Skip to content

Add ChatGPT Support #97

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
donatj merged 3 commits into from
Aug 28, 2024
Merged

Add ChatGPT Support #97

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9cd7ded
Add ChatGPT Support
donatj Aug 28, 2024
b0ffbe4
Make webkit logic a little safer
donatj Aug 28, 2024
8781e03
Add support for all ChatGPT crawlers
donatj Aug 28, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions src/UserAgent/Browsers.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@ interface Browsers {
const BROWSER = 'Browser';
const BUNJALLOO = 'Bunjalloo';
const CAMINO = 'Camino';
const CHATGPT_USER = 'ChatGPT-User';
const CHROME = 'Chrome';
const CURL = 'curl';
const EDGE = 'Edge';
Expand All @@ -24,6 +25,7 @@ interface Browsers {
const GOOGLEBOT = 'Googlebot';
const GOOGLEBOT_IMAGE = 'Googlebot-Image';
const GOOGLEBOT_VIDEO = 'Googlebot-Video';
const GPTBOT = 'GPTBot';
const HEADLESSCHROME = 'HeadlessChrome';
const IEMOBILE = 'IEMobile';
const IMESSAGEBOT = 'iMessageBot';
Expand All @@ -35,6 +37,7 @@ interface Browsers {
const MSNBOT_MEDIA = 'msnbot-media';
const NETFRONT = 'NetFront';
const NINTENDOBROWSER = 'NintendoBrowser';
const OAI_SEARCHBOT = 'OAI-SearchBot';
const OCULUSBROWSER = 'OculusBrowser';
const OPERA = 'Opera';
const PUFFIN = 'Puffin';
Expand Down
26 changes: 16 additions & 10 deletions src/UserAgentParser.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -90,7 +90,7 @@ function parse_user_agent( $u_agent = null ) {
} elseif( $platform == 'Adr' ) {
$platform = 'Android';
} elseif( $platform === null ) {
if(preg_match_all('%(?P<platform>Android)[:/ ]%ix', $u_agent, $result)) {
if( preg_match_all('%(?P<platform>Android)[:/ ]%ix', $u_agent, $result) ) {
$platform = $result[PLATFORM][0];
}
}
Expand All @@ -99,11 +99,12 @@ function parse_user_agent( $u_agent = null ) {
%(?P<browser>Camino|Kindle(\ Fire)?|Firefox|Iceweasel|IceCat|Safari|MSIE|Trident|AppleWebKit|
TizenBrowser|(?:Headless)?Chrome|YaBrowser|Vivaldi|IEMobile|Opera|OPR|Silk|Midori|(?-i:Edge)|EdgA?|CriOS|UCBrowser|Puffin|
OculusBrowser|SamsungBrowser|SailfishBrowser|XiaoMi/MiuiBrowser|YaApp_Android|
Baiduspider|Applebot|Facebot|Googlebot|YandexBot|bingbot|Lynx|Version|Wget|curl|
Baiduspider|Applebot|Facebot|Googlebot|YandexBot|bingbot|Lynx|Version|Wget|curl|ChatGPT-User|GPTBot|OAI-SearchBot|
Valve\ Steam\ Tenfoot|
NintendoBrowser|PLAYSTATION\ (?:\d|Vita)+)
\)?;?
(?:[:/ ](?P<version>[0-9A-Z.]+)|/[A-Z]*)%ix
(?:[:/ ](?P<version>[0-9A-Z.]+)|/[A-Z]*)
%ix
REGEX
, $u_agent, $result);

Expand All @@ -125,7 +126,7 @@ function parse_user_agent( $u_agent = null ) {

$lowerBrowser = array_map('strtolower', $result[BROWSER]);

$find = function ( $search, &$key = null, &$value = null ) use ( $lowerBrowser ) {
$find = function( $search, &$key = null, &$value = null ) use ( $lowerBrowser ) {
$search = (array)$search;

foreach( $search as $val ) {
Expand All @@ -141,7 +142,7 @@ function parse_user_agent( $u_agent = null ) {
return false;
};

$findT = function ( array $search, &$key = null, &$value = null ) use ( $find ) {
$findT = function( array $search, &$key = null, &$value = null ) use ( $find ) {
$value2 = null;
if( $find(array_keys($search), $key, $value2) ) {
$value = $search[$value2];
Expand All @@ -168,7 +169,7 @@ function parse_user_agent( $u_agent = null ) {
} elseif( $find('NintendoBrowser', $key) || $platform == 'Nintendo 3DS' ) {
$browser = 'NintendoBrowser';
$version = $result[BROWSER_VERSION][$key];
} elseif( $find('Kindle', $key, $platform) ) {
} elseif( $find([ 'Kindle' ], $key, $platform) ) {
$browser = $result[BROWSER][$key];
$version = $result[BROWSER_VERSION][$key];
} elseif( $find('Opera', $key, $browser) ) {
Expand Down Expand Up @@ -200,12 +201,17 @@ function parse_user_agent( $u_agent = null ) {
$platform = 'BlackBerry';
} elseif( $platform == 'BlackBerry' || $platform == 'PlayBook' ) {
$browser = 'BlackBerry Browser';
} else {
$find('Safari', $key, $browser) || $find('TizenBrowser', $key, $browser);
} elseif( $find('Safari', $key, $browser) || $find('TizenBrowser', $key, $browser) ) {
$version = $result[BROWSER_VERSION][$key];
} elseif( count($result[BROWSER]) ) {
$key = count($result[BROWSER]) - 1;
$browser = $result[BROWSER][$key];
$version = $result[BROWSER_VERSION][$key];
}

$find('Version', $key);
$version = $result[BROWSER_VERSION][$key];
if( $find('Version', $key) ) {
$version = $result[BROWSER_VERSION][$key];
}
} elseif( $pKey = preg_grep('/playstation \d/i', $result[BROWSER]) ) {
$pKey = reset($pKey);

Expand Down
15 changes: 15 additions & 0 deletions tests/user_agents.dist.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1399,6 +1399,11 @@
"browser": "bingbot",
"version": "2.0"
},
"Mozilla\/5.0 AppleWebKit\/537.36 (KHTML, like Gecko); compatible; ChatGPT-User\/1.0; +https:\/\/openai.com\/bot": {
"platform": null,
"browser": "ChatGPT-User",
"version": "1.0"
},
"curl\/7.19.7 (universal-apple-darwin10.0) libcurl\/7.19.7 OpenSSL\/0.9.8r zlib\/1.2.3": {
"platform": null,
"browser": "curl",
Expand Down Expand Up @@ -1439,6 +1444,11 @@
"browser": "Googlebot-Video",
"version": "1.0"
},
"Mozilla\/5.0 AppleWebKit\/537.36 (KHTML, like Gecko); compatible; GPTBot\/1.1; +https:\/\/openai.com\/gptbot": {
"platform": null,
"browser": "GPTBot",
"version": "1.1"
},
"Lynx\/2.8.6rel.4 libwww-FM\/2.14 SSL-MM\/1.4.1 OpenSSL\/0.9.7l Lynxlet\/0.7.0": {
"platform": null,
"browser": "Lynx",
Expand All @@ -1449,6 +1459,11 @@
"browser": "msnbot-media",
"version": "1.1"
},
"Mozilla\/5.0 AppleWebKit\/537.36 (KHTML, like Gecko); compatible; OAI-SearchBot\/1.0; +https:\/\/openai.com\/searchbot": {
"platform": null,
"browser": "OAI-SearchBot",
"version": "1.0"
},
"Slackbot 1.0 (+https:\/\/api.slack.com\/robots)": {
"platform": null,
"browser": "Slackbot",
Expand Down