phpQuery ------實戰(zhàn)應(yīng)用thinkphp框架

2024-09-09 15:20:17

字體：大中小

供稿：網(wǎng)友

相信許多朋友看小說都有一種感覺就是總有一些廣告頁面彈出來,加上最近在研究phpQuery進(jìn)行數(shù)據(jù)采集,所以萌生了一個寫一個小說網(wǎng)站玩的想法,經(jīng)過大概4天的時間終于完成了,主要運(yùn)用thinkphp框架MongoDb和phpQuery.

如下是一個分頁采集的例子:

public function pageHtml($searchkey, $page = 1) {

        Vendor('phpQuery.phpQuery.phpQuery');

        $pageHtml = Baidu::searchPage($searchkey, $page);

        $pageHtml = /phpQuery::newDocumentHTML($pageHtml);

        $count = $pageHtml->find('#pagelink .last')->html();

        $trs = $pageHtml->find('#content tr');

        foreach ($trs as $tr) {

            $book['href'] = pq($tr)->find('td:eq(0) a')->attr('href');

            $book['title'] = Baidu::utf8(pq($tr)->find('td:eq(0) a')->html());

            $book['bookId'] = intval(end(explode('/', $book['href'])));

            $href = explode('/', pq($tr)->find('td:eq(1) a')->attr('href'));

            $book['newZj'] = Baidu::DING_DIAN . $href[3] . '/' . $href[4] . '/' . $href[5] . '.html';

            $book['newName'] = Baidu::utf8(pq($tr)->find('td:eq(1) a')->html());

            $book['author'] = Baidu::utf8(pq($tr)->find('td:eq(2)')->html());

            $book['ziNum'] = Baidu::utf8(pq($tr)->find('td:eq(3)')->html());

            $book['lastDate'] = Baidu::utf8(pq($tr)->find('td:eq(4)')->html());

            $book['status'] = Baidu::utf8(pq($tr)->find('td:eq(5)')->html());

            $n = D('book')->where(array('bookId' => $book['bookId']))->find();

            $book['update'] = time();

            if ($n) {

                $book['_id'] = $n['_id'];

                $book['create'] = $n['create'];

                D('book')->create($book);

                D('book')->save();

            } else {

                if ($book['href']) {

                    $book['create'] = time();

                    D('book')->add($book);

                }

            }

        }

        /phpQuery::$documents = array();

        return $count;

    }

由于用的是mongoDb所以字符串要用utf-8的編碼多有在Think/BaiduModel中做了一個轉(zhuǎn)碼如下:

public static function utf8(String $string) {

            if (is_string($string)) {

               $untion = mb_detect_encoding($string, array("ASCII", 'UTF-8', "GB2312", "GBK", 'BIG5')); //轉(zhuǎn)碼

            if ($untion != 'UTF-8') {

                $string = mb_convert_encoding($string, "UTF-8", $untion);

            } //開源軟件:Vevb.com

            return $string;

        }

        return 'this is not string';

     }