X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=lib%2FDOM%2FTiny.pm;h=77e4d914aeda53d2214ccc55977d987b08a71abc;hb=2d9f516571abb22d42ea26ffaf07bda8a29314f0;hp=cf6cddc398bbb604125249cc3c2d802dd6a6aa17;hpb=8563f5274bc14e4ee3994b6ceefc66d816d87f1d;p=catagits%2FDOM-Tiny.git diff --git a/lib/DOM/Tiny.pm b/lib/DOM/Tiny.pm index cf6cddc..77e4d91 100644 --- a/lib/DOM/Tiny.pm +++ b/lib/DOM/Tiny.pm @@ -12,15 +12,15 @@ use overload use Carp 'croak'; use DOM::Tiny::_Collection; -use DOM::Tiny::CSS; -use DOM::Tiny::HTML; +use DOM::Tiny::_CSS; +use DOM::Tiny::_HTML; use Scalar::Util qw(blessed weaken); -our $VERSION = '0.001'; +our $VERSION = '0.002'; sub new { my $class = shift; - my $self = bless \DOM::Tiny::HTML->new, ref $class || $class; + my $self = bless \DOM::Tiny::_HTML->new, ref $class || $class; return @_ ? $self->parse(@_) : $self; } @@ -67,7 +67,7 @@ sub content { my $type = $self->type; if ($type eq 'root' || $type eq 'tag') { return $self->_content(0, 1, @_) if @_; - my $html = DOM::Tiny::HTML->new(xml => $self->xml); + my $html = DOM::Tiny::_HTML->new(xml => $self->xml); return join '', map { $html->tree($_)->render } _nodes($self->tree); } @@ -153,7 +153,7 @@ sub tag { return $self; } -sub tap { shift->DOM::Tiny::_Collection::tap(@_) } +sub tap { DOM::Tiny::_Collection::tap(@_) } sub text { shift->_all_text(0, @_) } @@ -167,7 +167,8 @@ sub val { my $self = shift; # "option" - return $self->{value} // $self->text if (my $tag = $self->tag) eq 'option'; + return defined($self->{value}) ? $self->{value} : $self->text + if (my $tag = $self->tag) eq 'option'; # "textarea", "input" or "button" return $tag eq 'textarea' ? $self->text : $self->{value} if $tag ne 'select'; @@ -213,7 +214,7 @@ sub _all_text { sub _ancestors { my ($self, $root) = @_; - return unless my $tree = $self->_parent; + return () unless my $tree = $self->_parent; my @ancestors; do { push @ancestors, $tree } while ($tree->[0] eq 'tag') && ($tree = $tree->[3]); @@ -244,7 +245,7 @@ sub _content { return $self; } -sub _css { DOM::Tiny::CSS->new(tree => shift->tree) } +sub _css { DOM::Tiny::_CSS->new(tree => shift->tree) } sub _delegate { my ($self, $method) = (shift, shift); @@ -269,7 +270,7 @@ sub _link { sub _maybe { $_[1] ? $_[0]->_build($_[1], $_[0]->xml) : undef } sub _nodes { - return unless my $tree = shift; + return () unless my $tree = shift; my @nodes = @$tree[_start($tree) .. $#$tree]; return shift() ? grep { $_->[0] eq 'tag' } @nodes : @nodes; } @@ -283,7 +284,7 @@ sub _offset { sub _parent { $_[0]->tree->[$_[0]->type eq 'tag' ? 3 : 2] } -sub _parse { DOM::Tiny::HTML->new(xml => shift->xml)->parse(shift)->tree } +sub _parse { DOM::Tiny::_HTML->new(xml => shift->xml)->parse(shift)->tree } sub _replace { my ($self, $parent, $child, @nodes) = @_; @@ -389,8 +390,6 @@ sub _wrap { =encoding utf8 -=for Pod::Coverage TO_JSON - =head1 NAME DOM::Tiny - Minimalistic HTML/XML DOM parser with CSS selectors @@ -424,10 +423,11 @@ DOM::Tiny - Minimalistic HTML/XML DOM parser with CSS selectors =head1 DESCRIPTION -L is a minimalistic and relaxed pure-perl HTML/XML DOM parser with -support for the L and -L based on L. It -will even try to interpret broken HTML and XML, so you should not use it for +L is a minimalistic and relaxed pure-perl HTML/XML DOM parser based +on L. It supports the L +and L, and +matching based on L. It will +even try to interpret broken HTML and XML, so you should not use it for validation. =head1 NODES AND ELEMENTS @@ -482,6 +482,264 @@ XML detection can also be disabled with the L method. my $dom = DOM::Tiny->new->xml(0)->parse('

Hi!

