334 lines
12 KiB
PHP
334 lines
12 KiB
PHP
|
<?php
|
||
|
|
|
||
|
|
namespace Tests\Unit\Services\Parsers;
|
||
|
|
|
||
|
|
use App\Services\Parsers\BelgaArticlePageParser;
|
||
|
|
use Tests\TestCase;
|
||
|
|
|
||
|
|
class BelgaArticlePageParserTest extends TestCase
|
||
|
|
{
|
||
|
|
public function test_extract_title_from_og_meta_tag(): void
|
||
|
|
{
|
||
|
|
$html = '<html><head><meta property="og:title" content="Test Article Title"/></head><body></body></html>';
|
||
|
|
|
||
|
|
$title = BelgaArticlePageParser::extractTitle($html);
|
||
|
|
|
||
|
|
$this->assertEquals('Test Article Title', $title);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_title_from_h1_tag(): void
|
||
|
|
{
|
||
|
|
$html = '<html><body><h1>H1 Title Test</h1></body></html>';
|
||
|
|
|
||
|
|
$title = BelgaArticlePageParser::extractTitle($html);
|
||
|
|
|
||
|
|
$this->assertEquals('H1 Title Test', $title);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_title_from_title_tag(): void
|
||
|
|
{
|
||
|
|
$html = '<html><head><title>Page Title Test</title></head><body></body></html>';
|
||
|
|
|
||
|
|
$title = BelgaArticlePageParser::extractTitle($html);
|
||
|
|
|
||
|
|
$this->assertEquals('Page Title Test', $title);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_title_with_html_entities(): void
|
||
|
|
{
|
||
|
|
$html = '<html><head><meta property="og:title" content="Test & Article "Title""/></head></html>';
|
||
|
|
|
||
|
|
$title = BelgaArticlePageParser::extractTitle($html);
|
||
|
|
|
||
|
|
$this->assertEquals('Test & Article "Title"', $title);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_title_returns_null_when_not_found(): void
|
||
|
|
{
|
||
|
|
$html = '<html><body><p>No title here</p></body></html>';
|
||
|
|
|
||
|
|
$title = BelgaArticlePageParser::extractTitle($html);
|
||
|
|
|
||
|
|
$this->assertNull($title);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_description_from_og_meta_tag(): void
|
||
|
|
{
|
||
|
|
$html = '<html><head><meta property="og:description" content="Test article description"/></head></html>';
|
||
|
|
|
||
|
|
$description = BelgaArticlePageParser::extractDescription($html);
|
||
|
|
|
||
|
|
$this->assertEquals('Test article description', $description);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_description_from_paragraph(): void
|
||
|
|
{
|
||
|
|
$html = '<html><body><p>This is the first paragraph description.</p></body></html>';
|
||
|
|
|
||
|
|
$description = BelgaArticlePageParser::extractDescription($html);
|
||
|
|
|
||
|
|
$this->assertEquals('This is the first paragraph description.', $description);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_description_with_html_entities(): void
|
||
|
|
{
|
||
|
|
$html = '<html><head><meta property="og:description" content="Description with & entities <test>"/></head></html>';
|
||
|
|
|
||
|
|
$description = BelgaArticlePageParser::extractDescription($html);
|
||
|
|
|
||
|
|
$this->assertEquals('Description with & entities <test>', $description);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_description_returns_null_when_not_found(): void
|
||
|
|
{
|
||
|
|
$html = '<html><body><div>No description here</div></body></html>';
|
||
|
|
|
||
|
|
$description = BelgaArticlePageParser::extractDescription($html);
|
||
|
|
|
||
|
|
$this->assertNull($description);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_full_article_from_belga_paragraph_class(): void
|
||
|
|
{
|
||
|
|
$html = '
|
||
|
|
<html>
|
||
|
|
<body>
|
||
|
|
<p class="styles_paragraph__6o_o7">First paragraph content.</p>
|
||
|
|
<p class="styles_paragraph__6o_o7">Second paragraph content.</p>
|
||
|
|
<p class="other-class">This should be ignored.</p>
|
||
|
|
</body>
|
||
|
|
</html>
|
||
|
|
';
|
||
|
|
|
||
|
|
$fullArticle = BelgaArticlePageParser::extractFullArticle($html);
|
||
|
|
|
||
|
|
$expected = "First paragraph content.\n\nSecond paragraph content.";
|
||
|
|
$this->assertEquals($expected, $fullArticle);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_full_article_filters_empty_paragraphs(): void
|
||
|
|
{
|
||
|
|
$html = '
|
||
|
|
<html>
|
||
|
|
<body>
|
||
|
|
<p class="styles_paragraph__ABC123">Content paragraph.</p>
