Commit | Line | Data |
d6512b50 |
1 | =pod |
2 | |
3 | =encoding utf8 |
4 | |
5 | =head1 NAME |
6 | |
7 | DOM::Tiny - Minimalistic HTML/XML DOM parser with CSS selectors |
8 | |
9 | =head1 SYNOPSIS |
10 | |
11 | use DOM::Tiny; |
12 | |
13 | # Parse |
14 | my $dom = DOM::Tiny->new('<div><p id="a">Test</p><p id="b">123</p></div>'); |
15 | |
16 | # Find |
17 | say $dom->at('#b')->text; |
18 | say $dom->find('p')->map('text')->join("\n"); |
19 | say $dom->find('[id]')->map(attr => 'id')->join("\n"); |
20 | |
21 | # Iterate |
22 | $dom->find('p[id]')->reverse->each(sub { say $_->{id} }); |
23 | |
24 | # Loop |
25 | for my $e ($dom->find('p[id]')->each) { |
26 | say $e->{id}, ':', $e->text; |
27 | } |
28 | |
29 | # Modify |
30 | $dom->find('div p')->last->append('<p id="c">456</p>'); |
31 | $dom->find(':not(p)')->map('strip'); |
32 | |
33 | # Render |
34 | say "$dom"; |
35 | |
36 | =head1 DESCRIPTION |
37 | |
9a5f1e3f |
38 | L<DOM::Tiny> is a minimalistic and relaxed pure-perl HTML/XML DOM parser based |
39 | on L<Mojo::DOM>. It supports the L<HTML Living Standard|https://html.spec.whatwg.org/> |
40 | and L<Extensible Markup Language (XML) 1.0|http://www.w3.org/TR/xml/>, and |
41 | matching based on L<CSS3 selectors|http://www.w3.org/TR/selectors/>. It will |
42 | even try to interpret broken HTML and XML, so you should not use it for |
5a70ee9d |
43 | validation. |
d6512b50 |
44 | |
45 | =head1 NODES AND ELEMENTS |
46 | |
47 | When we parse an HTML/XML fragment, it gets turned into a tree of nodes. |
48 | |
49 | <!DOCTYPE html> |
50 | <html> |
51 | <head><title>Hello</title></head> |
52 | <body>World!</body> |
53 | </html> |
54 | |
55 | There are currently eight different kinds of nodes, C<cdata>, C<comment>, |
56 | C<doctype>, C<pi>, C<raw>, C<root>, C<tag> and C<text>. Elements are nodes of |
57 | the type C<tag>. |
58 | |
59 | root |
60 | |- doctype (html) |
61 | +- tag (html) |
62 | |- tag (head) |
63 | | +- tag (title) |
64 | | +- raw (Hello) |
65 | +- tag (body) |
66 | +- text (World!) |
67 | |
68 | While all node types are represented as L<DOM::Tiny> objects, some methods like |
69 | L</"attr"> and L</"namespace"> only apply to elements. |
70 | |
71 | =head1 CASE-SENSITIVITY |
72 | |
73 | L<DOM::Tiny> defaults to HTML semantics, that means all tags and attribute |
74 | names are lowercased and selectors need to be lowercase as well. |
75 | |
76 | # HTML semantics |
77 | my $dom = DOM::Tiny->new('<P ID="greeting">Hi!</P>'); |
78 | say $dom->at('p[id]')->text; |
79 | |
80 | If XML processing instructions are found, the parser will automatically switch |
81 | into XML mode and everything becomes case-sensitive. |
82 | |
83 | # XML semantics |
84 | my $dom = DOM::Tiny->new('<?xml version="1.0"?><P ID="greeting">Hi!</P>'); |
85 | say $dom->at('P[ID]')->text; |
86 | |
87 | XML detection can also be disabled with the L</"xml"> method. |
88 | |
89 | # Force XML semantics |
90 | my $dom = DOM::Tiny->new->xml(1)->parse('<P ID="greeting">Hi!</P>'); |
91 | say $dom->at('P[ID]')->text; |
92 | |
93 | # Force HTML semantics |
94 | my $dom = DOM::Tiny->new->xml(0)->parse('<P ID="greeting">Hi!</P>'); |
95 | say $dom->at('p[id]')->text; |
96 | |
63873d67 |
97 | =head1 SELECTORS |
98 | |
99 | L<DOM::Tiny> uses a CSS selector engine based on L<Mojo::DOM::CSS>. All CSS |
100 | selectors that make sense for a standalone parser are supported. |
101 | |
102 | =head2 * |
103 | |
104 | Any element. |
105 | |
106 | my $all = $dom->find('*'); |
107 | |
108 | =head2 E |
109 | |
110 | An element of type C<E>. |
111 | |
112 | my $title = $dom->at('title'); |
113 | |
114 | =head2 E[foo] |
115 | |
116 | An C<E> element with a C<foo> attribute. |
117 | |
118 | my $links = $dom->find('a[href]'); |
119 | |
120 | =head2 E[foo="bar"] |
121 | |
122 | An C<E> element whose C<foo> attribute value is exactly equal to C<bar>. |
123 | |
124 | my $case_sensitive = $dom->find('input[type="hidden"]'); |
125 | my $case_sensitive = $dom->find('input[type=hidden]'); |
126 | |
127 | =head2 E[foo="bar" i] |
128 | |
129 | An C<E> element whose C<foo> attribute value is exactly equal to any |
130 | (ASCII-range) case-permutation of C<bar>. Note that this selector is |
131 | EXPERIMENTAL and might change without warning! |
132 | |
133 | my $case_insensitive = $dom->find('input[type="hidden" i]'); |
134 | my $case_insensitive = $dom->find('input[type=hidden i]'); |
135 | my $case_insensitive = $dom->find('input[class~="foo" i]'); |
136 | |
137 | This selector is part of |
138 | L<Selectors Level 4|http://dev.w3.org/csswg/selectors-4>, which is still a work |
139 | in progress. |
140 | |
141 | =head2 E[foo~="bar"] |
142 | |
