yonderly.org/4get
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fixed google not working in yurop

Browse Source
This commit is contained in:
lolcat 2024-03-20 10:59:51 -04:00
parent c4c008c192
commit 635b2386d4
2 changed files with 30 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
data/config.php
View File

@ -92,7 +92,7 @@ class config{
const PROXY_DDG = false; // duckduckgo const PROXY_DDG = false; // duckduckgo
const PROXY_BRAVE = false; const PROXY_BRAVE = false;
const PROXY_FB = false; // facebook const PROXY_FB = false; // facebook
const PROXY_GOOGLE = false; const PROXY_GOOGLE = "webshare_google";
const PROXY_MARGINALIA = false; const PROXY_MARGINALIA = false;
const PROXY_MOJEEK = false; const PROXY_MOJEEK = false;
const PROXY_SC = false; // soundcloud const PROXY_SC = false; // soundcloud

34
scraper/google.php
View File

@ -522,6 +522,7 @@ class google{
"Accept-Language: en-US,en;q=0.5", "Accept-Language: en-US,en;q=0.5",
"Accept-Encoding: gzip", "Accept-Encoding: gzip",
"DNT: 1", "DNT: 1",
"Cookie: SOCS=CAESNQgCEitib3FfaWRlbnRpdHlmcm9udGVuZHVpc2VydmVyXzIwMjQwMzE3LjA4X3AwGgJlbiAEGgYIgM7orwY",
"Connection: keep-alive", "Connection: keep-alive",
"Upgrade-Insecure-Requests: 1", "Upgrade-Insecure-Requests: 1",
"Sec-Fetch-Dest: document", "Sec-Fetch-Dest: document",
@ -977,9 +978,9 @@ class google{
"related" => [] "related" => []
]; ];
if($this->detect_sorry($html)){ if($error = $this->detect_sorry($html)){
throw new Exception("Google blocked this 4get instance. Please set up a proxy!"); throw new Exception($error);
} }
$this->parsejavascript($html); $this->parsejavascript($html);
@ -2813,9 +2814,9 @@ class google{
throw new Exception("Failed to get search page"); throw new Exception("Failed to get search page");
} }
if($this->detect_sorry($html)){ if($error = $this->detect_sorry($html)){
throw new Exception("Google blocked this 4get instance. Please set up a proxy!"); throw new Exception($error);
} }
$out = [ $out = [
@ -3649,7 +3650,30 @@ class google{
$detect_sorry[0]["innerHTML"] == "302 Moved" $detect_sorry[0]["innerHTML"] == "302 Moved"
){ ){
return true; // may be consent.google.com in europe or /sorry captcha page
$url =
$this->fuckhtml
->getElementsByTagName("a");
if(
strpos(
parse_url(
$this->fuckhtml
->getTextContent(
$url[0]["attributes"]["href"]
),
PHP_URL_PATH
),
"/sorry"
) === 0
){
// found /sorry
return "Google blocked this 4get instance. Please setup a proxy!";
}
// found consent.google, should not happen anymore
return "Google served a GPDR consent form. This should not happen, please report if you encounter this message";
} }
return false; return false;