parent
fb6c1a0574
commit
033784bfc8
@ -25,19 +25,15 @@ class CienResolver extends MetadataResolver
|
||||
public function resolve(string $url): Metadata
|
||||
{
|
||||
$res = $this->client->get($url);
|
||||
if ($res->getStatusCode() === 200) {
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
|
||||
// 画像URLから有効期限の起点を拾う
|
||||
parse_str(parse_url($metadata->image, PHP_URL_QUERY), $params);
|
||||
if (empty($params['px-time'])) {
|
||||
throw new \RuntimeException('Parameter "px-time" not found. Image=' . $metadata->image . ' Source=' . $url);
|
||||
}
|
||||
$metadata->expires_at = Carbon::createFromTimestamp($params['px-time'])->addHour(1);
|
||||
|
||||
return $metadata;
|
||||
} else {
|
||||
throw new \RuntimeException("{$res->getStatusCode()}: $url");
|
||||
// 画像URLから有効期限の起点を拾う
|
||||
parse_str(parse_url($metadata->image, PHP_URL_QUERY), $params);
|
||||
if (empty($params['px-time'])) {
|
||||
throw new \RuntimeException('Parameter "px-time" not found. Image=' . $metadata->image . ' Source=' . $url);
|
||||
}
|
||||
$metadata->expires_at = Carbon::createFromTimestamp($params['px-time'])->addHour(1);
|
||||
|
||||
return $metadata;
|
||||
}
|
||||
}
|
||||
|
@ -73,59 +73,55 @@ class DLsiteResolver implements Resolver
|
||||
}
|
||||
|
||||
$res = $this->client->get($url);
|
||||
if ($res->getStatusCode() === 200) {
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
|
||||
$dom = new \DOMDocument();
|
||||
@$dom->loadHTML(mb_convert_encoding($res->getBody(), 'HTML-ENTITIES', 'UTF-8'));
|
||||
$xpath = new \DOMXPath($dom);
|
||||
$dom = new \DOMDocument();
|
||||
@$dom->loadHTML(mb_convert_encoding($res->getBody(), 'HTML-ENTITIES', 'UTF-8'));
|
||||
$xpath = new \DOMXPath($dom);
|
||||
|
||||
// OGPタイトルから[]に囲まれているmakerを取得する
|
||||
// 複数の作者がいる場合スペース区切りになるためexplodeしている
|
||||
// スペースを含むmakerの場合名前の一部しか取れないが動作には問題ない
|
||||
preg_match('~ \[([^\[\]]*)\] (予告作品 )?\| DLsite(がるまに)?$~', $metadata->title, $match);
|
||||
$makers = explode(' ', $match[1]);
|
||||
// OGPタイトルから[]に囲まれているmakerを取得する
|
||||
// 複数の作者がいる場合スペース区切りになるためexplodeしている
|
||||
// スペースを含むmakerの場合名前の一部しか取れないが動作には問題ない
|
||||
preg_match('~ \[([^\[\]]*)\] (予告作品 )?\| DLsite(がるまに)?$~', $metadata->title, $match);
|
||||
$makers = explode(' ', $match[1]);
|
||||
|
||||
//フォローボタン(.btn_follow)はテキストを含んでしまうことがあるので要素を削除しておく
|
||||
$followButtonNode = $xpath->query('//*[@class="btn_follow"]')->item(0);
|
||||
$followButtonNode->parentNode->removeChild($followButtonNode);
|
||||
//フォローボタン(.btn_follow)はテキストを含んでしまうことがあるので要素を削除しておく
|
||||
$followButtonNode = $xpath->query('//*[@class="btn_follow"]')->item(0);
|
||||
$followButtonNode->parentNode->removeChild($followButtonNode);
|
||||
|
||||
// maker, makerHeadを探す
|
||||
// maker, makerHeadを探す
|
||||
|
||||
// makers
|
||||
// #work_makerから「makerを含むテキスト」を持つ要素を持つtdを探す
|
||||
// 作者名単体の場合もあるし、"作者A / 作者B"のようになることもある
|
||||
$makersNode = $xpath->query('//*[@id="work_maker"]//*[contains(text(), "' . $makers[0] . '")]/ancestor::td')->item(0);
|
||||
// nbspをspaceに置換
|
||||
$makers = trim(str_replace("\xc2\xa0", ' ', $makersNode->textContent));
|
||||
// makers
|
||||
// #work_makerから「makerを含むテキスト」を持つ要素を持つtdを探す
|
||||
// 作者名単体の場合もあるし、"作者A / 作者B"のようになることもある
|
||||
$makersNode = $xpath->query('//*[@id="work_maker"]//*[contains(text(), "' . $makers[0] . '")]/ancestor::td')->item(0);
|
||||
// nbspをspaceに置換
|
||||
$makers = trim(str_replace("\xc2\xa0", ' ', $makersNode->textContent));
|
||||
|
||||
// makersHaed
|
||||
// $makerNode(td)に対するthを探す
|
||||
// "著者", "サークル名", "ブランド名"など
|
||||
$makersHeadNode = $xpath->query('preceding-sibling::th', $makersNode)->item(0);
|
||||
$makersHead = trim($makersHeadNode->textContent);
|
||||
