Commit | Line | Data |
a292be34 |
1 | package DOM::Tiny; |
2 | |
3 | use strict; |
4 | use warnings; |
5 | |
d6512b50 |
6 | use overload |
7 | '@{}' => sub { shift->child_nodes }, |
8 | '%{}' => sub { shift->attr }, |
9 | bool => sub {1}, |
10 | '""' => sub { shift->to_string }, |
11 | fallback => 1; |
12 | |
13 | use Carp 'croak'; |
78ba4051 |
14 | use DOM::Tiny::_Collection; |
9a5f1e3f |
15 | use DOM::Tiny::_CSS; |
16 | use DOM::Tiny::_HTML; |
d6512b50 |
17 | use Scalar::Util qw(blessed weaken); |
18 | |
22cfa6c8 |
19 | our $VERSION = '0.004'; |
a292be34 |
20 | |
3793c28f |
21 | sub new { |
22 | my $class = shift; |
9a5f1e3f |
23 | my $self = bless \DOM::Tiny::_HTML->new, ref $class || $class; |
3793c28f |
24 | return @_ ? $self->parse(@_) : $self; |
25 | } |
26 | |
78ba4051 |
27 | sub TO_JSON { shift->_delegate('render') } |
28 | |
d6512b50 |
29 | sub all_text { shift->_all_text(1, @_) } |
30 | |
31 | sub ancestors { _select($_[0]->_collect($_[0]->_ancestors), $_[1]) } |
32 | |
33 | sub append { shift->_add(1, @_) } |
34 | sub append_content { shift->_content(1, 0, @_) } |
35 | |
36 | sub at { |
37 | my $self = shift; |
38 | return undef unless my $result = $self->_css->select_one(@_); |
39 | return $self->_build($result, $self->xml); |
40 | } |
41 | |
42 | sub attr { |
43 | my $self = shift; |
44 | |
45 | # Hash |
46 | my $tree = $self->tree; |
47 | my $attrs = $tree->[0] ne 'tag' ? {} : $tree->[2]; |
48 | return $attrs unless @_; |
49 | |
50 | # Get |
51 | return $attrs->{$_[0]} unless @_ > 1 || ref $_[0]; |
52 | |
53 | # Set |
54 | my $values = ref $_[0] ? $_[0] : {@_}; |
55 | @$attrs{keys %$values} = values %$values; |
56 | |
57 | return $self; |
58 | } |
59 | |
60 | sub child_nodes { $_[0]->_collect(_nodes($_[0]->tree)) } |
61 | |
62 | sub children { _select($_[0]->_collect(_nodes($_[0]->tree, 1)), $_[1]) } |
63 | |
64 | sub content { |
65 | my $self = shift; |
66 | |
67 | my $type = $self->type; |
68 | if ($type eq 'root' || $type eq 'tag') { |
69 | return $self->_content(0, 1, @_) if @_; |
9a5f1e3f |
70 | my $html = DOM::Tiny::_HTML->new(xml => $self->xml); |
d6512b50 |
71 | return join '', map { $html->tree($_)->render } _nodes($self->tree); |
72 | } |
73 | |
74 | return $self->tree->[1] unless @_; |
75 | $self->tree->[1] = shift; |
76 | return $self; |
77 | } |
78 | |
79 | sub descendant_nodes { $_[0]->_collect(_all(_nodes($_[0]->tree))) } |
80 | |
81 | sub find { $_[0]->_collect(@{$_[0]->_css->select($_[1])}) } |
82 | |
83 | sub following { _select($_[0]->_collect(@{$_[0]->_siblings(1)->[1]}), $_[1]) } |
84 | sub following_nodes { $_[0]->_collect(@{$_[0]->_siblings->[1]}) } |
85 | |
86 | sub matches { shift->_css->matches(@_) } |
87 | |
88 | sub namespace { |
89 | my $self = shift; |
90 | |
91 | return undef if (my $tree = $self->tree)->[0] ne 'tag'; |
92 | |
93 | # Extract namespace prefix and search parents |
94 | my $ns = $tree->[1] =~ /^(.*?):/ ? "xmlns:$1" : undef; |
95 | for my $node ($tree, $self->_ancestors) { |
96 | |
97 | # Namespace for prefix |
98 | my $attrs = $node->[2]; |
99 | if ($ns) { $_ eq $ns and return $attrs->{$_} for keys %$attrs } |
100 | |
101 | # Namespace attribute |
102 | elsif (defined $attrs->{xmlns}) { return $attrs->{xmlns} } |
103 | } |
104 | |
105 | return undef; |
106 | } |
107 | |
d6512b50 |
108 | sub next { $_[0]->_maybe($_[0]->_siblings(1, 0)->[1]) } |
109 | sub next_node { $_[0]->_maybe($_[0]->_siblings(0, 0)->[1]) } |
110 | |
111 | sub parent { |
112 | my $self = shift; |
113 | return undef if $self->tree->[0] eq 'root'; |
114 | return $self->_build($self->_parent, $self->xml); |
115 | } |
116 | |
117 | sub parse { shift->_delegate(parse => @_) } |
118 | |
119 | sub preceding { _select($_[0]->_collect(@{$_[0]->_siblings(1)->[0]}), $_[1]) } |
120 | sub preceding_nodes { $_[0]->_collect(@{$_[0]->_siblings->[0]}) } |
121 | |
122 | sub prepend { shift->_add(0, @_) } |
123 | sub prepend_content { shift->_content(0, 0, @_) } |
124 | |
125 | sub previous { $_[0]->_maybe($_[0]->_siblings(1, -1)->[0]) } |
126 | sub previous_node { $_[0]->_maybe($_[0]->_siblings(0, -1)->[0]) } |
127 | |
128 | sub remove { shift->replace('') } |
129 | |
130 | sub replace { |
131 | my ($self, $new) = @_; |
132 | return $self->parse($new) if (my $tree = $self->tree)->[0] eq 'root'; |
133 | return $self->_replace($self->_parent, $tree, _nodes($self->_parse($new))); |
134 | } |
135 | |
136 | sub root { |
137 | my $self = shift; |
138 | return $self unless my $tree = $self->_ancestors(1); |
139 | return $self->_build($tree, $self->xml); |
140 | } |
141 | |
142 | sub strip { |
143 | my $self = shift; |
144 | return $self if (my $tree = $self->tree)->[0] ne 'tag'; |
145 | return $self->_replace($tree->[3], $tree, _nodes($tree)); |
146 | } |
147 | |
148 | sub tag { |
149 | my ($self, $tag) = @_; |
150 | return undef if (my $tree = $self->tree)->[0] ne 'tag'; |
151 | return $tree->[1] unless $tag; |
152 | $tree->[1] = $tag; |
153 | return $self; |
154 | } |
155 | |
1644a3ee |
156 | sub tap { DOM::Tiny::_Collection::tap(@_) } |
d6512b50 |
157 | |
158 | sub text { shift->_all_text(0, @_) } |
159 | |
160 | sub to_string { shift->_delegate('render') } |
161 | |
162 | sub tree { shift->_delegate(tree => @_) } |
163 | |
164 | sub type { shift->tree->[0] } |
165 | |
166 | sub val { |
167 | my $self = shift; |
168 | |
169 | # "option" |
2d9f5165 |
170 | return defined($self->{value}) ? $self->{value} : $self->text |
171 | if (my $tag = $self->tag) eq 'option'; |
d6512b50 |
172 | |
4b5e2513 |
173 | # "input" ("type=checkbox" and "type=radio") |
174 | my $type = $self->{type} || ''; |
175 | return defined $self->{value} ? $self->{value} : 'on' |
176 | if $tag eq 'input' && ($type eq 'radio' || $type eq 'checkbox'); |
177 | |
d6512b50 |
178 | # "textarea", "input" or "button" |
179 | return $tag eq 'textarea' ? $self->text : $self->{value} if $tag ne 'select'; |
180 | |
181 | # "select" |
182 | my $v = $self->find('option:checked')->map('val'); |
183 | return exists $self->{multiple} ? $v->size ? $v->to_array : undef : $v->last; |
184 | } |
185 | |
186 | sub wrap { shift->_wrap(0, @_) } |
187 | sub wrap_content { shift->_wrap(1, @_) } |
188 | |
189 | sub xml { shift->_delegate(xml => @_) } |
190 | |
191 | sub _add { |
192 | my ($self, $offset, $new) = @_; |
193 | |
194 | return $self if (my $tree = $self->tree)->[0] eq 'root'; |
195 | |
196 | my $parent = $self->_parent; |
197 | splice @$parent, _offset($parent, $tree) + $offset, 0, |
198 | _link($parent, _nodes($self->_parse($new))); |
199 | |
200 | return $self; |
201 | } |
202 | |
203 | sub _all { |
