334 lines
47 KiB
HTML
334 lines
47 KiB
HTML
|
|
<!DOCTYPE html>
|
||
|
|
<html lang="en">
|
||
|
|
<head>
|
||
|
|
<meta charset="UTF-8">
|
||
|
|
<title>Code Coverage for /var/www/html/backend/app/Services/Parsers/VrtArticlePageParser.php</title>
|
||
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||
|
|
<link href="../../_css/bootstrap.min.css?v=11.0.10" rel="stylesheet" type="text/css">
|
||
|
|
<link href="../../_css/octicons.css?v=11.0.10" rel="stylesheet" type="text/css">
|
||
|
|
<link href="../../_css/style.css?v=11.0.10" rel="stylesheet" type="text/css">
|
||
|
|
<link href="../../_css/custom.css" rel="stylesheet" type="text/css">
|
||
|
|
</head>
|
||
|
|
<body>
|
||
|
|
<header>
|
||
|
|
<div class="container-fluid">
|
||
|
|
<div class="row">
|
||
|
|
<div class="col-md-12">
|
||
|
|
<nav aria-label="breadcrumb">
|
||
|
|
<ol class="breadcrumb">
|
||
|
|
<li class="breadcrumb-item"><a href="../../index.html">/var/www/html/backend/app</a></li>
|
||
|
|
<li class="breadcrumb-item"><a href="../index.html">Services</a></li>
|
||
|
|
<li class="breadcrumb-item"><a href="index.html">Parsers</a></li>
|
||
|
|
<li class="breadcrumb-item active">VrtArticlePageParser.php</li>
|
||
|
|
|
||
|
|
</ol>
|
||
|
|
</nav>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
</header>
|
||
|
|
<div class="container-fluid">
|
||
|
|
<div class="table-responsive">
|
||
|
|
<table class="table table-bordered">
|
||
|
|
<thead>
|
||
|
|
<tr>
|
||
|
|
<td> </td>
|
||
|
|
<td colspan="10"><div align="center"><strong>Code Coverage</strong></div></td>
|
||
|
|
</tr>
|
||
|
|
<tr>
|
||
|
|
<td> </td>
|
||
|
|
<td colspan="3"><div align="center"><strong>Lines</strong></div></td>
|
||
|
|
<td colspan="4"><div align="center"><strong>Functions and Methods</strong></div></td>
|
||
|
|
<td colspan="3"><div align="center"><strong>Classes and Traits</strong></div></td>
|
||
|
|
</tr>
|
||
|
|
</thead>
|
||
|
|
<tbody>
|
||
|
|
<tr>
|
||
|
|
<td class="danger">Total</td>
|
||
|
|
<td class="danger big"> <div class="progress">
|
||
|
|
<div class="progress-bar bg-danger" role="progressbar" aria-valuenow="0.00" aria-valuemin="0" aria-valuemax="100" style="width: 0.00%">
|
||
|
|
<span class="visually-hidden">0.00% covered (danger)</span>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
</td>
|
||
|
|
<td class="danger small"><div align="right">0.00%</div></td>
|
||
|
|
<td class="danger small"><div align="right">0 / 35</div></td>
|
||
|
|
<td class="danger big"> <div class="progress">
|
||
|
|
<div class="progress-bar bg-danger" role="progressbar" aria-valuenow="0.00" aria-valuemin="0" aria-valuemax="100" style="width: 0.00%">
|
||
|
|
<span class="visually-hidden">0.00% covered (danger)</span>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
</td>
|
||
|
|
<td class="danger small"><div align="right">0.00%</div></td>
|
||
|
|
<td class="danger small"><div align="right">0 / 5</div></td>
|
||
|
|
<td class="danger small"><abbr title="Change Risk Anti-Patterns (CRAP) Index">CRAP</abbr></td>
|
||
|
|
<td class="danger big"> <div class="progress">
|
||
|
|
<div class="progress-bar bg-danger" role="progressbar" aria-valuenow="0.00" aria-valuemin="0" aria-valuemax="100" style="width: 0.00%">
|
||
|
|
<span class="visually-hidden">0.00% covered (danger)</span>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
</td>
|
||
|
|
<td class="danger small"><div align="right">0.00%</div></td>
|
||
|
|
<td class="danger small"><div align="right">0 / 1</div></td>
|
||
|
|
</tr>
|
||
|
|
|
||
|
|
<tr>
|
||
|
|
<td class="danger"><abbr title="App\Services\Parsers\VrtArticlePageParser">VrtArticlePageParser</abbr></td>
|
||
|
|
<td class="danger big"> <div class="progress">
|
||
|
|
<div class="progress-bar bg-danger" role="progressbar" aria-valuenow="0.00" aria-valuemin="0" aria-valuemax="100" style="width: 0.00%">
|
||
|
|
<span class="visually-hidden">0.00% covered (danger)</span>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
</td>
|
||
|
|
<td class="danger small"><div align="right">0.00%</div></td>
|
||
|
|
<td class="danger small"><div align="right">0 / 35</div></td>
|
||
|
|
<td class="danger big"> <div class="progress">
|
||
|
|
<div class="progress-bar bg-danger" role="progressbar" aria-valuenow="0.00" aria-valuemin="0" aria-valuemax="100" style="width: 0.00%">
|
||
|
|
<span class="visually-hidden">0.00% covered (danger)</span>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
</td>
|
||
|
|
<td class="danger small"><div align="right">0.00%</div></td>
|
||
|
|
<td class="danger small"><div align="right">0 / 5</div></td>
|
||
|
|
<td class="danger small">210</td>
|
||
|
|
<td class="danger big"> <div class="progress">
|
||
|
|
<div class="progress-bar bg-danger" role="progressbar" aria-valuenow="0.00" aria-valuemin="0" aria-valuemax="100" style="width: 0.00%">
|
||
|
|
<span class="visually-hidden">0.00% covered (danger)</span>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
