CrawlerTools::getNodeHtml() - Code Metrics - magabriel/trefoil - Measure and Improve Code Quality continuously with Scrutinizer

CrawlerTools::getNodeHtml() A
last analyzed 2018-11-26 10:45 UTC

↳ Parent: CrawlerTools

Complexity

Conditions	2
Paths	2

Size

Total Lines

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	16
CRAP Score	2.0008

Importance

Changes

Metric	Value
dl	0
loc	29
ccs	16
cts	17
cp	0.9412
rs	9.456
c	0
b	0
f	0
cc	2
nc	2
nop	1
crap	2.0008

<?php
/*
 * This file is part of the trefoil application.
 *
 * (c) Miguel Angel Gabriel <[email protected]>
 *
 * For the full copyright and license information, please view the LICENSE
 * file that was distributed with this source code.
 */
namespace Trefoil\Util;

use Symfony\Component\DomCrawler\Crawler;

/**
 * Serveral utility operations for Crawler objects.
 *
 */
class CrawlerTools
{

    /**
     * Return the node name
     *
     * @param Crawler $node
     *
     * @return string
     */
    public static function getNodeName(Crawler $node)
    {
        return $node->getNode(0)->nodeName;
    }

    /**
     * Return the node text contents (w/o the children).
     *
     * @param Crawler $node
     *
     * @return string
     */
    public static function getNodeText(Crawler $node)
    {
        foreach ($node->getNode(0)->childNodes as $cNode) {
            if ("#text" == $cNode->nodeName) {
                return $cNode->nodeValue;
            }
        }

        return '';
    }

    /**
     * Return the node HTML contents
     *
     * @param Crawler $node
     *
     * @return string
     */
    public static function getNodeHtml(Crawler $node)
    {
        $domNode = $node->getNode(0);

        if (null === $domNode) {
            return '';
        }

        $html = $domNode->ownerDocument->saveHtml($domNode);

        // remove line breaks
        $html = str_replace(array("\n", "\r"), '', $html);

        // remove surrounding tag
        $regExp = '/';
        $regExp .= '<(?<tag>.*)>';
        $regExp .= '(?<html>.*)$';
        $regExp .= '/Ums'; // Ungreedy, multiline, dotall

        $html = preg_replace_callback(
            $regExp,
            function ($matches) {
                return '<' . $matches['tag'] . '>' . $matches['html'];
            },
            $html
        );

        return $html;
    }
}


1		<?php
2		/*
3		* This file is part of the trefoil application.
4		*
5		* (c) Miguel Angel Gabriel <[email protected]>
6		*
7		* For the full copyright and license information, please view the LICENSE
8		* file that was distributed with this source code.
9		*/
10		namespace Trefoil\Util;
11
12		use Symfony\Component\DomCrawler\Crawler;
13
14		/**
15		* Serveral utility operations for Crawler objects.
16		*
17		*/
18		class CrawlerTools
19		{
20
21		/**
22		* Return the node name
23		*
24		* @param Crawler $node
25		*
26		* @return string
27		*/
28	1	public static function getNodeName(Crawler $node)
29		{
30	1	return $node->getNode(0)->nodeName;
31		}
32
33		/**
34		* Return the node text contents (w/o the children).
35		*
36		* @param Crawler $node
37		*
38		* @return string
39		*/
40		public static function getNodeText(Crawler $node)
41		{
42		foreach ($node->getNode(0)->childNodes as $cNode) {
43		if ("#text" == $cNode->nodeName) {
44		return $cNode->nodeValue;
45		}
46		}
47
48		return '';
49		}
50
51		/**
52		* Return the node HTML contents
53		*
54		* @param Crawler $node
55		*
56		* @return string
57		*/
58	1	public static function getNodeHtml(Crawler $node)
59		{
60	1	$domNode = $node->getNode(0);
61
62	1	if (null === $domNode) {
63		return '';
64		}
65
66	1	$html = $domNode->ownerDocument->saveHtml($domNode);
67
68		// remove line breaks
69	1	$html = str_replace(array("\n", "\r"), '', $html);
70
71		// remove surrounding tag
72	1	$regExp = '/';
73	1	$regExp .= '<(?<tag>.*)>';
74	1	$regExp .= '(?<html>.*)$';
75	1	$regExp .= '/Ums'; // Ungreedy, multiline, dotall
76
77	1	$html = preg_replace_callback(
78	1	$regExp,
79	1	function ($matches) {
80	1	return '<' . $matches['tag'] . '>' . $matches['html'];
81	1	},
82		$html
83	1	);
84
85	1	return $html;
86		}
87		}
88

magabriel / trefoil

GitHub Access Token became invalid

CrawlerTools::getNodeHtml() A last analyzed 2018-11-26 10:45 UTC

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like

CrawlerTools::getNodeHtml() A
last analyzed 2018-11-26 10:45 UTC