meta_oxide 0.1.1

Universal metadata extraction library supporting 13 formats (HTML Meta, Open Graph, Twitter Cards, JSON-LD, Microdata, Microformats, RDFa, Dublin Core, Web App Manifest, oEmbed, rel-links, Images, SEO) with 7 language bindings
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
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
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597

"""
Python API integration tests for MetaOxide.

These tests verify that the public Python API functions work correctly
and return properly formatted data.

Run with: python -m pytest tests/test_python_api.py -v
"""

import os
import sys

# Add parent directory to path to import meta_oxide
sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))

try:
    import meta_oxide
except ImportError:
    print("ERROR: meta_oxide module not found. Build it first with: maturin develop")
    sys.exit(1)


class TestExtractMeta:
    """Test extract_meta() function."""

    def test_extract_meta_basic(self):
        """Test basic meta tag extraction."""
        html = """
        <html>
            <head>
                <title>Test Page</title>
                <meta name="description" content="Test description">
                <meta name="keywords" content="test, example">
            </head>
        </html>
        """
        result = meta_oxide.extract_meta(html)

        assert isinstance(result, dict)
        assert result.get("title") == "Test Page"
        assert result.get("description") == "Test description"
        assert result.get("keywords") == ["test", "example"]

    def test_extract_meta_with_base_url(self):
        """Test meta extraction with base URL for relative URLs."""
        html = """
        <html>
            <head>
                <link rel="canonical" href="/page">
            </head>
        </html>
        """
        result = meta_oxide.extract_meta(html, base_url="https://example.com")

        assert isinstance(result, dict)
        assert result.get("canonical") == "https://example.com/page"

    def test_extract_meta_empty_html(self):
        """Test with minimal HTML."""
        html = "<html><head></head></html>"
        result = meta_oxide.extract_meta(html)

        assert isinstance(result, dict)

    def test_extract_meta_verification_tags(self):
        """Test extraction of verification meta tags."""
        html = """
        <html>
            <head>
                <meta name="google-site-verification" content="abc123">
                <meta name="facebook-domain-verification" content="fb789">
            </head>
        </html>
        """
        result = meta_oxide.extract_meta(html)

        assert result.get("google_site_verification") == "abc123"
        assert result.get("facebook_domain_verification") == "fb789"


class TestExtractOpenGraph:
    """Test extract_opengraph() function."""

    def test_extract_opengraph_basic(self):
        """Test basic Open Graph extraction."""
        html = """
        <html>
            <head>
                <meta property="og:title" content="Article Title">
                <meta property="og:description" content="Article description">
                <meta property="og:url" content="https://example.com/article">
                <meta property="og:type" content="article">
            </head>
        </html>
        """
        result = meta_oxide.extract_opengraph(html)

        assert isinstance(result, dict)
        assert result.get("title") == "Article Title"
        assert result.get("description") == "Article description"
        assert result.get("url") == "https://example.com/article"
        assert result.get("type") == "article"

    def test_extract_opengraph_image(self):
        """Test Open Graph image extraction."""
        html = """
        <html>
            <head>
                <meta property="og:image" content="https://example.com/image.jpg">
                <meta property="og:image:width" content="1200">
                <meta property="og:image:height" content="630">
            </head>
        </html>
        """
        result = meta_oxide.extract_opengraph(html)

        assert isinstance(result, dict)
        assert result.get("image") is not None


class TestExtractTwitter:
    """Test extract_twitter() and extract_twitter_with_fallback() functions."""

    def test_extract_twitter_basic(self):
        """Test basic Twitter Card extraction."""
        html = """
        <html>
            <head>
                <meta name="twitter:card" content="summary_large_image">
                <meta name="twitter:title" content="Tweet Title">
                <meta name="twitter:description" content="Tweet description">
            </head>
        </html>
        """
        result = meta_oxide.extract_twitter(html)

        assert isinstance(result, dict)
        assert result.get("card") == "summary_large_image"
        assert result.get("title") == "Tweet Title"

    def test_extract_twitter_with_fallback_to_og(self):
        """Test Twitter extraction with fallback to Open Graph."""
        html = """
        <html>
            <head>
                <meta property="og:title" content="OG Title">
                <meta property="og:description" content="OG Description">
            </head>
        </html>
        """
        result = meta_oxide.extract_twitter_with_fallback(html)

        assert isinstance(result, dict)


class TestExtractJsonLD:
    """Test extract_jsonld() function."""

