NAME DOM::Tiny - Minimalistic HTML/XML DOM parser with CSS selectors SYNOPSIS use DOM::Tiny; # Parse my $dom = DOM::Tiny->new('

Test

123

'); # Find say $dom->at('#b')->text; say $dom->find('p')->map('text')->join("\n"); say $dom->find('[id]')->map(attr => 'id')->join("\n"); # Iterate $dom->find('p[id]')->reverse->each(sub { say $_->{id} }); # Loop for my $e ($dom->find('p[id]')->each) { say $e->{id}, ':', $e->text; } # Modify $dom->find('div p')->last->append('

456

'); $dom->find(':not(p)')->map('strip'); # Render say "$dom"; DESCRIPTION DOM::Tiny is a minimalistic and relaxed pure-perl HTML/XML DOM parser based on Mojo::DOM. It supports the HTML Living Standard and Extensible Markup Language (XML) 1.0 , and matching based on CSS3 selectors . It will even try to interpret broken HTML and XML, so you should not use it for validation. NODES AND ELEMENTS When we parse an HTML/XML fragment, it gets turned into a tree of nodes. Hello World! There are currently eight different kinds of nodes, cdata, comment, doctype, pi, raw, root, tag and text. Elements are nodes of the type tag. root |- doctype (html) +- tag (html) |- tag (head) | +- tag (title) | +- raw (Hello) +- tag (body) +- text (World!) While all node types are represented as DOM::Tiny objects, some methods like "attr" and "namespace" only apply to elements. CASE-SENSITIVITY DOM::Tiny defaults to HTML semantics, that means all tags and attribute names are lowercased and selectors need to be lowercase as well. # HTML semantics my $dom = DOM::Tiny->new('

Hi!

'); say $dom->at('p[id]')->text; If an XML declaration is found, the parser will automatically switch into XML mode and everything becomes case-sensitive. # XML semantics my $dom = DOM::Tiny->new('

Hi!

'); say $dom->at('P[ID]')->text; XML detection can also be disabled with the "xml" method. # Force XML semantics my $dom = DOM::Tiny->new->xml(1)->parse('

Hi!

'); say $dom->at('P[ID]')->text; # Force HTML semantics my $dom = DOM::Tiny->new->xml(0)->parse('

Hi!