'); say $dom->at('p[id]')->text; +=head1 SELECTORS + +L uses a CSS selector engine based on L. All CSS +selectors that make sense for a standalone parser are supported. + +=over + +=item Z<>* + +Any element. + + my $all = $dom->find('*'); + +=item E + +An element of type C. + + my $title = $dom->at('title'); + +=item E[foo] + +An C element with a C attribute. + + my $links = $dom->find('a[href]'); + +=item E[foo="bar"] + +An C element whose C attribute value is exactly equal to C. + + my $case_sensitive = $dom->find('input[type="hidden"]'); + my $case_sensitive = $dom->find('input[type=hidden]'); + +=item E[foo="bar" i] + +An C element whose C attribute value is exactly equal to any +(ASCII-range) case-permutation of C. 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 +L, which is still a work +in progress. + +=item E[foo~="bar"] + +An C element whose C attribute value is a list of whitespace-separated +values, one of which is exactly equal to C. + + my $foo = $dom->find('input[class~="foo"]'); + my $foo = $dom->find('input[class~=foo]'); + +=item E[foo^="bar"] + +An C element whose C attribute value begins exactly with the string +C. + + my $begins_with = $dom->find('input[name^="f"]'); + my $begins_with = $dom->find('input[name^=f]'); + +=item E[foo$="bar"] + +An C element whose C attribute value ends exactly with the string +C. + + my $ends_with = $dom->find('input[name$="o"]'); + my $ends_with = $dom->find('input[name$=o]'); + +=item E[foo*="bar"] + +An C element whose C attribute value contains the substring C. + + my $contains = $dom->find('input[name*="fo"]'); + my $contains = $dom->find('input[name*=fo]'); + +=item E:root + +An C element, root of the document. + + my $root = $dom->at(':root'); + +=item E:nth-child(n) + +An C element, the C 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)'); + +=item E:nth-last-child(n) + +An C element, the C 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)'); + +=item E:nth-of-type(n) + +An C element, the C 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)'); + +=item E:nth-last-of-type(n) + +An C element, the C 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)'); + +=item E:first-child + +An C element, first child of its parent. + + my $first = $dom->find('div p:first-child'); + +=item E:last-child + +An C element, last child of its parent. + + my $last = $dom->find('div p:last-child'); + +=item E:first-of-type + +An C element, first sibling of its type. + + my $first = $dom->find('div p:first-of-type'); + +=item E:last-of-type + +An C element, last sibling of its type. + + my $last = $dom->find('div p:last-of-type'); + +=item E:only-child + +An C element, only child of its parent. + + my $lonely = $dom->find('div p:only-child'); + +=item E:only-of-type + +An C element, only sibling of its type. + + my $lonely = $dom->find('div p:only-of-type'); + +=item E:empty + +An C element that has no children (including text nodes). + + my $empty = $dom->find(':empty'); + +=item E:checked + +A user interface element C which is checked (for instance a radio-button or +checkbox). + + my $input = $dom->find(':checked'); + +=item E.warning + +An C element whose class is "warning". + + my $warning = $dom->find('div.warning'); + +=item E#myid + +An C element with C equal to "myid". + + my $foo = $dom->at('div#foo'); + +=item E:not(s) + +An C element that does not match simple selector C. + + my $others = $dom->find('div p:not(:first-child)'); + +=item E F + +An C element descendant of an C element. + + my $headlines = $dom->find('div h1'); + +=item E E F + +An C element child of an C element. + + my $headlines = $dom->find('html > body > div > h1'); + +=item E + F + +An C element immediately preceded by an C element. + + my $second = $dom->find('h1 + h2'); + +=item E ~ F + +An C element preceded by an C element. + + my $second = $dom->find('h1 ~ h2'); + +=item E, F, G + +Elements of type C, C and C. + + my $headlines = $dom->find('h1, h2, h3'); + +=item E[foo=bar][bar=baz] + +An C element whose attributes match all following attribute selectors. + + my $links = $dom->find('a[foo^=b][foo$=ar]'); + +=back + +=head1 OPERATORS + +L overloads the following operators. + +=head2 array + + my @nodes = @$dom; + +Alias for L. + + # "" + $dom->parse('123')->[0]; + +=head2 bool + + my $bool = !!$dom; + +Always true. + +=head2 hash + + my %attrs = %$dom; + +Alias for L. + + # "test" + $dom->parse('
Test
