Perl Web::Scraper 结构化提取网页内容 crawler
用 Web::Scraper 解析 html / xml 数据
教程：http://e8y.net/mag/013-web-scraper/
注意：tag如果有大写字母，例如
#!/usr/bin/perl
use strict;
use warnings;
use Web::Scraper;
use Data::Dumper;
my $html =q[
<Message name="testn" value="testv">
<Sub_Message title="abc">just abc</Sub_Message>
<Sub_Message title="efg">just efg</Sub_Message>
</Message>];
my $scraper = scraper {
process_first 'message', 'msg_name' => '@name', 'msg_value' => '@value';
process 'sub_message' , 'sub_message[]' => {
'title' => '@title',
'content' => 'TEXT',
};
};
my $res = $scraper->scrape(\$html);
print Dumper($res);