summaryrefslogtreecommitdiff
path: root/src/HTMLParser.php
blob: ca994b397f3e453d627be2451f3a4ed7254dc2d7 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
<?php

namespace andreskrey\Readability;

use DOMDocument;

class HTMLParser
{

    private $dom = null;

    private $metadata = [];
    private $title = [];
    private $elementsToScore = [];
    private $regexps = [
        'unlikelyCandidates' => '/banner|combx|comment|community|disqus|extra|foot|header|menu|modal|related|remark|rss|share|shoutbox|sidebar|skyscraper|sponsor|ad-break|agegate|pagination|pager|popup/i',
        'okMaybeItsACandidate' => '/and|article|body|column|main|shadow/i',
        'extraneous' => '/print|archive|comment|discuss|e[\-]?mail|share|reply|all|login|sign|single|utility/i',
        'byline' => '/byline|author|dateline|writtenby|p-author/i',
        'replaceFonts' => '/<(\/?)font[^>]*>/gi',
        'normalize' => '/\s{2,}/g',
        'videos' => '/\/\/(www\.)?(dailymotion|youtube|youtube-nocookie|player\.vimeo)\.com/i',
        'nextLink' => '/(next|weiter|continue|>([^\|]|$)|»([^\|]|$))/i',
        'prevLink' => '/(prev|earl|old|new|<|«)/i',
        'whitespace' => '/^\s*$/',
        'hasContent' => '/\S$/'
    ];

    public function __construct()
    {
        $this->dom = new DOMDocument('1.0', 'utf-8');
        libxml_use_internal_errors(true);
    }

    public function parse($html)
    {
        $this->loadHTML($html);

        $this->removeScripts();

        $this->metadata = $this->getMetadata();

        $this->title = $this->getTitle();

        if (!($root = $this->dom->getElementsByTagName('body')->item(0))) {
            throw new \InvalidArgumentException('Invalid HTML was provided');
        }

        $root = new DOMElement($root);

        $this->getNodes($root);

        $this->rateNodes($this->elementsToScore);
    }

    private function loadHTML($html)
    {
        $this->dom->loadHTML($html);
        $this->dom->encoding = 'utf-8';
    }

    private function removeScripts()
    {
        while ($script = $this->dom->getElementsByTagName('script')) {
            if ($script->item(0)) {
                $script->item(0)->parentNode->removeChild($script->item(0));
            } else {
                break;
            }
        }
    }

    private function getMetadata()
    {
        $metadata = [];
        foreach ($this->dom->getElementsByTagName('meta') as $meta) {
            $name = $meta->getAttribute('name');
            $property = $meta->getAttribute('property');

            $item = ($name ? $name : $property);

            if ($item == 'og:title' || $item == 'twitter:title') {
                $metadata['title'] = $meta->getAttribute('content');
            }

            if ($item == 'og:description' || $item == 'twitter:description') {
                $metadata['excerpt'] = $meta->getAttribute('content');
            }

            if ($item == 'author') {
                $metadata['byline'] = $meta->getAttribute('content');
            }
        }

        return $metadata;
    }

    private function getTitle()
    {
        if (isset($this->metadata['title'])) {
            return $this->metadata['title'];
        }

        $title = $this->dom->getElementsByTagName('title');
        if ($title) {
            return $title->item(0)->nodeValue;
        }

        return null;
    }

    private function getNodes(DOMElementInterface $node)
    {
        $matchString = $node->getAttribute('class') . ' ' . $node->getAttribute('id');

        if (
            preg_match($this->regexps['unlikelyCandidates'], $matchString) &&
            !preg_match($this->regexps['okMaybeItsACandidate'], $matchString) &&
            !$node->tagNameEqualsTo('body') &&
            !$node->tagNameEqualsTo('a')
        ) {
            return;
        }

        if ($node->hasChildren()) {
            foreach ($node->getChildren() as $child) {
                $this->getNodes($child);
            }
        }

        if ($node->hasSinglePNode()) {
            $pNode = $node->getChildren();
            $node = $pNode[0];
        }

        if (trim($node->getValue())) {
            $this->elementsToScore[] = $node;
        }
    }

    /**
     * @param array $nodes
     */
    private function rateNodes($nodes)
    {
        $candidates = [];

        foreach ($nodes as $node) {
            if (strlen($node->getValue()) < 25) {
                continue;
            }

            $ancestors = $node->getNodeAncestors();
            if ($ancestors < 3) {
                continue;
            }

            // Start with a point for the paragraph itself as a base.
            $contentScore = 1;

            // Add points for any commas within this paragraph.
            $contentScore += count(explode(', ', $node->getValue()));

            // For every 100 characters in this paragraph, add another point. Up to 3 points.
            $contentScore += min(floor(strlen($node->getValue()) / 100), 3);

            foreach ($ancestors as $ancestor) {
                $readability = new Readability($ancestor);
                $candidates[] = $readability->initializeNode();
            }

        }
    }
}