diff --git a/app/Controllers/Mangboard/Crawler/InvenCrawler.php b/app/Controllers/Mangboard/Crawler/InvenCrawler.php index b05dc6a..f24385a 100644 --- a/app/Controllers/Mangboard/Crawler/InvenCrawler.php +++ b/app/Controllers/Mangboard/Crawler/InvenCrawler.php @@ -110,13 +110,17 @@ class InvenCrawler extends MyCrawler $response = $this->getMySocket()->getContent(getenv("inven.list.url.{$this->getBoardName()}")); $this->getSelector($response, getenv("inven.list.tag.{$this->getBoardName()}"))->each( function (Crawler $node) use (&$listInfos): void { + $nickname = $node->filter(getenv("inven.list.item.nickname.tag"))->text(); $hit = $node->filter(getenv("inven.list.item.hit.tag"))->text(); $date = date("Y") . "-" . $node->filter(getenv("inven.list.item.date.tag"))->text(); - $nickname = $node->filter(getenv("inven.list.item.nickname.tag"))->text(); + //title및 detail url $link_node = $node->filter(getenv("inven.list.item.link.tag")); $detail_url = $link_node->attr("href"); $title = $link_node->text(); - $listInfos[] = ['title' => $title, 'nickname' => $nickname, 'detail_url' => $detail_url, 'date' => $date, 'hit' => $hit]; + //title에서 예외사항비교 + if (strpos($title, getenv("inven.list.tag.except.{$this->getBoardName()}")) === false) { + $listInfos[] = ['title' => $title, 'nickname' => $nickname, 'detail_url' => $detail_url, 'date' => $date, 'hit' => $hit]; + } } ); } diff --git a/app/Controllers/Mangboard/Crawler/SirCrawler.php b/app/Controllers/Mangboard/Crawler/SirCrawler.php index df43df0..d194032 100644 --- a/app/Controllers/Mangboard/Crawler/SirCrawler.php +++ b/app/Controllers/Mangboard/Crawler/SirCrawler.php @@ -114,14 +114,15 @@ class SirCrawler extends MyCrawler $response = $this->getMySocket()->getContent(getenv("sir.list.url.{$this->getBoardName()}")); $this->getSelector($response, getenv("sir.list.tag.{$this->getBoardName()}"))->each( function (Crawler $node) use (&$listInfos): void { - $link_node = $node->filter(getenv("sir.list.item.link.tag")); - // href url의 맨 앞이 /가 두개라서 한개를 빼기위함 - $detail_url = $this->changeURLByCrawler($link_node->attr("href")); - // $detail_url = $link_node->attr("href"); - $title = $link_node->text(); $nickname = $node->filter(getenv("sir.list.item.nickname.tag"))->text(); $hit = $node->filter(getenv("sir.list.item.hit.tag"))->text(); + // 작성시간은 detail에서 정의 // $date = $node->filter(getenv("sir.list.item.date.tag"))->text(); + //title및 detail url + $link_node = $node->filter(getenv("sir.list.item.link.tag")); + // href url의 맨 앞이 /sir.kr가 빼기 + $detail_url = $this->changeURLByCrawler($link_node->attr("href")); + $title = $link_node->text(); $listInfos[] = ['title' => $title, 'nickname' => $nickname, 'detail_url' => $detail_url, 'date' => "", 'hit' => $hit]; } ); diff --git a/app/Controllers/Mangboard/Crawler/YamapCrawler.php b/app/Controllers/Mangboard/Crawler/YamapCrawler.php index c32e2c7..87563a6 100644 --- a/app/Controllers/Mangboard/Crawler/YamapCrawler.php +++ b/app/Controllers/Mangboard/Crawler/YamapCrawler.php @@ -71,18 +71,17 @@ class YamapCrawler extends MyCrawler $listInfos[] = $listInfo; } else { $response = $this->getMySocket()->getContent(getenv("yamap.list.url.{$this->getBoardName()}")); - $selector = $this->getSelector($response, getenv("yamap.list.tag.{$this->getBoardName()}")); - $selector->filter(getenv("yamap.list.item.tag.{$this->getBoardName()}"))->each( + $this->getSelector($response, getenv("yamap.list.tag.{$this->getBoardName()}"))->each( function (Crawler $node) use (&$listInfos): void { + $nickname = $node->filter(getenv("yamap.list.item.nickname.tag"))->text(); $hit = $node->filter(getenv("yamap.list.item.hit.tag"))->text(); $date = $node->filter(getenv("yamap.list.item.date.tag"))->text(); - $nickname = $node->filter(getenv("yamap.list.item.nickname.tag"))->text(); - //bbs_item에서 span.g_nickname 객체를 찾아서 작성자가 "관리자" 아닌지 확인 후 Return Bool - if ($nickname != getenv("yamap.list.item.nickname.except")) { - //작성자가 "관리자"가 아닌 게시물이면 해당 bbs_item에서 a.list_subject 객체를 찾아서 - $link_node = $node->filter(getenv("yamap.list.item.link.tag")); - $detail_url = $link_node->attr("href"); - $title = $link_node->children()->last()->text(); + //title및 detail url + $link_node = $node->filter(getenv("yamap.list.item.link.tag")); + $detail_url = $link_node->attr("href"); + $title = $link_node->children()->last()->text(); + //title에서 예외사항비교 + if (strpos($title, getenv("yamap.list.tag.except.{$this->getBoardName()}")) === false) { $listInfos[] = ['title' => $title, 'nickname' => $nickname, 'detail_url' => $detail_url, 'date' => $date, 'hit' => $hit]; } } diff --git a/app/Controllers/Mangboard/Crawler/YamoonCrawler.php b/app/Controllers/Mangboard/Crawler/YamoonCrawler.php index bf7da7a..4213fbd 100644 --- a/app/Controllers/Mangboard/Crawler/YamoonCrawler.php +++ b/app/Controllers/Mangboard/Crawler/YamoonCrawler.php @@ -82,9 +82,11 @@ class YamoonCrawler extends MyCrawler $response = $this->getMySocket()->getContent(getenv("yamoon.list.url.{$this->getBoardName()}")); $this->getSelector($response, getenv("yamoon.list.tag.{$this->getBoardName()}"))->each( function (Crawler $node) use (&$listInfos): void { + //title및 detail url $link_node = $node->filter(getenv("yamoon.list.item.link.tag")); $detail_url = $link_node->attr("href"); $title = $link_node->text(); + //기타정보기 |로 구분되어 있어 작업 $info_node = $node->filter(getenv("yamoon.list.item.info.tag")); $infos = explode("|", $info_node->text()); $listInfos[] = ['title' => $title, 'detail_url' => $detail_url, 'nickname' => trim($infos[0]), 'hit' => trim($infos[2]), 'date' => trim($infos[4])];