</td>
|
||
|
|
<td class="danger small"><div align="right">0.00%</div></td>
|
||
|
|
<td class="danger small"><div align="right">0 / 1</div></td>
|
||
|
|
</tr>
|
||
|
|
|
||
|
|
<tr>
|
||
|
|
<td class="danger"> <a href="#7"><abbr title="extractTitle(string $html): ?string">extractTitle</abbr></a></td>
|
||
|
|
<td class="danger big"> <div class="progress">
|
||
|
|
<div class="progress-bar bg-danger" role="progressbar" aria-valuenow="0.00" aria-valuemin="0" aria-valuemax="100" style="width: 0.00%">
|
||
|
|
<span class="visually-hidden">0.00% covered (danger)</span>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
</td>
|
||
|
|
<td class="danger small"><div align="right">0.00%</div></td>
|
||
|
|
<td class="danger small"><div align="right">0 / 7</div></td>
|
||
|
|
<td class="danger big"> <div class="progress">
|
||
|
|
<div class="progress-bar bg-danger" role="progressbar" aria-valuenow="0.00" aria-valuemin="0" aria-valuemax="100" style="width: 0.00%">
|
||
|
|
<span class="visually-hidden">0.00% covered (danger)</span>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
</td>
|
||
|
|
<td class="danger small"><div align="right">0.00%</div></td>
|
||
|
|
<td class="danger small"><div align="right">0 / 1</div></td>
|
||
|
|
<td class="danger small">20</td>
|
||
|
|
<td class="danger" colspan="3"></td>
|
||
|
|
</tr>
|
||
|
|
|
||
|
|
<tr>
|
||
|
|
<td class="danger"> <a href="#27"><abbr title="extractDescription(string $html): ?string">extractDescription</abbr></a></td>
|
||
|
|
<td class="danger big"> <div class="progress">
|
||
|
|
<div class="progress-bar bg-danger" role="progressbar" aria-valuenow="0.00" aria-valuemin="0" aria-valuemax="100" style="width: 0.00%">
|
||
|
|
<span class="visually-hidden">0.00% covered (danger)</span>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
</td>
|
||
|
|
<td class="danger small"><div align="right">0.00%</div></td>
|
||
|
|
<td class="danger small"><div align="right">0 / 5</div></td>
|
||
|
|
<td class="danger big"> <div class="progress">
|
||
|
|
<div class="progress-bar bg-danger" role="progressbar" aria-valuenow="0.00" aria-valuemin="0" aria-valuemax="100" style="width: 0.00%">
|
||
|
|
<span class="visually-hidden">0.00% covered (danger)</span>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
</td>
|
||
|
|
<td class="danger small"><div align="right">0.00%</div></td>
|
||
|
|
<td class="danger small"><div align="right">0 / 1</div></td>
|
||
|
|
<td class="danger small">12</td>
|
||
|
|
<td class="danger" colspan="3"></td>
|
||
|
|
</tr>
|
||
|
|
|
||
|
|
<tr>
|
||
|
|
<td class="danger"> <a href="#42"><abbr title="extractFullArticle(string $html): ?string">extractFullArticle</abbr></a></td>
|
||
|
|
<td class="danger big"> <div class="progress">
|
||
|
|
<div class="progress-bar bg-danger" role="progressbar" aria-valuenow="0.00" aria-valuemin="0" aria-valuemax="100" style="width: 0.00%">
|
||
|
|
<span class="visually-hidden">0.00% covered (danger)</span>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
</td>
|
||
|
|
<td class="danger small"><div align="right">0.00%</div></td>
|
||
|
|
<td class="danger small"><div align="right">0 / 12</div></td>
|
||
|
|
<td class="danger big"> <div class="progress">
|
||
|
|
<div class="progress-bar bg-danger" role="progressbar" aria-valuenow="0.00" aria-valuemin="0" aria-valuemax="100" style="width: 0.00%">
|
||
|
|
<span class="visually-hidden">0.00% covered (danger)</span>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
</td>
|
||
|
|
<td class="danger small"><div align="right">0.00%</div></td>
|
||
|
|
<td class="danger small"><div align="right">0 / 1</div></td>
|
||
|
|
<td class="danger small">12</td>
|
||
|
|
<td class="danger" colspan="3"></td>
|
||
|
|
</tr>
|
||
|
|
|
||
|
|
<tr>
|
||
|
|
<td class="danger"> <a href="#67"><abbr title="extractThumbnail(string $html): ?string">extractThumbnail</abbr></a></td>
|
||
|
|
<td class="danger big"> <div class="progress">
|
||
|
|
<div class="progress-bar bg-danger" role="progressbar" aria-valuenow="0.00" aria-valuemin="0" aria-valuemax="100" style="width: 0.00%">
|
||
|
|
<span class="visually-hidden">0.00% covered (danger)</span>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
</td>
|
||
|
|
<td class="danger small"><div align="right">0.00%</div></td>
|
||
|
|
<td class="danger small"><div align="right">0 / 5</div></td>
|
||
|
|
<td class="danger big"> <div class="progress">
|
||
|
|
<div class="progress-bar bg-danger" role="progressbar" aria-valuenow="0.00" aria-valuemin="0" aria-valuemax="100" style="width: 0.00%">
|
||
|
|
<span class="visually-hidden">0.00% covered (danger)</span>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
</td>
|
||
|
|
<td class="danger small"><div align="right">0.00%</div></td>
|
||
|
|
<td class="danger small"><div align="right">0 / 1</div></td>
|
||
|
|
<td class="danger small">12</td>
|
||
|
|
<td class="danger" colspan="3"></td>
|
||
|
|
</tr>
|
||
|
|
|
||