'); say $dom->at('p[id]')->text; SELECTORS DOM::Tiny uses a CSS selector engine based on Mojo::DOM::CSS. All CSS selectors that make sense for a standalone parser are supported. * Any element. my $all = $dom->find('*'); E An element of type E. my $title = $dom->at('title'); E[foo] An E element with a foo attribute. my $links = $dom->find('a[href]'); E[foo="bar"] An E element whose foo attribute value is exactly equal to bar. my $case_sensitive = $dom->find('input[type="hidden"]'); my $case_sensitive = $dom->find('input[type=hidden]'); E[foo="bar" i] An E element whose foo attribute value is exactly equal to any (ASCII-range) case-permutation of bar. Note that this selector is EXPERIMENTAL and might change without warning! my $case_insensitive = $dom->find('input[type="hidden" i]'); my $case_insensitive = $dom->find('input[type=hidden i]'); my $case_insensitive = $dom->find('input[class~="foo" i]'); This selector is part of Selectors Level 4 , which is still a work in progress. E[foo~="bar"] An E element whose foo attribute value is a list of whitespace-separated values, one of which is exactly equal to bar. my $foo = $dom->find('input[class~="foo"]'); my $foo = $dom->find('input[class~=foo]'); E[foo^="bar"] An E element whose foo attribute value begins exactly with the string bar. my $begins_with = $dom->find('input[name^="f"]'); my $begins_with = $dom->find('input[name^=f]'); E[foo$="bar"] An E element whose foo attribute value ends exactly with the string bar. my $ends_with = $dom->find('input[name$="o"]'); my $ends_with = $dom->find('input[name$=o]'); E[foo*="bar"] An E element whose foo attribute value contains the substring bar. my $contains = $dom->find('input[name*="fo"]'); my $contains = $dom->find('input[name*=fo]'); E:root An E element, root of the document. my $root = $dom->at(':root'); E:nth-child(n) An E element, the n-th child of its parent. my $third = $dom->find('div:nth-child(3)'); my $odd = $dom->find('div:nth-child(odd)'); my $even = $dom->find('div:nth-child(even)'); my $top3 = $dom->find('div:nth-child(-n+3)'); E:nth-last-child(n) An E element, the n-th child of its parent, counting from the last one. my $third = $dom->find('div:nth-last-child(3)'); my $odd = $dom->find('div:nth-last-child(odd)'); my $even = $dom->find('div:nth-last-child(even)'); my $bottom3 = $dom->find('div:nth-last-child(-n+3)'); E:nth-of-type(n) An E element, the n-th sibling of its type. my $third = $dom->find('div:nth-of-type(3)'); my $odd = $dom->find('div:nth-of-type(odd)'); my $even = $dom->find('div:nth-of-type(even)'); my $top3 = $dom->find('div:nth-of-type(-n+3)'); E:nth-last-of-type(n) An E element, the n-th sibling of its type, counting from the last one. my $third = $dom->find('div:nth-last-of-type(3)'); my $odd = $dom->find('div:nth-last-of-type(odd)'); my $even = $dom->find('div:nth-last-of-type(even)'); my $bottom3 = $dom->find('div:nth-last-of-type(-n+3)'); E:first-child An E element, first child of its parent. my $first = $dom->find('div p:first-child'); E:last-child An E element, last child of its parent. my $last = $dom->find('div p:last-child'); E:first-of-type An E element, first sibling of its type. my $first = $dom->find('div p:first-of-type'); E:last-of-type An E element, last sibling of its type. my $last = $dom->find('div p:last-of-type'); E:only-child An E element, only child of its parent. my $lonely = $dom->find('div p:only-child'); E:only-of-type An E element, only sibling of its type. my $lonely = $dom->find('div p:only-of-type'); E:empty An E element that has no children (including text nodes). my $empty = $dom->find(':empty'); E:checked A user interface element E which is checked (for instance a radio-button or checkbox). my $input = $dom->find(':checked'); E.warning An E element whose class is "warning". my $warning = $dom->find('div.warning'); E#myid An E element with ID equal to "myid". my $foo = $dom->at('div#foo'); E:not(s) An E element that does not match simple selector s. my $others = $dom->find('div p:not(:first-child)'); E F An F element descendant of an E element. my $headlines = $dom->find('div h1'); E > F An F element child of an E element. my $headlines = $dom->find('html > body > div > h1'); E + F An F element immediately preceded by an E element. my $second = $dom->find('h1 + h2'); E ~ F An F element preceded by an E element. my $second = $dom->find('h1 ~ h2'); E, F, G Elements of type E, F and G. my $headlines = $dom->find('h1, h2, h3'); E[foo=bar][bar=baz] An E element whose attributes match all following attribute selectors. my $links = $dom->find('a[foo^=b][foo$=ar]'); OPERATORS DOM::Tiny overloads the following operators. array my @nodes = @$dom; Alias for "child_nodes". # "" $dom->parse('123')->[0]; bool my $bool = !!$dom; Always true. hash my %attrs = %$dom; Alias for "attr". # "test" $dom->parse('
Test
')->at('div')->{id}; stringify my $str = "$dom"; Alias for "to_string". METHODS DOM::Tiny implements the following methods. new my $dom = DOM::Tiny->new; my $dom = DOM::Tiny->new('I ♥ DOM::Tiny!'); Construct a new scalar-based DOM::Tiny object and "parse" HTML/XML fragment if necessary. all_text my $trimmed = $dom->all_text; my $untrimmed = $dom->all_text(0); Extract text content from all descendant nodes of this element, smart whitespace trimming is enabled by default. # "foo bar baz" $dom->parse("
foo\n

bar

baz\n
")->at('div')->all_text; # "foo\nbarbaz\n" $dom->parse("
foo\n

bar

baz\n
")->at('div')->all_text(0); ancestors my $collection = $dom->ancestors; my $collection = $dom->ancestors('div ~ p'); Find all ancestor elements of this node matching the CSS selector and return a collection containing these elements as DOM::Tiny objects. All selectors listed in "SELECTORS" are supported. # List tag names of ancestor elements say $dom->ancestors->map('tag')->join("\n"); append $dom = $dom->append('

I ♥ DOM::Tiny!

