douya2433 2019-04-27 14:02
浏览 22

C#page navi PHP scrape

i tried to scrape this page: http://eshop.saphokft.hu/shop/Productslist.aspx?CategoryCode=sprchove-zasteny

i tried to load 9. page from navi with PHP cURL, but i is not working.

i can just 1-8 scrape, but i cannot step from 8 to 9. page.

what is the problem? I tried to with phantomJs and simple PHP cURL.

function downloadUrl($url){
    //$content = 'error';
    $client = Client::getInstance();
    //$p = explode(':', $proxy);
    //$Proxy = $p[0];
    //$proxyPort = $p[0];
    //$client->getEngine()->addOption("--proxy=176.61.143.43:80");
    //$client->getEngine()->addOption("--proxy-auth=".$proxyUser.":".$proxyPassword."");
    $client->getEngine()->setPath('/home/admin/web/xyz/public_html/bin/phantomjs');
    //$client->getEngine()->addOption("--proxy=".$proxy."");
    //$client->getEngine()->addOption("--proxy-auth=".$proxyUser.":".$proxyPassword."");
    $client->getEngine()->addOption("--proxy-type=http");

    $file = '/home/admin/web/xyz/public_html/stemp/pcookies.txt';
    $client->getEngine()->addOption('--cookies-file='.$file);

    $request  = $client->getMessageFactory()->createRequest();
    $response = $client->getMessageFactory()->createResponse();

    //$request->setMethod('GET');
    $data = array(
        'ctl00$ScriptManager1' => 'ctl00$MainContent$UpdatePanel2|ctl00$MainContent$pagerTop$ctl01$ctl02',
        //'ctl00$HiddenSearchCategory' => '#all',
        //'ctl00$searchtext' => '',
        //'ctl00$MainContent$HiddenFilter' => '[{"filterValue":"sprchove-zasteny","filterType":"pcategoria"},{"filterValue":"ctvrtkruhove-zasteny","filterType":"categoria"}]',
        //'ctl00$MainContent$ex2' => '7990,686990',
        //'min' => '7990',
        //'max' => '686990',
        'ctl00$MainContent$HiddenField1' => 'PageChanged',
        '__EVENTTARGET' => 'ctl00$MainContent$pagerTop$ctl01$ctl02',
        '__VIEWSTATE' => '',
        '__VIEWSTATEGENERATOR' => '5956E682',
        '__VIEWSTATEENCRYPTED' => '5956E682',
        '__ASYNCPOST' => 'true',
    );
    $request->setMethod('POST');
    $request->setUrl($url);
    $request->setRequestData($data);

    $client->send($request, $response);

    if($response->getStatus() === 200) {
        $content = $response->getContent();
    }

    return $content;
}
  • 写回答

0条回答 默认 最新

    报告相同问题?

    悬赏问题

    • ¥60 求一个简单的网页(标签-安全|关键词-上传)
    • ¥35 lstm时间序列共享单车预测,loss值优化,参数优化算法
    • ¥15 基于卷积神经网络的声纹识别
    • ¥15 Python中的request,如何使用ssr节点,通过代理requests网页。本人在泰国,需要用大陆ip才能玩网页游戏,合法合规。
    • ¥100 为什么这个恒流源电路不能恒流?
    • ¥15 有偿求跨组件数据流路径图
    • ¥15 写一个方法checkPerson,入参实体类Person,出参布尔值
    • ¥15 我想咨询一下路面纹理三维点云数据处理的一些问题,上传的坐标文件里是怎么对无序点进行编号的,以及xy坐标在处理的时候是进行整体模型分片处理的吗
    • ¥15 CSAPPattacklab
    • ¥15 一直显示正在等待HID—ISP