Doc/lib/libhtmlparser.tex

\section{\module{HTMLParser} ---
         Simple HTML and XHTML parser}

\declaremodule{standard}{HTMLParser}
\modulesynopsis{A simple parser that can handle HTML and XHTML.}

This module defines a class \class{HTMLParser} which serves as the
basis for parsing text files formatted in HTML\index{HTML} (HyperText
Mark-up Language) and XHTML.\index{XHTML}


\begin{classdesc}{HTMLParser}{}
The \class{HTMLParser} class is instantiated without arguments.

An HTMLParser instance is fed HTML data and calls handler functions
when tags begin and end.  The \class{HTMLParser} class is meant to be
overridden by the user to provide a desired behavior.
\end{classdesc}


\class{HTMLParser} instances have the following methods:

\begin{methoddesc}{reset}{}
Reset the instance.  Loses all unprocessed data.  This is called
implicitly at instantiation time.
\end{methoddesc}

\begin{methoddesc}{feed}{data}
Feed some text to the parser.  It is processed insofar as it consists
of complete elements; incomplete data is buffered until more data is
fed or \method{close()} is called.
\end{methoddesc}

\begin{methoddesc}{close}{}
Force processing of all buffered data as if it were followed by an
end-of-file mark.  This method may be redefined by a derived class to
define additional processing at the end of the input, but the
redefined version should always call the \class{HTMLParser} base class
method \method{close()}.
\end{methoddesc}

\begin{methoddesc}{getpos}{}
Return current line number and offset.
\end{methoddesc}

\begin{methoddesc}{get_starttag_text}{}
Return the text of the most recently opened start tag.  This should
not normally be needed for structured processing, but may be useful in
dealing with HTML ``as deployed'' or for re-generating input with
minimal changes (whitespace between attributes can be preserved,
etc.).
\end{methoddesc}

\begin{methoddesc}{handle_starttag}{tag, attrs} 
This method is called to handle the start of a tag.  It is intended to
be overridden by a derived class; the base class implementation does
nothing.  

The \var{tag} argument is the name of the tag converted to
lower case.  The \var{attrs} argument is a list of \code{(\var{name},
\var{value})} pairs containing the attributes found inside the tag's
\code{<>} brackets.  The \var{name} will be translated to lower case
and double quotes and backslashes in the \var{value} have been
interpreted.  For instance, for the tag \code{<A
HREF="http://www.cwi.nl/">}, this method would be called as
\samp{handle_starttag('a', [('href', 'http://www.cwi.nl/')])}.
\end{methoddesc}

\begin{methoddesc}{handle_startendtag}{tag, attrs}
Similar to \method{handle_starttag()}, but called when the parser
encounters an XHTML-style empty tag (\code{<a .../>}).  This method
may be overridden by subclasses which require this particular lexical
information; the default implementation simple calls
\method{handle_starttag()} and \method{handle_endtag()}.
\end{methoddesc}

\begin{methoddesc}{handle_endtag}{tag}
This method is called to handle the end tag of an element.  It is
intended to be overridden by a derived class; the base class
implementation does nothing.  The \var{tag} argument is the name of
the tag converted to lower case.
\end{methoddesc}

\begin{methoddesc}{handle_data}{data}
This method is called to process arbitrary data.  It is intended to be
overridden by a derived class; the base class implementation does
nothing.
\end{methoddesc}

\begin{methoddesc}{handle_charref}{name} This method is called to
process a character reference of the form \samp{\&\#\var{ref};}.  It
is intended to be overridden by a derived class; the base class
implementation does nothing.  
\end{methoddesc}

\begin{methoddesc}{handle_entityref}{name} 
This method is called to process a general entity reference of the
form \samp{\&\var{name};} where \var{name} is an general entity
reference.  It is intended to be overridden by a derived class; the
base class implementation does nothing.
\end{methoddesc}

\begin{methoddesc}{handle_comment}{data}
This method is called when a comment is encountered.  The
\var{comment} argument is a string containing the text between the
\samp{<!--} and \samp{-->} delimiters, but not the delimiters
themselves.  For example, the comment \samp{<!--text-->} will cause
this method to be called with the argument \code{'text'}.  It is
intended to be overridden by a derived class; the base class
implementation does nothing.
\end{methoddesc}

\begin{methoddesc}{handle_decl}{decl}
Method called when an SGML declaration is read by the parser.  The
\var{decl} parameter will be the entire contents of the declaration
inside the \code{<!}...\code{>} markup.It is intended to be overridden
by a derived class; the base class implementation does nothing.
\end{methoddesc}


\subsection{Example HTML Parser \label{htmlparser-example}}

As a basic example, below is a very basic HTML parser that uses the
\class{HTMLParser} class to print out tags as they are encountered:

\begin{verbatim}
from HTMLParser import HTMLParser

class MyHTMLParser(HTMLParser):

    def handle_starttag(self, tag, attrs):
        print "Encountered the beginning of a %s tag" % tag

    def handle_endtag(self, tag):
        print "Encountered the end of a %s tag" % tag
\end{verbatim}