7 '@{}' => sub { shift->child_nodes },
8 '%{}' => sub { shift->attr },
10 '""' => sub { shift->to_string },
14 use DOM::Tiny::_Collection;
17 use Scalar::Util qw(blessed weaken);
19 our $VERSION = '0.003';
23 my $self = bless \DOM::Tiny::_HTML->new, ref $class || $class;
24 return @_ ? $self->parse(@_) : $self;
27 sub TO_JSON { shift->_delegate('render') }
29 sub all_text { shift->_all_text(1, @_) }
31 sub ancestors { _select($_[0]->_collect($_[0]->_ancestors), $_[1]) }
33 sub append { shift->_add(1, @_) }
34 sub append_content { shift->_content(1, 0, @_) }
38 return undef unless my $result = $self->_css->select_one(@_);
39 return $self->_build($result, $self->xml);
46 my $tree = $self->tree;
47 my $attrs = $tree->[0] ne 'tag' ? {} : $tree->[2];
48 return $attrs unless @_;
51 return $attrs->{$_[0]} unless @_ > 1 || ref $_[0];
54 my $values = ref $_[0] ? $_[0] : {@_};
55 @$attrs{keys %$values} = values %$values;
60 sub child_nodes { $_[0]->_collect(_nodes($_[0]->tree)) }
62 sub children { _select($_[0]->_collect(_nodes($_[0]->tree, 1)), $_[1]) }
67 my $type = $self->type;
68 if ($type eq 'root' || $type eq 'tag') {
69 return $self->_content(0, 1, @_) if @_;
70 my $html = DOM::Tiny::_HTML->new(xml => $self->xml);
71 return join '', map { $html->tree($_)->render } _nodes($self->tree);
74 return $self->tree->[1] unless @_;
75 $self->tree->[1] = shift;
79 sub descendant_nodes { $_[0]->_collect(_all(_nodes($_[0]->tree))) }
81 sub find { $_[0]->_collect(@{$_[0]->_css->select($_[1])}) }
83 sub following { _select($_[0]->_collect(@{$_[0]->_siblings(1)->[1]}), $_[1]) }
84 sub following_nodes { $_[0]->_collect(@{$_[0]->_siblings->[1]}) }
86 sub matches { shift->_css->matches(@_) }
91 return undef if (my $tree = $self->tree)->[0] ne 'tag';
93 # Extract namespace prefix and search parents
94 my $ns = $tree->[1] =~ /^(.*?):/ ? "xmlns:$1" : undef;
95 for my $node ($tree, $self->_ancestors) {
97 # Namespace for prefix
98 my $attrs = $node->[2];
99 if ($ns) { $_ eq $ns and return $attrs->{$_} for keys %$attrs }
101 # Namespace attribute
102 elsif (defined $attrs->{xmlns}) { return $attrs->{xmlns} }
108 sub next { $_[0]->_maybe($_[0]->_siblings(1, 0)->[1]) }
109 sub next_node { $_[0]->_maybe($_[0]->_siblings(0, 0)->[1]) }
113 return undef if $self->tree->[0] eq 'root';
114 return $self->_build($self->_parent, $self->xml);
117 sub parse { shift->_delegate(parse => @_) }
119 sub preceding { _select($_[0]->_collect(@{$_[0]->_siblings(1)->[0]}), $_[1]) }
120 sub preceding_nodes { $_[0]->_collect(@{$_[0]->_siblings->[0]}) }
122 sub prepend { shift->_add(0, @_) }
123 sub prepend_content { shift->_content(0, 0, @_) }
125 sub previous { $_[0]->_maybe($_[0]->_siblings(1, -1)->[0]) }
126 sub previous_node { $_[0]->_maybe($_[0]->_siblings(0, -1)->[0]) }
128 sub remove { shift->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)));
138 return $self unless my $tree = $self->_ancestors(1);
139 return $self->_build($tree, $self->xml);
144 return $self if (my $tree = $self->tree)->[0] ne 'tag';
145 return $self->_replace($tree->[3], $tree, _nodes($tree));
149 my ($self, $tag) = @_;
150 return undef if (my $tree = $self->tree)->[0] ne 'tag';
151 return $tree->[1] unless $tag;
156 sub tap { DOM::Tiny::_Collection::tap(@_) }
158 sub text { shift->_all_text(0, @_) }
160 sub to_string { shift->_delegate('render') }
162 sub tree { shift->_delegate(tree => @_) }
164 sub type { shift->tree->[0] }
170 return defined($self->{value}) ? $self->{value} : $self->text
171 if (my $tag = $self->tag) eq 'option';
173 # "textarea", "input" or "button"
174 return $tag eq 'textarea' ? $self->text : $self->{value} if $tag ne 'select';
177 my $v = $self->find('option:checked')->map('val');
178 return exists $self->{multiple} ? $v->size ? $v->to_array : undef : $v->last;
181 sub wrap { shift->_wrap(0, @_) }
182 sub wrap_content { shift->_wrap(1, @_) }
184 sub xml { shift->_delegate(xml => @_) }
187 my ($self, $offset, $new) = @_;
189 return $self if (my $tree = $self->tree)->[0] eq 'root';
191 my $parent = $self->_parent;
192 splice @$parent, _offset($parent, $tree) + $offset, 0,
193 _link($parent, _nodes($self->_parse($new)));
199 map { $_->[0] eq 'tag' ? ($_, _all(_nodes($_))) : ($_) } @_;
203 my ($self, $recurse, $trim) = @_;
206 my $tree = $self->tree;
207 $trim = 1 unless defined $trim;
208 map { $_->[1] eq 'pre' and $trim = 0 } $self->_ancestors, $tree
209 if $trim && $tree->[0] ne 'root';
