#!/usr/bin/perl -w
use strict;
use HTML::Parser ();

# See PYX format description
# http://www.xml.com/pub/a/2000/03/15/feature/index.html

my $parser = HTML::Parser->new(
        xml_mode        => 1,
        unbroken_text   => 1,
        ignore_elements => ['style', 'script'], # CDATA isn't supporte
+d
        start_h => [
                sub {
                        my ($tag, $attr) = @_;
                        print "($tag\n";
                        print "A$_\n-$attr->{$_}\n" foreach keys %{$at
+tr};
                }, "tagname, attr"],
        end_h   => [
                sub {
                        print ")" . shift() . "\n";
                }, "tagname"],
        text_h  => [
                sub {
                        my $text = shift;
                        $text =~ s/^\s*|\s*$//g;
                        print "-$text\n"
                }, "dtext"],
);

die "usage: $0 file1.html > file1.pyx\n" unless @ARGV;

foreach (@ARGV){
        $parser->parse_file($_);
        $parser->eof();
}

[download]

In reply to html2pyx by OeufMayo

Title:
Use:  <p> text here (a paragraph) </p>
and:  <code> code here </code>
to format your post, it's "PerlMonks-approved HTML":


  • Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!
  • Titles consisting of a single word are discouraged, and in most cases are disallowed outright.
  • Read Where should I post X? if you're not absolutely sure you're posting in the right place.
  • Please read these before you post! —
  • Posts may use any of the Perl Monks Approved HTML tags:
    a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, details, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, summary, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr
  • You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)
            For:     Use:
    & &amp;
    < &lt;
    > &gt;
    [ &#91;
    ] &#93;
  • Link using PerlMonks shortcuts! What shortcuts can I use for linking?
  • See Writeup Formatting Tips and other pages linked from there for more info.