#NAME
Mojo::DOM - Minimalistic HTML/XML DOM parser with CSS selectors
#SYNOPSIS
use Mojo::DOM;
# Parse
my $dom = Mojo::DOM->new('<div><p id="a">Test</p><p id="b">123</p></div>');
# 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('<p id="c">456</p>');
$dom->at('#c')->prepend($dom->new_tag('p', id => 'd', '789'));
$dom->find(':not(p)')->map('strip');
# Render
say "$dom";
#DESCRIPTION
Mojo::DOM is a minimalistic and relaxed HTML/XML DOM parser with CSS selector support. 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.
<!DOCTYPE html>
<html>
<head><title>Hello</title></head>
<body>World!</body>
</html>
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 Mojo::DOM objects, some methods like "attr" and "namespace" only apply to elements.
#HTML AND XML
Mojo::DOM 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 = Mojo::DOM->new('<P ID="greeting">Hi!</P>');
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 = Mojo::DOM->new('<?xml version="1.0"?><P ID="greeting">Hi!</P>');
say $dom->at('P[ID]')->text;
HTML or XML semantics can also be forced with the "xml" method.
# Force HTML semantics
my $dom = Mojo::DOM->new->xml(0)->parse('<P ID="greeting">Hi!</P>');
say $dom->at('p[id]')->text;
# Force XML semantics
my $dom = Mojo::DOM->new->xml(1)->parse('<P ID="greeting">Hi!</P>');
say $dom->at('P[ID]')->text;
#METHODS
Mojo::DOM implements the following methods.
#all_text
my $text = $dom->all_text;
Extract text content from all descendant nodes of this element. For HTML documents script
and style
elements are excluded.
# "foo\nbarbaz\n"
$dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->all_text;
#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 Mojo::Collection object containing these elements as Mojo::DOM objects. All selectors from "SELECTORS" in Mojo::DOM::CSS are supported.
# List tag names of ancestor elements
say $dom->ancestors->map('tag')->join("\n");
#append
$dom = $dom->append('<p>I ♥ Mojolicious!</p>');
$dom = $dom->append(Mojo::DOM->new);
Append HTML/XML fragment to this node (for all node types other than root
).
# "<div><h1>Test</h1><h2>123</h2></div>"
$dom->parse('<div><h1>Test</h1></div>')
->at('h1')->append('<h2>123</h2>')->root;
# "<p>Test 123</p>"
$dom->parse('<p>Test</p>')->at('p')
->child_nodes->first->append(' 123')->root;
#append_content
$dom = $dom->append_content('<p>I ♥ Mojolicious!</p>');
$dom = $dom->append_content(Mojo::DOM->new);
Append HTML/XML fragment (for root
and tag
nodes) or raw content to this node's content.
# "<div><h1>Test123</h1></div>"
$dom->parse('<div><h1>Test</h1></div>')
->at('h1')->append_content('123')->root;
# "<!-- Test 123 --><br>"
$dom->parse('<!-- Test --><br>')
->child_nodes->first->append_content('123 ')->root;
# "<p>Test<i>123</i></p>"
$dom->parse('<p>Test</p>')->at('p')->append_content('<i>123</i>')->root;
#at
my $result = $dom->at('div ~ p');
my $result = $dom->at('svg|line', svg => 'http://www.w3.org/2000/svg');
Find first descendant element of this element matching the CSS selector and return it as a Mojo::DOM object, or undef
if none could be found. All selectors from "SELECTORS" in Mojo::DOM::CSS are supported.
# Find first element with "svg" namespace definition
my $namespace = $dom->at('[xmlns\:svg]')->{'xmlns:svg'};
Trailing key/value pairs can be used to declare xml namespace aliases.
# "<rect />"
$dom->parse('<svg xmlns="http://www.w3.org/2000/svg"><rect /></svg>')
->at('svg|rect', svg => 'http://www.w3.org/2000/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 Mojo::Collection object containing all child nodes of this element as Mojo::DOM objects.
# "<p><b>123</b></p>"
$dom->parse('<p>Test<b>123</b></p>')->at('p')->child_nodes->first->remove;
# "<!DOCTYPE html>"
$dom->parse('<!DOCTYPE html><b>123</b>')->child_nodes->first;
# " Test "
$dom->parse('<b>123</b><!-- Test -->')->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 Mojo::Collection object containing these elements as Mojo::DOM objects. All selectors from "SELECTORS" in Mojo::DOM::CSS are supported.
# Show tag name of random child element
say $dom->children->shuffle->first->tag;
#content
my $str = $dom->content;
$dom = $dom->content('<p>I ♥ Mojolicious!</p>');
$dom = $dom->content(Mojo::DOM->new);
Return this node's content or replace it with HTML/XML fragment (for root
and tag
nodes) or raw content.
