.\" Automatically generated by Pod::Man 4.11 (Pod::Simple 3.35)
.\"
.\" 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
.\" ========================================================================
.\"
.IX Title "LinkExtractor 3pm"
.TH LinkExtractor 3pm "2020-09-09" "perl v5.30.3" "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::LinkExtractor \- Extract links from an HTML document
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
HTML::LinkExtractor is used for extracting links from \s-1HTML.\s0
It is very similar to HTML::LinkExtor,
except that besides getting the \s-1URL,\s0 you also get the link-text.
.PP
Example ( \fBplease run the examples\fR ):
.PP
.Vb 2
\& use HTML::LinkExtractor;
\& use Data::Dumper;
\&
\& my $input = q{If I am a LINK!!! };
\& my $LX = new HTML::LinkExtractor();
\&
\& $LX\->parse(\e$input);
\&
\& print Dumper($LX\->links);
\& _\|_END_\|_
\& # the above example will yield
\& $VAR1 = [
\& {
\& \*(Aq_TEXT\*(Aq => \*(Aq I am a LINK!!! \*(Aq,
\& \*(Aqhref\*(Aq => bless(do{\e(my $o = \*(Aqhttp://perl.com/\*(Aq)}, \*(AqURI::http\*(Aq),
\& \*(Aqtag\*(Aq => \*(Aqa\*(Aq
\& }
\& ];
.Ve
.PP
\&\f(CW\*(C`HTML::LinkExtractor\*(C'\fR will also correctly extract nested
\&\fIlink-type\fR tags.
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
.Vb 3
\& ## the demo
\& perl LinkExtractor.pm
\& perl LinkExtractor.pm file.html othefile.html
\&
\& ## or if the module is installed, but you don\*(Aqt know where
\&
\& perl \-MHTML::LinkExtractor \-e" system $^X, $INC{q{HTML/LinkExtractor.pm}} "
\& perl \-MHTML::LinkExtractor \-e\*(Aq system $^X, $INC{q{HTML/LinkExtractor.pm}} \*(Aq
\&
\& ## or
\&
\& use HTML::LinkExtractor;
\& use LWP qw( get ); # use LWP::Simple qw( get );
\&
\& my $base = \*(Aqhttp://search.cpan.org\*(Aq;
\& my $html = get($base.\*(Aq/recent\*(Aq);
\& my $LX = new HTML::LinkExtractor();
\&
\& $LX\->parse(\e$html);
\&
\& print qq{\en};
\&
\& for my $Link( @{ $LX\->links } ) {
\& ## new modules are linked by /author/NAME/Dist
\& if( $$Link{href}=~ m{^\e/author\e/\ew+} ) {
\& print $$Link{_TEXT}."\en";
\& }
\& }
\&
\& undef $LX;
\& _\|_END_\|_
\&
\& ## or
\&
\& use HTML::LinkExtractor;
\& use Data::Dumper;
\&
\& my $input = q{If I am a LINK!!! };
\& my $LX = new HTML::LinkExtractor(
\& sub {
\& print Data::Dumper::Dumper(@_);
\& },
\& \*(Aqhttp://perlFox.org/\*(Aq,
\& );
\&
\& $LX\->parse(\e$input);
\& $LX\->strip(1);
\& $LX\->parse(\e$input);
\& _\|_END_\|_
\&
\& #### Calculate to total size of a web\-page
\& #### adds up the sizes of all the images and stylesheets and stuff
\&
\& use strict;
\& use LWP; # use LWP::Simple;
\& use HTML::LinkExtractor;
\& #
\& my $url = shift || \*(Aqhttp://www.google.com\*(Aq;
\& my $html = get($url);
\& my $Total = length $html;
\& #
\& print "initial size $Total\en";
\& #
\& my $LX = new HTML::LinkExtractor(
\& sub {
\& my( $X, $tag ) = @_;
\& #
\& unless( grep {$_ eq $tag\->{tag} } @HTML::LinkExtractor::TAGS_IN_NEED ) {
\& #
\& print "$$tag{tag}\en";
\& #
\& for my $urlAttr ( @{$HTML::LinkExtractor::TAGS{$$tag{tag}}} ) {
\& if( exists $$tag{$urlAttr} ) {
\& my $size = (head( $$tag{$urlAttr} ))[1];
\& $Total += $size if $size;
\& print "adding $size\en" if $size;
\& }
\& }
\& }
\& },
\& $url,
\& 0
\& );
\& #
\& $LX\->parse(\e$html);
\& #
\& print "The total size of \en$url\en is $Total bytes\en";
\& _\|_END_\|_
.Ve
.SH "METHODS"
.IX Header "METHODS"
.ie n .SS """$LX\->new([\e&callback, [$baseUrl, [1]]])"""
.el .SS "\f(CW$LX\->new([\e&callback, [$baseUrl, [1]]])\fP"
.IX Subsection "$LX->new([&callback, [$baseUrl, [1]]])"
Accepts 3 arguments, all of which are optional.
