php 爬取网站内容

复制直接可用

注意正则匹配仅限与示例中的网址 

index();
function index()
{  
    // 要爬取的网页
    $url = 'https://mc.dfrobot.com.cn/';
    $result = httpCurl($url,[],'GET');
    // 图片
    $avatarRule = "/<div class=\"imgBox\".*?>.*?<\/div>/s"; 
    preg_match_all($avatarRule,$result,$avatar);
    $preg = '/<img.*?src=[\"|\']?(.*?)[\"|\']?\s.*?>/i';

    $titleRule = "/<div class=\"titleBox\".*?>.*?<\/div>/s"; 
    preg_match_all($titleRule,$result,$title);
    $titleRulea = "/<a href=\"([^<>]*)\">([^<>]*)<\/a>/s";

    // 简介
    $titleRuleb = "/<div class=\"descBox\">([^<>]*)<\/div>/s";
    preg_match_all($titleRuleb,$result,$content);
    $insert=[];
    $titleRulec = "/<div class=\"descBox\">([^<>]*)<\/div>/s";
    foreach ($content[0] as $k => $v) {
        preg_match($titleRulec, $v, $arrc);
        // 简介
        $arr['content']=trim($arrc[1]);

        // 图片
        preg_match($preg, $avatar[0][$k], $imgs);
        $arr['img']='https://mc.dfrobot.com.cn/'.$imgs[1];

        preg_match($titleRulea, $title[0][$k], $url_title);
        $arr['url']=str_replace('"  target="_blank','',$url_title[1]);// 链接地址
        $arr['title']=$url_title[2];// 标题
        $insert[]=$arr;
    }
    var_dump($insert);die;
}
function httpCurl($url, $params, $method = 'POST', $header = array(), $multi = false){
    date_default_timezone_set('PRC');
    $opts = array(
        CURLOPT_TIMEOUT        => 30,
        CURLOPT_RETURNTRANSFER => 1,
        CURLOPT_SSL_VERIFYPEER => false,
        CURLOPT_SSL_VERIFYHOST => false,
        CURLOPT_HTTPHEADER     => $header,
        CURLOPT_COOKIESESSION  => true,
        CURLOPT_FOLLOWLOCATION => 1,
        CURLOPT_COOKIE         =>session_name().'='.session_id(),
    );
    /* 根据请求类型设置特定参数 */
    switch(strtoupper($method)){
        case 'GET':
            // $opts[CURLOPT_URL] = $url . '?' . http_build_query($params);
            // 链接后拼接参数  &  非？
            $opts[CURLOPT_URL] = $url . '?' . http_build_query($params);
            break;
        case 'POST':
            //判断是否传输文件
            $params = $multi ? $params : http_build_query($params);
            $opts[CURLOPT_URL] = $url;
            $opts[CURLOPT_POST] = 1;
            $opts[CURLOPT_POSTFIELDS] = $params;
            break;
        default:
            echo '不支持的请求方式！';
    }
    /* 初始化并执行curl请求 */
    $ch = curl_init();
    curl_setopt_array($ch, $opts);
    $data  = curl_exec($ch);
    $error = curl_error($ch);
    curl_close($ch);
    // if($error) throw new Exception('请求发生错误：' . $error);
    return  $data;
}