Felix\Scraper\Crawler

Complexity

Total Complexity

6

Size/Duplication

Total Lines	68
Duplicated Lines	0 %

Coupling/Cohesion

Components	1
Dependencies	1

Test Coverage

Coverage

61.11%

Importance

Changes

0

6 Methods

Rating	Name	Duplication	Size	Complexity
A	start()	0	8	1
A	getHtml()	0	6	1
A	setContent()	0	5	1
A	getUrl()	0	4	1
A	setTimeout()	0	4	1
A	getContent()	0	4	1

<?php

namespace Felix\Scraper;

class Crawler
{
    protected $timeout = 60;
    protected $url = '';
    protected $xpath = '';
    protected $html = '';
    protected $content = '';

    public function start(string $url, string $xpath)
    {
        $html = $this->getHtml($url);

        $this->setContent($html, $xpath);

        return $this->content;
    }

    /**
     * Obtener el contenido HTML de una página.
     *
     *
     * @param string $url Url de la página a scrapear
     *
     * @return string
     */
    public function getHtml(string $url)
    {
        $this->html = @file_get_contents($url);

        return $this->html;
    }

    /**
     * Almacenar el codigo HTML.
     *
     * @param string $html
     * @param string $xpath
     */
    public function setContent($html, $xpath)
    {
        $crawler = new \Symfony\Component\DomCrawler\Crawler($html);
        $this->content = $crawler->evaluate($xpath);

It seems like $crawler->evaluate($xpath) of type object<Symfony\Component\DomCrawler\Crawler> or array<integer,?,{"0":"?"}> is incompatible with the declared type string of property $content.

    }

    /**
     * Obtner el contenido.
     */
    public function getContent()
    {
        return $this->content;
    }

    /**
     * Obtner la URL.
     */
    public function getUrl()
    {
        return $this->url;
    }

    /**
     * Guardar el tiempo de espera de una página.
     */
    public function setTimeout(int $timeout)
    {
        $this->timeout = $timeout;
    }
}