|
|
<tr>
|
||
|
|
<td class="danger"> <a href="#83"><abbr title="extractData(string $html): array">extractData</abbr></a></td>
|
||
|
|
<td class="danger big"> <div class="progress">
|
||
|
|
<div class="progress-bar bg-danger" role="progressbar" aria-valuenow="0.00" aria-valuemin="0" aria-valuemax="100" style="width: 0.00%">
|
||
|
|
<span class="visually-hidden">0.00% covered (danger)</span>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
</td>
|
||
|
|
<td class="danger small"><div align="right">0.00%</div></td>
|
||
|
|
<td class="danger small"><div align="right">0 / 6</div></td>
|
||
|
|
<td class="danger big"> <div class="progress">
|
||
|
|
<div class="progress-bar bg-danger" role="progressbar" aria-valuenow="0.00" aria-valuemin="0" aria-valuemax="100" style="width: 0.00%">
|
||
|
|
<span class="visually-hidden">0.00% covered (danger)</span>
|
||
|
|
</div>
|
||
|
|
</div>
|
||
|
|
</td>
|
||
|
|
<td class="danger small"><div align="right">0.00%</div></td>
|
||
|
|
<td class="danger small"><div align="right">0 / 1</div></td>
|
||
|
|
<td class="danger small">2</td>
|
||
|
|
<td class="danger" colspan="3"></td>
|
||
|
|
</tr>
|
||
|
|
|
||
|
|
|
||
|
|
</tbody>
|
||
|
|
</table>
|
||
|
|
</div>
|
||
|
|
<table id="code" class="table table-borderless table-condensed">
|
||
|
|
<tbody>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="1" href="#1">1</a></td><td class="col-11 codeLine"><span class="default"><?php</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="2" href="#2">2</a></td><td class="col-11 codeLine"></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="3" href="#3">3</a></td><td class="col-11 codeLine"><span class="keyword">namespace</span><span class="default"> </span><span class="default">App\Services\Parsers</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="4" href="#4">4</a></td><td class="col-11 codeLine"></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="5" href="#5">5</a></td><td class="col-11 codeLine"><span class="keyword">class</span><span class="default"> </span><span class="default">VrtArticlePageParser</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="6" href="#6">6</a></td><td class="col-11 codeLine"><span class="keyword">{</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="7" href="#7">7</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">public</span><span class="default"> </span><span class="keyword">static</span><span class="default"> </span><span class="keyword">function</span><span class="default"> </span><span class="default">extractTitle</span><span class="keyword">(</span><span class="default">string</span><span class="default"> </span><span class="default">$html</span><span class="keyword">)</span><span class="keyword">:</span><span class="default"> </span><span class="keyword">?</span><span class="default">string</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="8" href="#8">8</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">{</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="9" href="#9">9</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="comment">// Try meta title first</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="10" href="#10">10</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">if</span><span class="default"> </span><span class="keyword">(</span><span class="default">preg_match</span><span class="keyword">(</span><span class="default">'/<meta property="og:title" content="([^"]+)"/i'</span><span class="keyword">,</span><span class="default"> </span><span class="default">$html</span><span class="keyword">,</span><span class="default"> </span><span class="default">$matches</span><span class="keyword">)</span><span class="keyword">)</span><span class="default"> </span><span class="keyword">{</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="11" href="#11">11</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">return</span><span class="default"> </span><span class="default">html_entity_decode</span><span class="keyword">(</span><span class="default">$matches</span><span class="keyword">[</span><span class="default">1</span><span class="keyword">]</span><span class="keyword">,</span><span class="default"> </span><span class="default">ENT_QUOTES</span><span class="keyword">,</span><span class="default"> </span><span class="default">'UTF-8'</span><span class="keyword">)</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="12" href="#12">12</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">}</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="13" href="#13">13</a></td><td class="col-11 codeLine"></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="14" href="#14">14</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="comment">// Try h1 tag</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="15" href="#15">15</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">if</span><span class="default"> </span><span