204 | map { $_->[0] eq 'tag' ? ($_, _all(_nodes($_))) : ($_) } @_; |
205 | } |
206 | |
207 | sub _all_text { |
208 | my ($self, $recurse, $trim) = @_; |
209 | |
210 | # Detect "pre" tag |
211 | my $tree = $self->tree; |
212 | $trim = 1 unless defined $trim; |
213 | map { $_->[1] eq 'pre' and $trim = 0 } $self->_ancestors, $tree |
214 | if $trim && $tree->[0] ne 'root'; |
215 | |
216 | return _text([_nodes($tree)], $recurse, $trim); |
217 | } |
218 | |
219 | sub _ancestors { |
220 | my ($self, $root) = @_; |
221 | |
4c89d5f3 |
222 | return () unless my $tree = $self->_parent; |
d6512b50 |
223 | my @ancestors; |
224 | do { push @ancestors, $tree } |
225 | while ($tree->[0] eq 'tag') && ($tree = $tree->[3]); |
226 | return $root ? $ancestors[-1] : @ancestors[0 .. $#ancestors - 1]; |
227 | } |
228 | |
229 | sub _build { shift->new->tree(shift)->xml(shift) } |
230 | |
231 | sub _collect { |
232 | my $self = shift; |
233 | my $xml = $self->xml; |
78ba4051 |
234 | return DOM::Tiny::_Collection->new(map { $self->_build($_, $xml) } @_); |
d6512b50 |
235 | } |
236 | |
237 | sub _content { |
238 | my ($self, $start, $offset, $new) = @_; |
239 | |
240 | my $tree = $self->tree; |
241 | unless ($tree->[0] eq 'root' || $tree->[0] eq 'tag') { |
242 | my $old = $self->content; |
4b5e2513 |
243 | return $self->content($start ? $old . $new : $new . $old); |
d6512b50 |
244 | } |
245 | |
246 | $start = $start ? ($#$tree + 1) : _start($tree); |
247 | $offset = $offset ? $#$tree : 0; |
248 | splice @$tree, $start, $offset, _link($tree, _nodes($self->_parse($new))); |
249 | |
250 | return $self; |
251 | } |
252 | |
9a5f1e3f |
253 | sub _css { DOM::Tiny::_CSS->new(tree => shift->tree) } |
d6512b50 |
254 | |
255 | sub _delegate { |
256 | my ($self, $method) = (shift, shift); |
257 | return $$self->$method unless @_; |
258 | $$self->$method(@_); |
259 | return $self; |
260 | } |
261 | |
262 | sub _link { |
263 | my ($parent, @children) = @_; |
264 | |
265 | # Link parent to children |
266 | for my $node (@children) { |
267 | my $offset = $node->[0] eq 'tag' ? 3 : 2; |
268 | $node->[$offset] = $parent; |
269 | weaken $node->[$offset]; |
270 | } |
271 | |
272 | return @children; |
273 | } |
274 | |
275 | sub _maybe { $_[1] ? $_[0]->_build($_[1], $_[0]->xml) : undef } |
276 | |
277 | sub _nodes { |
4c89d5f3 |
278 | return () unless my $tree = shift; |
d6512b50 |
279 | my @nodes = @$tree[_start($tree) .. $#$tree]; |
280 | return shift() ? grep { $_->[0] eq 'tag' } @nodes : @nodes; |
281 | } |
282 | |
283 | sub _offset { |
284 | my ($parent, $child) = @_; |
285 | my $i = _start($parent); |
286 | $_ eq $child ? last : $i++ for @$parent[$i .. $#$parent]; |
287 | return $i; |
288 | } |
289 | |
290 | sub _parent { $_[0]->tree->[$_[0]->type eq 'tag' ? 3 : 2] } |
291 | |
9a5f1e3f |
292 | sub _parse { DOM::Tiny::_HTML->new(xml => shift->xml)->parse(shift)->tree } |
d6512b50 |
293 | |
294 | sub _replace { |
927f1351 |
295 | my ($self, $parent, $child, @nodes) = @_; |
296 | splice @$parent, _offset($parent, $child), 1, _link($parent, @nodes); |
d6512b50 |
297 | return $self->parent; |
298 | } |
299 | |
300 | sub _select { |
301 | my ($collection, $selector) = @_; |
302 | return $collection unless $selector; |
303 | return $collection->new(grep { $_->matches($selector) } @$collection); |
304 | } |
305 | |
306 | sub _siblings { |
307 | my ($self, $tags, $i) = @_; |
308 | |
309 | return [] unless my $parent = $self->parent; |
310 | |
311 | my $tree = $self->tree; |
312 | my (@before, @after, $match); |
313 | for my $node (_nodes($parent->tree)) { |
314 | ++$match and next if !$match && $node eq $tree; |
315 | next if $tags && $node->[0] ne 'tag'; |
316 | $match ? push @after, $node : push @before, $node; |
317 | } |
318 | |
319 | return defined $i ? [$before[$i], $after[$i]] : [\@before, \@after]; |
320 | } |
321 | |
322 | sub _squish { |
323 | my $str = shift; |
324 | $str =~ s/^\s+//; |
325 | $str =~ s/\s+$//; |
326 | $str =~ s/\s+/ /g; |
327 | return $str; |
328 | } |
329 | |
330 | sub _start { $_[0][0] eq 'root' ? 1 : 4 } |
331 | |
332 | sub _text { |
333 | my ($nodes, $recurse, $trim) = @_; |
334 | |
335 | # Merge successive text nodes |
336 | my $i = 0; |
337 | while (my $next = $nodes->[$i + 1]) { |
338 | ++$i and next unless $nodes->[$i][0] eq 'text' && $next->[0] eq 'text'; |
339 | splice @$nodes, $i, 2, ['text', $nodes->[$i][1] . $next->[1]]; |
340 | } |
341 | |
342 | my $text = ''; |
343 | for my $node (@$nodes) { |
344 | my $type = $node->[0]; |
345 | |
346 | # Text |
347 | my $chunk = ''; |
348 | if ($type eq 'text') { $chunk = $trim ? _squish $node->[1] : $node->[1] } |
349 | |
350 | # CDATA or raw text |
351 | elsif ($type eq 'cdata' || $type eq 'raw') { $chunk = $node->[1] } |
352 | |
353 | # Nested tag |
354 | elsif ($type eq 'tag' && $recurse) { |
355 | no warnings 'recursion'; |
356 | $chunk = _text([_nodes($node)], 1, $node->[1] eq 'pre' ? 0 : $trim); |
357 | } |
358 | |
359 | # Add leading whitespace if punctuation allows it |
360 | $chunk = " $chunk" if $text =~ /\S\z/ && $chunk =~ /^[^.!?,;:\s]+/; |
361 | |
362 | # Trim whitespace blocks |
363 | $text .= $chunk if $chunk =~ /\S+/ || !$trim; |
364 | } |
365 | |
366 | return $text; |
367 | } |
368 | |
369 | sub _wrap { |
370 | my ($self, $content, $new) = @_; |
371 | |
c7cad649 |
372 | return $self if (my $tree = $self->tree)->[0] eq 'root' && !$content; |
373 | return $self if $tree->[0] ne 'root' && $tree->[0] ne 'tag' && $content; |
d6512b50 |
374 | |
375 | # Find innermost tag |
376 | my $current; |
377 | my $first = $new = $self->_parse($new); |
378 | $current = $first while $first = (_nodes($first, 1))[0]; |
379 | return $self unless $current; |
380 | |
381 | # Wrap content |
382 | if ($content) { |
383 | push @$current, _link($current, _nodes($tree)); |
384 | splice @$tree, _start($tree), $#$tree, _link($tree, _nodes($new)); |
385 | return $self; |
386 | } |
387 | |
388 | # Wrap element |
389 | $self->_replace($self->_parent, $tree, _nodes($new)); |
390 | push @$current, _link($current, $tree); |
391 | return $self; |
392 | } |
393 | |
a292be34 |
394 | 1; |
395 | |
d6512b50 |
396 | =encoding utf8 |
397 | |
a292be34 |
398 | =head1 NAME |
399 | |
d6512b50 |
400 | DOM::Tiny - Minimalistic HTML/XML DOM parser with CSS selectors |
a292be34 |
401 | |
402 | =head1 SYNOPSIS |
403 | |
d6512b50 |
404 | use DOM::Tiny; |
405 | |
406 | # Parse |
407 | my $dom = DOM::Tiny->new('<div><p id="a">Test</p><p id="b">123</p></div>'); |
408 | |
409 | # Find |
410 | say $dom->at('#b')->text; |
411 | say $dom->find('p')->map('text')->join("\n"); |
412 | say $dom->find('[id]')->map(attr => 'id')->join("\n"); |
413 | |
414 | # Iterate |
415 | $dom->find('p[id]')->reverse->each(sub { say $_->{id} }); |
416 | |
417 | # Loop |
418 | for my $e ($dom->find('p[id]')->each) { |
419 | say $e->{id}, ':', $e->text; |
420 | } |
421 | |
422 | # Modify |
423 | $dom->find('div p')->last->append('<p id="c">456</p>'); |
424 | $dom->find(':not(p)')->map('strip'); |
425 | |
426 | # Render |
427 | say "$dom"; |
428 | |
a292be34 |
429 | =head1 DESCRIPTION |
430 | |
9a5f1e3f |
431 | L<DOM::Tiny> is a minimalistic and relaxed pure-perl HTML/XML DOM parser based |
432 | on L<Mojo::DOM>. It supports the L<HTML Living Standard|https://html.spec.whatwg.org/> |
433 | and L<Extensible Markup Language (XML) 1.0|http://www.w3.org/TR/xml/>, and |
434 | matching based on L<CSS3 selectors|http://www.w3.org/TR/selectors/>. It will |
435 | even try to interpret broken HTML and XML, so you should not use it for |
5a70ee9d |
436 | validation. |
d6512b50 |
437 | |
438 | =head1 NODES AND ELEMENTS |
439 | |
440 | When we parse an HTML/XML fragment, it gets turned into a tree of nodes. |
441 | |
442 | <!DOCTYPE html> |
443 | <html> |
444 | <head><title>Hello</title></head> |
445 | <body>World!</body> |
446 | </html> |
447 | |
448 | There are currently eight different kinds of nodes, C<cdata>, C<comment>, |
449 | C<doctype>, C<pi>, C<raw>, C<root>, C<tag> and C<text>. Elements are nodes of |
450 | the type C<tag>. |
451 | |
452 | root |
453 | |- doctype (html) |
454 | +- tag (html) |
455 | |- tag (head) |
456 | | +- tag (title) |
457 | | +- raw (Hello) |
458 | +- tag (body) |
459 | +- text (World!) |
460 | |
461 | While all node types are represented as L<DOM::Tiny> objects, some methods like |
462 | L</"attr"> and L</"namespace"> only apply to elements. |
463 | |
464 | =head1 CASE-SENSITIVITY |
465 | |
466 | L<DOM::Tiny> defaults to HTML semantics, that means all tags and attribute |
467 | names are lowercased and selectors need to be lowercase as well. |
468 | |
469 | # HTML semantics |
470 | my $dom = DOM::Tiny->new('<P ID="greeting">Hi!</P>'); |
471 | say $dom->at('p[id]')->text; |
472 | |
eb9737f2 |
473 | If an XML declaration is found, the parser will automatically switch into XML |
474 | mode and everything becomes case-sensitive. |
d6512b50 |
475 | |
476 | # XML semantics |
477 | my $dom = DOM::Tiny->new('<?xml version="1.0"?><P ID="greeting">Hi!</P>'); |
478 | say $dom->at('P[ID]')->text; |
479 | |
480 | XML detection can also be disabled with the L</"xml"> method. |
481 | |
482 | # Force XML semantics |
483 | my $dom = DOM::Tiny->new->xml(1)->parse('<P ID="greeting">Hi!</P>'); |
484 | say $dom->at('P[ID]')->text; |
485 | |
486 | # Force HTML semantics |
487 | my $dom = DOM::Tiny->new->xml(0)->parse('<P ID="greeting">Hi!</P>'); |
488 | say $dom->at('p[id]')->text; |
489 | |
63873d67 |
490 | =head1 SELECTORS |
491 | |
492 | L<DOM::Tiny> uses a CSS selector engine based on L<Mojo::DOM::CSS>. All CSS |
493 | selectors that make sense for a standalone parser are supported. |
494 | |
03eb5521 |
495 | =over |
496 | |
497 | =item Z<>* |
63873d67 |
498 | |
499 | Any element. |
500 | |
501 | my $all = $dom->find('*'); |
502 | |
03eb5521 |
503 | =item E |
63873d67 |
504 | |
505 | An element of type C<E>. |
506 | |
507 | my $title = $dom->at('title'); |
508 | |
03eb5521 |
509 | =item E[foo] |
63873d67 |
510 | |
511 | An C<E> element with a C<foo> attribute. |
512 | |
513 | my $links = $dom->find('a[href]'); |
514 | |
03eb5521 |
515 | =item E[foo="bar"] |
63873d67 |
516 | |
517 | An C<E> element whose C<foo> attribute value is exactly equal to C<bar>. |
518 | |
519 | my $case_sensitive = $dom->find('input[type="hidden"]'); |
520 | my $case_sensitive = $dom->find('input[type=hidden]'); |
521 | |
03eb5521 |
522 | =item E[foo="bar" i] |
63873d67 |
523 | |
524 | An C<E> element whose C<foo> attribute value is exactly equal to any |
525 | (ASCII-range) case-permutation of C<bar>. Note that this selector is |
526 | EXPERIMENTAL and might change without warning! |
527 | |
528 | my $case_insensitive = $dom->find('input[type="hidden" i]'); |
529 | my $case_insensitive = $dom->find('input[type=hidden i]'); |
530 | my $case_insensitive = $dom->find('input[class~="foo" i]'); |
531 | |
532 | This selector is part of |
533 | L<Selectors Level 4|http://dev.w3.org/csswg/selectors-4>, which is still a work |
534 | in progress. |
535 | |
03eb5521 |
536 | =item E[foo~="bar"] |
63873d67 |
537 | |
538 | An C<E> element whose C<foo> attribute value is a list of whitespace-separated |
539 | values, one of which is exactly equal to C<bar>. |
540 | |
541 | my $foo = $dom->find('input[class~="foo"]'); |
542 | my $foo = $dom->find('input[class~=foo]'); |
543 | |
03eb5521 |
544 | =item E[foo^="bar"] |
63873d67 |
545 | |
546 | An C<E> element whose C<foo> attribute value begins exactly with the string |
547 | C<bar>. |
548 | |
549 | my $begins_with = $dom->find('input[name^="f"]'); |
550 | my $begins_with = $dom->find('input[name^=f]'); |
551 | |
03eb5521 |
552 | =item E[foo$="bar"] |
63873d67 |
553 | |
554 | An C<E> element whose C<foo> attribute value ends exactly with the string |
555 | C<bar>. |
556 | |
557 | my $ends_with = $dom->find('input[name$="o"]'); |
558 | my $ends_with = $dom->find('input[name$=o]'); |
559 | |
03eb5521 |
560 | =item E[foo*="bar"] |
63873d67 |
561 | |
562 | An C<E> element whose C<foo> attribute value contains the substring C<bar>. |
563 | |
564 | my $contains = $dom->find('input[name*="fo"]'); |
565 | my $contains = $dom->find('input[name*=fo]'); |
566 | |
03eb5521 |
567 | =item E:root |
63873d67 |
568 | |
569 | An C<E> element, root of the document. |
570 | |
571 | my $root = $dom->at(':root'); |
572 | |
03eb5521 |
573 | =item E:nth-child(n) |
63873d67 |
574 | |
575 | An C<E> element, the C<n-th> child of its parent. |
576 | |
577 | my $third = $dom->find('div:nth-child(3)'); |
578 | my $odd = $dom->find('div:nth-child(odd)'); |
579 | my $even = $dom->find('div:nth-child(even)'); |
580 | my $top3 = $dom->find('div:nth-child(-n+3)'); |
581 | |
03eb5521 |
582 | =item E:nth-last-child(n) |
63873d67 |
583 | |
584 | An C<E> element, the C<n-th> child of its parent, counting from the last one. |
585 | |
586 | my $third = $dom->find('div:nth-last-child(3)'); |
587 | my $odd = $dom->find('div:nth-last-child(odd)'); |
588 | my $even = $dom->find('div:nth-last-child(even)'); |
589 | my $bottom3 = $dom->find('div:nth-last-child(-n+3)'); |
590 | |
03eb5521 |
591 | =item E:nth-of-type(n) |
63873d67 |
592 | |
593 | An C<E> element, the C<n-th> sibling of its type. |