211 return _text([_nodes($tree)], $recurse, $trim);
215 my ($self, $root) = @_;
217 return () unless my $tree = $self->_parent;
219 do { push @ancestors, $tree }
220 while ($tree->[0] eq 'tag') && ($tree = $tree->[3]);
221 return $root ? $ancestors[-1] : @ancestors[0 .. $#ancestors - 1];
224 sub _build { shift->new->tree(shift)->xml(shift) }
228 my $xml = $self->xml;
229 return DOM::Tiny::_Collection->new(map { $self->_build($_, $xml) } @_);
233 my ($self, $start, $offset, $new) = @_;
235 my $tree = $self->tree;
236 unless ($tree->[0] eq 'root' || $tree->[0] eq 'tag') {
237 my $old = $self->content;
238 return $self->content($start ? "$old$new" : "$new$old");
241 $start = $start ? ($#$tree + 1) : _start($tree);
242 $offset = $offset ? $#$tree : 0;
243 splice @$tree, $start, $offset, _link($tree, _nodes($self->_parse($new)));
248 sub _css { DOM::Tiny::_CSS->new(tree => shift->tree) }
251 my ($self, $method) = (shift, shift);
252 return $$self->$method unless @_;
258 my ($parent, @children) = @_;
260 # Link parent to children
261 for my $node (@children) {
262 my $offset = $node->[0] eq 'tag' ? 3 : 2;
263 $node->[$offset] = $parent;
264 weaken $node->[$offset];
270 sub _maybe { $_[1] ? $_[0]->_build($_[1], $_[0]->xml) : undef }
273 return () unless my $tree = shift;
274 my @nodes = @$tree[_start($tree) .. $#$tree];
275 return shift() ? grep { $_->[0] eq 'tag' } @nodes : @nodes;
279 my ($parent, $child) = @_;
280 my $i = _start($parent);
281 $_ eq $child ? last : $i++ for @$parent[$i .. $#$parent];
285 sub _parent { $_[0]->tree->[$_[0]->type eq 'tag' ? 3 : 2] }
287 sub _parse { DOM::Tiny::_HTML->new(xml => shift->xml)->parse(shift)->tree }
290 my ($self, $parent, $child, @nodes) = @_;
291 splice @$parent, _offset($parent, $child), 1, _link($parent, @nodes);
292 return $self->parent;
296 my ($collection, $selector) = @_;
297 return $collection unless $selector;
298 return $collection->new(grep { $_->matches($selector) } @$collection);
302 my ($self, $tags, $i) = @_;
304 return [] unless my $parent = $self->parent;
306 my $tree = $self->tree;
307 my (@before, @after, $match);
308 for my $node (_nodes($parent->tree)) {
309 ++$match and next if !$match && $node eq $tree;
310 next if $tags && $node->[0] ne 'tag';
311 $match ? push @after, $node : push @before, $node;
314 return defined $i ? [$before[$i], $after[$i]] : [\@before, \@after];
325 sub _start { $_[0][0] eq 'root' ? 1 : 4 }
328 my ($nodes, $recurse, $trim) = @_;
330 # Merge successive text nodes
332 while (my $next = $nodes->[$i + 1]) {
333 ++$i and next unless $nodes->[$i][0] eq 'text' && $next->[0] eq 'text';
334 splice @$nodes, $i, 2, ['text', $nodes->[$i][1] . $next->[1]];
338 for my $node (@$nodes) {
339 my $type = $node->[0];
343 if ($type eq 'text') { $chunk = $trim ? _squish $node->[1] : $node->[1] }
346 elsif ($type eq 'cdata' || $type eq 'raw') { $chunk = $node->[1] }
349 elsif ($type eq 'tag' && $recurse) {
350 no warnings 'recursion';
351 $chunk = _text([_nodes($node)], 1, $node->[1] eq 'pre' ? 0 : $trim);
354 # Add leading whitespace if punctuation allows it
355 $chunk = " $chunk" if $text =~ /\S\z/ && $chunk =~ /^[^.!?,;:\s]+/;
357 # Trim whitespace blocks
358 $text .= $chunk if $chunk =~ /\S+/ || !$trim;
365 my ($self, $content, $new) = @_;
367 $content = 1 if (my $tree = $self->tree)->[0] eq 'root';
368 $content = 0 if $tree->[0] ne 'root' && $tree->[0] ne 'tag';
372 my $first = $new = $self->_parse($new);
373 $current = $first while $first = (_nodes($first, 1))[0];
374 return $self unless $current;
378 push @$current, _link($current, _nodes($tree));
379 splice @$tree, _start($tree), $#$tree, _link($tree, _nodes($new));
384 $self->_replace($self->_parent, $tree, _nodes($new));
385 push @$current, _link($current, $tree);
395 DOM::Tiny - Minimalistic HTML/XML DOM parser with CSS selectors
402 my $dom = DOM::Tiny->new('<div><p id="a">Test</p><p id="b">123</p></div>');
405 say $dom->at('#b')->text;
406 say $dom->find('p')->map('text')->join("\n");
407 say $dom->find('[id]')->map(attr => 'id')->join("\n");
410 $dom->find('p[id]')->reverse->each(sub { say $_->{id} });
413 for my $e ($dom->find('p[id]')->each) {
414 say $e->{id}, ':', $e->text;
418 $dom->find('div p')->last->append('<p id="c">456</p>');
419 $dom->find(':not(p)')->map('strip');
426 L<DOM::Tiny> is a minimalistic and relaxed pure-perl HTML/XML DOM parser based
427 on L<Mojo::DOM>. It supports the L<HTML Living Standard|https://html.spec.whatwg.org/>
