trek-rs 0.2.1

A web content extraction library that removes clutter from web pages
Documentation 
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

<!DOCTYPE html>
<html>
<head>
    <title>Trek WASM Demo</title>
    <style>
        body {
            font-family: Arial, sans-serif;
            margin: 20px;
            max-width: 1200px;
            margin: 0 auto;
            padding: 20px;
        }
        .container {
            display: grid;
            grid-template-columns: 1fr 1fr;
            gap: 20px;
        }
        textarea {
            width: 100%;
            height: 400px;
            font-family: monospace;
            font-size: 12px;
        }
        button {
            background: #007bff;
            color: white;
            border: none;
            padding: 10px 20px;
            cursor: pointer;
            margin-top: 10px;
        }
        button:hover {
            background: #0056b3;
        }
        .output {
            border: 1px solid #ccc;
            padding: 20px;
            min-height: 400px;
            background: #f8f9fa;
            overflow: auto;
        }
        pre {
            background: #e9ecef;
            padding: 10px;
            overflow: auto;
        }
    </style>
</head>
<body>
    <h1>Trek WASM Demo</h1>
    <p>This demonstrates the Trek content extraction library compiled to WebAssembly.</p>
    
    <div class="container">
        <div>
            <h2>Input HTML</h2>
            <textarea id="input" placeholder="Paste HTML here...">
<html>
<head>
    <title>Sample Article</title>
    <meta name="author" content="John Doe">
    <meta name="description" content="A sample article for testing">
</head>
<body>
    <nav>Navigation Menu</nav>
    <aside class="sidebar">
        <h3>Related Links</h3>
        <a href="/link1">Link 1</a>
        <a href="/link2">Link 2</a>
    </aside>
    <article>
        <h1>Sample Article Title</h1>
        <p>Published on January 1, 2024</p>
        <p>This is the first paragraph of the article with some interesting content.</p>
        <p>This is the second paragraph with even more content to demonstrate extraction.</p>
        <pre><code class="language-javascript">
// Example code block
function hello() {
    console.log("Hello, Trek!");
}
        </code></pre>
    </article>
    <footer>© 2024 Example Site</footer>
</body>
</html>
            </textarea>
            <button onclick="extractContent()">Extract Content</button>
        </div>
        
        <div>
            <h2>Extracted Content</h2>
            <div id="output" class="output">
                <p>Click "Extract Content" to see the results...</p>
            </div>
        </div>
    </div>
    
    <script type="module">
        // This is a placeholder - the actual WASM module would be loaded here
        window.extractContent = async function() {
            const input = document.getElementById('input').value;
            const output = document.getElementById('output');
            
            try {
                // Placeholder for WASM call
                output.innerHTML = `
                    <h3>Extracted Successfully!</h3>
                    <p><strong>Note:</strong> This is a demo placeholder. The actual WASM module would process the HTML.</p>
                    <h4>Metadata:</h4>
                    <pre>{
  "title": "Sample Article Title",
  "author": "John Doe",
  "description": "A sample article for testing",
  "wordCount": 42
}</pre>
                    <h4>Content:</h4>
                    <div style="border: 1px solid #dee2e6; padding: 15px; background: white;">
                        <h1>Sample Article Title</h1>
                        <p>Published on January 1, 2024</p>
                        <p>This is the first paragraph of the article with some interesting content.</p>
                        <p>This is the second paragraph with even more content to demonstrate extraction.</p>
                        <pre><code class="language-javascript">
// Example code block
function hello() {
    console.log("Hello, Trek!");
}
                        </code></pre>
                    </div>
                `;
            } catch (error) {
                output.innerHTML = `<p style="color: red;">Error: ${error.message}</p>`;
            }
        };
    </script>
</body>
</html>