594 | |
595 | my $third = $dom->find('div:nth-of-type(3)'); |
596 | my $odd = $dom->find('div:nth-of-type(odd)'); |
597 | my $even = $dom->find('div:nth-of-type(even)'); |
598 | my $top3 = $dom->find('div:nth-of-type(-n+3)'); |
599 | |
03eb5521 |
600 | =item E:nth-last-of-type(n) |
63873d67 |
601 | |
602 | An C<E> element, the C<n-th> sibling of its type, counting from the last one. |
603 | |
604 | my $third = $dom->find('div:nth-last-of-type(3)'); |
605 | my $odd = $dom->find('div:nth-last-of-type(odd)'); |
606 | my $even = $dom->find('div:nth-last-of-type(even)'); |
607 | my $bottom3 = $dom->find('div:nth-last-of-type(-n+3)'); |
608 | |
03eb5521 |
609 | =item E:first-child |
63873d67 |
610 | |
611 | An C<E> element, first child of its parent. |
612 | |
613 | my $first = $dom->find('div p:first-child'); |
614 | |
03eb5521 |
615 | =item E:last-child |
63873d67 |
616 | |
617 | An C<E> element, last child of its parent. |
618 | |
619 | my $last = $dom->find('div p:last-child'); |
620 | |
03eb5521 |
621 | =item E:first-of-type |
63873d67 |
622 | |
623 | An C<E> element, first sibling of its type. |
624 | |
625 | my $first = $dom->find('div p:first-of-type'); |
626 | |
03eb5521 |
627 | =item E:last-of-type |
63873d67 |
628 | |
629 | An C<E> element, last sibling of its type. |
630 | |
631 | my $last = $dom->find('div p:last-of-type'); |
632 | |
03eb5521 |
633 | =item E:only-child |
63873d67 |
634 | |
635 | An C<E> element, only child of its parent. |
636 | |
637 | my $lonely = $dom->find('div p:only-child'); |
638 | |
03eb5521 |
639 | =item E:only-of-type |
63873d67 |
640 | |
641 | An C<E> element, only sibling of its type. |
642 | |
643 | my $lonely = $dom->find('div p:only-of-type'); |
644 | |
03eb5521 |
645 | =item E:empty |
63873d67 |
646 | |
647 | An C<E> element that has no children (including text nodes). |
648 | |
649 | my $empty = $dom->find(':empty'); |
650 | |
03eb5521 |
651 | =item E:checked |
63873d67 |
652 | |
653 | A user interface element C<E> which is checked (for instance a radio-button or |
654 | checkbox). |
655 | |
656 | my $input = $dom->find(':checked'); |
657 | |
03eb5521 |
658 | =item E.warning |
63873d67 |
659 | |
660 | An C<E> element whose class is "warning". |
661 | |
662 | my $warning = $dom->find('div.warning'); |
663 | |
03eb5521 |
664 | =item E#myid |
63873d67 |
665 | |
666 | An C<E> element with C<ID> equal to "myid". |
667 | |
668 | my $foo = $dom->at('div#foo'); |
669 | |
03eb5521 |
670 | =item E:not(s) |
63873d67 |
671 | |
672 | An C<E> element that does not match simple selector C<s>. |
673 | |
674 | my $others = $dom->find('div p:not(:first-child)'); |
675 | |
03eb5521 |
676 | =item E F |
63873d67 |
677 | |
678 | An C<F> element descendant of an C<E> element. |
679 | |
680 | my $headlines = $dom->find('div h1'); |
681 | |
03eb5521 |
682 | =item E E<gt> F |
63873d67 |
683 | |
684 | An C<F> element child of an C<E> element. |
685 | |
686 | my $headlines = $dom->find('html > body > div > h1'); |
687 | |
03eb5521 |
688 | =item E + F |
63873d67 |
689 | |
690 | An C<F> element immediately preceded by an C<E> element. |
691 | |
692 | my $second = $dom->find('h1 + h2'); |
693 | |
03eb5521 |
694 | =item E ~ F |
63873d67 |
695 | |
696 | An C<F> element preceded by an C<E> element. |
697 | |
698 | my $second = $dom->find('h1 ~ h2'); |
699 | |
03eb5521 |
700 | =item E, F, G |
63873d67 |
701 | |
702 | Elements of type C<E>, C<F> and C<G>. |
703 | |
704 | my $headlines = $dom->find('h1, h2, h3'); |
705 | |
03eb5521 |
706 | =item E[foo=bar][bar=baz] |
63873d67 |
707 | |
708 | An C<E> element whose attributes match all following attribute selectors. |
709 | |
710 | my $links = $dom->find('a[foo^=b][foo$=ar]'); |
711 | |
03eb5521 |
712 | =back |
713 | |
9a5f1e3f |
714 | =head1 OPERATORS |
715 | |
716 | L<DOM::Tiny> overloads the following operators. |
717 | |
718 | =head2 array |
719 | |
720 | my @nodes = @$dom; |
721 | |
722 | Alias for L</"child_nodes">. |
723 | |
724 | # "<!-- Test -->" |
725 | $dom->parse('<!-- Test --><b>123</b>')->[0]; |
726 | |
727 | =head2 bool |
728 | |
729 | my $bool = !!$dom; |
730 | |
731 | Always true. |
732 | |
733 | =head2 hash |
734 | |
735 | my %attrs = %$dom; |
736 | |
737 | Alias for L</"attr">. |
738 | |
739 | # "test" |
740 | $dom->parse('<div id="test">Test</div>')->at('div')->{id}; |
741 | |
742 | =head2 stringify |
743 | |
744 | my $str = "$dom"; |
745 | |
746 | Alias for L</"to_string">. |
747 | |
d6512b50 |
748 | =head1 METHODS |
749 | |
750 | L<DOM::Tiny> implements the following methods. |
751 | |
3793c28f |
752 | =head2 new |
753 | |
754 | my $dom = DOM::Tiny->new; |
755 | my $dom = DOM::Tiny->new('<foo bar="baz">I ♥ DOM::Tiny!</foo>'); |
756 | |
757 | Construct a new scalar-based L<DOM::Tiny> object and L</"parse"> HTML/XML |
758 | fragment if necessary. |
759 | |
d6512b50 |
760 | =head2 all_text |
761 | |
762 | my $trimmed = $dom->all_text; |
763 | my $untrimmed = $dom->all_text(0); |
764 | |
765 | Extract text content from all descendant nodes of this element, smart |
766 | whitespace trimming is enabled by default. |
767 | |
768 | # "foo bar baz" |
769 | $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->all_text; |
770 | |
771 | # "foo\nbarbaz\n" |
772 | $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->all_text(0); |
773 | |
774 | =head2 ancestors |
775 | |
776 | my $collection = $dom->ancestors; |
777 | my $collection = $dom->ancestors('div ~ p'); |
778 | |
779 | Find all ancestor elements of this node matching the CSS selector and return a |
8563f527 |
780 | L<collection|/"COLLECTION METHODS"> containing these elements as L<DOM::Tiny> |
9a5f1e3f |
781 | objects. All selectors listed in L</"SELECTORS"> are supported. |
d6512b50 |
782 | |
783 | # List tag names of ancestor elements |
784 | say $dom->ancestors->map('tag')->join("\n"); |
785 | |
786 | =head2 append |
787 | |
788 | $dom = $dom->append('<p>I ♥ DOM::Tiny!</p>'); |
789 | |
c7cad649 |
790 | Append HTML/XML fragment to this node (for all node types other than C<root>). |
d6512b50 |
791 | |
792 | # "<div><h1>Test</h1><h2>123</h2></div>" |
793 | $dom->parse('<div><h1>Test</h1></div>') |
794 | ->at('h1')->append('<h2>123</h2>')->root; |
795 | |
796 | # "<p>Test 123</p>" |
797 | $dom->parse('<p>Test</p>')->at('p') |
798 | ->child_nodes->first->append(' 123')->root; |
799 | |
800 | =head2 append_content |
801 | |
802 | $dom = $dom->append_content('<p>I ♥ DOM::Tiny!</p>'); |
803 | |
804 | Append HTML/XML fragment (for C<root> and C<tag> nodes) or raw content to this |
805 | node's content. |