class="keyword">(</span><span class="default">preg_match</span><span class="keyword">(</span><span class="default">'/<h1[^>]*>([^<]+)<\/h1>/i'</span><span class="keyword">,</span><span class="default"> </span><span class="default">$html</span><span class="keyword">,</span><span class="default"> </span><span class="default">$matches</span><span class="keyword">)</span><span class="keyword">)</span><span class="default"> </span><span class="keyword">{</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="16" href="#16">16</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">return</span><span class="default"> </span><span class="default">html_entity_decode</span><span class="keyword">(</span><span class="default">strip_tags</span><span class="keyword">(</span><span class="default">$matches</span><span class="keyword">[</span><span class="default">1</span><span class="keyword">]</span><span class="keyword">)</span><span class="keyword">,</span><span class="default"> </span><span class="default">ENT_QUOTES</span><span class="keyword">,</span><span class="default"> </span><span class="default">'UTF-8'</span><span class="keyword">)</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="17" href="#17">17</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">}</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="18" href="#18">18</a></td><td class="col-11 codeLine"></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="19" href="#19">19</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="comment">// Try title tag</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="20" href="#20">20</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">if</span><span class="default"> </span><span class="keyword">(</span><span class="default">preg_match</span><span class="keyword">(</span><span class="default">'/<title>([^<]+)<\/title>/i'</span><span class="keyword">,</span><span class="default"> </span><span class="default">$html</span><span class="keyword">,</span><span class="default"> </span><span class="default">$matches</span><span class="keyword">)</span><span class="keyword">)</span><span class="default"> </span><span class="keyword">{</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="21" href="#21">21</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">return</span><span class="default"> </span><span class="default">html_entity_decode</span><span class="keyword">(</span><span class="default">$matches</span><span class="keyword">[</span><span class="default">1</span><span class="keyword">]</span><span class="keyword">,</span><span class="default"> </span><span class="default">ENT_QUOTES</span><span class="keyword">,</span><span class="default"> </span><span class="default">'UTF-8'</span><span class="keyword">)</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="22" href="#22">22</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">}</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="23" href="#23">23</a></td><td class="col-11 codeLine"></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="24" href="#24">24</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">return</span><span class="default"> </span><span class="default">null</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="25" href="#25">25</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">}</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="26" href="#26">26</a></td><td class="col-11 codeLine"></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="27" href="#27">27</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">public</span><span class="default"> </span><span class="keyword">static</span><span class="default"> </span><span class="keyword">function</span><span class="default"> </span><span class="default">extractDescription</span><span class="keyword">(</span><span class="default">string</span><span class="default"> </span><span class="default">$html</span><span class="keyword">)</span><span class="keyword">:</span><span class="default"> </span><span class="keyword">?</span><span class="default">string</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="28" href="#28">28</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">{</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="29" href="#29">29</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="comment">// Try meta description first</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="30" href="#30">30</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">if</span><span class="default"> </span><span class="keyword">(</span><span class="default">preg_match</span><span class="keyword">(</span><span class="default">'/<meta property="og:description" content="([^"]+)"/i'</span><span class="keyword">,</span><span class="default"> </span><span class="default">$html</span><span class="keyword">,</span><span class="default"> </span><span class="default">$matches</span><span class="keyword">)</span><span