// makersHaed
|
||||
// $makerNode(td)に対するthを探す
|
||||
// "著者", "サークル名", "ブランド名"など
|
||||
$makersHeadNode = $xpath->query('preceding-sibling::th', $makersNode)->item(0);
|
||||
$makersHead = trim($makersHeadNode->textContent);
|
||||
|
||||
// 余分な文を消す
|
||||
// 余分な文を消す
|
||||
|
||||
// OGPタイトルから作者名とサイト名を消す
|
||||
$metadata->title = trim(preg_replace('~ \[[^\[\]]*\] (予告作品 )?\| DLsite(がるまに)?$~', '', $metadata->title));
|
||||
// OGPタイトルから作者名とサイト名を消す
|
||||
$metadata->title = trim(preg_replace('~ \[[^\[\]]*\] (予告作品 )?\| DLsite(がるまに)?$~', '', $metadata->title));
|
||||
|
||||
// OGP説明文から定型文を消す
|
||||
if (strpos($url, 'dlsite.com/eng/') || strpos($url, 'dlsite.com/ecchi-eng/')) {
|
||||
$metadata->description = preg_replace('~DLsite.+ is a download shop for .+With a huge selection of products, we\'re sure you\'ll find whatever tickles your fancy\. DLsite is one of the greatest indie contents download shops in Japan\.$~', '', $metadata->description);
|
||||
} else {
|
||||
$metadata->description = preg_replace('~「DLsite.+」は.+のダウンロードショップ。お気に入りの作品をすぐダウンロードできてすぐ楽しめる!毎日更新しているのであなたが探している作品にきっと出会えます。国内最大級の二次元総合ダウンロードショップ「DLsite」!$~', '', $metadata->description);
|
||||
}
|
||||
$metadata->description = trim(strip_tags($metadata->description));
|
||||
|
||||
// 整形
|
||||
$metadata->description = $makersHead . ': ' . $makers . PHP_EOL . $metadata->description;
|
||||
$metadata->image = str_replace('img_sam.jpg', 'img_main.jpg', $metadata->image);
|
||||
$metadata->tags = $this->extractTags($res->getBody());
|
||||
|
||||
return $metadata;
|
||||
// OGP説明文から定型文を消す
|
||||
if (strpos($url, 'dlsite.com/eng/') || strpos($url, 'dlsite.com/ecchi-eng/')) {
|
||||
$metadata->description = preg_replace('~DLsite.+ is a download shop for .+With a huge selection of products, we\'re sure you\'ll find whatever tickles your fancy\. DLsite is one of the greatest indie contents download shops in Japan\.$~', '', $metadata->description);
|
||||
} else {
|
||||
throw new \RuntimeException("{$res->getStatusCode()}: $url");
|
||||
$metadata->description = preg_replace('~「DLsite.+」は.+のダウンロードショップ。お気に入りの作品をすぐダウンロードできてすぐ楽しめる!毎日更新しているのであなたが探している作品にきっと出会えます。国内最大級の二次元総合ダウンロードショップ「DLsite」!$~', '', $metadata->description);
|
||||
}
|
||||
$metadata->description = trim(strip_tags($metadata->description));
|
||||
|
||||
// 整形
|
||||
$metadata->description = $makersHead . ': ' . $makers . PHP_EOL . $metadata->description;
|
||||
$metadata->image = str_replace('img_sam.jpg', 'img_main.jpg', $metadata->image);
|
||||
$metadata->tags = $this->extractTags($res->getBody());
|
||||
|
||||
return $metadata;
|
||||
}
|
||||
}
|
||||
|
@ -24,21 +24,17 @@ class FC2ContentsResolver implements Resolver
|
||||
public function resolve(string $url): Metadata
|
||||
{
|
||||
$res = $this->client->get($url);
|
||||
if ($res->getStatusCode() === 200) {
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
|
||||
$dom = new \DOMDocument();
|
||||
@$dom->loadHTML(mb_convert_encoding($res->getBody(), 'HTML-ENTITIES', 'UTF-8'));
|
||||
$xpath = new \DOMXPath($dom);
|
||||
$dom = new \DOMDocument();
|
||||
@$dom->loadHTML(mb_convert_encoding($res->getBody(), 'HTML-ENTITIES', 'UTF-8'));
|
||||
$xpath = new \DOMXPath($dom);
|
||||
|
||||
$thumbnailNode = $xpath->query('//*[@class="main_thum_img"]/a')->item(0);
|
||||
if ($thumbnailNode) {
|
||||
$metadata->image = preg_replace('~^http:~', 'https:', $thumbnailNode->getAttribute('href'));
|
||||
}
|
||||
|
||||
return $metadata;
|
||||
} else {
|
||||
throw new \RuntimeException("{$res->getStatusCode()}: $url");
|
||||
$thumbnailNode = $xpath->query('//*[@class="main_thum_img"]/a')->item(0);
|
||||
if ($thumbnailNode) {
|
||||
$metadata->image = preg_replace('~^http:~', 'https:', $thumbnailNode->getAttribute('href'));
|
||||
}
|
||||
|
||||
return $metadata;
|
||||
}
|
||||
}
|
||||
|
@ -28,29 +28,25 @@ class FantiaResolver implements Resolver
|
||||
$postId = $match[0];
|
||||
|
||||
$res = $this->client->get($url);
|
||||
if ($res->getStatusCode() === 200) {
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
|
||||
$dom = new \DOMDocument();
|
||||
@$dom->loadHTML(mb_convert_encoding($res->getBody(), 'HTML-ENTITIES', 'UTF-8'));
|
||||
$xpath = new \DOMXPath($dom);
|
||||
$dom = new \DOMDocument();
|
||||
@$dom->loadHTML(mb_convert_encoding($res->getBody(), 'HTML-ENTITIES', 'UTF-8'));
|
||||
$xpath = new \DOMXPath($dom);
|
||||
|
||||
$node = $xpath->query("//meta[@property='twitter:image']")->item(0);
|
||||
$ogpUrl = $node->getAttribute('content');
|
||||
$node = $xpath->query("//meta[@property='twitter:image']")->item(0);
|
||||
$ogpUrl = $node->getAttribute('content');
|
||||
|
||||
// 投稿に画像がない場合(ogp.jpgでない場合)のみ大きい画像に変換する
|
||||
if ($ogpUrl != 'http://fantia.jp/images/ogp.jpg') {
|
||||
preg_match("~https://fantia\.s3\.amazonaws\.com/uploads/post/file/{$postId}/ogp_(.*?)\.(jpg|png)~", $ogpUrl, $match);
|
||||
$uuid = $match[1];
|
||||
$extension = $match[2];
|
||||
// 投稿に画像がない場合(ogp.jpgでない場合)のみ大きい画像に変換する
|
||||
if ($ogpUrl != 'http://fantia.jp/images/ogp.jpg') {
|
||||
preg_match("~https://fantia\.s3\.amazonaws\.com/uploads/post/file/{$postId}/ogp_(.*?)\.(jpg|png)~", $ogpUrl, $match);
|
||||
$uuid = $match[1];
|
||||
$extension = $match[2];
|
||||
|
||||
// 大きい画像に変換
|
||||
$metadata->image = "https://c.fantia.jp/uploads/post/file/{$postId}/main_{$uuid}.{$extension}";
|
||||
}
|
||||
|
||||
return $metadata;
|
||||
} else {
|
||||
throw new \RuntimeException("{$res->getStatusCode()}: $url");
|
||||
// 大きい画像に変換
|
||||
$metadata->image = "https://c.fantia.jp/uploads/post/file/{$postId}/main_{$uuid}.{$extension}";
|
||||
}
|
||||
|
||||
return $metadata;
|
||||
}
|
||||
}
|
||||
|
@ -24,14 +24,10 @@ class FanzaResolver implements Resolver
|
||||
public function resolve(string $url): Metadata
|
||||
{
|
||||
$res = $this->client->get($url);
|
||||
if ($res->getStatusCode() === 200) {
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
$metadata->image = preg_replace("~(pr|ps)\.jpg$~", 'pl.jpg', $metadata->image);
|
||||
$metadata->description = str_replace('<>', '', $metadata->description);
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
$metadata->image = preg_replace("~(pr|ps)\.jpg$~", 'pl.jpg', $metadata->image);
|
||||
$metadata->description = str_replace('<>', '', $metadata->description);
|
||||
|
||||
return $metadata;
|
||||
} else {
|
||||
throw new \RuntimeException("{$res->getStatusCode()}: $url");
|
||||
}
|
||||
return $metadata;
|
||||
}
|
||||
}
|
||||
|
@ -20,45 +20,41 @@ class IwaraResolver implements Resolver
|
||||
public function resolve(string $url): Metadata
|
||||
{
|
||||
$res = $this->client->get($url);
|
||||
if ($res->getStatusCode() === 200) {
|
||||
$metadata = new Metadata();
|
||||
$html = (string) $res->getBody();
|
||||
$crawler = new Crawler($html);
|
||||
$metadata = new Metadata();
|
||||
$html = (string) $res->getBody();
|
||||
$crawler = new Crawler($html);
|
||||
|
||||
$infoElements = $crawler->filter('#video-player + div, .field-name-field-video-url + div, .field-name-field-images + div');
|
||||
$title = $infoElements->filter('h1.title')->text();
|
||||
$author = $infoElements->filter('.username')->text();
|
||||
$description = $infoElements->filter('.field-type-text-with-summary')->text('');
|
||||
$tags = $infoElements->filter('a[href^="/videos"], a[href^="/images"]')->extract('_text');
|
||||
// 役に立たないタグを削除する
|
||||
