#!/usr/bin/perl -w
# html2latex
# Copyright (C) 2000 Peter Thatcher
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, or (at your option) any later version.
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
###################### BEGIN SETUP #########################
use strict;
use Getopt::Long;
use File::Basename;
my $usage = << 'STOP';
Usage: html2latex [options] <filename>
Optional Parameters:
--help -h ? print this help
--image_scale --image -i <float> set image scale
--font_size --font -f <integer> set font size. Must be 10-12
--debug -d print debugging info
--table_border --border sets table around borders
--document_class --document
--class=s <string> sets latex document class
--package <string> adds a latex package each time
--latex2pdf --pdf -p creates a pdf and latex file
--paragraph --par -P sets the style of the paragraph to
HTML style
--ban -b <string> ban (ignore) tag
--head <string> add option to documentclass defenition
--conf -C <string> use alternate configuration file
--log -l <string> use alternate log file
STOP
################## BEGIN OPTION PARSING ####################
my %options = ();
my @packages = ();
my @heads = ();
my @banned = ();
my $latex2pdf;
my $conffile;
my $logfile;
GetOptions(
'image_scale|image|i=f' => \$options{image},
'font_size|font=i' => \$options{font_size},
'debug|d+' => \$options{debug},
'table_border|table|border!' => \$options{border},
'document_class|document|class=s' => \$options{document_class},
'help|?|h' => sub {print $usage and exit},
'package=s' => \@packages,
'head=s' => \@heads,
'ban|b=s' => \@banned,
'latex2pdf|pdf|p!' => \$latex2pdf,
'mbox|m!' => \$options{mbox},
'cache|local' => \$options{cache},
'paragraph|par|P!' => \$options{paragraph},
'conf|C=s' => \$conffile,
'log|l=s' => \$logfile
);
print $usage and exit unless @ARGV;
chomp(my $START_DIR = `pwd`); #place we start out from
################### END OPTION PARSING ####################
###################### BEGIN MAIN #########################
use HTML::Latex;
my $parser = new HTML::Latex();
$parser->set_option(\%options);
$parser->add_package(@packages);
$parser->add_head(@heads);
$parser->ban_tag(@banned);
$parser->set_log($logfile) if defined($logfile);
foreach my $uri (@ARGV) {
#Option 1:
#my $in = IO::File->new("< $uri");
#my $out = IO::File->new("> $uri.tex");
#$parser->html2latex($in,$out);
#Option 2:
print "Processing $uri\n";
my ($htmlfile,$latexfile) = $parser->html2latex($uri);
latex2pdf($htmlfile,$latexfile) if $latex2pdf;
}
#Option 3:
#my $html_string = join("\n",<>);
#my $html_string = join("",@ARGV);
#my $tex_string = $parser->parse_string($html_string,1);
#print $tex_string;
####################### END MAIN ##########################
####################### BEGIN SUBS ########################
#Routine to print help
# runs the system command "pdflatex" after checking for existing files
# and backing them up.
# <1> The base of the filename
sub latex2pdf {
my ($htmlfile,$latexfile) = @_;
my ($base,$path,$extension) = fileparse($latexfile,'\.tex');
my $texrel = "$base$extension"; #relative name of the tex file
my $logfile = "$path$base.log";
my $pdffile = "$path$base.pdf";
print "PDF: Processing $latexfile from $htmlfile and $texrel\n";
chdir($path); #pdflatex, no matter what I do always insists on making the output
#files in the current directory. So here is my workaround.
my @errors = grep /^!/, `pdflatex -interaction=nonstopmode $texrel`;
chdir($START_DIR);
if(@errors){
print "PDF: pdflatex reported " . scalar(@errors) . " errors while creating PDF.\n\tCheck $logfile for more information.\n";
}
}
=head1 NAME
html2latex - HTML to latex converter.
=head1 SYNOPSIS
html2latex [OPTION]... URLS...
=head1 DESCRIPTION
html2latex uses HTML::TreeBuilder to parse an HTML file and then it
converts the HTML::Element into to a Latex file. Each URL will have a
.*html extension stripped. If you use a URL, then the files taken
from the Internet will be stored in your ~/.html2latex directory. If
pictures are included, they are converted to .PNG, which can only be
used with pdflatex. As an added bonus, there is an option to
automatically create a PDF from the Latex file (using pdflatex).
