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 | |
03eb5521 |
102 | =over |
103 | |
104 | =item Z<>* |
63873d67 |
105 | |
106 | Any element. |
107 | |
108 | my $all = $dom->find('*'); |
109 | |
03eb5521 |
110 | =item E |
63873d67 |
111 | |
112 | An element of type C<E>. |
113 | |
114 | my $title = $dom->at('title'); |
115 | |
03eb5521 |
116 | =item E[foo] |
63873d67 |
117 | |
118 | An C<E> element with a C<foo> attribute. |
119 | |
120 | my $links = $dom->find('a[href]'); |
121 | |
03eb5521 |
122 | =item E[foo="bar"] |
63873d67 |
123 | |
124 | An C<E> element whose C<foo> attribute value is exactly equal to C<bar>. |
125 | |
126 | my $case_sensitive = $dom->find('input[type="hidden"]'); |
127 | my $case_sensitive = $dom->find('input[type=hidden]'); |
128 | |
03eb5521 |
129 | =item E[foo="bar" i] |
63873d67 |
130 | |
131 | An C<E> element whose C<foo> attribute value is exactly equal to any |
132 | (ASCII-range) case-permutation of C<bar>. Note that this selector is |
133 | EXPERIMENTAL and might change without warning! |
134 | |
135 | my $case_insensitive = $dom->find('input[type="hidden" i]'); |
136 | my $case_insensitive = $dom->find('input[type=hidden i]'); |
137 | my $case_insensitive = $dom->find('input[class~="foo" i]'); |
138 | |
139 | This selector is part of |
140 | L<Selectors Level 4|http://dev.w3.org/csswg/selectors-4>, which is still a work |
141 | in progress. |
142 | |
03eb5521 |
143 | =item E[foo~="bar"] |
63873d67 |
144 | |
145 | An C<E> element whose C<foo> attribute value is a list of whitespace-separated |
146 | values, one of which is exactly equal to C<bar>. |
147 | |
148 | my $foo = $dom->find('input[class~="foo"]'); |
149 | my $foo = $dom->find('input[class~=foo]'); |
150 | |
03eb5521 |
151 | =item E[foo^="bar"] |
63873d67 |
152 | |
153 | An C<E> element whose C<foo> attribute value begins exactly with the string |
154 | C<bar>. |
155 | |
156 | my $begins_with = $dom->find('input[name^="f"]'); |
157 | my $begins_with = $dom->find('input[name^=f]'); |
158 | |
03eb5521 |
159 | =item E[foo$="bar"] |
63873d67 |
160 | |
161 | An C<E> element whose C<foo> attribute value ends exactly with the string |
162 | C<bar>. |
163 | |
164 | my $ends_with = $dom->find('input[name$="o"]'); |
165 | my $ends_with = $dom->find('input[name$=o]'); |
166 | |
03eb5521 |
167 | =item E[foo*="bar"] |
63873d67 |
168 | |
169 | An C<E> element whose C<foo> attribute value contains the substring C<bar>. |
170 | |
171 | my $contains = $dom->find('input[name*="fo"]'); |
172 | my $contains = $dom->find('input[name*=fo]'); |
173 | |
03eb5521 |
174 | =item E:root |
63873d67 |
175 | |
176 | An C<E> element, root of the document. |
177 | |
178 | my $root = $dom->at(':root'); |
179 | |
03eb5521 |
180 | =item E:nth-child(n) |
63873d67 |
181 | |
182 | An C<E> element, the C<n-th> child of its parent. |
183 | |
184 | my $third = $dom->find('div:nth-child(3)'); |
185 | my $odd = $dom->find('div:nth-child(odd)'); |
186 | my $even = $dom->find('div:nth-child(even)'); |
187 | my $top3 = $dom->find('div:nth-child(-n+3)'); |
188 | |
03eb5521 |
189 | =item E:nth-last-child(n) |
63873d67 |
190 | |
191 | An C<E> element, the C<n-th> child of its parent, counting from the last one. |
192 | |
193 | my $third = $dom->find('div:nth-last-child(3)'); |
194 | my $odd = $dom->find('div:nth-last-child(odd)'); |
195 | my $even = $dom->find('div:nth-last-child(even)'); |
196 | my $bottom3 = $dom->find('div:nth-last-child(-n+3)'); |
197 | |
03eb5521 |
198 | =item E:nth-of-type(n) |
63873d67 |
199 | |
200 | An C<E> element, the C<n-th> sibling of its type. |
201 | |
202 | my $third = $dom->find('div:nth-of-type(3)'); |
203 | my $odd = $dom->find('div:nth-of-type(odd)'); |
204 | my $even = $dom->find('div:nth-of-type(even)'); |
205 | my $top3 = $dom->find('div:nth-of-type(-n+3)'); |
206 | |
03eb5521 |
207 | =item E:nth-last-of-type(n) |
63873d67 |
208 | |
209 | An C<E> element, the C<n-th> sibling of its type, counting from the last one. |
210 | |
211 | my $third = $dom->find('div:nth-last-of-type(3)'); |
212 | my $odd = $dom->find('div:nth-last-of-type(odd)'); |
213 | my $even = $dom->find('div:nth-last-of-type(even)'); |
214 | my $bottom3 = $dom->find('div:nth-last-of-type(-n+3)'); |
215 | |
03eb5521 |
216 | =item E:first-child |
63873d67 |
217 | |
218 | An C<E> element, first child of its parent. |
219 | |