$tags = array_values(array_diff($tags, ['Uncategorized', 'Other']));
|
||||
array_push($tags, $author);
|
||||
$infoElements = $crawler->filter('#video-player + div, .field-name-field-video-url + div, .field-name-field-images + div');
|
||||
$title = $infoElements->filter('h1.title')->text();
|
||||
$author = $infoElements->filter('.username')->text();
|
||||
$description = $infoElements->filter('.field-type-text-with-summary')->text('');
|
||||
$tags = $infoElements->filter('a[href^="/videos"], a[href^="/images"]')->extract('_text');
|
||||
// 役に立たないタグを削除する
|
||||
$tags = array_values(array_diff($tags, ['Uncategorized', 'Other']));
|
||||
array_push($tags, $author);
|
||||
|
||||
$metadata->title = $title;
|
||||
$metadata->description = '投稿者: ' . $author . PHP_EOL . $description;
|
||||
$metadata->tags = $tags;
|
||||
$metadata->title = $title;
|
||||
$metadata->description = '投稿者: ' . $author . PHP_EOL . $description;
|
||||
$metadata->tags = $tags;
|
||||
|
||||
// iwara video
|
||||
if ($crawler->filter('#video-player')->count()) {
|
||||
$metadata->image = 'https:' . $crawler->filter('#video-player')->attr('poster');
|
||||
}
|
||||
|
||||
// youtube
|
||||
if ($crawler->filter('iframe[src^="//www.youtube.com"]')->count()) {
|
||||
if (preg_match('~youtube\.com/embed/(\S+)\?~', $crawler->filter('iframe[src^="//www.youtube.com"]')->attr('src'), $matches) === 1) {
|
||||
$youtubeId = $matches[1];
|
||||
$metadata->image = 'https://img.youtube.com/vi/' . $youtubeId . '/maxresdefault.jpg';
|
||||
}
|
||||
}
|
||||
|
||||
// images
|
||||
if ($crawler->filter('.field-name-field-images')->count()) {
|
||||
$metadata->image = 'https:' . $crawler->filter('.field-name-field-images a')->first()->attr('href');
|
||||
}
|
||||
|
||||
return $metadata;
|
||||
} else {
|
||||
throw new \RuntimeException("{$res->getStatusCode()}: $url");
|
||||
// iwara video
|
||||
if ($crawler->filter('#video-player')->count()) {
|
||||
$metadata->image = 'https:' . $crawler->filter('#video-player')->attr('poster');
|
||||
}
|
||||
|
||||
// youtube
|
||||
if ($crawler->filter('iframe[src^="//www.youtube.com"]')->count()) {
|
||||
if (preg_match('~youtube\.com/embed/(\S+)\?~', $crawler->filter('iframe[src^="//www.youtube.com"]')->attr('src'), $matches) === 1) {
|
||||
$youtubeId = $matches[1];
|
||||
$metadata->image = 'https://img.youtube.com/vi/' . $youtubeId . '/maxresdefault.jpg';
|
||||
}
|
||||
}
|
||||
|
||||
// images
|
||||
if ($crawler->filter('.field-name-field-images')->count()) {
|
||||
$metadata->image = 'https:' . $crawler->filter('.field-name-field-images a')->first()->attr('href');
|
||||
}
|
||||
|
||||
return $metadata;
|
||||
}
|
||||
}
|
||||
|
@ -24,33 +24,28 @@ class KomifloResolver implements Resolver
|
||||
$id = $matches[1];
|
||||
|
||||
$res = $this->client->get('https://api.komiflo.com/content/id/' . $id);
|
||||
if ($res->getStatusCode() === 200) {
|
||||
$json = json_decode($res->getBody()->getContents(), true);
|
||||
$metadata = new Metadata();
|
||||
$json = json_decode($res->getBody()->getContents(), true);
|
||||
$metadata = new Metadata();
|
||||
|
||||
$metadata->title = $json['content']['data']['title'] ?? '';
|
||||
$metadata->description = ($json['content']['attributes']['artists']['children'][0]['data']['name'] ?? '?') .
|
||||
' - ' .
|
||||
($json['content']['parents'][0]['data']['title'] ?? '?');
|
||||
$metadata->image = 'https://t.komiflo.com/564_mobile_large_3x/' . $json['content']['named_imgs']['cover']['filename'];
|
||||
$metadata->title = $json['content']['data']['title'] ?? '';
|
||||
$metadata->description = ($json['content']['attributes']['artists']['children'][0]['data']['name'] ?? '?') .
