46 lines
1.2 KiB
Perl
Executable File
46 lines
1.2 KiB
Perl
Executable File
#!/usr/bin/env perl
|
|
use 5.016;
|
|
use common::sense;
|
|
use utf8::all;
|
|
|
|
# Use fast binary libraries
|
|
use EV;
|
|
use Web::Scraper::LibXML;
|
|
use YADA 0.039;
|
|
use Data::Structure::Util qw( unbless );
|
|
|
|
YADA->new(
|
|
common_opts => {
|
|
# Available opts @ http://curl.haxx.se/libcurl/c/curl_easy_setopt.html
|
|
encoding => '',
|
|
followlocation => 1,
|
|
maxredirs => 5,
|
|
}, http_response => 1, max => 4,
|
|
)->append([qw[
|
|
http://foo.qa/release
|
|
]] => sub {
|
|
my ($self) = @_;
|
|
return if $self->has_error
|
|
or not $self->response->is_success
|
|
or not $self->response->content_is_html;
|
|
|
|
# Declare the scraper once and then reuse it
|
|
state $scraper = scraper {
|
|
process q(ol > .message > .innerContainer > .messageInfo > .messageContent), q(op) => {
|
|
q(links[]) => scraper{ process q(a), q(shit[]) => q(@href);},
|
|
post => q(TEXT)
|
|
};
|
|
};
|
|
|
|
# Employ amazing Perl (en|de)coding powers to handle HTML charsets
|
|
my @doc = $scraper->scrape(
|
|
$self->response->decoded_content,
|
|
$self->final_url,
|
|
);
|
|
|
|
|
|
# print "$_\n" for @{$doc->{op} // []};
|
|
print Data::Dumper->Dump( \@doc );
|
|
# print $doc->{op}."\n"
|
|
|
|
})->wait; |