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

"""Tests for Dublin Core metadata extraction"""

import meta_oxide


def test_dublin_core_title():
    """Test Dublin Core title extraction"""
    html = '<meta name="DC.title" content="My Document Title">'
    dc = meta_oxide.extract_dublin_core(html)
    assert dc["title"] == "My Document Title"


def test_dublin_core_creator():
    """Test Dublin Core creator extraction"""
    html = '<meta name="DC.creator" content="John Doe">'
    dc = meta_oxide.extract_dublin_core(html)
    assert dc["creator"] == "John Doe"


def test_dublin_core_subject():
    """Test Dublin Core subject extraction with multiple values"""
    html = '<meta name="DC.subject" content="rust, metadata, extraction">'
    dc = meta_oxide.extract_dublin_core(html)
    assert dc["subject"] == ["rust", "metadata", "extraction"]


def test_dublin_core_description():
    """Test Dublin Core description extraction"""
    html = '<meta name="DC.description" content="A comprehensive guide to metadata">'
    dc = meta_oxide.extract_dublin_core(html)
    assert dc["description"] == "A comprehensive guide to metadata"


def test_dublin_core_publisher():
    """Test Dublin Core publisher extraction"""
    html = '<meta name="DC.publisher" content="Example Press">'
    dc = meta_oxide.extract_dublin_core(html)
    assert dc["publisher"] == "Example Press"


def test_dublin_core_date():
    """Test Dublin Core date extraction"""
    html = '<meta name="DC.date" content="2024-01-15">'
    dc = meta_oxide.extract_dublin_core(html)
    assert dc["date"] == "2024-01-15"


def test_dublin_core_type():
    """Test Dublin Core type extraction"""
    html = '<meta name="DC.type" content="Text">'
    dc = meta_oxide.extract_dublin_core(html)
    assert dc["type"] == "Text"


def test_dublin_core_format():
    """Test Dublin Core format extraction"""
    html = '<meta name="DC.format" content="text/html">'
    dc = meta_oxide.extract_dublin_core(html)
    assert dc["format"] == "text/html"


def test_dublin_core_identifier():
    """Test Dublin Core identifier extraction"""
    html = '<meta name="DC.identifier" content="ISBN:123-456-789">'
    dc = meta_oxide.extract_dublin_core(html)
    assert dc["identifier"] == "ISBN:123-456-789"


def test_dublin_core_language():
    """Test Dublin Core language extraction"""
    html = '<meta name="DC.language" content="en-US">'
    dc = meta_oxide.extract_dublin_core(html)
    assert dc["language"] == "en-US"


def test_dublin_core_rights():
    """Test Dublin Core rights extraction"""
    html = '<meta name="DC.rights" content="Copyright 2024 Example Corp">'
    dc = meta_oxide.extract_dublin_core(html)
    assert dc["rights"] == "Copyright 2024 Example Corp"


def test_dublin_core_lowercase_prefix():
    """Test Dublin Core with lowercase prefix"""
    html = '<meta name="dc.title" content="Lowercase Prefix">'
    dc = meta_oxide.extract_dublin_core(html)
    assert dc["title"] == "Lowercase Prefix"


def test_dublin_core_dcterms_prefix():
    """Test Dublin Core with dcterms prefix"""
    html = '<meta name="dcterms.title" content="DCTerms Title">'
    dc = meta_oxide.extract_dublin_core(html)
    assert dc["title"] == "DCTerms Title"


def test_dublin_core_complete():
    """Test extraction of complete Dublin Core document"""
    html = """
        <html>
        <head>
            <meta name="DC.title" content="Complete Document">
            <meta name="DC.creator" content="Jane Smith">
            <meta name="DC.subject" content="technology, innovation">
            <meta name="DC.description" content="A complete example">
            <meta name="DC.publisher" content="Tech Publishers">
            <meta name="DC.date" content="2024-02-01">
            <meta name="DC.type" content="Article">
            <meta name="DC.format" content="text/html">
            <meta name="DC.identifier" content="DOI:10.1234/example">
            <meta name="DC.language" content="en">
            <meta name="DC.rights" content="CC-BY-4.0">
        </head>
        </html>
    """
    dc = meta_oxide.extract_dublin_core(html)
    assert dc["title"] == "Complete Document"
    assert dc["creator"] == "Jane Smith"
    assert dc["subject"] == ["technology", "innovation"]
    assert dc["description"] == "A complete example"
    assert dc["publisher"] == "Tech Publishers"
    assert dc["date"] == "2024-02-01"
    assert dc["type"] == "Article"
    assert dc["format"] == "text/html"
    assert dc["identifier"] == "DOI:10.1234/example"
    assert dc["language"] == "en"
    assert dc["rights"] == "CC-BY-4.0"


def test_dublin_core_empty():
    """Test empty Dublin Core extraction"""
    html = "<html><head><title>No Dublin Core</title></head></html>"
    dc = meta_oxide.extract_dublin_core(html)
    assert "title" not in dc
    assert "creator" not in dc
    assert "description" not in dc


def test_dublin_core_contributor_list():
    """Test Dublin Core contributor with multiple values"""
    html = '<meta name="DC.contributor" content="Alice, Bob, Charlie">'
    dc = meta_oxide.extract_dublin_core(html)
    assert dc["contributor"] == ["Alice", "Bob", "Charlie"]