|
||
|
|
<p class="styles_paragraph__DEF456"> </p>
|
||
|
|
<p class="styles_paragraph__GHI789"></p>
|
||
|
|
<p class="styles_paragraph__JKL012">Another content paragraph.</p>
|
||
|
|
</body>
|
||
|
|
</html>
|
||
|
|
';
|
||
|
|
|
||
|
|
$fullArticle = BelgaArticlePageParser::extractFullArticle($html);
|
||
|
|
|
||
|
|
$expected = "Content paragraph.\n\nAnother content paragraph.";
|
||
|
|
$this->assertEquals($expected, $fullArticle);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_full_article_handles_nested_tags(): void
|
||
|
|
{
|
||
|
|
$html = '
|
||
|
|
<html>
|
||
|
|
<body>
|
||
|
|
<p class="styles_paragraph__TEST">This has <strong>bold text</strong> and <em>italic text</em>.</p>
|
||
|
|
<p class="styles_paragraph__TEST2">This has <a href="#">a link</a> inside.</p>
|
||
|
|
</body>
|
||
|
|
</html>
|
||
|
|
';
|
||
|
|
|
||
|
|
$fullArticle = BelgaArticlePageParser::extractFullArticle($html);
|
||
|
|
|
||
|
|
$expected = "This has bold text and italic text.\n\nThis has a link inside.";
|
||
|
|
$this->assertEquals($expected, $fullArticle);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_full_article_removes_scripts_and_styles(): void
|
||
|
|
{
|
||
|
|
$html = '
|
||
|
|
<html>
|
||
|
|
<head>
|
||
|
|
<script>console.log("test");</script>
|
||
|
|
<style>.test { color: red; }</style>
|
||
|
|
</head>
|
||
|
|
<body>
|
||
|
|
<p class="styles_paragraph__TEST">Clean content.</p>
|
||
|
|
<script>alert("bad");</script>
|
||
|
|
</body>
|
||
|
|
</html>
|
||
|
|
';
|
||
|
|
|
||
|
|
$fullArticle = BelgaArticlePageParser::extractFullArticle($html);
|
||
|
|
|
||
|
|
$this->assertEquals('Clean content.', $fullArticle);
|
||
|
|
$this->assertStringNotContainsString('console.log', $fullArticle);
|
||
|
|
$this->assertStringNotContainsString('alert', $fullArticle);
|
||
|
|
$this->assertStringNotContainsString('color: red', $fullArticle);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_full_article_fallback_to_prezly_document(): void
|
||
|
|
{
|
||
|
|
$html = '
|
||
|
|
<html>
|
||
|
|
<body>
|
||
|
|
<section class="prezly-slate-document">
|
||
|
|
<p>Content from prezly section.</p>
|
||
|
|
<p>More prezly content.</p>
|
||
|
|
</section>
|
||
|
|
</body>
|
||
|
|
</html>
|
||
|
|
';
|
||
|
|
|
||
|
|
$fullArticle = BelgaArticlePageParser::extractFullArticle($html);
|
||
|
|
|
||
|
|
$expected = "Content from prezly section.\n\nMore prezly content.";
|
||
|
|
$this->assertEquals($expected, $fullArticle);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_full_article_fallback_to_all_paragraphs(): void
|
||
|
|
{
|
||
|
|
$html = '
|
||
|
|
<html>
|
||
|
|
<body>
|
||
|
|
<p>First general paragraph.</p>
|
||
|
|
<p>Second general paragraph.</p>
|
||
|
|
</body>
|
||
|
|
</html>
|
||
|
|
';
|
||
|
|
|
||
|
|
$fullArticle = BelgaArticlePageParser::extractFullArticle($html);
|
||
|
|
|
||
|
|
$expected = "First general paragraph.\n\nSecond general paragraph.";
|
||
|
|
$this->assertEquals($expected, $fullArticle);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_full_article_returns_null_when_no_content(): void
|
||
|
|
{
|
||
|
|
$html = '<html><body><div>No paragraphs here</div></body></html>';
|
||
|
|
|
||
|
|
$fullArticle = BelgaArticlePageParser::extractFullArticle($html);
|
||
|
|
|
||
|
|
$this->assertNull($fullArticle);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_thumbnail_from_og_image(): void
|
||
|
|
{
|
||
|
|
$html = '<html><head><meta property="og:image" content="https://example.com/image.jpg"/></head></html>';
|
||
|
|
|
||
|
|
$thumbnail = BelgaArticlePageParser::extractThumbnail($html);
|
||
|
|
|
||
|
|
$this->assertEquals('https://example.com/image.jpg', $thumbnail);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_thumbnail_from_img_tag(): void
|
||
|
|
{
|
||
|
|
$html = '<html><body><img src="https://example.com/article-image.png" alt="test"/></body></html>';
|
||
|
|
|
||
|
|
$thumbnail = BelgaArticlePageParser::extractThumbnail($html);
|
||
|
|
|
||
|
|
$this->assertEquals('https://example.com/article-image.png', $thumbnail);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_thumbnail_prefers_og_image(): void
|
||
|
|
{
|
||
|
|
$html = '
|
||
|
|