# "<b>Test</b>"
$dom->parse('<div><b>Test</b></div>')->at('div')->content;
# "<div><h1>123</h1></div>"
$dom->parse('<div><h1>Test</h1></div>')->at('h1')->content('123')->root;
# "<p><i>123</i></p>"
$dom->parse('<p>Test</p>')->at('p')->content('<i>123</i>')->root;
# "<div><h1></h1></div>"
$dom->parse('<div><h1>Test</h1></div>')->at('h1')->content('')->root;
# " Test "
$dom->parse('<!-- Test --><br>')->child_nodes->first->content;
# "<div><!-- 123 -->456</div>"
$dom->parse('<div><!-- Test -->456</div>')
->at('div')->child_nodes->first->content(' 123 ')->root;
#descendant_nodes
my $collection = $dom->descendant_nodes;
Return a Mojo::Collection object containing all descendant nodes of this element as Mojo::DOM objects.
# "<p><b>123</b></p>"
$dom->parse('<p><!-- Test --><b>123<!-- 456 --></b></p>')
->descendant_nodes->grep(sub { $_->type eq 'comment' })
->map('remove')->first;
# "<p><b>test</b>test</p>"
$dom->parse('<p><b>123</b>456</p>')
->at('p')->descendant_nodes->grep(sub { $_->type eq 'text' })
->map(content => 'test')->first->root;
#find
my $collection = $dom->find('div ~ p');
my $collection = $dom->find('svg|line', svg => 'http://www.w3.org/2000/svg');
Find all descendant elements of this element matching the CSS selector and return a Mojo::Collection object containing these elements as Mojo::DOM objects. All selectors from "SELECTORS" in Mojo::DOM::CSS 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;
Trailing key/value pairs can be used to declare xml namespace aliases.
# "<rect />"
$dom->parse('<svg xmlns="http://www.w3.org/2000/svg"><rect /></svg>')
->find('svg|rect', svg => 'http://www.w3.org/2000/svg')->first;
#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 Mojo::Collection object containing these elements as Mojo::DOM objects. All selectors from "SELECTORS" in Mojo::DOM::CSS 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 Mojo::Collection object containing all sibling nodes after this node as Mojo::DOM objects.
# "C"
$dom->parse('<p>A</p><!-- B -->C')->at('p')->following_nodes->last->content;
#matches
my $bool = $dom->matches('div ~ p');
my $bool = $dom->matches('svg|line', svg => 'http://www.w3.org/2000/svg');
Check if this element matches the CSS selector. All selectors from "SELECTORS" in Mojo::DOM::CSS are supported.
# True
$dom->parse('<p class="a">A</p>')->at('p')->matches('.a');
$dom->parse('<p class="a">A</p>')->at('p')->matches('p[class]');
# False
$dom->parse('<p class="a">A</p>')->at('p')->matches('.b');
$dom->parse('<p class="a">A</p>')->at('p')->matches('p[id]');
Trailing key/value pairs can be used to declare xml namespace aliases.
# True
$dom->parse('<svg xmlns="http://www.w3.org/2000/svg"><rect /></svg>')
->matches('svg|rect', svg => 'http://www.w3.org/2000/svg');
#namespace
my $namespace = $dom->namespace;
Find this element's namespace, or return undef
if none could be found.
# "http://www.w3.org/2000/svg"
Mojo::DOM->new('<svg xmlns:svg="http://www.w3.org/2000/svg"><svg:circle>3.14</svg:circle></svg>')->at('svg\:circle')->namespace;
# 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;
#new
my $dom = Mojo::DOM->new;
my $dom = Mojo::DOM->new('<foo bar="baz">I ♥ Mojolicious!</foo>');
Construct a new scalar-based Mojo::DOM object and "parse" HTML/XML fragment if necessary.
#new_tag
my $tag = Mojo::DOM->new_tag('div');
my $tag = $dom->new_tag('div');
my $tag = $dom->new_tag('div', id => 'foo', hidden => undef);
my $tag = $dom->new_tag('div', 'safe content');
my $tag = $dom->new_tag('div', id => 'foo', 'safe content');
my $tag = $dom->new_tag('div', data => {mojo => 'rocks'}, 'safe content');
my $tag = $dom->new_tag('div', id => 'foo', sub { 'unsafe content' });
Construct a new Mojo::DOM object for an HTML/XML tag with or without attributes and content. The data
attribute may contain a hash reference with key/value pairs to generate attributes from.
