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
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

use std::collections::HashMap;
use pyo3::{
    prelude::*,
    exceptions::{PyValueError, PyRuntimeError},
    types::PyType,
};

use crate::document::{HtmlDocument, HtmlNode, XPathResult};
use crate::markdown::{html_to_markdown_with_converter, HtmlToMarkdown};
use crate::errors::{Result, PackageError};


impl From<PackageError> for PyErr {
    fn from(error: PackageError) -> Self {
        match error {
            PackageError::HTMLParseError(e) => PyValueError::new_err(e.to_string()),
            PackageError::SelectorParseError(e) => PyValueError::new_err(e.to_string()),
            PackageError::UnknownError(e) => PyRuntimeError::new_err(e.to_string()),
        }
    }
}


/// An XPath result object.
#[derive(IntoPyObject)]
pub enum PyXPathResult {
    /// The HtmlNode itself
    Node(PyHtmlNode),
    /// A string
    String(String),
}

impl From<XPathResult> for PyXPathResult {
    fn from(result: XPathResult) -> Self {
        match result {
            XPathResult::Node(node) => PyXPathResult::Node(PyHtmlNode { inner: node }),
            XPathResult::String(string) => PyXPathResult::String(string),
        }
    }
}

/// An HTML document object.
/// 
/// This object is used to parse and manipulate HTML documents.
/// 
/// # Examples
/// 
/// ```python
/// from pickaxe import HtmlDocument
/// 
/// doc = HtmlDocument.from_str("<html><body><h1>Hello, world!</h1></body></html>")
/// h1 = doc.find("h1")
/// print(h1.inner_text)
/// ```
#[pyclass(name = "HtmlDocument")]
#[derive(Clone)]
pub struct PyHtmlDocument {
    inner: HtmlDocument,
}

#[pymethods]
impl PyHtmlDocument {
    fn __repr__(&self) -> String {
        format!("{:?}", self.inner)
    }

    /// Create an `HtmlDocument` from a string.
    /// 
    /// * `raw` - The raw HTML string.
    #[classmethod]
    #[allow(unused_variables)]
    pub fn from_str(cls: &Bound<'_, PyType>, py: Python<'_>, raw: String) -> Self {
        py.allow_threads(|| Self {
            inner: HtmlDocument::from_str(raw),
        })
    }

    #[getter]
    /// The raw HTML string of the document.
    pub fn raw(&self) -> &str {
        self.inner.raw()
    }
    
    #[getter]
    /// Get the immediate children of the root node.
    pub fn children(&self) -> Vec<PyHtmlNode> {
        self.inner
            .children()
            .into_iter()
            .map(|node| PyHtmlNode { inner: node })
            .collect()
    }

    #[getter]
    /// Get the root node of the document.
    pub fn root(&self) -> PyHtmlNode {
        PyHtmlNode { inner: self.inner.root() }
    }

    /// Query the document for matching elements using a CSS selector.
    /// 
    /// * `selector` - The CSS selector to use.
    pub fn find_all(&self, selector: &str) -> Result<Vec<PyHtmlNode>> {
        Ok(
            self.inner
                .find_all(selector)?
                .into_iter()
                .map(|node| PyHtmlNode { inner: node })
                .collect()
        )
    }

    /// Query the document for matching elements using an XPath expression.
    /// 
    /// * `xpath` - The XPath expression to use.
    pub fn find_all_xpath(&self, xpath: &str) -> Result<Vec<PyXPathResult>> {
        Ok(
            self.inner
                .find_all_xpath(xpath)?
                .into_iter()
                .map(|result| result.into())
                .collect()
        )
    }

    /// Query the document for the first matching element using a CSS selector.
    /// 
    /// * `selector` - The CSS selector to use.
    pub fn find(&self, selector: &str) -> Result<Option<PyHtmlNode>> {
        Ok(
            self.inner
                .find(selector)?
                .map(|node| PyHtmlNode { inner: node })
        )
    }

    /// Query the document for the first matching element using an XPath expression.
    ///
    /// * `xpath` - The XPath expression to use.
    pub fn find_xpath(&self, xpath: &str) -> Result<Option<PyXPathResult>> {
        Ok(
            self.inner
                .find_xpath(xpath)?
                .map(|result| result.into())
        )
    }

    /// Query the `n`th element using a CSS selector.
    /// 
    /// * `selector` - The CSS selector to use.
    /// * `n` - The index of the element to query.
    pub fn find_nth(&self, selector: &str, n: usize) -> Result<Option<PyHtmlNode>> {
        Ok(
            self.inner
                .find_nth(selector, n)?
                .map(|node| PyHtmlNode { inner: node })
        )
    }

    /// Query the `n`th element using an XPath expression.
    /// 
    /// * `xpath` - The XPath expression to use.
    /// * `n` - The index of the element to query.
    pub fn find_nth_xpath(&self, xpath: &str, n: usize) -> Result<Option<PyXPathResult>> {
        Ok(
            self.inner
                .find_nth_xpath(xpath, n)?
                .map(|result| result.into())
        )
    }
}


