http.conf
View File

1
docker/apache/http/conf.d/ssl.conf
View File

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

0
docker/apache/https/httpd.conf → docker/apache/https.conf
View File

19
docker/docker-entrypoint.sh
View File

@ -8,27 +8,18 @@ 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 -r ${FOURGET_SRC}/docker/apache/https/httpd.conf /etc/apache2
cp -r ${FOURGET_SRC}/docker/apache/https/conf.d/* /etc/apache2/conf.d
cp /etc/apache2/https.conf /etc/apache2/httpd.conf
else
echo "Using http configuration"
cp -r ${FOURGET_SRC}/docker/apache/http/httpd.conf /etc/apache2
cp -r ${FOURGET_SRC}/docker/apache/http/conf.d/* /etc/apache2/conf.d
cp /etc/apache2/http.conf /etc/apache2/httpd.conf
fi
php ./docker/gen_config.php
if [ "$@" = "start" ]; then
echo "4get is running"
exec httpd -DFOREGROUND
else
exec "$@"
fi
echo "4get is running"
exec httpd -DFOREGROUND

195
docs/apache2-example.md
View File

@ -1,195 +0,0 @@
# Sample Apache2 configuration
This is the apache2 configuration file used on the 4get.ca official instance, in hopes that it's useful to you!
Looking for the apache2 guide? <a href="https://git.lolcat.ca/lolcat/4get/src/branch/master/docs/apache2.md">go here.</a>.
```xml
<VirtualHost *:443>
ServerName www.4get.ca
SSLEngine On
SSLCertificateFile /etc/letsencrypt/live/4get.ca/fullchain.pem
SSLCertificateKeyFile /etc/letsencrypt/live/4get.ca/privkey.pem
SSLCertificateChainFile /etc/letsencrypt/live/4get.ca/chain.pem
RedirectMatch 301 ^(.*)$ https://4get.ca$1
</VirtualHost>
<VirtualHost *:443>
ServerName 4get.ca
ServerAdmin will@lolcat.ca
DocumentRoot /var/www/4get
SSLEngine On
SSLOptions +StdEnvVars
#ErrorLog ${APACHE_LOG_DIR}/error.log
AddOutputFilterByType DEFLATE application/json
AddOutputFilterByType DEFLATE application/javascript
AddOutputFilterByType DEFLATE application/x-javascript
AddOutputFilterByType DEFLATE text/html
AddOutputFilterByType DEFLATE text/plain
AddOutputFilterByType DEFLATE text/css
SSLCertificateFile /etc/letsencrypt/live/4get.ca/fullchain.pem
SSLCertificateKeyFile /etc/letsencrypt/live/4get.ca/privkey.pem
SSLCertificateChainFile /etc/letsencrypt/live/4get.ca/chain.pem
<Directory /var/www/4get>
Options -MultiViews
AllowOverride All
Require all granted
RewriteEngine On
RewriteCond %{REQUEST_FILENAME} !-d
RewriteCond %{REQUEST_FILENAME} !-f
RewriteRule ^([^\.]+)$ $1.php [NC,L]
</Directory>
# deny access to private resources
<Directory /var/www/4get/data/>
Order Deny,allow
Deny from all
</Directory>
</VirtualHost>
<VirtualHost *:443>
ServerName www.lolcat.ca
SSLEngine On
SSLCertificateFile /etc/letsencrypt/live/4get.ca/fullchain.pem
SSLCertificateKeyFile /etc/letsencrypt/live/4get.ca/privkey.pem
SSLCertificateChainFile /etc/letsencrypt/live/4get.ca/chain.pem
RedirectMatch 301 ^(.*)$ https://lolcat.ca$1
</VirtualHost>
<VirtualHost *:443>
ServerName lolcat.ca
ServerAdmin will@lolcat.ca
DocumentRoot /var/www/lolcat
SSLEngine On
SSLOptions +StdEnvVars
#ErrorLog ${APACHE_LOG_DIR}/error.log
AddOutputFilterByType DEFLATE application/json
AddOutputFilterByType DEFLATE application/javascript
AddOutputFilterByType DEFLATE application/x-javascript
AddOutputFilterByType DEFLATE text/html
AddOutputFilterByType DEFLATE text/plain
AddOutputFilterByType DEFLATE text/css
SSLCertificateFile /etc/letsencrypt/live/4get.ca/fullchain.pem
SSLCertificateKeyFile /etc/letsencrypt/live/4get.ca/privkey.pem
SSLCertificateChainFile /etc/letsencrypt/live/4get.ca/chain.pem
<Directory /var/www/lolcat>
Options -MultiViews
AllowOverride All
Require all granted
RewriteEngine On
RewriteCond %{REQUEST_FILENAME} !-d
RewriteCond %{REQUEST_FILENAME} !-f
RewriteRule ^([^\.]+)$ $1.php [NC,L]
</Directory>
</VirtualHost>
<VirtualHost *:443>
ServerName www.nyym.co
SSLEngine On
SSLCertificateFile /etc/letsencrypt/live/nyym.co/fullchain.pem
SSLCertificateKeyFile /etc/letsencrypt/live/nyym.co/privkey.pem
SSLCertificateChainFile /etc/letsencrypt/live/nyym.co/chain.pem
RedirectMatch 301 ^(.*)$ https://nyym.co$1
</VirtualHost>
<VirtualHost *:443>
ServerName nyym.co
ServerAdmin will@lolcat.ca
DocumentRoot /var/www/nyym
SSLEngine On
SSLOptions +StdEnvVars
#ErrorLog ${APACHE_LOG_DIR}/error.log
AddOutputFilterByType DEFLATE application/json
AddOutputFilterByType DEFLATE application/javascript
AddOutputFilterByType DEFLATE application/x-javascript
AddOutputFilterByType DEFLATE text/html
AddOutputFilterByType DEFLATE text/plain
AddOutputFilterByType DEFLATE text/css
SSLCertificateFile /etc/letsencrypt/live/nyym.co/fullchain.pem
SSLCertificateKeyFile /etc/letsencrypt/live/nyym.co/privkey.pem
SSLCertificateChainFile /etc/letsencrypt/live/nyym.co/chain.pem
<Directory /var/www/nyym>
Options -MultiViews
AllowOverride All
Require all granted
RewriteEngine On
RewriteCond %{REQUEST_FILENAME} !-d
RewriteCond %{REQUEST_FILENAME} !-f
RewriteRule ^([^\.]+)$ $1.php [NC,L]
</Directory>
</VirtualHost>
<VirtualHost *:443>
ServerName git.lolcat.ca
SSLEngine On
SSLOptions +StdEnvVars
#ErrorLog ${APACHE_LOG_DIR}/error.log
AddOutputFilterByType DEFLATE application/json
AddOutputFilterByType DEFLATE application/javascript
AddOutputFilterByType DEFLATE application/x-javascript
AddOutputFilterByType DEFLATE text/html
AddOutputFilterByType DEFLATE text/plain
AddOutputFilterByType DEFLATE text/css
SSLCertificateFile /etc/letsencrypt/live/4get.ca/fullchain.pem
SSLCertificateKeyFile /etc/letsencrypt/live/4get.ca/privkey.pem
SSLCertificateChainFile /etc/letsencrypt/live/4get.ca/chain.pem
ProxyPreserveHost On
ProxyRequests off
AllowEncodedSlashes NoDecode
ProxyPass / http://localhost:3000/ nocanon
</VirtualHost>
<VirtualHost *:443>
ServerName live.lolcat.ca
ServerAdmin will@lolcat.ca
DocumentRoot /var/www/live
SSLEngine On
SSLOptions +StdEnvVars
#ErrorLog ${APACHE_LOG_DIR}/error.log
AddOutputFilterByType DEFLATE application/json
AddOutputFilterByType DEFLATE application/javascript
AddOutputFilterByType DEFLATE application/x-javascript
AddOutputFilterByType DEFLATE text/html
AddOutputFilterByType DEFLATE text/plain
AddOutputFilterByType DEFLATE text/css
SSLCertificateFile /etc/letsencrypt/live/4get.ca/fullchain.pem
SSLCertificateKeyFile /etc/letsencrypt/live/4get.ca/privkey.pem
SSLCertificateChainFile /etc/letsencrypt/live/4get.ca/chain.pem
</VirtualHost>
```