If for example you want to pass a \f(CW$baseUrl\fR, but don't
want to have a callback invoked, just put \f(CW\*(C`undef\*(C'\fR in place of a subref.
.PP
This is the only class method.
.IP "1." 4
a callback ( a sub reference, as in \f(CW\*(C`sub{}\*(C'\fR, or \f(CW\*(C`\e&sub\*(C'\fR)
which is to be called each time a new \s-1LINK\s0 is encountered
( for \f(CW@HTML::LinkExtractor::TAGS_IN_NEED\fR this means
after the closing tag is encountered )
.Sp
The callback receives an object reference(\f(CW$LX\fR) and a link hashref.
.IP "2." 4
and a base \s-1URL\s0 ( \s-1URI\-\s0>new, so its up to you to make sure it's valid
which is used to convert all relative \s-1URI\s0's to absolute ones.
.Sp
.Vb 1
\& $ALinkP{href} = URI\->new_abs( $ALink{href}, $base );
.Ve
.IP "3." 4
A \*(L"boolean\*(R" (just stick with 1).
See the example in \*(L"\s-1DESCRIPTION\*(R"\s0.
Normally, you'd get back _TEXT that looks like
.Sp
.Vb 1
\& \*(Aq_TEXT\*(Aq => \*(Aq I am a LINK!!! \*(Aq,
.Ve
.Sp
If you turn this option on, you'll get the following instead
.Sp
.Vb 1
\& \*(Aq_TEXT\*(Aq => \*(Aq I am a LINK!!! \*(Aq,
.Ve
.Sp
The private utility function \f(CW\*(C`_stripHTML\*(C'\fR does this
by using HTML::TokeParsers
method get_trimmed_text.
.Sp
You can turn this feature on an off by using
\&\f(CW\*(C`$LX\->strip(undef || 0 || 1)\*(C'\fR
.ie n .SS """$LX\->parse( $filename || *FILEHANDLE || \e$FileContent )"""
.el .SS "\f(CW$LX\->parse( $filename || *FILEHANDLE || \e$FileContent )\fP"
.IX Subsection "$LX->parse( $filename || *FILEHANDLE || $FileContent )"
Each time you call \f(CW\*(C`parse\*(C'\fR, you should pass it a
\&\f(CW$filename\fR a \f(CW*FILEHANDLE\fR or a \f(CW\*(C`\e$FileContent\*(C'\fR
.PP
Each time you call \f(CW\*(C`parse\*(C'\fR a new \f(CW\*(C`HTML::TokeParser\*(C'\fR object
is created and stored in \f(CW\*(C`$this\->{_tp}\*(C'\fR.
.PP
You shouldn't need to mess with the TokeParser object.
.ie n .SS """$LX\->links()"""
.el .SS "\f(CW$LX\->links()\fP"
.IX Subsection "$LX->links()"
Only after you call \f(CW\*(C`parse\*(C'\fR will this method return anything.
This method returns a reference to an ArrayOfHashes,
which basically looks like (Data::Dumper output)
.PP
.Vb 1
\& $VAR1 = [ { tag => \*(Aqimg\*(Aq, src => \*(Aqimage.png\*(Aq }, ];
.Ve
.PP
Please note that if yo provide a callback this array will be empty.
.ie n .SS """$LX\->strip( [ 0 || 1 ])"""
.el .SS "\f(CW$LX\->strip( [ 0 || 1 ])\fP"
.IX Subsection "$LX->strip( [ 0 || 1 ])"
If you pass in \f(CW\*(C`undef\*(C'\fR (or nothing), returns the state of the option.
