【开源推荐】只为证明PHP是世界上最好语言的蜘蛛爬虫phpspider框架

require_once __DIR__ . '/../autoloader.php';
use phpspider\core\phpspider;
use phpspider\core\requests;

/* Do NOT delete this comment */
/* 不要删除这段注释 */

$configs = array(
    'name' => '糗事百科',
    'domains' => array(
        'qiushibaike.com',
        'www.qiushibaike.com'
    ),
    'scan_urls' => array(
        'http://www.qiushibaike.com/'
    ),
    'content_url_regexes' => array(
        "http://www.qiushibaike.com/article/\d+"
    ),
    'list_url_regexes' => array(
        "http://www.qiushibaike.com/8hr/page/\d+\?s=\d+"
    ),
    'fields' => array(
        array(
            // 抽取内容页的文章内容
            'name' => "article_content",
            'selector' => "//*[@id='single-next-link']",
            'required' => true
        ),
        array(
            // 抽取内容页的文章作者
            'name' => "article_author",
            'selector' => "//div[contains(@class,'author')]//h2",
            'required' => true
        ),
    ),
);
$spider = new phpspider($configs);
$spider->start();