已爬网的网站未插入到我的 SQL 表中 | PHP网络爬虫

我制作了一个 PHP 网络爬虫，然后制作了一个名为“dex”的 MySQL 表（如索引），然后通过 PDO 连接到数据库，并将代码调整为“INSERT”尚未爬入表中的网站，“ UPDATE”用于被抓取的网站，并使用 URL 哈希作为链接的指示器或“id”。 终端显示了所有链接以及与其相关的链接，if语句运行良好并且没有重大错误，那么为什么它不将数据插入到“dex”表中呢？ 每次我在处理后检查表时，我只找到手动插入的行来测试“UPDATE”或“INSERT”的 if 语句。 我该如何解决此问题并插入爬网程序检索的日期？

测试.html：

<a href="https://google.com"></a>
<a href="https://www.yahoo.com/"></a>
<a href="https://www.bing.com/"></a>
<a href="https://duckduckgo.com/"></a>

爬虫：

<?php

error_reporting(E_ALL);
ini_set('display_errors', 1);

$start = "http://localhost/deepsearch/test.html";

$pdo = new PDO('mysql:host=127.0.0.1;dbname=deepsearch', 'root', '');

$already_crawled = array();
$crawling = array();

function get_details($url) {
    $options = array('http'=>array('method'=>"GET", 'headers'=>"User-Agent: howBot/0.1\n"));
    $context = stream_context_create($options);

    // Suppress warnings for HTML parsing errors
    libxml_use_internal_errors(true);

    $doc = new DOMDocument();
    @$html = @file_get_contents($url, false, $context);

    // Load HTML content and check for parsing errors
    if ($doc->loadHTML($html)) {
        if (!empty($titleElements)) {
            $title = $titleElements->item(0);
            $title = $title->nodeValue;
        } else {
            $title = "";
        }
        
        $description = "";
        $keywords = "";
        $metas = $doc->getElementsByTagName("meta");
        for ($i = 0; $i < $metas->length; $i++) {
            $meta = $metas->item($i);

            if ($meta->getAttribute("name") == strtolower("description")) {
                $description = $meta->getAttribute("content");
            }
            if ($meta->getAttribute("name") == strtolower("keywords")) {
                $keywords = $meta->getAttribute("content");
            }
        }

        return '{"Title": "'.str_replace("\n", "", $title).'", "Description": "'.str_replace("\n", "", $description).'", "Keywords": "'.str_replace("\n", "", $keywords).'", "URL": "'.$url.'"}';
    } else {
        // Handle the parsing error
        echo "HTML parsing error: " . libxml_get_last_error()->message . "\n";
        return ''; // Return an empty string or handle the error as needed
    }
}
function follow_links($url)
{

    global $pdo;
    global $already_crawled;
    global $crawling;

    $options = array('http' => array('method' => "GET", 'headers' => "User-Agent: howBot/0.1\n"));
    $context = stream_context_create($options);

    $doc = new DOMDocument();
    @$doc->loadHTML(@file_get_contents($url, false, $context));

    $linklist = $doc->getElementsByTagName("a");

    foreach ($linklist as $link) {
        $l = $link->getAttribute("href");

        if (substr($l, 0, 1) == "/" && substr($l, 0, 2) != "//") {
            $l = parse_url($url)["scheme"] . "://" . parse_url($url)["host"] . $l;
        } else if (substr($l, 0, 2) == "//") {
            $l = parse_url($url)["scheme"] . ":" . $l;
        } else if (substr($l, 0, 2) == "./") {
            $l = parse_url($url)["scheme"] . "://" . parse_url($url)["host"] . dirname(parse_url($url)["path"]) . substr($l, 1);
        } else if (substr($l, 0, 1) == "#") {
            $l = parse_url($url)["scheme"] . "://" . parse_url($url)["host"] . parse_url($url)["path"] . $l;
        } else if (substr($l, 0, 3) == "../") {
            $l = parse_url($url)["scheme"] . "://" . parse_url($url)["host"] . "/" . $l;
        } else if (substr($l, 0, 11) == "javascript:") {
            continue;
        } else if (substr($l, 0, 5) != "https" && substr($l, 0, 4) != "http") {
            $l = parse_url($url)["scheme"] . "://" . parse_url($url)["host"] . "/" . $l;
        }

        if (!in_array($l, $already_crawled)) {
            $already_crawled[] = $l;
            $crawling[] = $l;

            $details = json_decode(get_details($l));
            echo $details->URL . " ";

            $rows = $pdo->query("SELECT * FROM dex WHERE url_hash='" . md5($details->URL) . "'");
            $rows = $rows->fetchColumn();

            $params = array(':title' => $details->Title, ':description' => $details->Description, ':keywords' => $details->Keywords, ':url' => $details->URL, ':url_hash' => md5($details->URL));

            if ($rows > 0) {
                echo "UPDATE" . "\n";
            } else {

                if (!is_null($params[':title']) && !is_null($params[':description']) && $params[':title'] != '') {

                    $result = $pdo->prepare("INSERT INTO dex (title, description, keywords, url, url_hash) VALUES (:title, :description, :keywords, :url, :url_hash)");
                    $result= $result->execute($params); 


                    //if ($result) {
                    //    echo "Inserted successfully.\n";
                    //} else {
                    //    echo "Insertion failed.\n";
                    //    print_r($stmt->errorInfo());
                    //}
                }
            }


            //print_r($details)."\n";
            //echo get_details($l)."\n";
            //echo $l."\n";
        }

    }
    array_shift($crawling);
    foreach ($crawling as $site) {
        follow_links($site);
    }
}




follow_links($start);
//print_r($already_crawled);
?>

我尝试过的：

起初，我尝试了不同的链接，这些链接给了我一个空值，导致错误和警告，然后我更改了链接并开始编写“UPDATE”、“INSERT” if 语句，并首先开始专门编写插入 PDO 来测试它。 当我使用命令 php 执行文件时，我得到了预期的结果，即它在终端中的外观，但后来我检查了表格，发现没有插入任何内容。 我想插入这些以在我的搜索引擎中使用它们并使它们可通过查询进行搜索。