90
docs/apache2.md
View File

@ -74,7 +74,7 @@ Now, edit the following file: `/etc/apache2/sites-available/000-default.conf`, r
DocumentRoot /var/www/4get
Options -MultiViews
Options +MultiViews
RewriteEngine On
RewriteCond %{REQUEST_FILENAME} !-d
RewriteCond %{REQUEST_FILENAME} !-f
@ -92,56 +92,47 @@ To make the above snippet work, please refer to our <a href="https://git.lolcat.
## default-ssl.conf
Now, edit the file `/etc/apache2/sites-available/default-ssl.conf`, remove everything and, again, add each rule while modifying the relevant fields:
First, append the following redirect rule to point traffic from `www.4get.ca` to `4get.ca`:
This ruleset will redirect all clients that specify an unknown `Host` to the domain of our choice. I recommend you uncomment the `ErrorLog` directive while setting things up in case a problem occurs with PHP. Don't worry about the invalid SSL paths, we will generate our certificates later; Just make sure you specify the right domains in there:
```xml
<VirtualHost *:443>
ServerName www.4get.ca
SSLEngine On
SSLCertificateFile /etc/letsencrypt/live/4get.ca/fullchain.pem
SSLCertificateKeyFile /etc/letsencrypt/live/4get.ca/privkey.pem
SSLCertificateChainFile /etc/letsencrypt/live/4get.ca/chain.pem
RedirectMatch 301 ^(.*)$ https://4get.ca$1
</VirtualHost>
```
This ruleset tells apache2 where 4get is located (`/var/www/4get`), ensures that `4get.ca/settings` resolves to `4get.ca/settings.php` internally and that we deny access to `/data/*`, which may contain files you might want to keep private. `StdEnvVArs+` will make it so that PHP can view if the connection uses HTTPS, and which cipher was used. Useful for basic bot protection.
Make sure to replace `4get.ca` with your own domain under the `SSLCertificate*` directives!
```xml
<VirtualHost *:443>
ServerName 4get.ca
ServerAdmin will@lolcat.ca
DocumentRoot /var/www/4get
SSLEngine On
SSLOptions +StdEnvVars
#ErrorLog ${APACHE_LOG_DIR}/error.log
SSLEngine on
<FilesMatch "\.(?:cgi|shtml|phtml|php)$">
SSLOptions +StdEnvVars
</FilesMatch>
<Directory /usr/lib/cgi-bin>
SSLOptions +StdEnvVars
</Directory>
AddOutputFilterByType DEFLATE application/json
AddOutputFilterByType DEFLATE application/javascript
AddOutputFilterByType DEFLATE application/x-javascript
AddOutputFilterByType DEFLATE text/html
AddOutputFilterByType DEFLATE text/plain
AddOutputFilterByType DEFLATE text/css
SSLCertificateFile /etc/letsencrypt/live/4get.ca/fullchain.pem
SSLCertificateKeyFile /etc/letsencrypt/live/4get.ca/privkey.pem
SSLCertificateChainFile /etc/letsencrypt/live/4get.ca/chain.pem
<Directory /var/www/4get>
Options -MultiViews
AllowOverride All
Require all granted
RewriteEngine On
RewriteCond %{REQUEST_FILENAME} !-d
RewriteCond %{REQUEST_FILENAME} !-f
RewriteRule ^([^\.]+)$ $1.php [NC,L]
</Directory>
</VirtualHost>
```
This ruleset tells apache2 where 4get is located (`/var/www/4get`), ensures that `4get.ca/settings` resolves to `4get.ca/settings.php` internally and that we deny access to `/data/*`, which may contain files you might want to keep private.
```xml
<VirtualHost *:443>
ServerName 4get.ca
DocumentRoot /var/www/4get
Options +MultiViews
RewriteEngine On
RewriteCond %{REQUEST_FILENAME} !-d
RewriteCond %{REQUEST_FILENAME} !-f
RewriteRule ^([^\.]+)$ $1.php [NC,L]
# deny access to private resources
<Directory /var/www/4get/data/>
@ -151,7 +142,28 @@ Make sure to replace `4get.ca` with your own domain under the `SSLCertificate*`
</VirtualHost>
```
By default, the first rule dictates where traffic should be redirected to in case the client specifies an unknown domain name. Don't forget your webserver's other rules! For a complete real-world example, please <a href="https://git.lolcat.ca/lolcat/4get/src/branch/master/docs/apache2-example.md">check out my real-world config file I use on 4get.ca</a>.
Don't forget to specify your other services here! Here's an example of a ruleset I use for `lolcat.ca`:
```xml
<VirtualHost *:443>
ServerName lolcat.ca
DocumentRoot /var/www/lolcat
Options +MultiViews
RewriteEngine On
RewriteCond %{REQUEST_FILENAME} !-d
RewriteCond %{REQUEST_FILENAME} !-f
RewriteRule ^([^\.]+)$ $1.php [NC,L]
</VirtualHost>
```
... Alongside with it's redirect rules.
```xml
<VirtualHost *:443>
ServerName www.lolcat.ca
RedirectMatch 301 ^(.*)$ https://lolcat.ca$1
</VirtualHost>
```
## security.conf
If you enabled the `headers` module, you can head over to `/etc/apache2/conf-enabled/security.conf` and edit:

4
docs/configure.md
View File

@ -8,10 +8,10 @@ Welcome! This guide assumes that you have a working 4get instance. This will hel
3. The captcha imagesets are located in `data/captcha/your_image_set/*.png`
4. The captcha font is located in `data/fonts/captcha.ttf`
# Cloudflare bypass (TLS check)
# Cloudflare bypass
**Note: this only allows you to bypass the browser integrity checks. Captchas & javascript challenges will not be bypassed.**
Configuring this lets you fetch images sitting behind Cloudflare and allows you to scrape the **Yep** & the **Mwmbl** search engines. Please be aware that APT will fight against you and will re-install the openSSL-version of curl constantly when updating.
Configuring this lets you fetch images sitting behind Cloudflare and allows you to scrape the **Yep** search engine. Following these instructions might make your package manager unhappy.
First, follow these instructions. Only install the Firefox modules:

271
docs/nginx.md
View File

@ -1,194 +1,103 @@
<h1 align=center>Installation of 4get in NGINX</h1>
# Install on NGINX
<div align=right>
>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.
> 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.
Login as root.
> 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.
Create a file in `/etc/nginx/sites-avaliable/` called `4get.conf` or any name you want and put this into the file:
</div>
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`
<div align=right>
> 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;
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;
}
```
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;
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 $uri @php;
}
```
A real world example is present in [^2].
5. Once done, check the configuration with `nginx -t`. If everything's fine and dandy, refer to <a href="https://git.lolcat.ca/lolcat/4get/src/branch/master/docs/tor.md">the Tor guide</a> to setup your onion site.
<h2 align=center>Other important things</h2>
location ~* ^(.*)\.php$ {
return 301 $1;
}
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.
listen 80;
}
```
<h2 align=center>Known issues</h2>
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)
1. https://git.lolcat.ca/lolcat/4get/issues
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:
[^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.
```sh
ln -s /etc/nginx/sites-available/4get.conf /etc/nginx/sites-available/4get.conf
```
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;
}
location / {
try_files $uri @php;
}
location ~* ^(.*)\.php$ {
return 301 $1;
}
}
```
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)
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.

39
donate.php
View File

@ -1,39 +0,0 @@
<?php
include "data/config.php";
include "lib/frontend.php";
$frontend = new frontend();
echo
$frontend->load(
"header_nofilters.html",
[
"title" => "Donate to the project",
"class" => " class=\"about\""
]
);
$left =
explode(
"\n",
file_get_contents("template/donate.html")
);
$out = "";
foreach($left as $line){
$out .= trim($line);
}
echo
$frontend->load(
"search.html",
[
"timetaken" => null,
"class" => "",
"right-left" => "",
"right-right" => "",
"left" => $out
]
);

7
favicon.php
View File

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

2
lib/backend.php
View File

@ -75,8 +75,6 @@ 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);
break;

38
lib/frontend.php
View File

@ -89,7 +89,6 @@ class frontend{
$user_agent = "";
$bad_header = false;
// block bots that present X-Forwarded-For, Via, etc
foreach($headers_raw as $headerkey => $headervalue){
$headerkey = strtolower($headerkey);
@ -107,27 +106,12 @@ class frontend{
}
}
// SSL check
$bad_ssl = false;
if(
isset($_SERVER["https"]) &&
$_SERVER["https"] == "on" &&
isset($_SERVER["SSL_CIPHER"]) &&
in_array($_SERVER["SSL_CIPHER"], config::FILTERED_HEADER_KEYS)
){
$bad_ssl = true;
}
if(
$bad_header === true ||
$bad_ssl === true ||
$user_agent == "" ||
// user agent check
preg_match(
config::HEADER_REGEX,
$user_agent
)
) ||
$bad_header === true
){
// bot detected !!
@ -838,10 +822,10 @@ 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>';
@ -939,16 +923,12 @@ class frontend{
"brave" => "Brave",
"yandex" => "Yandex",
"google" => "Google",
"google_cse" => "Google CSE",
"startpage" => "Startpage",
"qwant" => "Qwant",
"ghostery" => "Ghostery",
"yep" => "Yep",
"greppr" => "Greppr",
"crowdview" => "Crowdview",
"mwmbl" => "Mwmbl",
"mojeek" => "Mojeek",
"solofield" => "Solofield",
"marginalia" => "Marginalia",
"wiby" => "wiby",
"curlie" => "Curlie"
@ -964,14 +944,9 @@ class frontend{
"yandex" => "Yandex",
"brave" => "Brave",
"google" => "Google",
"google_cse" => "Google CSE",
"startpage" => "Startpage",
"qwant" => "Qwant",
"yep" => "Yep",
"solofield" => "Solofield",
"pinterest" => "Pinterest",
"fivehpx" => "500px",
"vsco" => "VSCO",
//"pinterest" => "Pinterest",
"imgur" => "Imgur",
"ftm" => "FindThatMeme"
]
@ -988,9 +963,7 @@ class frontend{
"brave" => "Brave",
"yandex" => "Yandex",
"google" => "Google",
"startpage" => "Startpage",
"qwant" => "Qwant",
"solofield" => "Solofield"
"qwant" => "Qwant"
]
];
break;
@ -1002,7 +975,6 @@ class frontend{
"ddg" => "DuckDuckGo",
"brave" => "Brave",
"google" => "Google",
"startpage" => "Startpage",
"qwant" => "Qwant",
"yep" => "Yep",
"mojeek" => "Mojeek"

112
lib/fuckhtml.php
View File

@ -381,8 +381,6 @@ class fuckhtml{
$json_out = null;
$last_char = null;
$keyword_check = null;
for($i=0; $i<strlen($json); $i++){
switch($json[$i]){
@ -398,7 +396,6 @@ class fuckhtml{
$bracket = false;
$is_close_bracket = true;
}else{
if($bracket === false){
@ -427,41 +424,19 @@ class fuckhtml{
$escape = false;
}
$lastchar = $json[$i];
if(
$bracket === false &&
$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]){
case "[":
case "{":
// dont execute whats in "default"
$json_out .= $json[$i];
break;
@ -526,85 +501,4 @@ 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;
}
}
}
}

666
license.txt
View File

@ -1,661 +1,13 @@
GNU AFFERO GENERAL PUBLIC LICENSE
Version 3, 19 November 2007
DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE
Version 2, December 2004
Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Copyright (C) 2023 lolcat <will@lolcat.ca>
Preamble
Everyone is permitted to copy and distribute verbatim or modified
copies of this license document, and changing it is allowed as long
as the name is changed.
The GNU Affero General Public License is a free, copyleft license for
software and other kinds of works, specifically designed to ensure
cooperation with the community in the case of network server software.
DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE
TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
our General Public Licenses are intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
Developers that use our General Public Licenses protect your rights
with two steps: (1) assert copyright on the software, and (2) offer
you this License which gives you legal permission to copy, distribute
and/or modify the software.
A secondary benefit of defending all users' freedom is that
improvements made in alternate versions of the program, if they
receive widespread use, become available for other developers to
incorporate. Many developers of free software are heartened and
encouraged by the resulting cooperation. However, in the case of
software used on network servers, this result may fail to come about.
The GNU General Public License permits making a modified version and
letting the public access it on a server without ever releasing its
source code to the public.
The GNU Affero General Public License is designed specifically to
ensure that, in such cases, the modified source code becomes available
to the community. It requires the operator of a network server to
provide the source code of the modified version running there to the
users of that server. Therefore, public use of a modified version, on
a publicly accessible server, gives the public access to the source
code of the modified version.
An older license, called the Affero General Public License and
published by Affero, was designed to accomplish similar goals. This is
a different license, not a version of the Affero GPL, but Affero has
released a new version of the Affero GPL which permits relicensing under
this license.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU Affero General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Remote Network Interaction; Use with the GNU General Public License.
Notwithstanding any other provision of this License, if you modify the
Program, your modified version must prominently offer all users
interacting with it remotely through a computer network (if your version
supports such interaction) an opportunity to receive the Corresponding
Source of your version by providing access to the Corresponding Source
from a network server at no charge, through some standard or customary
means of facilitating copying of software. This Corresponding Source
shall include the Corresponding Source for any work covered by version 3
of the GNU General Public License that is incorporated pursuant to the
following paragraph.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the work with which it is combined will remain governed by version
3 of the GNU General Public License.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU Affero General Public License from time to time. Such new versions
will be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU Affero General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU Affero General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU Affero General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If your software can interact with users remotely through a computer
network, you should also make sure that it provides a way for users to
get its source. For example, if your program is a web application, its
interface could display a "Source" link that leads users to an archive
of the code. There are many ways you could offer source, and different
solutions will be better for different programs; see section 13 for the
specific requirements.
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU AGPL, see
<https://www.gnu.org/licenses/>.
0. You just DO WHAT THE FUCK YOU WANT TO.

245
scraper/brave.php
View File

@ -210,63 +210,6 @@ 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"]){
@ -350,9 +293,8 @@ class brave{
/*
$handle = fopen("scraper/brave.html", "r");
$html = fread($handle, filesize("scraper/brave.html"));
fclose($handle);*/
fclose($handle);
*/
try{
$html =
$this->get(
@ -403,7 +345,7 @@ class brave{
$nextpage =
$this->fuckhtml
->getElementsByClassName("button", "a");
->getElementsByClassName("btn", "a");
if(count($nextpage) !== 0){
@ -439,22 +381,40 @@ class brave{
}
}
// do some magic
$this->fuckhtml->load($html);
$data = $this->get_js();
if(
isset($data[2]["data"]["title"]) &&
stripos($data[2]["data"]["title"], "PoW Captcha") !== false
){
$script_disc =
$this->fuckhtml
->getElementsByTagName(
"script"
);
$grep = [];
foreach($script_disc as $discs){
throw new Exception("Brave returned a PoW captcha");
preg_match(
'/const data ?= ?(\[{.*}]);/',
$discs["innerHTML"],
$grep
);
if(isset($grep[1])){
break;
}
}
if(!isset($data[1]["data"]["body"]["response"])){
if(!isset($grep[1])){
throw new Exception("Brave did not return a result object");
throw new Exception("Could not get data JS");
}
$data =
$this->fuckhtml
->parseJsObject(
$grep[1]
);
unset($grep);
$data = $data[1]["data"]["body"]["response"];
@ -684,10 +644,7 @@ class brave{
$table["Address"] = $result["location"]["postal_address"]["displayAddress"];
}
if(
isset($result["location"]["rating"]) &&
$result["location"]["rating"] != "void 0"
){
if(isset($result["location"]["rating"])){
$table["Rating"] =
$result["location"]["rating"]["ratingValue"] . "/" .
@ -695,19 +652,13 @@ class brave{
number_format($result["location"]["rating"]["reviewCount"]) . " votes)";
}
if(
isset($result["location"]["contact"]["telephone"]) &&
$result["location"]["contact"]["telephone"] != "void 0"
){
if(isset($result["location"]["contact"]["telephone"])){
$table["Phone number"] =
$result["location"]["contact"]["telephone"];
}
if(
isset($result["location"]["price_range"]) &&
$result["location"]["price_range"] != "void 0"
){
if(isset($result["location"]["price_range"])){
$table["Price"] =
$result["location"]["price_range"];
@ -1190,8 +1141,23 @@ class brave{
$proxy
);
$this->fuckhtml->load($html);
$json = $this->get_js();
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");
}
foreach(
$json[1]["data"]["body"]["response"]["news"]["results"]
@ -1273,8 +1239,22 @@ class brave{
$html = fread($handle, filesize("scraper/brave-image.html"));
fclose($handle);*/
$this->fuckhtml->load($html);
$json = $this->get_js();
preg_match(
'/const data = (\[{.*}\]);/',
$html,
$json
);
if(!isset($json[1])){
throw new Exception("Failed to get data object");
}
$json =
$this->fuckhtml
->parseJsObject(
$json[1]
);
foreach(
$json[1]
@ -1404,8 +1384,22 @@ class brave{
$html = fread($handle, filesize("scraper/brave-video.html"));
fclose($handle);*/
$this->fuckhtml->load($html);
$json = $this->get_js();
preg_match(
'/const data = (\[{.*}\]);/',
$html,
$json
);
if(!isset($json[1])){
throw new Exception("Failed to get data object");
}
$json =
$this->fuckhtml
->parseJsObject(
$json[1]
);
foreach(
$json
@ -1777,57 +1771,42 @@ class brave{
$nextpage =
$this->fuckhtml
->getElementById(
"pagination",
"div"
);
->getElementsByClassName("btn", "a");
if($nextpage){
$this->fuckhtml->load($nextpage);
if(count($nextpage) !== 0){
$nextpage =
$this->fuckhtml
->getElementsByClassName(
"button",
"a"
);
$nextpage[count($nextpage) - 1];
if(count($nextpage) !== 0){
$nextpage =
$nextpage[count($nextpage) - 1];
if(
strtolower(
$this->fuckhtml
->getTextContent(
$nextpage
)
) == "next"
){
preg_match(
'/offset=([0-9]+)/',
$this->fuckhtml->getTextContent($nextpage["attributes"]["href"]),
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
);
return
$this->backend->store(
json_encode(
[
"q" => $q,
"offset" => (int)$nextpage[1],
"nsfw" => $nsfw,
"country" => $country,
"spellcheck" => $spellcheck
]
),
$page,
$proxy
);
}
}
}

3698
scraper/ddg.php
View File

File diff suppressed because it is too large Load Diff

262
scraper/fivehpx.php
View File

@ -1,262 +0,0 @@
<?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)
];
}
}

2
scraper/ftm.php
View File

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

320
scraper/ghostery.php
View File

@ -1,320 +0,0 @@
<?php
class ghostery{
public function __construct(){
include "lib/backend.php";
$this->backend = new backend("ghostery");
include "lib/fuckhtml.php";
$this->fuckhtml = new fuckhtml();
}
public function getfilters($page){
if($page != "web"){
return [];
}
return [
"country" => [
"display" => "Country",
"option" => [
"any" => "All regions",
"AR" => "Argentina",
"AU" => "Australia",
"AT" => "Austria",
"BE" => "Belgium",
"BR" => "Brazil",
"CA" => "Canada",
"CL" => "Chile",
"DK" => "Denmark",
"FI" => "Finland",
"FR" => "France",
"DE" => "Germany",
"HK" => "Hong Kong",
"IN" => "India",
"ID" => "Indonesia",
"IT" => "Italy",
"JP" => "Japan",
"KR" => "Korea",
"MY" => "Malaysia",
"MX" => "Mexico",
"NL" => "Netherlands",
"NZ" => "New Zealand",
"NO" => "Norway",
"CN" => "People's Republic of China",
"PL" => "Poland",
"PT" => "Portugal",
"PH" => "Republic of the Philippines",
"RU" => "Russia",
"SA" => "Saudi Arabia",
"ZA" => "South Africa",
"ES" => "Spain",
"SE" => "Sweden",
"CH" => "Switzerland",
"TW" => "Taiwan",
"TR" => "Turkey",
"GB" => "United Kingdom",
"US" => "United States"
]
]
];
}
private function get($proxy, $url, $get = [], $country){
$curlproc = curl_init();
if($get !== []){
$get = http_build_query($get);
$url .= "?" . $get;
}
curl_setopt($curlproc, CURLOPT_URL, $url);
curl_setopt($curlproc, CURLOPT_ENCODING, ""); // default encoding
curl_setopt($curlproc, CURLOPT_HTTPHEADER,
["User-Agent: " . config::USER_AGENT,
"Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8",
"Accept-Language: en-US,en;q=0.5",
"Accept-Encoding: gzip",
"Referer: https://ghosterysearch.com",
"DNT: 1",
"Sec-GPC: 1",
"Connection: keep-alive",
"Cookie: ctry=" . ($country == "any" ? "--" : $country) . "; noads=true",
"Upgrade-Insecure-Requests: 1",
"Sec-Fetch-Dest: document",
"Sec-Fetch-Mode: navigate",
"Sec-Fetch-Site: same-origin",
"Sec-Fetch-User: ?1",
"Priority: u=0, i"]
);
// http2 bypass
curl_setopt($curlproc, CURLOPT_HTTP_VERSION, CURL_HTTP_VERSION_2_0);
curl_setopt($curlproc, CURLOPT_RETURNTRANSFER, true);
curl_setopt($curlproc, CURLOPT_SSL_VERIFYHOST, 2);
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 $data;
}
public function web($get){
if($get["npt"]){
[$query, $proxy] = $this->backend->get($get["npt"], "web");
parse_str($query, $query);
// country
$country = $query["c"];
unset($query["c"]);
$query = http_build_query($query);
try{
$html =
$this->get(
$proxy,
"https://ghosterysearch.com/search?" . $query,
[],
$country
);
}catch(Exception $error){
throw new Exception("Failed to fetch search page");
}
}else{
$proxy = $this->backend->get_ip();
try{
$html =
$this->get(
$proxy,
"https://ghosterysearch.com/search",
[
"q" => $get["s"]
],
$get["country"]
);
}catch(Exception $error){
throw new Exception("Failed to fetch search page");
}
}
$out = [
"status" => "ok",
"spelling" => [
"type" => "no_correction",
"using" => null,
"correction" => null
],
"npt" => null,
"answer" => [],
"web" => [],
"image" => [],
"video" => [],
"news" => [],
"related" => []
];
$this->fuckhtml->load($html);
$results_wrapper =
$this->fuckhtml
->getElementsByClassName(
"results",
"section"
);
if(count($results_wrapper) === 0){
throw new Exception("Failed to grep result section");
}
$this->fuckhtml->load($results_wrapper[0]);
// get search results
$results =
$this->fuckhtml
->getElementsByClassName(
"result",
"li"
);
if(count($results) === 0){
return $out;
}
foreach($results as $result){
$this->fuckhtml->load($result);
$a =
$this->fuckhtml
->getElementsByClassName(
"url",
"a"
);
if(count($a) === 0){
continue;
}
$a = $a[0];
$out["web"][] = [
"title" =>
$this->titledots(
$this->fuckhtml
->getTextContent(
$this->fuckhtml
->getElementsByTagName(
"h2"
)[0]
)
),
"description" =>
$this->titledots(
$this->fuckhtml
->getTextContent(
$this->fuckhtml
->getElementsByTagName(
"p"
)[0]
)
),
"url" =>
$this->fuckhtml
->getTextContent(
$a
["attributes"]
["href"]
),
"date" => null,
"type" => "web",
"thumb" => [
"url" => null,
"ratio" => null
],
"sublink" => [],
"table" => []
];
}
$this->fuckhtml->load($html);
// get pagination token
$pagination_wrapper =
$this->fuckhtml
->getElementsByClassName(
"pagination",
"div"
);
if(count($pagination_wrapper) !== 0){
// found next page!
$this->fuckhtml->load($pagination_wrapper[0]);
$a =
$this->fuckhtml
->getElementsByTagName(
"a"
);
if(count($a) !== 0){
$q =
parse_url(
$this->fuckhtml
->getTextContent(
$a[count($a) - 1]
["attributes"]
["href"]
),
PHP_URL_QUERY
);
$out["npt"] =
$this->backend
->store(
$q . "&c=" . $get["country"],
"web",
$proxy
);
}
}
return $out;
}
private function titledots($title){
return trim($title, " .\t\n\r\0\x0B…");
}
}

4313
scraper/google.php
View File

File diff suppressed because it is too large Load Diff

1054
scraper/google_cse.php
View File

File diff suppressed because it is too large Load Diff

20
scraper/greppr.php
View File

@ -298,8 +298,9 @@ class greppr{
$description =
$this->fuckhtml
->getElementsByClassName(
"highlightedDesc",
->getElementsByFuzzyAttributeValue(
"style",
"color:#777777;",
"p"
);
@ -309,11 +310,9 @@ class greppr{
}else{
$description =
$this->limitstrlen(
$this->fuckhtml
->getTextContent(
$description[0]
)
$this->fuckhtml
->getTextContent(
$description[0]
);
}
@ -326,7 +325,7 @@ class greppr{
$date =
strtotime(
explode(
":",
"Added:",
$this->fuckhtml
->getTextContent(
$date[count($date) - 1]["innerHTML"]
@ -427,9 +426,4 @@ class greppr{
return $tokens;
}
private function limitstrlen($text){
return explode("\n", wordwrap($text, 300, "\n"))[0];
}
}

