fix voice
This commit is contained in:
@@ -25,8 +25,7 @@ class SourcesAPIController extends Controller
|
|||||||
'zaviyani',
|
'zaviyani',
|
||||||
'funadhoo-times',
|
'funadhoo-times',
|
||||||
'psm',
|
'psm',
|
||||||
'raajjemv',
|
'raajjemv'
|
||||||
'voice'
|
|
||||||
])->get());
|
])->get());
|
||||||
});
|
});
|
||||||
}
|
}
|
||||||
|
@@ -11,6 +11,7 @@ class VoiceFeed implements Feed
|
|||||||
{
|
{
|
||||||
$this->client = new Client();
|
$this->client = new Client();
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Get all the latest news
|
* Get all the latest news
|
||||||
*
|
*
|
||||||
@@ -18,11 +19,14 @@ class VoiceFeed implements Feed
|
|||||||
*/
|
*/
|
||||||
public function get() : array
|
public function get() : array
|
||||||
{
|
{
|
||||||
|
|
||||||
$crawler = $this->client->request('GET', "https://voice.mv/");
|
$crawler = $this->client->request('GET', "https://voice.mv/");
|
||||||
|
|
||||||
return $crawler->filter('div[id*="latest-news"] .content a')
|
return $crawler->filter('div#latest-news > div > a')->each(function ($node) {
|
||||||
->extract(['_text', '_attr' => 'href']);
|
return [
|
||||||
|
"title" => $node->filter('.dv-bold')->text(),
|
||||||
|
"link" => 'https://voice.mv' . $node->attr('href'),
|
||||||
|
"date" => $node->filter('.en-font')->text(),
|
||||||
|
];
|
||||||
|
});
|
||||||
}
|
}
|
||||||
}
|
}
|
@@ -8,54 +8,46 @@ use Illuminate\Support\Carbon;
|
|||||||
class VoiceScraper
|
class VoiceScraper
|
||||||
{
|
{
|
||||||
protected $client;
|
protected $client;
|
||||||
|
protected $author = 'unknown';
|
||||||
protected $author;
|
protected $content = [];
|
||||||
protected $content;
|
|
||||||
protected $topics = [];
|
protected $topics = [];
|
||||||
|
|
||||||
public function __construct()
|
public function __construct()
|
||||||
{
|
{
|
||||||
$this->client = new Client;
|
$this->client = new Client();
|
||||||
}
|
}
|
||||||
|
|
||||||
public function extract($url)
|
public function extract($url)
|
||||||
{
|
{
|
||||||
|
|
||||||
$crawler = $this->client->request('GET', $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();
|
||||||
|
|
||||||
|
|
||||||
|
// Extracting article content
|
||||||
$image = $crawler->filter('.image img')->first()->attr('src');
|
$crawler->filter('.container .dv')->each(function ($node) {
|
||||||
|
$this->content[] = $node->text();
|
||||||
$crawler->filter('article p')->each(function ($node) {
|
|
||||||
$this->content[] = preg_replace("/[a-zA-Z]/", "", $node->text());
|
|
||||||
});
|
});
|
||||||
|
|
||||||
|
// Extracting topics
|
||||||
|
$this->topics = [];
|
||||||
$crawler->filter('.related-tags-holder a')->each(function ($node) {
|
$crawler->filter('.related-tags-holder a')->each(function ($node) {
|
||||||
|
|
||||||
$this->topics[] = [
|
$this->topics[] = [
|
||||||
"name" => $node->text(),
|
"name" => $node->text(),
|
||||||
"slug" => str_replace("/", "", $node->attr('href'))
|
"slug" => str_replace("/", "", $node->attr('href'))
|
||||||
];
|
];
|
||||||
});
|
});
|
||||||
|
|
||||||
if ($crawler->filter(".authorname a")->count() == 1) {
|
// Returning extracted data
|
||||||
$this->author = str_replace("- ", "", $crawler->filter('.authorname a')->first()->text());
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
//Remove all the alphabets from string
|
|
||||||
//preg_replace("/[a-zA-Z]/", "",$string);
|
|
||||||
return [
|
return [
|
||||||
'source' => 'Voice',
|
'source' => 'Voice',
|
||||||
'title' => $title,
|
'title' => $title,
|
||||||
'og_title' => $crawler->filter('meta[property*="og:title"]')->first()->attr('content'),
|
'og_title' => $crawler->filter('meta[property*="og:title"]')->first()->attr('content'),
|
||||||
'image' => $image,
|
'image' => $crawler->filter('meta[property="og:image"]')->first()->attr('content'),
|
||||||
'content' => $this->content,
|
'content' => $this->content,
|
||||||
'url' => $url,
|
'url' => $url,
|
||||||
'date' => Carbon::parse(str_replace("- ", "", $crawler->filter('.authordatecomment .date')->first()->text()))->format("Y-m-d H:i:s"),
|
'date' => Carbon::now(),
|
||||||
'guid' => str_replace("https://voice.mv/", "", $url),
|
'guid' => str_replace("https://voice.mv/", "", $url),
|
||||||
'author' => $this->author,
|
'author' => $this->author,
|
||||||
'topics' => $this->topics
|
'topics' => $this->topics
|
||||||
|
@@ -1,4 +1,5 @@
|
|||||||
<?php
|
<?php
|
||||||
|
|
||||||
namespace App\Services;
|
namespace App\Services;
|
||||||
|
|
||||||
use App\Services\Feeds\VoiceFeed;
|
use App\Services\Feeds\VoiceFeed;
|
||||||
@@ -18,7 +19,8 @@ class VoiceService
|
|||||||
$articlesitems = [];
|
$articlesitems = [];
|
||||||
//Looping through the articles and scraping and while scraping it creates a new instance of the scraper.
|
//Looping through the articles and scraping and while scraping it creates a new instance of the scraper.
|
||||||
foreach ($articles as $article) {
|
foreach ($articles as $article) {
|
||||||
$articlesitems[] = (new VoiceScraper)->extract("https://voice.mv".$article[1]);
|
|
||||||
|
$articlesitems[] = (new VoiceScraper)->extract($article["link"]);
|
||||||
}
|
}
|
||||||
|
|
||||||
return $articlesitems;
|
return $articlesitems;
|
||||||
|
Reference in New Issue
Block a user