Passing in a true or false value sets the option.
.PP
If you wanna know what the option does see
\&\f(CW\*(C`$LX\->new([\e&callback, [$baseUrl, [1]]])\*(C'\fR
.SH "WHAT'S A LINK-type tag"
.IX Header "WHAT'S A LINK-type tag"
Take a look at \f(CW%HTML::LinkExtractor::TAGS\fR to see
what I consider to be link-type-tag.
.PP
Take a look at \f(CW@HTML::LinkExtractor::VALID_URL_ATTRIBUTES\fR to see
all the possible tag attributes which can contain \s-1URI\s0's (the links!!)
.PP
Take a look at \f(CW@HTML::LinkExtractor::TAGS_IN_NEED\fR to see
the tags for which the \f(CW\*(Aq_TEXT\*(Aq\fR attribute is provided,
like \f(CW\*(C` TEST \*(C'\fR
.SS "How can that be?!?!"
.IX Subsection "How can that be?!?!"
I took at look at \f(CW%HTML::Tagset::linkElements\fR
and the following \s-1URL\s0's
.PP
.Vb 1
\& http://www.blooberry.com/indexdot/html/tagindex/all.htm
\&
\& http://www.blooberry.com/indexdot/html/tagpages/a/a\-hyperlink.htm
\& http://www.blooberry.com/indexdot/html/tagpages/a/applet.htm
\& http://www.blooberry.com/indexdot/html/tagpages/a/area.htm
\&
\& http://www.blooberry.com/indexdot/html/tagpages/b/base.htm
\& http://www.blooberry.com/indexdot/html/tagpages/b/bgsound.htm
\&
\& http://www.blooberry.com/indexdot/html/tagpages/d/del.htm
\& http://www.blooberry.com/indexdot/html/tagpages/d/div.htm
\&
\& http://www.blooberry.com/indexdot/html/tagpages/e/embed.htm
\& http://www.blooberry.com/indexdot/html/tagpages/f/frame.htm
\&
\& http://www.blooberry.com/indexdot/html/tagpages/i/ins.htm
\& http://www.blooberry.com/indexdot/html/tagpages/i/image.htm
\& http://www.blooberry.com/indexdot/html/tagpages/i/iframe.htm
\& http://www.blooberry.com/indexdot/html/tagpages/i/ilayer.htm
\& http://www.blooberry.com/indexdot/html/tagpages/i/inputimage.htm
\&
\& http://www.blooberry.com/indexdot/html/tagpages/l/layer.htm
\& http://www.blooberry.com/indexdot/html/tagpages/l/link.htm
\&
\& http://www.blooberry.com/indexdot/html/tagpages/o/object.htm
\&
\& http://www.blooberry.com/indexdot/html/tagpages/q/q.htm
\&
\& http://www.blooberry.com/indexdot/html/tagpages/s/script.htm
\& http://www.blooberry.com/indexdot/html/tagpages/s/sound.htm
\&
\& And the special cases
\&
\&
\& http://www.blooberry.com/indexdot/html/tagpages/d/doctype.htm
\& \*(Aq!doctype\*(Aq is really a process instruction, but is still listed
\& in %TAGS with \*(Aqurl\*(Aq as the attribute
\&
\& and
\&
\&
\& http://www.blooberry.com/indexdot/html/tagpages/m/meta.htm
\& If there is a valid url, \*(Aqurl\*(Aq is set as the attribute.
\& The meta tag has no \*(Aqattributes\*(Aq listed in %TAGS.
.Ve
.SH "SEE ALSO"
.IX Header "SEE ALSO"
HTML::LinkExtor, HTML::TokeParser, HTML::Tagset.
.SH "AUTHOR"
.IX Header "AUTHOR"
D.H (PodMaster)
.PP
Please use http://rt.cpan.org/ to report bugs.
.PP
Just go to
http://rt.cpan.org/NoAuth/Bugs.html?Dist=HTML\-Scrubber
to see a bug list and/or repot new ones.
.SH "LICENSE"
.IX Header "LICENSE"
Copyright (c) 2003, 2004 by D.H. (PodMaster).
All rights reserved.
.PP
This module is free software;
you can redistribute it and/or modify it under
the same terms as Perl itself.
The \s-1LICENSE\s0 file contains the full text of the license.