806 | |
807 | # "<div><h1>Test123</h1></div>" |
808 | $dom->parse('<div><h1>Test</h1></div>') |
809 | ->at('h1')->append_content('123')->root; |
810 | |
811 | # "<!-- Test 123 --><br>" |
812 | $dom->parse('<!-- Test --><br>') |
813 | ->child_nodes->first->append_content('123 ')->root; |
814 | |
815 | # "<p>Test<i>123</i></p>" |
816 | $dom->parse('<p>Test</p>')->at('p')->append_content('<i>123</i>')->root; |
817 | |
818 | =head2 at |
819 | |
820 | my $result = $dom->at('div ~ p'); |
821 | |
822 | Find first descendant element of this element matching the CSS selector and |
eb9737f2 |
823 | return it as a L<DOM::Tiny> object, or C<undef> if none could be found. All |
824 | selectors listed in L</"SELECTORS"> are supported. |
d6512b50 |
825 | |
826 | # Find first element with "svg" namespace definition |
827 | my $namespace = $dom->at('[xmlns\:svg]')->{'xmlns:svg'}; |
828 | |
829 | =head2 attr |
830 | |
831 | my $hash = $dom->attr; |
832 | my $foo = $dom->attr('foo'); |
833 | $dom = $dom->attr({foo => 'bar'}); |
834 | $dom = $dom->attr(foo => 'bar'); |
835 | |
836 | This element's attributes. |
837 | |
838 | # Remove an attribute |
839 | delete $dom->attr->{id}; |
840 | |
841 | # Attribute without value |
842 | $dom->attr(selected => undef); |
843 | |
844 | # List id attributes |
845 | say $dom->find('*')->map(attr => 'id')->compact->join("\n"); |
846 | |
847 | =head2 child_nodes |
848 | |
849 | my $collection = $dom->child_nodes; |
850 | |
8563f527 |
851 | Return a L<collection|/"COLLECTION METHODS"> containing all child nodes of this |
d6512b50 |
852 | element as L<DOM::Tiny> objects. |
853 | |
854 | # "<p><b>123</b></p>" |
855 | $dom->parse('<p>Test<b>123</b></p>')->at('p')->child_nodes->first->remove; |
856 | |
857 | # "<!DOCTYPE html>" |
858 | $dom->parse('<!DOCTYPE html><b>123</b>')->child_nodes->first; |
859 | |
860 | # " Test " |
861 | $dom->parse('<b>123</b><!-- Test -->')->child_nodes->last->content; |
862 | |
863 | =head2 children |
864 | |
865 | my $collection = $dom->children; |
866 | my $collection = $dom->children('div ~ p'); |
867 | |
868 | Find all child elements of this element matching the CSS selector and return a |
8563f527 |
869 | L<collection|/"COLLECTION METHODS"> containing these elements as L<DOM::Tiny> |
9a5f1e3f |
870 | objects. All selectors listed in L</"SELECTORS"> are supported. |
d6512b50 |
871 | |
872 | # Show tag name of random child element |
873 | say $dom->children->shuffle->first->tag; |
874 | |
875 | =head2 content |
876 | |
877 | my $str = $dom->content; |
878 | $dom = $dom->content('<p>I ♥ DOM::Tiny!</p>'); |
879 | |
880 | Return this node's content or replace it with HTML/XML fragment (for C<root> |
881 | and C<tag> nodes) or raw content. |
882 | |
883 | # "<b>Test</b>" |
884 | $dom->parse('<div><b>Test</b></div>')->at('div')->content; |
885 | |
886 | # "<div><h1>123</h1></div>" |
887 | $dom->parse('<div><h1>Test</h1></div>')->at('h1')->content('123')->root; |
888 | |
889 | # "<p><i>123</i></p>" |
890 | $dom->parse('<p>Test</p>')->at('p')->content('<i>123</i>')->root; |
891 | |
892 | # "<div><h1></h1></div>" |
893 | $dom->parse('<div><h1>Test</h1></div>')->at('h1')->content('')->root; |
894 | |
895 | # " Test " |
896 | $dom->parse('<!-- Test --><br>')->child_nodes->first->content; |
897 | |
898 | # "<div><!-- 123 -->456</div>" |
899 | $dom->parse('<div><!-- Test -->456</div>') |
900 | ->at('div')->child_nodes->first->content(' 123 ')->root; |
901 | |
902 | =head2 descendant_nodes |
903 | |
904 | my $collection = $dom->descendant_nodes; |
905 | |
8563f527 |
906 | Return a L<collection|/"COLLECTION METHODS"> containing all descendant nodes of |
d6512b50 |
907 | this element as L<DOM::Tiny> objects. |
908 | |
909 | # "<p><b>123</b></p>" |
910 | $dom->parse('<p><!-- Test --><b>123<!-- 456 --></b></p>') |
911 | ->descendant_nodes->grep(sub { $_->type eq 'comment' }) |
912 | ->map('remove')->first; |
913 | |
914 | # "<p><b>test</b>test</p>" |
915 | $dom->parse('<p><b>123</b>456</p>') |
916 | ->at('p')->descendant_nodes->grep(sub { $_->type eq 'text' }) |
917 | ->map(content => 'test')->first->root; |
918 | |
919 | =head2 find |
920 | |
921 | my $collection = $dom->find('div ~ p'); |
922 | |
923 | Find all descendant elements of this element matching the CSS selector and |
8563f527 |
924 | return a L<collection|/"COLLECTION METHODS"> containing these elements as |
9a5f1e3f |
925 | L<DOM::Tiny> objects. All selectors listed in L</"SELECTORS"> are supported. |
d6512b50 |
926 | |
927 | # Find a specific element and extract information |
928 | my $id = $dom->find('div')->[23]{id}; |
929 | |
930 | # Extract information from multiple elements |
931 | my @headers = $dom->find('h1, h2, h3')->map('text')->each; |
932 | |
933 | # Count all the different tags |
934 | my $hash = $dom->find('*')->reduce(sub { $a->{$b->tag}++; $a }, {}); |
935 | |
936 | # Find elements with a class that contains dots |
937 | my @divs = $dom->find('div.foo\.bar')->each; |
938 | |
939 | =head2 following |
940 | |
941 | my $collection = $dom->following; |
942 | my $collection = $dom->following('div ~ p'); |
943 | |
944 | Find all sibling elements after this node matching the CSS selector and return |
8563f527 |
945 | a L<collection|/"COLLECTION METHODS"> containing these elements as L<DOM::Tiny> |
9a5f1e3f |
946 | objects. All selectors listen in L</"SELECTORS"> are supported. |
d6512b50 |
947 | |
948 | # List tags of sibling elements after this node |
949 | say $dom->following->map('tag')->join("\n"); |
950 | |
951 | =head2 following_nodes |
952 | |
953 | my $collection = $dom->following_nodes; |
954 | |
8563f527 |
955 | Return a L<collection|/"COLLECTION METHODS"> containing all sibling nodes after |
d6512b50 |
956 | this node as L<DOM::Tiny> objects. |
957 | |
958 | # "C" |
959 | $dom->parse('<p>A</p><!-- B -->C')->at('p')->following_nodes->last->content; |
960 | |
961 | =head2 matches |
962 | |
963 | my $bool = $dom->matches('div ~ p'); |
964 | |
9a5f1e3f |
965 | Check if this element matches the CSS selector. All selectors listed in |
966 | L</"SELECTORS"> are supported. |
d6512b50 |
967 | |
968 | # True |
969 | $dom->parse('<p class="a">A</p>')->at('p')->matches('.a'); |
970 | $dom->parse('<p class="a">A</p>')->at('p')->matches('p[class]'); |
971 | |
972 | # False |
973 | $dom->parse('<p class="a">A</p>')->at('p')->matches('.b'); |
974 | $dom->parse('<p class="a">A</p>')->at('p')->matches('p[id]'); |
975 | |
976 | =head2 namespace |
977 | |
978 | my $namespace = $dom->namespace; |
979 | |
eb9737f2 |
980 | Find this element's namespace, or return C<undef> if none could be found. |
