rust-pickaxe 0.5.5

HTML data extraction library
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

class HtmlDocument:
    """
    A parsed HTML document.
    """
    @classmethod
    def from_str(cls, raw: str) -> HtmlDocument:
        """
        Parse an HTML document from a string.
        """
        ...

    @property
    def raw(self) -> str:
        """
        The raw HTML content of the document.
        """
        ...

    @property
    def root(self) -> HtmlNode:
        """
        Get the root node of the document.
        """
        ...

    @property
    def children(self) -> list[HtmlNode]:
        """
        Get the immediate children of the document.
        """
        ...

    def find_all(self, selector: str) -> list[HtmlNode]:
        """
        Find all nodes matching the given CSS selector.
        """
        ...

    def find_all_xpath(self, xpath: str) -> list[HtmlNode | str | None]:
        """
        Find all nodes matching the given XPath selector.
        """
        ...

    def find(self, selector: str) -> HtmlNode | None:
        """
        Find the first node matching the given CSS selector.
        """
        ...

    def find_xpath(self, xpath: str) -> HtmlNode | str | None:
        """
        Find the first node matching the given XPath selector.
        """
        ...

    def find_nth(self, selector: str, n: int) -> HtmlNode | None:
        """
        Find the nth node matching the given CSS selector.
        """
        ...

    def find_nth_xpath(self, xpath: str, n: int) -> HtmlNode | str | None:
        """
        Find the nth node matching the given XPath selector.
        """
        ...


class HtmlNode:
    @property
    def text(self) -> str:
        """
        The visible text of this node.
        """
        ...

    @property
    def inner_text(self) -> str:
        """
        The inner visible text of the node and its children.
        """
        ...

    @property
    def inner_html(self) -> str:
        """
        The inner HTML of the node and its children.
        """
        ...

    @property
    def outer_html(self) -> str:
        """
        The outer HTML of the node.
        """
        ...

    @property
    def tag_name(self) -> str:
        """
        The tag name of the node.
        """
        ...

    @property
    def attributes(self) -> dict[str, str | None]:
        """
        All attributes of the node.
        """
        ...

    @property
    def children(self) -> list[HtmlNode]:
        """
        The immediate children of the node.
        """
        ...

    def find_all(self, selector: str) -> list[HtmlNode]:
        """
        Find all nodes matching the given CSS selector.
        """
        ...

    def find_all_xpath(self, xpath: str) -> list[HtmlNode | str | None]:
        """
        Find all nodes matching the given XPath selector.
        """
        ...

    def find(self, selector: str) -> HtmlNode | None:
        """
        Find the first node matching the given CSS selector.
        """
        ...

    def find_xpath(self, xpath: str) -> HtmlNode | str | None:
        """
        Find the first node matching the given XPath selector.
        """
        ...

    def find_nth(self, selector: str, n: int) -> HtmlNode | None:
        """
        Find the nth node matching the given CSS selector.
        """
        ...

    def find_nth_xpath(self, xpath: str, n: int) -> HtmlNode | str | None:
        """
        Find the nth node matching the given XPath selector.
        """
        ...

    def get_attribute(self, name: str) -> str | None:
        """
        Get the value of an attribute.
        """
        ...


def html_to_markdown(html: str, skip_tags: list[str] = ["script", "style"]) -> str:
    """
    Convert an HTML string to markdown.
    """
    ...