<html>
|
||
|
|
<head><meta property="og:image" content="https://example.com/og-image.jpg"/></head>
|
||
|
|
<body><img src="https://example.com/body-image.png" alt="test"/></body>
|
||
|
|
</html>
|
||
|
|
';
|
||
|
|
|
||
|
|
$thumbnail = BelgaArticlePageParser::extractThumbnail($html);
|
||
|
|
|
||
|
|
$this->assertEquals('https://example.com/og-image.jpg', $thumbnail);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_thumbnail_returns_null_when_not_found(): void
|
||
|
|
{
|
||
|
|
$html = '<html><body><div>No images here</div></body></html>';
|
||
|
|
|
||
|
|
$thumbnail = BelgaArticlePageParser::extractThumbnail($html);
|
||
|
|
|
||
|
|
$this->assertNull($thumbnail);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_data_returns_all_components(): void
|
||
|
|
{
|
||
|
|
$html = '
|
||
|
|
<html>
|
||
|
|
<head>
|
||
|
|
<meta property="og:title" content="Test Article"/>
|
||
|
|
<meta property="og:description" content="Test description"/>
|
||
|
|
<meta property="og:image" content="https://example.com/image.jpg"/>
|
||
|
|
</head>
|
||
|
|
<body>
|
||
|
|
<p class="styles_paragraph__TEST">Full article content here.</p>
|
||
|
|
</body>
|
||
|
|
</html>
|
||
|
|
';
|
||
|
|
|
||
|
|
$data = BelgaArticlePageParser::extractData($html);
|
||
|
|
|
||
|
|
$this->assertIsArray($data);
|
||
|
|
$this->assertArrayHasKey('title', $data);
|
||
|
|
$this->assertArrayHasKey('description', $data);
|
||
|
|
$this->assertArrayHasKey('full_article', $data);
|
||
|
|
$this->assertArrayHasKey('thumbnail', $data);
|
||
|
|
|
||
|
|
$this->assertEquals('Test Article', $data['title']);
|
||
|
|
$this->assertEquals('Test description', $data['description']);
|
||
|
|
$this->assertEquals('Full article content here.', $data['full_article']);
|
||
|
|
$this->assertEquals('https://example.com/image.jpg', $data['thumbnail']);
|
||
|
|
}
|
||
|
|
|
||
|
|
public function test_extract_data_handles_missing_components_gracefully(): void
|
||
|
|
{
|
||
|
|
$html = '<html><body><div>Minimal content</div></body></html>';
|
||
|
|
|
||
|
|
$data = BelgaArticlePageParser::extractData($html);
|
||
|
|
|
||
|
|
$this->assertIsArray($data);
|
||
|
|
$this->assertArrayHasKey('title', $data);
|
||
|
|
$this->assertArrayHasKey('description', $data);
|
||
|
|
$this->assertArrayHasKey('full_article', $data);
|
||
|
|
$this->assertArrayHasKey('thumbnail', $data);
|
||
|
|
|
||
|
|
$this->assertNull($data['title']);
|
||
|
|
$this->assertNull($data['description']);
|
||
|
|
$this->assertNull($data['full_article']);
|
||
|
|
$this->assertNull($data['thumbnail']);
|
||
|
|
}
|
||
|
|
|
||
|
|
/**
|
||
|
|
* Test based on actual Belga HTML structure from real article
|
||
|
|
*/
|
||
|
|
public function test_extract_full_article_with_realistic_belga_html(): void
|
||
|
|
{
|
||
|
|
$html = '
|
||
|
|
<html>
|
||
|
|
<body>
|
||
|
|
<div class="ContentRenderer_renderer__IBbst">
|
||
|
|
<section class="prezly-slate-document">
|
||
|
|
<p class="styles_paragraph__6o_o7"><strong>Around 110,000 people joined the Antwerp Pride Parade on Saturday afternoon, according to police.</strong></p>
|
||
|
|
<p class="styles_paragraph__6o_o7">The event passed without major incidents. Earlier in the day, far-right group Voorpost held a pre-approved protest.</p>
|
||
|
|
<p class="styles_paragraph__6o_o7">Police say they expect no problems with crowd dispersal, as departures will be staggered.</p>
|
||
|
|
</section>
|
||
|
|
</div>
|
||
|
|
</body>
|
||
|
|
</html>
|
||
|
|
';
|
||
|
|
|
||
|
|
$fullArticle = BelgaArticlePageParser::extractFullArticle($html);
|
||
|
|
|
||
|
|
$this->assertNotNull($fullArticle);
|
||
|
|
$this->assertStringContainsString('110,000 people joined', $fullArticle);
|
||
|
|
$this->assertStringContainsString('major incidents', $fullArticle);
|
||
|
|
$this->assertStringContainsString('crowd dispersal', $fullArticle);
|
||
|
|
|
||
|
|
// Should join paragraphs with double newlines
|
||
|
|
$this->assertStringContainsString("\n\n", $fullArticle);
|
||
|
|
|
||
|
|
// Should strip HTML tags
|
||
|
|
$this->assertStringNotContainsString('<strong>', $fullArticle);
|
||
|
|
$this->assertStringNotContainsString('</strong>', $fullArticle);
|
||
|
|
}
|
||
|
|
}
|