From e0f0e29bd46478a80d5127e4079e862a510a5a6e Mon Sep 17 00:00:00 2001
From: Mohamed Jinas <j@live.mv>
Date: Tue, 18 Aug 2020 00:47:08 +0500
Subject: [PATCH] Voice intergration

---
 app/Console/Commands/ScrapeVoiceCommand.php | 73 +++++++++++++++++++++
 app/Services/Feeds/VoiceFeed.php            | 28 ++++++++
 app/Services/Scrapers/VoiceScraper.php      | 64 ++++++++++++++++++
 app/Services/VoiceService.php               | 26 ++++++++
 4 files changed, 191 insertions(+)
 create mode 100644 app/Console/Commands/ScrapeVoiceCommand.php
 create mode 100644 app/Services/Feeds/VoiceFeed.php
 create mode 100644 app/Services/Scrapers/VoiceScraper.php
 create mode 100644 app/Services/VoiceService.php

diff --git a/app/Console/Commands/ScrapeVoiceCommand.php b/app/Console/Commands/ScrapeVoiceCommand.php
new file mode 100644
index 0000000..c4394fe
--- /dev/null
+++ b/app/Console/Commands/ScrapeVoiceCommand.php
@@ -0,0 +1,73 @@
+<?php
+
+namespace App\Console\Commands;
+
+use App\Source;
+use Illuminate\Console\Command;
+use App\Services\VoiceService;
+use App\Topic;
+use Illuminate\Support\Carbon;
+
+class ScrapeVoiceCommand extends Command
+{
+    /**
+     * The name and signature of the console command.
+     *
+     * @var string
+     */
+    protected $signature = 'scrape:voice';
+
+    /**
+     * The console command description.
+     *
+     * @var string
+     */
+    protected $description = 'Scrape Voice';
+
+    /**
+     * Create a new command instance.
+     *
+     * @return void
+     */
+    public function __construct()
+    {
+        parent::__construct();
+    }
+
+    /**
+     * Execute the console command.
+     *
+     * @return int
+     */
+    public function handle()
+    {
+        $source = Source::where('slug', 'voice')->first();
+
+        $articles = (new VoiceService)->scrape();
+
+        foreach ($articles as $article) {
+
+            // Attach the relationship between source and article and return the curren article instance
+            $articleModel = $source->articles()->firstOrCreate(["guid" => $article["guid"]],
+                [
+                "title" => $article["title"],
+                "url" => $article["url"],
+                "author" => $article["author"],
+                "featured_image" => $article["image"],
+                "body" => $article["content"],
+                "published_date" => $article["date"],
+                "meta" => [
+                    "title" => $article["og_title"]
+                ]
+
+            ]);
+
+            collect($article["topics"])->each(function($topic) use ($articleModel) {
+                $topicModel = Topic::firstOrCreate(["slug" => $topic["slug"]],["name" => $topic["name"]]);
+
+                $topicModel->articles()->syncWithoutDetaching($articleModel);
+            });
+
+        }
+    }
+}
diff --git a/app/Services/Feeds/VoiceFeed.php b/app/Services/Feeds/VoiceFeed.php
new file mode 100644
index 0000000..c7b24dc
--- /dev/null
+++ b/app/Services/Feeds/VoiceFeed.php
@@ -0,0 +1,28 @@
+<?php
+namespace App\Services\Feeds;
+
+use Goutte\Client;
+
+class VoiceFeed
+{
+    protected $client;
+
+    public function __construct()
+    {
+        $this->client = new Client();        
+    }    
+    /**
+     * Get all the latest news
+     *
+     * @return array
+     */
+    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']);             
+
+    }
+}
\ No newline at end of file
diff --git a/app/Services/Scrapers/VoiceScraper.php b/app/Services/Scrapers/VoiceScraper.php
new file mode 100644
index 0000000..60d3eff
--- /dev/null
+++ b/app/Services/Scrapers/VoiceScraper.php
@@ -0,0 +1,64 @@
+<?php
+
+namespace App\Services\Scrapers;
+
+use Goutte\Client;
+use Illuminate\Support\Carbon;
+
+class VoiceScraper
+{
+    protected $client;
+
+    protected $author;
+    protected $content;
+    protected $topics = [];
+
+    public function __construct()
+    {
+        $this->client = new Client;
+    }
+
+    public function extract($url)
+    {
+
+        $crawler = $this->client->request('GET', $url);
+
+        $title = $crawler->filter('.content h1')->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());
+        });
+
+        $crawler->filter('.related-tags-holder a')->each(function ($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);
+        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
+        ];
+    }
+}
\ No newline at end of file
diff --git a/app/Services/VoiceService.php b/app/Services/VoiceService.php
new file mode 100644
index 0000000..91b5593
--- /dev/null
+++ b/app/Services/VoiceService.php
@@ -0,0 +1,26 @@
+<?php
+namespace App\Services;
+
+use App\Services\Feeds\VoiceFeed;
+use App\Services\Scrapers\VoiceScraper;
+
+class VoiceService
+{
+    /**
+     * Scrap all the rss articles from Sun
+     *
+     * @return array
+     */
+    public function scrape(): array
+    {
+        $articles = (new VoiceFeed)->get();
+
+        $articlesitems = [];
+        //Looping through the articles and scraping and while scraping it creates a new instance of the scraper.
+        foreach ($articles as $article) {
+            $articlesitems[] = (new VoiceScraper)->extract("https://voice.mv/".$article[1]);
+        }
+
+        return $articlesitems;
+    }
+}
\ No newline at end of file