實(shí)驗(yàn)樓數(shù)據(jù)提取實(shí)驗(yàn)

https://www.shiyanlou.com/contests/lou5/console
創(chuàng)建數(shù)據(jù)庫(kù)表

create database shiyanlou_data;
use shiyanlou_data;
create table course_data (
    id int(11) not null auto_increment,
    cname varchar(255) default null,
    cdesc varchar(255) default null,
    ctype varchar(255) default null,
    nlong enum('true','false') default null,
    primary key (id)
) ENGINE=INNODB DEFAULT CHARSET=utf8mb4;

php 代碼

<?php
/**
 * micro php Crawler
 * 以下代碼結(jié)構(gòu)僅供參考,可自由發(fā)揮,只要能實(shí)現(xiàn)挑戰(zhàn)目的就可以。
 */
class Crawler
{
    private $content;
    private $data;
    static private $mysql;
    function __construct()
    {
        echo "開始爬取內(nèi)容...<br>";
        //使用面向?qū)ο筮M(jìn)行數(shù)據(jù)庫(kù)的連接,在創(chuàng)建對(duì)象的時(shí)候就自動(dòng)的連接數(shù)據(jù)
        self::$mysql = new MySQLi('localhost','root','','shiyanlou_data',3306);
        //判斷數(shù)據(jù)庫(kù)是否連接
        if(self::$mysql ->connect_errno){
            die('連接錯(cuò)誤' . self::$mysql ->connect_error);
        }
        //設(shè)置字符集
        self::$mysql ->set_charset('utf8');

    }

    public function loadFile($file_path)
    {
        echo "正在加載文件...<br>";
        //TODO
        $this->content = file_get_contents($file_path);

    }
    public function parseCourseBody()
    {
        //TODO
    }

    public function parseContent()
    {
        echo "開始解析內(nèi)容...<br>";
        preg_match_all('#<div class="course-body">[\s\S]*?</div>\s*?</div>#',$this->content,$data);
        $this->content = $data[0]; //全匹配
        foreach ($this->content as $item) {
            $course = [];
            preg_match('#<div class="course-name">(.*?)</div>#',$item,$title);
            $course['cname'] = $title[1];
            preg_match('#<div class="course-desc">(.*?)</div>#',$item,$desc);
            if(count($desc)==2){
                $course['cdesc'] = $desc[1];
            }else {
                $course['cdesc']='';
            }

            preg_match('#<div class="course-desc">(.*?)</div>#',$item,$desc);//
            preg_match('#<span class=".*?pull-right">(.*?)</span>#',$item,$type);
            if (!empty($type)) {
                $course['ctype'] = $type[1];
            }else{
                $course['ctype'] = '';
            }
            if (strlen($course['cname'])> 16) {
                $course['nlong'] = 'true';
            } else {
                $course['nlong'] = 'false';
            }
            $course['name_length'] = strlen($course['cname']);
            $this->data[] = $course;
        }
        echo "<pre>";
        print_r($this->data);
        echo "<pre>";
        echo "解析內(nèi)容結(jié)束! <br>";

    }

    public function saveData()
    {
        echo "存入數(shù)據(jù)庫(kù)...";
        //TODO
        foreach ($this->data as $one) {
            $cname = $one['cname'];
            $ctype = $one['ctype'];
            $nlong = $one['nlong'];
            $cdesc = $one['cdesc'];
            $sql = "insert into course_data (ctype,cname,nlong,cdesc) values ('$ctype','$cname','$nlong','$cdesc')";
            var_dump($sql);
            $res = self::$mysql->query($sql);
            if($res){
                echo '添加成功';
            }else{
                echo '添加失敗' . self::$mysql-> error;
            }
        }
    }

    public function parseTitle()
    {
        echo "解析課程標(biāo)題...<br>";

        //TODO
    }

    public function parseDesc()
    {
        echo "解析課程簡(jiǎn)介...<br>";
        //TODO
    }

    public function parseType()
    {
        echo "解析課程類型...<br>";
        //TODO
    }

    public function titleIsLong()
    {
        echo "判斷課程名是否超長(zhǎng)...<br>";
        //TODO
    }
}
header("Content-Type: text/html;charset=utf-8");
$Crawler = new Crawler();
$Crawler->loadFile('shiyanlou.html');
$Crawler->parseContent();

$Crawler->saveData();
最后編輯于
?著作權(quán)歸作者所有,轉(zhuǎn)載或內(nèi)容合作請(qǐng)聯(lián)系作者
【社區(qū)內(nèi)容提示】社區(qū)部分內(nèi)容疑似由AI輔助生成,瀏覽時(shí)請(qǐng)結(jié)合常識(shí)與多方信息審慎甄別。
平臺(tái)聲明:文章內(nèi)容(如有圖片或視頻亦包括在內(nèi))由作者上傳并發(fā)布,文章內(nèi)容僅代表作者本人觀點(diǎn),簡(jiǎn)書系信息發(fā)布平臺(tái),僅提供信息存儲(chǔ)服務(wù)。

相關(guān)閱讀更多精彩內(nèi)容

  • Android 自定義View的各種姿勢(shì)1 Activity的顯示之ViewRootImpl詳解 Activity...
    passiontim閱讀 178,816評(píng)論 25 709
  • # Python 資源大全中文版 我想很多程序員應(yīng)該記得 GitHub 上有一個(gè) Awesome - XXX 系列...
    aimaile閱讀 26,823評(píng)論 6 427
  • 嘗試了一下快要考試的模擬試卷,瞬間想要抓狂,兼職的工資剛剛到手。還是出去走走吧。說好的要帶上令我抓狂的東西,想了想...
    茜姑娘呀閱讀 387評(píng)論 0 2

友情鏈接更多精彩內(nèi)容