'); Append HTML/XML fragment to this node (for all node types other than root). # "

Test

123

" $dom->parse('

Test

') ->at('h1')->append('

123

')->root; # "

Test 123

" $dom->parse('

Test

')->at('p') ->child_nodes->first->append(' 123')->root; append_content $dom = $dom->append_content('

I ♥ DOM::Tiny!

'); Append HTML/XML fragment (for root and tag nodes) or raw content to this node's content. # "

Test123

" $dom->parse('

Test

') ->at('h1')->append_content('123')->root; # "
" $dom->parse('
') ->child_nodes->first->append_content('123 ')->root; # "

Test123

" $dom->parse('

Test

')->at('p')->append_content('123')->root; at my $result = $dom->at('div ~ p'); Find first descendant element of this element matching the CSS selector and return it as a DOM::Tiny object, or undef if none could be found. All selectors listed in "SELECTORS" are supported. # Find first element with "svg" namespace definition my $namespace = $dom->at('[xmlns\:svg]')->{'xmlns:svg'}; attr my $hash = $dom->attr; my $foo = $dom->attr('foo'); $dom = $dom->attr({foo => 'bar'}); $dom = $dom->attr(foo => 'bar'); This element's attributes. # Remove an attribute delete $dom->attr->{id}; # Attribute without value $dom->attr(selected => undef); # List id attributes say $dom->find('*')->map(attr => 'id')->compact->join("\n"); child_nodes my $collection = $dom->child_nodes; Return a collection containing all child nodes of this element as DOM::Tiny objects. # "

123

" $dom->parse('

Test123

')->at('p')->child_nodes->first->remove; # "" $dom->parse('123')->child_nodes->first; # " Test " $dom->parse('123')->child_nodes->last->content; children my $collection = $dom->children; my $collection = $dom->children('div ~ p'); Find all child elements of this element matching the CSS selector and return a collection containing these elements as DOM::Tiny objects. All selectors listed in "SELECTORS" are supported. # Show tag name of random child element say $dom->children->shuffle->first->tag; content my $str = $dom->content; $dom = $dom->content('

I ♥ DOM::Tiny!

'); Return this node's content or replace it with HTML/XML fragment (for root and tag nodes) or raw content. # "Test" $dom->parse('
Test
')->at('div')->content; # "

123

" $dom->parse('

Test

')->at('h1')->content('123')->root; # "

123

" $dom->parse('

Test

')->at('p')->content('123')->root; # "

" $dom->parse('

Test

')->at('h1')->content('')->root; # " Test " $dom->parse('
')->child_nodes->first->content; # "
456
" $dom->parse('
456
') ->at('div')->child_nodes->first->content(' 123 ')->root; descendant_nodes my $collection = $dom->descendant_nodes; Return a collection containing all descendant nodes of this element as DOM::Tiny objects. # "

123

" $dom->parse('

123

') ->descendant_nodes->grep(sub { $_->type eq 'comment' }) ->map('remove')->first; # "

testtest

" $dom->parse('

123456

') ->at('p')->descendant_nodes->grep(sub { $_->type eq 'text' }) ->map(content => 'test')->first->root; find my $collection = $dom->find('div ~ p'); Find all descendant elements of this element matching the CSS selector and return a collection containing these elements as DOM::Tiny objects. All selectors listed in "SELECTORS" are supported. # Find a specific element and extract information my $id = $dom->find('div')->[23]{id}; # Extract information from multiple elements my @headers = $dom->find('h1, h2, h3')->map('text')->each; # Count all the different tags my $hash = $dom->find('*')->reduce(sub { $a->{$b->tag}++; $a }, {}); # Find elements with a class that contains dots my @divs = $dom->find('div.foo\.bar')->each; following my $collection = $dom->following; my $collection = $dom->following('div ~ p'); Find all sibling elements after this node matching the CSS selector and return a collection containing these elements as DOM::Tiny objects. All selectors listen in "SELECTORS" are supported. # List tags of sibling elements after this node say $dom->following->map('tag')->join("\n"); following_nodes my $collection = $dom->following_nodes; Return a collection containing all sibling nodes after this node as DOM::Tiny objects. # "C" $dom->parse('