220 | my $first = $dom->find('div p:first-child'); |
221 | |
03eb5521 |
222 | =item E:last-child |
63873d67 |
223 | |
224 | An C<E> element, last child of its parent. |
225 | |
226 | my $last = $dom->find('div p:last-child'); |
227 | |
03eb5521 |
228 | =item E:first-of-type |
63873d67 |
229 | |
230 | An C<E> element, first sibling of its type. |
231 | |
232 | my $first = $dom->find('div p:first-of-type'); |
233 | |
03eb5521 |
234 | =item E:last-of-type |
63873d67 |
235 | |
236 | An C<E> element, last sibling of its type. |
237 | |
238 | my $last = $dom->find('div p:last-of-type'); |
239 | |
03eb5521 |
240 | =item E:only-child |
63873d67 |
241 | |
242 | An C<E> element, only child of its parent. |
243 | |
244 | my $lonely = $dom->find('div p:only-child'); |
245 | |
03eb5521 |
246 | =item E:only-of-type |
63873d67 |
247 | |
248 | An C<E> element, only sibling of its type. |
249 | |
250 | my $lonely = $dom->find('div p:only-of-type'); |
251 | |
03eb5521 |
252 | =item E:empty |
63873d67 |
253 | |
254 | An C<E> element that has no children (including text nodes). |
255 | |
256 | my $empty = $dom->find(':empty'); |
257 | |
03eb5521 |
258 | =item E:checked |
63873d67 |
259 | |
260 | A user interface element C<E> which is checked (for instance a radio-button or |
261 | checkbox). |
262 | |
263 | my $input = $dom->find(':checked'); |
264 | |
03eb5521 |
265 | =item E.warning |
63873d67 |
266 | |
267 | An C<E> element whose class is "warning". |
268 | |
269 | my $warning = $dom->find('div.warning'); |
270 | |
03eb5521 |
271 | =item E#myid |
63873d67 |
272 | |
273 | An C<E> element with C<ID> equal to "myid". |
274 | |
275 | my $foo = $dom->at('div#foo'); |
276 | |
03eb5521 |
277 | =item E:not(s) |
63873d67 |
278 | |
279 | An C<E> element that does not match simple selector C<s>. |
280 | |
281 | my $others = $dom->find('div p:not(:first-child)'); |
282 | |
03eb5521 |
283 | =item E F |
63873d67 |
284 | |
285 | An C<F> element descendant of an C<E> element. |
286 | |
287 | my $headlines = $dom->find('div h1'); |
288 | |
03eb5521 |
289 | =item E E<gt> F |
63873d67 |
290 | |
291 | An C<F> element child of an C<E> element. |
292 | |
293 | my $headlines = $dom->find('html > body > div > h1'); |
294 | |
03eb5521 |
295 | =item E + F |
63873d67 |
296 | |
297 | An C<F> element immediately preceded by an C<E> element. |
298 | |
299 | my $second = $dom->find('h1 + h2'); |
300 | |
03eb5521 |
301 | =item E ~ F |
63873d67 |
302 | |
303 | An C<F> element preceded by an C<E> element. |
304 | |
305 | my $second = $dom->find('h1 ~ h2'); |
306 | |
03eb5521 |
307 | =item E, F, G |
63873d67 |
308 | |
309 | Elements of type C<E>, C<F> and C<G>. |
310 | |
311 | my $headlines = $dom->find('h1, h2, h3'); |
312 | |
03eb5521 |
313 | =item E[foo=bar][bar=baz] |
63873d67 |
314 | |
315 | An C<E> element whose attributes match all following attribute selectors. |
316 | |
317 | my $links = $dom->find('a[foo^=b][foo$=ar]'); |
318 | |
03eb5521 |
319 | =back |
320 | |
9a5f1e3f |
321 | =head1 OPERATORS |
322 | |
323 | L<DOM::Tiny> overloads the following operators. |
324 | |
325 | =head2 array |
326 | |
327 | my @nodes = @$dom; |
328 | |
329 | Alias for L</"child_nodes">. |
330 | |
331 | # "<!-- Test -->" |
332 | $dom->parse('<!-- Test --><b>123</b>')->[0]; |
333 | |
334 | =head2 bool |
335 | |
336 | my $bool = !!$dom; |
337 | |
338 | Always true. |
339 | |
340 | =head2 hash |
341 | |
342 | my %attrs = %$dom; |
343 | |
344 | Alias for L</"attr">. |
345 | |
346 | # "test" |
347 | $dom->parse('<div id="test">Test</div>')->at('div')->{id}; |
348 | |
349 | =head2 stringify |
350 | |
351 | my $str = "$dom"; |
352 | |
353 | Alias for L</"to_string">. |
354 | |
d6512b50 |
355 | =head1 METHODS |
356 | |
357 | L<DOM::Tiny> implements the following methods. |
358 | |
3793c28f |
359 | =head2 new |
360 | |
361 | my $dom = DOM::Tiny->new; |
362 | my $dom = DOM::Tiny->new('<foo bar="baz">I ♥ DOM::Tiny!</foo>'); |
363 | |
364 | Construct a new scalar-based L<DOM::Tiny> object and L</"parse"> HTML/XML |
365 | fragment if necessary. |
366 | |
d6512b50 |
367 | =head2 all_text |
368 | |
369 | my $trimmed = $dom->all_text; |
370 | my $untrimmed = $dom->all_text(0); |
371 | |
372 | Extract text content from all descendant nodes of this element, smart |
373 | whitespace trimming is enabled by default. |
374 | |
375 | # "foo bar baz" |
