Created
February 5, 2010 06:27
-
-
Save kidd/295567 to your computer and use it in GitHub Desktop.
This file contains hidden or 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/perl | |
| use strict; | |
| use warnings; | |
| use HTML::TreeBuilder; | |
| use LWP::UserAgent; | |
| use Data::Dump qw(ddx dump); | |
| use Memoize; | |
| use feature ':5.10'; | |
| sub getShippingRate { | |
| #http://www.iberlibro.com/servlet/ShipRates?vid=51947087 | |
| my ($id) = @_; | |
| my $response = LWP::UserAgent->new->request( | |
| HTTP::Request->new( GET => "http://www.iberlibro.com/servlet/ShipRates?vid=$id")); #$id | |
| my $tree = HTML::TreeBuilder->new(); | |
| $tree->parse($response->content); | |
| $tree->eof; | |
| my $t = ($tree->look_down( | |
| 'class','data' | |
| ))[0]; | |
| my $row = ($t->look_down('_tag' , 'tr'))[1]; | |
| my $col = ($row->look_down('_tag', 'td'))[1]; | |
| $col->as_text =~ /EUR (.+)/; | |
| return $1; | |
| } | |
| sub fixPaths { | |
| my ($root) = @_; | |
| foreach my $link ( | |
| $root->look_down('_tag','a', | |
| sub { | |
| return unless $_[0]->attr('href') =~ /^\//; | |
| $_[0]->attr('href', "http://iberlibro.com". $_[0]->attr('href')); | |
| } | |
| )) | |
| { | |
| # say $link->dump; # | |
| }} | |
| memoize('getShippingRate'); | |
| my $tree = HTML::TreeBuilder->new; | |
| $tree->parse_file('sr.html'); | |
| #$tree->dump; | |
| my $root = $tree->root; | |
| #fixPaths($root); | |
| # print $tree->as_HTML; | |
| my @a = $root->look_down('_tag','table', 'class','result'); | |
| for (my $i=0 ; $i<@a ; $i++) { | |
| $i++; | |
| my $price = $a[$i]->look_down('class','price'); | |
| # print $a[$i]->dump; | |
| #die; | |
| my $scndInfo = $a[$i]->look_down('_tag' , 'div' , 'class','scndInfo'); | |
| # print $price->as_text , " <-preu \n"; | |
| my @link = $scndInfo->look_down('_tag', 'a'); | |
| # print $link[0]->dump; | |
| # die; | |
| my ($id) = $link[0]->attr('href') =~ /vid=(.+)$/; | |
| #http://www.iberlibro.com/servlet/ShipRates?vid=51947087 | |
| # say getShippingRate($1); | |
| my $element = HTML::Element->new('b'); | |
| $price->as_text =~ /EUR (.+)/; | |
| # say $1; | |
| # say $id; | |
| $element->push_content(getShippingRate($id) + $1); | |
| $scndInfo->push_content($element); | |
| } | |
| #ddx \@b; | |
| #print $_->dump; | |
| fixPaths($root); | |
| print $tree->as_HTML; | |
| $tree->delete; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment