#!/usr/bin/perl
use strict;
use warnings;
use utf8;
use 5.10.0;
use Data::Dumper;
use Readonly;
use HTML::TreeBuilder::XPath;
use LWP::Simple;
use POSIX qw(strftime);

binmode STDOUT, 'utf8';

Readonly my $BASEURL => 'https://twitter.com';
Readonly my $USAGE   => "$0 <search_term>: make an rss of a twitter search";

die $USAGE unless $#ARGV==0;

my $term = $ARGV[0];

my $content = get("$BASEURL/search?q=$term&src=typd");
die "Couldn't get search results" unless defined $content;


my @items;

my $tree= HTML::TreeBuilder::XPath->new;
$tree->parse($content);
my $tweets = $tree->findnodes( '//li' . class_contains('js-stream-item') );  

for my $li (@$tweets) {    
  my $tweet = $li->findnodes('./div' 
                              . class_contains("tweet") 
                              . '/div' 
                              . class_contains("content") )->[0]
  ;
  my $header = $tweet->findnodes('./div' . class_contains("stream-item-header"))->[0];
  my $body   = $tweet->findvalue('./p' . class_contains("tweet-text"));
  $body = "<![CDATA[$body]]>";
  my $avatar = $header->findvalue('./a/img' . class_contains("avatar") . "/\@src"); 
  my $fullname = $header->findvalue('./a/strong' . class_contains("fullname"));
  my $username = '@' . $header->findvalue('./a/span' . class_contains("username") . '/b');
  my $uri = $BASEURL . $header->findvalue('./small' 
                              . class_contains("time") 
                              . '/a'
                              . class_contains("tweet-timestamp") 
                              . '/@href'
  );  
  my $timestamp = $header->findvalue('./small' 
                  . class_contains("time") 
                  . '/a'
                  . class_contains("tweet-timestamp") 
                  . '/span/@data-time'
  );  

  my $pub_date = strftime("%a, %d %b %Y %H:%M:%S %z", localtime($timestamp));

  push @items, {
    username => $username,
    fullname => $fullname,
    link => $uri,
    guid => $uri,
    title => $body,
    description => $body,
    timestamp => $timestamp,
    pubDate => $pub_date
  }
}
$tree->delete; 
 
# now print as an rss feed
print<<ENDHEAD
<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" xmlns:georss="http://www.georss.org/georss" xmlns:twitter="http://api.twitter.com" version="2.0">
  <channel>
    <title>Twitter Search / $term </title>
    <link>http://twitter.com/search/q=$term</link>
    <description>Twitter search for: $term.</description>
    <language>en-us</language>
    <ttl>40</ttl>
ENDHEAD
;

for (@items) {
  print<<ENDITEM
    <item>
      <title>$_->{username}: $_->{title}</title>
      <description>$_->{description}</description>
      <pubDate>$_->{pubDate}</pubDate>
      <guid>$_->{guid}</guid>
      <link>$_->{link}</link>
      <twitter:source/>
      <twitter:place/>
    </item>
ENDITEM
;
}

print<<ENDRSS
  </channel>
</rss>      
ENDRSS
;
            
  
sub class_contains {
  my $classname = shift;
  "[contains(concat(' ',normalize-space(\@class),' '),' $classname ')]";
}