428 and L<Extensible Markup Language (XML) 1.0|http://www.w3.org/TR/xml/>, and
429 matching based on L<CSS3 selectors|http://www.w3.org/TR/selectors/>. It will
430 even try to interpret broken HTML and XML, so you should not use it for
433 =head1 NODES AND ELEMENTS
435 When we parse an HTML/XML fragment, it gets turned into a tree of nodes.
439 <head><title>Hello</title></head>
443 There are currently eight different kinds of nodes, C<cdata>, C<comment>,
444 C<doctype>, C<pi>, C<raw>, C<root>, C<tag> and C<text>. Elements are nodes of
456 While all node types are represented as L<DOM::Tiny> objects, some methods like
457 L</"attr"> and L</"namespace"> only apply to elements.
459 =head1 CASE-SENSITIVITY
461 L<DOM::Tiny> defaults to HTML semantics, that means all tags and attribute
462 names are lowercased and selectors need to be lowercase as well.
465 my $dom = DOM::Tiny->new('<P ID="greeting">Hi!</P>');
466 say $dom->at('p[id]')->text;
468 If XML processing instructions are found, the parser will automatically switch
469 into XML mode and everything becomes case-sensitive.
472 my $dom = DOM::Tiny->new('<?xml version="1.0"?><P ID="greeting">Hi!</P>');
473 say $dom->at('P[ID]')->text;
475 XML detection can also be disabled with the L</"xml"> method.
477 # Force XML semantics
478 my $dom = DOM::Tiny->new->xml(1)->parse('<P ID="greeting">Hi!</P>');
479 say $dom->at('P[ID]')->text;
481 # Force HTML semantics
482 my $dom = DOM::Tiny->new->xml(0)->parse('<P ID="greeting">Hi!</P>');
483 say $dom->at('p[id]')->text;
487 L<DOM::Tiny> uses a CSS selector engine based on L<Mojo::DOM::CSS>. All CSS
488 selectors that make sense for a standalone parser are supported.
496 my $all = $dom->find('*');
500 An element of type C<E>.
502 my $title = $dom->at('title');
506 An C<E> element with a C<foo> attribute.
508 my $links = $dom->find('a[href]');
512 An C<E> element whose C<foo> attribute value is exactly equal to C<bar>.
514 my $case_sensitive = $dom->find('input[type="hidden"]');
515 my $case_sensitive = $dom->find('input[type=hidden]');
519 An C<E> element whose C<foo> attribute value is exactly equal to any
520 (ASCII-range) case-permutation of C<bar>. Note that this selector is
521 EXPERIMENTAL and might change without warning!
523 my $case_insensitive = $dom->find('input[type="hidden" i]');
524 my $case_insensitive = $dom->find('input[type=hidden i]');
525 my $case_insensitive = $dom->find('input[class~="foo" i]');
527 This selector is part of
528 L<Selectors Level 4|http://dev.w3.org/csswg/selectors-4>, which is still a work
533 An C<E> element whose C<foo> attribute value is a list of whitespace-separated
534 values, one of which is exactly equal to C<bar>.
536 my $foo = $dom->find('input[class~="foo"]');
537 my $foo = $dom->find('input[class~=foo]');
541 An C<E> element whose C<foo> attribute value begins exactly with the string
544 my $begins_with = $dom->find('input[name^="f"]');
545 my $begins_with = $dom->find('input[name^=f]');
549 An C<E> element whose C<foo> attribute value ends exactly with the string
552 my $ends_with = $dom->find('input[name$="o"]');
553 my $ends_with = $dom->find('input[name$=o]');
557 An C<E> element whose C<foo> attribute value contains the substring C<bar>.
559 my $contains = $dom->find('input[name*="fo"]');
560 my $contains = $dom->find('input[name*=fo]');
564 An C<E> element, root of the document.
566 my $root = $dom->at(':root');
570 An C<E> element, the C<n-th> child of its parent.
572 my $third = $dom->find('div:nth-child(3)');
573 my $odd = $dom->find('div:nth-child(odd)');
574 my $even = $dom->find('div:nth-child(even)');
575 my $top3 = $dom->find('div:nth-child(-n+3)');
577 =item E:nth-last-child(n)