143 | An C<E> element whose C<foo> attribute value is a list of whitespace-separated |
144 | values, one of which is exactly equal to C<bar>. |
145 | |
146 | my $foo = $dom->find('input[class~="foo"]'); |
147 | my $foo = $dom->find('input[class~=foo]'); |
148 | |
149 | =head2 E[foo^="bar"] |
150 | |
151 | An C<E> element whose C<foo> attribute value begins exactly with the string |
152 | C<bar>. |
153 | |
154 | my $begins_with = $dom->find('input[name^="f"]'); |
155 | my $begins_with = $dom->find('input[name^=f]'); |
156 | |
157 | =head2 E[foo$="bar"] |
158 | |
159 | An C<E> element whose C<foo> attribute value ends exactly with the string |
160 | C<bar>. |
161 | |
162 | my $ends_with = $dom->find('input[name$="o"]'); |
163 | my $ends_with = $dom->find('input[name$=o]'); |
164 | |
165 | =head2 E[foo*="bar"] |
166 | |
167 | An C<E> element whose C<foo> attribute value contains the substring C<bar>. |
168 | |
169 | my $contains = $dom->find('input[name*="fo"]'); |
170 | my $contains = $dom->find('input[name*=fo]'); |
171 | |
172 | =head2 E:root |
173 | |
174 | An C<E> element, root of the document. |
175 | |
176 | my $root = $dom->at(':root'); |
177 | |
178 | =head2 E:nth-child(n) |
179 | |
180 | An C<E> element, the C<n-th> child of its parent. |
181 | |
182 | my $third = $dom->find('div:nth-child(3)'); |
183 | my $odd = $dom->find('div:nth-child(odd)'); |
184 | my $even = $dom->find('div:nth-child(even)'); |
185 | my $top3 = $dom->find('div:nth-child(-n+3)'); |
186 | |
187 | =head2 E:nth-last-child(n) |
188 | |
189 | An C<E> element, the C<n-th> child of its parent, counting from the last one. |
190 | |
191 | my $third = $dom->find('div:nth-last-child(3)'); |
192 | my $odd = $dom->find('div:nth-last-child(odd)'); |
193 | my $even = $dom->find('div:nth-last-child(even)'); |
194 | my $bottom3 = $dom->find('div:nth-last-child(-n+3)'); |
195 | |
196 | =head2 E:nth-of-type(n) |
197 | |
198 | An C<E> element, the C<n-th> sibling of its type. |
199 | |
200 | my $third = $dom->find('div:nth-of-type(3)'); |
201 | my $odd = $dom->find('div:nth-of-type(odd)'); |
202 | my $even = $dom->find('div:nth-of-type(even)'); |
203 | my $top3 = $dom->find('div:nth-of-type(-n+3)'); |
204 | |
205 | =head2 E:nth-last-of-type(n) |
206 | |
207 | An C<E> element, the C<n-th> sibling of its type, counting from the last one. |
208 | |
209 | my $third = $dom->find('div:nth-last-of-type(3)'); |
210 | my $odd = $dom->find('div:nth-last-of-type(odd)'); |
211 | my $even = $dom->find('div:nth-last-of-type(even)'); |
212 | my $bottom3 = $dom->find('div:nth-last-of-type(-n+3)'); |
213 | |
214 | =head2 E:first-child |
215 | |
216 | An C<E> element, first child of its parent. |
217 | |
218 | my $first = $dom->find('div p:first-child'); |
219 | |
220 | =head2 E:last-child |
221 | |
222 | An C<E> element, last child of its parent. |
223 | |
224 | my $last = $dom->find('div p:last-child'); |
225 | |
226 | =head2 E:first-of-type |
227 | |
228 | An C<E> element, first sibling of its type. |
229 | |
230 | my $first = $dom->find('div p:first-of-type'); |
231 | |
232 | =head2 E:last-of-type |
233 | |
234 | An C<E> element, last sibling of its type. |
235 | |
236 | my $last = $dom->find('div p:last-of-type'); |
237 | |
238 | =head2 E:only-child |
239 | |
240 | An C<E> element, only child of its parent. |
241 | |
242 | my $lonely = $dom->find('div p:only-child'); |
243 | |
244 | =head2 E:only-of-type |
245 | |
246 | An C<E> element, only sibling of its type. |
247 | |
248 | my $lonely = $dom->find('div p:only-of-type'); |
249 | |
250 | =head2 E:empty |
251 | |
252 | An C<E> element that has no children (including text nodes). |
253 | |
254 | my $empty = $dom->find(':empty'); |
255 | |
256 | =head2 E:checked |
257 | |
258 | A user interface element C<E> which is checked (for instance a radio-button or |
259 | checkbox). |
260 | |
261 | my $input = $dom->find(':checked'); |
262 | |
263 | =head2 E.warning |
264 | |
265 | An C<E> element whose class is "warning". |
266 | |
267 | my $warning = $dom->find('div.warning'); |
268 | |
269 | =head2 E#myid |
270 | |
271 | An C<E> element with C<ID> equal to "myid". |
272 | |
273 | my $foo = $dom->at('div#foo'); |
274 | |
275 | =head2 E:not(s) |
276 | |
277 | An C<E> element that does not match simple selector C<s>. |
278 | |
279 | my $others = $dom->find('div p:not(:first-child)'); |
280 | |
281 | =head2 E F |
282 | |
283 | An C<F> element descendant of an C<E> element. |
284 | |
285 | my $headlines = $dom->find('div h1'); |
286 | |
287 | =head2 E E<gt> F |
288 | |
289 | An C<F> element child of an C<E> element. |
290 | |
291 | my $headlines = $dom->find('html > body > div > h1'); |
292 | |
293 | =head2 E + F |
294 | |
295 | An C<F> element immediately preceded by an C<E> element. |
