tissue/app/MetadataResolver/MelonbooksResolver.php
2019-09-10 07:03:46 +09:00

69 lines
2.1 KiB
PHP
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<?php
namespace App\MetadataResolver;
use GuzzleHttp\Client;
use GuzzleHttp\Cookie\CookieJar;
class MelonbooksResolver implements Resolver
{
/**
* @var Client
*/
private $client;
/**
* @var OGPResolver
*/
private $ogpResolver;
public function __construct(Client $client, OGPResolver $ogpResolver)
{
$this->client = $client;
$this->ogpResolver = $ogpResolver;
}
public function resolve(string $url): Metadata
{
$cookieJar = CookieJar::fromArray(['AUTH_ADULT' => '1'], 'www.melonbooks.co.jp');
$res = $this->client->get($url, ['cookies' => $cookieJar]);
$metadata = $this->ogpResolver->parse($res->getBody());
$dom = new \DOMDocument();
@$dom->loadHTML(mb_convert_encoding($res->getBody(), 'HTML-ENTITIES', 'UTF-8'));
$xpath = new \DOMXPath($dom);
$descriptionNodelist = $xpath->query('//div[@id="description"]//p');
$specialDescriptionNodelist = $xpath->query('//div[@id="special_description"]//p');
// censoredフラグの除去
if (mb_strpos($metadata->image, '&c=1') !== false) {
$metadata->image = preg_replace('/&c=1/u', '', $metadata->image);
}
// 抽出
preg_match('~^(.+)(.+))の通販・購入はメロンブックス$~', $metadata->title, $match);
$title = $match[1];
$maker = $match[2];
// 整形
$description = 'サークル: ' . $maker . "\n";
if ($specialDescriptionNodelist->length !== 0) {
$description .= trim(str_replace('<br>', "\n", $specialDescriptionNodelist->item(0)->nodeValue)) . "\n";
if ($specialDescriptionNodelist->length === 2) {
$description .= "\n";
$description .= trim(str_replace('<br>', "\n", $specialDescriptionNodelist->item(1)->nodeValue)) . "\n";
}
}
if ($descriptionNodelist->length !== 0) {
$description .= trim(str_replace('<br>', "\n", $descriptionNodelist->item(0)->nodeValue));
}
$metadata->title = $title;
$metadata->description = trim($description);
return $metadata;
}
}