MicrodataAdapter::extractPublishDate() - Code Metrics - zrashwani/news-scrapper - Measure and Improve Code Quality continuously with Scrutinizer

MicrodataAdapter::extractPublishDate() B
last analyzed 2017-08-17 08:42 UTC

↳ Parent: MicrodataAdapter

Complexity

Conditions	4
Paths	2

Size

Total Lines	26
Code Lines	16

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
dl	0
loc	26
rs	8.5806
c	0
b	0
f	0
nc	2
cc	4
eloc	16
nop	1

<?php

namespace Zrashwani\NewsScrapper\Adapters;

use \Symfony\Component\DomCrawler\Crawler;

/**
 * Adapter to extract news base on microdata format base on schema.org specifications
 * @link http://schema.org/Article schema.org NewsArticle specification
 * @author Zeid Rashwani <zrashwani.com>
 */
class MicrodataAdapter extends AbstractAdapter
{

    /**
     * @param Crawler $crawler
     * @return string
     */
    public function extractTitle(Crawler $crawler)

    {
        $ret = null;

        $crawler->filterXPath('//*[@itemprop="headline"]')
            ->each(
                function(Crawler $node) use (&$ret) {
                            $ret = trim($node->text());
                }
            );


        return $ret;
    }

    public function extractImage(Crawler $crawler)
    {
        
        $ret = $this->getSrcByImgSelector($crawler, '//img[@itemprop="image"]');
        return $ret;
    }

    public function extractDescription(Crawler $crawler)

    {
        $ret = null;

        $crawler->filterXPath('//*[@itemprop="description"]')
            ->each(
                function(Crawler $node) use (&$ret) {
                    if ($node->nodeName() === 'meta') {
                        $ret = trim($node->attr('content'));
                    } else {
                        $ret = trim($node->text());
                    }
                }
            );

        return $ret;
    }

    /**
     * extract keywords out of crawler object
     * @param Crawler $crawler
     * @return array
     */
    public function extractKeywords(Crawler $crawler)
    {
        $ret = array();

        $crawler->filterXPath('//*[@itemprop="keywords"]')
            ->each(
                function(Crawler $node) use (&$ret) {

                    if ($node->nodeName() === 'meta') {
                        $keyword_txt = trim($node->attr('content'));
                    } else {
                        $keyword_txt = trim($node->text());
                    }

                    if (empty($keyword_txt) !== true) {
                        $ret = explode(',', $keyword_txt);
                    }
                }
            );

        return $ret;
    }

    public function extractBody(Crawler $crawler)
    {
        $ret = '';

        $crawler->filterXPath('//*[@itemprop="articleBody"]')
            ->each(
                function(Crawler $node) use (&$ret) {
                        $ret .= $node->html();
                }
            );

        if (empty($ret) === true) {
            $article_types = ['Article', 'NewsArticle', 'Report', 'ScholarlyArticle',
                'MedicalScholarlyArticle', 'SocialMediaPosting',
                'BlogPosting', 'LiveBlogPosting',
                'DiscussionForumPosting', 'TechArticle',
                'APIReference'];

            foreach ($article_types as $article_type) {
                $crawler->filterXPath(
                    "//*[@itemtype='http://schema.org/$article_type']"
                )
                    ->each(
                        function(Crawler $node) use (&$ret) {
                                    $ret .= $node->html();
                        }
                    );
                
                if (empty($ret) === false) { //if content found, exit loop
                    break;
                }
            }
        }

        $ret = $this->normalizeHtml($ret);
        
        return $ret;
    }

    public function extractPublishDate(Crawler $crawler)
    {
        $date_str = null;

        $crawler->filterXPath('//*[@itemprop="datePublished"]')
            ->each(
                function(Crawler $node) use (&$date_str) {
                    if ($node->nodeName() === 'meta') {
                        $date_str = $node->attr('content');
                    } elseif ($node->attr('datetime')) {
''   == false // true
''   == null  // true
'ab' == false // false
'ab' == null  // false

// It is often better to use strict comparison
'' === false // false
'' === null  // false
                        $date_str = $node->attr('datetime');
                    } else {
                        $date_str = $node->text();
                    }
                }
            );

        if (!is_null($date_str)) {
            //remove extra unneeded suffix from date
            $date_str = str_replace('ET', '', $date_str);
            $ret = new \DateTime($date_str);
            return $ret->format(\DateTime::ISO8601);
        }
        
        return $date_str; //null
    }

    public function extractAuthor(Crawler $crawler)
    {
        $ret = null;
        $crawler->filterXPath(
            '//*[@itemprop="author" '.
            'and @itemtype="http://schema.org/Person"]//*[@itemprop="name"]'
        )
            ->each(
                function(Crawler $node) use (&$ret) {
                            $ret = $node->text();
                }
            );

        if (is_null($ret)) {
            $crawler->filterXPath('//*[@itemprop="author"]')
                ->each(
                    function(Crawler $node) use (&$ret) {
                        if ($node->nodeName() === 'meta') {
                                $ret = $node->attr('content');
                        } else {
                            $ret = $node->text();
                        }
                    }
                );
        }
        $ret = preg_replace('@\s{2,}@', ' ', $ret);
        