class="keyword">)</span><span class="default"> </span><span class="keyword">{</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="31" href="#31">31</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">return</span><span class="default"> </span><span class="default">html_entity_decode</span><span class="keyword">(</span><span class="default">$matches</span><span class="keyword">[</span><span class="default">1</span><span class="keyword">]</span><span class="keyword">,</span><span class="default"> </span><span class="default">ENT_QUOTES</span><span class="keyword">,</span><span class="default"> </span><span class="default">'UTF-8'</span><span class="keyword">)</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="32" href="#32">32</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">}</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="33" href="#33">33</a></td><td class="col-11 codeLine"></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="34" href="#34">34</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="comment">// Try to find first paragraph in article content</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="35" href="#35">35</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">if</span><span class="default"> </span><span class="keyword">(</span><span class="default">preg_match</span><span class="keyword">(</span><span class="default">'/<p[^>]*>([^<]+(?:<[^\/](?!p)[^>]*>[^<]*<\/[^>]*>[^<]*)*)<\/p>/i'</span><span class="keyword">,</span><span class="default"> </span><span class="default">$html</span><span class="keyword">,</span><span class="default"> </span><span class="default">$matches</span><span class="keyword">)</span><span class="keyword">)</span><span class="default"> </span><span class="keyword">{</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="36" href="#36">36</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">return</span><span class="default"> </span><span class="default">html_entity_decode</span><span class="keyword">(</span><span class="default">strip_tags</span><span class="keyword">(</span><span class="default">$matches</span><span class="keyword">[</span><span class="default">1</span><span class="keyword">]</span><span class="keyword">)</span><span class="keyword">,</span><span class="default"> </span><span class="default">ENT_QUOTES</span><span class="keyword">,</span><span class="default"> </span><span class="default">'UTF-8'</span><span class="keyword">)</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="37" href="#37">37</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">}</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="38" href="#38">38</a></td><td class="col-11 codeLine"></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="39" href="#39">39</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">return</span><span class="default"> </span><span class="default">null</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="40" href="#40">40</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">}</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="41" href="#41">41</a></td><td class="col-11 codeLine"></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="42" href="#42">42</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">public</span><span class="default"> </span><span class="keyword">static</span><span class="default"> </span><span class="keyword">function</span><span class="default"> </span><span class="default">extractFullArticle</span><span class="keyword">(</span><span class="default">string</span><span class="default"> </span><span class="default">$html</span><span class="keyword">)</span><span class="keyword">:</span><span class="default"> </span><span class="keyword">?</span><span class="default">string</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="43" href="#43">43</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">{</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="44" href="#44">44</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="comment">// Remove scripts, styles, and other non-content elements</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="45" href="#45">45</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="default">$cleanHtml</span><span class="default"> </span><span class="keyword">=</span><span class="default"> </span><span class="default">preg_replace</span><span class="keyword">(</span><span class="default">'/<script\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/script>/mi'</span><span class="keyword">,</span><span class="default"> </span><span class="default">''</span><span class="keyword">,</span><span class="default"> </span><span class="default">$html</span><span class="keyword">)</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="46" href="#46">46</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="default">$cleanHtml</span><span class="default"> </span><span class="keyword">=</span><span class="default"> </span><span class="default">preg_replace</span><span class="keyword">(</span><span class="default">'/<style\b[^<]*(?:(?!