|
||||
' - ' . ($json['content']['parents'][0]['data']['title'] ?? '?');
|
||||
$metadata->image = 'https://t.komiflo.com/564_mobile_large_3x/' . $json['content']['named_imgs']['cover']['filename'];
|
||||
|
||||
// 作者情報
|
||||
if (!empty($json['content']['attributes']['artists']['children'])) {
|
||||
foreach ($json['content']['attributes']['artists']['children'] as $artist) {
|
||||
$metadata->tags[] = preg_replace('/\s/', '_', $artist['data']['name']);
|
||||
}
|
||||
// 作者情報
|
||||
if (!empty($json['content']['attributes']['artists']['children'])) {
|
||||
foreach ($json['content']['attributes']['artists']['children'] as $artist) {
|
||||
$metadata->tags[] = preg_replace('/\s/', '_', $artist['data']['name']);
|
||||
}
|
||||
|
||||
// タグ
|
||||
if (!empty($json['content']['attributes']['tags']['children'])) {
|
||||
foreach ($json['content']['attributes']['tags']['children'] as $tag) {
|
||||
$metadata->tags[] = preg_replace('/\s/', '_', $tag['data']['name']);
|
||||
}
|
||||
}
|
||||
|
||||
return $metadata;
|
||||
} else {
|
||||
throw new \RuntimeException("{$res->getStatusCode()}: $url");
|
||||
}
|
||||
|
||||
// タグ
|
||||
if (!empty($json['content']['attributes']['tags']['children'])) {
|
||||
foreach ($json['content']['attributes']['tags']['children'] as $tag) {
|
||||
$metadata->tags[] = preg_replace('/\s/', '_', $tag['data']['name']);
|
||||
}
|
||||
}
|
||||
|
||||
return $metadata;
|
||||
}
|
||||
}
|
||||
|
@ -27,46 +27,42 @@ class MelonbooksResolver implements Resolver
|
||||
$cookieJar = CookieJar::fromArray(['AUTH_ADULT' => '1'], 'www.melonbooks.co.jp');
|
||||
|
||||
$res = $this->client->get($url, ['cookies' => $cookieJar]);
|
||||
if ($res->getStatusCode() === 200) {
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
$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');
|
||||
$dom = new \DOMDocument();
|
||||
@$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 $metadata;
|
||||
} else {
|
||||
throw new \RuntimeException("{$res->getStatusCode()}: $url");
|
||||
// censoredフラグの除去
|
||||
if (mb_strpos($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;
|
||||
}
|
||||
}
|
||||
|
@ -27,34 +27,30 @@ class NarouResolver implements Resolver
|
||||
$cookieJar = CookieJar::fromArray(['over18' => 'yes'], '.syosetu.com');
|
||||
|
||||
$res = $this->client->get($url, ['cookies' => $cookieJar]);
|
||||
if ($res->getStatusCode() === 200) {
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
$metadata->description = '';
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
$metadata->description = '';
|
||||
|
||||
$dom = new \DOMDocument();
|
||||
@$dom->loadHTML(mb_convert_encoding($res->getBody(), 'HTML-ENTITIES', 'ASCII,JIS,UTF-8,eucJP-win,SJIS-win'));
|
||||
$xpath = new \DOMXPath($dom);
|
||||
$dom = new \DOMDocument();
|
||||
@$dom->loadHTML(mb_convert_encoding($res->getBody(), 'HTML-ENTITIES', 'ASCII,JIS,UTF-8,eucJP-win,SJIS-win'));
|
||||
$xpath = new \DOMXPath($dom);
|
||||
|
||||
$description = [];
|
||||
$description = [];
|
||||
|
||||
// 作者名
|
||||
$writerNodes = $xpath->query('//*[contains(@class, "novel_writername")]');
|
||||
if ($writerNodes->length !== 0 && !empty($writerNodes->item(0)->textContent)) {
|
||||
$description[] = trim($writerNodes->item(0)->textContent);
|
||||
}
|
||||
|
||||
// あらすじ
|
||||
$exNodes = $xpath->query('//*[@id="novel_ex"]');
|
||||
if ($exNodes->length !== 0 && !empty($exNodes->item(0)->textContent)) {
|
||||
$summary = trim($exNodes->item(0)->textContent);
|
||||
$description[] = mb_strimwidth($summary, 0, 101, '…'); // 100 + '…'(1)
|
||||
}
|
||||
|
||||
$metadata->description = implode(' / ', $description);
|
||||
|
||||
return $metadata;
|
||||
} else {
|
||||
throw new \RuntimeException("{$res->getStatusCode()}: $url");
|
||||
// 作者名
|
||||
$writerNodes = $xpath->query('//*[contains(@class, "novel_writername")]');