579 An C<E> element, the C<n-th> child of its parent, counting from the last one.
581 my $third = $dom->find('div:nth-last-child(3)');
582 my $odd = $dom->find('div:nth-last-child(odd)');
583 my $even = $dom->find('div:nth-last-child(even)');
584 my $bottom3 = $dom->find('div:nth-last-child(-n+3)');
586 =item E:nth-of-type(n)
588 An C<E> element, the C<n-th> sibling of its type.
590 my $third = $dom->find('div:nth-of-type(3)');
591 my $odd = $dom->find('div:nth-of-type(odd)');
592 my $even = $dom->find('div:nth-of-type(even)');
593 my $top3 = $dom->find('div:nth-of-type(-n+3)');
595 =item E:nth-last-of-type(n)
597 An C<E> element, the C<n-th> sibling of its type, counting from the last one.
599 my $third = $dom->find('div:nth-last-of-type(3)');
600 my $odd = $dom->find('div:nth-last-of-type(odd)');
601 my $even = $dom->find('div:nth-last-of-type(even)');
602 my $bottom3 = $dom->find('div:nth-last-of-type(-n+3)');
606 An C<E> element, first child of its parent.
608 my $first = $dom->find('div p:first-child');
612 An C<E> element, last child of its parent.
614 my $last = $dom->find('div p:last-child');
616 =item E:first-of-type
618 An C<E> element, first sibling of its type.
620 my $first = $dom->find('div p:first-of-type');
624 An C<E> element, last sibling of its type.
626 my $last = $dom->find('div p:last-of-type');
630 An C<E> element, only child of its parent.
632 my $lonely = $dom->find('div p:only-child');
636 An C<E> element, only sibling of its type.
638 my $lonely = $dom->find('div p:only-of-type');
642 An C<E> element that has no children (including text nodes).
644 my $empty = $dom->find(':empty');
648 A user interface element C<E> which is checked (for instance a radio-button or
651 my $input = $dom->find(':checked');
655 An C<E> element whose class is "warning".
657 my $warning = $dom->find('div.warning');
661 An C<E> element with C<ID> equal to "myid".
663 my $foo = $dom->at('div#foo');
667 An C<E> element that does not match simple selector C<s>.
669 my $others = $dom->find('div p:not(:first-child)');
673 An C<F> element descendant of an C<E> element.
675 my $headlines = $dom->find('div h1');
679 An C<F> element child of an C<E> element.
681 my $headlines = $dom->find('html > body > div > h1');
685 An C<F> element immediately preceded by an C<E> element.
687 my $second = $dom->find('h1 + h2');
691 An C<F> element preceded by an C<E> element.
693 my $second = $dom->find('h1 ~ h2');
697 Elements of type C<E>, C<F> and C<G>.
699 my $headlines = $dom->find('h1, h2, h3');
701 =item E[foo=bar][bar=baz]
703 An C<E> element whose attributes match all following attribute selectors.
705 my $links = $dom->find('a[foo^=b][foo$=ar]');
711 L<DOM::Tiny> overloads the following operators.
717 Alias for L</"child_nodes">.
720 $dom->parse('<!-- Test --><b>123</b>')->[0];
732 Alias for L</"attr">.
735 $dom->parse('<div id="test">Test</div>')->at('div')->{id};
741 Alias for L</"to_string">.
745 L<DOM::Tiny> implements the following methods.
749 my $dom = DOM::Tiny->new;
750 my $dom = DOM::Tiny->new('<foo bar="baz">I ♥ DOM::Tiny!</foo>');
752 Construct a new scalar-based L<DOM::Tiny> object and L</"parse"> HTML/XML
753 fragment if necessary.
757 my $trimmed = $dom->all_text;
758 my $untrimmed = $dom->all_text(0);
760 Extract text content from all descendant nodes of this element, smart
761 whitespace trimming is enabled by default.
764 $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->all_text;
767 $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->all_text(0);
771 my $collection = $dom->ancestors;
772 my $collection = $dom->ancestors('div ~ p');
774 Find all ancestor elements of this node matching the CSS selector and return a
775 L<collection|/"COLLECTION METHODS"> containing these elements as L<DOM::Tiny>
776 objects. All selectors listed in L</"SELECTORS"> are supported.
778 # List tag names of ancestor elements
779 say $dom->ancestors->map('tag')->join("\n");
783 $dom = $dom->append('<p>I ♥ DOM::Tiny!</p>');
785 Append HTML/XML fragment to this node.
787 # "<div><h1>Test</h1><h2>123</h2></div>"
788 $dom->parse('<div><h1>Test</h1></div>')
789 ->at('h1')->append('<h2>123</h2>')->root;
792 $dom->parse('<p>Test</p>')->at('p')
793 ->child_nodes->first->append(' 123')->root;
795 =head2 append_content
797 $dom = $dom->append_content('<p>I ♥ DOM::Tiny!</p>');
799 Append HTML/XML fragment (for C<root> and C<tag> nodes) or raw content to this
802 # "<div><h1>Test123</h1></div>"
803 $dom->parse('<div><h1>Test</h1></div>')
804 ->at('h1')->append_content('123')->root;
806 # "<!-- Test 123 --><br>"
807 $dom->parse('<!-- Test --><br>')
808 ->child_nodes->first->append_content('123 ')->root;
810 # "<p>Test<i>123</i></p>"
811 $dom->parse('<p>Test</p>')->at('p')->append_content('<i>123</i>')->root;
815 my $result = $dom->at('div ~ p');
817 Find first descendant element of this element matching the CSS selector and
818 return it as a L<DOM::Tiny> object or return C<undef> if none could be found.
819 All selectors listed in L</"SELECTORS"> are supported.
821 # Find first element with "svg" namespace definition
822 my $namespace = $dom->at('[xmlns\:svg]')->{'xmlns:svg'};
826 my $hash = $dom->attr;
827 my $foo = $dom->attr('foo');
828 $dom = $dom->attr({foo => 'bar'});
829 $dom = $dom->attr(foo => 'bar');
831 This element's attributes.
833 # Remove an attribute
834 delete $dom->attr->{id};
836 # Attribute without value
837 $dom->attr(selected => undef);
840 say $dom->find('*')->map(attr => 'id')->compact->join("\n");
844 my $collection = $dom->child_nodes;
846 Return a L<collection|/"COLLECTION METHODS"> containing all child nodes of this
847 element as L<DOM::Tiny> objects.
849 # "<p><b>123</b></p>"
850 $dom->parse('<p>Test<b>123</b></p>')->at('p')->child_nodes->first->remove;
853 $dom->parse('<!DOCTYPE html><b>123</b>')->child_nodes->first;
856 $dom->parse('<b>123</b><!-- Test -->')->child_nodes->last->content;
860 my $collection = $dom->children;
861 my $collection = $dom->children('div ~ p');
863 Find all child elements of this element matching the CSS selector and return a
864 L<collection|/"COLLECTION METHODS"> containing these elements as L<DOM::Tiny>
865 objects. All selectors listed in L</"SELECTORS"> are supported.
867 # Show tag name of random child element
868 say $dom->children->shuffle->first->tag;
872 my $str = $dom->content;
873 $dom = $dom->content('<p>I ♥ DOM::Tiny!</p>');
875 Return this node's content or replace it with HTML/XML fragment (for C<root>
876 and C<tag> nodes) or raw content.
879 $dom->parse('<div><b>Test</b></div>')->at('div')->content;
881 # "<div><h1>123</h1></div>"
882 $dom->parse('<div><h1>Test</h1></div>')->at('h1')->content('123')->root;
884 # "<p><i>123</i></p>"
885 $dom->parse('<p>Test</p>')->at('p')->content('<i>123</i>')->root;
887 # "<div><h1></h1></div>"
888 $dom->parse('<div><h1>Test</h1></div>')->at('h1')->content('')->root;
891 $dom->parse('<!-- Test --><br>')->child_nodes->first->content;
893 # "<div><!-- 123 -->456</div>"
894 $dom->parse('<div><!-- Test -->456</div>')
895 ->at('div')->child_nodes->first->content(' 123 ')->root;
897 =head2 descendant_nodes
899 my $collection = $dom->descendant_nodes;
901 Return a L<collection|/"COLLECTION METHODS"> containing all descendant nodes of
902 this element as L<DOM::Tiny> objects.
904 # "<p><b>123</b></p>"
905 $dom->parse('<p><!-- Test --><b>123<!-- 456 --></b></p>')
906 ->descendant_nodes->grep(sub { $_->type eq 'comment' })
907 ->map('remove')->first;
909 # "<p><b>test</b>test</p>"
910 $dom->parse('<p><b>123</b>456</p>')
911 ->at('p')->descendant_nodes->grep(sub { $_->type eq 'text' })
912 ->map(content => 'test')->first->root;
916 my $collection = $dom->find('div ~ p');
918 Find all descendant elements of this element matching the CSS selector and
919 return a L<collection|/"COLLECTION METHODS"> containing these elements as
920 L<DOM::Tiny> objects. All selectors listed in L</"SELECTORS"> are supported.
922 # Find a specific element and extract information
923 my $id = $dom->find('div')->[23]{id};
925 # Extract information from multiple elements
926 my @headers = $dom->find('h1, h2, h3')->map('text')->each;
928 # Count all the different tags
929 my $hash = $dom->find('*')->reduce(sub { $a->{$b->tag}++; $a }, {});
931 # Find elements with a class that contains dots
932 my @divs = $dom->find('div.foo\.bar')->each;
936 my $collection = $dom->following;
937 my $collection = $dom->following('div ~ p');
939 Find all sibling elements after this node matching the CSS selector and return
940 a L<collection|/"COLLECTION METHODS"> containing these elements as L<DOM::Tiny>
941 objects. All selectors listen in L</"SELECTORS"> are supported.
943 # List tags of sibling elements after this node
944 say $dom->following->map('tag')->join("\n");
946 =head2 following_nodes
948 my $collection = $dom->following_nodes;
950 Return a L<collection|/"COLLECTION METHODS"> containing all sibling nodes after
951 this node as L<DOM::Tiny> objects.