')->at('div')->{id}; + +=head2 stringify + + my $str = "$dom"; + +Alias for L. + =head1 METHODS L implements the following methods. @@ -515,7 +773,7 @@ whitespace trimming is enabled by default. Find all ancestor elements of this node matching the CSS selector and return a L containing these elements as L -objects. All selectors from L are supported. +objects. All selectors listed in L are supported. # List tag names of ancestor elements say $dom->ancestors->map('tag')->join("\n"); @@ -558,7 +816,7 @@ node's content. Find first descendant element of this element matching the CSS selector and return it as a L object or return C if none could be found. -All selectors from L are supported. +All selectors listed in L are supported. # Find first element with "svg" namespace definition my $namespace = $dom->at('[xmlns\:svg]')->{'xmlns:svg'}; @@ -604,7 +862,7 @@ element as L objects. Find all child elements of this element matching the CSS selector and return a L containing these elements as L -objects. All selectors from L are supported. +objects. All selectors listed in L are supported. # Show tag name of random child element say $dom->children->shuffle->first->tag; @@ -659,8 +917,7 @@ this element as L objects. Find all descendant elements of this element matching the CSS selector and return a L containing these elements as -L objects. All selectors from L are -supported. +L objects. All selectors listed in L are supported. # Find a specific element and extract information my $id = $dom->find('div')->[23]{id}; @@ -681,7 +938,7 @@ supported. Find all sibling elements after this node matching the CSS selector and return a L containing these elements as L -objects. All selectors from L are supported. +objects. All selectors listen in L are supported. # List tags of sibling elements after this node say $dom->following->map('tag')->join("\n"); @@ -700,8 +957,8 @@ this node as L objects. my $bool = $dom->matches('div ~ p'); -Check if this element matches the CSS selector. All selectors from -L are supported. +Check if this element matches the CSS selector. All selectors listed in +L are supported. # True $dom->parse('

A

')->at('p')->matches('.a'); @@ -759,7 +1016,7 @@ no parent. $dom = $dom->parse('I ♥ DOM::Tiny!'); -Parse HTML/XML fragment with L. +Parse HTML/XML fragment. # Parse XML my $dom = DOM::Tiny->new->xml(1)->parse($xml); @@ -771,7 +1028,7 @@ Parse HTML/XML fragment with L. Find all sibling elements before this node matching the CSS selector and return a L containing these elements as L -objects. All selectors from L are supported. +objects. All selectors listed in L are supported. # List tags of sibling elements before this node say $dom->preceding->map('tag')->join("\n"); @@ -1030,45 +1287,11 @@ children of the first innermost element. Disable HTML semantics in parser and activate case-sensitivity, defaults to auto detection based on processing instructions. -=head1 OPERATORS - -L overloads the following operators. - -=head2 array - - my @nodes = @$dom; - -Alias for L. - - # "" - $dom->parse('123')->[0]; - -=head2 bool - - my $bool = !!$dom; - -Always true. - -=head2 hash - - my %attrs = %$dom; - -Alias for L. - - # "test" - $dom->parse('
Test
')->at('div')->{id}; - -=head2 stringify - - my $str = "$dom"; - -Alias for L. - =head1 COLLECTION METHODS -Some L methods return an array-based collection object, which can -either be accessed directly as an array reference, or with the following -methods. +Some L methods return an array-based collection object based on +L, which can either be accessed directly as an array +reference, or with the following methods. # Chain methods $collection->map(sub { ucfirst })->shuffle->each(sub { @@ -1121,8 +1344,8 @@ passed to the callback and is also available as C<$_>. # Longer version my $first = $collection->first(sub { $_->$method(@args) }); - # Find first value that contains the word "dom" - my $interesting = $collection->first(qr/dom/i); + # 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 { $_ > 5 }); @@ -1153,8 +1376,8 @@ C<$_>. # Longer version my $new = $collection->grep(sub { $_->$method(@args) }); - # Find all values that contain the word "dom" - my $interesting = $collection->grep(qr/dom/i); + # 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 { $_ > 5 }); @@ -1188,8 +1411,8 @@ passed to the callback and is also available as C<$_>. # Longer version my $new = $collection->map(sub { $_->$method(@args) }); - # Append the word "dom" to all values - my $domified = $collection->map(sub { $_ . 'dom' }); + # Append the word "tiny" to all values + my $domified = $collection->map(sub { $_ . 'tiny' }); =head2 reduce @@ -1283,6 +1506,14 @@ Report any issues on the public bugtracker. Dan Book +=head1 CONTRIBUTORS + +=over + +=item Matt S Trout (mst) + +=back + =head1 COPYRIGHT AND LICENSE This software is Copyright (c) 2015 by Dan Book. @@ -1293,4 +1524,8 @@ This is free software, licensed under: =head1 SEE ALSO -L, L, L, L, L +L, L, L, L, L + +=for Pod::Coverage TO_JSON + +=cut