.\" Automatically generated by Pod::Man 4.14 (Pod::Simple 3.43)
.\"
.\" Standard preamble:
.\" ========================================================================
.de Sp \" Vertical space (when we can't use .PP)
.if t .sp .5v
.if n .sp
..
.de Vb \" Begin verbatim text
.ft CW
.nf
.ne \\$1
..
.de Ve \" End verbatim text
.ft R
.fi
..
.\" Set up some character translations and predefined strings.  \*(-- will
.\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
.\" double quote, and \*(R" will give a right double quote.  \*(C+ will
.\" give a nicer C++.  Capital omega is used to do unbreakable dashes and
.\" therefore won't be available.  \*(C` and \*(C' expand to `' in nroff,
.\" nothing in troff, for use with C<>.
.tr \(*W-
.ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
.ie n \{\
.    ds -- \(*W-
.    ds PI pi
.    if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
.    if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\"  diablo 12 pitch
.    ds L" ""
.    ds R" ""
.    ds C` ""
.    ds C' ""
'br\}
.el\{\
.    ds -- \|\(em\|
.    ds PI \(*p
.    ds L" ``
.    ds R" ''
.    ds C`
.    ds C'
'br\}
.\"
.\" Escape single quotes in literal strings from groff's Unicode transform.
.ie \n(.g .ds Aq \(aq
.el       .ds Aq '
.\"
.\" If the F register is >0, we'll generate index entries on stderr for
.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
.\" entries marked with X<> in POD.  Of course, you'll have to process the
.\" output yourself in some meaningful fashion.
.\"
.\" Avoid warning from groff about undefined register 'F'.
.de IX
..
.nr rF 0
.if \n(.g .if rF .nr rF 1
.if (\n(rF:(\n(.g==0)) \{\
.    if \nF \{\
.        de IX
.        tm Index:\\$1\t\\n%\t"\\$2"
..
.        if !\nF==2 \{\
.            nr % 0
.            nr F 2
.        \}
.    \}
.\}
.rr rF
.\"
.\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
.\" Fear.  Run.  Save yourself.  No user-serviceable parts.
.    \" fudge factors for nroff and troff
.if n \{\
.    ds #H 0
.    ds #V .8m
.    ds #F .3m
.    ds #[ \f1
.    ds #] \fP
.\}
.if t \{\
.    ds #H ((1u-(\\\\n(.fu%2u))*.13m)
.    ds #V .6m
.    ds #F 0
.    ds #[ \&
.    ds #] \&
.\}
.    \" simple accents for nroff and troff
.if n \{\
.    ds ' \&
.    ds ` \&
.    ds ^ \&
.    ds , \&
.    ds ~ ~
.    ds /
.\}
.if t \{\
.    ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
.    ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
.    ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
.    ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
.    ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
.    ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
.\}
.    \" troff and (daisy-wheel) nroff accents
.ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
.ds 8 \h'\*(#H'\(*b\h'-\*(#H'
.ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
.ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
.ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
.ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
.ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
.ds ae a\h'-(\w'a'u*4/10)'e
.ds Ae A\h'-(\w'A'u*4/10)'E
.    \" corrections for vroff
.if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
.if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
.    \" for low resolution devices (crt and lpr)
.if \n(.H>23 .if \n(.V>19 \
\{\
.    ds : e
.    ds 8 ss
.    ds o a
.    ds d- d\h'-1'\(ga
.    ds D- D\h'-1'\(hy
.    ds th \o'bp'
.    ds Th \o'LP'
.    ds ae ae
.    ds Ae AE
.\}
.rm #[ #] #H #V #F C
.\" ========================================================================
.\"
.IX Title "HTML::FormatText::WithLinks 3pm"
.TH HTML::FormatText::WithLinks 3pm "2022-12-07" "perl v5.36.0" "User Contributed Perl Documentation"
.\" For nroff, turn off justification.  Always turn off hyphenation; it makes
.\" way too many mistakes in technical documents.
.if n .ad l
.nh
.SH "NAME"
HTML::FormatText::WithLinks \- HTML to text conversion with links as footnotes
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
.Vb 1
\&    use HTML::FormatText::WithLinks;
\&
\&    my $f = HTML::FormatText::WithLinks\->new();
\&
\&    my $html = qq(
\&    <html>
\&    <body>
\&    <p>
\&        Some html with a <a href="http://example.com/">link</a>
\&    </p>
\&    </body>
\&    </html>
\&    );
\&
\&    my $text = $f\->parse($html);
\&
\&    print $text;
\&
\&    # results in something like
\&
\&    Some html with a [1]link
\&
\&    1. http://example.com/
\&
\&    my $f2 = HTML::FormatText::WithLinks\->new(
\&        before_link => \*(Aq\*(Aq,
\&        after_link => \*(Aq [%l]\*(Aq,
\&        footnote => \*(Aq\*(Aq
\&    );
\&
\&    $text = $f2\->parse($html);
\&    print $text;
\&
\&    # results in something like
\&
\&    Some html with a link [http://example.com/]
\&
\&    my $f3 = HTML::FormatText::WithLinks\->new(
\&        link_num_generator => sub {
\&            return "*" x (shift() + 1);
\&        },
\&        footnote => \*(Aq[%n] %l\*(Aq
\&    );
\&
\&    $text = $f3\->parse($html);
\&    print $text;
\&
\&    # results in something like
\&
\&    Some html with a [*]link
\&
\&    [*] http://example.com/
.Ve
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
HTML::FormatText::WithLinks takes \s-1HTML\s0 and turns it into plain text
but prints all the links in the \s-1HTML\s0 as footnotes. By default, it attempts
to mimic the format of the lynx text based web browser's \-\-dump option.