A

C')->at('p')->following_nodes->last->content; matches my $bool = $dom->matches('div ~ p'); Check if this element matches the CSS selector. All selectors listed in "SELECTORS" are supported. # True $dom->parse('

A

')->at('p')->matches('.a'); $dom->parse('

A

')->at('p')->matches('p[class]'); # False $dom->parse('

A

')->at('p')->matches('.b'); $dom->parse('

A

')->at('p')->matches('p[id]'); namespace my $namespace = $dom->namespace; Find this element's namespace, or return undef if none could be found. # Find namespace for an element with namespace prefix my $namespace = $dom->at('svg > svg\:circle')->namespace; # Find namespace for an element that may or may not have a namespace prefix my $namespace = $dom->at('svg > circle')->namespace; next my $sibling = $dom->next; Return DOM::Tiny object for next sibling element, or undef if there are no more siblings. # "

123

" $dom->parse('

Test

123

')->at('h1')->next; next_node my $sibling = $dom->next_node; Return DOM::Tiny object for next sibling node, or undef if there are no more siblings. # "456" $dom->parse('

123456

') ->at('b')->next_node->next_node; # " Test " $dom->parse('

123456

') ->at('b')->next_node->content; parent my $parent = $dom->parent; Return DOM::Tiny object for parent of this node, or undef if this node has no parent. # "Test" $dom->parse('

Test

')->at('i')->parent; parse $dom = $dom->parse('I ♥ DOM::Tiny!'); Parse HTML/XML fragment. # Parse XML my $dom = DOM::Tiny->new->xml(1)->parse('I ♥ DOM::Tiny!'); preceding my $collection = $dom->preceding; my $collection = $dom->preceding('div ~ p'); Find all sibling elements before this node matching the CSS selector and return a collection containing these elements as DOM::Tiny objects. All selectors listed in "SELECTORS" are supported. # List tags of sibling elements before this node say $dom->preceding->map('tag')->join("\n"); preceding_nodes my $collection = $dom->preceding_nodes; Return a collection containing all sibling nodes before this node as DOM::Tiny objects. # "A" $dom->parse('A

C

')->at('p')->preceding_nodes->first->content; prepend $dom = $dom->prepend('

I ♥ DOM::Tiny!

'); Prepend HTML/XML fragment to this node (for all node types other than root). # "

Test

123

" $dom->parse('

123

') ->at('h2')->prepend('

Test

')->root; # "

Test 123

" $dom->parse('

123

') ->at('p')->child_nodes->first->prepend('Test ')->root; prepend_content $dom = $dom->prepend_content('

I ♥ DOM::Tiny!

'); Prepend HTML/XML fragment (for root and tag nodes) or raw content to this node's content. # "

Test123

" $dom->parse('

123

') ->at('h2')->prepend_content('Test')->root; # "
" $dom->parse('
') ->child_nodes->first->prepend_content(' Test')->root; # "

123Test

" $dom->parse('

Test

')->at('p')->prepend_content('123')->root; previous my $sibling = $dom->previous; Return DOM::Tiny object for previous sibling element, or undef if there are no more siblings. # "

Test

" $dom->parse('

Test

123

')->at('h2')->previous; previous_node my $sibling = $dom->previous_node; Return DOM::Tiny object for previous sibling node, or undef if there are no more siblings. # "123" $dom->parse('

123456

') ->at('b')->previous_node->previous_node; # " Test " $dom->parse('

123456

') ->at('b')->previous_node->content; remove my $parent = $dom->remove; Remove this node and return "root" (for root nodes) or "parent". # "
" $dom->parse('

Test

')->at('h1')->remove; # "

456

" $dom->parse('

123456

') ->at('p')->child_nodes->first->remove->root; replace my $parent = $dom->replace('
I ♥ DOM::Tiny!
'); Replace this node with HTML/XML fragment and return "root" (for root nodes) or "parent". # "

123

" $dom->parse('

Test

')->at('h1')->replace('

123

'); # "

123

" $dom->parse('

Test

') ->at('p')->child_nodes->[0]->replace('123')->root; root my $root = $dom->root; Return DOM::Tiny object for root node. strip my $parent = $dom->strip; Remove this element while preserving its content and return "parent". # "
Test
" $dom->parse('