|
||||
if ($writerNodes->length !== 0 && !empty($writerNodes->item(0)->textContent)) {
|
||||
$description[] = trim($writerNodes->item(0)->textContent);
|
||||
}
|
||||
|
||||
// あらすじ
|
||||
$exNodes = $xpath->query('//*[@id="novel_ex"]');
|
||||
if ($exNodes->length !== 0 && !empty($exNodes->item(0)->textContent)) {
|
||||
$summary = trim($exNodes->item(0)->textContent);
|
||||
$description[] = mb_strimwidth($summary, 0, 101, '…'); // 100 + '…'(1)
|
||||
}
|
||||
|
||||
$metadata->description = implode(' / ', $description);
|
||||
|
||||
return $metadata;
|
||||
}
|
||||
}
|
||||
|
@ -32,32 +32,28 @@ class NijieResolver implements Resolver
|
||||
}
|
||||
|
||||
$res = $this->client->get($url);
|
||||
if ($res->getStatusCode() === 200) {
|
||||
$html = (string) $res->getBody();
|
||||
$metadata = $this->ogpResolver->parse($html);
|
||||
$crawler = new Crawler($html);
|
||||
$html = (string) $res->getBody();
|
||||
$metadata = $this->ogpResolver->parse($html);
|
||||
$crawler = new Crawler($html);
|
||||
|
||||
// DomCrawler内でjson内の日本語がHTMLエンティティに変換されるのでhtml_entity_decode
|
||||
$json = html_entity_decode($crawler->filter('script[type="application/ld+json"]')->first()->text());
|
||||
// DomCrawler内でjson内の日本語がHTMLエンティティに変換されるのでhtml_entity_decode
|
||||
$json = html_entity_decode($crawler->filter('script[type="application/ld+json"]')->first()->text());
|
||||
|
||||
// 改行がそのまま入っていることがあるのでデコード前にエスケープが必要
|
||||
$data = json_decode(preg_replace('/\r?\n/', '\n', $json), true);
|
||||
// 改行がそのまま入っていることがあるのでデコード前にエスケープが必要
|
||||
$data = json_decode(preg_replace('/\r?\n/', '\n', $json), true);
|
||||
|
||||
$metadata->title = $data['name'];
|
||||
$metadata->description = '投稿者: ' . $data['author']['name'] . PHP_EOL . $data['description'];
|
||||
if (
|
||||
isset($data['thumbnailUrl']) &&
|
||||
!ends_with($data['thumbnailUrl'], '.gif') &&
|
||||
!ends_with($data['thumbnailUrl'], '.mp4')
|
||||
) {
|
||||
// サムネイルからメイン画像に
|
||||
$metadata->image = str_replace('__rs_l160x160/', '', $data['thumbnailUrl']);
|
||||
}
|
||||
$metadata->tags = $crawler->filter('#view-tag span.tag_name')->extract('_text');
|
||||
|
||||
return $metadata;
|
||||
} else {
|
||||
throw new \RuntimeException("{$res->getStatusCode()}: $url");
|
||||
$metadata->title = $data['name'];
|
||||
$metadata->description = '投稿者: ' . $data['author']['name'] . PHP_EOL . $data['description'];
|
||||
if (
|
||||
isset($data['thumbnailUrl']) &&
|
||||
!ends_with($data['thumbnailUrl'], '.gif') &&
|
||||
!ends_with($data['thumbnailUrl'], '.mp4')
|
||||
) {
|
||||
// サムネイルからメイン画像に
|
||||
$metadata->image = str_replace('__rs_l160x160/', '', $data['thumbnailUrl']);
|
||||
}
|
||||
$metadata->tags = $crawler->filter('#view-tag span.tag_name')->extract('_text');
|
||||
|
||||
return $metadata;
|
||||
}
|
||||
}
|
||||
|
@ -19,11 +19,7 @@ class OGPResolver implements Resolver, Parser
|
||||
public function resolve(string $url): Metadata
|
||||
{
|
||||
$res = $this->client->get($url);
|
||||
if ($res->getStatusCode() === 200) {
|
||||
return $this->parse($res->getBody());
|
||||
} else {
|
||||
throw new \RuntimeException("{$res->getStatusCode()}: $url");
|
||||
}
|
||||
return $this->parse($res->getBody());
|
||||
}
|
||||
|
||||
public function parse(string $html): Metadata
|
||||
|
@ -25,18 +25,14 @@ class PatreonResolver implements Resolver
|
||||
public function resolve(string $url): Metadata
|
||||
{
|
||||
$res = $this->client->get($url);
|
||||
if ($res->getStatusCode() === 200) {
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
|
||||
parse_str(parse_url($metadata->image, PHP_URL_QUERY), $query);
|
||||
if (isset($query['token-time'])) {
|
||||
$expires_at_unixtime = $query['token-time'];
|
||||
$metadata->expires_at = Carbon::createFromTimestamp($expires_at_unixtime);
|
||||
}
|
