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">A</p><p id="b">B</p></div>');
# Find
say $dom->at('#b')->text;
say $dom->find('p')->pluck('text');
# Walk
say $dom->div->p->[0]->text;
say $dom->div->children('p')->first->{id};
# Iterate
$dom->find('p[id]')->each(sub { say shift->{id} });
# Loop
for my $e ($dom->find('p[id]')->each) {
say $e->text;
}
# Modify
$dom->div->p->[1]->append('<p id="c">C</p>');
# 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 XML, so you should not use it for validation.
CASE SENSITIVITY
Mojo::DOM defaults to HTML semantics, that means all tags and attributes are lowercased and selectors need to be lowercase as well.
my $dom = Mojo::DOM->new('<P ID="greeting">Hi!</P>');
say $dom->at('p')->text;
say $dom->p->{id};If XML processing instructions are found, the parser will automatically switch into XML mode and everything becomes case sensitive.
my $dom = Mojo::DOM->new('<?xml version="1.0"?><P ID="greeting">Hi!</P>');
say $dom->at('P')->text;
say $dom->P->{ID};XML detection can also be disabled with the xml method.
# Force XML semantics
$dom->xml(1);
# Force HTML semantics
$dom->xml(0);METHODS
Mojo::DOM implements the following methods.
new
my $dom = Mojo::DOM->new;
my $dom = Mojo::DOM->new('<foo bar="baz">test</foo>');Construct a new Mojo::DOM object.
all_text
my $trimmed = $dom->all_text;
my $untrimmed = $dom->all_text(0);Extract all text content from DOM structure, smart whitespace trimming is enabled by default.
# "foo bar baz"
$dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->div->all_text;
# "foo\nbarbaz\n"
$dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->div->all_text(0);append
$dom = $dom->append('<p>Hi!</p>');Append to element.
# "<div><h1>A</h1><h2>B</h2></div>"
$dom->parse('<div><h1>A</h1></div>')->at('h1')->append('<h2>B</h2>')->root;append_content
$dom = $dom->append_content('<p>Hi!</p>');Append to element content.
# "<div><h1>AB</h1></div>"
$dom->parse('<div><h1>A</h1></div>')->at('h1')->append_content('B')->root;at
my $result = $dom->at('html title');Find a single element with CSS selectors. All selectors from Mojo::DOM::CSS are supported.
# Find first element with "svg" namespace definition
my $namespace = $dom->at('[xmlns\:svg]')->{'xmlns:svg'};attrs
my $attrs = $dom->attrs;
my $foo = $dom->attrs('foo');
$dom = $dom->attrs({foo => 'bar'});
$dom = $dom->attrs(foo => 'bar');Element attributes.
charset
my $charset = $dom->charset;
$dom = $dom->charset('UTF-8');Charset used for decoding and encoding HTML/XML.
children
my $collection = $dom->children;
my $collection = $dom->children('div');Return a Mojo::Collection object containing the children of this element, similar to find.
# Show type of random child element
say $dom->children->shuffle->first->type;content_xml
my $xml = $dom->content_xml;Render content of this element to XML. Note that the XML will be encoded if a charset has been defined.
# "<b>test</b>"
$dom->parse('<div><b>test</b></div>')->div->content_xml;find
my $collection = $dom->find('html title');Find elements with CSS selectors and return a Mojo::Collection object. All selectors from 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')->pluck('text')->each;namespace
my $namespace = $dom->namespace;Find element 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;parent
my $parent = $dom->parent;Parent of element.
parse
$dom = $dom->parse('<foo bar="baz">test</foo>');Parse HTML/XML document with Mojo::DOM::HTML.
# Parse UTF-8 encoded XML
my $dom = Mojo::DOM->new->charset('UTF-8')->xml(1)->parse($xml);prepend
$dom = $dom->prepend('<p>Hi!</p>');Prepend to element.
# "<div><h1>A</h1><h2>B</h2></div>"
$dom->parse('<div><h2>B</h2></div>')->at('h2')->prepend('<h1>A</h1>')->root;prepend_content
$dom = $dom->prepend_content('<p>Hi!</p>');Prepend to element content.
# "<div><h2>AB</h2></div>"
$dom->parse('<div><h2>B</h2></div>')->at('h2')->prepend_content('A')->root;remove
my $old = $dom->remove;Remove element.
# "<div></div>"
$dom->parse('<div><h1>A</h1></div>')->at('h1')->remove->root;replace
my $old = $dom->replace('<div>test</div>');Replace element.
# "<div><h2>B</h2></div>"
$dom->parse('<div><h1>A</h1></div>')->at('h1')->replace('<h2>B</h2>')->root;
# "<div></div>"
$dom->parse('<div><h1>A</h1></div>')->at('h1')->replace('')->root;replace_content
$dom = $dom->replace_content('test');Replace element content.
# "<div><h1>B</h1></div>"
$dom->parse('<div><h1>A</h1></div>')->at('h1')->replace_content('B')->root;
# "<div><h1></h1></div>"
$dom->parse('<div><h1>A</h1></div>')->at('h1')->replace_content('')->root;root
my $root = $dom->root;Find root node.
text
my $trimmed = $dom->text;
my $untrimmed = $dom->text(0);Extract text content from element only (not including child elements), smart whitespace trimming is enabled by default.
# "foo baz"
$dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->div->text;
# "foo\nbaz\n"
$dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->div->text(0);text_after
my $trimmed = $dom->text_after;
my $untrimmed = $dom->text_after(0);Extract text content immediately following element, smart whitespace trimming is enabled by default.
# "baz"
$dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->div->p->text_after;
# "baz\n"
$dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->div->p->text_after(0);text_before
my $trimmed = $dom->text_before;
my $untrimmed = $dom->text_before(0);Extract text content immediately preceding element, smart whitespace trimming is enabled by default.
# "foo"
$dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->div->p->text_before;
# "foo\n"
$dom->parse("<div>foo\n<p>bar</p>baz\n</div>")->div->p->text_before(0);to_xml
my $xml = $dom->to_xml;
my $xml = "$dom";Render this element and its content to XML. Note that the XML will be encoded if a charset has been defined.
# "<b>test</b>"
$dom->parse('<div><b>test</b></div>')->div->b->to_xml;tree
my $tree = $dom->tree;
$dom = $dom->tree(['root', [qw(text lalala)]]);Document Object Model.
type
my $type = $dom->type;
$dom = $dom->type('div');Element type.
# List types of child elements
say $dom->children->pluck('type');xml
my $xml = $dom->xml;
$dom = $dom->xml(1);Disable HTML semantics in parser and activate case sensitivity, defaults to auto detection based on processing instructions.
CHILD ELEMENTS
In addition to the methods above, many child elements are also automatically available as object methods, which return a Mojo::DOM or Mojo::Collection object, depending on number of children.
say $dom->p->text;
say $dom->div->[23]->text;
say $dom->div->pluck('text');ELEMENT ATTRIBUTES
Direct hash reference access to element attributes is also possible.
say $dom->{foo};
say $dom->div->{id};