127
scraper/marginalia.php
View File

@ -220,14 +220,13 @@ class marginalia{
"related" => []
];
// API scraper
if(config::MARGINALIA_API_KEY !== null){
try{
$json =
$this->get(
$this->backend->get_ip(), // no nextpage
"https://api.marginalia-search.com/" . config::MARGINALIA_API_KEY . "/search/" . urlencode($search),
"https://api.marginalia.nu/" . config::MARGINALIA_API_KEY . "/search/" . urlencode($search),
[
"count" => 20
]
@ -264,57 +263,34 @@ class marginalia{
return $out;
}
// HTML parser
$proxy = $this->backend->get_ip();
// no more cloudflare!! Parse html by default
$params = [
"query" => $search
];
if($get["npt"]){
foreach(["adtech", "recent", "intitle"] as $v){
[$params, $proxy] =
$this->backend->get(
$get["npt"],
"web"
);
try{
$html =
$this->get(
$proxy,
"https://old-search.marginalia.nu/search?" . $params
);
}catch(Exception $error){
if($get[$v] == "yes"){
throw new Exception("Failed to get HTML");
}
}else{
$params = [
"query" => $search
];
foreach(["adtech", "recent", "intitle"] as $v){
if($get[$v] == "yes"){
switch($v){
switch($v){
case "adtech": $params["adtech"] = "reduce"; break;
case "recent": $params["recent"] = "recent"; break;
case "adtech": $params["searchTitle"] = "title"; break;
}
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){
try{
$html =
$this->get(
$proxy,
"https://old-search.marginalia.nu/search",
$params
);
}catch(Exception $error){
throw new Exception("Failed to get HTML");
}
throw new Exception("Failed to get HTML");
}
$this->fuckhtml->load($html);
@ -411,65 +387,6 @@ 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;
}
}

8
scraper/mojeek.php
View File

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

76
scraper/mwmbl.php
View File

@ -27,24 +27,18 @@ class mwmbl{
curl_setopt($curlproc, CURLOPT_URL, $url);
// use http2
curl_setopt($curlproc, CURLOPT_HTTP_VERSION, CURL_HTTP_VERSION_2_0);
curl_setopt($curlproc, CURLOPT_ENCODING, ""); // default encoding
curl_setopt($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",
"Referer: https://beta.mwmbl.org/",
"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",
"Priority: u=0, i",
"Sec-Fetch-Site: none",
"Sec-Fetch-User: ?1"]
);
@ -78,14 +72,14 @@ class mwmbl{
try{
$html = $this->get(
$this->backend->get_ip(), // no next page!
"https://beta.mwmbl.org/",
"https://mwmbl.org/app/home/",
[
"q" => $search
]
);
}catch(Exception $error){
throw new Exception("Failed to fetch HTML. If you're getting a timeout, make sure you have curl-impersonate setup.");
throw new Exception("Failed to fetch HTML");
}
$out = [
@ -121,68 +115,6 @@ class mwmbl{
$this->fuckhtml
->getElementsByTagName("p");
$sublinks = [];
$mores =
$this->fuckhtml
->getElementsByClassName(
"result-link-more",
"div"
);
foreach($mores as $more){
$this->fuckhtml->load($more);
$as =
$this->fuckhtml
->getElementsByClassName(
"more",
"a"
);
if(count($as) === 0){
// ?? invalid
continue;
}
$sublinks[] = [
"title" =>
$this->titledots(
$this->fuckhtml
->getTextContent(
$this->fuckhtml
->getElementsByClassName(
"more-title",
"span"
)[0]
)
),
"description" =>
$this->titledots(
$this->fuckhtml
->getTextContent(
$this->fuckhtml
->getElementsByClassName(
"more-extract",
"span"
)[0]
)
),
"url" =>
$this->fuckhtml
->getTextContent(
$as[0]
["attributes"]
["href"]
)
];
}
// reset
$this->fuckhtml->load($result);
$out["web"][] = [
"title" =>
$this->titledots(
@ -221,7 +153,7 @@ class mwmbl{
"url" => null,
"ratio" => null
],
"sublink" => $sublinks,
"sublink" => [],
"table" => []
];
}

403
scraper/pinterest.php
View File

@ -13,104 +13,31 @@ class pinterest{
return [];
}
private function get($proxy, $url, $get = [], &$cookies, $header_data_post = null){
private function get($url, $get = []){
$curlproc = curl_init();
if($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 .= "?" . $get;
}
}else{
// handling POST (pagination)
if($get !== []){
$get = http_build_query($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);
$url .= "?" . $get;
}
curl_setopt($curlproc, CURLOPT_URL, $url);
curl_setopt($curlproc, CURLOPT_ENCODING, ""); // default encoding
// http2 bypass
curl_setopt($curlproc, CURLOPT_HTTP_VERSION, CURL_HTTP_VERSION_2_0);
curl_setopt($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"]
);
curl_setopt($curlproc, CURLOPT_RETURNTRANSFER, true);
curl_setopt($curlproc, CURLOPT_SSL_VERIFYHOST, 2);
@ -118,7 +45,7 @@ class pinterest{
curl_setopt($curlproc, CURLOPT_CONNECTTIMEOUT, 30);
curl_setopt($curlproc, CURLOPT_TIMEOUT, 30);
$this->backend->assign_proxy($curlproc, $proxy);
$this->proxy->assign_proxy($curlproc);
$data = curl_exec($curlproc);
@ -127,175 +54,13 @@ 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 $data;
}
public function image($get){
if($get["npt"]){
[$data, $proxy] =
$this->backend->get(
$get["npt"], "images"
);
$data = json_decode($data, true);
$search = $data["q"];
$cookies = $data["cookies"];
try{
$json =
$this->get(
$proxy,
"https://ca.pinterest.com/resource/BaseSearchResource/get/",
[
"source_url" => "/search/pins/?q=" . urlencode($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{
$search = $get["s"];
if(strlen($search) === 0){
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" => $source_url,
"rs" => "typed",
"data" =>
json_encode(
[
"options" => [
"applied_unified_filters" => null,
"appliedProductFilters" => "---",
"article" => null,
"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" => $search,
"redux_normalize_feed" => true,
"request_params" => null,
"rs" => "ac",
"scope" => "pins", // pins, boards, videos,
"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" => []
]
),
"_" => substr(str_replace(".", "", (string)microtime(true)), 0, -1)
];
$proxy = $this->backend->get_ip();
$cookies = [];
try{
$json =
$this->get(
$proxy,
"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");
}
$search = $get["s"];
$out = [
"status" => "ok",
@ -303,60 +68,55 @@ class pinterest{
"image" => []
];
if(
!isset(
$json["resource_response"]
["status"]
)
){
throw new Exception("Unknown API failure");
}
$filter = [
"source_url" => "/search/pins/?q=" . urlencode($search),
"rs" => "typed",
"data" =>
json_encode(
[
"options" => [
"article" => null,
"applied_filters" => null,
"appliedProductFilters" => "---",
"auto_correction_disabled" => false,
"corpus" => null,
"customized_rerank_type" => null,
"filters" => null,
"query" => $search,
"query_pin_sigs" => null,
"redux_normalize_feed" => true,
"rs" => "typed",
"scope" => "pins", // pins, boards, videos,
"source_id" => null
],
"context" => []
]
),
"_" => substr(str_replace(".", "", (string)microtime(true)), 0, -1)
];
if($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
try{
$json =
json_decode(
$this->get(
"https://www.pinterest.ca/resource/BaseSearchResource/get/",
$filter
),
true
);
}catch(Exception $error){
throw new Exception("Failed to fetch JSON");
}
if($json === null){
throw new Exception("Failed to decode JSON");
}
//print_r($json);
foreach(
$json
["resource_response"]
@ -368,7 +128,6 @@ class pinterest{
switch($item["type"]){
case "pin":
case "board":
/*
Handle image object
@ -425,15 +184,43 @@ class pinterest{
"height" => (int)$thumb["height"]
]
],
"url" =>
$item["link"] === null ?
"https://ca.pinterest.com/pin/" . $item["id"] :
$item["link"]
"url" => "https://www.pinterest.com/pin/" . $item["id"]
];
break;
case "board":
if(isset($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
);
}
}