=head1 REQUIRES
If your html2latex is not working correctly, this may be because you
do not have many of the needed packages. html2latex requires
HTML::TreeBuilder perhaps LWP::Simple and URI. If you do not have
either of these, try typing B<perl -MCPAN -e shell> at the command
line. This will bring up a shell for CPAN (The Comprehensive Perl
Archive Network). Then, as root try typing B<install
HTML::TreeBuilder>. Should work like magic.
=head1 URLS
In your list of URLs any filename given after a URL will continue to
use the latest HOST given. Also, files default to index.html,
regardless of what the server thinks. So, if you type:
C<html2latex http://slashdot.org foo.html http://linuxtoday.net bar.html>
html2latex will try to grab http://slashdot.org/index.html,
http://slashdot.org/foo.html, http://linuxtoday.net/index.html, and
http://linuxtoday.net/bar.html
=head1 OPTIONS
Options are secondary to document-specified options. So, if your HTML
file has border=1, a border will be printed regardless of the
B<--border> option. The do overide, however, options given in the
configuration file. If you want to change things more permanently,
try changing the config file, html2latex.xml. For information on it,
try the HTML::Latex under section CONFIGURATION FILE.
=over 4
=item B<-h -? --help>
Print the brief help and usage.
=item B<--latex2pdf --pdf -p>
Automatically create a PDF along with a latex file named FILE.pdf.
This may fail and print a number of cryptic errors.
=item B<-i --image --image_scale=SCALE>
Set the scale for images in the latex file. This is usefull because
some images in HTML or much to big to fit on a page. Default is 1.0.
SCALE can be any non-zere positive floating point number, large
numbers are not reccomended.
=item B<-f --font --font_size=SIZE>
Set the default font size. Can be 10-12. Do not try anything else.
html2latex will not check it, but the latex file will not compile (at
least I think not). Default is 12.
=item B<-d --debug>
Level of debugging info to print. The more times this option is used,
the higher the level. Default is 0, and you cannot lower that. Right
now, 0 prints nothing. 1 prints fun code-tracking info. 2 prints
lots of data-structure information, so don't do it unless you're
serious.
=item B<--border --table --table_border>
Sets table around borders on. Default is off. Also, B<--noborder> or
B<--notable> will explicity turn table borders off.
=item B<--class --document --document_class=CLASS>
Set the documentclass to use. Any valid latex document class is
valid. Examples are B<report>, B<book>, and B<article>. B<article>
is the default. If an invalid document class is used, the output
latex file will not compile.
=item B<--package=PACKAGE>
html2latex will create a latex file using any packages that you
specify. PACKAGE will be added to the list of class to put in the
file. html2latex will not make sure the packages are valid, but if
they aren't the latex file won't compile.
=item B<--head=HEAD>
Latex allows you to add options in the preamble of the form
\documentclass[OPTIONS]{article}. Each HEAD you add gets added to the
list included. For instance, you could use C<--head=twocolumn> to add
the 'twocolumn' feature of Latex. Since font sizes are already added,
don't add them yourself. See C<--font>
=item B<--mbox -m>
With any of these, html2latex will put a tex \mbox around all of the
tables it creates. I do not know why, but with a lot of tables
(especially nested ones), the tex and pdf output will work better.
So, if you do not like your output with tables, try this.
=item B<--paragraph --par -P>
Uses HTML-style paragraphs. This is by default, so try --noparagrph
or --nopar or -P! to turn it back to Latex-style paragraphs.
=item B<--cache --local>
=item B<--log -l LOGFILE>
Print all messages to LOGFILE instead of STDERR.
=item B<--conf -C CONFFILE>
Change the configuration file to CONFFILE. For more information on
this file, see the HTML::Latex manpage.
=back
=head1 Development
Development is being carried out by Peter Thatcher
(peterthatcher@asu.edu) and Stan Seibert (volsung@asu.edu). Homepage
is http://html2latex.sourceforge.net.
=cut