d6512b50 |
981 | |
982 | # Find namespace for an element with namespace prefix |
983 | my $namespace = $dom->at('svg > svg\:circle')->namespace; |
984 | |
985 | # Find namespace for an element that may or may not have a namespace prefix |
986 | my $namespace = $dom->at('svg > circle')->namespace; |
987 | |
d6512b50 |
988 | =head2 next |
989 | |
990 | my $sibling = $dom->next; |
991 | |
eb9737f2 |
992 | Return L<DOM::Tiny> object for next sibling element, or C<undef> if there are |
993 | no more siblings. |
d6512b50 |
994 | |
995 | # "<h2>123</h2>" |
996 | $dom->parse('<div><h1>Test</h1><h2>123</h2></div>')->at('h1')->next; |
997 | |
998 | =head2 next_node |
999 | |
1000 | my $sibling = $dom->next_node; |
1001 | |
eb9737f2 |
1002 | Return L<DOM::Tiny> object for next sibling node, or C<undef> if there are no |
d6512b50 |
1003 | more siblings. |
1004 | |
1005 | # "456" |
1006 | $dom->parse('<p><b>123</b><!-- Test -->456</p>') |
1007 | ->at('b')->next_node->next_node; |
1008 | |
1009 | # " Test " |
1010 | $dom->parse('<p><b>123</b><!-- Test -->456</p>') |
1011 | ->at('b')->next_node->content; |
1012 | |
1013 | =head2 parent |
1014 | |
1015 | my $parent = $dom->parent; |
1016 | |
eb9737f2 |
1017 | Return L<DOM::Tiny> object for parent of this node, or C<undef> if this node |
1018 | has no parent. |
1019 | |
1020 | # "<b><i>Test</i></b>" |
1021 | $dom->parse('<p><b><i>Test</i></b></p>')->at('i')->parent; |
d6512b50 |
1022 | |
1023 | =head2 parse |
1024 | |
1025 | $dom = $dom->parse('<foo bar="baz">I ♥ DOM::Tiny!</foo>'); |
1026 | |
9a5f1e3f |
1027 | Parse HTML/XML fragment. |
d6512b50 |
1028 | |
1029 | # Parse XML |
eb9737f2 |
1030 | my $dom = DOM::Tiny->new->xml(1)->parse('<foo>I ♥ DOM::Tiny!</foo>'); |
d6512b50 |
1031 | |
1032 | =head2 preceding |
1033 | |
1034 | my $collection = $dom->preceding; |
1035 | my $collection = $dom->preceding('div ~ p'); |
1036 | |
1037 | Find all sibling elements before this node matching the CSS selector and return |
8563f527 |
1038 | a L<collection|/"COLLECTION METHODS"> containing these elements as L<DOM::Tiny> |
9a5f1e3f |
1039 | objects. All selectors listed in L</"SELECTORS"> are supported. |
d6512b50 |
1040 | |
1041 | # List tags of sibling elements before this node |
1042 | say $dom->preceding->map('tag')->join("\n"); |
1043 | |
1044 | =head2 preceding_nodes |
1045 | |
1046 | my $collection = $dom->preceding_nodes; |
1047 | |
8563f527 |
1048 | Return a L<collection|/"COLLECTION METHODS"> containing all sibling nodes |
1049 | before this node as L<DOM::Tiny> objects. |
d6512b50 |
1050 | |
1051 | # "A" |
1052 | $dom->parse('A<!-- B --><p>C</p>')->at('p')->preceding_nodes->first->content; |
1053 | |
1054 | =head2 prepend |
1055 | |
1056 | $dom = $dom->prepend('<p>I ♥ DOM::Tiny!</p>'); |
1057 | |
c7cad649 |
1058 | Prepend HTML/XML fragment to this node (for all node types other than C<root>). |
d6512b50 |
1059 | |
1060 | # "<div><h1>Test</h1><h2>123</h2></div>" |
1061 | $dom->parse('<div><h2>123</h2></div>') |
1062 | ->at('h2')->prepend('<h1>Test</h1>')->root; |
1063 | |
1064 | # "<p>Test 123</p>" |
1065 | $dom->parse('<p>123</p>') |
1066 | ->at('p')->child_nodes->first->prepend('Test ')->root; |
1067 | |
1068 | =head2 prepend_content |
1069 | |
1070 | $dom = $dom->prepend_content('<p>I ♥ DOM::Tiny!</p>'); |
1071 | |
1072 | Prepend HTML/XML fragment (for C<root> and C<tag> nodes) or raw content to this |
1073 | node's content. |
1074 | |
1075 | # "<div><h2>Test123</h2></div>" |
1076 | $dom->parse('<div><h2>123</h2></div>') |
1077 | ->at('h2')->prepend_content('Test')->root; |
1078 | |
1079 | # "<!-- Test 123 --><br>" |
1080 | $dom->parse('<!-- 123 --><br>') |
1081 | ->child_nodes->first->prepend_content(' Test')->root; |
1082 | |
1083 | # "<p><i>123</i>Test</p>" |
1084 | $dom->parse('<p>Test</p>')->at('p')->prepend_content('<i>123</i>')->root; |
1085 | |
1086 | =head2 previous |
1087 | |
1088 | my $sibling = $dom->previous; |
1089 | |
eb9737f2 |
1090 | Return L<DOM::Tiny> object for previous sibling element, or C<undef> if there |
d6512b50 |
1091 | are no more siblings. |
1092 | |
1093 | # "<h1>Test</h1>" |
1094 | $dom->parse('<div><h1>Test</h1><h2>123</h2></div>')->at('h2')->previous; |
1095 | |
1096 | =head2 previous_node |
1097 | |
1098 | my $sibling = $dom->previous_node; |
1099 | |
eb9737f2 |
1100 | Return L<DOM::Tiny> object for previous sibling node, or C<undef> if there are |
d6512b50 |
1101 | no more siblings. |
1102 | |
1103 | # "123" |
1104 | $dom->parse('<p>123<!-- Test --><b>456</b></p>') |
1105 | ->at('b')->previous_node->previous_node; |
1106 | |
1107 | # " Test " |
1108 | $dom->parse('<p>123<!-- Test --><b>456</b></p>') |
1109 | ->at('b')->previous_node->content; |
1110 | |
1111 | =head2 remove |
1112 | |
1113 | my $parent = $dom->remove; |
1114 | |
1115 | Remove this node and return L</"root"> (for C<root> nodes) or L</"parent">. |
1116 | |
1117 | # "<div></div>" |
1118 | $dom->parse('<div><h1>Test</h1></div>')->at('h1')->remove; |
1119 | |
1120 | # "<p><b>456</b></p>" |
1121 | $dom->parse('<p>123<b>456</b></p>') |
1122 | ->at('p')->child_nodes->first->remove->root; |
1123 | |
1124 | =head2 replace |
1125 | |
1126 | my $parent = $dom->replace('<div>I ♥ DOM::Tiny!</div>'); |
1127 | |
1128 | Replace this node with HTML/XML fragment and return L</"root"> (for C<root> |
1129 | nodes) or L</"parent">. |
1130 | |
1131 | # "<div><h2>123</h2></div>" |
1132 | $dom->parse('<div><h1>Test</h1></div>')->at('h1')->replace('<h2>123</h2>'); |
1133 | |
1134 | # "<p><b>123</b></p>" |
1135 | $dom->parse('<p>Test</p>') |
1136 | ->at('p')->child_nodes->[0]->replace('<b>123</b>')->root; |
1137 | |
1138 | =head2 root |
1139 | |
1140 | my $root = $dom->root; |
1141 | |
1142 | Return L<DOM::Tiny> object for C<root> node. |
1143 | |
1144 | =head2 strip |
1145 | |
1146 | my $parent = $dom->strip; |
1147 | |
1148 | Remove this element while preserving its content and return L</"parent">. |
1149 | |
1150 | # "<div>Test</div>" |
1151 | $dom->parse('<div><h1>Test</h1></div>')->at('h1')->strip; |
1152 | |
1153 | =head2 tag |
1154 | |
1155 | my $tag = $dom->tag; |
1156 | $dom = $dom->tag('div'); |
1157 | |
1158 | This element's tag name. |
1159 | |
1160 | # List tag names of child elements |
1161 | say $dom->children->map('tag')->join("\n"); |
1162 | |
1163 | =head2 tap |
1164 | |
1165 | $dom = $dom->tap(sub {...}); |
1166 | |
e99ef07d |
1167 | Equivalent to L<Mojo::Base/"tap">. |
d6512b50 |
1168 | |
1169 | =head2 text |
1170 | |
1171 | my $trimmed = $dom->text; |
1172 | my $untrimmed = $dom->text(0); |