62
scraper/qwant.php
View File

@ -353,17 +353,26 @@ class qwant{
"related" => []
];
if(
$json["status"] != "success" &&
$json["data"]["error_code"] === 5
){
if($json["status"] != "success"){
// no results
return $out;
if($json["data"]["error_code"] === 5){
return $out;
}
if(isset($json["data"]["error_code"])){
switch($json["data"]["error_code"]){
case 27:
throw new Exception("Qwant returned a captcha");
break;
}
}
throw new Exception("Qwant returned an error code: " . $json["data"]["error_code"]);
}
$this->detect_errors($json);
if(!isset($json["data"]["result"]["items"]["mainline"])){
throw new Exception("Server did not return a result object");
@ -645,7 +654,10 @@ class qwant{
throw new Exception("Failed to decode JSON");
}
$this->detect_errors($json);
if($json["status"] != "success"){
throw new Exception("Qwant returned an API error");
}
if(isset($json["data"]["result"]["items"]["mainline"])){
@ -742,7 +754,10 @@ class qwant{
throw new Exception("Could not parse JSON");
}
$this->detect_errors($json);
if($json["status"] != "success"){
throw new Exception("Qwant returned an API error");
}
if(isset($json["data"]["result"]["items"]["mainline"])){
@ -846,7 +861,10 @@ class qwant{
throw new Exception("Could not parse JSON");
}
$this->detect_errors($json);
if($json["status"] != "success"){
throw new Exception("Qwant returned an API error");
}
if(isset($json["data"]["result"]["items"]["mainline"])){
@ -888,28 +906,6 @@ class qwant{
return $out;
}
private function detect_errors($json){
if(
isset($json["status"]) &&
$json["status"] == "error"
){
if(isset($json["data"]["error_data"]["captchaUrl"])){
throw new Exception("Qwant returned a captcha");
}elseif(isset($json["data"]["error_data"]["error_code"])){
throw new Exception(
"Qwant returned an API error: " .
$json["data"]["error_data"]["error_code"]
);
}
throw new Exception("Qwant returned an API error");
}
}
private function limitstrlen($text){
return explode("\n", wordwrap($text, 300, "\n"))[0];

110
scraper/sc.php
View File

@ -6,9 +6,6 @@ class sc{
include "lib/backend.php";
$this->backend = new backend("sc");
include "lib/fuckhtml.php";
$this->fuckhtml = new fuckhtml();
}
public function getfilters($page){
@ -28,7 +25,7 @@ class sc{
];
}
private function get($proxy, $url, $get = [], $web_req = false){
private function get($proxy, $url, $get = []){
$curlproc = curl_init();
@ -40,43 +37,19 @@ class sc{
curl_setopt($curlproc, CURLOPT_URL, $url);
curl_setopt($curlproc, CURLOPT_ENCODING, ""); // default encoding
// use http2
curl_setopt($curlproc, CURLOPT_HTTP_VERSION, CURL_HTTP_VERSION_2_0);
if($web_req === false){
curl_setopt($curlproc, CURLOPT_HTTPHEADER,
["User-Agent: " . config::USER_AGENT,
"Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8",
"Accept-Language: en-US,en;q=0.5",
"Accept-Encoding: gzip",
"Referer: https://soundcloud.com/",
"Origin: https://soundcloud.com",
"DNT: 1",
"Connection: keep-alive",
"Sec-Fetch-Dest: empty",
"Sec-Fetch-Mode: cors",
"Sec-Fetch-Site: same-site",
"Priority: u=1"]
);
}else{
curl_setopt($curlproc, CURLOPT_HTTPHEADER,
["User-Agent: " . config::USER_AGENT,
"Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8",
"Accept-Language: en-US,en;q=0.5",
"Accept-Encoding: gzip",
"DNT: 1",
"Connection: keep-alive",
"Upgrade-Insecure-Requests: 1",
"Sec-Fetch-Dest: document",
"Sec-Fetch-Mode: navigate",
"Sec-Fetch-Site: cross-site",
"Priority: u=1",
"TE: trailers"]
);
}
curl_setopt($curlproc, CURLOPT_HTTPHEADER,
["User-Agent: " . config::USER_AGENT,
"Accept: application/json, text/javascript, */*; q=0.01",
"Accept-Language: en-US,en;q=0.5",
"Accept-Encoding: gzip",
"Referer: https://soundcloud.com/",
"Origin: https://soundcloud.com",
"DNT: 1",
"Connection: keep-alive",
"Sec-Fetch-Dest: empty",
"Sec-Fetch-Mode: cors",
"Sec-Fetch-Site: same-site"]
);
curl_setopt($curlproc, CURLOPT_RETURNTRANSFER, true);
curl_setopt($curlproc, CURLOPT_SSL_VERIFYHOST, 2);
@ -327,12 +300,9 @@ class sc{
$description[] = $song["title"];
}
if(count($description) !== 0){
if(count($description) != 0){
$description = trim($count . " songs. " . implode(", ", $description));
}else{
$description = "";
}
if(
@ -426,48 +396,13 @@ class sc{
$token = apcu_fetch("sc_token");
if($token !== false){
return $token;
}
// search through all javascript components on the main page
try{
$html =
$this->get(
$proxy,
"https://soundcloud.com",
[],
true
);
}catch(Exception $error){
throw new Exception("Failed to fetch front page");
}
$this->fuckhtml->load($html);
$scripts =
$this->fuckhtml
->getElementsByTagName(
"script"
);
foreach($scripts as $script){
if(
!isset($script["attributes"]["src"]) ||
strpos($script["attributes"]["src"], "sndcdn.com") === false
){
continue;
}
if($token === false){
try{
$js =
$this->get(
$proxy,
$script["attributes"]["src"],
"https://a-v2.sndcdn.com/assets/0-a901c1e0.js",
[]
);
}catch(Exception $error){
@ -481,15 +416,16 @@ class sc{
$token
);
if(isset($token[1])){
if(!isset($token[1])){
apcu_store("sc_token", $token[1]);
return $token[1];
break;
throw new Exception("Failed to get search token");
}
apcu_store("sc_token", $token[1]);
return $token[1];
}
throw new Exception("Did not find a Soundcloud token in the Javascript blobs");
return $token;
}
private function limitstrlen($text){

