一个高手的htmlparser笔记

先来大致看看HTMLParser的源代码吧：

 """A parser for HTML and XHTML."""

 # This file is based on sgmllib.py, but the API is slightly different.

 # XXX There should be a way to distinguish between PCDATA (parsed
 # character data -- the normal case), RCDATA (replaceable character
 # data -- only char and entity references and end tags are special)
 # and CDATA (character data -- only end tags are special).


 import markupbase
 import re

 # Regular expressions used for parsing

 interesting_normal = re.compile('[&<]')
 interesting_cdata = re.compile(r'<(/|\Z)')
 incomplete = re.compile('&[a-zA-Z#]')

 entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]')
 charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]')

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

 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)
 endendtag = re.compile('>')
 endtagfind = re.compile('</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>')


 class HTMLParseError(Exception):
     """Exception raised for all parse errors."""

     def __init__(self, msg, position=(None, None)):
         assert msg
         self.msg = msg
         self.lineno = position[0]
         self.offset = position[1]

     def __str__(self):
         result = self.msg
         if self.lineno is not None:
             result = result + ", at line %d" % self.lineno
         if self.offset is not None:
             result = result + ", column %d" % (self.offset + 1)
         return result


 class HTMLParser(markupbase.ParserBase):
     """Find tags and other markup and call handler functions.

     Usage:
         p = HTMLParser()
         p.feed(data)
         ...
         p.close()

     Start tags are handled by calling self.handle_starttag() or
     self.handle_startendtag(); end tags by self.handle_endtag().  The
     data between tags is passed from the parser to the derived class
     by calling self.handle_data() with the data as argument (the data
     may be split up in arbitrary chunks).  Entity references are
     passed by calling self.handle_entityref() with the entity
     reference as the argument.  Numeric character references are
     passed to self.handle_charref() with the string containing the
     reference as the argument.
     """

     CDATA_CONTENT_ELEMENTS = ("script", "style")


     def __init__(self):
         """Initialize and reset this instance."""
         self.reset()

     def reset(self):
         """Reset this instance.  Loses all unprocessed data."""
         self.rawdata = ''
         self.lasttag = '???'
         self.interesting = interesting_normal
         markupbase.ParserBase.reset(self)

     def feed(self, data):
         """Feed data to the parser.

         Call this as often as you want, with as little or as much text
         as you want (may include '\n').
         """
         self.rawdata = self.rawdata + data
         self.goahead(0)

     def close(self):
         """Handle any buffered data."""
         self.goahead(1)

     def error(self, message):
         raise HTMLParseError(message, self.getpos())

     __starttag_text = None

     def get_starttag_text(self):
         """Return full source of start tag: '<...>'."""
         return self.__starttag_text

     def set_cdata_mode(self):
         self.interesting = interesting_cdata

     def clear_cdata_mode(self):
         self.interesting = interesting_normal

     # Internal -- handle data as far as reasonable.  May leave state
     # and data to be processed by a subsequent call.  If 'end' is
     # true, force handling all data as if followed by EOF marker.
     def goahead(self, end):
         rawdata = self.rawdata
         i = 0
         n = len(rawdata)
         while i < n:
             match = self.interesting.search(rawdata, i) # < or &
             if match:
                 j = match.start()
             else:
                 j = n
             if i < j: self.handle_data(rawdata[i:j])
             i = self.updatepos(i, j)
             if i == n: break
             startswith = rawdata.startswith
             if startswith('<', i):
                 if starttagopen.match(rawdata, i): # < + letter
                     k = self.parse_starttag(i)
                 elif startswith("</", i):
                     k = self.parse_endtag(i)
                 elif startswith("<!--", i):
                     k = self.parse_comment(i)
                 elif startswith("<?", i):
                     k = self.parse_pi(i)
                 elif startswith("<!", i):
                     k = self.parse_declaration(i)
                 elif (i + 1) < n:
                     self.handle_data("<")
                     k = i + 1
                 else:
                     break
                 if k < 0:
                     if end:
                         self.error("EOF in middle of construct")
                     break
                 i = self.updatepos(i, k)
             elif startswith("&#", i):
                 match = charref.match(rawdata, i)
                 if match:
                     name = match.group()[2:-1]
                     self.handle_charref(name)
                     k = match.end()
                     if not startswith(';', k-1):
                         k = k - 1
                     i = self.updatepos(i, k)
                     continue
                 else:
                     if ";" in rawdata[i:]: #bail by consuming &#
                         self.handle_data(rawdata[0:2])
                         i = self.updatepos(i, 2)
                     break
             elif startswith('&', i):
                 match = entityref.match(rawdata, i)
                 if match:
                     name = match.group(1)
                     self.handle_entityref(name)
                     k = match.end()
                     if not startswith(';', k-1):
                         k = k - 1
                     i = self.updatepos(i, k)
                     continue
                 match = incomplete.match(rawdata, i)
                 if match:
                     # match.group() will contain at least 2 chars
                     if end and match.group() == rawdata[i:]:
                         self.error("EOF in middle of entity or char ref")
                     # incomplete
                     break
                 elif (i + 1) < n:
                     # not the end of the buffer, and can't be confused
                     # with some other construct
                     self.handle_data("&")
                     i = self.updatepos(i, i + 1)
                 else:
                     break
             else:
                 assert 0, "interesting.search() lied"
         # end while
         if end and i < n:
             self.handle_data(rawdata[i:n])
             i = self.updatepos(i, n)
         self.rawdata = rawdata[i:]