376 | $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->all_text; |
377 | |
378 | # "foo\nbarbaz\n" |
379 | $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->all_text(0); |
380 | |
381 | =head2 ancestors |
382 | |
383 | my $collection = $dom->ancestors; |
384 | my $collection = $dom->ancestors('div ~ p'); |
385 | |
386 | Find all ancestor elements of this node matching the CSS selector and return a |
8563f527 |
387 | L<collection|/"COLLECTION METHODS"> containing these elements as L<DOM::Tiny> |
9a5f1e3f |
388 | objects. All selectors listed in L</"SELECTORS"> are supported. |
d6512b50 |
389 | |
390 | # List tag names of ancestor elements |
391 | say $dom->ancestors->map('tag')->join("\n"); |
392 | |
393 | =head2 append |
394 | |
395 | $dom = $dom->append('<p>I ♥ DOM::Tiny!</p>'); |
396 | |
397 | Append HTML/XML fragment to this node. |
398 | |
399 | # "<div><h1>Test</h1><h2>123</h2></div>" |
400 | $dom->parse('<div><h1>Test</h1></div>') |
401 | ->at('h1')->append('<h2>123</h2>')->root; |
402 | |
403 | # "<p>Test 123</p>" |
404 | $dom->parse('<p>Test</p>')->at('p') |
405 | ->child_nodes->first->append(' 123')->root; |
406 | |
407 | =head2 append_content |
408 | |
409 | $dom = $dom->append_content('<p>I ♥ DOM::Tiny!</p>'); |
410 | |
411 | Append HTML/XML fragment (for C<root> and C<tag> nodes) or raw content to this |
412 | node's content. |
413 | |
414 | # "<div><h1>Test123</h1></div>" |
415 | $dom->parse('<div><h1>Test</h1></div>') |
416 | ->at('h1')->append_content('123')->root; |
417 | |
418 | # "<!-- Test 123 --><br>" |
419 | $dom->parse('<!-- Test --><br>') |
420 | ->child_nodes->first->append_content('123 ')->root; |
421 | |
422 | # "<p>Test<i>123</i></p>" |
423 | $dom->parse('<p>Test</p>')->at('p')->append_content('<i>123</i>')->root; |
424 | |
425 | =head2 at |
426 | |
427 | my $result = $dom->at('div ~ p'); |
428 | |
429 | Find first descendant element of this element matching the CSS selector and |
430 | return it as a L<DOM::Tiny> object or return C<undef> if none could be found. |
9a5f1e3f |
431 | All selectors listed in L</"SELECTORS"> are supported. |
d6512b50 |
432 | |
433 | # Find first element with "svg" namespace definition |
434 | my $namespace = $dom->at('[xmlns\:svg]')->{'xmlns:svg'}; |
435 | |
436 | =head2 attr |
437 | |
438 | my $hash = $dom->attr; |
439 | my $foo = $dom->attr('foo'); |
440 | $dom = $dom->attr({foo => 'bar'}); |
441 | $dom = $dom->attr(foo => 'bar'); |
442 | |
443 | This element's attributes. |
444 | |
445 | # Remove an attribute |
446 | delete $dom->attr->{id}; |
447 | |
448 | # Attribute without value |
449 | $dom->attr(selected => undef); |
450 | |
451 | # List id attributes |
452 | say $dom->find('*')->map(attr => 'id')->compact->join("\n"); |
453 | |
454 | =head2 child_nodes |
455 | |
456 | my $collection = $dom->child_nodes; |
457 | |
8563f527 |
458 | Return a L<collection|/"COLLECTION METHODS"> containing all child nodes of this |
d6512b50 |
459 | element as L<DOM::Tiny> objects. |
460 | |
461 | # "<p><b>123</b></p>" |
462 | $dom->parse('<p>Test<b>123</b></p>')->at('p')->child_nodes->first->remove; |
463 | |
464 | # "<!DOCTYPE html>" |
465 | $dom->parse('<!DOCTYPE html><b>123</b>')->child_nodes->first; |
466 | |
467 | # " Test " |
468 | $dom->parse('<b>123</b><!-- Test -->')->child_nodes->last->content; |
469 | |
470 | =head2 children |
471 | |
472 | my $collection = $dom->children; |
473 | my $collection = $dom->children('div ~ p'); |
474 | |
475 | Find all child elements of this element matching the CSS selector and return a |
8563f527 |
476 | L<collection|/"COLLECTION METHODS"> containing these elements as L<DOM::Tiny> |
9a5f1e3f |
477 | objects. All selectors listed in L</"SELECTORS"> are supported. |
d6512b50 |
478 | |
479 | # Show tag name of random child element |
480 | say $dom->children->shuffle->first->tag; |
481 | |
482 | =head2 content |
483 | |
484 | my $str = $dom->content; |
485 | $dom = $dom->content('<p>I ♥ DOM::Tiny!</p>'); |
486 | |
487 | Return this node's content or replace it with HTML/XML fragment (for C<root> |
488 | and C<tag> nodes) or raw content. |
489 | |
490 | # "<b>Test</b>" |
491 | $dom->parse('<div><b>Test</b></div>')->at('div')->content; |
492 | |
493 | # "<div><h1>123</h1></div>" |
494 | $dom->parse('<div><h1>Test</h1></div>')->at('h1')->content('123')->root; |
495 | |
496 | # "<p><i>123</i></p>" |