954 $dom->parse('<p>A</p><!-- B -->C')->at('p')->following_nodes->last->content;
958 my $bool = $dom->matches('div ~ p');
960 Check if this element matches the CSS selector. All selectors listed in
961 L</"SELECTORS"> are supported.
964 $dom->parse('<p class="a">A</p>')->at('p')->matches('.a');
965 $dom->parse('<p class="a">A</p>')->at('p')->matches('p[class]');
968 $dom->parse('<p class="a">A</p>')->at('p')->matches('.b');
969 $dom->parse('<p class="a">A</p>')->at('p')->matches('p[id]');
973 my $namespace = $dom->namespace;
975 Find this element's namespace or return C<undef> if none could be found.
977 # Find namespace for an element with namespace prefix
978 my $namespace = $dom->at('svg > svg\:circle')->namespace;
980 # Find namespace for an element that may or may not have a namespace prefix
981 my $namespace = $dom->at('svg > circle')->namespace;
985 my $sibling = $dom->next;
987 Return L<DOM::Tiny> object for next sibling element or C<undef> if there are no
991 $dom->parse('<div><h1>Test</h1><h2>123</h2></div>')->at('h1')->next;
995 my $sibling = $dom->next_node;
997 Return L<DOM::Tiny> object for next sibling node or C<undef> if there are no
1001 $dom->parse('<p><b>123</b><!-- Test -->456</p>')
1002 ->at('b')->next_node->next_node;
1005 $dom->parse('<p><b>123</b><!-- Test -->456</p>')
1006 ->at('b')->next_node->content;
1010 my $parent = $dom->parent;
1012 Return L<DOM::Tiny> object for parent of this node or C<undef> if this node has
1017 $dom = $dom->parse('<foo bar="baz">I ♥ DOM::Tiny!</foo>');
1019 Parse HTML/XML fragment.
1022 my $dom = DOM::Tiny->new->xml(1)->parse($xml);
1026 my $collection = $dom->preceding;
1027 my $collection = $dom->preceding('div ~ p');
1029 Find all sibling elements before this node matching the CSS selector and return
1030 a L<collection|/"COLLECTION METHODS"> containing these elements as L<DOM::Tiny>
1031 objects. All selectors listed in L</"SELECTORS"> are supported.
1033 # List tags of sibling elements before this node
1034 say $dom->preceding->map('tag')->join("\n");
1036 =head2 preceding_nodes
1038 my $collection = $dom->preceding_nodes;
1040 Return a L<collection|/"COLLECTION METHODS"> containing all sibling nodes
1041 before this node as L<DOM::Tiny> objects.
1044 $dom->parse('A<!-- B --><p>C</p>')->at('p')->preceding_nodes->first->content;
1048 $dom = $dom->prepend('<p>I ♥ DOM::Tiny!</p>');
1050 Prepend HTML/XML fragment to this node.
1052 # "<div><h1>Test</h1><h2>123</h2></div>"
1053 $dom->parse('<div><h2>123</h2></div>')
1054 ->at('h2')->prepend('<h1>Test</h1>')->root;
1057 $dom->parse('<p>123</p>')
1058 ->at('p')->child_nodes->first->prepend('Test ')->root;
1060 =head2 prepend_content
1062 $dom = $dom->prepend_content('<p>I ♥ DOM::Tiny!</p>');
1064 Prepend HTML/XML fragment (for C<root> and C<tag> nodes) or raw content to this
1067 # "<div><h2>Test123</h2></div>"
1068 $dom->parse('<div><h2>123</h2></div>')
1069 ->at('h2')->prepend_content('Test')->root;
1071 # "<!-- Test 123 --><br>"
1072 $dom->parse('<!-- 123 --><br>')
1073 ->child_nodes->first->prepend_content(' Test')->root;
1075 # "<p><i>123</i>Test</p>"
1076 $dom->parse('<p>Test</p>')->at('p')->prepend_content('<i>123</i>')->root;
1080 my $sibling = $dom->previous;
1082 Return L<DOM::Tiny> object for previous sibling element or C<undef> if there
1083 are no more siblings.
1086 $dom->parse('<div><h1>Test</h1><h2>123</h2></div>')->at('h2')->previous;
1088 =head2 previous_node
1090 my $sibling = $dom->previous_node;
1092 Return L<DOM::Tiny> object for previous sibling node or C<undef> if there are
1096 $dom->parse('<p>123<!-- Test --><b>456</b></p>')
1097 ->at('b')->previous_node->previous_node;
1100 $dom->parse('<p>123<!-- Test --><b>456</b></p>')
1101 ->at('b')->previous_node->content;
1105 my $parent = $dom->remove;
1107 Remove this node and return L</"root"> (for C<root> nodes) or L</"parent">.
1110 $dom->parse('<div><h1>Test</h1></div>')->at('h1')->remove;
1112 # "<p><b>456</b></p>"
1113 $dom->parse('<p>123<b>456</b></p>')
1114 ->at('p')->child_nodes->first->remove->root;
1118 my $parent = $dom->replace('<div>I ♥ DOM::Tiny!</div>');
1120 Replace this node with HTML/XML fragment and return L</"root"> (for C<root>
1121 nodes) or L</"parent">.
