--- batch m <[EMAIL PROTECTED]> wrote:
> Date: Wed, 14 Aug 2002 15:23:50 -0700 (PDT)
> From: batch m <[EMAIL PROTECTED]>
> Subject: unable to parse html
> To: [EMAIL PROTECTED]
>
> Hail,
> I'm stuck with this parsing script, (attached) I
> found
> on perlmonks.org.
>
> I've got Lemay's SAMS 21 day and O'reily's 2rd
> edition.
>
> My Perl experience is just modifying a config file
> from the plethora of free scripts to now finally
> trying to modify a script to accomplish the
> following
> task.
>
> I'd like to import the contents of over 3k html
> files,
> between the tags <body> to </body> after I've
> grepped
> out the header and footer <!-includes-> into a table
> cell in the new templates I'm creating for the site.
>
> I'm stuck on the error: 'unable to parse'
>
> line: $content = $header_html . $1 .
> $footer_html;
============
total script
===========
# opens up original HTML and inserts
# into template html. and mirrors the other
# files that it doesn't parse....
#!/usr/bin/perl -w
use strict ;
use warnings ;
$|++ ;
#Define variables
##################
#Directory to parse (with trailing slash)
my $open_dir = 'C:/My
Documents/carlist/carlist_test/';
#Directory to save parsed documents to (with
trailing slash)
my $save_dir = 'C:/My
Documents/carlist/carlist_test/parsed/';
#Location of template HTML file
my $html_file = 'C:/My
Documents/carlist/carlist_test/template/newtemplate.html';
#Extensions allowed to parse
my @exts = ('html','htm','shtml','shtm');
my $exts;
my $ext;
my $header_html= 'C:/My
Documents/carlist/carlist_test/template/ccheader.html';
my $footer_html= 'C:/My
Documents/carlist/carlist_test/template/ccfooter.html';
my $title;
#Used to find html files to replace
use File::Find;
#Used to copy files to new location
use File::Copy;
#Assists in copying path directory structure
use File::Path;
#Starts the actual code
&main();
exit; #Just in case of any accidents
sub eachFile {
my $filename = $_;
my $fullpath = $File::Find::name;
#remember that File::Find changes your CWD,
#so you can call open with just $_
my $found = 0;
foreach $ext (@exts) {
if($filename=~/\.$ext$/) {
print "\tOpening file $filename - ";
my $content = &open_file("$filename");
print "Completed\n";
if($content=~m|<TITLE>(.*)</TITLE>|si) {
$title = $1;
} else{
$title = "www.carlist.com - List your
used car for sale for FREE with the longest running
used car database in the world.";
}
print "\t\tParsing Document - ";
if($content=~m|<BODY.*?>(.*?)</BODY>|si) {
$content = $header_html . $1 .
$footer_html;
$content =~ s|%title%|$title|;
&save_file("$fullpath",$content);
print "Completed\n";
} else{
print "Couldn't parse\n";
}
$found = 1;
last; #So it doesn't reopen it with
similar extension
}
}
if($found==0) {
my $dir = $fullpath;
$dir=~s/\Q$open_dir\E/$save_dir/i; #Removes
current root dir, and replaces it with new one
copy("$fullpath","$dir");
}
}
#Returns the contents of a filename specified...
sub open_file{
my($file) = @_;
my($file_contents) = "";
open(DATA,"$file") || die "Not Completed\n";
while(<DATA>) {
$file_contents .= $_;
}
close(DATA);
return($file_contents);
}
#Saves the new file to its new location
sub save_file{
my($file,$file_contents) = @_;
$file=~s/$open_dir/$save_dir/i; #Removes current
root dir, and replaces it with new one
my($dir) = $file;
if($dir =~ /(.*)\/.*/) {$dir = $1;}
if(!(-e "$dir/")) {
mkdir("$dir/",0755);
}
open(DATA,">$file") || die "Cannot saved parse
document\n";
print DATA "$file_contents";
close(DATA);
}
sub main{
#Retrieves HTML for template
print "Opening Template - ";
open(FILE,"$html_file") || die "Cannot open HTML
because $!";
my $data = join('',<FILE>);
close(FILE);
#Please let them be global variables
($header_html,$footer_html) =
split(/\%content\%/,$data);
print "Successful\n";
#Copys directory structure of old to new one...
print "Copying Directory Path - ";
mkpath([$open_dir, $save_dir], 1, 0711);
print "Successful\n";
#Starts the actual File Search & Replace
print "Starting Search and Replace - \n";
find (\&eachFile, "$open_dir");
print "Successful\n";
}
===============
>
> I defined $header_html and $footer_html. Pointing to
> actual html header and footer files.
>
> obliged,
> Stretch
>
__________________________________________________
Do You Yahoo!?
HotJobs - Search Thousands of New Jobs
http://www.hotjobs.com
--
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]