Source code for html.parser


"""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 re
import _markupbase

from html import unescape


__all__ = ['HTMLParser']

# Regular expressions used for parsing

interesting_normal = re.compile('[&)
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(')
piclose = re.compile('>')
commentclose = re.compile(r'--\s*>')
# Note:
#  1) if you change tagfind/attrfind remember to update locatestarttagend too;
#  2) if you change tagfind/attrfind and/or locatestarttagend the parser will
#     explode, so don't do it.
# see http://www.w3.org/TR/html5/tokenization.html#tag-open-state
# and http://www.w3.org/TR/html5/tokenization.html#tag-name-state
tagfind_tolerant = re.compile(r'([a-zA-Z][^\t\n\r\f />\x00]*)(?:\s|/(?!>))*')
attrfind_tolerant = re.compile(
    r'((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*'
    r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*')
locatestarttagend_tolerant = re.compile(r"""
  \x00]*       # tag name
  (?:[\s/]*                          # optional whitespace before attribute name
    (?:(?<=['"\s/])[^\s/>][^\s/=>]*  # attribute name
      (?:\s*=+\s*                    # value indicator
        (?:'[^']*'                   # LITA-enclosed value
          |"[^"]*"                   # LIT-enclosed value
          |(?!['"])[^>\s]*           # bare value
         )
        \s*                          # possibly followed by a space
       )?(?:\s|/(?!>))*
     )*
   )?
  \s*                                # trailing whitespace
""", re.VERBOSE)
endendtag = re.compile('>')
# the HTML 5 spec, section 8.1.2.2, doesn't allow spaces between
#  and the tag name, so maybe this should be fixed
endtagfind = re.compile(r'\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>')



[docs]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).  If convert_charrefs is
    True the character references are converted automatically to the
    corresponding Unicode character (and self.handle_data() is no
    longer split in chunks), otherwise they are passed by calling
    self.handle_entityref() or self.handle_charref() with the string
    containing respectively the named or numeric reference as the
    argument.
    """

    CDATA_CONTENT_ELEMENTS = ("script", "style")

    def __init__(self, *, convert_charrefs=True):
        """Initialize and reset this instance.

        If convert_charrefs is True (the default), all character references
        are automatically converted to the corresponding Unicode characters.
        """
        self.convert_charrefs = convert_charrefs
        self.reset()

[docs]    def reset(self):
        """Reset this instance.  Loses all unprocessed data."""
        self.rawdata = ''
        self.lasttag = '???'
        self.interesting = interesting_normal
        self.cdata_elem = None
        _markupbase.ParserBase.reset(self)

[docs]    def feed(self, data):
        r"""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)

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

    __starttag_text = None

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

    def set_cdata_mode(self, elem):
        self.cdata_elem = elem.lower()
        self.interesting = re.compile(r'\s*%s\s*>' % self.cdata_elem, re.I)

    def clear_cdata_mode(self):
        self.interesting = interesting_normal
        self.cdata_elem = None

    # 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:
            if self.convert_charrefs and not self.cdata_elem:
                j = rawdata.find(', i)
                if j < 0:
                    # if we can't find the next 
                    # or there's more text incoming.  If the latter is True,
                    # we can't pass the text to handle_data in case we have
                    # a charref cut in half at end.  Try to determine if
                    # this is the case before proceeding by looking for an
                    # & near the end and see if it's followed by a space or ;.
                    amppos = rawdata.rfind('&', max(i, n-34))
                    if (amppos >= 0 and
                        not re.compile(r'[\s;]').search(rawdata, amppos)):
                        break  # wait till we get all the text
                    j = n
            else:
                match = self.interesting.search(rawdata, i)  # < or &
                if match:
                    j = match.start()
                else:
                    if self.cdata_elem:
                        break
                    j = n
            if i < j:
                if self.convert_charrefs and not self.cdata_elem:
                    self.handle_data(unescape(rawdata[i:j]))
                else:
                    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("