.SH "METHODS"
.IX Header "METHODS"
.SS "new"
.IX Subsection "new"
.Vb 1
\&    my $f = HTML::FormatText::WithLinks\->new( %options );
.Ve
.PP
Returns a new instance. It accepts all the options of HTML::FormatText plus
.IP "base" 4
.IX Item "base"
a base option. This should be set to a \s-1URI\s0 which will be used to turn any 
relative URIs on the \s-1HTML\s0 to absolute ones.
.IP "doc_overrides_base" 4
.IX Item "doc_overrides_base"
If a base element is found in the document and it has an href attribute
then setting doc_overrides_base to true will cause the document's base
to be used. This defaults to false.
.IP "before_link (default: '[%n]')" 4
.IX Item "before_link (default: '[%n]')"
.PD 0
.IP "after_link (default: '')" 4
.IX Item "after_link (default: '')"
.ie n .IP "footnote (default: '[%n] %l')" 4
.el .IP "footnote (default: '[%n] \f(CW%l\fR')" 4
.IX Item "footnote (default: '[%n] %l')"
.PD
a string to print before a link (i.e. when the <a> is found), 
after link has ended (i.e. when then </a> is found) and when printing 
out footnotes.
.Sp
\&\*(L"%n\*(R" will be replaced by the link number, \*(L"%l\*(R" will be replaced by the 
link itself.
.Sp
If footnote is set to '', no footnotes will be printed.
.IP "link_num_generator (default: sub { return \fBshift()\fR + 1 })" 4
.IX Item "link_num_generator (default: sub { return shift() + 1 })"
link_num_generator is a sub that returns the value to be printed for a 
given link number. The internal store starts numbering at 0.
.IP "with_emphasis" 4
.IX Item "with_emphasis"
If set to 1 then italicised text will be surrounded by \f(CW\*(C`/\*(C'\fR and bolded text by
\&\f(CW\*(C`_\*(C'\fR.  You can change these markers by using the \f(CW\*(C`italic_marker\*(C'\fR and
\&\f(CW\*(C`bold_marker\*(C'\fR options.
.IP "unique_links" 4
.IX Item "unique_links"
If set to 1 then will only generate 1 footnote per unique \s-1URI\s0 as oppose to the default behaviour which is to generate a footnote per \s-1URI.\s0
.IP "anchor_links" 4
.IX Item "anchor_links"
If set to 0 then links pointing to local anchors will be skipped.
The default behaviour is to include all links.
.IP "skip_linked_urls" 4
.IX Item "skip_linked_urls"
If set to 1, then links where the text equals the href value will be skipped.
The default behaviour is to include all links.
.SS "parse"
.IX Subsection "parse"
.Vb 1
\&    my $text = $f\->parse($html);
.Ve
.PP
Takes some \s-1HTML\s0 and returns it as text. Returns undef on error.
.PP
Will also return undef if you pass it undef. Returns an empty
string if passed an empty string.
.SS "parse_file"
.IX Subsection "parse_file"
.Vb 1
\&    my $text = $f\->parse_file($filename);
.Ve
.PP
Takes a filename and returns the contents of the file as plain text.
Returns undef on error.
.SS "error"
.IX Subsection "error"
.Vb 1
\&    $f\->error();
.Ve
.PP
Returns the last error that occurred. In practice this is likely to be 
either a warning that parse_file couldn't find the file or that
HTML::TreeBuilder failed.
.SH "CAVEATS"
.IX Header "CAVEATS"
When passing \s-1HTML\s0 fragments the results may be a little unpredictable. 
I've tried to work round the most egregious of the issues but any 
unexpected results are welcome.
.PP
Also note that if for some reason there is an a tag in the document
that does not have an href attribute then it will be quietly ignored.
If this is really a problem for anyone then let me know and I'll see
if I can think of a sensible thing to do in this case.
.SH "AUTHOR"
.IX Header "AUTHOR"
Struan Donald. <struan@cpan.org>
.PP
<http://www.exo.org.uk/code/>
.PP
Ian Malpass <ian@indecorous.com> was responsible for the custom 
formatting bits and the nudge to release the code.
.PP
Simon Dassow <janus@errornet.de<gt> for the anchor_links option plus 
a few bugfixes and optimisations
.PP
Kevin Ryde for the code for pulling the base out the document.
.PP
Thomas Sibley <trs@bestpractical.com> patches for skipping links that are their urls and to change the delimiters for bold and italic text..
.SH "SOURCE CODE"
.IX Header "SOURCE CODE"
The source code for this module is hosted on GitHub
<http://github.com/struan/html\-formattext\-withlinks>
.SH "COPYRIGHT"
.IX Header "COPYRIGHT"
Copyright (C) 2003\-2010 Struan Donald and Ian Malpass. All rights reserved.
.SH "LICENSE"
.IX Header "LICENSE"
This program is free software; you can redistribute
it and/or modify it under the same terms as Perl itself.
.SH "SEE ALSO"
.IX Header "SEE ALSO"
\&\fBperl\fR\|(1), HTML::Formatter.