Created
October 29, 2012 20:12
-
-
Save jberger/3976227 to your computer and use it in GitHub Desktop.
data from imdb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env perl | |
use strict; | |
use warnings; | |
use v5.10; | |
use Mojo::DOM; | |
my $dom = Mojo::DOM->new( <<'HTML' ); | |
<table border="0" cellpadding="2"> | |
<tbody><tr><th class="xxxx">Country</th><th class="xxxx">Date</th></tr> | |
<tr><td><b><a href="/calendar/?region=US">USA</a></b></td> | |
<td align="right"><a href="/date/01-18/">18 January</a> <a href="/year/2009/">2009</a></td> | |
<td> (Sundance Film Festival)</td></tr> | |
<tr><td><b><a href="/calendar/?region=DE">Germany</a></b></td> | |
<td align="right"><a href="/date/02-06/">6 February</a> <a href="/year/2009/">2009</a></td> | |
<td> (European Film Market)</td></tr> | |
<tr><td><b><a href="/calendar/?region=US">USA</a></b></td> | |
<td align="right"><a href="/date/03-20/">20 March</a> <a href="/year/2009/">2009</a></td> | |
<td> (limited)</td></tr> | |
</tbody></table> | |
HTML | |
sub get_row_data { | |
my $col = $_->find('td, a'); | |
return () unless $col->size; | |
my $data = $col->pluck('text'); | |
return [grep { length } $data->each]; | |
} | |
my @rows = $dom->find('tr')->map( \&get_row_data )->each; | |
use DDP; | |
p @rows; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment