#!/usr/local/bin/perl use strict; use warnings; use LWP::Simple; my $url3 = "http://www.ebi.ac.uk/thornton-srv/databases/cgi-bin/pdbsum/GetPage.pl?pdbcode=2j6p&template=ligands.html&l=1.1"; my $content =get ($url3); use HTML::TreeBuilder; my $p = HTML::TreeBuilder->new; $p->parse_content($content); my @href; my @anchors = $p->look_down(_tag => q{a}); for my $anchor (@anchors){ my $txt = $anchor->as_text; if ($txt=~ /EPE\s/){ print $txt, qq{\n}; my $href = $anchor->attr(q{href}); print $href, qq{\n}; chomp ($href); push @href, $href; #now I need to go to the link where there are my EPE ligand and then parse and extract the link of the RunLigplot.pl that is the output of a program LigPlot, written in perl, is a postcript, and I need that file as a script to extract info....I need to repeat these parsing for every link,for every EPE.... my $i=1; for my $href(@href) {my $url4= "http://www.ebi.ac.uk$href[$i]; $content=get($url4); $i=$i+1; } } } $p->delete; $p = HTML::TreeBuilder->new; $p->parse_content($content); my @href0; my @anchors0 = $p->look_down(_tag => q{a}); for my $anchor0 (@anchors0){ my $href0 = $anchor0->attr(q{href}); my $txt4 = $href0->as_text; if ($txt4=~ /ligplot\d\d_\d\d'/){ print $txt4, qq{\n}; push @href0, $txt4; } } $p->delete; }; my $u=1; foreach $txt4(@href0){ my $url5= "http://www.ebi.ac.uk$txt4[$u]"; $u=$u+1; #I need to download every file of EPE (as http://www.ebi.ac.uk/thornton-srv/databases/cgi-bin/pdbsum/RunLigplot.pl?pdb=2j6p&file=ligplot04_01 and http://www.ebi.ac.uk/thornton-srv/databases/cgi-bin/pdbsum/RunLigplot.pl?pdb=2j6p&file=ligplot04_02) in this case, these are my $url5 use LWP::Simple; my @files = (["$url5", "2j6p.$u.pl"], ["http://www.ebi.ac.uk/thornton-srv/databases/cgi-bin/pdbsum/GetText.pl?pdb=2j6p&chain=A&seq_fasta=1?pdb=2j6p&chain=A&seq_fasta=1", "$path/$Dir/2j6p.seq.fasta"] ); for my $duplet (@files) { mirror($duplet->[0], $duplet->[1]); }