Package Pyblosxom :: Module tools :: Class Stripper
[show private | hide private]
[frames | no frames]

Class Stripper

ParserBase --+    
             |    
    SGMLParser --+
                 |
                Stripper


Strips HTML

An SGMLParser subclass to strip away HTMLs
Method Summary
  __init__(self)
  gettext(self)
  handle_data(self, data)
  unknown_endtag(self, tag)
  unknown_starttag(self, tag, attrs)
    Inherited from SGMLParser
  close(self)
Handle the remaining data.
  error(self, message)
  feed(self, data)
Feed some data to the parser.
  finish_endtag(self, tag)
  finish_shorttag(self, tag, data)
  finish_starttag(self, tag, attrs)
  get_starttag_text(self)
  goahead(self, end)
  handle_charref(self, name)
Handle character reference, no need to override.
  handle_comment(self, data)
  handle_decl(self, decl)
  handle_endtag(self, tag, method)
  handle_entityref(self, name)
Handle entity references.
  handle_pi(self, data)
  handle_starttag(self, tag, method, attrs)
  parse_endtag(self, i)
  parse_pi(self, i)
  parse_starttag(self, i)
  report_unbalanced(self, tag)
  reset(self)
Reset this instance.
  setliteral(self, *args)
Enter literal mode (CDATA).
  setnomoretags(self)
Enter literal mode (CDATA) till EOF.
  unknown_charref(self, ref)
  unknown_entityref(self, ref)
    Inherited from ParserBase
  getpos(self)
Return current line number and offset.
  parse_comment(self, i, report)
  parse_declaration(self, i)
  parse_marked_section(self, i, report)
  unknown_decl(self, data)
  updatepos(self, i, j)
  _parse_doctype_attlist(self, i, declstartpos)
  _parse_doctype_element(self, i, declstartpos)
  _parse_doctype_entity(self, i, declstartpos)
  _parse_doctype_notation(self, i, declstartpos)
  _parse_doctype_subset(self, i, declstartpos)
  _scan_name(self, i, declstartpos)

Class Variable Summary
    Inherited from SGMLParser
dict entitydefs = {'amp': '&', 'lt': '<', 'gt': '>', 'apos': ...
str _decl_otherchars = '='

Generated by Epydoc 2.1 on Tue Feb 7 21:43:58 2006 http://epydoc.sf.net