CODEWITHSUNDEEP
perlfileinputmojolicious
tlialin
tlialin

Reputation: 71

how to get files for Mojolicious from a directory

So I have some code and I can use it in terminal fine but I can't figure out how to get multiple files for Mojolicious from a directory rather than feeding them 1 by 1. I'm super new to perl and could use excel to make 2,000 lines and pass it in terminal but I'd rather not. Any help is greatly appreciated. Here's the code:

use lib '/Users/lialin/perl5/lib/perl5';
use strict;
use warnings;
use feature 'say';

use File::Slurp 'slurp';    # makes it easy to read files.
use Mojo;
use Mojo::UserAgent;
use URI;

#my $html_file = "Ask/Agilent_Technologies_ask.html";  # take file from directory
my $html_file = shift @ARGV;    # take file from command lin

my $dom = Mojo::DOM->new( scalar slurp $html_file);
print $html_file ;

#for my $csshref ($dom->find('a[href]')->attr('href')->each) {
#for my $link ($dom->find('a[href]')->attr('href')->each) {
#   print $1;
#say $1 #if $link->attr('href') =~ m{^https?://(.+?)/index\.php}s;
for my $csshref ( $dom->find('a[href]')->attr('href')->each ) {
    my $cssurl = URI->new($csshref)->abs($html_file);
    print "$cssurl\n";
}

Any help is greatly appreciated.

There was a comment below about what to use and I've tried the first method, still don't quite get glob. Here's what I already tried and errored out on:

use lib '/Users/lialin/perl5/lib/perl5';
use strict;
use warnings;
use feature 'say';
use File::Slurp 'slurp';    # makes it easy to read files.
use Mojo;
use Mojo::UserAgent;
use URI;

#my $html_file = "Ask/Agilent_Technologies_ask.html";  # take file from directory
#my $html_file = shift @ARGV; # take file from command lin

my $calls_dir = "Ask/";
opendir( my $search_dir, $calls_dir ) or die "$!\n";
my @html_files = grep /\.html$/i, readdir $search_dir;
closedir $search_dir;
#print "Got ", scalar @files, " files\n";

#my %seen = ();
foreach my $html_files (@html_files) {
    my %seen         = ();
    my $current_file = $calls_dir . $html_files;
    open my $FILE, '<', $current_file or die "$html_files: $!\n";

    my $dom = Mojo::DOM->new( scalar slurp $html_files);
    print $html_files ;

    #for my $csshref ($dom->find('a[href]')->attr('href')->each) {
    #for my $link ($dom->find('a[href]')->attr('href')->each) {
    #   print $1;
    #say $1 #if $link->attr('href') =~ m{^https?://(.+?)/index\.php}s;
    for my $csshref ( $dom->find('a[href]')->attr('href')->each ) {
        my $cssurl = URI->new($csshref)->abs($html_files);

        open my $fh, '>', "${html_files}result.txt" or die $!;
        $fh->print("$html_files\t$_\n");

        #print "$cssurl\n";
    }
}

I think I need to string but use the same one and mess something up. Thanks again for assisting the newbie.

Upvotes: 1

Views: 880

Answers (1)

Miller
Miller

Reputation: 35198

You failed to include the directory information in your output file:

    open my $fh, '>', "${html_files}result.txt" or die $!;

I would recommend revamping your code to use Path::Class to handle the file and directory operations for you in a cross platform compatible way.

Note, it's not entirely clear what you're trying to do with your code, but this is probably what you're aiming for stylistically:

use lib '/Users/lialin/perl5/lib/perl5';
use strict;
use warnings;
use feature 'say';

use Mojo::DOM;
use Path::class;
use URI;

my $dir = dir("Ask/");

for my $file ( $dir->children ) {
    next if $file->is_dir || $file !~ /\.html$/i;

    my $data = $html_file->slurp;
    my $dom  = Mojo::DOM->new($data);

    my $fh = file( $file . 'result.txt' )->openw;

    for my $csshref ( $dom->find('a[href]')->attr('href')->each ) {
        my $cssurl = URI->new($csshref)->abs( $file->basename );   # What are you doing with abs ?

        $fh->print("$file\t$_\n");  # <-- What is $_ supposed to be ?
    }
}

Upvotes: 1

Related Questions