    def test_extract_jsonld_basic(self):
        """Test basic JSON-LD extraction."""
        html = """
        <html>
            <head>
                <script type="application/ld+json">
                {
                    "@context": "https://schema.org",
                    "@type": "Article",
                    "headline": "Article Title",
                    "description": "Article description"
                }
                </script>
            </head>
        </html>
        """
        result = meta_oxide.extract_jsonld(html)

        assert isinstance(result, list)
        assert len(result) > 0
        assert result[0].get("headline") == "Article Title"

    def test_extract_jsonld_multiple(self):
        """Test extraction of multiple JSON-LD objects."""
        html = """
        <html>
            <head>
                <script type="application/ld+json">
                {
                    "@context": "https://schema.org",
                    "@type": "Organization",
                    "name": "Example Corp"
                }
                </script>
                <script type="application/ld+json">
                {
                    "@context": "https://schema.org",
                    "@type": "Person",
                    "name": "John Doe"
                }
                </script>
            </head>
        </html>
        """
        result = meta_oxide.extract_jsonld(html)

        assert isinstance(result, list)
        assert len(result) >= 2

    def test_extract_jsonld_empty(self):
        """Test with no JSON-LD data."""
        html = "<html><head></head></html>"
        result = meta_oxide.extract_jsonld(html)

        assert isinstance(result, list)
        assert len(result) == 0


class TestExtractMicrodata:
    """Test extract_microdata() function."""

    def test_extract_microdata_basic(self):
        """Test basic microdata extraction."""
        html = """
        <html>
            <body>
                <div itemscope itemtype="https://schema.org/Person">
                    <span itemprop="name">John Doe</span>
                    <span itemprop="email">john@example.com</span>
                </div>
            </body>
        </html>
        """
        result = meta_oxide.extract_microdata(html)

        assert isinstance(result, list)
        assert len(result) > 0

    def test_extract_microdata_multiple(self):
        """Test extraction of multiple microdata items."""
        html = """
        <html>
            <body>
                <div itemscope itemtype="https://schema.org/Person">
                    <span itemprop="name">John Doe</span>
                </div>
                <div itemscope itemtype="https://schema.org/Person">
                    <span itemprop="name">Jane Doe</span>
                </div>
            </body>
        </html>
        """
        result = meta_oxide.extract_microdata(html)

        assert isinstance(result, list)
        assert len(result) >= 2


class TestExtractDublinCore:
    """Test extract_dublin_core() function."""

    def test_extract_dublin_core_basic(self):
        """Test basic Dublin Core extraction."""
        html = """
        <html>
            <head>
                <meta name="DC.title" content="Document Title">
                <meta name="DC.creator" content="Author Name">
                <meta name="DC.date" content="2024-01-15">
            </head>
        </html>
        """
        result = meta_oxide.extract_dublin_core(html)

        assert isinstance(result, dict)


class TestExtractOEmbed:
    """Test extract_oembed() function."""

    def test_extract_oembed_basic(self):
        """Test basic oEmbed endpoint discovery."""
        html = """
        <html>
            <head>
                <link rel="alternate" type="application/json+oembed"
                      href="https://example.com/oembed?url=https%3A%2F%2Fexample.com%2Fpage"
                      title="Example Page">
            </head>
        </html>
        """
        result = meta_oxide.extract_oembed(html)

        assert isinstance(result, dict)


class TestExtractRelLinks:
    """Test extract_rel_links() function."""

