User:Wherebot/Source

#!/usr/bin/perl
use strict;

#some of the IRC parts of this bot are based off of the Bot::BasicBot sample code

Wherebot->new(channels => ["#en.wikipedia", "#en.wikiversity"], nick=>"Wherebot4", server => "irc.wikimedia.org")->run(); #CONFIG: change Wherebot4 to something unique

package Wherebot;
use base qw/Bot::BasicBot/;
use IPC::Open2;

sub said {
   shift(); #don't care about the first parameter
   our %hash = %{shift()};

   our $rawMessage = $hash{"body"};
   our $channel = $hash{"channel"};
   our $site = $channel;
   $site =~ s&#&&;
   $rawMessage =~ m#02(http://$site.org[^ ]+)#;
   our $url = $1;
#CONFIG: the next four lines are to ignore certain pages. Customize if you like
   if ($url =~ /[Tt]alk:/) {return;}
   if ($url =~ /Sandbox/) {return;}
   if ($url =~ /Articles for deletion/) {return;}
   if ($url =~ /Wikipedia:Introduction/) {return;}
   chop $rawMessage;
   if ($rawMessage =~ /N\x{03}10/) {
#CONFIG: the next four lines are to ignore certain namespaces. Customize if you like.
      if ($url =~ /User:/) {return;}
      if ($url =~ /Wikipedia:/) {return;}
      if ($url =~ /Portal:/) {return;}
      if ($url =~ /Help:/) {return;}
      if ($url =~ /Template:/) {return;}
      if ($url =~ /Category:/) {return;}
      if ($url =~ /Image:/) {return;}

      &act($channel, $url);
   }
}


 sub URLDecode { #From http://glennf.com/writing/hexadecimal.url.encoding.html
    my $theURL = $_[0];
    $theURL =~ tr/+/ /;
    $theURL =~ s/%([a-fA-F0-9]{2,2})/chr(hex($1))/eg;
    $theURL =~ s/<!--(.|\n)*-->//g;
   return $theURL;
 }




sub act {
   our $misc = "/home/where/misc";
   our $channel = shift;
   our $url = shift;
   $url =~ s#'##g; #just in case, although this would never be necessary
   chop $url;
   our $term = `wget '$url?action=raw' -q -O - | head -n 1`;
   chomp $term;

   our $origUrl = $url;
   $url =~ m#view_html.php?sq=Qlik&lang=&q=(.*)#;
   our $page = $1;
   $url .= "?action=raw";
   $url =~ s#'##g; #shouldn't be a problem, but hey, I'm paranoid
   chomp $term;
   $term = &trim($term); #get it to <100 words so yahoo doesn't go crazy
   if ($term =~ /#redirect/i) {
      return;
   }
   if ($term =~ /^\{/) {
      return;
   }
   if ($term =~ /^</) {
      return;
   }

   $term =~ s#'''##g;
   $term =~ s#''##g;
   $term =~ s#\[\[##g;
   $term =~ s#\]\]##g;
   $term =~ s#\*##g;
   $term =~ s#"##g; #Yahoo chokes on quotes; yes, this will probably return false matches, but it is better than the alternative
   $term =~ s#\(##g;
   $term =~ s#\)##g;
#   if (m#([^\(\)]+)[\(\)]#) { #same thing with parenthesis
#      $term = $1;
#   }

   if (length($term) < 75) {
      return;
   }

   our $firstLine;
   our $n=0;
   while (1) {
      our $pid = open2(*Reader, *Writer, "python", "$misc/search.py", "-t", "web", '"' . $term . '"'); #CONFIG: CHANGE $misc/search2.py to the path to search.py from the Yahoo search API
      $firstLine = <Reader>;
     # print "($url): FL: $firstLine\n";
      if ($firstLine =~ /Internal WebService error, temporarily unavailable/ || $firstLine =~ /^Got an error/) {
        warn "Search failed; retrying\n";
        sleep 60;
        waitpid $pid, 0;
        ++$n;
        if ($n < 3) {
           next;
        }
        else {
           last;
        }
      }
      else {
        waitpid $pid, 0;
        last;
      }
   }

   if (!($firstLine =~ /^No results\s*/)) {
      <Reader>;<Reader>; #skip some lines
      our $from = <Reader>;
      $from =~ s#\s##g;
      if ($from =~ m#^http://en\.wikipedia\.org# || $from =~ m#\.gov# || $from =~ m#^http://en.wikibooks#) {
        return;
      }

      #Get the page in the proper format
      $page = &URLDecode($page);
      $page =~ s#_# #g;

      our $strippedUrl = $from;
      $strippedUrl =~ s#^http://##;
      #print "($page) copyvio from $from\n";

      if ($channel eq "#en.wikipedia") { #CONFIG: change this line according to your language and version
        chdir "$misc/pywikipedia"; #CONFIG: change this line according to where your pywikipedia directory is
      }
      print "Writing\n";
      open APPEND_PY, "|nice -n 10 python append.py";
      print APPEND_PY  "* [[$page]] -- [$from $strippedUrl]. Reported at ~~~~~";
      close APPEND_PY;
   }
}

sub trim { #cut parameter to <100 words
   our $in = shift;
   our @in = split / /, $in;
   our $out = "";
   our $i = 1;
   for (@in) {
      $out .= $_ . " ";
      ++$i;
      if ($i == 99) {
        last;
      }
   }
   chop $out; #get rid of last space
   return $out;
}