497 | $dom->parse('<p>Test</p>')->at('p')->content('<i>123</i>')->root; |
498 | |
499 | # "<div><h1></h1></div>" |
500 | $dom->parse('<div><h1>Test</h1></div>')->at('h1')->content('')->root; |
501 | |
502 | # " Test " |
503 | $dom->parse('<!-- Test --><br>')->child_nodes->first->content; |
504 | |
505 | # "<div><!-- 123 -->456</div>" |
506 | $dom->parse('<div><!-- Test -->456</div>') |
507 | ->at('div')->child_nodes->first->content(' 123 ')->root; |
508 | |
509 | =head2 descendant_nodes |
510 | |
511 | my $collection = $dom->descendant_nodes; |
512 | |
8563f527 |
513 | Return a L<collection|/"COLLECTION METHODS"> containing all descendant nodes of |
d6512b50 |
514 | this element as L<DOM::Tiny> objects. |
515 | |
516 | # "<p><b>123</b></p>" |
517 | $dom->parse('<p><!-- Test --><b>123<!-- 456 --></b></p>') |
518 | ->descendant_nodes->grep(sub { $_->type eq 'comment' }) |
519 | ->map('remove')->first; |
520 | |
521 | # "<p><b>test</b>test</p>" |
522 | $dom->parse('<p><b>123</b>456</p>') |
523 | ->at('p')->descendant_nodes->grep(sub { $_->type eq 'text' }) |
524 | ->map(content => 'test')->first->root; |
525 | |
526 | =head2 find |
527 | |
528 | my $collection = $dom->find('div ~ p'); |
529 | |
530 | Find all descendant elements of this element matching the CSS selector and |
8563f527 |
531 | return a L<collection|/"COLLECTION METHODS"> containing these elements as |
9a5f1e3f |
532 | L<DOM::Tiny> objects. All selectors listed in L</"SELECTORS"> are supported. |
d6512b50 |
533 | |
534 | # Find a specific element and extract information |
535 | my $id = $dom->find('div')->[23]{id}; |
536 | |
537 | # Extract information from multiple elements |
538 | my @headers = $dom->find('h1, h2, h3')->map('text')->each; |
539 | |
540 | # Count all the different tags |
541 | my $hash = $dom->find('*')->reduce(sub { $a->{$b->tag}++; $a }, {}); |
542 | |
543 | # Find elements with a class that contains dots |
544 | my @divs = $dom->find('div.foo\.bar')->each; |
545 | |
546 | =head2 following |
547 | |
548 | my $collection = $dom->following; |
549 | my $collection = $dom->following('div ~ p'); |
550 | |
551 | Find all sibling elements after this node matching the CSS selector and return |
8563f527 |
552 | a L<collection|/"COLLECTION METHODS"> containing these elements as L<DOM::Tiny> |
9a5f1e3f |
553 | objects. All selectors listen in L</"SELECTORS"> are supported. |
d6512b50 |
554 | |
555 | # List tags of sibling elements after this node |
556 | say $dom->following->map('tag')->join("\n"); |
557 | |
558 | =head2 following_nodes |
559 | |
560 | my $collection = $dom->following_nodes; |
561 | |
8563f527 |
562 | Return a L<collection|/"COLLECTION METHODS"> containing all sibling nodes after |
d6512b50 |
563 | this node as L<DOM::Tiny> objects. |
564 | |
565 | # "C" |
566 | $dom->parse('<p>A</p><!-- B -->C')->at('p')->following_nodes->last->content; |
567 | |
568 | =head2 matches |
569 | |
570 | my $bool = $dom->matches('div ~ p'); |
571 | |
9a5f1e3f |
572 | Check if this element matches the CSS selector. All selectors listed in |
573 | L</"SELECTORS"> are supported. |
d6512b50 |
574 | |
575 | # True |
576 | $dom->parse('<p class="a">A</p>')->at('p')->matches('.a'); |
577 | $dom->parse('<p class="a">A</p>')->at('p')->matches('p[class]'); |
578 | |
579 | # False |
580 | $dom->parse('<p class="a">A</p>')->at('p')->matches('.b'); |
581 | $dom->parse('<p class="a">A</p>')->at('p')->matches('p[id]'); |
582 | |
583 | =head2 namespace |
584 | |
585 | my $namespace = $dom->namespace; |
586 | |
587 | Find this element's namespace or return C<undef> if none could be found. |
588 | |
589 | # Find namespace for an element with namespace prefix |
590 | my $namespace = $dom->at('svg > svg\:circle')->namespace; |
591 | |
592 | # Find namespace for an element that may or may not have a namespace prefix |
593 | my $namespace = $dom->at('svg > circle')->namespace; |
594 | |
d6512b50 |
595 | =head2 next |
596 | |
597 | my $sibling = $dom->next; |
598 | |
599 | Return L<DOM::Tiny> object for next sibling element or C<undef> if there are no |
600 | more siblings. |
601 | |
602 | # "<h2>123</h2>" |
603 | $dom->parse('<div><h1>Test</h1><h2>123</h2></div>')->at('h1')->next; |
604 | |
605 | =head2 next_node |
606 | |
607 | my $sibling = $dom->next_node; |
608 | |
609 | Return L<DOM::Tiny> object for next sibling node or C<undef> if there are no |
610 | more siblings. |