    def test_extract_rel_links_basic(self):
        """Test basic rel link extraction."""
        html = """
        <html>
            <head>
                <link rel="canonical" href="https://example.com/page">
                <link rel="alternate" href="/page-de" hreflang="de">
                <link rel="alternate" href="/feed.xml" type="application/rss+xml">
            </head>
        </html>
        """
        result = meta_oxide.extract_rel_links(html)

        assert isinstance(result, dict)
        assert "canonical" in result or len(result) >= 0


class TestExtractMicroformats:
    """Test individual microformat extraction functions."""

    def test_extract_hcard(self):
        """Test h-card extraction."""
        html = """
        <div class="h-card">
            <span class="p-name">Jane Doe</span>
            <a class="u-url" href="https://example.com">Website</a>
            <img class="u-photo" src="https://example.com/photo.jpg" alt="Photo">
        </div>
        """
        result = meta_oxide.extract_hcard(html)

        assert isinstance(result, list)
        assert len(result) > 0
        assert result[0].get("name") == "Jane Doe"

    def test_extract_hentry(self):
        """Test h-entry extraction."""
        html = """
        <article class="h-entry">
            <h1 class="p-name">Entry Title</h1>
            <p class="p-summary">Entry summary</p>
            <time class="dt-published" datetime="2024-01-15">Jan 15</time>
        </article>
        """
        result = meta_oxide.extract_hentry(html)

        assert isinstance(result, list)
        assert len(result) > 0

    def test_extract_hevent(self):
        """Test h-event extraction."""
        html = """
        <div class="h-event">
            <span class="p-name">Event Name</span>
            <time class="dt-start" datetime="2024-06-15T10:00:00">June 15</time>
            <time class="dt-end" datetime="2024-06-15T17:00:00">5pm</time>
        </div>
        """
        result = meta_oxide.extract_hevent(html)

        assert isinstance(result, list)
        assert len(result) > 0

    def test_extract_hreview(self):
        """Test h-review extraction."""
        html = """
        <div class="h-review">
            <span class="p-name">Product Review</span>
            <p class="p-summary">Great product</p>
            <span class="p-rating">5</span>
        </div>
        """
        result = meta_oxide.extract_hreview(html)

        assert isinstance(result, list)

    def test_extract_hrecipe(self):
        """Test h-recipe extraction."""
        html = """
        <div class="h-recipe">
            <span class="p-name">Chocolate Cake</span>
            <span class="p-yield">10 servings</span>
            <span class="dt-duration">PT30M</span>
        </div>
        """
        result = meta_oxide.extract_hrecipe(html)

        assert isinstance(result, list)

    def test_extract_hproduct(self):
        """Test h-product extraction."""
        html = """
        <div class="h-product">
            <span class="p-name">Product Name</span>
            <span class="p-price">$99.99</span>
            <img class="u-photo" src="/product.jpg" alt="Product">
        </div>
        """
        result = meta_oxide.extract_hproduct(html)

        assert isinstance(result, list)

    def test_extract_hfeed(self):
        """Test h-feed extraction."""
        html = """
        <div class="h-feed">
            <span class="p-name">My Blog</span>
            <article class="h-entry">
                <h1 class="p-name">Post 1</h1>
            </article>
        </div>
        """
        result = meta_oxide.extract_hfeed(html)

        assert isinstance(result, list)

    def test_extract_hadr(self):
        """Test h-adr extraction."""
        html = """
        <div class="h-adr">
            <span class="p-street-address">123 Main St</span>
            <span class="p-locality">Springfield</span>
            <span class="p-postal-code">12345</span>
        </div>
        """
        result = meta_oxide.extract_hadr(html)

        assert isinstance(result, list)

    def test_extract_hgeo(self):
        """Test h-geo extraction."""
        html = """
        <span class="h-geo">
            <span class="p-latitude">37.7749</span>
            <span class="p-longitude">-122.4194</span>
            <span class="p-altitude">52</span>
        </span>
        """
        result = meta_oxide.extract_hgeo(html)

        assert isinstance(result, list)


class TestExtractAll:
    """Test the main extract_all() function."""

