Hola Andreiya
aqui te dejo el codigo para parsear en google, espero te ayude.
aqui el ejemplo en vivo
http://creaelicita.cl/ayuda/foro_111...hp?texto=gatos
usa la variable texto para buscar lo que quieras
Código PHP:
<?php
include('simple_html_dom.php');
$handler = curl_init();// iniciar el comando CURL POR PHP
curl_setopt($handler, CURLOPT_URL, 'https://www.google.com/search?q=gatitos&ie=utf-8&oe=utf-8');
curl_setopt($handler, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($handler,CURLOPT_USERAGENT,'Mozilla/4.0 (PDA; PalmOS/sony/model prmr/Revision:1.1.54 (en)) NetFront/3.0');// IMPORTANTE HACRCE PASAR POR UNA PALM TE ASEGURA UN RESULTADO MAS LIMPIO
// OTROS COMPLEMENTOS
curl_setopt($handler,CURLOPT_HOTS,'www.google.com');
curl_setopt($handler,CURLOPT_ACCEPT,'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8');
curl_setopt($handler,CURLOPT_ACCEPTLANGUAGE,'es-cl,es;q=0.8,en-us;q=0.5,en;q=0.3');
curl_setopt($handler,CURLOPT_COOKIE,'NID=67=nHypWZWZS_T-SlSSuXAJTMhZB4gIvYOtOUP0vjoOPGjE8HYSK0ONSY1luZeWkIvH7iqpVdxH6Xf0BEcTqIj1Y6rrZJQ8z8O3HdX2gFekYHs-Eh0dJ6d_aw8Lq2VHtFwlBLVxEk5P4t77cyvTNK7EeEDrmUtrgoBFEX72EDgPHvJ42GJshGlaYLTa-Gr2pguDypLsCNRySdDN5dyxSnIn; SID=DQAAAAICAABeps3N4B3sU4HJ1vIE97a98emN7n94wpIoW5MJRRMNHexTSzoY_NfXTV8CIZ2NW6vnC0K2G8Sq7YqEWI_pEEuHPvWA4CkLxMFMC_An3BkmgX9ZD9MywaLuUGlMF-3Hyf8PgJbc6NYTqaN1Qo6duT3aMplkRVmVMHVdPfq46VffGIq0ayEzcd-uYmTjE7ckT0rpb-RqrcuGUyvqUZPnvFbCwDqcGtSd98bEj6bfwDyG3Ap6apF_v6DmQan-eNkIE1FEXzHB0bXd_nKROCm4FKJrz1tONYJGRVP43XHbgv89UkEyF9OAgiZvUB3PyFUU4ihkv0raYQZBcLiiY6NvRPANpKfN885MNwaFPHLHR1woTELjrorj-YASvVxr8ai3blqs7nFI8fy1S_DwWe_weJxn6PvZsX757xh0GQBMOfKznHlx6XFNKaVmwlhdhwlVY3UfJO-svRhpOSCReeLzFlhye19A1sSY-HCTlBEZVI6eXKhCkb5YzTr5DZM79bC2Px45RBu39M4i8znhjIgNe3a6xC5P6crGjAkes6qx7LEdc9keJB27X0ZN5e_S6wccrp9zbMGn9jJ03hW47A4FISDqhyETipj40sXIx0xEDungKl9U_4cGbAMeyWdjwc-HqVu4jSHNw5mOwNloTY_zFWlAdXnalvNzRoBEiRWHHh59Z9rtvxnekr33q7t3xMqo8Gg; HSID=AbEEV6EbfNcqLumK2; SSID=ApgzPR1FFU_d2zQU7; APISID=HugUvpV0VR3gJMIQ/AVyBODG-BvQpt5r7O; SAPISID=oCYqAoqsB6_lPdrh/AFw8b_LEX6RubiuAr; PREF=ID=b904718712cc0d24:U=39272d8d77cdf325:FF=0:LD=es-419:NR=100:TM=1407341101:LM=1421081382:GM=1:SG=1:S=Iy_OMhncF0Buyype; GOOGAPPUID=739; enabledapps.uploader=0; llbcs=0');
curl_setopt($ch,CURLOPT_CONNECTION,'keep-alive');
curl_setopt($ch,CURLOPT_PRAGMA,'no-cache');
curl_setopt($ch,CURLOPT_CACHECONTROL,'no-cache');
$response = curl_exec($handler);// EJECURAT Y DEVOLVER EL RESULTADO
curl_close($handler); //CERRAR LA LLAMADA
// ALGUNOS FILTROS PARA EL HTML
$response = ereg_replace("<script([^>]*)>([^<]*)<\/script>",'',$response);