611 | |
612 | # "456" |
613 | $dom->parse('<p><b>123</b><!-- Test -->456</p>') |
614 | ->at('b')->next_node->next_node; |
615 | |
616 | # " Test " |
617 | $dom->parse('<p><b>123</b><!-- Test -->456</p>') |
618 | ->at('b')->next_node->content; |
619 | |
620 | =head2 parent |
621 | |
622 | my $parent = $dom->parent; |
623 | |
624 | Return L<DOM::Tiny> object for parent of this node or C<undef> if this node has |
625 | no parent. |
626 | |
627 | =head2 parse |
628 | |
629 | $dom = $dom->parse('<foo bar="baz">I ♥ DOM::Tiny!</foo>'); |
630 | |
9a5f1e3f |
631 | Parse HTML/XML fragment. |
d6512b50 |
632 | |
633 | # Parse XML |
634 | my $dom = DOM::Tiny->new->xml(1)->parse($xml); |
635 | |
636 | =head2 preceding |
637 | |
638 | my $collection = $dom->preceding; |
639 | my $collection = $dom->preceding('div ~ p'); |
640 | |
641 | Find all sibling elements before this node matching the CSS selector and return |
8563f527 |
642 | a L<collection|/"COLLECTION METHODS"> containing these elements as L<DOM::Tiny> |
9a5f1e3f |
643 | objects. All selectors listed in L</"SELECTORS"> are supported. |
d6512b50 |
644 | |
645 | # List tags of sibling elements before this node |
646 | say $dom->preceding->map('tag')->join("\n"); |
647 | |
648 | =head2 preceding_nodes |
649 | |
650 | my $collection = $dom->preceding_nodes; |
651 | |
8563f527 |
652 | Return a L<collection|/"COLLECTION METHODS"> containing all sibling nodes |
653 | before this node as L<DOM::Tiny> objects. |
d6512b50 |
654 | |
655 | # "A" |
656 | $dom->parse('A<!-- B --><p>C</p>')->at('p')->preceding_nodes->first->content; |
657 | |
658 | =head2 prepend |
659 | |
660 | $dom = $dom->prepend('<p>I ♥ DOM::Tiny!</p>'); |
661 | |
662 | Prepend HTML/XML fragment to this node. |
663 | |
664 | # "<div><h1>Test</h1><h2>123</h2></div>" |
665 | $dom->parse('<div><h2>123</h2></div>') |
666 | ->at('h2')->prepend('<h1>Test</h1>')->root; |
667 | |
668 | # "<p>Test 123</p>" |
669 | $dom->parse('<p>123</p>') |
670 | ->at('p')->child_nodes->first->prepend('Test ')->root; |
671 | |
672 | =head2 prepend_content |
673 | |
674 | $dom = $dom->prepend_content('<p>I ♥ DOM::Tiny!</p>'); |
675 | |
676 | Prepend HTML/XML fragment (for C<root> and C<tag> nodes) or raw content to this |
677 | node's content. |
678 | |
679 | # "<div><h2>Test123</h2></div>" |
680 | $dom->parse('<div><h2>123</h2></div>') |
681 | ->at('h2')->prepend_content('Test')->root; |
682 | |
683 | # "<!-- Test 123 --><br>" |
684 | $dom->parse('<!-- 123 --><br>') |
685 | ->child_nodes->first->prepend_content(' Test')->root; |
686 | |
687 | # "<p><i>123</i>Test</p>" |
688 | $dom->parse('<p>Test</p>')->at('p')->prepend_content('<i>123</i>')->root; |
689 | |
690 | =head2 previous |
691 | |
692 | my $sibling = $dom->previous; |
693 | |
694 | Return L<DOM::Tiny> object for previous sibling element or C<undef> if there |
695 | are no more siblings. |
696 | |
697 | # "<h1>Test</h1>" |
698 | $dom->parse('<div><h1>Test</h1><h2>123</h2></div>')->at('h2')->previous; |
699 | |
700 | =head2 previous_node |
701 | |
702 | my $sibling = $dom->previous_node; |
703 | |
704 | Return L<DOM::Tiny> object for previous sibling node or C<undef> if there are |
705 | no more siblings. |
706 | |
707 | # "123" |
708 | $dom->parse('<p>123<!-- Test --><b>456</b></p>') |
709 | ->at('b')->previous_node->previous_node; |
710 | |
711 | # " Test " |
712 | $dom->parse('<p>123<!-- Test --><b>456</b></p>') |
713 | ->at('b')->previous_node->content; |
714 | |
715 | =head2 remove |
716 | |
717 | my $parent = $dom->remove; |
718 | |
719 | Remove this node and return L</"root"> (for C<root> nodes) or L</"parent">. |
720 | |
721 | # "<div></div>" |
722 | $dom->parse('<div><h1>Test</h1></div>')->at('h1')->remove; |
723 | |
724 | # "<p><b>456</b></p>" |
725 | $dom->parse('<p>123<b>456</b></p>') |
726 | ->at('p')->child_nodes->first->remove->root; |
727 | |
728 | =head2 replace |
729 | |
730 | my $parent = $dom->replace('<div>I ♥ DOM::Tiny!</div>'); |
731 | |
732 | Replace this node with HTML/XML fragment and return L</"root"> (for C<root> |
733 | nodes) or L</"parent">. |
734 | |
735 | # "<div><h2>123</h2></div>" |
736 | $dom->parse('<div><h1>Test</h1></div>')->at('h1')->replace('<h2>123</h2>'); |
737 | |
738 | # "<p><b>123</b></p>" |
739 | $dom->parse('<p>Test</p>') |
740 | ->at('p')->child_nodes->[0]->replace('<b>123</b>')->root; |
741 | |