||||
|
||||
return $metadata;
|
||||
} else {
|
||||
throw new \RuntimeException("{$res->getStatusCode()}: $url");
|
||||
parse_str(parse_url($metadata->image, PHP_URL_QUERY), $query);
|
||||
if (isset($query['token-time'])) {
|
||||
$expires_at_unixtime = $query['token-time'];
|
||||
$metadata->expires_at = Carbon::createFromTimestamp($expires_at_unixtime);
|
||||
}
|
||||
|
||||
return $metadata;
|
||||
}
|
||||
}
|
||||
|
@ -38,14 +38,10 @@ class PixivResolver implements Resolver
|
||||
{
|
||||
if (preg_match('~www\.pixiv\.net/user/\d+/series/\d+~', $url, $matches)) {
|
||||
$res = $this->client->get($url);
|
||||
if ($res->getStatusCode() === 200) {
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
$metadata->image = $this->proxize($metadata->image);
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
$metadata->image = $this->proxize($metadata->image);
|
||||
|
||||
return $metadata;
|
||||
} else {
|
||||
throw new \RuntimeException("{$res->getStatusCode()}: $url");
|
||||
}
|
||||
return $metadata;
|
||||
}
|
||||
|
||||
parse_str(parse_url($url, PHP_URL_QUERY), $params);
|
||||
@ -58,32 +54,28 @@ class PixivResolver implements Resolver
|
||||
}
|
||||
|
||||
$res = $this->client->get('https://www.pixiv.net/ajax/illust/' . $illustId);
|
||||
if ($res->getStatusCode() === 200) {
|
||||
$json = json_decode($res->getBody()->getContents(), true);
|
||||
$metadata = new Metadata();
|
||||
$json = json_decode($res->getBody()->getContents(), true);
|
||||
$metadata = new Metadata();
|
||||
|
||||
$metadata->title = $json['body']['illustTitle'] ?? '';
|
||||
$metadata->description = '投稿者: ' . $json['body']['userName'] . PHP_EOL . strip_tags(str_replace('<br />', PHP_EOL, $json['body']['illustComment'] ?? ''));
|
||||
$metadata->image = $this->proxize($json['body']['urls']['regular'] ?? '');
|
||||
$metadata->title = $json['body']['illustTitle'] ?? '';
|
||||
$metadata->description = '投稿者: ' . $json['body']['userName'] . PHP_EOL . strip_tags(str_replace('<br />', PHP_EOL, $json['body']['illustComment'] ?? ''));
|
||||
$metadata->image = $this->proxize($json['body']['urls']['regular'] ?? '');
|
||||
|
||||
// ページ数の指定がある場合は画像URLをそのページにする
|
||||
if ($page != 0) {
|
||||
$metadata->image = str_replace('_p0', '_p'.$page, $metadata->image);
|
||||
}
|
||||
// ページ数の指定がある場合は画像URLをそのページにする
|
||||
if ($page != 0) {
|
||||
$metadata->image = str_replace('_p0', '_p' . $page, $metadata->image);
|
||||
}
|
||||
|
||||
// タグ
|
||||
if (!empty($json['body']['tags']['tags'])) {
|
||||
foreach ($json['body']['tags']['tags'] as $tag) {
|
||||
// 一部の固定キーワードは無視
|
||||
if (array_search($tag['tag'], ['R-18', 'イラスト', 'pixiv', 'ピクシブ'], true) === false) {
|
||||
$metadata->tags[] = preg_replace('/\s/', '_', $tag['tag']);
|
||||
}
|
||||
// タグ
|
||||
if (!empty($json['body']['tags']['tags'])) {
|
||||
foreach ($json['body']['tags']['tags'] as $tag) {
|
||||
// 一部の固定キーワードは無視
|
||||
if (array_search($tag['tag'], ['R-18', 'イラスト', 'pixiv', 'ピクシブ'], true) === false) {
|
||||
$metadata->tags[] = preg_replace('/\s/', '_', $tag['tag']);
|
||||
}
|
||||
}
|
||||
|
||||
return $metadata;
|
||||
} else {
|
||||
throw new \RuntimeException("{$res->getStatusCode()}: $url");
|
||||
}
|
||||
|
||||
return $metadata;
|
||||
}
|
||||
}
|
||||
|
@ -24,21 +24,17 @@ class PlurkResolver implements Resolver
|
||||
public function resolve(string $url): Metadata
|
||||
{
|
||||
$res = $this->client->get($url);
|
||||
if ($res->getStatusCode() === 200) {
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
|
||||
$dom = new \DOMDocument();
|
||||
@$dom->loadHTML(mb_convert_encoding($res->getBody(), 'HTML-ENTITIES', 'UTF-8'));
|
||||
$xpath = new \DOMXPath($dom);
|
||||
$imageNode = $xpath->query('//div[@class="text_holder"]/a[1]')->item(0);
|
||||
$dom = new \DOMDocument();
|
||||
