Automatically check jury duty on-call status

jury-mojo.pl

#!/usr/bin/env perl
#
# A simple script to repeatedly check on-call status for United States
# District Court juror instructions.  It will send mail with any instructions
# and, if necessary, schedule itself to check again when instructed.
#
# Usage: /path/to/jury-mojo.pl PARTICIPANT_ID ZIP_CODE

use 5.012;
use Mojo::UserAgent;
use DateTime::Format::DateParse;
use Email::Simple;
use Email::Sender::Simple qw( sendmail );

my $email = Email::Simple->create(
    header => [
        To   => '"Me" <me@example.com>',
        From => '"Me Too" <me@example.com>',
    ],
);

# Safety first!
$SIG{'__DIE__'} = sub {
    $email->header_set( 'Subject' => 'Jury Check: Died' );
    $email->body_set( $_[0] );
    sendmail($email);
    die @_;
};

my $ua  = Mojo::UserAgent->new;
my $url = 'http://jury.casd.uscourts.gov/AppearWeb/Default.aspx';
my $res = $ua->get($url)->res;  # initial fetch to get cookie and form fields
my $tx  = $ua->max_redirects(3)->post_form(
    $url => {
        '__VIEWSTATE'           => $res->dom('form#Form1 > input#__VIEWSTATE')->[0]->attrs('value'),
        '__EVENTVALIDATION'     => $res->dom('form#Form1 > input#__EVENTVALIDATION')->[0]->attrs('value'),
        'ctl02$txtPart'         => $ARGV[0],
        'ctl02$txtZip'          => $ARGV[1],
        'ctl02$btnInstructions' => 'Reporting Instructions',
    }
);

$res = $tx->success or die $tx->error;

# This is what the response message looks like in the HTML:
# <span id="ctl02_lblMsg">Please check again Sunday, April 29, after 6:00pm for further reporting instructions. Do NOT report at this time.</span>
my $message = $res->dom('span#ctl02_lblMsg')->[0]->text;

if ( $message !~ /Do NOT report at this time/ ) {
    # We didn't see the message we wanted to see, so we'd better alert.
    $email->header_set( 'Subject' => 'Jury Check: You may need to report' );
    $email->body_set("$message\n");
    sendmail($email);
    exit;
}

if ( $message !~ /Please check again (?<weekday>\w+), (?<month>\w+) (?<day>\d+)/ ) {
    # We couldn't parse the next date to check, so we'd better alert.
    $email->header_set( 'Subject' => 'Jury Check: Failed to parse date' );
    $email->body_set("$message\n");
    sendmail($email);
    exit;
}

my $dt = DateTime::Format::DateParse->parse_datetime("$+{'weekday'}, $+{'day'} $+{'month'} 18:15");

# Set up an at(1) job for the next time we need to check.  The jury
# instructions are always updated at 18:00, so we're hard-coding that bit with
# a buffer.
open my $at, '|-', 'at', $dt->strftime('%R'), $dt->strftime('%F') or die "at: $!";
say {$at} "$0 @ARGV 2>/dev/null";    # $0 must be fully qualified or in PATH
close $at;

# We should alert anyway, just in case things didn't work out quite right.
$email->header_set( 'Subject' => 'Jury Check: Do NOT report at this time' );
$email->body_set( sprintf "%s\n\nNext check scheduled for %s.\n", $message, $dt->strftime('%c') );
sendmail($email);

jury.pl

#!/usr/bin/env perl
#
# A simple script to repeatedly check on-call status for United States
# District Court juror instructions.  It will send mail with any instructions
# and, if necessary, schedule itself to check again when instructed.
#
# Usage: /path/to/jury.pl PARTICIPANT_ID ZIP_CODE

use 5.012;
use WWW::Scripter;  # h/t cpansprout (https://gist.github.com/2522558#gistcomment-292147)
use DateTime::Format::DateParse;
use Email::Simple;
use Email::Sender::Simple qw( sendmail );

my $email = Email::Simple->create(
    header => [
        To   => '"Me" <me@example.com>',
        From => '"Me Too" <me@example.com>',
    ],
);

# Safety first!
$SIG{'__DIE__'} = sub {
    $email->header_set( 'Subject' => 'Jury Check: Died' );
    $email->body_set( $_[0] );
    sendmail($email);
    die @_;
};

# This may only work for the Southern District of California.
my $mech = WWW::Scripter->new();
$mech->get('http://jury.casd.uscourts.gov/AppearWeb/Default.aspx');
$mech->submit_form(
    form_name => 'Form1',
    fields    => {
        'ctl02$txtPart' => $ARGV[0],
        'ctl02$txtZip'  => $ARGV[1],
    },
    button => 'ctl02$btnInstructions',
);

# This is what the response message looks like in the HTML:
# <span id="ctl02_lblMsg">Please check again Sunday, April 29, after 6:00pm for further reporting instructions. Do NOT report at this time.</span>
my $message = $mech->document->getElementById('ctl02_lblMsg')->innerHTML;

if ( $message !~ /Do NOT report at this time/ ) {
    # We didn't see the message we wanted to see, so we'd better alert.
    $email->header_set( 'Subject' => 'Jury Check: You may need to report' );
    $email->body_set("$message\n");
    sendmail($email);
    exit;
}

if ( $message !~ /Please check again (?<weekday>\w+), (?<month>\w+) (?<day>\d+)/ ) {
    # We couldn't parse the next date to check, so we'd better alert.
    $email->header_set( 'Subject' => 'Jury Check: Failed to parse date' );
    $email->body_set("$message\n");
    sendmail($email);
    exit;
}

my $dt = DateTime::Format::DateParse->parse_datetime("$+{'weekday'}, $+{'day'} $+{'month'} 18:15");

# Set up an at(1) job for the next time we need to check.  The jury
# instructions are always updated at 18:00, so we're hard-coding that bit with
# a buffer.
open my $at, '|-', 'at', $dt->strftime('%R'), $dt->strftime('%F') or die "at: $!";
say {$at} "$0 @ARGV 2>/dev/null";    # $0 must be fully qualified or in PATH
close $at;

# We should alert anyway, just in case things didn't work out quite right.
$email->header_set( 'Subject' => 'Jury Check: Do NOT report at this time' );
$email->body_set( sprintf "%s\n\nNext check scheduled for %s.\n", $message, $dt->strftime('%c') );
sendmail($email);

Instead of

$dom->parse_file( IO::Scalar->new( do { my $c = $mech->content; \$c } ) );

you could write simply

$dom->write($mech->content);
$dom->close;

Alternatively, you could s/WWW::Mechanize/WWW::Scripter/ and write

my $message = $mech->document->getElementById('ctl02_lblMsg')->innerHTML;

WWW::Scripter, a subclass of WWW::Mechanize, is HTML::DOM’s raison d’être

Oh, that's excellent. As I was working on a version using Mojo::UserAgent (as someone recommended I try), I found myself thinking, "It would be awesome if WWW::Mechanize gave me access to the document with HTML::DOM." Thanks for the pointer to the module that filled exactly that need.