超映画批評をスクレイピング

fetch_movie_score.pl

#!/usr/bin/env perl
=pod
perl fetch_movie_score.pl 1 100|sort -nrk3 -t $'\t'
みたいな感じの使い方を想定
=cut
use strict;
use warnings;
use Try::Tiny;
use Carp;
use LWP::Simple;
use Encode;

my $begin = $ARGV[0];
my $end = $ARGV[1];
carp "$begin -> $end";

my $id = $begin - 1;
while($id < $end){
  sleep 1;
  carp ++$id;
  my $url = "http://movie.maeda-y.com/movie/@{[sprintf('%05d', $id)]}.htm";
  my $html = get($url) or next;
  $html = Encode::encode_utf8 $html;
  $html =~ s/　|\t|\n/ /g;
  next unless $html =~ /<h1 class="title">\s*(?:『|「)(.+)(?:』|」)\s*(\d+)点/;
  print "$id\t$1\t$2\t$url\n";
}