html.parser无法完全解析网页之BUG的修正

<a href="www.baidu.com"style="hot">badidu</a>

locatestarttagend = re.compile(r"""
  <[a-zA-Z][-.a-zA-Z0-9:_]*          # tag name
  (?:\s+                             # whitespace before attribute name
    (?:[a-zA-Z_][-.:a-zA-Z0-9_]*     # attribute name
      (?:\s*=\s*                     # value indicator
        (?:‘[^‘]*‘                   # LITA-enclosed value
          |\"[^\"]*\"                # LIT-enclosed value
          |[^‘\">\s]+                # bare value
         )
       )?
     )
   )*
  \s*                                # trailing whitespace
""", re.VERBOSE)

locatestarttagend = re.compile(r"""
  <[a-zA-Z][-.a-zA-Z0-9:_]*              # tag name
  (?:\s*(?=>)                            # tag without attributes
    |\s+                                 # whitespace before attribute name
     (?:\s*                              # whitespace between attributes
        (?:[a-zA-Z_][-.:a-zA-Z0-9_]*     # attribute name
          (?:\s*=\s*                     # value indicator
            (?:‘[^‘]*‘                   # LITA-enclosed value
              |\"[^\"]*\"                # LIT-enclosed value
              |[^‘\">\s]+                # bare value
             )
           )?
        )
     )*
     \s*                                # trailing whitespace
  )
""", re.VERBOSE)