Web::Scraper与Template::Extract获取网页数据

001Web::Scraper获取广州天气

#!/usr/bin/perl
use utf8;
use URI;
use Web::Scraper;

binmode( STDOUT, ':encoding(utf8)' );

my $url = "";
my $proce = scraper {
    process '.yuBaoTable > tr', 'rows[]' =>scraper {
        process 'td', 'cols[]' => 'TEXT';
    };
};

my $res = $proce->scrape( URI->new($url) );
for my $row ( @{ $res->{rows} } ) {

    my @weather=@{ $row->{cols} };
    print "@weather\n";

}

002Web::Scraper获取网页表格数据

#!/usr/bin/perl
use utf8;
use URI;
use Web::Scraper;

binmode( STDOUT, ':encoding(utf8)' );

my $url = "";
my $proce = scraper {
    process 'table#UCITeamList > tr', 'rows[]' =>scraper {
        process 'td', 'cols[]' => 'TEXT';
    };
};

my $res = $proce->scrape( URI->new($url) );

for my $row ( @{ $res->{rows} } ) {
    my ($code,$team,$country)=@{ $row->{cols} }[0,1,2];
    printf "%-5s \| %-30s \| %-2s\n", $code,$team,$country;
}

__END__
#html 样式
<table id=UCITeamList class=WithBorder>
  <tr>
    <td class=ColHeader>Code</td>
    <td class=ColHeader>Team</td>
    <td class=ColHeader>Country</td>
  </tr>
  <tr>
    <td><a href=/Modules/SUCI/TEAMS/TeamDetails.asp?id=OA&RefDate=05.06.2010&MenuId=MTU4MzI&LangId=1&BackLink=%2Ftemplates%2FUCI%2FUCI2%2Flayout%2Easp%3FMenuId%3DMTU4MzI%26LangId%3D1>ALM</a></td>
    <td><a href=/Modules/SUCI/TEAMS/TeamDetails.asp?id=OA&RefDate=05.06.2010&MenuId=MTU4MzI&LangId=1&BackLink=%2Ftemplates%2FUCI%2FUCI2%2Flayout%2Easp%3FMenuId%3DMTU4MzI%26LangId%3D1>AG2R LA MONDIALE</a>
    </td>
    <td><a href=/Modules/SUCI/TEAMS/TeamDetails.asp?id=OA&RefDate=05.06.2010&MenuId=MTU4MzI&LangId=1&BackLink=%2Ftemplates%2FUCI%2FUCI2%2Flayout%2Easp%3FMenuId%3DMTU4MzI%26LangId%3D1>FRA</a></td>
  </tr>

003Template::Extract获取sina新闻

#!/usr/bin/perl
use Encode;
use LWP::Simple 'get';
use Template::Extract;

#use Data::Dumper;

my $html = get('');
my $rule = <<RULE;
<div class="blkContainerSblkCon"[% ... %]>
[% ... %]
[% FOREACH record %]
<p>[% content %]</p>
[% ... %]
[% END %]
RULE

my $extract = Template::Extract->new();
my $data = $extract->extract( $rule, T($html) );

#print Dumper(\$data);

foreach ( 0 .. @{ $data->{'record'} } ) {
    my $contents = $data->{'record'}->[$_]->{content};
    print $contents, "\n";
}

sub T {
    my $text = shift;
    return encode( 'utf8', $text );

}
__END__
my $rule = <<RULE;
[% FOREACH record %]
<h1 id="artibodyTitle"[% ... %]>[% title %]</h1>
[% END %]
RULE

也是很早以前放QQ空间的文章。