.\" Automatically generated by Pod::Man 2.22 (Pod::Simple 3.07)
.\"
.\" 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" ''
'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 turned on, 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.
.ie \nF \{\
.    de IX
.    tm Index:\\$1\t\\n%\t"\\$2"
..
.    nr % 0
.    rr F
.\}
.el \{\
.    de IX
..
.\}
.\"
.\" 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 "RSSLite 3pm"
.TH RSSLite 3pm "2010-10-25" "perl v5.10.1" "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"
XML::RSSLite \- lightweight, "relaxed" RSS (and XML\-ish) parser
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
.Vb 1
\&  use XML::RSSLite;
\&
\&  . . .
\&
\&  parseRSS(\e%result, \e$content);
\&
\&  print "=== Channel ===\en",
\&        "Title: $result{\*(Aqtitle\*(Aq}\en",
\&        "Desc:  $result{\*(Aqdescription\*(Aq}\en",
\&        "Link:  $result{\*(Aqlink\*(Aq}\en\en";
\&
\&  foreach $item (@{$result{\*(Aqitem\*(Aq}}) {
\&  print "  \-\-\- Item \-\-\-\en",
\&        "  Title: $item\->{\*(Aqtitle\*(Aq}\en",
\&        "  Desc:  $item\->{\*(Aqdescription\*(Aq}\en",
\&        "  Link:  $item\->{\*(Aqlink\*(Aq}\en\en";
\&  }
.Ve
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
This module attempts to extract the maximum amount of content from
available documents, and is less concerned with \s-1XML\s0 compliance than
alternatives. Rather than rely on XML::Parser, it uses heuristics and good
old-fashioned Perl regular expressions. It stores the data in a simple
hash structure, and \*(L"aliases\*(R" certain tags so that when done, you can
count on having the minimal data necessary for re-constructing a valid
\&\s-1RSS\s0 file. This means you get the basic title, description, and link for a
channel and its items.
.PP
This module extracts more usable links by parsing \*(L"scriptingNews\*(R" and
\&\*(L"weblog\*(R" formats in addition to \s-1RDF\s0 & \s-1RSS\s0. It also \*(L"sanitizes\*(R" the
output for best results. The munging includes:
.IP "Remove html tags to leave plain text" 4
.IX Item "Remove html tags to leave plain text"
.PD 0
.IP "Remove characters other than 0\-9~!@#$%^&*()\-+=a\-zA\-Z[];',.:""<>?\es" 4
.IX Item "Remove characters other than 0-9~!@#$%^&*()-+=a-zA-Z[];',.:""<>?s"
.IP "Remove leading whitespace from URIs" 4
.IX Item "Remove leading whitespace from URIs"
.IP "Use <url> tags when <link> is empty" 4
.IX Item "Use <url> tags when <link> is empty"
.IP "Use misplaced urls in <title> when <link> is empty" 4
.IX Item "Use misplaced urls in <title> when <link> is empty"
.IP "Exract links from <a href=...> if required" 4
.IX Item "Exract links from <a href=...> if required"
.IP "Limit links to ftp and http(s)" 4
.IX Item "Limit links to ftp and http(s)"
.IP "Join relative item urls (beginning with / or #) to the site base" 4
.IX Item "Join relative item urls (beginning with / or #) to the site base"
.PD
.SS "\s-1EXPORT\s0"
.IX Subsection "EXPORT"
.ie n .IP "parseRSS($outHashRef, $inScalarRef)" 4
.el .IP "parseRSS($outHashRef, \f(CW$inScalarRef\fR)" 4
.IX Item "parseRSS($outHashRef, $inScalarRef)"
\&\fI\f(CI$inScalarRef\fI\fR is a reference to a scalar containing the document to be
parsed, the contents will effectively be destroyed. \fI\f(CI$outHashRef\fI\fR is a
reference to the hash within which to store the parsed content.
.SS "\s-1EXPORTABLE\s0"
.IX Subsection "EXPORTABLE"
.ie n .IP "parseXML(\e%parsedTree, \e$parseThis, 'topTag', $comments);" 4
.el .IP "parseXML(\e%parsedTree, \e$parseThis, 'topTag', \f(CW$comments\fR);" 4
.IX Item "parseXML(%parsedTree, $parseThis, 'topTag', $comments);"
.RS 4
.PD 0
.IP "parsedTree \- required" 4
.IX Item "parsedTree - required"
.PD
Reference to hash to store the parsed document within.
.IP "parseThis  \- required" 4
.IX Item "parseThis  - required"
Reference to scalar containing the document to parse.
.IP "topTag     \- optional" 4
.IX Item "topTag     - optional"
Tag to consider the root node, leaving this undefined is not recommended.
.IP "comments   \- optional" 4
.IX Item "comments   - optional"
.RS 4
.PD 0
.IP "false will remove contents from parseThis" 4
.IX Item "false will remove contents from parseThis"
.IP "true will not remove comments from parseThis" 4
.IX Item "true will not remove comments from parseThis"
.IP "array reference is true, comments are stored here" 4
.IX Item "array reference is true, comments are stored here"
.RE
.RS 4
.RE
.RE
.RS 4
.RE
.PD
.SS "\s-1CAVEATS\s0"
.IX Subsection "CAVEATS"
This is not a conforming parser. It does not handle the following
.IP "\(bu" 4

.Sp
.Vb 1
\&  <foo bar=">">
.Ve
.IP "\(bu" 4

.Sp
.Vb 1
\&  <foo><bar> <bar></bar> <bar></bar> </bar></foo>
.Ve
.IP "\(bu" 4

.Sp
.Vb 1
\&  <![CDATA[ ]]>
.Ve
.IP "\(bu" 4

.Sp
.Vb 1
\&  PI
.Ve
.PP
It's non-validating, without a \s-1DTD\s0 the following cannot be properly addressed
.IP "entities" 4
.IX Item "entities"
.PD 0
.IP "namespaces" 4
.IX Item "namespaces"
.PD
This may or may not be arriving in some future release.
.SH "SEE ALSO"
.IX Header "SEE ALSO"
\&\fIperl\fR\|(1), \f(CW\*(C`XML::RSS\*(C'\fR, \f(CW\*(C`XML::SAX::PurePerl\*(C'\fR,
\&\f(CW\*(C`XML::Parser::Lite\*(C'\fR, <XML::Parser>
.SH "AUTHOR"
.IX Header "AUTHOR"
Jerrad Pierce <jpierce@cpan.org>.
.PP
Scott Thomason <scott@thomasons.org>
.SH "LICENSE"
.IX Header "LICENSE"
Portions Copyright (c) 2002,2003,2009 Jerrad Pierce, (c) 2000 Scott Thomason.
All rights reserved. This program is free software; you can redistribute it 
and/or modify it under the same terms as Perl itself.