     # Internal -- parse processing instr, return end or -1 if not terminated
     def parse_pi(self, i):
         rawdata = self.rawdata
         assert rawdata[i:i+2] == '<?', 'unexpected call to parse_pi()'
         match = piclose.search(rawdata, i+2) # >
         if not match:
             return -1
         j = match.start()
         self.handle_pi(rawdata[i+2: j])
         j = match.end()
         return j

     # Internal -- handle starttag, return end or -1 if not terminated
     def parse_starttag(self, i):
         self.__starttag_text = None
         endpos = self.check_for_whole_start_tag(i)
         if endpos < 0:
             return endpos
         rawdata = self.rawdata
         self.__starttag_text = rawdata[i:endpos]

         # Now parse the data between i+1 and j into a tag and attrs
         attrs = []
         match = tagfind.match(rawdata, i+1)
         assert match, 'unexpected call to parse_starttag()'
         k = match.end()
         self.lasttag = tag = rawdata[i+1:k].lower()

         while k < endpos:
             m = attrfind.match(rawdata, k)
             if not m:
                 break
             attrname, rest, attrvalue = m.group(1, 2, 3)
             if not rest:
                 attrvalue = None
             elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
                  attrvalue[:1] == '"' == attrvalue[-1:]:
                 attrvalue = attrvalue[1:-1]
                 attrvalue = self.unescape(attrvalue)
             attrs.append((attrname.lower(), attrvalue))
             k = m.end()

         end = rawdata[k:endpos].strip()
         if end not in (">", "/>"):
             lineno, offset = self.getpos()
             if "\n" in self.__starttag_text:
                 lineno = lineno + self.__starttag_text.count("\n")
                 offset = len(self.__starttag_text) \
                          - self.__starttag_text.rfind("\n")
             else:
                 offset = offset + len(self.__starttag_text)
             self.error("junk characters in start tag: %r"
                        % (rawdata[k:endpos][:20],))
         if end.endswith('/>'):
             # XHTML-style empty tag: <span attr="value" />
             self.handle_startendtag(tag, attrs)
         else:
             self.handle_starttag(tag, attrs)
             if tag in self.CDATA_CONTENT_ELEMENTS:
                 self.set_cdata_mode()
         return endpos

     # Internal -- check to see if we have a complete starttag; return end
     # or -1 if incomplete.
     def check_for_whole_start_tag(self, i):
         rawdata = self.rawdata
         m = locatestarttagend.match(rawdata, i)
         if m:
             j = m.end()
             next = rawdata[j:j+1]
             if next == ">":
                 return j + 1
             if next == "/":
                 if rawdata.startswith("/>", j):
                     return j + 2
                 if rawdata.startswith("/", j):
                     # buffer boundary
                     return -1
                 # else bogus input
                 self.updatepos(i, j + 1)
                 self.error("malformed empty start tag")
             if next == "":
                 # end of input
                 return -1
             if next in ("abcdefghijklmnopqrstuvwxyz=/"
                         "ABCDEFGHIJKLMNOPQRSTUVWXYZ"):
                 # end of input in or before attribute value, or we have the
                 # '/' from a '/>' ending
                 return -1
             self.updatepos(i, j)
             self.error("malformed start tag")
         raise AssertionError("we should not get here!")

     # Internal -- parse endtag, return end or -1 if incomplete
     def parse_endtag(self, i):
         rawdata = self.rawdata
         assert rawdata[i:i+2] == "</", "unexpected call to parse_endtag"
         match = endendtag.search(rawdata, i+1) # >
         if not match:
             return -1
         j = match.end()
         match = endtagfind.match(rawdata, i) # </ + tag + >
         if not match:
             self.error("bad end tag: %r" % (rawdata[i:j],))
         tag = match.group(1)
         self.handle_endtag(tag.lower())
         self.clear_cdata_mode()
         return j

     # Overridable -- finish processing of start+end tag: <tag.../>
     def handle_startendtag(self, tag, attrs):
         self.handle_starttag(tag, attrs)
         self.handle_endtag(tag)