        return $ret;
    }
}


1		<?php
2
3		namespace Zrashwani\NewsScrapper\Adapters;
4
5		use \Symfony\Component\DomCrawler\Crawler;
6
7		/**
8		* Adapter to extract news base on microdata format base on schema.org specifications
9		* @link http://schema.org/Article schema.org NewsArticle specification
10		* @author Zeid Rashwani <zrashwani.com>
11		*/
12		class MicrodataAdapter extends AbstractAdapter
13		{
14
15		/**
16		* @param Crawler $crawler
17		* @return string
18		*/
19	View Code Duplication	public function extractTitle(Crawler $crawler)
		0 ignored issues – show Duplication introduced 2017-08-17 08:40 UTC by Report Bug Copy Issue Report This method seems to be duplicated in your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
20		{
21		$ret = null;
22
23		$crawler->filterXPath('//*[@itemprop="headline"]')
24		->each(
25		function(Crawler $node) use (&$ret) {
26		$ret = trim($node->text());
27		}
28		);
29
30
31		return $ret;
32		}
33
34		public function extractImage(Crawler $crawler)
35		{
36
37		$ret = $this->getSrcByImgSelector($crawler, '//img[@itemprop="image"]');
38		return $ret;
39		}
40
41	View Code Duplication	public function extractDescription(Crawler $crawler)
		0 ignored issues – show Duplication introduced 2017-08-17 08:40 UTC by Report Bug Copy Issue Report This method seems to be duplicated in your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
42		{
43		$ret = null;
44
45		$crawler->filterXPath('//*[@itemprop="description"]')
46		->each(
47		function(Crawler $node) use (&$ret) {
48		if ($node->nodeName() === 'meta') {
49		$ret = trim($node->attr('content'));
50		} else {
51		$ret = trim($node->text());
52		}
53		}
54		);
55
56		return $ret;
57		}
58
59		/**
60		* extract keywords out of crawler object
61		* @param Crawler $crawler
62		* @return array
63		*/
64		public function extractKeywords(Crawler $crawler)
65		{
66		$ret = array();
67
68		$crawler->filterXPath('//*[@itemprop="keywords"]')
69		->each(
70	View Code Duplication	function(Crawler $node) use (&$ret) {
		0 ignored issues – show Duplication introduced 2015-11-28 14:05 UTC by Report Bug Copy Issue Report This code seems to be duplicated across your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
71		if ($node->nodeName() === 'meta') {
72		$keyword_txt = trim($node->attr('content'));
73		} else {
74		$keyword_txt = trim($node->text());
75		}
76
77		if (empty($keyword_txt) !== true) {
78		$ret = explode(',', $keyword_txt);
79		}
80		}
81		);
82
83		return $ret;
84		}
85
86		public function extractBody(Crawler $crawler)
87		{
88		$ret = '';
89
90		$crawler->filterXPath('//*[@itemprop="articleBody"]')
91		->each(
92		function(Crawler $node) use (&$ret) {
93		$ret .= $node->html();
94		}
95		);
96
97		if (empty($ret) === true) {
98		$article_types = ['Article', 'NewsArticle', 'Report', 'ScholarlyArticle',
99		'MedicalScholarlyArticle', 'SocialMediaPosting',
100		'BlogPosting', 'LiveBlogPosting',
101		'DiscussionForumPosting', 'TechArticle',
102		'APIReference'];
103
104		foreach ($article_types as $article_type) {
105		$crawler->filterXPath(
106		"//*[@itemtype='http://schema.org/$article_type']"
107		)
108		->each(
109		function(Crawler $node) use (&$ret) {
110		$ret .= $node->html();
111		}
112		);
113
114		if (empty($ret) === false) { //if content found, exit loop
115		break;
116		}
117		}
118		}
119
120		$ret = $this->normalizeHtml($ret);
121
122		return $ret;
123		}
124
125		public function extractPublishDate(Crawler $crawler)
126		{
127		$date_str = null;
128
129		$crawler->filterXPath('//*[@itemprop="datePublished"]')
130		->each(
131		function(Crawler $node) use (&$date_str) {
132		if ($node->nodeName() === 'meta') {
133		$date_str = $node->attr('content');
134		} elseif ($node->attr('datetime')) {
		0 ignored issues – show Bug Best Practice introduced 2015-11-28 14:05 UTC by Report Bug Copy Issue Report The expression `$node->attr('datetime')` of type `string\|null` is loosely compared to `true`; this is ambiguous if the string can be empty. You might want to explicitly use `!== null` instead. In PHP, under loose comparison (like `==`, or `!=`, or `switch` conditions), values of different types might be equal. For `string` values, the empty string `''` is a special case, in particular the following results might be unexpected: '' == false // true '' == null // true 'ab' == false // false 'ab' == null // false // It is often better to use strict comparison '' === false // false '' === null // false Loading history...
135		$date_str = $node->attr('datetime');
136		} else {
137		$date_str = $node->text();
138		}
139		}
140		);
141
142		if (!is_null($date_str)) {
143		//remove extra unneeded suffix from date
144		$date_str = str_replace('ET', '', $date_str);
145		$ret = new \DateTime($date_str);
146		return $ret->format(\DateTime::ISO8601);
147		}
148
149		return $date_str; //null
150		}
151
152		public function extractAuthor(Crawler $crawler)
153		{
154		$ret = null;
155		$crawler->filterXPath(
156		'//*[@itemprop="author" '.
157		'and @itemtype="http://schema.org/Person"]//*[@itemprop="name"]'
158		)
159		->each(
160		function(Crawler $node) use (&$ret) {
161		$ret = $node->text();
162		}
163		);
164
165		if (is_null($ret)) {
166		$crawler->filterXPath('//*[@itemprop="author"]')
167		->each(
168		function(Crawler $node) use (&$ret) {
169		if ($node->nodeName() === 'meta') {
170		$ret = $node->attr('content');
171		} else {
172		$ret = $node->text();
173		}
174		}
175		);
176		}
177		$ret = preg_replace('@\s{2,}@', ' ', $ret);
178
179		return $ret;
180		}
181		}
182

zrashwani / news-scrapper

MicrodataAdapter::extractPublishDate() B last analyzed 2017-08-17 08:42 UTC

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like

MicrodataAdapter::extractPublishDate() B
last analyzed 2017-08-17 08:42 UTC