#!/usr/bin/perl # Copyright Mark Nielsen January 20001 # Copyright under the GPL license. system ("lynx --source http://www.debian.org/News/weekly/index.html > /tmp/List2.txt"); ### Open up the webpage we just downloaded and put it into an array. open(FILE,'/tmp/List2.txt'); my @Lines = ; close FILE; ### Extract out the parts that are between beginning and end of TOC. my @TOC = (); my $Count = 0; my $Start = 'Recent issues of Debian Weekly News'; my $End = '

'; foreach my $Line (@Lines) { if (($Line =~ /\Q$End\E/i) && ($Count > 0)) {$Count = 2;} if ($Count == 1) {push(@TOC, $Line);} if ($Line =~ /^\Q$Start\E/i) {$Count = 1;} } ### Relink all the links to point to the DWN my $Relink = "http://www.debian.org/News/weekly/"; grep($_ =~ s/HREF\=\"/HREF\=\"$Relink/ig, @TOC); grep($_ =~ s/\"\>/\" target=_external\>/ig, @TOC); ### Save the output open(FILE,">/tmp/D.html"); print FILE @TOC; close FILE; ### Done!