<\/style>)<[^<]*)*<\/style>/mi'</span><span class="keyword">,</span><span class="default"> </span><span class="default">''</span><span class="keyword">,</span><span class="default"> </span><span class="default">$cleanHtml</span><span class="keyword">)</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="47" href="#47">47</a></td><td class="col-11 codeLine"></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="48" href="#48">48</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="comment">// Extract all paragraph content</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="49" href="#49">49</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="default">preg_match_all</span><span class="keyword">(</span><span class="default">'/<p[^>]*>(.*?)<\/p>/is'</span><span class="keyword">,</span><span class="default"> </span><span class="default">$cleanHtml</span><span class="keyword">,</span><span class="default"> </span><span class="default">$matches</span><span class="keyword">)</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="50" href="#50">50</a></td><td class="col-11 codeLine"></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="51" href="#51">51</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">if</span><span class="default"> </span><span class="keyword">(</span><span class="keyword">!</span><span class="keyword">empty</span><span class="keyword">(</span><span class="default">$matches</span><span class="keyword">[</span><span class="default">1</span><span class="keyword">]</span><span class="keyword">)</span><span class="keyword">)</span><span class="default"> </span><span class="keyword">{</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="52" href="#52">52</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="default">$paragraphs</span><span class="default"> </span><span class="keyword">=</span><span class="default"> </span><span class="default">array_map</span><span class="keyword">(</span><span class="keyword">function</span><span class="keyword">(</span><span class="default">$paragraph</span><span class="keyword">)</span><span class="default"> </span><span class="keyword">{</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="53" href="#53">53</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">return</span><span class="default"> </span><span class="default">html_entity_decode</span><span class="keyword">(</span><span class="default">strip_tags</span><span class="keyword">(</span><span class="default">$paragraph</span><span class="keyword">)</span><span class="keyword">,</span><span class="default"> </span><span class="default">ENT_QUOTES</span><span class="keyword">,</span><span class="default"> </span><span class="default">'UTF-8'</span><span class="keyword">)</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="54" href="#54">54</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">}</span><span class="keyword">,</span><span class="default"> </span><span class="default">$matches</span><span class="keyword">[</span><span class="default">1</span><span class="keyword">]</span><span class="keyword">)</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="55" href="#55">55</a></td><td class="col-11 codeLine"></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="56" href="#56">56</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="comment">// Filter out empty paragraphs and join with double newlines</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="57" href="#57">57</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="default">$fullText</span><span class="default"> </span><span class="keyword">=</span><span class="default"> </span><span class="default">implode</span><span class="keyword">(</span><span class="default">"\n\n"</span><span class="keyword">,</span><span class="default"> </span><span class="default">array_filter</span><span class="keyword">(</span><span class="default">$paragraphs</span><span class="keyword">,</span><span class="default"> </span><span class="keyword">function</span><span class="keyword">(</span><span class="default">$p</span><span class="keyword">)</span><span class="default"> </span><span class="keyword">{</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="58" href="#58">58</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">return</span><span class="default"> </span><span class="default">trim</span><span class="keyword">(</span><span class="default">$p</span><span class="keyword">)</span><span class="default"> </span><span class="default">!==</span><span class="default"> </span><span class="default">''</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="59" href="#59">59</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">}</span><span class="keyword">)</span><span class="keyword">)</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="60" href="#60">60</a></td><td class="col-11 codeLine"></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="61" href="#61">61</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">return</span><span class="default"> </span><span class="default">$fullText</span><span class="default"> </span><span class="keyword">?</span><span class="keyword">:</span><span class="default"> </span><span class="default">null</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="62" href="#62">62</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">}</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="63" href="#63">63</a></td><td class="col-11 codeLine"></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="64" href="#64">64</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">return</span><span class="default"> </span><span class="default">null</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="65" href="#65">65</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">}</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="66" href="#66">66</a></td><td class="col-11 codeLine"></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="67" href="#67">67</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">public</span><span class="default"> </span><span class="keyword">static</span><span class="default"> </span><span class="keyword">function</span><span class="default"> </span><span class="default">extractThumbnail</span><span class="keyword">(</span><span class="default">string</span><span class="default"> </span><span class="default">$html</span><span class="keyword">)</span><span class="keyword">:</span><span class="default"> </span><span class="keyword">?</span><span class="default">string</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="68" href="#68">68</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">{</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="69" href="#69">69</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">if</span><span class="default"> </span><span class="keyword">(</span><span class="default">preg_match</span><span class="keyword">(</span><span class="default">'/<meta property="og:image" content="([^"]+)"/i'</span><span class="keyword">,</span><span class="default"> </span><span class="default">$html</span><span class="keyword">,</span><span class="default"> </span><span class="default">$matches</span><span class="keyword">)</span><span class="keyword">)</span><span class="default"> </span><span class="keyword">{</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="70" href="#70">70</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">return</span><span class="default"> </span><span class="default">$matches</span><span class="keyword">[</span><span class="default">1</span><span class="keyword">]</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="71" href="#71">71</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">}</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="72" href="#72">72</a></td><td class="col-11 codeLine"></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="73" href="#73">73</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">if</span><span class="default"> </span><span class="keyword">(</span><span class="default">preg_match</span><span class="keyword">(</span><span class="default">'/<img[^>]+src="([^"]+)"/i'</span><span class="keyword">,</span><span class="default"> </span><span class="default">$html</span><span class="keyword">,</span><span class="default"> </span><span class="default">$matches</span><span class="keyword">)</span><span class="keyword">)</span><span class="default"> </span><span class="keyword">{</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="74" href="#74">74</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">return</span><span class="default"> </span><span class="default">$matches</span><span class="keyword">[</span><span class="default">1</span><span class="keyword">]</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="75" href="#75">75</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">}</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="76" href="#76">76</a></td><td class="col-11 codeLine"></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="77" href="#77">77</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">return</span><span class="default"> </span><span class="default">null</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="78" href="#78">78</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">}</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="79" href="#79">79</a></td><td class="col-11 codeLine"></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="80" href="#80">80</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="comment">/**</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="81" href="#81">81</a></td><td class="col-11 codeLine"><span class="comment"> * @return array<string, string|null></span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="82" href="#82">82</a></td><td class="col-11 codeLine"><span class="comment"> */</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="83" href="#83">83</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">public</span><span class="default"> </span><span class="keyword">static</span><span class="default"> </span><span class="keyword">function</span><span class="default"> </span><span class="default">extractData</span><span class="keyword">(</span><span class="default">string</span><span class="default"> </span><span class="default">$html</span><span class="keyword">)</span><span class="keyword">:</span><span class="default"> </span><span class="keyword">array</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="84" href="#84">84</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">{</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="85" href="#85">85</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">return</span><span class="default"> </span><span class="keyword">[</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="86" href="#86">86</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="default">'title'</span><span class="default"> </span><span class="default">=></span><span class="default"> </span><span class="default">self</span><span class="default">::</span><span class="default">extractTitle</span><span class="keyword">(</span><span class="default">$html</span><span class="keyword">)</span><span class="keyword">,</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="87" href="#87">87</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="default">'description'</span><span class="default"> </span><span class="default">=></span><span class="default"> </span><span class="default">self</span><span class="default">::</span><span class="default">extractDescription</span><span class="keyword">(</span><span class="default">$html</span><span class="keyword">)</span><span class="keyword">,</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="88" href="#88">88</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="default">'full_article'</span><span class="default"> </span><span class="default">=></span><span class="default"> </span><span class="default">self</span><span class="default">::</span><span class="default">extractFullArticle</span><span class="keyword">(</span><span class="default">$html</span><span class="keyword">)</span><span class="keyword">,</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="89" href="#89">89</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="default">'thumbnail'</span><span class="default"> </span><span class="default">=></span><span class="default"> </span><span class="default">self</span><span class="default">::</span><span class="default">extractThumbnail</span><span class="keyword">(</span><span class="default">$html</span><span class="keyword">)</span><span class="keyword">,</span></td></tr>
|
||
|
|
<tr class="danger d-flex"><td class="col-1 text-end"><a id="90" href="#90">90</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">]</span><span class="keyword">;</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="91" href="#91">91</a></td><td class="col-11 codeLine"><span class="default"> </span><span class="keyword">}</span></td></tr>
|
||
|
|
<tr class=" d-flex"><td class="col-1 text-end"><a id="92" href="#92">92</a></td><td class="col-11 codeLine"><span class="keyword">}</span></td></tr>
|
||
|
|
|
||
|
|
</tbody>
|
||
|
|
</table>
|
||
|
|
|
||
|
|
|
||
|
|
<footer>
|
||
|
|
<hr/>
|
||
|
|
<h4>Legend</h4>
|
||
|
|
<p><span class="legend covered-by-small-tests">Covered by small (and larger) tests</span><span class="legend covered-by-medium-tests">Covered by medium (and large) tests</span><span class="legend covered-by-large-tests">Covered by large tests (and tests of unknown size)</span><span class="legend not-covered">Not covered</span><span class="legend not-coverable">Not coverable</span></p>
|
||
|
|
<p>
|
||
|
|
<small>Generated by <a href="https://github.com/sebastianbergmann/php-code-coverage" target="_top">php-code-coverage 11.0.10</a> using <a href="https://www.php.net/" target="_top">PHP 8.4.10</a> and <a href="https://phpunit.de/">PHPUnit 11.5.28</a> at Sun Aug 3 18:53:46 UTC 2025.</small>
|
||
|
|
</p>
|
||
|
|
<a title="Back to the top" id="toplink" href="#">
|
||
|
|
<svg xmlns="http://www.w3.org/2000/svg" width="12" height="16" viewBox="0 0 12 16"><path fill-rule="evenodd" d="M12 11L6 5l-6 6h12z"/></svg>
|
||
|
|
</a>
|
||
|
|
</footer>
|
||
|
|
</div>
|
||
|
|
<script src="../../_js/jquery.min.js?v=11.0.10" type="text/javascript"></script>
|
||
|
|
<script src="../../_js/bootstrap.bundle.min.js?v=11.0.10" type="text/javascript"></script>
|
||
|
|
<script src="../../_js/file.js?v=11.0.10" type="text/javascript"></script>
|
||
|
|
</body>
|
||
|
|
</html>
|