742 | =head2 root |
743 | |
744 | my $root = $dom->root; |
745 | |
746 | Return L<DOM::Tiny> object for C<root> node. |
747 | |
748 | =head2 strip |
749 | |
750 | my $parent = $dom->strip; |
751 | |
752 | Remove this element while preserving its content and return L</"parent">. |
753 | |
754 | # "<div>Test</div>" |
755 | $dom->parse('<div><h1>Test</h1></div>')->at('h1')->strip; |
756 | |
757 | =head2 tag |
758 | |
759 | my $tag = $dom->tag; |
760 | $dom = $dom->tag('div'); |
761 | |
762 | This element's tag name. |
763 | |
764 | # List tag names of child elements |
765 | say $dom->children->map('tag')->join("\n"); |
766 | |
767 | =head2 tap |
768 | |
769 | $dom = $dom->tap(sub {...}); |
770 | |
e99ef07d |
771 | Equivalent to L<Mojo::Base/"tap">. |
d6512b50 |
772 | |
773 | =head2 text |
774 | |
775 | my $trimmed = $dom->text; |
776 | my $untrimmed = $dom->text(0); |
777 | |
778 | Extract text content from this element only (not including child elements), |
779 | smart whitespace trimming is enabled by default. |
780 | |
781 | # "foo baz" |
782 | $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->text; |
783 | |
784 | # "foo\nbaz\n" |
785 | $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->text(0); |
786 | |
787 | =head2 to_string |
788 | |
789 | my $str = $dom->to_string; |
790 | |
791 | Render this node and its content to HTML/XML. |
792 | |
793 | # "<b>Test</b>" |
794 | $dom->parse('<div><b>Test</b></div>')->at('div b')->to_string; |
795 | |
796 | =head2 tree |
797 | |
798 | my $tree = $dom->tree; |
799 | $dom = $dom->tree(['root']); |
800 | |
801 | Document Object Model. Note that this structure should only be used very |
802 | carefully since it is very dynamic. |
803 | |
804 | =head2 type |
805 | |
806 | my $type = $dom->type; |
807 | |
808 | This node's type, usually C<cdata>, C<comment>, C<doctype>, C<pi>, C<raw>, |
809 | C<root>, C<tag> or C<text>. |
810 | |
811 | # "cdata" |
812 | $dom->parse('<![CDATA[Test]]>')->child_nodes->first->type; |
813 | |
814 | # "comment" |
815 | $dom->parse('<!-- Test -->')->child_nodes->first->type; |
816 | |
817 | # "doctype" |
818 | $dom->parse('<!DOCTYPE html>')->child_nodes->first->type; |
819 | |
820 | # "pi" |
821 | $dom->parse('<?xml version="1.0"?>')->child_nodes->first->type; |
822 | |
823 | # "raw" |
824 | $dom->parse('<title>Test</title>')->at('title')->child_nodes->first->type; |
825 | |
826 | # "root" |
827 | $dom->parse('<p>Test</p>')->type; |
828 | |
829 | # "tag" |
830 | $dom->parse('<p>Test</p>')->at('p')->type; |
831 | |
832 | # "text" |
833 | $dom->parse('<p>Test</p>')->at('p')->child_nodes->first->type; |
834 | |
835 | =head2 val |
836 | |
837 | my $value = $dom->val; |
838 | |
839 | Extract value from form element (such as C<button>, C<input>, C<option>, |
840 | C<select> and C<textarea>) or return C<undef> if this element has no value. In |
841 | the case of C<select> with C<multiple> attribute, find C<option> elements with |
842 | C<selected> attribute and return an array reference with all values or C<undef> |
843 | if none could be found. |
844 | |
845 | # "a" |
846 | $dom->parse('<input name="test" value="a">')->at('input')->val; |
847 | |
848 | # "b" |
849 | $dom->parse('<textarea>b</textarea>')->at('textarea')->val; |
850 | |
851 | # "c" |
852 | $dom->parse('<option value="c">Test</option>')->at('option')->val; |
853 | |
854 | # "d" |
855 | $dom->parse('<select><option selected>d</option></select>') |
856 | ->at('select')->val; |
857 | |
858 | # "e" |
859 | $dom->parse('<select multiple><option selected>e</option></select>') |
860 | ->at('select')->val->[0]; |
861 | |
862 | =head2 wrap |
863 | |
864 | $dom = $dom->wrap('<div></div>'); |
865 | |
866 | Wrap HTML/XML fragment around this node, placing it as the last child of the |
867 | first innermost element. |
868 | |
869 | # "<p>123<b>Test</b></p>" |
870 | $dom->parse('<b>Test</b>')->at('b')->wrap('<p>123</p>')->root; |
871 | |
872 | # "<div><p><b>Test</b></p>123</div>" |
873 | $dom->parse('<b>Test</b>')->at('b')->wrap('<div><p></p>123</div>')->root; |
874 | |
875 | # "<p><b>Test</b></p><p>123</p>" |
876 | $dom->parse('<b>Test</b>')->at('b')->wrap('<p></p><p>123</p>')->root; |
877 | |
878 | # "<p><b>Test</b></p>" |
879 | $dom->parse('<p>Test</p>')->at('p')->child_nodes->first->wrap('<b>')->root; |
880 | |
881 | =head2 wrap_content |
882 | |