296 | |
297 | my $second = $dom->find('h1 + h2'); |
298 | |
299 | =head2 E ~ F |
300 | |
301 | An C<F> element preceded by an C<E> element. |
302 | |
303 | my $second = $dom->find('h1 ~ h2'); |
304 | |
305 | =head2 E, F, G |
306 | |
307 | Elements of type C<E>, C<F> and C<G>. |
308 | |
309 | my $headlines = $dom->find('h1, h2, h3'); |
310 | |
311 | =head2 E[foo=bar][bar=baz] |
312 | |
313 | An C<E> element whose attributes match all following attribute selectors. |
314 | |
315 | my $links = $dom->find('a[foo^=b][foo$=ar]'); |
316 | |
9a5f1e3f |
317 | =head1 OPERATORS |
318 | |
319 | L<DOM::Tiny> overloads the following operators. |
320 | |
321 | =head2 array |
322 | |
323 | my @nodes = @$dom; |
324 | |
325 | Alias for L</"child_nodes">. |
326 | |
327 | # "<!-- Test -->" |
328 | $dom->parse('<!-- Test --><b>123</b>')->[0]; |
329 | |
330 | =head2 bool |
331 | |
332 | my $bool = !!$dom; |
333 | |
334 | Always true. |
335 | |
336 | =head2 hash |
337 | |
338 | my %attrs = %$dom; |
339 | |
340 | Alias for L</"attr">. |
341 | |
342 | # "test" |
343 | $dom->parse('<div id="test">Test</div>')->at('div')->{id}; |
344 | |
345 | =head2 stringify |
346 | |
347 | my $str = "$dom"; |
348 | |
349 | Alias for L</"to_string">. |
350 | |
d6512b50 |
351 | =head1 METHODS |
352 | |
353 | L<DOM::Tiny> implements the following methods. |
354 | |
3793c28f |
355 | =head2 new |
356 | |
357 | my $dom = DOM::Tiny->new; |
358 | my $dom = DOM::Tiny->new('<foo bar="baz">I ♥ DOM::Tiny!</foo>'); |
359 | |
360 | Construct a new scalar-based L<DOM::Tiny> object and L</"parse"> HTML/XML |
361 | fragment if necessary. |
362 | |
d6512b50 |
363 | =head2 all_text |
364 | |
365 | my $trimmed = $dom->all_text; |
366 | my $untrimmed = $dom->all_text(0); |
367 | |
368 | Extract text content from all descendant nodes of this element, smart |
369 | whitespace trimming is enabled by default. |
370 | |
371 | # "foo bar baz" |
372 | $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->all_text; |
373 | |
374 | # "foo\nbarbaz\n" |
375 | $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->all_text(0); |
376 | |
377 | =head2 ancestors |
378 | |
379 | my $collection = $dom->ancestors; |
380 | my $collection = $dom->ancestors('div ~ p'); |
381 | |
382 | Find all ancestor elements of this node matching the CSS selector and return a |
8563f527 |
383 | L<collection|/"COLLECTION METHODS"> containing these elements as L<DOM::Tiny> |
9a5f1e3f |
384 | objects. All selectors listed in L</"SELECTORS"> are supported. |
d6512b50 |
385 | |
386 | # List tag names of ancestor elements |
387 | say $dom->ancestors->map('tag')->join("\n"); |
388 | |
389 | =head2 append |
390 | |
391 | $dom = $dom->append('<p>I ♥ DOM::Tiny!</p>'); |
392 | |
393 | Append HTML/XML fragment to this node. |
394 | |
395 | # "<div><h1>Test</h1><h2>123</h2></div>" |
396 | $dom->parse('<div><h1>Test</h1></div>') |
397 | ->at('h1')->append('<h2>123</h2>')->root; |
398 | |
399 | # "<p>Test 123</p>" |
400 | $dom->parse('<p>Test</p>')->at('p') |
401 | ->child_nodes->first->append(' 123')->root; |
402 | |
403 | =head2 append_content |
404 | |
405 | $dom = $dom->append_content('<p>I ♥ DOM::Tiny!</p>'); |
406 | |
407 | Append HTML/XML fragment (for C<root> and C<tag> nodes) or raw content to this |
408 | node's content. |
409 | |
410 | # "<div><h1>Test123</h1></div>" |
411 | $dom->parse('<div><h1>Test</h1></div>') |
412 | ->at('h1')->append_content('123')->root; |
413 | |
414 | # "<!-- Test 123 --><br>" |
415 | $dom->parse('<!-- Test --><br>') |
416 | ->child_nodes->first->append_content('123 ')->root; |
417 | |
418 | # "<p>Test<i>123</i></p>" |
419 | $dom->parse('<p>Test</p>')->at('p')->append_content('<i>123</i>')->root; |
420 | |
421 | =head2 at |
422 | |
423 | my $result = $dom->at('div ~ p'); |
424 | |
425 | Find first descendant element of this element matching the CSS selector and |
426 | return it as a L<DOM::Tiny> object or return C<undef> if none could be found. |
9a5f1e3f |
427 | All selectors listed in L</"SELECTORS"> are supported. |
d6512b50 |
428 | |
429 | # Find first element with "svg" namespace definition |
430 | my $namespace = $dom->at('[xmlns\:svg]')->{'xmlns:svg'}; |
431 | |
432 | =head2 attr |
433 | |
434 | my $hash = $dom->attr; |
435 | my $foo = $dom->attr('foo'); |
436 | $dom = $dom->attr({foo => 'bar'}); |
437 | $dom = $dom->attr(foo => 'bar'); |
438 | |
439 | This element's attributes. |
440 | |
441 | # Remove an attribute |
442 | delete $dom->attr->{id}; |
443 | |
444 | # Attribute without value |
445 | $dom->attr(selected => undef); |
446 | |
447 | # List id attributes |
448 | say $dom->find('*')->map(attr => 'id')->compact->join("\n"); |
449 | |
