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*[^>]*>([^>]+)<\\/a>/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 "
      
       \\r\\n";        echo "
       
\\r\\n";        var_dump($var);        echo "\\r\\n
\\r\\n";        echo "
      
";    }}?>
      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 = '
        
         ';$end = '
         ';//获取区间内的文章URL和TITLE$code = $gather->get_sub_content($html, $start, $end);$killHtml = '';$killHtml2 = '';$code = str_replace($killHtml, "", $code);$code = str_replace($killHtml2, "", $code);$gather->vd($code);?>//该片段来自于http://outofmemory.cn
        
       
      
     

 

 

php 文章采集正则代码

//采集html function getwebcontent($url){ $ch = curl_init(); $timeout = 10; curl_setopt($ch, CURLOPT_URL, $url); curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, $timeout); curl_setopt ($ch, CURLOPT_FOLLOWLOCATION, 1); $contents = trim(curl_exec($ch)); curl_close($ch); return $contents; } //获得标题和url $string = getwebcontent('http://www.***.com/learn/zhunbeihuaiyun/jijibeiyun/2'); //正则匹配
获取标题和地址 preg_match_all ("/
(.*)<\/a>/",$string, $out, PREG_SET_ORDER);foreach($out as $key => $value){ $article['title'][] = $out[$key][2]; $article['link'][] = "http://www.***.com/learn/article/".$out[$key][1]; } //根据url获取文章内容 foreach($article['link'] as $key=>$value){ $content_html = getwebcontent($article['link'][$key]); preg_match("/
       
        [\s|\S]*?<\/div>/",$content_html,$matches); $article[content][$key] = $matches[0]; } //不转码还真不能保存成文件 foreach($article[title] as $key=>$value){ $article[title][$key] = iconv('utf-8', 'gbk', $value);//转码 } //存入文件 $num = count($article['title']); for($i=0; $i<$num; $i++){ file_put_contents("{
   $article[title][$i]}.txt", $article['content'][$i]); } ?>