htmlparser.py

网络蜘蛛

"""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).

# Anand Sep29 2003 (Re)copied this module from Python 2.3 library.
#                  Added javascript (<script> tag) handler.
#                  This fixes problems with <script> tag parsing
#                  and helps to save jscript (.js) files embedded
#                  inside <script>...</script> tags.
# Anand Sep 30 2003 Added code to handle java applets ((<applet>) tag).
# Feb 10 2004        Anand   1.3.1 bug fix version.

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*>')

#( for javascript parsing added 29-09-03 abp)
jscriptclose = re.compile(r'</script>', re.IGNORECASE)      
jscriptsrc=re.compile(r'src=([\'\"])?.[^>]*\.js([\'\"\s+])?', re.IGNORECASE)

#( for java applets added 30-09-03 abp)
appletclose = re.compile(r'</applet>', re.IGNORECASE)

#( for java applet code -> .class files)
appletcode=re.compile(r'code=([\'\"])?[a-zA-Z_][-.a-zA-Z0-9:_]*([\'\"\s+])?', re.IGNORECASE)
#( for java applet codebase url )
appletcodebase=re.compile(r'codebase=([\'\"])?.[^>^\s+]*([\'\"\s+])?', re.IGNORECASE)

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):
                # script parse code added abp 29-09-03
                # this need to come before parse_starttag to avoid
                # errors with javascript parsing, otherwise parse_starttag
                # fails for javascript tags.
                if startswith("<script", i) or startswith("<SCRIPT", i):
                    k = self.parse_script_tag(i)
                # same for java applet tag
                elif startswith('<applet', i) or startswith('<APPLET', i):
                    k = self.parse_applet_tag(i)                    
                elif 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:
                    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 comment, return end or -1 if not terminated
    def parse_comment(self, i, report=1):
        rawdata = self.rawdata
        assert rawdata[i:i+4] == '<!--', 'unexpected call to parse_comment()'
        match = commentclose.search(rawdata, i+4)