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
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
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670

use std::{
    fmt::{Debug, Formatter},
    sync::Arc,
    collections::HashMap,
};
use ego_tree::{NodeId, NodeRef};
use scraper::{ElementRef, Html, Node, Selector};

use crate::xpath::{parse_xpath, NodeAccessor};
use crate::errors::{Result, PackageError};


/// The result of an XPath query.
#[derive(Debug)]
pub enum XPathResult {
    Node(HtmlNode),
    String(String),
}

impl XPathResult {
    /// Get the result as a string.
    pub fn as_string(&self) -> Option<&str> {
        match self {
            XPathResult::String(s) => Some(s),
            _ => None,
        }
    }

    /// Get the result as a node.
    pub fn as_node(&self) -> Option<&HtmlNode> {
        match self {
            XPathResult::Node(node) => Some(node),
            _ => None,
        }
    }

    /// Convert the result into a string.
    pub fn into_string(self) -> Option<String> {
        match self {
            XPathResult::String(s) => Some(s),
            _ => None,
        }
    }

    /// Convert the result into a node.
    pub fn into_node(self) -> Option<HtmlNode> {
        match self {
            XPathResult::Node(node) => Some(node),
            _ => None,
        }
    }
}

/// An HTML document that has been parsed into a virtual DOM.
#[derive(Clone)]
pub struct HtmlDocument {
    raw: String,
    dom: Arc<Html>,
    is_fragment: bool,
}

// NOTE: This is safe because `HtmlDocument` is immutable, so no UB can occur. Any modifications
// to the DOM must be wrapped in some kind of synchronization primitive if this is ever
// changed.
// Don't try this at home kids.
unsafe impl Send for HtmlDocument {}
unsafe impl Sync for HtmlDocument {}

impl HtmlDocument {
    /// Create a new `HtmlDocument` from a string of HTML and a [`Html`] DOM.
    /// 
    /// * `raw` - The raw HTML string.
    /// * `dom` - The parsed HTML DOM.
    pub fn new(raw: String, dom: Html, is_fragment: bool) -> Self {
        Self {
            raw,
            dom: Arc::new(dom),
            is_fragment,
        }
    }

    /// Parse an HTML document from a string.
    /// 
    /// * `html` - The HTML string to parse.
    pub fn from_str(html: String) -> Self {
        let is_fragment = !html.contains("html");
        let dom = if is_fragment {
            Html::parse_fragment(&html)
        } else {
            Html::parse_document(&html)
        };

        Self::new(html, dom, is_fragment)
    }

    /// The raw HTML string that was parsed.
    pub fn raw(&self) -> &str {
        &self.raw
    }

    /// Get the root node of the document.
    pub fn root(&self) -> HtmlNode {
        HtmlNode::new(
            self.dom.clone(),
            match self.is_fragment {
                false => self.dom
                            .root_element()
                            .id(),
                true => self.dom
                            .root_element()
                            .children()
                            .next()
                            .expect("no root element")
                            .id(),
            }
        )
    }

    /// Query the document for matching elements using a CSS selector..
    ///
    /// * `selector` - The CSS selector to query for.
    pub fn find_all(&self, selector: &str) -> Result<Vec<HtmlNode>> {
        self.root()
            .find_all(selector)
    }

    /// Query the document for matching elements using an XPath expression.
    /// 
    /// * `xpath` - The XPath expression to query for.
    pub fn find_all_xpath(&self, xpath: &str) -> Result<Vec<XPathResult>> {
        self.root()
            .find_all_xpath(xpath)
    }

    /// Query the document for the first matching element using a CSS selector.
    /// 
    /// * `selector` - The CSS selector to query for.
    pub fn find(&self, selector: &str) -> Result<Option<HtmlNode>> {
        self.root()
            .find(selector)
    }

    /// Query the document for the first matching element using an XPath expression.
    /// 
    /// * `xpath` - The XPath expression to query for.
    pub fn find_xpath(&self, xpath: &str) -> Result<Option<XPathResult>> {
        self.root()
            .find_xpath(xpath)
    }

    /// Query the document for the nth matching element using a CSS selector.
    /// 
    /// * `selector` - The CSS selector to query for.
    /// * `n` - The index of the element to get.
    pub fn find_nth(&self, selector: &str, n: usize) -> Result<Option<HtmlNode>> {
        self.root()
            .find_nth(selector, n)
    }

    /// Query the document for the nth matching element using an XPath expression.
    /// 
    /// * `xpath` - The XPath expression to query for.
    /// * `n` - The index of the element to get.
    pub fn find_nth_xpath(&self, xpath: &str, n: usize) -> Result<Option<XPathResult>> {
        self.root()
            .find_nth_xpath(xpath, n)
    }

    /// Get the children of the document. This is the same as getting the children
    /// of the root node.
    pub fn children(&self) -> Vec<HtmlNode> {
        self.root()
            .children()
    }
}

impl Debug for HtmlDocument {
    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
        write!(f, "<HtmlDocument is_fragment={:?}>", self.is_fragment)
    }
}

/// An HTML element in a document.
#[derive(Clone)]
pub struct HtmlNode {
    dom: Arc<Html>,
    node: NodeId,
}

// NOTE: This is safe because `HtmlNode` is immutable, so no UB can occur. Any modifications
// to the DOM must be wrapped in some kind of synchronization primitive if this is ever
// changed.
// Don't try this at home kids.
unsafe impl Send for HtmlNode {}
unsafe impl Sync for HtmlNode {}

impl HtmlNode {
    /// Create a new [`HtmlNode`] from a [`Html`] DOM and a [`NodeId`].
    /// 
    /// * `dom` - The parsed HTML DOM.
    /// * `node` - The HTML node.
    pub fn new(dom: Arc<Html>, node: NodeId) -> Self {
        Self { dom, node }
    }

    fn node(&self) -> Option<NodeRef<'_, Node>> {
        self.dom
            .tree
            .get(self.node)
    }

    fn element(&self) -> Option<ElementRef<'_>> {
        ElementRef::wrap(self.node()?)
    }

    /// Get the tag name of the node.
    pub fn tag_name(&self) -> &str {
        self.element()
            .expect("element not found")
            .value()
            .name()
    }

    /// Find all elements matching a CSS selector.
    /// 
    /// * `selector` - The CSS selector to query for.
    pub fn find_all(&self, selector: &str) -> Result<Vec<HtmlNode>> {
        Ok(
            self.element()
                .expect("element not found")
                .select(
                    &Selector::parse(selector)
                        .map_err(|e| PackageError::SelectorParseError(e.to_string()))?
                )
                .map(|element| HtmlNode::new(self.dom.clone(), element.id()))
                .collect()
        )
    }

    /// Find all elements matching an XPath expression.
    /// 
    /// * `xpath` - The XPath expression to query for.
    pub fn find_all_xpath(&self, xpath: &str) -> Result<Vec<XPathResult>> {
        fn resolve_accessor(node: &HtmlNode, accessor: &NodeAccessor) -> Option<XPathResult> {
            match accessor {
                NodeAccessor::Text { recursive } => {
                    Some(XPathResult::String(if *recursive {
                        node.inner_text()
                    } else {
                        node.text()
                    }))
                },
                NodeAccessor::Attribute(name) => {
                    Some(XPathResult::String(node
                        .get_attribute(name.as_str())?
                        .to_string()
                    ))
                },
                _ => Some(XPathResult::Node(node.clone())),
            }
        }

        match parse_xpath(xpath) {
            Some((selector, accessor)) => {
                match selector.as_str() {
                    "" => Ok(
                        resolve_accessor(self, &accessor)
                            .into_iter()
                            .collect()
                    ),
                    _ => Ok(
                        self.find_all(&selector)?
                            .into_iter()
                            .filter_map(|node| resolve_accessor(&node, &accessor))
                            .collect()
                    ),
                }
            },
            None => Ok(Vec::new()),
        }
    }

    /// Find the first element matching a CSS selector.
    /// 
    /// * `selector` - The CSS selector to query for.
    pub fn find(&self, selector: &str) -> Result<Option<HtmlNode>> {
        Ok(
            self.find_all(selector)?
                .into_iter()
                .next()
        )
    }

    /// Find the first element matching an XPath expression.
    /// 
    /// * `xpath` - The XPath expression to query for.
    pub fn find_xpath(&self, xpath: &str) -> Result<Option<XPathResult>> {
        Ok(
            self.find_all_xpath(xpath)?
                .into_iter()
                .next()
        )
    }

    /// Find the nth element matching a CSS selector.
    ///
    /// * `selector` - The CSS selector to query for.
    /// * `n` - The index of the element to get.
    pub fn find_nth(&self, selector: &str, n: usize) -> Result<Option<HtmlNode>> {
        Ok(
            self.find_all(selector)?
                .into_iter()
                .nth(n)
        )
    }

    /// Find the nth element matching an XPath expression.
    /// 
    /// * `xpath` - The XPath expression to query for.
    /// * `n` - The index of the element to get.
    pub fn find_nth_xpath(&self, xpath: &str, n: usize) -> Result<Option<XPathResult>> {
        Ok(
            self.find_all_xpath(xpath)?
                .into_iter()
                .nth(n)
        )
    }

    /// Get the attributes of the node.
    pub fn attributes(&self) -> HashMap<&str, Option<&str>> {
        self.element()
            .expect("element not found")
            .value()
            .attrs()
            .map(|(k, v)| (k, Some(v)))
            .collect()
    }

    /// Get the attribute of the node with the specified name.
    ///
    /// * `name` - The name of the attribute to get.
    pub fn get_attribute(&self, name: &str) -> Option<&str> {
        self.element()
            .expect("element not found")
            .value()
            .attr(name)
    }

    /// Get the text content of the node.
    pub fn text(&self) -> String {
        self.element()
            .expect("element not found")
            .text()
            .next()
            .unwrap_or("")
            .to_string()
    }

    /// Get the inner text of the node.
    pub fn inner_text(&self) -> String {
        self.element()
            .expect("element not found")
            .text()
            .collect::<Vec<_>>()
            .join("")
    }

    /// Get the inner HTML of the node.
    pub fn inner_html(&self) -> String {
        self.element()
            .expect("element not found")
            .inner_html()
    }

    /// Get the outer HTML of the node.
    pub fn outer_html(&self) -> String {
        self.element()
            .expect("element not found")
            .html()
    }

    /// Get the children of the node.
    pub fn children(&self) -> Vec<HtmlNode> {
        self.element()
            .expect("element not found")
            .children()
            .filter_map(|child| child
                .value()
                .is_element()
                .then(|| HtmlNode::new(self.dom.clone(), child.id()))
            )
            .collect()
    }
}

impl Debug for HtmlNode {
    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
        write!(f, "<{}", self.tag_name())?;

        for (key, value) in self.attributes() {
            if let Some(val) = value {
                write!(f, " {}=\"{}\"", key, val)?;
            }
        }

        write!(f, ">")
    }
}


#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn test_html_document_from_str() {
        let html = "<html><head></head><body><h1>Hello, world!</h1></body></html>";
        let doc = HtmlDocument::from_str(html.to_string());

        assert_eq!(doc.raw, html);
        assert_eq!(doc.root().tag_name(), "html");
    }

    #[test]
    fn test_html_document_fragment_from_str() {
        let html = "<h1>Hello, world!</h1>";
        let doc = HtmlDocument::from_str(html.to_string());

        assert_eq!(doc.root().tag_name(), "h1");
        assert_eq!(doc.root().children().len(), 0);
        assert_eq!(doc.root().inner_text(), "Hello, world!".to_string());
    }

    #[test]
    fn test_html_document_query_selector() {
        let html = r#"<html><head></head><body><h1 id="test">Hello, world!</h1><h1>Not hello world</h1></body></html>"#;
        let doc = HtmlDocument::from_str(html.to_string());

        let h1 = doc.find("h1#test").unwrap().unwrap();
        assert_eq!(h1.inner_text(), "Hello, world!".to_string());
    }

    #[test]
    fn test_html_node_text() {
        let html = "<html><head></head><body><h1>Hello, <span>world!</span></h1></body></html>";
        let doc = HtmlDocument::from_str(html.to_string());

        let h1 = doc.find("h1").unwrap().unwrap();
        assert_eq!(h1.text(), "Hello, ".to_string());
    }

    #[test]
    fn test_html_node_inner_text() {
        let html = "<html><head></head><body><h1>Hello, <span>world!</span></h1></body></html>";
        let doc = HtmlDocument::from_str(html.to_string());

        let root = doc.root();
        assert_eq!(root.inner_text(), "Hello, world!".to_string());
    }

    #[test]
    fn test_html_node_inner_html() {
        let html = "<html><head></head><body><h1>Hello,<span>world!</span></h1></body></html>";
        let doc = HtmlDocument::from_str(html.to_string());

        let h1 = doc.find("h1").unwrap().unwrap();
        assert_eq!(h1.inner_html(), "Hello,<span>world!</span>".to_string());
    }

    #[test]
    fn test_html_node_outer_html() {
        let html = "<html><head></head><body><h1>Hello, world!</h1></body></html>";
        let doc = HtmlDocument::from_str(html.to_string());

        let h1 = doc.find("h1").unwrap().unwrap();
        assert_eq!(h1.outer_html(), "<h1>Hello, world!</h1>".to_string());
    }

    #[test]
    fn test_html_node_get_attribute() {
        let html = r#"<html><head></head><body><h1 id="title">Hello, world!</h1></body></html>"#;
        let doc = HtmlDocument::from_str(html.to_string());

        let h1 = doc.find("h1").unwrap().unwrap();
        assert_eq!(h1.get_attribute("id"), Some("title"));
    }

    #[test]
    fn test_html_node_children() {
        let html = "<html><head></head><body><h1>Hello, world!</h1><p>Paragraph</p></body></html>";
        let doc = HtmlDocument::from_str(html.to_string());

        let body = doc.find("body").unwrap().unwrap();
        let children = body.children();

        assert_eq!(children.len(), 2);
        assert_eq!(children[0].inner_text(), "Hello, world!".to_string());
        assert_eq!(children[1].inner_text(), "Paragraph".to_string());
    }

    #[test]
    fn test_html_document_find_xpath() {
        let html = r#"<html><head></head><body><h1 id="title">Hello, world!</h1></body></html>"#;
        let doc = HtmlDocument::from_str(html.to_string());

        let h1 = doc.find_xpath("//h1[@id='title']")
            .unwrap()
            .unwrap()
            .into_node()
            .unwrap();
        assert_eq!(h1.inner_text(), "Hello, world!".to_string());
    }

    #[test]
    fn test_html_document_find_xpath_attribute() {
        let html = r#"<html><head></head><body><h1 id="title">Hello, world!</h1></body></html>"#;
        let doc = HtmlDocument::from_str(html.to_string());

        let h1 = doc.find_xpath("//h1/@id")
            .unwrap()
            .unwrap()
            .into_string()
            .unwrap();
        assert_eq!(h1, "title".to_string());
    }

    #[test]
    fn test_html_document_find_xpath_text() {
        let html = r#"<html><head></head><body><h1 id="title">Hello, <span>world!</span></h1></body></html>"#;
        let doc = HtmlDocument::from_str(html.to_string());

        let h1 = doc.find_xpath("//h1/text()")
            .unwrap()
            .unwrap()
            .into_string()
            .unwrap();
        assert_eq!(h1, "Hello, ".to_string());
    }

    #[test]
    fn test_html_document_find_xpath_inner_text() {
        let html = r#"<html><head></head><body><h1 id="title">Hello, <span>world!</span></h1></body></html>"#;
        let doc = HtmlDocument::from_str(html.to_string());

        let h1 = doc.find_xpath("//h1//text()")
            .unwrap()
            .unwrap()
            .into_string()
            .unwrap();
        assert_eq!(h1, "Hello, world!".to_string());
    }

    #[test]
    fn test_html_document_find_xpath_bad() {
        let html = r#"<html><head></head><body><h1 id="title">Hello, world!</h1></body></html>"#;
        let doc = HtmlDocument::from_str(html.to_string());

        let h1 = doc.find_xpath("//h1[@id='title']/@src").unwrap();
        assert!(h1.is_none());
    }

    #[test]
    fn test_html_document_find_nth() {
        let html = "<html><head></head><body><h1>Hello, world!</h1><h1>Not hello world</h1></body></html>";
        let doc = HtmlDocument::from_str(html.to_string());

        let h1 = doc.find_nth("h1", 1).unwrap().unwrap();
        assert_eq!(h1.inner_text(), "Not hello world".to_string());
    }

    #[test]
    fn test_html_document_find_nth_selector() {
        let html = "<html><head></head><body><h1>Hello, world!</h1><h1>Not hello world</h1></body></html>";
        let doc = HtmlDocument::from_str(html.to_string());

        let h1 = doc.find("h1:nth-of-type(2)").unwrap().unwrap();
        assert_eq!(h1.inner_text(), "Not hello world".to_string());
    }

    #[test]
    fn test_html_document_find_xpath_nth() {
        let html = r#"<html><head></head><body><h1>Hello, world!</h1><h1>Not hello world</h1></body></html>"#;
        let doc = HtmlDocument::from_str(html.to_string());

        let h1 = doc.find_xpath("//h1[2]")
            .unwrap()
            .unwrap()
            .into_node()
            .unwrap();
        assert_eq!(h1.inner_text(), "Not hello world".to_string());
    }

    #[test]
    fn test_html_node_find_all() {
        let html = "<html><head></head><body><h1>Hello, world!</h1><h1>Not hello world</h1></body></html>";
        let doc = HtmlDocument::from_str(html.to_string());

        let body = doc.find("body").unwrap().unwrap();
        let h1s = body.find_all("h1").unwrap();

        assert_eq!(h1s.len(), 2);
        assert_eq!(h1s[0].inner_text(), "Hello, world!".to_string());
        assert_eq!(h1s[1].inner_text(), "Not hello world".to_string());
    }

    #[test]
    fn test_html_node_find_all_xpath() {
        let html = r#"<html><head></head><body><h1>Hello, world!</h1><h1>Not hello world</h1></body></html>"#;
        let doc = HtmlDocument::from_str(html.to_string());

        let body = doc.find("body").unwrap().unwrap();
        let h1s = body.find_all_xpath("//h1").unwrap();

        assert_eq!(h1s.len(), 2);
        assert_eq!(h1s[0].as_node().unwrap().inner_text(), "Hello, world!".to_string());
        assert_eq!(h1s[1].as_node().unwrap().inner_text(), "Not hello world".to_string());
    }

    #[test]
    fn test_html_node_find_nth() {
        let html = "<html><head></head><body><h1>Hello, world!</h1><h1>Not hello world</h1></body></html>";
        let doc = HtmlDocument::from_str(html.to_string());

        let body = doc.find("body").unwrap().unwrap();
        let h1 = body.find_nth("h1", 1).unwrap().unwrap();

        assert_eq!(h1.inner_text(), "Not hello world".to_string());
    }

    #[test]
    fn test_html_node_find_nth_xpath() {
        let html = r#"<html><head></head><body><h1>Hello, world!</h1><h1>Not hello world</h1></body></html>"#;
        let doc = HtmlDocument::from_str(html.to_string());

        let body = doc.find("body").unwrap().unwrap();
        let h1 = body.find_nth_xpath("//h1", 1).unwrap().unwrap().into_node().unwrap();

        assert_eq!(h1.inner_text(), "Not hello world".to_string());
    }

    #[test]
    fn test_html_node_relative_find_xpath() {
        let html = r#"<html><head></head><body><h1>Hello, world!</h1><h1>Not hello world</h1></body></html>"#;
        let doc = HtmlDocument::from_str(html.to_string());

        let body = doc.find("body").unwrap().unwrap();
        let h1 = body.find_xpath(".//h1[2]")
            .unwrap()
            .unwrap()
            .into_node()
            .unwrap();

        assert_eq!(h1.inner_text(), "Not hello world".to_string());
    }

    #[test]
    fn test_html_node_relative_find_xpath_text_accessor() {
        let html = r#"<html><head></head><body><h1>Hello, world!</h1><h1>Not hello world</h1></body></html>"#;
        let doc = HtmlDocument::from_str(html.to_string());

        let h1 = doc.find_xpath("//h1[1]").unwrap().unwrap().into_node().unwrap();
        let text = h1.find_xpath("./text()")
            .unwrap()
            .unwrap()
            .into_string()
            .unwrap();

        assert_eq!(text, "Hello, world!".to_string());
    }
}