初心者でもできる！PHPでスクレイピング入門の10ステップ

<?php
$ch = curl_init(); // cURLセッションの初期化
curl_setopt($ch, CURLOPT_URL, "https://example.com"); // 取得するURLを指定
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); // 結果を文字列で返すように設定

$html = curl_exec($ch); // URLの情報を取得
curl_close($ch); // cURLセッションの終了

$dom = new DOMDocument;
@$dom->loadHTML($html); // 取得したHTMLをDOMDocumentオブジェクトに読み込む

$xpath = new DOMXPath($dom);
$nodes = $xpath->query('//p'); // すべての<p>要素を取得

foreach ($nodes as $node) { // 取得した要素を表示
    echo $node->nodeValue, PHP_EOL;
}
?>

<?php
$urls = ["https://example.com/page1", "https://example.com/page2", "https://example.com/page3"]; // スクレイピング対象のURLを配列で指定

foreach ($urls as $url) {
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, $url); // 取得するURLを指定
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); // 結果を文字列で返すように設定

    $html = curl_exec($ch);
    curl_close($ch);

    $dom = new DOMDocument;
    @$dom->loadHTML($html); // 取得したHTMLをDOMDocumentオブジェクトに読み込む

    $xpath = new DOMXPath($dom);
    $nodes = $xpath->query('//p'); // すべての<p>要素を取得

    foreach ($nodes as $node) { // 取得した要素を表示
        echo $node->nodeValue, PHP_EOL;
    }
}
?>

<?php
$login_url = 'https://example.com/login';
$data = array(
    'username' => 'your_username',
    'password' => 'your_password'
);

$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, $login_url);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, http_build_query($data));
curl_setopt($ch, CURLOPT_COOKIEJAR, 'cookie.txt');
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);

curl_exec($ch);

curl_setopt($ch, CURLOPT_URL, 'https://example.com/target_page');
$html = curl_exec($ch);

curl_close($ch);

$dom = new DOMDocument;
@$dom->loadHTML($html);

$xpath = new DOMXPath($dom);
$nodes = $xpath->query('//p');

foreach ($nodes as $node) {
    echo $node->nodeValue, PHP_EOL;
}
?>

<?php
$url = 'https://example.com';
$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);

$html = curl_exec($ch);

curl_close($ch);

$dom = new DOMDocument;
@$dom->loadHTML($html);

$xpath = new DOMXPath($dom);
$nodes = $xpath->query('//h2');

foreach ($nodes as $node) {
    echo $node->nodeValue, PHP_EOL;
}
?>

<?php
$url = 'https://example.com';
$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);

$html = curl_exec($ch);

curl_close($ch);

$dom = new DOMDocument;
@$dom->loadHTML($html);

$xpath = new DOMXPath($dom);
$nodes = $xpath->query('//h2');

$data = [];
foreach ($nodes as $node) {
    $data[] = [$node->nodeValue];
}

$fp = fopen('data.csv', 'w');
foreach ($data as $row) {
    fputcsv($fp, $row);
}
fclose($fp);

if (($handle = fopen("data.csv", "r")) !== FALSE) {
    while (($data = fgetcsv($handle, 1000, ",")) !== FALSE) {
        var_dump($data);
    }
    fclose($handle);
}
?>