黄晓敏的个人博客 – 我们来一起荡秋千吧

PHP

PHP抓取谷歌搜索结果

#!/usr/local/php/bin/php
<?php
	$keyword = '黄晓敏'; //关键词
	$pageNum = 10; //每页显示几个
	$page = '1'; //第几页
	$lang = 'com'; //针对哪个国家的搜索结果
	$all = ''; //保存结果

	$query = urlencode($keyword);
	$ch = curl_init();
	curl_setopt($ch, CURLOPT_URL, 'http://www.google.' . $lang . '/search?oe=utf8&num=' . $pageNum . '&ie=utf8&source=uds&start='. $pageNum * ($page - 1).'&hl=en&q='. $query);
	curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
	curl_setopt($ch, CURLOPT_HEADER, 0);
	$content =  urldecode(htmlspecialchars_decode(curl_exec($ch)));
	preg_match_all('/<h3 class=\"r\"><a href=\"\/url\?q=(.*?)&sa=/', $content, $matchs);
	foreach($matchs[1] as $http) {
		$all .= $http. "\n";
	}
	//file_put_contents('1', $all);
	echo $all;
	curl_close($ch);

#!/usr/local/php/bin/php

<?php

$keyword = '黄晓敏'; //关键词

$pageNum = 10; //每页显示几个

$page = '1'; //第几页

$lang = 'com'; //针对哪个国家的搜索结果

$all = ''; //保存结果

$query = urlencode($keyword);

$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, 'http://www.google.' . $lang . '/search?oe=utf8&num=' . $pageNum . '&ie=utf8&source=uds&start='. $pageNum * ($page - 1).'&hl=en&q='. $query);

curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);

curl_setopt($ch, CURLOPT_HEADER, 0);

$content = urldecode(htmlspecialchars_decode(curl_exec($ch)));

preg_match_all('/<h3 class=\"r\"><a href=\"\/url\?q=(.*?)&sa=/', $content, $matchs);

foreach($matchs[1] as $http) {

$all .= $http. "\n";

}

//file_put_contents('1', $all);

echo $all;

curl_close($ch);

由webmaster，4年前