import re starttag = re.compile(r'<[a-zA-Z][-_.:a-zA-Z0-9]*\s*(' r'\s*([a-zA-Z_][-:.a-zA-Z_0-9]*)(\s*=\s*' r'(\'[^\']*\'|"[^"]*"|[-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~@]' r'[][\-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~\'"@]*(?=[\s>/<])))?' r')*\s*/?\s*(?=[<>])') foo = '