1173 | |
1174 | Extract text content from this element only (not including child elements), |
1175 | smart whitespace trimming is enabled by default. |
1176 | |
1177 | # "foo baz" |
1178 | $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->text; |
1179 | |
1180 | # "foo\nbaz\n" |
1181 | $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->text(0); |
1182 | |
1183 | =head2 to_string |
1184 | |
1185 | my $str = $dom->to_string; |
1186 | |
1187 | Render this node and its content to HTML/XML. |
1188 | |
1189 | # "<b>Test</b>" |
1190 | $dom->parse('<div><b>Test</b></div>')->at('div b')->to_string; |
1191 | |
1192 | =head2 tree |
1193 | |
1194 | my $tree = $dom->tree; |
1195 | $dom = $dom->tree(['root']); |
1196 | |
1197 | Document Object Model. Note that this structure should only be used very |
1198 | carefully since it is very dynamic. |
1199 | |
1200 | =head2 type |
1201 | |
1202 | my $type = $dom->type; |
1203 | |
1204 | This node's type, usually C<cdata>, C<comment>, C<doctype>, C<pi>, C<raw>, |
1205 | C<root>, C<tag> or C<text>. |
1206 | |
1207 | # "cdata" |
1208 | $dom->parse('<![CDATA[Test]]>')->child_nodes->first->type; |
1209 | |
1210 | # "comment" |
1211 | $dom->parse('<!-- Test -->')->child_nodes->first->type; |
1212 | |
1213 | # "doctype" |
1214 | $dom->parse('<!DOCTYPE html>')->child_nodes->first->type; |
1215 | |
1216 | # "pi" |
1217 | $dom->parse('<?xml version="1.0"?>')->child_nodes->first->type; |
1218 | |
1219 | # "raw" |
1220 | $dom->parse('<title>Test</title>')->at('title')->child_nodes->first->type; |
1221 | |
1222 | # "root" |
1223 | $dom->parse('<p>Test</p>')->type; |
1224 | |
1225 | # "tag" |
1226 | $dom->parse('<p>Test</p>')->at('p')->type; |
1227 | |
1228 | # "text" |
1229 | $dom->parse('<p>Test</p>')->at('p')->child_nodes->first->type; |
1230 | |
1231 | =head2 val |
1232 | |
1233 | my $value = $dom->val; |
1234 | |
1235 | Extract value from form element (such as C<button>, C<input>, C<option>, |
eb9737f2 |
1236 | C<select> and C<textarea>), or return C<undef> if this element has no value. In |
d6512b50 |
1237 | the case of C<select> with C<multiple> attribute, find C<option> elements with |
eb9737f2 |
1238 | C<selected> attribute and return an array reference with all values, or |
1239 | C<undef> if none could be found. |
d6512b50 |
1240 | |
1241 | # "a" |
4b5e2513 |
1242 | $dom->parse('<input name=test value=a>')->at('input')->val; |
d6512b50 |
1243 | |
1244 | # "b" |
1245 | $dom->parse('<textarea>b</textarea>')->at('textarea')->val; |
1246 | |
1247 | # "c" |
1248 | $dom->parse('<option value="c">Test</option>')->at('option')->val; |
1249 | |
1250 | # "d" |
1251 | $dom->parse('<select><option selected>d</option></select>') |
1252 | ->at('select')->val; |
1253 | |
1254 | # "e" |
1255 | $dom->parse('<select multiple><option selected>e</option></select>') |
1256 | ->at('select')->val->[0]; |
1257 | |
4b5e2513 |
1258 | # "on" |
1259 | $dom->parse('<input name=test type=checkbox>')->at('input')->val; |
1260 | |
d6512b50 |
1261 | =head2 wrap |
1262 | |
1263 | $dom = $dom->wrap('<div></div>'); |
1264 | |
c7cad649 |
1265 | Wrap HTML/XML fragment around this node (for all node types other than C<root>), |
1266 | placing it as the last child of the first innermost element. |
d6512b50 |
1267 | |
1268 | # "<p>123<b>Test</b></p>" |
1269 | $dom->parse('<b>Test</b>')->at('b')->wrap('<p>123</p>')->root; |
1270 | |
1271 | # "<div><p><b>Test</b></p>123</div>" |
1272 | $dom->parse('<b>Test</b>')->at('b')->wrap('<div><p></p>123</div>')->root; |
1273 | |
1274 | # "<p><b>Test</b></p><p>123</p>" |
1275 | $dom->parse('<b>Test</b>')->at('b')->wrap('<p></p><p>123</p>')->root; |
1276 | |
1277 | # "<p><b>Test</b></p>" |
1278 | $dom->parse('<p>Test</p>')->at('p')->child_nodes->first->wrap('<b>')->root; |
1279 | |
1280 | =head2 wrap_content |
1281 | |
1282 | $dom = $dom->wrap_content('<div></div>'); |
1283 | |
c7cad649 |
1284 | Wrap HTML/XML fragment around this node's content (for C<root> and C<tag> |
1285 | nodes), placing it as the last children of the first innermost element. |
d6512b50 |
1286 | |
1287 | # "<p><b>123Test</b></p>" |
1288 | $dom->parse('<p>Test<p>')->at('p')->wrap_content('<b>123</b>')->root; |
1289 | |
1290 | # "<p><b>Test</b></p><p>123</p>" |
1291 | $dom->parse('<b>Test</b>')->wrap_content('<p></p><p>123</p>'); |
1292 | |
1293 | =head2 xml |
1294 | |
1295 | my $bool = $dom->xml; |
1296 | $dom = $dom->xml($bool); |
1297 | |
1298 | Disable HTML semantics in parser and activate case-sensitivity, defaults to |
eb9737f2 |
1299 | auto detection based on XML declarations. |
d6512b50 |
1300 | |
78ba4051 |
1301 | =head1 COLLECTION METHODS |
1302 | |
9a5f1e3f |
1303 | Some L<DOM::Tiny> methods return an array-based collection object based on |
1304 | L<Mojo::Collection>, which can either be accessed directly as an array |
1305 | reference, or with the following methods. |
78ba4051 |
1306 | |
1307 | # Chain methods |
1308 | $collection->map(sub { ucfirst })->shuffle->each(sub { |
1309 | my ($word, $num) = @_; |
1310 | say "$num: $word"; |
1311 | }); |
1312 | |
1313 | # Access array directly to manipulate collection |
1314 | $collection->[23] += 100; |
1315 | say for @$collection; |
1316 | |
1317 | =head2 compact |
1318 | |
1319 | my $new = $collection->compact; |
1320 | |
1321 | Create a new collection with all elements that are defined and not an empty |
1322 | string. |
1323 | |
1324 | # $collection contains (0, 1, undef, 2, '', 3) |
1325 | $collection->compact->join(', '); # "0, 1, 2, 3" |
1326 | |
1327 | =head2 each |
1328 | |
1329 | my @elements = $collection->each; |
1330 | $collection = $collection->each(sub {...}); |
1331 | |
1332 | Evaluate callback for each element in collection or return all elements as a |
1333 | list if none has been provided. The element will be the first argument passed |
1334 | to the callback and is also available as C<$_>. |
1335 | |
1336 | # Make a numbered list |
1337 | $collection->each(sub { |
1338 | my ($e, $num) = @_; |
1339 | say "$num: $e"; |
1340 | }); |
1341 | |
1342 | =head2 first |
1343 | |
1344 | my $first = $collection->first; |
1345 | my $first = $collection->first(qr/foo/); |
1346 | my $first = $collection->first(sub {...}); |
1347 | my $first = $collection->first($method); |
1348 | my $first = $collection->first($method, @args); |
1349 | |
1350 | Evaluate regular expression/callback for, or call method on, each element in |
1351 | collection and return the first one that matched the regular expression, or for |
1352 | which the callback/method returned true. The element will be the first argument |
1353 | passed to the callback and is also available as C<$_>. |
1354 | |
1355 | # Longer version |
1356 | my $first = $collection->first(sub { $_->$method(@args) }); |
1357 | |
c7bc4d31 |
1358 | # Find first value that contains the word "tiny" |
1359 | my $interesting = $collection->first(qr/tiny/i); |
78ba4051 |
1360 | |
1361 | # Find first value that is greater than 5 |
1362 | my $greater = $collection->first(sub { $_ > 5 }); |
1363 | |
1364 | =head2 flatten |
1365 | |
1366 | my $new = $collection->flatten; |
1367 | |
1368 | Flatten nested collections/arrays recursively and create a new collection with |
1369 | all elements. |
1370 | |
1371 | # $collection contains (1, [2, [3, 4], 5, [6]], 7) |
1372 | $collection->flatten->join(', '); # "1, 2, 3, 4, 5, 6, 7" |
1373 | |
1374 | =head2 grep |
1375 | |
1376 | my $new = $collection->grep(qr/foo/); |
1377 | my $new = $collection->grep(sub {...}); |
1378 | my $new = $collection->grep($method); |
1379 | my $new = $collection->grep($method, @args); |
1380 | |
1381 | Evaluate regular expression/callback for, or call method on, each element in |
1382 | collection and create a new collection with all elements that matched the |
1383 | regular expression, or for which the callback/method returned true. The element |
1384 | will be the first argument passed to the callback and is also available as |
1385 | C<$_>. |
1386 | |
1387 | # Longer version |
1388 | my $new = $collection->grep(sub { $_->$method(@args) }); |
1389 | |
c7bc4d31 |
1390 | # Find all values that contain the word "tiny" |
1391 | my $interesting = $collection->grep(qr/tiny/i); |
78ba4051 |
1392 | |
1393 | # Find all values that are greater than 5 |
1394 | my $greater = $collection->grep(sub { $_ > 5 }); |
1395 | |
1396 | =head2 join |
1397 | |
1398 | my $stream = $collection->join; |
1399 | my $stream = $collection->join("\n"); |
1400 | |
1401 | Turn collection into string. |
1402 | |
1403 | # Join all values with commas |
1404 | $collection->join(', '); |
1405 | |
1406 | =head2 last |
1407 | |
1408 | my $last = $collection->last; |
1409 | |
1410 | Return the last element in collection. |
1411 | |
1412 | =head2 map |
1413 | |
1414 | my $new = $collection->map(sub {...}); |
1415 | my $new = $collection->map($method); |
1416 | my $new = $collection->map($method, @args); |
1417 | |
1418 | Evaluate callback for, or call method on, each element in collection and create |
1419 | a new collection from the results. The element will be the first argument |
1420 | passed to the callback and is also available as C<$_>. |
1421 | |
1422 | # Longer version |
1423 | my $new = $collection->map(sub { $_->$method(@args) }); |
1424 | |
c7bc4d31 |
1425 | # Append the word "tiny" to all values |
1426 | my $domified = $collection->map(sub { $_ . 'tiny' }); |
78ba4051 |
1427 | |
1428 | =head2 reduce |
1429 | |
1430 | my $result = $collection->reduce(sub {...}); |
1431 | my $result = $collection->reduce(sub {...}, $initial); |
1432 | |
1433 | Reduce elements in collection with callback, the first element will be used as |
1434 | initial value if none has been provided. |
1435 | |
1436 | # Calculate the sum of all values |
1437 | my $sum = $collection->reduce(sub { $a + $b }); |
1438 | |
1439 | # Count how often each value occurs in collection |
1440 | my $hash = $collection->reduce(sub { $a->{$b}++; $a }, {}); |
1441 | |
1442 | =head2 reverse |
1443 | |
1444 | my $new = $collection->reverse; |
1445 | |
1446 | Create a new collection with all elements in reverse order. |
1447 | |
1448 | =head2 slice |
1449 | |
1450 | my $new = $collection->slice(4 .. 7); |
1451 | |
1452 | Create a new collection with all selected elements. |
1453 | |
1454 | # $collection contains ('A', 'B', 'C', 'D', 'E') |
1455 | $collection->slice(1, 2, 4)->join(' '); # "B C E" |
1456 | |
1457 | =head2 shuffle |
1458 | |
1459 | my $new = $collection->shuffle; |
1460 | |
1461 | Create a new collection with all elements in random order. |
1462 | |
1463 | =head2 size |
1464 | |
1465 | my $size = $collection->size; |
1466 | |
1467 | Number of elements in collection. |
1468 | |
1469 | =head2 sort |
1470 | |
1471 | my $new = $collection->sort; |
1472 | my $new = $collection->sort(sub {...}); |
1473 | |
1474 | Sort elements based on return value of callback and create a new collection |
1475 | from the results. |
1476 | |
1477 | # Sort values case-insensitive |
1478 | my $case_insensitive = $collection->sort(sub { uc($a) cmp uc($b) }); |
1479 | |
1480 | =head2 tap |
1481 | |
1482 | $collection = $collection->tap(sub {...}); |
1483 | |
1484 | Equivalent to L<Mojo::Base/"tap">. |
1485 | |
1486 | =head2 to_array |
1487 | |
1488 | my $array = $collection->to_array; |
1489 | |
1490 | Turn collection into array reference. |
1491 | |
1492 | =head2 uniq |
1493 | |
1494 | my $new = $collection->uniq; |
1495 | my $new = $collection->uniq(sub {...}); |
1496 | my $new = $collection->uniq($method); |
1497 | my $new = $collection->uniq($method, @args); |
1498 | |
1499 | Create a new collection without duplicate elements, using the string |
1500 | representation of either the elements or the return value of the |
1501 | callback/method. |
1502 | |
1503 | # Longer version |
1504 | my $new = $collection->uniq(sub { $_->$method(@args) }); |
1505 | |
1506 | # $collection contains ('foo', 'bar', 'bar', 'baz') |
1507 | $collection->uniq->join(' '); # "foo bar baz" |
1508 | |
1509 | # $collection contains ([1, 2], [2, 1], [3, 2]) |
1510 | $collection->uniq(sub{ $_->[1] })->to_array; # "[[1, 2], [2, 1]]" |
1511 | |
a292be34 |
1512 | =head1 BUGS |
1513 | |
1514 | Report any issues on the public bugtracker. |
1515 | |
1516 | =head1 AUTHOR |
1517 | |
1518 | Dan Book <dbook@cpan.org> |
1519 | |
9ba11a91 |
1520 | Code and tests adapted from L<Mojo::DOM>, a lightweight DOM parser by the L<Mojolicious> team. |
7218d584 |
1521 | |
2d9f5165 |
1522 | =head1 CONTRIBUTORS |
1523 | |
1524 | =over |
1525 | |
1526 | =item Matt S Trout (mst) |
1527 | |
1528 | =back |
1529 | |
a292be34 |
1530 | =head1 COPYRIGHT AND LICENSE |
1531 | |
9ba11a91 |
1532 | Copyright (c) 2008-2015 Sebastian Riedel. |
1533 | |
1534 | Copyright (c) 2015 L</"AUTHOR"> and L</"CONTRIBUTORS"> for adaptation to standalone format. |
a292be34 |
1535 | |
1536 | This is free software, licensed under: |
1537 | |
1538 | The Artistic License 2.0 (GPL Compatible) |
1539 | |
1540 | =head1 SEE ALSO |
1541 | |
31877452 |
1542 | L<Mojo::DOM>, L<HTML::TreeBuilder>, L<XML::LibXML>, L<XML::Twig>, L<XML::Smart> |
9a5f1e3f |
1543 | |
1544 | =for Pod::Coverage TO_JSON |
1545 | |
1546 | =cut |