X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=README.pod;fp=README.pod;h=a2937c47e19af75aed2f864b3174582086c49db4;hb=9a5f1e3f0633370ed08c12af1542a9e38870c84a;hp=dc7e0593c87c7b7e8e7053d9310cc8ca46fb0369;hpb=8563f5274bc14e4ee3994b6ceefc66d816d87f1d;p=catagits%2FDOM-Tiny.git diff --git a/README.pod b/README.pod index dc7e059..a2937c4 100644 --- a/README.pod +++ b/README.pod @@ -2,8 +2,6 @@ =encoding utf8 -=for Pod::Coverage TO_JSON - =head1 NAME DOM::Tiny - Minimalistic HTML/XML DOM parser with CSS selectors @@ -37,10 +35,11 @@ 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 @@ -95,6 +94,40 @@ XML detection can also be disabled with the L method. my $dom = DOM::Tiny->new->xml(0)->parse('

Hi!

'); say $dom->at('p[id]')->text; +=head1 OPERATORS + +L overloads the following operators. + +=head2 array + + my @nodes = @$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. @@ -128,7 +161,7 @@ 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"); @@ -171,7 +204,7 @@ 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'}; @@ -217,7 +250,7 @@ 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; @@ -272,8 +305,7 @@ 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}; @@ -294,7 +326,7 @@ 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"); @@ -313,8 +345,8 @@ 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'); @@ -372,7 +404,7 @@ 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); @@ -384,7 +416,7 @@ 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 $dom->preceding->map('tag')->join("\n"); @@ -643,45 +675,11 @@ children of the first innermost element. Disable HTML semantics in parser and activate case-sensitivity, defaults to auto detection based on processing instructions. -=head1 OPERATORS - -L overloads the following operators. - -=head2 array - - my @nodes = @$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 { @@ -888,6 +886,226 @@ callback/method. # $collection contains ([1, 2], [2, 1], [3, 2]) $collection->uniq(sub{ $_->[1] })->to_array; # "[[1, 2], [2, 1]]" +=head1 SELECTORS + +L uses a CSS selector engine based on L. All CSS +selectors that make sense for a standalone parser are supported. + +=head2 * + +Any element. + + my $all = $dom->find('*'); + +=head2 E + +An element of type C. + + my $title = $dom->at('title'); + +=head2 E[foo] + +An C element with a C attribute. + + my $links = $dom->find('a[href]'); + +=head2 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]'); + +=head2 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. + +=head2 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]'); + +=head2 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 = $dom->find('input[name^=f]'); + +=head2 E[foo$="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]'); + +=head2 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]'); + +=head2 E:root + +An C element, root of the document. + + my $root = $dom->at(':root'); + +=head2 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)'); + +=head2 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)'); + +=head2 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)'); + +=head2 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)'); + +=head2 E:first-child + +An C element, first child of its parent. + + my $first = $dom->find('div p:first-child'); + +=head2 E:last-child + +An C element, last child of its parent. + + my $last = $dom->find('div p:last-child'); + +=head2 E:first-of-type + +An C element, first sibling of its type. + + my $first = $dom->find('div p:first-of-type'); + +=head2 E:last-of-type + +An C element, last sibling of its type. + + my $last = $dom->find('div p:last-of-type'); + +=head2 E:only-child + +An C element, only child of its parent. + + my $lonely = $dom->find('div p:only-child'); + +=head2 E:only-of-type + +An C element, only sibling of its type. + + my $lonely = $dom->find('div p:only-of-type'); + +=head2 E:empty + +An C element that has no children (including text nodes). + + my $empty = $dom->find(':empty'); + +=head2 E:checked + +A user interface element C which is checked (for instance a radio-button or +checkbox). + + my $input = $dom->find(':checked'); + +=head2 E.warning + +An C element whose class is "warning". + + my $warning = $dom->find('div.warning'); + +=head2 E#myid + +An C element with C equal to "myid". + + my $foo = $dom->at('div#foo'); + +=head2 E:not(s) + +An C element that does not match simple selector C. + + my $others = $dom->find('div p:not(:first-child)'); + +=head2 E F + +An C element descendant of an C element. + + my $headlines = $dom->find('div h1'); + +=head2 E E F + +An C element child of an C element. + + my $headlines = $dom->find('html > body > div > h1'); + +=head2 E + F + +An C element immediately preceded by an C element. + + my $second = $dom->find('h1 + h2'); + +=head2 E ~ F + +An C element preceded by an C element. + + my $second = $dom->find('h1 ~ h2'); + +=head2 E, F, G + +Elements of type C, C and C. + + my $headlines = $dom->find('h1, h2, h3'); + +=head2 E[foo=bar][bar=baz] + +An C element whose attributes match all following attribute selectors. + + my $links = $dom->find('a[foo^=b][foo$=ar]'); + =head1 BUGS Report any issues on the public bugtracker. @@ -908,4 +1126,6 @@ This is free software, licensed under: L, L, L, L, L +=for Pod::Coverage TO_JSON + =cut