From 66939341a357de3b8492b3a9a8ead4d1f797824c Mon Sep 17 00:00:00 2001
From: ROMANGOLIENKO <romangolienko@yandex.ru>
Date: Fri, 26 Jan 2024 14:45:33 +0300
Subject: [PATCH] newScrapper

---
 .gitignore                            |  1 +
 app/Services/PageScrapper.php         | 39 +++++++++++++++++++++++++++
 resources/views/menu/course.blade.php | 36 ++++++++++++++-----------
 3 files changed, 61 insertions(+), 15 deletions(-)

diff --git a/.gitignore b/.gitignore
index b01c8c9..2749dec 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,4 @@
+/public/img/icons/play-button.png
 /.phpunit.cache
 /node_modules
 /public/build
diff --git a/app/Services/PageScrapper.php b/app/Services/PageScrapper.php
index 0edaa7c..e3ac583 100644
--- a/app/Services/PageScrapper.php
+++ b/app/Services/PageScrapper.php
@@ -2,6 +2,9 @@
 
 namespace App\Services;
 
+use DiDom\Document;
+
+/*
 class PageScrapper
 {
     private string $url;
@@ -60,3 +63,39 @@ class PageScrapper
         return $content;
     }
 }
+*/
+
+class PageScrapper
+{
+    private string $url;
+    private string $contentMarker;
+
+    public function __construct($url, $contentMarker)
+    {
+        $this->url = $url;
+        $this->contentMarker = $contentMarker;
+        $this->document = new Document($this->url, true);
+    }
+    public function getFullHTML()
+    {
+        return $this->document;
+    }
+    public function printHTML()
+    {
+        $rez = $this->document;
+        $content = $rez->first($this->contentMarker)->html();
+        return $content;
+    }
+    public function normalizePath()
+    {
+        $links = (string) $this->document->find('a[href]');
+        dd($links);
+        foreach ($links as $link) {
+            if (!str_starts_with($link, 'https')) {
+                $this->document = str_replace($link, 'https://mkgtu.ru' . $link, $this->document);
+            }
+        }
+
+        return $this->document;
+    }
+}
diff --git a/resources/views/menu/course.blade.php b/resources/views/menu/course.blade.php
index 8779bd1..4dc52b1 100644
--- a/resources/views/menu/course.blade.php
+++ b/resources/views/menu/course.blade.php
@@ -36,25 +36,31 @@
 
         <div class="col-10">
             @php
+                use App\Services\PageScrapper;
+                $pageScrapper = new PageScrapper("https://mkgtu.ru/postuplenie/podat-dokumenty-onlayn/", '.content_info');
+                $content = $pageScrapper->printHTML();
+                $content = $pageScrapper->normalizePath();
+
+                echo $content;
 
 
 
 
-                use DiDom\Document;
-
-                    $document = new Document('https://mkgtu.ru/postuplenie/podat-dokumenty-onlayn/', true);
-
-                    $posts = $document->find('.content_info');
-
-                    echo $document->first('.content_info')->html();
-    /*
-                    use App\Services\PageScrapper;
-                    $pageScrapper = new PageScrapper("https://mkgtu.ru/postuplenie/podat-dokumenty-onlayn/", '<div class=["\']content_info["\']>');
-                    $row = $pageScrapper->getHTML();
-                    $content = $pageScrapper->normalizeURLFile($row);
-                    $content = $pageScrapper->cutHTML($content,'/<footer(.*)<\/footer>/isU');
-                    echo $content;
-    */
+                //                    use DiDom\Document;
+                //
+                //                    $document = new Document('https://mkgtu.ru/postuplenie/podat-dokumenty-onlayn/', true);
+                //
+                //                    $posts = $document->find('.content_info');
+                //
+                //                    echo $document->first('.content_info')->html();
+                    /*
+                                    use App\Services\PageScrapper;
+                                    $pageScrapper = new PageScrapper("https://mkgtu.ru/postuplenie/podat-dokumenty-onlayn/", '<div class=["\']content_info["\']>');
+                                    $row = $pageScrapper->getHTML();
+                                    $content = $pageScrapper->normalizeURLFile($row);
+                                    $content = $pageScrapper->cutHTML($content,'/<footer(.*)<\/footer>/isU');
+                                    echo $content;
+                    */
 
             @endphp