Test

')->at('h1')->strip; tag my $tag = $dom->tag; $dom = $dom->tag('div'); This element's tag name. # List tag names of child elements say $dom->children->map('tag')->join("\n"); tap $dom = $dom->tap(sub {...}); Equivalent to "tap" in Mojo::Base. text my $trimmed = $dom->text; my $untrimmed = $dom->text(0); Extract text content from this element only (not including child elements), smart whitespace trimming is enabled by default. # "foo baz" $dom->parse("
foo\n

bar

baz\n
")->at('div')->text; # "foo\nbaz\n" $dom->parse("
foo\n

bar

baz\n
")->at('div')->text(0); to_string my $str = $dom->to_string; Render this node and its content to HTML/XML. # "Test" $dom->parse('
Test
')->at('div b')->to_string; tree my $tree = $dom->tree; $dom = $dom->tree(['root']); Document Object Model. Note that this structure should only be used very carefully since it is very dynamic. type my $type = $dom->type; This node's type, usually cdata, comment, doctype, pi, raw, root, tag or text. # "cdata" $dom->parse('')->child_nodes->first->type; # "comment" $dom->parse('')->child_nodes->first->type; # "doctype" $dom->parse('')->child_nodes->first->type; # "pi" $dom->parse('')->child_nodes->first->type; # "raw" $dom->parse('Test')->at('title')->child_nodes->first->type; # "root" $dom->parse('

Test

')->type; # "tag" $dom->parse('

Test

')->at('p')->type; # "text" $dom->parse('

Test

')->at('p')->child_nodes->first->type; val my $value = $dom->val; Extract value from form element (such as button, input, option, select and textarea), or return undef if this element has no value. In the case of select with multiple attribute, find option elements with selected attribute and return an array reference with all values, or undef if none could be found. # "a" $dom->parse('')->at('input')->val; # "b" $dom->parse('')->at('textarea')->val; # "c" $dom->parse('')->at('option')->val; # "d" $dom->parse('') ->at('select')->val; # "e" $dom->parse('') ->at('select')->val->[0]; # "on" $dom->parse('')->at('input')->val; wrap $dom = $dom->wrap('
'); Wrap HTML/XML fragment around this node (for all node types other than root), placing it as the last child of the first innermost element. # "

123Test

" $dom->parse('Test')->at('b')->wrap('

123

')->root; # "

Test

123
" $dom->parse('Test')->at('b')->wrap('

123
')->root; # "

Test

123

" $dom->parse('Test')->at('b')->wrap('

123

')->root; # "

Test

" $dom->parse('

Test

')->at('p')->child_nodes->first->wrap('')->root; wrap_content $dom = $dom->wrap_content('
'); Wrap HTML/XML fragment around this node's content (for root and tag nodes), placing it as the last children of the first innermost element. # "

123Test

" $dom->parse('

Test

')->at('p')->wrap_content('123')->root; # "

Test

123

" $dom->parse('Test')->wrap_content('