668
scraper/solofield.php
View File

@ -1,668 +0,0 @@
<?php
class solofield{
public function __construct(){
include "lib/backend.php";
$this->backend = new backend("solofield");
include "lib/fuckhtml.php";
$this->fuckhtml = new fuckhtml();
}
public function getfilters($page){
return [
"nsfw" => [
"display" => "NSFW",
"option" => [
"yes" => "Yes",
"no" => "No",
]
]
];
}
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($curlproc, CURLOPT_HTTPHEADER,
["User-Agent: " . config::USER_AGENT,
"Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8",
"Accept-Language: en-US,en;q=0.5",
"Accept-Encoding: gzip",
"Referer: https://solofield.net",
"DNT: 1",
"Connection: keep-alive",
"Cookie: cross-site-cookie=name; lno=35842050",
"Upgrade-Insecure-Requests: 1",
"Sec-Fetch-Dest: document",
"Sec-Fetch-Mode: navigate",
"Sec-Fetch-Site: same-origin",
"Sec-Fetch-User: ?1"]
);
curl_setopt($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 $data;
}
public function web($get){
if($get["npt"]){
[$query, $proxy] = $this->backend->get($get["npt"], "web");
try{
$html =
$this->get(
$proxy,
"https://solofield.net/search?" . $query,
[]
);
}catch(Exception $error){
throw new Exception("Failed to fetch search page");
}
}else{
$proxy = $this->backend->get_ip();
try{
$html =
$this->get(
$proxy,
"https://solofield.net/search",
[
"q" => $get["s"],
"ie" => "UTF-8",
"oe" => "UTF-8",
"hl" => "ja", // changing this doesnt do anything
"lr" => "lang_ja", // same here
//"ls" => "", // ??
"f" => ($get["nsfw"] == "yes" ? "off" : "on")
]
);
}catch(Exception $error){
throw new Exception("Failed to fetch search page");
}
}
$out = [
"status" => "ok",
"spelling" => [
"type" => "no_correction",
"using" => null,
"correction" => null
],
"npt" => null,
"answer" => [],
"web" => [],
"image" => [],
"video" => [],
"news" => [],
"related" => []
];
// check for errors and load the result div
if($this->error_and_load($html)){
return $out;
}
$items =
$this->fuckhtml
->getElementsByClassName(
"g0",
"li"
);
foreach($items as $item){
$this->fuckhtml->load($item);
$title_tag =
$this->fuckhtml
->getElementsByClassName(
"r",
"h3"
);
if(count($title_tag) === 0){
continue;
}
$this->fuckhtml->load($title_tag[0]);
$link =
$this->fuckhtml
->getTextContent(
$this->fuckhtml
->getElementsByTagName(
"a"
)[0]
["attributes"]
["href"]
);
$this->fuckhtml->load($item);
$thumb =
$this->fuckhtml
->getElementsByClassName(
"webshot",
"img"
);
if(count($thumb) !== 0){
$uri =
$this->fuckhtml
->getTextContent(
$thumb[0]
["attributes"]
["src"]
);
if(stripos($uri, "now_printing") === false){
$thumb = [
"ratio" => "1:1",
"url" =>
"https://solofield.net" .
$this->fuckhtml
->getTextContent(
$thumb[0]
["attributes"]
["src"]
)
];
}else{
$thumb = [
"ratio" => null,
"url" => null
];
}
}else{
$thumb = [
"ratio" => null,
"url" => null
];
}
$out["web"][] = [
"title" =>
$this->fuckhtml
->getTextContent(
$title_tag[0]
),
"description" =>
$this->fuckhtml
->getTextContent(
$this->fuckhtml
->getElementsByClassName(
"s",
"div"
)[0]
),
"url" => $link,
"date" => null,
"type" => "web",
"thumb" => $thumb,
"sublink" => [],
"table" => []
];
}
// get next page
$this->get_npt($html, $proxy, $out, "web");
return $out;
}
public function image($get){
// no pagination
$html =
$this->get(
$this->backend->get_ip(),
"https://solofield.net/isearch",
[
"q" => $get["s"],
"ie" => "UTF-8",
"oe" => "UTF-8",
"hl" => "ja", // changing this doesnt do anything
//"lr" => "lang_ja", // same here
"ls" => "", // ??
"f" => ($get["nsfw"] == "yes" ? "off" : "on")
]
);
$out = [
"status" => "ok",
"npt" => null,
"image" => []
];
// check for errors and load the result div
if($this->error_and_load($html)){
return $out;
}
$images =
$this->fuckhtml
->getElementsByTagName(
"li"
);
foreach($images as $image){
$this->fuckhtml->load($image);
$img =
$this->fuckhtml
->getElementsByTagName(
"img"
);
if(count($img) === 0){
// ?? invalid
continue;
}
$img = $img[0];
$size =
explode(
"x",
$this->fuckhtml
->getTextContent(
$image
),
2
);
$size = [
(int)trim($size[0]), // width
(int)trim($size[1]) // height
];
$out["image"][] = [
"title" => null,
"source" => [
[
"url" =>
"https://solofield.net/" .
$this->fuckhtml
->getTextContent(
$img["attributes"]["src"]
),
"width" => $size[0],
"height" => $size[1]
]
],
"url" =>
$this->fuckhtml
->getTextContent(
$this->fuckhtml
->getElementsByTagName(
"a"
)[0]
["attributes"]
["href"]
)
];
}
return $out;
}
public function video($get){
if($get["npt"]){
[$query, $proxy] = $this->backend->get($get["npt"], "videos");
try{
$html =
$this->get(
$proxy,
"https://solofield.net/vsearch?" . $query,
[]
);
}catch(Exception $error){
throw new Exception("Failed to fetch search page");
}
}else{
$proxy = $this->backend->get_ip();
try{
$html =
$this->get(
$proxy,
"https://solofield.net/vsearch",
[
"q" => $get["s"],
"ie" => "UTF-8",
"oe" => "UTF-8",
"hl" => "ja", // changing this doesnt do anything
//"lr" => "lang_ja", // same here
"ls" => "", // ??
"f" => ($get["nsfw"] == "yes" ? "off" : "on")
]
);
}catch(Exception $error){
throw new Exception("Failed to fetch search page");
}
}
$out = [
"status" => "ok",
"npt" => null,
"video" => [],
"author" => [],
"livestream" => [],
"playlist" => [],
"reel" => []
];
// check for errors and load the result div
if($this->error_and_load($html)){
return $out;
}
$items =
$this->fuckhtml
->getElementsByTagName(
"li"
);
foreach($items as $item){
$this->fuckhtml->load($item);
$as =
$this->fuckhtml
->getElementsByTagName(
"a"
);
if(count($as) === 0){
continue;
}
$thumb =
$this->fuckhtml
->getElementsByTagName(
"img"
);
if(count($thumb) !== 0){
$thumb = [
"ratio" => "16:9",
"url" =>
"https://solofield.net/" .
$thumb[0]
["attributes"]
["src"]
];
}else{
$thumb = [
"ratio" => null,
"url" => null
];
}
$date =
$this->fuckhtml
->getElementsByAttributeValue(
"style",
"font-size: 10px;",
"span"
);
if(count($date) !== 0){
$date =
$this->unfuckdate(
$this->fuckhtml
->getTextContent(
$date[0]
)
);
}else{
$date = null;
}
$center_td =
$this->fuckhtml
->getElementsByAttributeValue(
"align",
"center",
"td"
);
if(count($center_td) === 2){
$duration =
$this->fuckhtml
->getTextContent(
$this->hms2int(
$center_td[0]
)
);
}else{
$duration = null;
}
$out["video"][] = [
"title" =>
$this->fuckhtml
->getTextContent(
$as[1]
),
"description" => null,
"author" => [
"name" => null,
"url" => null,
"avatar" => null
],
"date" => $date,
"duration" => $duration,
"views" => null,
"thumb" => $thumb,
"url" =>
$this->fuckhtml
->getTextContent(
$as[0]
["attributes"]
["href"]
)
];
}
// get next page
$this->get_npt($html, $proxy, $out, "videos");
return $out;
}
private function get_npt($html, $proxy, &$out, $type){
// get next page
$this->fuckhtml->load($html);
$pjs =
$this->fuckhtml
->getElementById(
"pjs"
);
if($pjs){
$alnk =
$this->fuckhtml
->getElementsByClassName(
"alnk",
"span"
);
foreach($alnk as $lnk){
if(
stripos(
$this->fuckhtml
->getTextContent(
$lnk
),
"Next"
) !== false
){
$this->fuckhtml->load($lnk);
$out["npt"] =
$this->backend->store(
parse_url(
$this->fuckhtml
->getElementsByTagName(
"a"
)[0]
["attributes"]
["href"],
PHP_URL_QUERY
),
$type,
$proxy
);
}
}
}
}
private function error_and_load($html){
if(strlen($html) === 0){
throw new Exception("Solofield blocked the request IP");
}
$this->fuckhtml->load($html);
$list =
$this->fuckhtml
->getElementById(
"list",
"div"
);
if($list === false){
$nosearch =
$this->fuckhtml
->getElementById(
"nosearch",
"div"
);
if($nosearch){
return true;
}
throw new Exception("Failed to grep search list");
}
$this->fuckhtml->load($list);
return false;
}
private function unfuckdate($date){
return
strtotime(
rtrim(
preg_replace(
'/[^0-9]+/',
"-",
explode(
":",
$date,
2
)[1]
),
"-"
)
);
}
private function hms2int($time){
$parts = explode(":", $time, 3);
$time = 0;
if(count($parts) === 3){
// hours
$time = $time + ((int)$parts[0] * 3600);
array_shift($parts);
}
if(count($parts) === 2){
// minutes
$time = $time + ((int)$parts[0] * 60);
array_shift($parts);
}
// seconds
$time = $time + (int)$parts[0];
return $time;
}
}

1579
scraper/startpage.php
View File

File diff suppressed because it is too large Load Diff

257
scraper/vsco.php
View File

@ -1,257 +0,0 @@
<?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)
];
}
}

14
scraper/yandex.php
View File

@ -37,7 +37,7 @@ class yandex{
"Accept-Encoding: gzip",
"Accept-Language: en-US,en;q=0.5",
"DNT: 1",
"Cookie: yp=" . (time() - 4000033) . ".szm.1:1920x1080:876x1000#" . time() . ".sp.family:" . $nsfw,
"Cookie: yp=1716337604.sp.family%3A{$nsfw}#1685406411.szm.1:1920x1080:1920x999",
"Referer: https://yandex.com/images/search",
"Connection: keep-alive",
"Upgrade-Insecure-Requests: 1",
@ -668,6 +668,7 @@ class yandex{
foreach($json["blocks"] as $block){
$html .= $block["html"];
// get next page
if(
isset($block["params"]["nextPageUrl"]) &&
@ -750,13 +751,6 @@ class yandex{
"url" => htmlspecialchars_decode($image["snippet"]["url"])
];
// add preview URL
$tmp["source"][] = [
"url" => htmlspecialchars_decode($image["viewerData"]["preview"][0]["url"]),
"width" => (int)$image["viewerData"]["preview"][0]["w"],
"height" => (int)$image["viewerData"]["preview"][0]["h"],
];
foreach($image["viewerData"]["dups"] as $dup){
$tmp["source"][] = [
@ -773,8 +767,8 @@ class yandex{
"https://",
htmlspecialchars_decode($image["viewerData"]["thumb"]["url"])
),
"width" => (int)$image["viewerData"]["thumb"]["w"],
"height" => (int)$image["viewerData"]["thumb"]["h"]
"width" => (int)$image["viewerData"]["thumb"]["size"]["width"],
"height" => (int)$image["viewerData"]["thumb"]["size"]["height"]
];
$out["image"][] = $tmp;