1123 # "<div><h2>123</h2></div>"
1124 $dom->parse('<div><h1>Test</h1></div>')->at('h1')->replace('<h2>123</h2>');
1126 # "<p><b>123</b></p>"
1127 $dom->parse('<p>Test</p>')
1128 ->at('p')->child_nodes->[0]->replace('<b>123</b>')->root;
1132 my $root = $dom->root;
1134 Return L<DOM::Tiny> object for C<root> node.
1138 my $parent = $dom->strip;
1140 Remove this element while preserving its content and return L</"parent">.
1143 $dom->parse('<div><h1>Test</h1></div>')->at('h1')->strip;
1147 my $tag = $dom->tag;
1148 $dom = $dom->tag('div');
1150 This element's tag name.
1152 # List tag names of child elements
1153 say $dom->children->map('tag')->join("\n");
1157 $dom = $dom->tap(sub {...});
1159 Equivalent to L<Mojo::Base/"tap">.
1163 my $trimmed = $dom->text;
1164 my $untrimmed = $dom->text(0);
1166 Extract text content from this element only (not including child elements),
1167 smart whitespace trimming is enabled by default.
1170 $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->text;
1173 $dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->text(0);
1177 my $str = $dom->to_string;
1179 Render this node and its content to HTML/XML.
1182 $dom->parse('<div><b>Test</b></div>')->at('div b')->to_string;
1186 my $tree = $dom->tree;
1187 $dom = $dom->tree(['root']);
1189 Document Object Model. Note that this structure should only be used very
1190 carefully since it is very dynamic.
1194 my $type = $dom->type;
1196 This node's type, usually C<cdata>, C<comment>, C<doctype>, C<pi>, C<raw>,
1197 C<root>, C<tag> or C<text>.
1200 $dom->parse('<![CDATA[Test]]>')->child_nodes->first->type;
1203 $dom->parse('<!-- Test -->')->child_nodes->first->type;
1206 $dom->parse('<!DOCTYPE html>')->child_nodes->first->type;
1209 $dom->parse('<?xml version="1.0"?>')->child_nodes->first->type;
1212 $dom->parse('<title>Test</title>')->at('title')->child_nodes->first->type;
1215 $dom->parse('<p>Test</p>')->type;
1218 $dom->parse('<p>Test</p>')->at('p')->type;
1221 $dom->parse('<p>Test</p>')->at('p')->child_nodes->first->type;
1225 my $value = $dom->val;
1227 Extract value from form element (such as C<button>, C<input>, C<option>,
1228 C<select> and C<textarea>) or return C<undef> if this element has no value. In
1229 the case of C<select> with C<multiple> attribute, find C<option> elements with
1230 C<selected> attribute and return an array reference with all values or C<undef>
1231 if none could be found.
1234 $dom->parse('<input name="test" value="a">')->at('input')->val;
1237 $dom->parse('<textarea>b</textarea>')->at('textarea')->val;
1240 $dom->parse('<option value="c">Test</option>')->at('option')->val;
1243 $dom->parse('<select><option selected>d</option></select>')
1244 ->at('select')->val;
1247 $dom->parse('<select multiple><option selected>e</option></select>')
1248 ->at('select')->val->[0];
1252 $dom = $dom->wrap('<div></div>');
1254 Wrap HTML/XML fragment around this node, placing it as the last child of the
1255 first innermost element.
1257 # "<p>123<b>Test</b></p>"
1258 $dom->parse('<b>Test</b>')->at('b')->wrap('<p>123</p>')->root;
1260 # "<div><p><b>Test</b></p>123</div>"
1261 $dom->parse('<b>Test</b>')->at('b')->wrap('<div><p></p>123</div>')->root;
1263 # "<p><b>Test</b></p><p>123</p>"
1264 $dom->parse('<b>Test</b>')->at('b')->wrap('<p></p><p>123</p>')->root;
1266 # "<p><b>Test</b></p>"
1267 $dom->parse('<p>Test</p>')->at('p')->child_nodes->first->wrap('<b>')->root;
1271 $dom = $dom->wrap_content('<div></div>');
1273 Wrap HTML/XML fragment around this node's content, placing it as the last
1274 children of the first innermost element.
1276 # "<p><b>123Test</b></p>"
1277 $dom->parse('<p>Test<p>')->at('p')->wrap_content('<b>123</b>')->root;
1279 # "<p><b>Test</b></p><p>123</p>"
1280 $dom->parse('<b>Test</b>')->wrap_content('<p></p><p>123</p>');
1284 my $bool = $dom->xml;
1285 $dom = $dom->xml($bool);
1287 Disable HTML semantics in parser and activate case-sensitivity, defaults to
1288 auto detection based on processing instructions.
1290 =head1 COLLECTION METHODS
1292 Some L<DOM::Tiny> methods return an array-based collection object based on
1293 L<Mojo::Collection>, which can either be accessed directly as an array
1294 reference, or with the following methods.
1297 $collection->map(sub { ucfirst })->shuffle->each(sub {
1298 my ($word, $num) = @_;
1302 # Access array directly to manipulate collection
1303 $collection->[23] += 100;
1304 say for @$collection;
1308 my $new = $collection->compact;
1310 Create a new collection with all elements that are defined and not an empty
1313 # $collection contains (0, 1, undef, 2, '', 3)
1314 $collection->compact->join(', '); # "0, 1, 2, 3"
1318 my @elements = $collection->each;
1319 $collection = $collection->each(sub {...});
1321 Evaluate callback for each element in collection or return all elements as a
1322 list if none has been provided. The element will be the first argument passed
1323 to the callback and is also available as C<$_>.