     # Overridable -- handle start tag
     def handle_starttag(self, tag, attrs):
         pass

     # Overridable -- handle end tag
     def handle_endtag(self, tag):
         pass

     # Overridable -- handle character reference
     def handle_charref(self, name):
         pass

     # Overridable -- handle entity reference
     def handle_entityref(self, name):
         pass

     # Overridable -- handle data
     def handle_data(self, data):
         pass

     # Overridable -- handle comment
     def handle_comment(self, data):
         pass

     # Overridable -- handle declaration
     def handle_decl(self, decl):
         pass

     # Overridable -- handle processing instruction
     def handle_pi(self, data):
         pass

     def unknown_decl(self, data):
         self.error("unknown declaration: %r" % (data,))

     # Internal -- helper to remove special character quoting
     entitydefs = None
     def unescape(self, s):
         if '&' not in s:
             return s
         def replaceEntities(s):
             s = s.groups()[0]
             if s[0] == "#":
                 s = s[1:]
                 if s[0] in ['x','X']:
                     c = int(s[1:], 16)
                 else:
                     c = int(s)
                 return unichr(c)
             else:
                 # Cannot use name2codepoint directly, because HTMLParser supports apos,
                 # which is not part of HTML 4
                 import htmlentitydefs
                 if HTMLParser.entitydefs is None:
                     entitydefs = HTMLParser.entitydefs = {'apos':u"'"}
                     for k, v in htmlentitydefs.name2codepoint.iteritems():
                         entitydefs[k] = unichr(v)
                 try:
                     return self.entitydefs[s]
                 except KeyError:
                     return '&'+s+';'

         return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));", replaceEntities, s)

大家可以看到，其实内部的很多的方法都是没有实现的，所以需要我们继承这个类，自己去实现一些方法。关于HTMLParser的方法，大家可以参考官方文档：

http://docs.python.org/library/htmlparser.html#HTMLParser.HTMLParser （英文，笔者没有多少时间去翻译这些）

另外，给一个例子大家对照着看看，我相信这么简单的例子，大家都能看懂的。

假设我们要处理的文件在d盘根目录下，名字为hello.html,文件的内容为：

 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">

 <html xmlns="http://www.w3.org/1999/xhtml">

     <head>

         <meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>

         <title>Rollen Holt - cnblogs</title>
         <meta name="keywords" content="Rollen Holt,rollenholt" />

         <link type="text/css" rel="stylesheet" href="http://www.cnblogs.com/css/common.css"/>
         <link id="MainCss" type="text/css" rel="stylesheet" href="http://www.cnblogs.com/Skins/kubrick/style.css"/>
         <link type="text/css" rel="stylesheet" href="http://www.cnblogs.com/css/common2.css"/>

         <link type="text/css" rel="stylesheet" href="http://common.cnblogs.com/css/shCore.css"/>

         <link type="text/css" rel="stylesheet" href="http://common.cnblogs.com/css/shThemeDefault.css"/>

         <link title="RSS" type="application/rss+xml" rel="alternate" href="http://www.cnblogs.com/rollenholt/rss"/>

         <link title="RSD" type="application/rsd+xml" rel="EditURI" href="http://www.cnblogs.com/rollenholt/rsd.xml"/>
         <link type="application/wlwmanifest+xml" rel="wlwmanifest" href="http://www.cnblogs.com/rollenholt/wlwmanifest.xml"/>

         <script src="http://common.cnblogs.com/script/jquery.js" type="text/javascript"></script>

         <script src="/script/common.js" type="text/javascript"></script>

         <script src="http://common.cnblogs.com/script/jquery.json-2.2.min.js" type="text/javascript"></script>

         <script type="text/javascript" src="http://common.cnblogs.com/script/shCore.js"></script>

         <script type="text/javascript" src="http://common.cnblogs.com/script/shLanguage.js"></script>

     </head>

     <body>

         <a name="top"></a>

         <form method="post" action="" id="Form1">

             <div class="aspNetHidden">

                 <input type="hidden" name="__VIEWSTATE" id="__VIEWSTATE" value="" />

             </div>
         </form>
     </body>
 </html>

我们的python代码为：

 #coding=utf-8

 from HTMLParser import HTMLParser

 class MyParser(HTMLParser):
     """一个简单的HTMLparser的例子"""

     def handle_decl(self, decl):
         """处理头文档"""
         HTMLParser.handle_decl(self, decl)
         print decl

     def handle_starttag(self, tag, attrs):
         """处理起始标签"""
         HTMLParser.handle_starttag(self, tag, attrs)
         if not HTMLParser.get_starttag_text(self).endswith("/>"):
             print "<",tag,">"

     def handle_data(self, data):
         """处理文本元素"""
         HTMLParser.handle_data(self, data)
         print data,

     def handle_endtag(self, tag):
         """处理结束标签"""
         HTMLParser.handle_endtag(self, tag)
         if not HTMLParser.get_starttag_text(self).endswith("/>"):
             print "</",tag,">"

     def handle_startendtag(self, tag, attrs):
         """处理自闭标签"""
         HTMLParser.handle_startendtag(self, tag, attrs)
         print