[HTML Regex] Regular expression pattern for matching HTML tags.

html.regex

<(?(?=!--)!--[\s\S]*--|(?(?=\?)\?[\s\S]*\?|(?(?=\/)\/[^.\d-][^\/\]'"[!#$%&()*+,;<=>?@^`{|}~ ]*|[^.\d-][^\/\]'"[!#$%&()*+,;<=>?@^`{|}~ ]*(?:\s[^.\d-][^\/\]'"[!#$%&()*+,;<=>?@^`{|}~ ]*(?:=(?:"[^"]*"|'[^']*'|[^'"<\s]*))?)*)\s?\/?))>

<														# Tags always begin with <.
	(?													# What if...
		(?=!--)												# We have a comment?
			!--[\s\S]*--										# If so, anything goes between <!-- and -->.
			|											# OR
			(?											# What if...
				(?=\?)										# We have a scripting tag?
					\?[\s\S]*\?								# If so, anything goes between <? and ?>.
					|									# OR
					(?									# What if...
						(?=\/)								# We have a closing tag?
							\/							# It should begin with a /.
							[^.\d-]							# Then the tag name, which can't begin with any of these characters.
							[^\/\]'"[!#$%&()*+,;<=>?@^`{|}~ ]*			# And can't contain any of these characters.
							|							# OR... we must have some other tag.
							[^.\d-]							# Tag names can't begin with these characters.
							[^\/\]'"[!#$%&()*+,;<=>?@^`{|}~ ]*			# And can't contain any of these characters.
								(?:						# Do we have any attributes?
									\s					# If so, they'll begin with a space character.
									[^.\d-]					# Followed by a name that doesn't begin with any of these characters.
									[^\/\]'"[!#$%&()*+,;<=>?@^`{|}~ ]*	# And doesn't contain any of these characters.
										(?:				# Does our attribute have a value?
											=			# If so, the value will begin with an = sign.
											(?:			# The value could be:
											"[^"]*"			# Wrapped in double quotes.
											|			# OR
											'[^']*'			# Wrapped in single quotes.
											|			# OR
											[^'"<\s]*		# Not wrapped in anything.
											)			# That does it for our attribute value.
										)?				# If the attribute is boolean it won't need a value.
								)*						# We could have any number of attributes.
					)									# That does it for our closing vs other tag check.
					\s?									# There could be some space characters before the closing >.
					\/?									# There might also be a / if this is a self-closing tag.
			)											# That does it for our script vs html tag check.
	)													# That does it for our comment vs script tag check.
>														# Tags always end with a >.