Created
January 5, 2014 14:33
-
-
Save visar/8268883 to your computer and use it in GitHub Desktop.
Perl script for downloading multiple pdfs from a web-page
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/perl | |
use strict; | |
use warnings; | |
use WWW::Mechanize; | |
use File::Basename; | |
use LWP::Simple; | |
use PDF::API2; | |
my $page = WWW::Mechanize->new(); | |
$page->get("http://www.cs.cmu.edu/~guna/15-123S11/Lectures"); | |
my @pdfs = $page->find_all_links( | |
tag => "a", | |
url_regex => qr/\.pdf$/ | |
); | |
mkdir "pdfs"; | |
my $merged_file = "pdfs/merged.pdf"; | |
my $merged_pdf = PDF::API2->new( -file => $merged_file ); | |
foreach my $link (@pdfs) { | |
my $url = $link->url_abs(); | |
my $localfile = basename($url); | |
my $localpath = "pdfs/$localfile"; | |
getstore( $url, $localpath ); | |
my $input_pdf = PDF::API2->open($localpath); | |
my @numpages = ( 1 .. $input_pdf->pages() ); | |
foreach my $numpage (@numpages) { | |
$merged_pdf->importpage( $input_pdf, $numpage, 0 ); | |
} | |
} | |
$merged_pdf->save(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment