Regular expression for parsing HTML

html.regex

~

(?(DEFINE)
	(?<entity>
		&
		(
			[a-z][a-z0-9]+     # named entity
			|
			\#\d+              # decimal number
			|
			\#x[0-9a-f]+       # hexadecimal number
		)
		;
	)


	(?<attribute>
		\s+                     # at least one whitespace character before the attribute
		[^\s"'<>=`/]+           # attribute name
		(
			\s*=\s*             # equals sign before the value
			(
				"               # value enclosed in double quotes
					(
						[^"]    # any character except double quote
						|
						(?&entity)  # or HTML entity
					)*
				"
				|
				'               # value enclosed in single quotes
					(
						[^']    # any character except single quote
						|
						(?&entity)  # or HTML entity
					)*
				'
				|
				[^\s"'<>=`]+     # value without quotes
			)
		)?                       # value is optional
	)


	(?<void_element>
		<                  # start of tag
		(                  # element name
			img|hr|br|input|meta|area|embed|keygen|source|base|col
			|link|param|basefont|frame|isindex|wbr|command|track
		)
		(?&attribute)*     # optional attributes
		\s*
		/?                 # optional /
		>                  # end of tag
	)


	(?<special_element>
		<                  # start tag
		(?<special_element_name>
			script|style|textarea|title  # element name
		)
		(?&attribute)*     # optional attributes
		\s*
		>                  # end of start tag
		(?>                # atomic group
			.*?            # smallest possible number of any characters including new lines
			</             # end tag
			(?P=special_element_name)
		)
		\s*
		>                  # end of end tag
	)


	(?<element>
		<                  # start tag
		(?<element_name>
			[a-z][^\s/>]*  # element name
		)
		(?&attribute)*     # optional attributes
		\s*
		>                  # end of start tag
		(?&content)*
		</                 # end tag
		(?P=element_name)
		\s*
		>                  # end of end tag
	)


	(?<comment>
		<!--
		(?>                # atomic group
			.*?            # smallest possible number of any characters including new lines
			-->
		)
	)


	(?<doctype>
		<!doctype
		\s
		[^>]*              # any characters except '>'
		>
	)
)


\s*
(?&doctype)?               # optional doctype
(?<content>
	(?&void_element)       # void element
	|
	(?&special_element)    # special element
	|
	(?&element)            # paired element
	|
	(?&comment)            # comment
	|
	(?&entity)             # entity
	|
	[^<]                   # character
)*

~xis