1325 # Make a numbered list
1326 $collection->each(sub {
1333 my $first = $collection->first;
1334 my $first = $collection->first(qr/foo/);
1335 my $first = $collection->first(sub {...});
1336 my $first = $collection->first($method);
1337 my $first = $collection->first($method, @args);
1339 Evaluate regular expression/callback for, or call method on, each element in
1340 collection and return the first one that matched the regular expression, or for
1341 which the callback/method returned true. The element will be the first argument
1342 passed to the callback and is also available as C<$_>.
1345 my $first = $collection->first(sub { $_->$method(@args) });
1347 # Find first value that contains the word "tiny"
1348 my $interesting = $collection->first(qr/tiny/i);
1350 # Find first value that is greater than 5
1351 my $greater = $collection->first(sub { $_ > 5 });
1355 my $new = $collection->flatten;
1357 Flatten nested collections/arrays recursively and create a new collection with
1360 # $collection contains (1, [2, [3, 4], 5, [6]], 7)
1361 $collection->flatten->join(', '); # "1, 2, 3, 4, 5, 6, 7"
1365 my $new = $collection->grep(qr/foo/);
1366 my $new = $collection->grep(sub {...});
1367 my $new = $collection->grep($method);
1368 my $new = $collection->grep($method, @args);
1370 Evaluate regular expression/callback for, or call method on, each element in
1371 collection and create a new collection with all elements that matched the
1372 regular expression, or for which the callback/method returned true. The element
1373 will be the first argument passed to the callback and is also available as
1377 my $new = $collection->grep(sub { $_->$method(@args) });
1379 # Find all values that contain the word "tiny"
1380 my $interesting = $collection->grep(qr/tiny/i);
1382 # Find all values that are greater than 5
1383 my $greater = $collection->grep(sub { $_ > 5 });
1387 my $stream = $collection->join;
1388 my $stream = $collection->join("\n");
1390 Turn collection into string.
1392 # Join all values with commas
1393 $collection->join(', ');
1397 my $last = $collection->last;
1399 Return the last element in collection.
1403 my $new = $collection->map(sub {...});
1404 my $new = $collection->map($method);
1405 my $new = $collection->map($method, @args);
1407 Evaluate callback for, or call method on, each element in collection and create
1408 a new collection from the results. The element will be the first argument
1409 passed to the callback and is also available as C<$_>.
1412 my $new = $collection->map(sub { $_->$method(@args) });
1414 # Append the word "tiny" to all values
1415 my $domified = $collection->map(sub { $_ . 'tiny' });
1419 my $result = $collection->reduce(sub {...});
1420 my $result = $collection->reduce(sub {...}, $initial);
1422 Reduce elements in collection with callback, the first element will be used as
1423 initial value if none has been provided.
1425 # Calculate the sum of all values
1426 my $sum = $collection->reduce(sub { $a + $b });
1428 # Count how often each value occurs in collection
1429 my $hash = $collection->reduce(sub { $a->{$b}++; $a }, {});
1433 my $new = $collection->reverse;
1435 Create a new collection with all elements in reverse order.
1439 my $new = $collection->slice(4 .. 7);
1441 Create a new collection with all selected elements.
1443 # $collection contains ('A', 'B', 'C', 'D', 'E')
1444 $collection->slice(1, 2, 4)->join(' '); # "B C E"
1448 my $new = $collection->shuffle;
1450 Create a new collection with all elements in random order.
1454 my $size = $collection->size;
1456 Number of elements in collection.
1460 my $new = $collection->sort;
1461 my $new = $collection->sort(sub {...});
1463 Sort elements based on return value of callback and create a new collection
1466 # Sort values case-insensitive
1467 my $case_insensitive = $collection->sort(sub { uc($a) cmp uc($b) });
1471 $collection = $collection->tap(sub {...});
1473 Equivalent to L<Mojo::Base/"tap">.
1477 my $array = $collection->to_array;
1479 Turn collection into array reference.
1483 my $new = $collection->uniq;
1484 my $new = $collection->uniq(sub {...});
1485 my $new = $collection->uniq($method);
1486 my $new = $collection->uniq($method, @args);
1488 Create a new collection without duplicate elements, using the string
1489 representation of either the elements or the return value of the
1493 my $new = $collection->uniq(sub { $_->$method(@args) });
1495 # $collection contains ('foo', 'bar', 'bar', 'baz')
1496 $collection->uniq->join(' '); # "foo bar baz"
1498 # $collection contains ([1, 2], [2, 1], [3, 2])
1499 $collection->uniq(sub{ $_->[1] })->to_array; # "[[1, 2], [2, 1]]"
1503 Report any issues on the public bugtracker.
1507 Dan Book <dbook@cpan.org>
1509 Code and tests adapted from L<Mojo::DOM> by the L<Mojolicious> team.
1515 =item Matt S Trout (mst)
1519 =head1 COPYRIGHT AND LICENSE
1521 This software is Copyright (c) 2015 by Dan Book.
1523 This is free software, licensed under:
1525 The Artistic License 2.0 (GPL Compatible)
1529 L<Mojo::DOM>, L<HTML::TreeBuilder>, L<XML::LibXML>, L<XML::Twig>, L<XML::Smart>
1531 =for Pod::Coverage TO_JSON