$response = preg_replace('/(<[^>]+) style=".*?"/i', '$1', $response);
$response = preg_replace('/(<[^>]+) class=".*?"/i', '$1', $response);
$response = preg_replace('/(<[^>]+) bgcolor=".*?"/i', '$1', $response);
$response = preg_replace('/(<[^>]+) border=".*?"/i', '$1', $response);
$response = preg_replace('/(<[^>]+) title=".*?"/i', '$1', $response);
$response = preg_replace('/(<[^>]+) onDblClick=".*?"/i', '$1', $response);
$response = preg_replace('/(<[^>]+) onClick=".*?"/i', '$1', $response);
$response = preg_replace('/(<[^>]+) class=".*?"/i', '$1', $response);
$response = preg_replace('/(<[^>]+) role=".*?"/i', '$1', $response);
$response = preg_replace('/(<[^>]+) tabindex=".*?"/i', '$1', $response);
$response = preg_replace('/(<[^>]+) aria-expanded=".*?"/i', '$1', $response);
$response = preg_replace('/(<[^>]+) aria-haspopup=".*?"/i', '$1', $response);
$response = preg_replace('/(<[^>]+) data-ved=".*?"/i', '$1', $response);
$response = preg_replace('/\<ol\>/i', '$1', $response);$response = preg_replace('/\<\/ol\>/i', '$1', $response);
$response = preg_replace('/\<h.\>/i', '$1', $response);$response = preg_replace('/\<\/h.\>/i', '$1', $response);
$response = preg_replace('/\<br\>/i', '$1', $response);
$response = preg_replace('/\<span\>/i', '$1', $response);$response = preg_replace('/\<\/span\>/i', '$1', $response);
$response = preg_replace('/\<ul\>/i', '$1', $response); $response = preg_replace('/\<\/ul\>/i', '$1', $response);
$response = preg_replace('/\<b\>/i', '$1', $response); $response = preg_replace('/\<\/b\>/i', '$1', $response);
$response = ereg_replace("<cite([^>]*)>([^<]*)<\/cite>",'',$response);
$response =preg_replace('/thead/', 'tr', $response);
$response =preg_replace('/\<\/th>/', '</td> ', $response);
$response = preg_replace('/tbody/', 'tr', $response);
?><h1>Links</h1><?
$html = str_get_html($response); // USAR simple_html_dom PARA FACILITAR LA BUSQUEDA
$ret = $html->find('a'); // BUSCAR LOS LINKS
foreach($ret as $element){// RECORRER LOS LINKS
$link=$element->href;
$link='http'.preg_replace('/http(.*)http/', '', $link);// REEMPLASA LOS LINKS DE GOOGLE
$texto=$element->plaintext;// TEXTO DEL LINK
$q=substr($link,0,5);// LOS PRIMEROS 5 CARACTERES PARA FILTRAR RESULTADOS ENTRE PAGINAS DE GOOGLE Y BUSQIEDAS
if($q=='http:' && $texto!='Cached'){// FILTRADO ENTRE PAGINAS DE GOOGLE Y BUSQIEDAS
?>
<a href="<?=$link?>"><?=$texto?$texto:substr($link,0,(strpos(substr($link,8),"/")+8))// CODIGO AVANZADO (NO TOCAR :-) )?></a><br>
<?
}
}
?>
NOTA: Usa el codigo del cometario anterior para el include