450 | =head2 child_nodes |
451 | |
452 | my $collection = $dom->child_nodes; |
453 | |
8563f527 |
454 | Return a L<collection|/"COLLECTION METHODS"> containing all child nodes of this |
d6512b50 |
455 | element as L<DOM::Tiny> objects. |
456 | |
457 | # "<p><b>123</b></p>" |
458 | $dom->parse('<p>Test<b>123</b></p>')->at('p')->child_nodes->first->remove; |
459 | |
460 | # "<!DOCTYPE html>" |
461 | $dom->parse('<!DOCTYPE html><b>123</b>')->child_nodes->first; |
462 | |
463 | # " Test " |
464 | $dom->parse('<b>123</b><!-- Test -->')->child_nodes->last->content; |
465 | |
466 | =head2 children |
467 | |
468 | my $collection = $dom->children; |
469 | my $collection = $dom->children('div ~ p'); |
470 | |
471 | Find all child elements of this element matching the CSS selector and return a |
8563f527 |
472 | L<collection|/"COLLECTION METHODS"> containing these elements as L<DOM::Tiny> |
9a5f1e3f |
473 | objects. All selectors listed in L</"SELECTORS"> are supported. |
d6512b50 |
474 | |
475 | # Show tag name of random child element |
476 | say $dom->children->shuffle->first->tag; |
477 | |
478 | =head2 content |
479 | |
480 | my $str = $dom->content; |
481 | $dom = $dom->content('<p>I ♥ DOM::Tiny!</p>'); |
482 | |
483 | Return this node's content or replace it with HTML/XML fragment (for C<root> |
484 | and C<tag> nodes) or raw content. |
485 | |
486 | # "<b>Test</b>" |
487 | $dom->parse('<div><b>Test</b></div>')->at('div')->content; |
488 | |
489 | # "<div><h1>123</h1></div>" |
490 | $dom->parse('<div><h1>Test</h1></div>')->at('h1')->content('123')->root; |
491 | |
492 | # "<p><i>123</i></p>" |
493 | $dom->parse('<p>Test</p>')->at('p')->content('<i>123</i>')->root; |
494 | |
495 | # "<div><h1></h1></div>" |
496 | $dom->parse('<div><h1>Test</h1></div>')->at('h1')->content('')->root; |
497 | |
498 | # " Test " |
499 | $dom->parse('<!-- Test --><br>')->child_nodes->first->content; |
500 | |
501 | # "<div><!-- 123 -->456</div>" |
502 | $dom->parse('<div><!-- Test -->456</div>') |
503 | ->at('div')->child_nodes->first->content(' 123 ')->root; |
504 | |
505 | =head2 descendant_nodes |
506 | |
507 | my $collection = $dom->descendant_nodes; |
508 | |
8563f527 |
509 | Return a L<collection|/"COLLECTION METHODS"> containing all descendant nodes of |
d6512b50 |
510 | this element as L<DOM::Tiny> objects. |
511 | |
512 | # "<p><b>123</b></p>" |
513 | $dom->parse('<p><!-- Test --><b>123<!-- 456 --></b></p>') |
514 | ->descendant_nodes->grep(sub { $_->type eq 'comment' }) |
515 | ->map('remove')->first; |
516 | |
517 | # "<p><b>test</b>test</p>" |
518 | $dom->parse('<p><b>123</b>456</p>') |
519 | ->at('p')->descendant_nodes->grep(sub { $_->type eq 'text' }) |
520 | ->map(content => 'test')->first->root; |
521 | |
522 | =head2 find |
523 | |
524 | my $collection = $dom->find('div ~ p'); |
525 | |
526 | Find all descendant elements of this element matching the CSS selector and |
8563f527 |
527 | return a L<collection|/"COLLECTION METHODS"> containing these elements as |
9a5f1e3f |
528 | L<DOM::Tiny> objects. All selectors listed in L</"SELECTORS"> are supported. |
d6512b50 |
529 | |
530 | # Find a specific element and extract information |
531 | my $id = $dom->find('div')->[23]{id}; |
532 | |
533 | # Extract information from multiple elements |
534 | my @headers = $dom->find('h1, h2, h3')->map('text')->each; |
535 | |
536 | # Count all the different tags |
537 | my $hash = $dom->find('*')->reduce(sub { $a->{$b->tag}++; $a }, {}); |
538 | |
539 | # Find elements with a class that contains dots |
540 | my @divs = $dom->find('div.foo\.bar')->each; |
541 | |
542 | =head2 following |
543 | |
544 | my $collection = $dom->following; |
545 | my $collection = $dom->following('div ~ p'); |
546 | |
547 | Find all sibling elements after this node matching the CSS selector and return |
8563f527 |
548 | a L<collection|/"COLLECTION METHODS"> containing these elements as L<DOM::Tiny> |
9a5f1e3f |
549 | objects. All selectors listen in L</"SELECTORS"> are supported. |
d6512b50 |
550 | |
551 | # List tags of sibling elements after this node |
552 | say $dom->following->map('tag')->join("\n"); |
553 | |
554 | =head2 following_nodes |
555 | |
556 | my $collection = $dom->following_nodes; |
557 | |
8563f527 |
558 | Return a L<collection|/"COLLECTION METHODS"> containing all sibling nodes after |
d6512b50 |
559 | this node as L<DOM::Tiny> objects. |
560 | |
561 | # "C" |
562 | $dom->parse('<p>A</p><!-- B -->C')->at('p')->following_nodes->last->content; |
563 | |
564 | =head2 matches |
565 | |
566 | my $bool = $dom->matches('div ~ p'); |
567 | |
9a5f1e3f |
568 | Check if this element matches the CSS selector. All selectors listed in |
