or if you really want to use HTML::TreeBuilder something like this may do the trick:

use warnings;
use strict;
use HTML::TreeBuilder;

my $Tree = HTML::TreeBuilder->new ();

$Tree->parse ("<HTML><body><p>First para.<br>Second line.</p><p>Second
+ para</p></body></HTML>");
my $Text;
my $empty_element_map = $Tree->_empty_element_map;

my(@C) = [$Tree]; # a stack containing lists of children
# I is a stack of indexes to current position in corresponding lists i
+n @C
# In each of these, 0 is the active point
my(@I) = (-1); # initial value must be -1 for each list
my @Context = ""; # Contains stack of current nodes

# scratch:
my $this;  # current node
my $content_r; # child list of $this
my $TagName;

# Loop over the tree
while (@C)
  {
  # Post processing
  # Move to next item in this frame
  if(!defined($I[0]) or ++$I[0] >= @{$C[0]})
    {
    $this = $Context [0];
    if (defined $this and ref $this)
      {# Close tag
      my $StartTag = $this->starttag ();
      $StartTag =~ s/[\r\n]*//gs;

      if ($StartTag =~ /^<p\b.*?>/g) 
        {
        $Text .= "</p>";
        }
      }

    shift @Context;
    shift @I;
    shift @C;
    next;
    }

  $this = $C[0][$I[0]];

  if (! ref $this)
    {# Add the text
    $Text .= $this;
    }
  else
    {# Process this element
    my $StartTag = $this->starttag ();
    $StartTag =~ s/[\r\n]*//gs;

    if ($StartTag =~ /^(<(?:p|br)\b.*?>)/g) 
      {
      $Text .= "$1"
      }
    }

  # Now queue up content list for the current element...
  if(
    ref $this and
    not
      ( # ...except for those which
      not($content_r = $this->{'_content'} and @$content_r) and
          # ...have empty content lists
      $this->{'_empty_element'} || $empty_element_map->{$this->{'_tag'
+} || ''}
          # ...and that don't get post-order callbacks
      )
    )
    {
    unshift @Context, $this;
    unshift @I, -1;
    unshift @C, $content_r || [];
    }
  }

print $Text;

[download]
<p>First para.<br>Second line.</p><p>Second para</p>

[download]
Perl is Huffman encoded by design.

In reply to Re: HTML::TreeBuilder Remove all HTML by GrandFather
in thread HTML::TreeBuilder Remove all HTML by Anonymous Monk

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.