17
scraper/yep.php
View File

@ -252,30 +252,21 @@ class yep{
curl_setopt($curlproc, CURLOPT_URL, $url);
// use http2
curl_setopt($curlproc, CURLOPT_HTTP_VERSION, CURL_HTTP_VERSION_2_0);
// set ciphers
curl_setopt(
$curlproc,
CURLOPT_SSL_CIPHER_LIST,
"aes_128_gcm_sha_256,chacha20_poly1305_sha_256,aes_256_gcm_sha_384,ecdhe_ecdsa_aes_128_gcm_sha_256,ecdhe_rsa_aes_128_gcm_sha_256,ecdhe_ecdsa_chacha20_poly1305_sha_256,ecdhe_rsa_chacha20_poly1305_sha_256,ecdhe_ecdsa_aes_256_gcm_sha_384,ecdhe_rsa_aes_256_gcm_sha_384,ecdhe_ecdsa_aes_256_sha,ecdhe_ecdsa_aes_128_sha,ecdhe_rsa_aes_128_sha,ecdhe_rsa_aes_256_sha,rsa_aes_128_gcm_sha_256,rsa_aes_256_gcm_sha_384,rsa_aes_128_sha,rsa_aes_256_sha"
);
curl_setopt($curlproc, CURLOPT_ENCODING, ""); // default encoding
curl_setopt($curlproc, CURLOPT_HTTPHEADER,
["User-Agent: " . config::USER_AGENT,
"Accept: */*",
"Accept-Language: en-US,en;q=0.5",
"Accept-Encoding: gzip, deflate, br, zstd",
"Referer: https://yep.com/",
"Origin: https://yep.com",
"Connection: keep-alive",
"DNT: 1",
"Priority: u=1",
"Origin: https://yep.com",
"Referer: https://yep.com/",
"Connection: keep-alive",
"Sec-Fetch-Dest: empty",
"Sec-Fetch-Mode: cors",
"Sec-Fetch-Site: same-site",
"Priority: u=4",
"TE: trailers"]
);

27
scraper/yt.php
View File

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

64
settings.php
View File

@ -79,22 +79,10 @@ $settings = [
"value" => "google",
"text" => "Google"
],
[
"value" => "startpage",
"text" => "Startpage"
],
[
"value" => "kagi",
"text" => "Kagi"
],
[
"value" => "qwant",
"text" => "Qwant"
],
[
"value" => "ghostery",
"text" => "Ghostery"
],
[
"value" => "yep",
"text" => "Yep"
@ -133,22 +121,10 @@ $settings = [
"value" => "google",
"text" => "Google"
],
[
"value" => "google_cse",
"text" => "Google CSE"
],
[
"value" => "startpage",
"text" => "Startpage"
],
[
"value" => "qwant",
"text" => "Qwant"
],
[
"value" => "ghostery",
"text" => "Ghostery"
],
[
"value" => "yep",
"text" => "Yep"
@ -169,10 +145,6 @@ $settings = [
"value" => "mojeek",
"text" => "Mojeek"
],
[
"value" => "solofield",
"text" => "Solofield"
],
[
"value" => "marginalia",
"text" => "Marginalia"
@ -207,14 +179,6 @@ $settings = [
"value" => "google",
"text" => "Google"
],
[
"value" => "google_cse",
"text" => "Google CSE"
],
[
"value" => "startpage",
"text" => "Startpage"
],
[
"value" => "qwant",
"text" => "Qwant"
@ -223,22 +187,10 @@ $settings = [
"value" => "yep",
"text" => "Yep"
],
[
"value" => "solofield",
"text" => "Solofield"
],
[
/*[
"value" => "pinterest",
"text" => "Pinterest"
],
[
"value" => "fivehpx",
"text" => "500px"
],
[
"value" => "vsco",
"text" => "VSCO"
],
],*/
[
"value" => "imgur",
"text" => "Imgur"
@ -273,18 +225,10 @@ $settings = [
"value" => "google",
"text" => "Google"
],
[
"value" => "startpage",
"text" => "Startpage"
],
[
"value" => "qwant",
"text" => "Qwant"
],
[
"value" => "solofield",
"text" => "Solofield"
]
]
],
[
@ -303,10 +247,6 @@ $settings = [
"value" => "google",
"text" => "Google"
],
[
"value" => "startpage",
"text" => "Startpage"
],
[
"value" => "qwant",
"text" => "Qwant"

4
static/style.css
View File

@ -794,10 +794,6 @@ table tr a:last-child{
background:var(--1d2021);
}
.web .wiki-head table td{
white-space:pre-line;
}
.web .wiki-head td, .about table td{
padding:4px 7px;
vertical-align:middle;

118
static/themes/Gore's shitty theme.css
View File

@ -1,45 +1,47 @@
: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;
@ -94,6 +96,7 @@ h3, h4, h5, h6{
display:inline-block;
}
.tabs .tab.selected{
border-bottom:2px solid #fc92a5;
}
@ -103,7 +106,7 @@ h3, h4, h5, h6{
padding-bottom:12px;
padding-top:7px;
margin-bottom:7px;
background-color:#232525;
background-color:#232525
}
.filters .filter{
@ -166,6 +169,7 @@ h3, h4, h5, h6{
font-size:12px;
}
.web .hover{
display:block;
text-decoration:none;
@ -189,13 +193,16 @@ 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;
@ -204,33 +211,39 @@ 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{
@ -244,14 +257,17 @@ 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;
@ -264,59 +280,43 @@ 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 design
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%; } }
@media only screen and (max-width:1550px){
.web .left,
/*
Responsive design
*/
@media only screen and (max-width: 1550px){
.web .left,
.searchbox{
width:60%;
}
}
@media only screen and (max-width:1100px){
.web .left,
.searchbox{
width:100%;
}
@media only screen and (max-width: 1000px){
}
.type{
color:var(--bdae93);
.type{
color:var(--bdae93);
}
}

40
static/themes/Wine.css
View File

@ -1,40 +0,0 @@
: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); }

20
template/donate.html
View File

@ -1,20 +0,0 @@
<a href="/" class="link">&lt; Go back</a>
<h1>Donate to the project</h1>
This project takes up most of my free time and costs money to run. If you feel like this project is worthy of a donation, please do so using the resources on this page!<br><br>
To run smoothly, 4get requires 20$/month for the server fees and 15-25$ for residential proxies. I also have plans to build my own index to provide better search results; funds raised here will go directly towards better hardware for these purposes. According to the number of captchas solved, <a href="https://4get.ca">4get.ca</a> serves between 800-1400 users every day, or around 7000-10000 searches!
<h2>Ko-fi</h2>
This is the most convenient way to donate. Supports PayPal.
<ul>
<li><a href="https://ko-fi.com/lolcat">ko-fi.com/lolcat</a></li>
</ul>
<h2>Monero</h2>
Due to popular demand, I have added an XMR addy. I'm planning to reward users who donate to me once paid tiers are introduced to 4get, so please let me know through email that you donated to me (don't forget your transaction ID)!
<ul>
<li><a href="monero:85G95fXXfuh72oQd9LmdMHNqDTqsUPKkLCBEYE7XnnMLPvBfkdnan2FVTmVAwT4JEuXsRL7xPgqzuV2YdbFkWmxK2FgGBmB?tx_description=4get+donation">85G95fXXfuh72oQd9LmdMHNqDTqsUPKkLCBEYE7XnnMLPvBfkdnan2FVTmVAwT4JEuXsRL7xPgqzuV2YdbFkWmxK2FgGBmB</a></li>
</ul>
Thank you all for your generous support!!

3
template/home.html
View File

@ -28,8 +28,7 @@
<div class="autocomplete"></div>
</div>
</form>
<a href="settings">Settings</a> • <a href="instances">Instances</a> • <a href="https://git.lolcat.ca/lolcat/4get_news">News</a> • <a href="api.txt">API</a> • <a href="about">About</a> • <a href="https://git.lolcat.ca/lolcat/4get">Source</a><br>
<a href="/donate"><b>Donate to the project</b></a>
<a href="settings">Settings</a> • <a href="instances">Instances</a> • <a href="https://git.lolcat.ca/lolcat/4get_news">News</a> • <a href="api.txt">API</a> • <a href="about">About</a> • <a href="https://git.lolcat.ca/lolcat/4get">Source</a> • <a href="https://ko-fi.com/lolcat" rel="noreferrer" target="BLANK">Donate</a>
<div class="subtext">
<a href="https://4get.ca">Clearnet</a> • <a href="http://4getwebfrq5zr4sxugk6htxvawqehxtdgjrbcn2oslllcol2vepa23yd.onion">Tor</a> • <a href="https://lolcat.ca">Report a problem</a><br>
Running on <b>v{%version%}</b>!!