/// An HTML node object.
/// 
/// This object is used to represent an HTML element in a document.
/// 
/// # Examples
/// 
/// ```python
/// from pickaxe import HtmlDocument
/// 
/// doc = HtmlDocument.from_str("<html><body><h1>Hello, world!</h1></body></html>")
/// h1 = doc.find("h1")
/// print(h1.inner_text)
/// ```
#[pyclass(name = "HtmlNode")]
#[derive(Clone)]
pub struct PyHtmlNode {
    inner: HtmlNode,
}

#[pymethods]
impl PyHtmlNode {
    fn __repr__(&self) -> String {
        format!("{:?}", self.inner)
    }

    /// Get the text of this node.
    #[getter]
    fn text(&self) -> String {
        self.inner.text()
    }

    /// Get the inner text of the node and its children.
    #[getter]
    fn inner_text(&self) -> String {
        self.inner.inner_text()
    }

    /// Get the inner HTML of the node and its children.
    #[getter]
    fn inner_html(&self) -> String {
        self.inner.inner_html()
    }

    /// Get the outer HTML of the node.
    #[getter]
    fn outer_html(&self) -> String {
        self.inner.outer_html()
    }

    /// Get the tag name of the node.
    #[getter]
    fn tag_name(&self) -> String {
        self.inner
            .tag_name()
            .to_string()
    }

    /// Get the attributes of the node.
    #[getter]
    fn attributes(&self) -> HashMap<&str, Option<&str>> {
        self.inner.attributes()
    }

    /// Get the children of the node.
    #[getter]
    fn children(&self) -> Vec<PyHtmlNode> {
        self.inner
            .children()
            .into_iter()
            .map(|node| PyHtmlNode { inner: node })
            .collect()
    }

    /// Query the node for matching elements using a CSS selector.
    /// 
    /// * `selector` - The CSS selector to use.
    pub fn find_all(&self, selector: &str) -> Result<Vec<PyHtmlNode>> {
        Ok(
            self.inner
                .find_all(selector)?
                .into_iter()
                .map(|node| PyHtmlNode { inner: node })
                .collect()
        )
    }

    /// Query the node for matching elements using an XPath expression.
    /// 
    /// * `xpath` - The XPath expression to use.
    pub fn find_all_xpath(&self, xpath: &str) -> Result<Vec<PyXPathResult>> {
        Ok(
            self.inner
                .find_all_xpath(xpath)?
                .into_iter()
                .map(|result| result.into())
                .collect()
        )
    }

    /// Query the node for the first matching element using a CSS selector.
    /// 
    /// * `selector` - The CSS selector to use.
    pub fn find(&self, selector: &str) -> Result<Option<PyHtmlNode>> {
        Ok(
            self.inner
                .find(selector)?
                .map(|node| PyHtmlNode { inner: node })
        )
    }

    /// Query the node for the first matching element using an XPath expression.
    /// 
    /// * `xpath` - The XPath expression to use.
    pub fn find_xpath(&self, xpath: &str) -> Result<Option<PyXPathResult>> {
        Ok(
            self.inner
                .find_xpath(xpath)?
                .map(|result| result.into())
        )
    }

    /// Query the `n`th element using a CSS selector.
    /// 
    /// * `selector` - The CSS selector to use.
    /// * `n` - The index of the element to query.
    pub fn find_nth(&self, selector: &str, n: usize) -> Result<Option<PyHtmlNode>> {
        Ok(
            self.inner
                .find_nth(selector, n)?
                .map(|node| PyHtmlNode { inner: node })
        )
    }

    /// Query the `n`th element using an XPath expression.
    /// 
    /// * `xpath` - The XPath expression to use.
    /// * `n` - The index of the element to query.
    pub fn find_nth_xpath(&self, xpath: &str, n: usize) -> Result<Option<PyXPathResult>> {
        Ok(
            self.inner
                .find_nth_xpath(xpath, n)?
                .map(|result| result.into())
        )
    }

    /// Get the value of an attribute.
    fn get_attribute(&self, name: &str) -> Option<&str> {
        self.inner.get_attribute(name)
    }
}


/// Convert an HTML string to markdown.
/// 
/// * `html` - The HTML string to convert.
/// * `skip_tags` - The tags to skip when converting to markdown.
#[pyfunction]
#[pyo3(signature = (html, skip_tags = vec!["script".to_string(), "style".to_string()]))]
fn html_to_markdown(html: String, skip_tags: Vec<String>) -> PyResult<String> {
    Ok(
        html_to_markdown_with_converter(
            html,
            HtmlToMarkdown::builder()
                .skip_tags(skip_tags.iter().map(|v| v.as_str()).collect())
                .build()
        )
        .map_err(|e| PyValueError::new_err(e.to_string()))?
    )
}


#[pymodule]
#[pyo3(name = "_pickaxe")]
fn pickaxe(py: Python<'_>, m: &Bound<'_, PyModule>) -> PyResult<()> {
    m.add_class::<PyHtmlDocument>()?;
    m.add_class::<PyHtmlNode>()?;
    m.add_function(wrap_pyfunction!(html_to_markdown, py)?)?;
    m.add("__version__", env!("CARGO_PKG_VERSION"))?;
    Ok(())
}