awesome_scrawler.php

<?php
error_reporting(0);

function get_raw_url($url)
{
    $parse = parse_url($url);
    return 'https://raw.githubusercontent.com' . $parse['path'] . '/master/readme.md';
}

function getData($object)
{
    $url = get_raw_url($object['url']);
    $result = file_get_contents($url);
    if (!$result) {
        $result = file_get_contents(str_replace('readme', 'README', $url));
    }
    $rows = explode("\n", $result);

    $category = null;
    $category_except = ['contents'];

    $data = [];
    foreach ($rows as $row) {
        if (strpos($row, '##') !== false) {
            $str = substr($row, 3);

            if (!in_array(strtolower($str), $category_except)) {
                $category = $str;
            }
            continue;
        }

        if ($category && strpos($row, '- ') !== false) {
            preg_match('/.*- \[(.*)\]\((.*)\)( - )?(.*)/', $row, $matches);
            $item = [];
            $item['category'] = $category;
            list(, $item['name'], $item['url'], ,$item['description']) = $matches;
            $data[] = $item;
        }
    }
    return $data;
}

$data[0] = [
    'category' => 'awesome',
    'name' => 'awesome',
    'url' => 'https://github.com/sindresorhus/awesome',
    'description' => null,
    'content' => [],
];

$data[0]['content'] = getData($data[0]);
foreach ($data[0]['content'] as &$datum) {
    echo $count ++ . PHP_EOL;
    $datum['content'] = getData($datum);
}
file_put_contents('/tmp/github.json', json_encode($data));