569 | L</"SELECTORS"> are supported. |
d6512b50 |
570 | |
571 | # True |
572 | $dom->parse('<p class="a">A</p>')->at('p')->matches('.a'); |
573 | $dom->parse('<p class="a">A</p>')->at('p')->matches('p[class]'); |
574 | |
575 | # False |
576 | $dom->parse('<p class="a">A</p>')->at('p')->matches('.b'); |
577 | $dom->parse('<p class="a">A</p>')->at('p')->matches('p[id]'); |
578 | |
579 | =head2 namespace |
580 | |
581 | my $namespace = $dom->namespace; |
582 | |
583 | Find this element's namespace or return C<undef> if none could be found. |
584 | |
585 | # Find namespace for an element with namespace prefix |
586 | my $namespace = $dom->at('svg > svg\:circle')->namespace; |
587 | |
588 | # Find namespace for an element that may or may not have a namespace prefix |
589 | my $namespace = $dom->at('svg > circle')->namespace; |
590 | |
d6512b50 |
591 | =head2 next |
592 | |
593 | my $sibling = $dom->next; |
594 | |
595 | Return L<DOM::Tiny> object for next sibling element or C<undef> if there are no |
596 | more siblings. |
597 | |
598 | # "<h2>123</h2>" |
599 | $dom->parse('<div><h1>Test</h1><h2>123</h2></div>')->at('h1')->next; |
600 | |
601 | =head2 next_node |
602 | |
603 | my $sibling = $dom->next_node; |
604 | |
605 | Return L<DOM::Tiny> object for next sibling node or C<undef> if there are no |
606 | more siblings. |
607 | |
608 | # "456" |
609 | $dom->parse('<p><b>123</b><!-- Test -->456</p>') |
610 | ->at('b')->next_node->next_node; |
611 | |
612 | # " Test " |
613 | $dom->parse('<p><b>123</b><!-- Test -->456</p>') |
614 | ->at('b')->next_node->content; |
615 | |
616 | =head2 parent |
617 | |
618 | my $parent = $dom->parent; |
619 | |
620 | Return L<DOM::Tiny> object for parent of this node or C<undef> if this node has |
621 | no parent. |
622 | |
623 | =head2 parse |
624 | |
625 | $dom = $dom->parse('<foo bar="baz">I ♥ DOM::Tiny!</foo>'); |
626 | |
9a5f1e3f |
627 | Parse HTML/XML fragment. |
d6512b50 |
628 | |
629 | # Parse XML |
630 | my $dom = DOM::Tiny->new->xml(1)->parse($xml); |
631 | |
632 | =head2 preceding |
633 | |
634 | my $collection = $dom->preceding; |
635 | my $collection = $dom->preceding('div ~ p'); |
636 | |
637 | Find all sibling elements before this node matching the CSS selector and return |
8563f527 |
638 | a L<collection|/"COLLECTION METHODS"> containing these elements as L<DOM::Tiny> |
9a5f1e3f |
639 | objects. All selectors listed in L</"SELECTORS"> are supported. |
d6512b50 |
640 | |
641 | # List tags of sibling elements before this node |
642 | say $dom->preceding->map('tag')->join("\n"); |
643 | |
644 | =head2 preceding_nodes |
645 | |
646 | my $collection = $dom->preceding_nodes; |
647 | |
8563f527 |
648 | Return a L<collection|/"COLLECTION METHODS"> containing all sibling nodes |
649 | before this node as L<DOM::Tiny> objects. |
d6512b50 |
650 | |
651 | # "A" |
652 | $dom->parse('A<!-- B --><p>C</p>')->at('p')->preceding_nodes->first->content; |
653 | |
654 | =head2 prepend |
655 | |
656 | $dom = $dom->prepend('<p>I ♥ DOM::Tiny!</p>'); |
657 | |
658 | Prepend HTML/XML fragment to this node. |
659 | |
660 | # "<div><h1>Test</h1><h2>123</h2></div>" |
661 | $dom->parse('<div><h2>123</h2></div>') |
662 | ->at('h2')->prepend('<h1>Test</h1>')->root; |
663 | |
664 | # "<p>Test 123</p>" |
665 | $dom->parse('<p>123</p>') |
666 | ->at('p')->child_nodes->first->prepend('Test ')->root; |
667 | |
668 | =head2 prepend_content |
669 | |
670 | $dom = $dom->prepend_content('<p>I ♥ DOM::Tiny!</p>'); |
671 | |
672 | Prepend HTML/XML fragment (for C<root> and C<tag> nodes) or raw content to this |
673 | node's content. |
674 | |
675 | # "<div><h2>Test123</h2></div>" |
676 | $dom->parse('<div><h2>123</h2></div>') |
677 | ->at('h2')->prepend_content('Test')->root; |
678 | |
679 | # "<!-- Test 123 --><br>" |
680 | $dom->parse('<!-- 123 --><br>') |
681 | ->child_nodes->first->prepend_content(' Test')->root; |
682 | |
683 | # "<p><i>123</i>Test</p>" |
684 | $dom->parse('<p>Test</p>')->at('p')->prepend_content('<i>123</i>')->root; |
685 | |
686 | =head2 previous |
687 | |
688 | my $sibling = $dom->previous; |
689 | |
690 | Return L<DOM::Tiny> object for previous sibling element or C<undef> if there |
691 | are no more siblings. |
692 | |
693 | # "<h1>Test</h1>" |
694 | $dom->parse('<div><h1>Test</h1><h2>123</h2></div>')->at('h2')->previous; |
695 | |
696 | =head2 previous_node |
697 | |
698 | my $sibling = $dom->previous_node; |
699 | |
700 | Return L<DOM::Tiny> object for previous sibling node or C<undef> if there are |
701 | no more siblings. |
702 | |
703 | # "123" |
704 | $dom->parse('<p>123<!-- Test --><b>456</b></p>') |
705 | ->at('b')->previous_node->previous_node; |
706 | |
707 | # " Test " |
