fix voice

app/Services/Feeds/VoiceFeed.php

@@ -9,8 +9,9 @@ class VoiceFeed implements Feed
 
     public function __construct()
     {
-        $this->client = new Client();        
-    }    
+        $this->client = new Client();
+    }
+
     /**
      * Get all the latest news
      *
@@ -18,11 +19,14 @@ class VoiceFeed implements Feed
      */
     public function get() : array
     {
-      
         $crawler = $this->client->request('GET', "https://voice.mv/");
 
-        return $crawler->filter('div[id*="latest-news"] .content a')
-                            ->extract(['_text', '_attr' => 'href']);             
-
+        return $crawler->filter('div#latest-news > div > a')->each(function ($node) {
+            return [
+                "title" => $node->filter('.dv-bold')->text(),
+                "link" => 'https://voice.mv' . $node->attr('href'),
+                "date" => $node->filter('.en-font')->text(),
+            ];
+        });
     }
-}
+}

app/Services/Scrapers/VoiceScraper.php

@@ -8,57 +8,49 @@ use Illuminate\Support\Carbon;
 class VoiceScraper
 {
     protected $client;
-
-    protected $author;
-    protected $content;
+    protected $author = 'unknown';
+    protected $content = [];
     protected $topics = [];
 
     public function __construct()
     {
-        $this->client = new Client;
+        $this->client = new Client();
     }
 
     public function extract($url)
     {
-
         $crawler = $this->client->request('GET', $url);
 
-        $title = $crawler->filter('.content h1')->first()->text();
+        // Extracting title - checking for multiple class names
+        $title = $crawler->filter('.text-3xl')->first()->text();
 
 
-
-        $image = $crawler->filter('.image img')->first()->attr('src');
-
-        $crawler->filter('article p')->each(function ($node) {
-            $this->content[] = preg_replace("/[a-zA-Z]/", "", $node->text());
+        // Extracting article content
+        $crawler->filter('.container .dv')->each(function ($node) {
+            $this->content[] = $node->text();
         });
 
+        // Extracting topics
+        $this->topics = [];
         $crawler->filter('.related-tags-holder a')->each(function ($node) {
-
             $this->topics[] = [
                 "name" => $node->text(),
                 "slug" => str_replace("/", "", $node->attr('href'))
             ];
         });
 
-        if ($crawler->filter(".authorname a")->count() == 1) {
-            $this->author = str_replace("- ", "", $crawler->filter('.authorname a')->first()->text());
-        }
-
-
-        //Remove all the alphabets from string
-        //preg_replace("/[a-zA-Z]/", "",$string);
+        // Returning extracted data
         return [
             'source'    => 'Voice',
-            'title'      => $title,
-            'og_title'   => $crawler->filter('meta[property*="og:title"]')->first()->attr('content'),
-            'image'      => $image,
-            'content'    => $this->content,
-            'url'        => $url,
-            'date'       => Carbon::parse(str_replace("- ", "", $crawler->filter('.authordatecomment .date')->first()->text()))->format("Y-m-d H:i:s"),
-            'guid'       => str_replace("https://voice.mv/", "", $url),
-            'author'     => $this->author,
-            'topics'       => $this->topics
+            'title'     => $title,
+            'og_title'  => $crawler->filter('meta[property*="og:title"]')->first()->attr('content'),
+            'image'     => $crawler->filter('meta[property="og:image"]')->first()->attr('content'),
+            'content'   => $this->content,
+            'url'       => $url,
+            'date'      => Carbon::now(),
+            'guid'      => str_replace("https://voice.mv/", "", $url),
+            'author'    => $this->author,
+            'topics'    => $this->topics
         ];
     }
-}
+}

app/Services/VoiceService.php

@@ -1,4 +1,5 @@
 <?php
+
 namespace App\Services;
 
 use App\Services\Feeds\VoiceFeed;
@@ -18,9 +19,10 @@ class VoiceService
         $articlesitems = [];
         //Looping through the articles and scraping and while scraping it creates a new instance of the scraper.
         foreach ($articles as $article) {
-            $articlesitems[] = (new VoiceScraper)->extract("https://voice.mv".$article[1]);
+
+            $articlesitems[] = (new VoiceScraper)->extract($article["link"]);
         }
 
         return $articlesitems;
     }
-}
+}