X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=README.pod;h=fc667fef37d1467389989b3f7b883c376c771166;hb=4b5e2513f7ea1ac132c1bb5c6732516d6cb1b917;hp=3c86b613d3d7da53d6e90d05f0f21ca327f3521c;hpb=5a70ee9d2295cf74db3b0e2476e906cdcaee1ff3;p=catagits%2FDOM-Tiny.git diff --git a/README.pod b/README.pod index 3c86b61..fc667fe 100644 --- a/README.pod +++ b/README.pod @@ -35,10 +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 @@ -76,8 +77,8 @@ names are lowercased and selectors need to be lowercase as well. my $dom = DOM::Tiny->new('

Hi!

'); say $dom->at('p[id]')->text; -If XML processing instructions are found, the parser will automatically switch -into XML mode and everything becomes case-sensitive. +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!

'); @@ -93,6 +94,264 @@ 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. @@ -125,8 +384,8 @@ whitespace trimming is enabled by default. my $collection = $dom->ancestors('div ~ p'); Find all ancestor elements of this node matching the CSS selector and return a -L object containing these elements as L -objects. All selectors from L are supported. +L containing these elements as L +objects. All selectors listed in L are supported. # List tag names of ancestor elements say $dom->ancestors->map('tag')->join("\n"); @@ -135,7 +394,7 @@ objects. All selectors from L are supported. $dom = $dom->append('

I ♥ DOM::Tiny!

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

Test

123

" $dom->parse('

Test

') @@ -168,8 +427,8 @@ node's content. my $result = $dom->at('div ~ p'); 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. +return it as a L object, or C if none could be found. All +selectors listed in L are supported. # Find first element with "svg" namespace definition my $namespace = $dom->at('[xmlns\:svg]')->{'xmlns:svg'}; @@ -196,7 +455,7 @@ This element's attributes. my $collection = $dom->child_nodes; -Return a L object containing all child nodes of this +Return a L containing all child nodes of this element as L objects. # "

123

" @@ -214,8 +473,8 @@ element as L objects. my $collection = $dom->children('div ~ p'); Find all child elements of this element matching the CSS selector and return a -L object containing these elements as L -objects. All selectors from L are supported. +L containing these elements as L +objects. All selectors listed in L are supported. # Show tag name of random child element say $dom->children->shuffle->first->tag; @@ -251,7 +510,7 @@ and C nodes) or raw content. my $collection = $dom->descendant_nodes; -Return a L object containing all descendant nodes of +Return a L containing all descendant nodes of this element as L objects. # "

123

" @@ -269,9 +528,8 @@ this element as L objects. my $collection = $dom->find('div ~ p'); Find all descendant elements of this element matching the CSS selector and -return a L object containing these elements as -L objects. All selectors from L are -supported. +return a L containing these elements as +L objects. All selectors listed in L are supported. # Find a specific element and extract information my $id = $dom->find('div')->[23]{id}; @@ -291,8 +549,8 @@ supported. my $collection = $dom->following('div ~ p'); Find all sibling elements after this node matching the CSS selector and return -a L object containing these elements as L -objects. All selectors from L are supported. +a L containing these elements as L +objects. All selectors listen in L are supported. # List tags of sibling elements after this node say $dom->following->map('tag')->join("\n"); @@ -301,7 +559,7 @@ objects. All selectors from L are supported. my $collection = $dom->following_nodes; -Return a L object containing all sibling nodes after +Return a L containing all sibling nodes after this node as L objects. # "C" @@ -311,8 +569,8 @@ 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'); @@ -326,7 +584,7 @@ L are supported. my $namespace = $dom->namespace; -Find this element's namespace or return C if none could be found. +Find this element's namespace, or return C if none could be found. # Find namespace for an element with namespace prefix my $namespace = $dom->at('svg > svg\:circle')->namespace; @@ -338,8 +596,8 @@ Find this element's namespace or return C if none could be found. my $sibling = $dom->next; -Return L object for next sibling element or C if there are no -more siblings. +Return L object for next sibling element, or C if there are +no more siblings. # "

123

" $dom->parse('

Test

123

')->at('h1')->next; @@ -348,7 +606,7 @@ more siblings. my $sibling = $dom->next_node; -Return L object for next sibling node or C if there are no +Return L object for next sibling node, or C if there are no more siblings. # "456" @@ -363,17 +621,20 @@ more siblings. my $parent = $dom->parent; -Return L object for parent of this node or C if this node has -no parent. +Return L object for parent of this node, or C if this node +has no parent. + + # "Test" + $dom->parse('

Test

')->at('i')->parent; =head2 parse $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); + my $dom = DOM::Tiny->new->xml(1)->parse('I ♥ DOM::Tiny!'); =head2 preceding @@ -381,8 +642,8 @@ Parse HTML/XML fragment with L. my $collection = $dom->preceding('div ~ p'); Find all sibling elements before this node matching the CSS selector and return -a L object containing these elements as L -objects. All selectors from L are supported. +a L containing these elements as L +objects. All selectors listed in L are supported. # List tags of sibling elements before this node say $dom->preceding->map('tag')->join("\n"); @@ -391,8 +652,8 @@ objects. All selectors from L are supported. my $collection = $dom->preceding_nodes; -Return a L object containing all sibling nodes before -this node as L objects. +Return a L containing all sibling nodes +before this node as L objects. # "A" $dom->parse('A

C

')->at('p')->preceding_nodes->first->content; @@ -401,7 +662,7 @@ this node as L objects. $dom = $dom->prepend('

I ♥ DOM::Tiny!

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

Test

123

" $dom->parse('

123

') @@ -433,7 +694,7 @@ node's content. my $sibling = $dom->previous; -Return L object for previous sibling element or C if there +Return L object for previous sibling element, or C if there are no more siblings. # "

Test

" @@ -443,7 +704,7 @@ are no more siblings. my $sibling = $dom->previous_node; -Return L object for previous sibling node or C if there are +Return L object for previous sibling node, or C if there are no more siblings. # "123" @@ -579,13 +840,13 @@ C, C or C. my $value = $dom->val; Extract value from form element (such as C