//调用方法 :http://localhost/2.php?id=1 (自动采集1-8的列表)
header("Content-type:text/html;charset=utf-8");
$con =mysql_connect("localhost", "root", "huweishen.com") or die("数据库链接错误");
mysql_select_db("liuyan", $con);
mysql_query("set names 'utf8'");
function preg_substr($start, $end, $str) // 正则截取函数
{
$temp = preg_split($start, $str);
$content = preg_split($end, $temp[1]);
return $content[0];
}
function str_substr($start, $end, $str) // 字符串截取函数
{
$temp = explode($start, $str, 2);
$content = explode($end, $temp[1], 2);
return $content[0];
}
// ---------------- 使用实例 ----------------
if($_GET['id']<=8&&$_GET['id']){
$id=$_GET['id'];
$url = "http://www.037c.com/New/list_5_$id.html"; //目标站
$fp = fopen($url, "r") or die("超时");
$fcontents = file_get_contents($url);
$pattern="//iUs";//正则
preg_match_all($pattern, $fcontents, $arr);
//print_r($arr);
foreach($arr[1] as $k=>$url)
{
$title = iconv('GB2312', 'UTF-8', addslashes($arr[2][$k]));
// echo $title;
// echo $url;
$str = iconv("GB2312","UTF-8", file_get_contents($url));
$author = preg_substr("/作者:/", "/
$content = str_substr('
$sql = "INSERT INTO `caiji` (`title`, `url` , `content`, `author` ) VALUES ('$title', '$url' , '$content' , '$author')";
// echo $sql."
";
mysql_query($sql);
}
$id++;
echo "正在采集URL数据列表$id...请稍后...";
echo "";
}
else{
echo "采集数据结束。";
}
?>
其中 title 设置唯一,可以防止重复采集,很好的的一个php采集小程序