883 | $dom = $dom->wrap_content('<div></div>'); |
884 | |
885 | Wrap HTML/XML fragment around this node's content, placing it as the last |
886 | children of the first innermost element. |
887 | |
888 | # "<p><b>123Test</b></p>" |
889 | $dom->parse('<p>Test<p>')->at('p')->wrap_content('<b>123</b>')->root; |
890 | |
891 | # "<p><b>Test</b></p><p>123</p>" |
892 | $dom->parse('<b>Test</b>')->wrap_content('<p></p><p>123</p>'); |
893 | |
894 | =head2 xml |
895 | |
896 | my $bool = $dom->xml; |
897 | $dom = $dom->xml($bool); |
898 | |
899 | Disable HTML semantics in parser and activate case-sensitivity, defaults to |
900 | auto detection based on processing instructions. |
901 | |
78ba4051 |
902 | =head1 COLLECTION METHODS |
903 | |
9a5f1e3f |
904 | Some L<DOM::Tiny> methods return an array-based collection object based on |
905 | L<Mojo::Collection>, which can either be accessed directly as an array |
906 | reference, or with the following methods. |
78ba4051 |
907 | |
908 | # Chain methods |
909 | $collection->map(sub { ucfirst })->shuffle->each(sub { |
910 | my ($word, $num) = @_; |
911 | say "$num: $word"; |
912 | }); |
913 | |
914 | # Access array directly to manipulate collection |
915 | $collection->[23] += 100; |
916 | say for @$collection; |
917 | |
918 | =head2 compact |
919 | |
920 | my $new = $collection->compact; |
921 | |
922 | Create a new collection with all elements that are defined and not an empty |
923 | string. |
924 | |
925 | # $collection contains (0, 1, undef, 2, '', 3) |
926 | $collection->compact->join(', '); # "0, 1, 2, 3" |
927 | |
928 | =head2 each |
929 | |
930 | my @elements = $collection->each; |
931 | $collection = $collection->each(sub {...}); |
932 | |
933 | Evaluate callback for each element in collection or return all elements as a |
934 | list if none has been provided. The element will be the first argument passed |
935 | to the callback and is also available as C<$_>. |
936 | |
937 | # Make a numbered list |
938 | $collection->each(sub { |
939 | my ($e, $num) = @_; |
940 | say "$num: $e"; |
941 | }); |
942 | |
943 | =head2 first |
944 | |
945 | my $first = $collection->first; |
946 | my $first = $collection->first(qr/foo/); |
947 | my $first = $collection->first(sub {...}); |
948 | my $first = $collection->first($method); |
949 | my $first = $collection->first($method, @args); |
950 | |
951 | Evaluate regular expression/callback for, or call method on, each element in |
952 | collection and return the first one that matched the regular expression, or for |
953 | which the callback/method returned true. The element will be the first argument |
954 | passed to the callback and is also available as C<$_>. |
955 | |
956 | # Longer version |
957 | my $first = $collection->first(sub { $_->$method(@args) }); |
958 | |
c7bc4d31 |
959 | # Find first value that contains the word "tiny" |
960 | my $interesting = $collection->first(qr/tiny/i); |
78ba4051 |
961 | |
962 | # Find first value that is greater than 5 |
963 | my $greater = $collection->first(sub { $_ > 5 }); |
964 | |
965 | =head2 flatten |
966 | |
967 | my $new = $collection->flatten; |
968 | |
969 | Flatten nested collections/arrays recursively and create a new collection with |
970 | all elements. |
971 | |
972 | # $collection contains (1, [2, [3, 4], 5, [6]], 7) |
973 | $collection->flatten->join(', '); # "1, 2, 3, 4, 5, 6, 7" |
974 | |
975 | =head2 grep |
976 | |
977 | my $new = $collection->grep(qr/foo/); |
978 | my $new = $collection->grep(sub {...}); |
979 | my $new = $collection->grep($method); |
980 | my $new = $collection->grep($method, @args); |
981 | |
982 | Evaluate regular expression/callback for, or call method on, each element in |
983 | collection and create a new collection with all elements that matched the |
984 | regular expression, or for which the callback/method returned true. The element |
985 | will be the first argument passed to the callback and is also available as |
986 | C<$_>. |
987 | |
988 | # Longer version |
989 | my $new = $collection->grep(sub { $_->$method(@args) }); |
990 | |
c7bc4d31 |
991 | # Find all values that contain the word "tiny" |
992 | my $interesting = $collection->grep(qr/tiny/i); |
78ba4051 |
993 | |
994 | # Find all values that are greater than 5 |
995 | my $greater = $collection->grep(sub { $_ > 5 }); |
996 | |
997 | =head2 join |
998 | |
999 | my $stream = $collection->join; |