708 | $dom->parse('<p>123<!-- Test --><b>456</b></p>') |
709 | ->at('b')->previous_node->content; |
710 | |
711 | =head2 remove |
712 | |
713 | my $parent = $dom->remove; |
714 | |
715 | Remove this node and return L</"root"> (for C<root> nodes) or L</"parent">. |
716 | |
717 | # "<div></div>" |
718 | $dom->parse('<div><h1>Test</h1></div>')->at('h1')->remove; |
719 | |
720 | # "<p><b>456</b></p>" |
721 | $dom->parse('<p>123<b>456</b></p>') |
722 | ->at('p')->child_nodes->first->remove->root; |
723 | |
724 | =head2 replace |
725 | |
726 | my $parent = $dom->replace('<div>I ♥ DOM::Tiny!</div>'); |
727 | |
728 | Replace this node with HTML/XML fragment and return L</"root"> (for C<root> |
729 | nodes) or L</"parent">. |
730 | |
731 | # "<div><h2>123</h2></div>" |
732 | $dom->parse('<div><h1>Test</h1></div>')->at('h1')->replace('<h2>123</h2>'); |
733 | |
734 | # "<p><b>123</b></p>" |
735 | $dom->parse('<p>Test</p>') |
736 | ->at('p')->child_nodes->[0]->replace('<b>123</b>')->root; |
737 | |
738 | =head2 root |
739 | |
740 | my $root = $dom->root; |
741 | |
742 | Return L<DOM::Tiny> object for C<root> node. |
743 | |
744 | =head2 strip |
745 | |
746 | my $parent = $dom->strip; |
747 | |
748 | Remove this element while preserving its content and return L</"parent">. |
749 | |
750 | # "<div>Test</div>" |
751 | $dom->parse('<div><h1>Test</h1></div>')->at('h1')->strip; |
752 | |
753 | =head2 tag |
754 | |
755 | my $tag = $dom->tag; |
756 | $dom = $dom->tag('div'); |
757 | |
758 | This element's tag name. |
759 | |
760 | # List tag names of child elements |
761 | say $dom->children->map('tag')->join("\n"); |
762 | |
763 | =head2 tap |
764 | |
765 | $dom = $dom->tap(sub {...}); |
766 | |
e99ef07d |
767 | Equivalent to L<Mojo::Base/"tap">. |
d6512b50 |
768 | |
769 | =head2 text |
770 | |
771 | my $trimmed = $dom->text; |
772 | my $untrimmed = $dom->text(0); |
773 | |
774 | Extract text content from this element only (not including child elements), |
775 | smart whitespace trimming is enabled by default. |
776 | |
777 | # "foo baz" |
778 | $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->text; |
779 | |
780 | # "foo\nbaz\n" |
781 | $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->text(0); |
782 | |
783 | =head2 to_string |
784 | |
785 | my $str = $dom->to_string; |
786 | |
787 | Render this node and its content to HTML/XML. |
788 | |
789 | # "<b>Test</b>" |
790 | $dom->parse('<div><b>Test</b></div>')->at('div b')->to_string; |
791 | |
792 | =head2 tree |
793 | |
794 | my $tree = $dom->tree; |
795 | $dom = $dom->tree(['root']); |
796 | |
797 | Document Object Model. Note that this structure should only be used very |
798 | carefully since it is very dynamic. |
799 | |
800 | =head2 type |
801 | |
802 | my $type = $dom->type; |
803 | |
804 | This node's type, usually C<cdata>, C<comment>, C<doctype>, C<pi>, C<raw>, |
805 | C<root>, C<tag> or C<text>. |
806 | |
807 | # "cdata" |
808 | $dom->parse('<![CDATA[Test]]>')->child_nodes->first->type; |
809 | |
810 | # "comment" |
811 | $dom->parse('<!-- Test -->')->child_nodes->first->type; |
812 | |
813 | # "doctype" |
814 | $dom->parse('<!DOCTYPE html>')->child_nodes->first->type; |
815 | |
816 | # "pi" |
817 | $dom->parse('<?xml version="1.0"?>')->child_nodes->first->type; |
818 | |
819 | # "raw" |
820 | $dom->parse('<title>Test</title>')->at('title')->child_nodes->first->type; |
821 | |
822 | # "root" |
823 | $dom->parse('<p>Test</p>')->type; |
824 | |
825 | # "tag" |
826 | $dom->parse('<p>Test</p>')->at('p')->type; |
827 | |
828 | # "text" |
829 | $dom->parse('<p>Test</p>')->at('p')->child_nodes->first->type; |
830 | |
831 | =head2 val |
832 | |
833 | my $value = $dom->val; |
834 | |
835 | Extract value from form element (such as C<button>, C<input>, C<option>, |
836 | C<select> and C<textarea>) or return C<undef> if this element has no value. In |
837 | the case of C<select> with C<multiple> attribute, find C<option> elements with |
838 | C<selected> attribute and return an array reference with all values or C<undef> |
839 | if none could be found. |
840 | |
841 | # "a" |
842 | $dom->parse('<input name="test" value="a">')->at('input')->val; |
843 | |
844 | # "b" |
845 | $dom->parse('<textarea>b</textarea>')->at('textarea')->val; |
846 | |
847 | # "c" |
848 | $dom->parse('<option value="c">Test</option>')->at('option')->val; |
849 | |
850 | # "d" |
851 | $dom->parse('<select><option selected>d</option></select>') |
852 | ->at('select')->val; |
853 | |
854 | # "e" |
855 | $dom->parse('<select multiple><option selected>e</option></select>') |
856 | ->at('select')->val->[0]; |
857 | |
858 | =head2 wrap |
859 | |
860 | $dom = $dom->wrap('<div></div>'); |
861 | |
