# goonow.pl
# Feeds queries specified in a text file to Google, querying
# for recent additions to the Google index.  The script appends
# to CSV files, one per query, creating them if they don't exist.
# usage: perl goonow.pl [query_filename]
     
# My Google API developer's key.
my $google_key='insert key here';
     
# Location of the GoogleSearch WSDL file.
my $google_wdsl = "GoogleSearch.wsdl";
     
use strict;
     
use SOAP::Lite;
use Time::JulianDay;
     
$ARGV[0] or die "usage: perl goonow.pl [query_filename]\n";
     
my $julian_date = int local_julian_day(time) - 2;
     
my $google_search  = SOAP::Lite->service("file:$google_wdsl");
     
open QUERIES, $ARGV[0] or die "Couldn't read $ARGV[0]: $!";
     
while (my $query = <QUERIES>) {
  chomp $query;
  warn "Searching Google for $query\n";
   
  $query .= " daterange:$julian_date-$julian_date";
  (my $outfile = $query) =~ s/\W/_/g;
  open (OUT, ">> $outfile.csv")
    or die "Couldn't open $outfile.csv: $!\n";
   
  my $results = $google_search ->
    doGoogleSearch(
      $google_key, $query, 0, 10, "false", "",  "false",
      "", "latin1", "latin1"
    );

  if ($results => "") {die "The soap call failed! \n"} 

  foreach (@{$results->{'resultElements'}}) {
    print OUT '"' . join('","', (
      map {
        s!\n!!g; # drop spurious newlines
        s!<.+?>!!g; # drop all HTML tags
        s!"!""!g; # double escape " marks
        $_;
      } @$_{'title','URL','snippet'}
    ) ) . "\"\n";
  }
}