Bug Fixes and thiladhun scraper intergration
This commit is contained in:
@@ -11,7 +11,7 @@ class MihaaruScraper
|
||||
protected $title;
|
||||
protected $content;
|
||||
protected $image;
|
||||
protected $tags = [];
|
||||
protected $topics = [];
|
||||
protected $author;
|
||||
|
||||
public function __construct()
|
||||
@@ -25,13 +25,11 @@ class MihaaruScraper
|
||||
$crawler = $this->client->request('GET', $url);
|
||||
|
||||
$crawler->filter('h1')->each(function ($node) {
|
||||
$title = $node->text();
|
||||
$this->title = $title;
|
||||
$this->title = $node->text();
|
||||
});
|
||||
|
||||
$crawler->filter('.container img')->eq(3)->each(function ($node) {
|
||||
$image = $node->attr('src');
|
||||
$this->image = $image;
|
||||
$this->image = $node->attr('src');
|
||||
});
|
||||
|
||||
$crawler->filter('.by-line address')->each(function ($node) {
|
||||
@@ -49,7 +47,7 @@ class MihaaruScraper
|
||||
|
||||
$crawler->filter('.article-tags')->each(function ($node) {
|
||||
|
||||
$this->tags[] = [
|
||||
$this->topics[] = [
|
||||
"name" => $node->text(),
|
||||
"slug" => str_replace("https://mihaaru.com/", "", $node->attr('href'))
|
||||
];
|
||||
@@ -57,7 +55,7 @@ class MihaaruScraper
|
||||
|
||||
//Remove all the alphabets from string
|
||||
//preg_replace("/[a-zA-Z]/", "",$string);
|
||||
$data = [
|
||||
return [
|
||||
'source' => 'Mihaaru',
|
||||
'title' => $this->title,
|
||||
'og_title' => $crawler->filter('meta[property*="og:title"]')->first()->attr('content'),
|
||||
@@ -67,9 +65,7 @@ class MihaaruScraper
|
||||
'date' => $date,
|
||||
'guid' => $guid,
|
||||
'author' => $this->author,
|
||||
'topics' => $this->tags,
|
||||
'topics' => $this->topics
|
||||
];
|
||||
|
||||
return $data;
|
||||
}
|
||||
}
|
||||
|
||||
78
app/Services/Scrapers/ThiladhunScraper.php
Normal file
78
app/Services/Scrapers/ThiladhunScraper.php
Normal file
@@ -0,0 +1,78 @@
|
||||
<?php
|
||||
|
||||
namespace App\Services\Scrapers;
|
||||
|
||||
use Goutte\Client;
|
||||
|
||||
class ThiladhunScraper
|
||||
{
|
||||
protected $client;
|
||||
|
||||
protected $title;
|
||||
protected $content;
|
||||
protected $guid;
|
||||
protected $image;
|
||||
protected $author;
|
||||
|
||||
/**
|
||||
* __construct.
|
||||
*
|
||||
* @return void
|
||||
*/
|
||||
public function __construct()
|
||||
{
|
||||
$this->client = new Client();
|
||||
}
|
||||
|
||||
/**
|
||||
* extract.
|
||||
*
|
||||
* @param mixed $url
|
||||
* @param mixed $date
|
||||
* @param mixed $guid
|
||||
*
|
||||
* @return array
|
||||
*/
|
||||
public function extract($url, $date = null, $guid = null)
|
||||
{
|
||||
$this->guid = str_replace('https://thiladhun.com/', '', $url);
|
||||
|
||||
$crawler = $this->client->request('GET', $url);
|
||||
|
||||
$crawler->filter('h1')->each(function ($node) {
|
||||
$this->title = $node->text();
|
||||
});
|
||||
|
||||
|
||||
$crawler->filter('div.single-body.entry-content.typography-copy p')->each(function ($node) {
|
||||
$this->content[] = preg_replace("/[a-zA-Z]/", "", $node->text());;
|
||||
});
|
||||
|
||||
$crawler->filter('div[class*="entry-thumb single-entry-thumb"] img')->each(function ($node) {
|
||||
$this->image = $node->attr('src');
|
||||
});
|
||||
|
||||
$crawler->filter('a[class*="entry-author__name"]')->each(function ($node) {
|
||||
$this->author = $node->text();
|
||||
});
|
||||
|
||||
|
||||
return [
|
||||
'service' => 'Thiladhun News',
|
||||
'title' => $this->title,
|
||||
'og_title' => str_replace(" | Thiladhun", "", $crawler->filter('title')->first()->text('content')),
|
||||
'image' => $this->image,
|
||||
'content' => $this->content,
|
||||
'date' => $date,
|
||||
'url' => $url,
|
||||
'author' => $this->author,
|
||||
'guid' => $this->guid,
|
||||
'topics' => [
|
||||
[
|
||||
"name" => "ވަކި މަޢުލޫއެއް ނޭންގެ",
|
||||
"slug" => "uncategorized"
|
||||
]
|
||||
]
|
||||
];
|
||||
}
|
||||
}
|
||||
30
app/Services/ThiladhunService.php
Normal file
30
app/Services/ThiladhunService.php
Normal file
@@ -0,0 +1,30 @@
|
||||
<?php
|
||||
|
||||
namespace App\Services;
|
||||
|
||||
use App\Services\Scrapers\ThiladhunScraper;
|
||||
|
||||
class ThiladhunService extends Client
|
||||
{
|
||||
/**
|
||||
* Scrap all the rss articles from mihaaru
|
||||
*
|
||||
* @return array
|
||||
*/
|
||||
public function scrape(): array
|
||||
{
|
||||
//Return only the rss that contains "news" keyboard in its url
|
||||
$articles = $this->get("https://thiladhun.com/feed")["channel"]["item"];
|
||||
|
||||
$articlesitems = [];
|
||||
//Looping through the articles and scraping and while scraping it creates a new instance of the scraper.
|
||||
foreach ($articles as $article) {
|
||||
$link = $article['link'];
|
||||
$date = $article['pubDate'];
|
||||
$guid = $article['guid'];
|
||||
$articlesitems[] = (new ThiladhunScraper)->extract($link, $date, $guid);
|
||||
}
|
||||
|
||||
return $articlesitems;
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user