From 0589b198436b01b0a0d7bdddbbfacbdc699438f9 Mon Sep 17 00:00:00 2001
From: Mohamed jinas <boringdragon98@gmail.com>
Date: Sun, 7 Jan 2024 21:42:31 +0500
Subject: [PATCH] fix thiladhun

---
 app/Services/Feeds/ThiladhunFeed.php       | 21 ++++++++--------
 app/Services/Scrapers/ThiladhunScraper.php | 29 ++++++++++++----------
 app/Services/ThiladhunService.php          |  4 +--
 3 files changed, 29 insertions(+), 25 deletions(-)

diff --git a/app/Services/Feeds/ThiladhunFeed.php b/app/Services/Feeds/ThiladhunFeed.php
index 798a15d..cf92bc4 100644
--- a/app/Services/Feeds/ThiladhunFeed.php
+++ b/app/Services/Feeds/ThiladhunFeed.php
@@ -18,22 +18,23 @@ class ThiladhunFeed implements Feed
      */
     public function get() : array
     {
-
         $crawler = $this->client->request('GET', "https://www.thiladhun.com");
 
         $feeds = [];
-        $crawler->filter('div[class*="posts-listing posts-list"] article')->each(function ($node) use (&$feeds) {
-
-
-            $feeds[] = [
-                "title" => $node->filter('.post__title a')->text(),
-                "link" => $node->filter('.post__title a')->attr('href'),
-               "date" => $node->filter('time')->first()->attr('datetime')
-            ];
+        // Assuming 'ފަހުގެ' is a unique identifier for the section of interest
+        $crawler->filter('.elementor-element:contains("ފަހުގެ")')->nextAll('.elementor-post')->each(function ($node) use (&$feeds) {
+            $title = $node->filter('.elementor-heading-title a')->count() ? $node->filter('.elementor-heading-title a')->text() : null;
+            $link = $node->filter('.elementor-heading-title a')->count() ? $node->filter('.elementor-heading-title a')->attr('href') : null;
 
+            if ($title && $link) {
+                $feeds[] = [
+                    "title" => $title,
+                    "link"  => $link,
+                ];
+            }
         });
 
         return $feeds;
-
     }
+
 }
diff --git a/app/Services/Scrapers/ThiladhunScraper.php b/app/Services/Scrapers/ThiladhunScraper.php
index a22aba4..beef35a 100644
--- a/app/Services/Scrapers/ThiladhunScraper.php
+++ b/app/Services/Scrapers/ThiladhunScraper.php
@@ -34,7 +34,7 @@ class ThiladhunScraper
      *
      * @return array
      */
-    public function extract($url, $date)
+    public function extract($url)
     {
 
         $crawler = $this->client->request('GET', $url);
@@ -51,20 +51,23 @@ class ThiladhunScraper
         $this->image = $crawler->filter('div[data-widget_type*="theme-post-featured-image.default"] figure img')->first()->attr('src');
 
         $crawler->filter('.entry-tags a')->each(function ($node) {
-            if(!preg_match('/[^A-Za-z0-9-]/', basename($node->attr('href'))))
-            {
-             $this->topics[] = [
-                 "name" => $node->text(),
-                 "slug" => basename($node->attr('href'))
-             ];
+            if (!preg_match('/[^A-Za-z0-9-]/', basename($node->attr('href')))) {
+                $this->topics[] = [
+                    "name" => $node->text(),
+                    "slug" => basename($node->attr('href'))
+                ];
             }
-
-         });
+        });
 
         $crawler->filter('a > .elementor-post-info__item--type-author')->each(function ($node) {
             $this->author = $node->text();
         });
 
+        $urlComponents = parse_url($url);
+        $cleanUrl = $urlComponents['scheme'] . '://' . $urlComponents['host'] . $urlComponents['path'];
+
+        // Extract and modify the guid
+        $guid = basename($urlComponents['path']);
 
         return [
             'source'    => 'Thiladhun News',
@@ -72,11 +75,11 @@ class ThiladhunScraper
             'og_title'   => str_replace(" | Thiladhun", "", $crawler->filter('title')->first()->text('content')),
             'image'      => $this->image,
             'content'    => $this->content,
-            'date'       => Carbon::parse($date)->format("Y-m-d H:i:s"),
-            'url'        => $url,
+            'date'       => Carbon::now(),
+            'url'       => $cleanUrl,
             'author'     => $this->author,
-            'guid'       => basename($url),
-            'topics'       =>  $this->topics ? : [
+            'guid'       => $guid,
+            'topics'       =>  $this->topics ?: [
                 [
                     "name" => "ވަކި މަޢުލޫއެއް ނޭންގެ",
                     "slug" => "no-specific-topic"
diff --git a/app/Services/ThiladhunService.php b/app/Services/ThiladhunService.php
index 8f4fd20..ac9cef8 100644
--- a/app/Services/ThiladhunService.php
+++ b/app/Services/ThiladhunService.php
@@ -20,12 +20,12 @@ class ThiladhunService extends Client
         $response = Http::get("https://thiladhun.com/feed")->body();
         $data = json_decode(json_encode(simplexml_load_string($response)), true);
         $articles = $data["channel"]["item"];
-        
+
         $articlesitems = [];
         //Looping through the articles and scraping and while scraping it creates a new instance of the scraper.
         foreach ($articles as $article) {
             //Remove query strings
-            $articlesitems[] = (new ThiladhunScraper)->extract(Str::before($article["link"], '?'), $article["pubDate"]);
+            $articlesitems[] = (new ThiladhunScraper)->extract($article["link"]);
         }
 
         return $articlesitems;