862 | Wrap HTML/XML fragment around this node, placing it as the last child of the |
863 | first innermost element. |
864 | |
865 | # "<p>123<b>Test</b></p>" |
866 | $dom->parse('<b>Test</b>')->at('b')->wrap('<p>123</p>')->root; |
867 | |
868 | # "<div><p><b>Test</b></p>123</div>" |
869 | $dom->parse('<b>Test</b>')->at('b')->wrap('<div><p></p>123</div>')->root; |
870 | |
871 | # "<p><b>Test</b></p><p>123</p>" |
872 | $dom->parse('<b>Test</b>')->at('b')->wrap('<p></p><p>123</p>')->root; |
873 | |
874 | # "<p><b>Test</b></p>" |
875 | $dom->parse('<p>Test</p>')->at('p')->child_nodes->first->wrap('<b>')->root; |
876 | |
877 | =head2 wrap_content |
878 | |
879 | $dom = $dom->wrap_content('<div></div>'); |
880 | |
881 | Wrap HTML/XML fragment around this node's content, placing it as the last |
882 | children of the first innermost element. |
883 | |
884 | # "<p><b>123Test</b></p>" |
885 | $dom->parse('<p>Test<p>')->at('p')->wrap_content('<b>123</b>')->root; |
886 | |
887 | # "<p><b>Test</b></p><p>123</p>" |
888 | $dom->parse('<b>Test</b>')->wrap_content('<p></p><p>123</p>'); |
889 | |
890 | =head2 xml |
891 | |
892 | my $bool = $dom->xml; |
893 | $dom = $dom->xml($bool); |
894 | |
895 | Disable HTML semantics in parser and activate case-sensitivity, defaults to |
896 | auto detection based on processing instructions. |
897 | |
78ba4051 |
898 | =head1 COLLECTION METHODS |
899 | |
9a5f1e3f |
900 | Some L<DOM::Tiny> methods return an array-based collection object based on |
901 | L<Mojo::Collection>, which can either be accessed directly as an array |
902 | reference, or with the following methods. |
78ba4051 |
903 | |
904 | # Chain methods |
905 | $collection->map(sub { ucfirst })->shuffle->each(sub { |
906 | my ($word, $num) = @_; |
907 | say "$num: $word"; |
908 | }); |
909 | |
910 | # Access array directly to manipulate collection |
911 | $collection->[23] += 100; |
912 | say for @$collection; |
913 | |
914 | =head2 compact |
915 | |
916 | my $new = $collection->compact; |
917 | |
918 | Create a new collection with all elements that are defined and not an empty |
919 | string. |
920 | |
921 | # $collection contains (0, 1, undef, 2, '', 3) |
922 | $collection->compact->join(', '); # "0, 1, 2, 3" |
923 | |
924 | =head2 each |
925 | |
926 | my @elements = $collection->each; |
927 | $collection = $collection->each(sub {...}); |
928 | |
929 | Evaluate callback for each element in collection or return all elements as a |
930 | list if none has been provided. The element will be the first argument passed |
931 | to the callback and is also available as C<$_>. |
932 | |
933 | # Make a numbered list |
934 | $collection->each(sub { |
935 | my ($e, $num) = @_; |
936 | say "$num: $e"; |
937 | }); |
938 | |
939 | =head2 first |
940 | |
941 | my $first = $collection->first; |
942 | my $first = $collection->first(qr/foo/); |
943 | my $first = $collection->first(sub {...}); |
944 | my $first = $collection->first($method); |
945 | my $first = $collection->first($method, @args); |
946 | |
947 | Evaluate regular expression/callback for, or call method on, each element in |
948 | collection and return the first one that matched the regular expression, or for |
949 | which the callback/method returned true. The element will be the first argument |
950 | passed to the callback and is also available as C<$_>. |
951 | |
952 | # Longer version |
953 | my $first = $collection->first(sub { $_->$method(@args) }); |
954 | |
c7bc4d31 |
955 | # Find first value that contains the word "tiny" |
956 | my $interesting = $collection->first(qr/tiny/i); |
78ba4051 |
957 | |
958 | # Find first value that is greater than 5 |
959 | my $greater = $collection->first(sub { $_ > 5 }); |
960 | |
961 | =head2 flatten |
962 | |
963 | my $new = $collection->flatten; |
964 | |
965 | Flatten nested collections/arrays recursively and create a new collection with |
966 | all elements. |
967 | |
968 | # $collection contains (1, [2, [3, 4], 5, [6]], 7) |
969 | $collection->flatten->join(', '); # "1, 2, 3, 4, 5, 6, 7" |
970 | |
971 | =head2 grep |
972 | |
973 | my $new = $collection->grep(qr/foo/); |
974 | my $new = $collection->grep(sub {...}); |
975 | my $new = $collection->grep($method); |
976 | my $new = $collection->grep($method, @args); |
977 | |
978 | Evaluate regular expression/callback for, or call method on, each element in |
979 | collection and create a new collection with all elements that matched the |
980 | regular expression, or for which the callback/method returned true. The element |
981 | will be the first argument passed to the callback and is also available as |
982 | C<$_>. |
983 | |
984 | # Longer version |
985 | my $new = $collection->grep(sub { $_->$method(@args) }); |