    def test_extract_all_returns_dict(self):
        """Test that extract_all() returns a dictionary."""
        html = "<html><head><title>Test</title></head></html>"
        result = meta_oxide.extract_all(html)

        assert isinstance(result, dict)

    def test_extract_all_includes_meta(self):
        """Test that extract_all() includes meta tags."""
        html = """
        <html>
            <head>
                <title>Test Page</title>
                <meta name="description" content="Test">
            </head>
        </html>
        """
        result = meta_oxide.extract_all(html)

        assert "meta" in result
        assert isinstance(result["meta"], dict)

    def test_extract_all_includes_opengraph(self):
        """Test that extract_all() includes Open Graph."""
        html = """
        <html>
            <head>
                <meta property="og:title" content="OG Title">
            </head>
        </html>
        """
        result = meta_oxide.extract_all(html)

        assert "opengraph" in result

    def test_extract_all_includes_twitter(self):
        """Test that extract_all() includes Twitter Cards."""
        html = """
        <html>
            <head>
                <meta name="twitter:card" content="summary">
            </head>
        </html>
        """
        result = meta_oxide.extract_all(html)

        assert "twitter" in result

    def test_extract_all_includes_jsonld(self):
        """Test that extract_all() includes JSON-LD."""
        html = """
        <html>
            <head>
                <script type="application/ld+json">
                {"@type": "Article"}
                </script>
            </head>
        </html>
        """
        result = meta_oxide.extract_all(html)

        assert "jsonld" in result

    def test_extract_all_includes_microdata(self):
        """Test that extract_all() includes microdata."""
        html = """
        <html>
            <body>
                <div itemscope itemtype="https://schema.org/Person">
                    <span itemprop="name">John</span>
                </div>
            </body>
        </html>
        """
        result = meta_oxide.extract_all(html)

        assert "microdata" in result

    def test_extract_all_includes_microformats(self):
        """Test that extract_all() includes microformats."""
        html = """
        <div class="h-card">
            <span class="p-name">Jane</span>
        </div>
        """
        result = meta_oxide.extract_all(html)

        assert "microformats" in result

    def test_extract_all_with_base_url(self):
        """Test extract_all() with base URL."""
        html = """
        <html>
            <head>
                <link rel="canonical" href="/page">
            </head>
        </html>
        """
        result = meta_oxide.extract_all(html, base_url="https://example.com")

        assert isinstance(result, dict)

    def test_extract_all_comprehensive(self):
        """Test extract_all() with all formats present."""
        html = """
        <html>
            <head>
                <title>Comprehensive Test</title>
                <meta name="description" content="Test page">
                <meta property="og:title" content="OG Title">
                <meta name="twitter:card" content="summary">
                <script type="application/ld+json">
                {"@type": "Article", "headline": "Test"}
                </script>
                <link rel="canonical" href="https://example.com/page">
            </head>
            <body>
                <div class="h-card">
                    <span class="p-name">Test</span>
                </div>
                <div itemscope itemtype="https://schema.org/Person">
                    <span itemprop="name">John</span>
                </div>
            </body>
        </html>
        """
        result = meta_oxide.extract_all(html, base_url="https://example.com")

        assert isinstance(result, dict)
        assert "meta" in result
        assert "opengraph" in result
        assert "twitter" in result
        assert "jsonld" in result


if __name__ == "__main__":
    # Run a quick smoke test if pytest is not available
    print("Running Python API smoke tests...\n")

    # Test extract_meta
    html = "<html><head><title>Test</title></head></html>"
    meta = meta_oxide.extract_meta(html)
    print(f"✓ extract_meta() works: {type(meta)}")

    # Test extract_all
    result = meta_oxide.extract_all(html)
    print(f"✓ extract_all() works: {type(result)}, keys: {list(result.keys())}")

    # Test extract_hcard
    html_hcard = '<div class="h-card"><span class="p-name">Jane</span></div>'
    cards = meta_oxide.extract_hcard(html_hcard)
    print(f"✓ extract_hcard() works: {len(cards)} cards found")

    print("\nAll smoke tests passed!")