Created
November 15, 2011 18:07
-
-
Save underdown/1367825 to your computer and use it in GitHub Desktop.
PHP Google Scraping Function
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
function findranking($domain, $keyword) { | |
usleep(400000*rand(0,16)); //set random interval between checks | |
$url="http://www.google.com/search?q=".urlencode($keyword)."&num=100"; | |
$ch = curl_init($url); | |
curl_setopt($ch, CURLOPT_HEADER,1); // set to 0 to eliminate header info from response | |
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); // Returns response data instead of TRUE(1) | |
$header = array(); | |
$header[0] = "Accept: text/xml,application/xml,application/xhtml+xml,"; | |
$header[0] .= "text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5"; | |
$header[] = "Cache-Control: max-age=0"; | |
$header[] = "Connection: keep-alive"; | |
$header[] = "Keep-Alive: 300"; | |
$header[] = "Accept-Charset: ISO-8859-1,utf-8;q=0.7,*;q=0.7"; | |
$header[] = "Accept-Language: en-us,en;q=0.5"; | |
$header[] = "Pragma: "; // browsers keep this blank. | |
curl_setopt( $ch, CURLOPT_HTTPHEADER, $header ); | |
curl_setopt( $ch, CURLOPT_USERAGENT, $useragents[rand(0, sizeof($useragents)-1)] ); | |
$resp = curl_exec($ch); //execute post and get results | |
curl_close ($ch); | |
if(strpos($resp, "Location: http://sorry.google.com/sorry/") && strpos($resp, "302 Found")) | |
return -200; | |
$count=0; | |
$bp=0; | |
while($bp=strpos($resp, "<h3 class=", $bp+1)) { | |
$count++; | |
$end=strpos($resp, "</h3>", $bp); | |
$link= substr($resp, $bp, $end-$bp+5); | |
$bp++; | |
if(stripos($link, ">Local business results for") && stripos($link, "href=\"http://maps.google.com/")){ | |
$count--; | |
} | |
// match all secure and www non-www | |
if(stripos($link, "http://".$domain) || stripos($link, "https://".$domain) || stripos($link, "http://www.".$domain) || stripos($link, "https://www.".$domain)){ | |
$rank=$count; | |
} | |
} | |
if (!$rank) $rank=101; | |
return $rank; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Estou tendo alguns erros na curl_setopt( $ch, CURLOPT_USERAGENT, $useragents[rand(0, sizeof($useragents)-1)] );
E com o while($bp=strpos($resp, "<h3 class=", $bp+1)) {