1000 | my $stream = $collection->join("\n"); |
1001 | |
1002 | Turn collection into string. |
1003 | |
1004 | # Join all values with commas |
1005 | $collection->join(', '); |
1006 | |
1007 | =head2 last |
1008 | |
1009 | my $last = $collection->last; |
1010 | |
1011 | Return the last element in collection. |
1012 | |
1013 | =head2 map |
1014 | |
1015 | my $new = $collection->map(sub {...}); |
1016 | my $new = $collection->map($method); |
1017 | my $new = $collection->map($method, @args); |
1018 | |
1019 | Evaluate callback for, or call method on, each element in collection and create |
1020 | a new collection from the results. The element will be the first argument |
1021 | passed to the callback and is also available as C<$_>. |
1022 | |
1023 | # Longer version |
1024 | my $new = $collection->map(sub { $_->$method(@args) }); |
1025 | |
c7bc4d31 |
1026 | # Append the word "tiny" to all values |
1027 | my $domified = $collection->map(sub { $_ . 'tiny' }); |
78ba4051 |
1028 | |
1029 | =head2 reduce |
1030 | |
1031 | my $result = $collection->reduce(sub {...}); |
1032 | my $result = $collection->reduce(sub {...}, $initial); |
1033 | |
1034 | Reduce elements in collection with callback, the first element will be used as |
1035 | initial value if none has been provided. |
1036 | |
1037 | # Calculate the sum of all values |
1038 | my $sum = $collection->reduce(sub { $a + $b }); |
1039 | |
1040 | # Count how often each value occurs in collection |
1041 | my $hash = $collection->reduce(sub { $a->{$b}++; $a }, {}); |
1042 | |
1043 | =head2 reverse |
1044 | |
1045 | my $new = $collection->reverse; |
1046 | |
1047 | Create a new collection with all elements in reverse order. |
1048 | |
1049 | =head2 slice |
1050 | |
1051 | my $new = $collection->slice(4 .. 7); |
1052 | |
1053 | Create a new collection with all selected elements. |
1054 | |
1055 | # $collection contains ('A', 'B', 'C', 'D', 'E') |
1056 | $collection->slice(1, 2, 4)->join(' '); # "B C E" |
1057 | |
1058 | =head2 shuffle |
1059 | |
1060 | my $new = $collection->shuffle; |
1061 | |
1062 | Create a new collection with all elements in random order. |
1063 | |
1064 | =head2 size |
1065 | |
1066 | my $size = $collection->size; |
1067 | |
1068 | Number of elements in collection. |
1069 | |
1070 | =head2 sort |
1071 | |
1072 | my $new = $collection->sort; |
1073 | my $new = $collection->sort(sub {...}); |
1074 | |
1075 | Sort elements based on return value of callback and create a new collection |
1076 | from the results. |
1077 | |
1078 | # Sort values case-insensitive |
1079 | my $case_insensitive = $collection->sort(sub { uc($a) cmp uc($b) }); |
1080 | |
1081 | =head2 tap |
1082 | |
1083 | $collection = $collection->tap(sub {...}); |
1084 | |
1085 | Equivalent to L<Mojo::Base/"tap">. |
1086 | |
1087 | =head2 to_array |
1088 | |
1089 | my $array = $collection->to_array; |
1090 | |
1091 | Turn collection into array reference. |
1092 | |
1093 | =head2 uniq |
1094 | |
1095 | my $new = $collection->uniq; |
1096 | my $new = $collection->uniq(sub {...}); |
1097 | my $new = $collection->uniq($method); |
1098 | my $new = $collection->uniq($method, @args); |
1099 | |
1100 | Create a new collection without duplicate elements, using the string |
1101 | representation of either the elements or the return value of the |
1102 | callback/method. |
1103 | |
1104 | # Longer version |
1105 | my $new = $collection->uniq(sub { $_->$method(@args) }); |
1106 | |
1107 | # $collection contains ('foo', 'bar', 'bar', 'baz') |
1108 | $collection->uniq->join(' '); # "foo bar baz" |
1109 | |
1110 | # $collection contains ([1, 2], [2, 1], [3, 2]) |
1111 | $collection->uniq(sub{ $_->[1] })->to_array; # "[[1, 2], [2, 1]]" |
1112 | |
d6512b50 |
1113 | =head1 BUGS |
1114 | |
1115 | Report any issues on the public bugtracker. |
1116 | |
1117 | =head1 AUTHOR |
1118 | |
1119 | Dan Book <dbook@cpan.org> |
1120 | |
1121 | =head1 COPYRIGHT AND LICENSE |
1122 | |
1123 | This software is Copyright (c) 2015 by Dan Book. |
1124 | |
1125 | This is free software, licensed under: |
1126 | |
1127 | The Artistic License 2.0 (GPL Compatible) |
1128 | |
1129 | =head1 SEE ALSO |
1130 | |
31877452 |
1131 | L<Mojo::DOM>, L<HTML::TreeBuilder>, L<XML::LibXML>, L<XML::Twig>, L<XML::Smart> |
d6512b50 |
1132 | |
9a5f1e3f |
1133 | =for Pod::Coverage TO_JSON |
1134 | |
d6512b50 |
1135 | =cut |