php采集程序

/**
* 根据URL采集网页内容
*
* @param string $url 链接地址
* @return string
*/

private function fetchbyurl($url){
$handle = fopen($url, ‘r’);
$content = ”;
while (!feof($handle)){
$content .= fgets($handle, 10000);
}
return $content;
//?$this->utf8_iconv($content):”;
}

/*获取所有匹配的内容
* @param string $str 内容
* @param string $start 起始匹配
* @param string $end 中止匹配
* @return array
*/

private function utf8_iconv($content){
return iconv(‘GBK’, ‘UTF-8’, $content);
}
private function strCutAll($str,$start,$end){
$content = explode($start,$str);
$matchs = array();
$sum = count($content);
for( $i = 1;$i < $sum;$i++ ){ $tmp = explode($end,$content[$i]); $matchs[] = $tmp[0]; unset($tmp); } return $matchs; } /*获取第一个匹配的内容 * @param string $str 内容 * @param string $start 起始匹配 * @param string $end 中止匹配 * @return string */ private function strCut($str, $start, $end){ $content = strstr( $str, $start ); $content = substr( $content, strlen( $start ), strpos( $content, $end ) - strlen( $start ) ); return $content; } 测试: [code lang="php"] /*采集程序*/ header("content-Type: text/html; charset=utf-8"); //$nr = file_get_contents('http://shanmao.me/webback/php/php-yi-ju-hua-hou-men-zhuan'); $nr = $this->fetchbyurl('http://shanmao.me/webback/php/php-yi-ju-hua-hou-men-zhuan');//推荐,还可以用curl dump($this->strCut($nr,'<div class="context">','<div class="betterrelated">'));//得到内容。需要进一步过滤用(preg_match_all) dump($this->strCutAll($nr,'<title>','</title>')); 得到标题 [/code]