Commands and scraper

app/Console/Commands/ScrapeMihaaruCommand.php

@@ -0,0 +1,42 @@
+<?php
+
+namespace App\Console\Commands;
+
+use Illuminate\Console\Command;
+
+class ScrapeMihaaruCommand extends Command
+{
+    /**
+     * The name and signature of the console command.
+     *
+     * @var string
+     */
+    protected $signature = 'scrape:mihaaru';
+
+    /**
+     * The console command description.
+     *
+     * @var string
+     */
+    protected $description = 'Scrape Mihaaru mv';
+
+    /**
+     * Create a new command instance.
+     *
+     * @return void
+     */
+    public function __construct()
+    {
+        parent::__construct();
+    }
+
+    /**
+     * Execute the console command.
+     *
+     * @return int
+     */
+    public function handle()
+    {
+        return 0;
+    }
+}

app/Services/MihaaruService.php

@@ -0,0 +1,31 @@
+<?php
+
+namespace App\Services;
+
+use App\Services\Scrapers\MihaaruScraper;
+
+class MihaaruService extends Client
+{    
+    /**
+     * Scrap all the rss articles from mihaaru
+     *
+     * @return array
+     */
+    public function scrape() : array
+    {
+
+        $articles = $this->get("https://mihaaru.com/rss")["channel"]["item"];
+        
+        $articlesitems = [];
+        $emihaaru = new MihaaruScraper();
+
+        foreach ($articles as $article) {
+            $link = $article['link'];
+            $date = $article['pubDate'];
+            $guid = $article['guid'];
+            $articlesitems[] = $emihaaru->extract($link, $date, $guid);
+        }
+
+        return $articlesitems;
+    }
+}

app/Services/Scrapers/MihaaruScraper.php

@@ -0,0 +1,75 @@
+<?php
+
+namespace App\Services\Scrapers;
+
+use Goutte\Client;
+
+class MihaaruScraper
+{
+    protected $client;
+
+    protected $title;
+    protected $content;
+    protected $image;
+    protected $tags = [];
+    protected $author;
+
+    public function __construct()
+    {
+        $this->client = new Client;
+    }
+
+    public function extract($url)
+    {
+
+        $crawler = $this->client->request('GET', $url);
+
+        $crawler->filter('h1')->each(function ($node) {
+            $title = $node->text();
+            $this->title = $title;
+        });
+
+        $crawler->filter('.container  img')->eq(3)->each(function ($node) {
+            $image = $node->attr('src');
+            $this->image = $image;
+        });
+
+        $crawler->filter('.by-line address')->each(function ($node) {
+            $author = $node->text();
+            //Trim all the white spaces
+            $spacetrim = str_replace(' ', '', $author);
+            //Replace multiple spaces and newlines with a single space
+            $cleaneddata = trim(preg_replace('/\s\s+/', ' ', $spacetrim));
+            $this->author = $cleaneddata;
+        });
+
+        $crawler->filter('article')->each(function ($node) {
+            $content = $node->text();
+
+            $input = str_replace("\n", '', $content);
+            $this->content = $input;
+        });
+
+        $crawler->filter('.article-tags')->each(function ($node) {
+            $tags[] = [
+                "name" => $node->text(),
+                "slug" => str_replace("https://mihaaru.com/", "", $node->attr('href'))
+            ];
+            $this->tags[] = $tags;
+        });
+
+        //Remove all the alphabets from string
+        //preg_replace("/[a-zA-Z]/", "",$string);
+        $data = [
+            'source'    => 'Mihaaru',
+            'title'      => $this->title,
+            'image'      => $this->image,
+            'content'    => $this->content,
+            'url'        => $url,
+            'author'     => $this->author,
+            'topics'       => $this->tags,
+        ];
+
+        return $data;
+    }
+}