#!/usr/bin/perl -w
use strict;
use LWP;
use Term::ReadKey;
use Getopt::Std;
use HTML::TokeParser;
use HTTP::Request::Common;
$| = 1;
use vars qw(%opts);
getopts('p:u:s:h',\%opts);
my ($user,$passwd,$help) = parse_args(\%opts);
USAGE() and exit unless $user and $passwd and not $help;
use constant URL => 'http://www.perlmonks.org/';
my $SEP = $opts{s} || "\t";
my $ua = LWP::UserAgent->new;
$ua->agent('personal_nodlet_extractor/1.0 (' . $ua->agent .')');
# log in and access your User Setting page in raw format
my $request = POST(URL,
Content => [
op => 'login',
user => $user,
passwd => $passwd,
node_id => 1072,
displaytype => 'raw',
]
);
my $response = $ua->request($request);
die $response->message unless $response->is_success;
# pass the HTML content to TokeParser
my $content = $response->content;
my $parser = HTML::TokeParser->new(\$content);
# 'fast forward' until we find "<b>Personal Nodelet</b>"
while ($parser->get_tag('b')) {
last if 'Personal Nodelet' eq $parser->get_text;
}
# these are the [links|droids] we are looking for
while (my $tag = $parser->get_tag('a')) {
if ($tag->[1]->{href} =~ /[^t]node_id=(\d+)/) {
print $1 . $SEP . $parser->get_text . "\n";
}
}
sub parse_args {
my %opt = %{+shift};
if (exists $opt{'p'} and not defined $opt{'p'} and defined $opt{'u'
+}) {
print "Enter password: ";
ReadMode 'noecho';
chomp($opt{'p'} = ReadLine 0);
ReadMode 'normal';
}
return @opt{qw(u p h)};
}
sub USAGE { print "USAGE: $0 -u user [-s separator] -p password\n" }
=pod
=head1 NAME
extract_personal_nodelet.pl - LWP script
=head1 DESCRIPTION
This is a simple script that uses LWP and HTML::TokeParser to
access your User Settings page and extracts your Personal
Nodelet links.
=head1 SYNOPSIS
for *nix:
./extract_personal_nodelet.pl -u uname -s : -p
for win32:
perl extract_personal_nodelet.pl -u uname -s : -p
Invokes the script for the specified username and use a
colon as the record separator. The script will prompt
you for your password if you do not specify it. The
contents would look something like this:
24270:Permutations and combinations
25730:Life in the land of OOP, and I'm confused.
17890:Shift, Pop, Unshift and Push with Impunity!
32005:Apache::MP3
34786:Why I like functional programming
The default record seperator is a tab. I recommend you use it
since just about any character is fair game for a node title.
=cut
-
Are you posting in the right place? Check out Where do I post X? to know for sure.
-
Posts may use any of the Perl Monks Approved HTML tags. Currently these include the following:
<code> <a> <b> <big>
<blockquote> <br /> <dd>
<dl> <dt> <em> <font>
<h1> <h2> <h3> <h4>
<h5> <h6> <hr /> <i>
<li> <nbsp> <ol> <p>
<small> <strike> <strong>
<sub> <sup> <table>
<td> <th> <tr> <tt>
<u> <ul>
-
Snippets of code should be wrapped in
<code> tags not
<pre> tags. In fact, <pre>
tags should generally be avoided. If they must
be used, extreme care should be
taken to ensure that their contents do not
have long lines (<70 chars), in order to prevent
horizontal scrolling (and possible janitor
intervention).
-
Want more info? How to link
or How to display code and escape characters
are good places to start.
|