986 | |
c7bc4d31 |
987 | # Find all values that contain the word "tiny" |
988 | my $interesting = $collection->grep(qr/tiny/i); |
78ba4051 |
989 | |
990 | # Find all values that are greater than 5 |
991 | my $greater = $collection->grep(sub { $_ > 5 }); |
992 | |
993 | =head2 join |
994 | |
995 | my $stream = $collection->join; |
996 | my $stream = $collection->join("\n"); |
997 | |
998 | Turn collection into string. |
999 | |
1000 | # Join all values with commas |
1001 | $collection->join(', '); |
1002 | |
1003 | =head2 last |
1004 | |
1005 | my $last = $collection->last; |
1006 | |
1007 | Return the last element in collection. |
1008 | |
1009 | =head2 map |
1010 | |
1011 | my $new = $collection->map(sub {...}); |
1012 | my $new = $collection->map($method); |
1013 | my $new = $collection->map($method, @args); |
1014 | |
1015 | Evaluate callback for, or call method on, each element in collection and create |
1016 | a new collection from the results. The element will be the first argument |
1017 | passed to the callback and is also available as C<$_>. |
1018 | |
1019 | # Longer version |
1020 | my $new = $collection->map(sub { $_->$method(@args) }); |
1021 | |
c7bc4d31 |
1022 | # Append the word "tiny" to all values |
1023 | my $domified = $collection->map(sub { $_ . 'tiny' }); |
78ba4051 |
1024 | |
1025 | =head2 reduce |
1026 | |
1027 | my $result = $collection->reduce(sub {...}); |
1028 | my $result = $collection->reduce(sub {...}, $initial); |
1029 | |
1030 | Reduce elements in collection with callback, the first element will be used as |
1031 | initial value if none has been provided. |
1032 | |
1033 | # Calculate the sum of all values |
1034 | my $sum = $collection->reduce(sub { $a + $b }); |
1035 | |
1036 | # Count how often each value occurs in collection |
1037 | my $hash = $collection->reduce(sub { $a->{$b}++; $a }, {}); |
1038 | |
1039 | =head2 reverse |
1040 | |
1041 | my $new = $collection->reverse; |
1042 | |
1043 | Create a new collection with all elements in reverse order. |
1044 | |
1045 | =head2 slice |
1046 | |
1047 | my $new = $collection->slice(4 .. 7); |
1048 | |
1049 | Create a new collection with all selected elements. |
1050 | |
1051 | # $collection contains ('A', 'B', 'C', 'D', 'E') |
1052 | $collection->slice(1, 2, 4)->join(' '); # "B C E" |
1053 | |
1054 | =head2 shuffle |
1055 | |
1056 | my $new = $collection->shuffle; |
1057 | |
1058 | Create a new collection with all elements in random order. |
1059 | |
1060 | =head2 size |
1061 | |
1062 | my $size = $collection->size; |
1063 | |
1064 | Number of elements in collection. |
1065 | |
1066 | =head2 sort |
1067 | |
1068 | my $new = $collection->sort; |
1069 | my $new = $collection->sort(sub {...}); |
1070 | |
1071 | Sort elements based on return value of callback and create a new collection |
1072 | from the results. |
1073 | |
1074 | # Sort values case-insensitive |
1075 | my $case_insensitive = $collection->sort(sub { uc($a) cmp uc($b) }); |
1076 | |
1077 | =head2 tap |
1078 | |
1079 | $collection = $collection->tap(sub {...}); |
1080 | |
1081 | Equivalent to L<Mojo::Base/"tap">. |
1082 | |
1083 | =head2 to_array |
1084 | |
1085 | my $array = $collection->to_array; |
1086 | |
1087 | Turn collection into array reference. |
1088 | |
1089 | =head2 uniq |
1090 | |
1091 | my $new = $collection->uniq; |
1092 | my $new = $collection->uniq(sub {...}); |
1093 | my $new = $collection->uniq($method); |
1094 | my $new = $collection->uniq($method, @args); |
1095 | |
1096 | Create a new collection without duplicate elements, using the string |
1097 | representation of either the elements or the return value of the |
1098 | callback/method. |
1099 | |
1100 | # Longer version |
1101 | my $new = $collection->uniq(sub { $_->$method(@args) }); |
1102 | |
1103 | # $collection contains ('foo', 'bar', 'bar', 'baz') |
1104 | $collection->uniq->join(' '); # "foo bar baz" |
1105 | |
1106 | # $collection contains ([1, 2], [2, 1], [3, 2]) |
1107 | $collection->uniq(sub{ $_->[1] })->to_array; # "[[1, 2], [2, 1]]" |
1108 | |
d6512b50 |
1109 | =head1 BUGS |
1110 | |
1111 | Report any issues on the public bugtracker. |
1112 | |
1113 | =head1 AUTHOR |
1114 | |
1115 | Dan Book <dbook@cpan.org> |
1116 | |
1117 | =head1 COPYRIGHT AND LICENSE |
1118 | |
1119 | This software is Copyright (c) 2015 by Dan Book. |
1120 | |
1121 | This is free software, licensed under: |
1122 | |
1123 | The Artistic License 2.0 (GPL Compatible) |
1124 | |
1125 | =head1 SEE ALSO |
1126 | |
31877452 |
1127 | L<Mojo::DOM>, L<HTML::TreeBuilder>, L<XML::LibXML>, L<XML::Twig>, L<XML::Smart> |
d6512b50 |
1128 | |
9a5f1e3f |
1129 | =for Pod::Coverage TO_JSON |
1130 | |
d6512b50 |
1131 | =cut |