# "<br>"
$dom->new_tag('br');
# "<div></div>"
$dom->new_tag('div');
# "<div id="foo" hidden></div>"
$dom->new_tag('div', id => 'foo', hidden => undef);
# "<div>test & 123</div>"
$dom->new_tag('div', 'test & 123');
# "<div id="foo">test & 123</div>"
$dom->new_tag('div', id => 'foo', 'test & 123');
# "<div data-foo="1" data-bar="test">test & 123</div>""
$dom->new_tag('div', data => {foo => 1, Bar => 'test'}, 'test & 123');
# "<div id="foo">test & 123</div>"
$dom->new_tag('div', id => 'foo', sub { 'test & 123' });
# "<div>Hello<b>Mojo!</b></div>"
$dom->parse('<div>Hello</div>')->at('div')
->append_content($dom->new_tag('b', 'Mojo!'))->root;
#next
my $sibling = $dom->next;
Return Mojo::DOM object for next sibling element, or undef
if there are no more siblings.
# "<h2>123</h2>"
$dom->parse('<div><h1>Test</h1><h2>123</h2></div>')->at('h1')->next;
#next_node
my $sibling = $dom->next_node;
Return Mojo::DOM object for next sibling node, or undef
if there are no more siblings.
# "456"
$dom->parse('<p><b>123</b><!-- Test -->456</p>')
->at('b')->next_node->next_node;
# " Test "
$dom->parse('<p><b>123</b><!-- Test -->456</p>')
->at('b')->next_node->content;
#parent
my $parent = $dom->parent;
Return Mojo::DOM object for parent of this node, or undef
if this node has no parent.
# "<b><i>Test</i></b>"
$dom->parse('<p><b><i>Test</i></b></p>')->at('i')->parent;
#parse
$dom = $dom->parse('<foo bar="baz">I ♥ Mojolicious!</foo>');
Parse HTML/XML fragment with Mojo::DOM::HTML.
# Parse XML
my $dom = Mojo::DOM->new->xml(1)->parse('<foo>I ♥ Mojolicious!</foo>');
#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 Mojo::Collection object containing these elements as Mojo::DOM objects. All selectors from "SELECTORS" in Mojo::DOM::CSS 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 Mojo::Collection object containing all sibling nodes before this node as Mojo::DOM objects.
# "A"
$dom->parse('A<!-- B --><p>C</p>')->at('p')->preceding_nodes->first->content;
#prepend
$dom = $dom->prepend('<p>I ♥ Mojolicious!</p>');
$dom = $dom->prepend(Mojo::DOM->new);
Prepend HTML/XML fragment to this node (for all node types other than root
).
# "<div><h1>Test</h1><h2>123</h2></div>"
$dom->parse('<div><h2>123</h2></div>')
->at('h2')->prepend('<h1>Test</h1>')->root;
# "<p>Test 123</p>"
$dom->parse('<p>123</p>')
->at('p')->child_nodes->first->prepend('Test ')->root;
#prepend_content
$dom = $dom->prepend_content('<p>I ♥ Mojolicious!</p>');
$dom = $dom->prepend_content(Mojo::DOM->new);
Prepend HTML/XML fragment (for root
and tag
nodes) or raw content to this node's content.
# "<div><h2>Test123</h2></div>"
$dom->parse('<div><h2>123</h2></div>')
->at('h2')->prepend_content('Test')->root;
# "<!-- Test 123 --><br>"
$dom->parse('<!-- 123 --><br>')
->child_nodes->first->prepend_content(' Test')->root;
# "<p><i>123</i>Test</p>"
$dom->parse('<p>Test</p>')->at('p')->prepend_content('<i>123</i>')->root;
#previous
my $sibling = $dom->previous;
Return Mojo::DOM object for previous sibling element, or undef
if there are no more siblings.
# "<h1>Test</h1>"
$dom->parse('<div><h1>Test</h1><h2>123</h2></div>')->at('h2')->previous;
#previous_node
my $sibling = $dom->previous_node;
Return Mojo::DOM object for previous sibling node, or undef
if there are no more siblings.
# "123"
$dom->parse('<p>123<!-- Test --><b>456</b></p>')
->at('b')->previous_node->previous_node;
# " Test "
$dom->parse('<p>123<!-- Test --><b>456</b></p>')
->at('b')->previous_node->content;
#remove
my $parent = $dom->remove;
Remove this node and return "root" (for root
nodes) or "parent".
# "<div></div>"
$dom->parse('<div><h1>Test</h1></div>')->at('h1')->remove;
# "<p><b>456</b></p>"
$dom->parse('<p>123<b>456</b></p>')
->at('p')->child_nodes->first->remove->root;
#replace
my $parent = $dom->replace('<div>I ♥ Mojolicious!</div>');
my $parent = $dom->replace(Mojo::DOM->new);
Replace this node with HTML/XML fragment and return "root" (for root
nodes) or "parent".