123

'); xml my $bool = $dom->xml; $dom = $dom->xml($bool); Disable HTML semantics in parser and activate case-sensitivity, defaults to auto detection based on XML declarations. COLLECTION METHODS Some DOM::Tiny methods return an array-based collection object based on Mojo::Collection, which can either be accessed directly as an array reference, or with the following methods. # Chain methods $collection->map(sub { ucfirst })->shuffle->each(sub { my ($word, $num) = @_; say "$num: $word"; }); # Access array directly to manipulate collection $collection->[23] += 100; say for @$collection; compact my $new = $collection->compact; Create a new collection with all elements that are defined and not an empty string. # $collection contains (0, 1, undef, 2, '', 3) $collection->compact->join(', '); # "0, 1, 2, 3" each my @elements = $collection->each; $collection = $collection->each(sub {...}); Evaluate callback for each element in collection or return all elements as a list if none has been provided. The element will be the first argument passed to the callback and is also available as $_. # Make a numbered list $collection->each(sub { my ($e, $num) = @_; say "$num: $e"; }); first my $first = $collection->first; my $first = $collection->first(qr/foo/); my $first = $collection->first(sub {...}); my $first = $collection->first($method); my $first = $collection->first($method, @args); Evaluate regular expression/callback for, or call method on, each element in collection and return the first one that matched the regular expression, or for which the callback/method returned true. The element will be the first argument passed to the callback and is also available as $_. # Longer version my $first = $collection->first(sub { $_->$method(@args) }); # Find first value that contains the word "tiny" my $interesting = $collection->first(qr/tiny/i); # Find first value that is greater than 5 my $greater = $collection->first(sub { $_ > 5 }); flatten my $new = $collection->flatten; Flatten nested collections/arrays recursively and create a new collection with all elements. # $collection contains (1, [2, [3, 4], 5, [6]], 7) $collection->flatten->join(', '); # "1, 2, 3, 4, 5, 6, 7" grep my $new = $collection->grep(qr/foo/); my $new = $collection->grep(sub {...}); my $new = $collection->grep($method); my $new = $collection->grep($method, @args); Evaluate regular expression/callback for, or call method on, each element in collection and create a new collection with all elements that matched the regular expression, or for which the callback/method returned true. The element will be the first argument passed to the callback and is also available as $_. # Longer version my $new = $collection->grep(sub { $_->$method(@args) }); # Find all values that contain the word "tiny" my $interesting = $collection->grep(qr/tiny/i); # Find all values that are greater than 5 my $greater = $collection->grep(sub { $_ > 5 }); join my $stream = $collection->join; my $stream = $collection->join("\n"); Turn collection into string. # Join all values with commas $collection->join(', '); last my $last = $collection->last; Return the last element in collection. map my $new = $collection->map(sub {...}); my $new = $collection->map($method); my $new = $collection->map($method, @args); Evaluate callback for, or call method on, each element in collection and create a new collection from the results. The element will be the first argument passed to the callback and is also available as $_. # Longer version my $new = $collection->map(sub { $_->$method(@args) }); # Append the word "tiny" to all values my $domified = $collection->map(sub { $_ . 'tiny' }); reduce my $result = $collection->reduce(sub {...}); my $result = $collection->reduce(sub {...}, $initial); Reduce elements in collection with callback, the first element will be used as initial value if none has been provided. # Calculate the sum of all values my $sum = $collection->reduce(sub { $a + $b }); # Count how often each value occurs in collection my $hash = $collection->reduce(sub { $a->{$b}++; $a }, {}); reverse my $new = $collection->reverse; Create a new collection with all elements in reverse order. slice my $new = $collection->slice(4 .. 7); Create a new collection with all selected elements. # $collection contains ('A', 'B', 'C', 'D', 'E') $collection->slice(1, 2, 4)->join(' '); # "B C E" shuffle my $new = $collection->shuffle; Create a new collection with all elements in random order. size my $size = $collection->size; Number of elements in collection. sort my $new = $collection->sort; my $new = $collection->sort(sub {...}); Sort elements based on return value of callback and create a new collection from the results. # Sort values case-insensitive my $case_insensitive = $collection->sort(sub { uc($a) cmp uc($b) }); tap $collection = $collection->tap(sub {...}); Equivalent to "tap" in Mojo::Base. to_array my $array = $collection->to_array; Turn collection into array reference. uniq my $new = $collection->uniq; my $new = $collection->uniq(sub {...}); my $new = $collection->uniq($method); my $new = $collection->uniq($method, @args); Create a new collection without duplicate elements, using the string representation of either the elements or the return value of the callback/method. # Longer version my $new = $collection->uniq(sub { $_->$method(@args) }); # $collection contains ('foo', 'bar', 'bar', 'baz') $collection->uniq->join(' '); # "foo bar baz" # $collection contains ([1, 2], [2, 1], [3, 2]) $collection->uniq(sub{ $_->[1] })->to_array; # "[[1, 2], [2, 1]]" BUGS Report any issues on the public bugtracker. AUTHOR Dan Book Code and tests adapted from Mojo::DOM, a lightweight DOM parser by the Mojolicious team. CONTRIBUTORS Matt S Trout (mst) COPYRIGHT AND LICENSE Copyright (c) 2008-2015 Sebastian Riedel. Copyright (c) 2015 "AUTHOR" and "CONTRIBUTORS" for adaptation to standalone format. This is free software, licensed under: The Artistic License 2.0 (GPL Compatible) SEE ALSO Mojo::DOM, HTML::TreeBuilder, XML::LibXML, XML::Twig, XML::Smart