@$dom->loadHTML(mb_convert_encoding($res->getBody(), 'HTML-ENTITIES', 'UTF-8'));
|
||||
$xpath = new \DOMXPath($dom);
|
||||
$imageNode = $xpath->query('//div[@class="text_holder"]/a[1]')->item(0);
|
||||
|
||||
if ($imageNode) {
|
||||
$metadata->image = $imageNode->getAttribute('href');
|
||||
}
|
||||
|
||||
return $metadata;
|
||||
} else {
|
||||
throw new \RuntimeException("{$res->getStatusCode()}: $url");
|
||||
if ($imageNode) {
|
||||
$metadata->image = $imageNode->getAttribute('href');
|
||||
}
|
||||
|
||||
return $metadata;
|
||||
}
|
||||
}
|
||||
|
@ -24,21 +24,17 @@ class SteamResolver implements Resolver
|
||||
$appid = $matches[1];
|
||||
|
||||
$res = $this->client->get('https://store.steampowered.com/api/appdetails/?l=japanese&appids=' . $appid);
|
||||
if ($res->getStatusCode() === 200) {
|
||||
$json = json_decode($res->getBody()->getContents(), true);
|
||||
if ($json[$appid]['success'] === false) {
|
||||
throw new \RuntimeException("API response [$appid][success] is false: $url");
|
||||
}
|
||||
$data = $json[$appid]['data'];
|
||||
$metadata = new Metadata();
|
||||
|
||||
$metadata->title = $data['name'] ?? '';
|
||||
$metadata->description = strip_tags(str_replace('<br />', PHP_EOL, html_entity_decode($data['short_description'] ?? '')));
|
||||
$metadata->image = $data['header_image'] ?? '';
|
||||
|
||||
return $metadata;
|
||||
} else {
|
||||
throw new \RuntimeException("{$res->getStatusCode()}: $url");
|
||||
$json = json_decode($res->getBody()->getContents(), true);
|
||||
if ($json[$appid]['success'] === false) {
|
||||
throw new \RuntimeException("API response [$appid][success] is false: $url");
|
||||
}
|
||||
$data = $json[$appid]['data'];
|
||||
$metadata = new Metadata();
|
||||
|
||||
$metadata->title = $data['name'] ?? '';
|
||||
$metadata->description = strip_tags(str_replace('<br />', PHP_EOL, html_entity_decode($data['short_description'] ?? '')));
|
||||
$metadata->image = $data['header_image'] ?? '';
|
||||
|
||||
return $metadata;
|
||||
}
|
||||
}
|
||||
|
@ -25,20 +25,16 @@ class ToranoanaResolver implements Resolver
|
||||
public function resolve(string $url): Metadata
|
||||
{
|
||||
$res = $this->client->get($url);
|
||||
if ($res->getStatusCode() === 200) {
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
$metadata = $this->ogpResolver->parse($res->getBody());
|
||||
|
||||
$dom = new \DOMDocument();
|
||||
@$dom->loadHTML(mb_convert_encoding($res->getBody(), 'HTML-ENTITIES', 'UTF-8'));
|
||||
$xpath = new \DOMXPath($dom);
|
||||
$imgNode = $xpath->query('//*[@id="preview"]//img')->item(0);
|
||||
if ($imgNode !== null) {
|
||||
$metadata->image = $imgNode->getAttribute('src');
|
||||
}
|
||||
|
||||
return $metadata;
|
||||
} else {
|
||||
throw new \RuntimeException("{$res->getStatusCode()}: $url");
|
||||
$dom = new \DOMDocument();
|
||||
@$dom->loadHTML(mb_convert_encoding($res->getBody(), 'HTML-ENTITIES', 'UTF-8'));
|
||||
$xpath = new \DOMXPath($dom);
|
||||
$imgNode = $xpath->query('//*[@id="preview"]//img')->item(0);
|
||||
if ($imgNode !== null) {
|
||||
$metadata->image = $imgNode->getAttribute('src');
|
||||
}
|
||||
|
||||
return $metadata;
|
||||
}
|
||||
}
|
||||
|
@ -3,21 +3,12 @@
|
||||
namespace Tests\Unit\MetadataResolver;
|
||||
|
||||
use App\MetadataResolver\OGPResolver;
|
||||
use GuzzleHttp\Exception\ClientException;
|
||||
use Tests\TestCase;
|
||||
|
||||
class OGPResolverTest extends TestCase
|
||||
{
|
||||
use CreateMockedResolver;
|
||||
|
||||
public function testMissingUrl()
|
||||
{
|
||||
$this->createResolver(OGPResolver::class, '', [], 404);
|
||||
|
||||
$this->expectException(\RuntimeException::class);
|
||||
$this->resolver->resolve('http://example.com/404');
|
||||
}
|
||||
|
||||
public function testResolve()
|
||||
{
|
||||
$response = <<< 'HTML'
|
||||
|
Loading…
Reference in New Issue
Block a user