想在程序加上文章采集功能,花了点时间写了个测试,流程走通了,丰富后可以用于正式环境。见代码:
/**
* 采集类
* @author Milkcy QQ:9877633
* @copyright (C) 2012-2015 TCCMS.COM
* @lastmodify 2012-07-10 14:00
*/
class gather {
public $pagestring = '';
private $db;
function __construct() {
global $db;
$this->db = $db;
}
function geturlfile($url) {
$url = trim($url);
$content = '';
if (extension_loaded('curl')) {
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
curl_setopt($ch, CURLOPT_HEADER, 0);
$content = curl_exec($ch);
curl_close($ch);
} else {
$content = file_get_contents($url);
}
return trim($content);
}
function get_all_url($code) {
preg_match_all('/"\\' ]+)["|\\']?\\s*[^>]*>([^>]+)/is', $code, $arr);
return array('name' => $arr[2], 'url' => $arr[1]);
}
function get_sub_content($str, $start, $end) {
$start = trim($start);
$end = trim($end);
if ($start == '' || $end == '') {
return $str;
}
$str = explode($start, $str);
$str = explode($end, $str[1]);
return $str[0];
}
function vd($var) {
echo "
echo "
\\r\\n";
var_dump($var);
echo "\\r\\n
\\r\\n";echo "
}
}
?>
define('ROOT_PATH', str_replace('\\\\', '/', dirname(__FILE__)));
include ROOT_PATH."/gather.class.php";
set_time_limit(0);
header("Content-type: text/html; charset=gb2312");
//目标网址
$url = 'http://news.163.com/special/00013C0O/guojibjtj_03.html';
//实例化采集机器
$gather = new gather();
//获取目标网址HTML
$html = $gather->geturlfile($url);
//定义采集列表区间
$start = '
$end = '
//获取区间内的文章URL和TITLE
$code = $gather->get_sub_content($html, $start, $end);
$newsAry = $gather->get_all_url($code);
//打印出结果
//$gather->vd($newsAry);
$tarGetUrl = $newsAry['url'][0];
//获取目标网址HTML
$html = $gather->geturlfile($tarGetUrl);
//定义采集列表区间
$start = '