COT Report Parser with PHP

Report.php

<?php

namespace OmKoding\Cot;

use GuzzleHttp\Client;

class Report
{
	/**
	 * @var \GuzzleHttp\Client
	 */
	protected $client;

	/**
	 * Initiate class
	 */
	public function __construct()
	{
		$this->client = new Client([
			'http_errors' => false,
		]);
	}

	/**
	 * Get latest COT Report
	 * 
	 * @return array
	 */
	public function latest()
	{
		$url = 'https://www.cftc.gov/dea/futures/deacmesf.htm';

		$response = $this->client->get($url);

		return $this->parse((string) $response->getBody());
	}

	/**
	 * Get COT Report by date
	 * 
	 * @param string Date of report in m/d/y format
	 * @return array
	 */
	public function byDate($date)
	{
		// ekstrak month, day, and year
		list($month, $day, $year) = explode('/', $date);

		$url = sprintf(
            'https://www.cftc.gov/sites/default/files/files/dea/cotarchives/%s/futures/deacmesf%s%s%s.htm',
            date('Y', strtotime($date)), // konversi menjadi tahun 4 digit
            $month,
            $day,
            $year
        );

        $response = $this->client->get($url);

		return $this->parse((string) $response->getBody());
	}

	/**
	 * Parsing HTML response and get data
	 *
	 * @param string HTML Response from GuzzleHTTP
	 * @return array
	 */
	protected function parse(string $html)
	{
		$lines = explode(PHP_EOL, $html);

		$result = [];

		foreach ($lines as $index => $line) {
			// cari baris yang mengandung nama item
			if (stripos($line, ' - CHICAGO MERCANTILE EXCHANGE') !== false) {
				// ambil nama item sebelum string berikut
				$nameLine = explode(' - CHICAGO MERCANTILE EXCHANGE', $line);

				$name = $nameLine[0];

				// ambil tanggal pada baris index + 1 dan pisahkan berdasarkan spasi
				$dateLine = preg_split('/\s+/', trim($lines[$index + 1]));

				$date = $date[5];

				// ambil Open Interest pada baris index + 7 dan pisahkan berdasarkan spasi
				$openInterestLine = preg_split('/\s+/', trim($lines[$index + 7]));

				// ambil index column terakhir
				$openInterest = end($openInterestLine);

				// ambil Open Interest Total Change pada baris index + 11 dan pisahkan
				$openInterestChangeLine = preg_split('/\s+/', trim($lines[$index + 7]));

				//  ambil index column terakhir dan hilangkan akhiran ")"
				$openInterestChange = rtrim(end($openInterestChangeLine), ')');

				// ambil posisi terkini pada baris index + 9 dan pisahkan berdasarkan spasi
				$current = preg_split('/\s+/', trim($lines[$index + 9]));

				// ambil perubahan dari minggu lalu pada baris index + 12 dan pisahkan berdasarkan spasi
				$changes = preg_split('/\s+/', trim($lines[$index + 12]));

				// ambil Open Interest Percent Changes pada baris index + 15 dan pisahkan berdasarkan spasi
				$percent = preg_split('/\s+/', trim($lines[$index + 15]));

				$result[$name] = [
					'name' => $name,
					'date' => $date,
					'current' => [
						'non-commercial' => [
							'long' => $current[0],
							'short' => $current[1],
							'spreads' => $current[2],
						],
						'commercial' => [
							'long' => $current[3],
							'short' => $current[4],
						],
					],
					'changes' => [
						'non-commercial' => [
							'long' => $changes[0],
							'short' => $changes[1],
							'spreads' => $changes[2],
						],
						'commercial' => [
							'long' => $changes[3],
							'short' => $changes[4],
						],
					],
					'open-interest' => [
						'current' => $openInterest,
						'change' => $openInterestChange,
						'non-commercial' => [
							'long' => $percent[0],
							'short' => $percent[1],
							'spreads' => $percent[2],
						],
						'commercial' => [
							'long' => $percent[3],
							'short' => $percent[4],
						],
					],
				];
			}
		}

		return $result;
	}
}