htmllib
index
/usr/lib/python2.2/htmllib.py

HTML 2.0 parser.
 
See the HTML 2.0 specification:
http://www.w3.org/hypertext/WWW/MarkUp/html-spec/html-spec_toc.html

 
Classes
            
sgmllib.SGMLParser(markupbase.ParserBase)
HTMLParser
 
class HTMLParser(sgmllib.SGMLParser)
       
  
Method resolution order:
HTMLParser
sgmllib.SGMLParser
markupbase.ParserBase

Methods defined here:
__init__(self, formatter, verbose=0)
anchor_bgn(self, href, name, type)
anchor_end(self)
ddpop(self, bl=0)
do_base(self, attrs)
do_br(self, attrs)
do_dd(self, attrs)
do_dt(self, attrs)
do_hr(self, attrs)
do_img(self, attrs)
do_isindex(self, attrs)
do_li(self, attrs)
do_link(self, attrs)
do_meta(self, attrs)
do_nextid(self, attrs)
do_p(self, attrs)
do_plaintext(self, attrs)
end_a(self)
end_address(self)
end_b(self)
end_blockquote(self)
end_body(self)
end_cite(self)
end_code(self)
end_dir(self)
end_dl(self)
end_em(self)
end_h1(self)
end_h2(self)
end_h3(self)
end_h4(self)
end_h5(self)
end_h6(self)
end_head(self)
end_html(self)
end_i(self)
end_kbd(self)
end_listing(self)
end_menu(self)
end_ol(self)
end_pre(self)
end_samp(self)
end_strong(self)
end_title(self)
end_tt(self)
end_ul(self)
end_var(self)
end_xmp(self)
handle_data(self, data)
handle_image(self, src, alt, *args)
save_bgn(self)
save_end(self)
start_a(self, attrs)
start_address(self, attrs)
start_b(self, attrs)
start_blockquote(self, attrs)
start_body(self, attrs)
start_cite(self, attrs)
start_code(self, attrs)
start_dir(self, attrs)
start_dl(self, attrs)
start_em(self, attrs)
start_h1(self, attrs)
start_h2(self, attrs)
start_h3(self, attrs)
start_h4(self, attrs)
start_h5(self, attrs)
start_h6(self, attrs)
start_head(self, attrs)
start_html(self, attrs)
start_i(self, attrs)
start_kbd(self, attrs)
start_listing(self, attrs)
start_menu(self, attrs)
start_ol(self, attrs)
start_pre(self, attrs)
start_samp(self, attrs)
start_strong(self, attrs)
start_title(self, attrs)
start_tt(self, attrs)
start_ul(self, attrs)
start_var(self, attrs)
start_xmp(self, attrs)
unknown_endtag(self, tag)
unknown_starttag(self, tag, attrs)

Data and non-method functions defined here:
__doc__ = None
__module__ = 'htmllib'
entitydefs = {'AElig': '\xc6', 'Aacute': '\xc1', 'Acirc': '\xc2', 'Agrave': '\xc0', 'Alpha': 'Α', 'Aring': '\xc5', 'Atilde': '\xc3', 'Auml': '\xc4', 'Beta': 'Β', 'Ccedil': '\xc7', ...}

Methods inherited from sgmllib.SGMLParser:
close(self)
Handle the remaining data.
error(self, message)
feed(self, data)
Feed some data to the parser.
 
        Call this as often as you want, with as little or as much text
        as you want (may include '
').  (This just saves the text,
        all the processing is done by goahead().)
finish_endtag(self, tag)
# Internal -- finish processing of end tag
finish_shorttag(self, tag, data)
# Internal -- finish parsing of <tag/data/ (same as <tag>data</tag>)
finish_starttag(self, tag, attrs)
# Internal -- finish processing of start tag
# Return -1 for unknown tag, 0 for open-only tag, 1 for balanced tag
get_starttag_text(self)
goahead(self, end)
# 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.
handle_charref(self, name)
Handle character reference, no need to override.
handle_comment(self, data)
# Example -- handle comment, could be overridden
handle_decl(self, decl)
# Example -- handle declaration, could be overridden
handle_endtag(self, tag, method)
# Overridable -- handle end tag
handle_entityref(self, name)
Handle entity references.
 
There should be no need to override this method; it can be
tailored by setting up the self.entitydefs mapping appropriately.
handle_pi(self, data)
# Example -- handle processing instruction, could be overridden
handle_starttag(self, tag, method, attrs)
# Overridable -- handle start tag
parse_comment(self, i, report=1)
# Internal -- parse comment, return length or -1 if not terminated
parse_endtag(self, i)
# Internal -- parse endtag
parse_pi(self, i)
# Internal -- parse processing instr, return length or -1 if not terminated
parse_starttag(self, i)
# Internal -- handle starttag, return length or -1 if not terminated
report_unbalanced(self, tag)
# Example -- report an unbalanced </...> tag.
reset(self)
Reset this instance. Loses all unprocessed data.
setliteral(self, *args)
Enter literal mode (CDATA).
 
Intended for derived classes only.
setnomoretags(self)
Enter literal mode (CDATA) till EOF.
 
Intended for derived classes only.
unknown_charref(self, ref)
unknown_entityref(self, ref)

Data and non-method functions inherited from sgmllib.SGMLParser:
_SGMLParser__starttag_text = None
_decl_otherchars = '='

Methods inherited from markupbase.ParserBase:
_parse_doctype_attlist(self, i, declstartpos)
# Internal -- scan past <!ATTLIST declarations
_parse_doctype_element(self, i, declstartpos)
# Internal -- scan past <!ELEMENT declarations
_parse_doctype_entity(self, i, declstartpos)
# Internal -- scan past <!ENTITY declarations
_parse_doctype_notation(self, i, declstartpos)
# Internal -- scan past <!NOTATION declarations
_parse_doctype_subset(self, i, declstartpos)
# Internal -- scan past the internal subset in a <!DOCTYPE declaration,
# returning the index just past any whitespace following the trailing ']'.
_scan_name(self, i, declstartpos)
# Internal -- scan a name token and the new position and the token, or
# return -1 if we've reached the end of the buffer.
getpos(self)
Return current line number and offset.
parse_declaration(self, i)
# Internal -- parse declaration (for use by subclasses).
unknown_decl(self, data)
# To be overridden -- handlers for unknown objects
updatepos(self, i, j)
# Internal -- update line number and offset.  This should be
# called for each piece of data exactly once, in order -- in other
# words the concatenation of all the input strings to this
# function should be exactly the entire input.
 
Functions
            
test(args=None)
 
Data
             AS_IS = None
__all__ = ['HTMLParser']
__file__ = '/usr/lib/python2.2/htmllib.pyc'
__name__ = 'htmllib'