# "<div><h2>123</h2></div>"
$dom->parse('<div><h1>Test</h1></div>')->at('h1')->replace('<h2>123</h2>');
# "<p><b>123</b></p>"
$dom->parse('<p>Test</p>')
->at('p')->child_nodes->[0]->replace('<b>123</b>')->root;
#root
my $root = $dom->root;
Return Mojo::DOM object for root
node.
#selector
my $selector = $dom->selector;
Get a unique CSS selector for this element.
# "ul:nth-child(1) > li:nth-child(2)"
$dom->parse('<ul><li>Test</li><li>123</li></ul>')->find('li')->last->selector;
# "p:nth-child(1) > b:nth-child(1) > i:nth-child(1)"
$dom->parse('<p><b><i>Test</i></b></p>')->at('i')->selector;
#strip
my $parent = $dom->strip;
Remove this element while preserving its content and return "parent".
# "<div>Test</div>"
$dom->parse('<div><h1>Test</h1></div>')->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 {...});
Alias for "tap" in Mojo::Base.
#text
my $text = $dom->text;
Extract text content from this element only (not including child elements).
# "bar"
$dom->parse("<div>foo<p>bar</p>baz</div>")->at('p')->text;
# "foo\nbaz\n"
$dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->at('div')->text;
To extract text content from all descendant nodes see "all_text".
#to_string
my $str = $dom->to_string;
Render this node and its content to HTML/XML.
# "<b>Test</b>"
$dom->parse('<div><b>Test</b></div>')->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('<![CDATA[Test]]>')->child_nodes->first->type;
# "comment"
$dom->parse('<!-- Test -->')->child_nodes->first->type;
# "doctype"
$dom->parse('<!DOCTYPE html>')->child_nodes->first->type;
# "pi"
$dom->parse('<?xml version="1.0"?>')->child_nodes->first->type;
# "raw"
$dom->parse('<title>Test</title>')->at('title')->child_nodes->first->type;
# "root"
$dom->parse('<p>Test</p>')->type;
# "tag"
$dom->parse('<p>Test</p>')->at('p')->type;
# "text"
$dom->parse('<p>Test</p>')->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('<input name=test value=a>')->at('input')->val;
# "b"
$dom->parse('<textarea>b</textarea>')->at('textarea')->val;
# "c"
$dom->parse('<option value="c">Test</option>')->at('option')->val;
# "d"
$dom->parse('<select><option selected>d</option></select>')
->at('select')->val;
# "e"
$dom->parse('<select multiple><option selected>e</option></select>')
->at('select')->val->[0];
# "on"
$dom->parse('<input name=test type=checkbox>')->at('input')->val;
#with_roles
my $new_class = Mojo::DOM->with_roles('Mojo::DOM::Role::One');
my $new_class = Mojo::DOM->with_roles('+One', '+Two');
$dom = $dom->with_roles('+One', '+Two');
Alias for "with_roles" in Mojo::Base.
#wrap
$dom = $dom->wrap('<div></div>');
$dom = $dom->wrap(Mojo::DOM->new);
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.
# "<p>123<b>Test</b></p>"
$dom->parse('<b>Test</b>')->at('b')->wrap('<p>123</p>')->root;
# "<div><p><b>Test</b></p>123</div>"
$dom->parse('<b>Test</b>')->at('b')->wrap('<div><p></p>123</div>')->root;
# "<p><b>Test</b></p><p>123</p>"
$dom->parse('<b>Test</b>')->at('b')->wrap('<p></p><p>123</p>')->root;
# "<p><b>Test</b></p>"
$dom->parse('<p>Test</p>')->at('p')->child_nodes->first->wrap('<b>')->root;
#wrap_content
$dom = $dom->wrap_content('<div></div>');
$dom = $dom->wrap_content(Mojo::DOM->new);
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.
# "<p><b>123Test</b></p>"
$dom->parse('<p>Test<p>')->at('p')->wrap_content('<b>123</b>')->root;
# "<p><b>Test</b></p><p>123</p>"
$dom->parse('<b>Test</b>')->wrap_content('<p></p><p>123</p>');
#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.
#OPERATORS
Mojo::DOM overloads the following operators.
#array
my @nodes = @$dom;
Alias for "child_nodes".
# "<!-- Test -->"
$dom->parse('<!-- Test --><b>123</b>')->[0];
#bool
my $bool = !!$dom;
Always true.
#hash
my %attrs = %$dom;
Alias for "attr".
# "test"
$dom->parse('<div id="test">Test</div>')->at('div')->{id};
#stringify
my $str = "$dom";
Alias for "to_string".