#
# myweb.pl
#
# Andrew's Comics and TV summary
# v0.0: Andrew Glassner, March 26
# v0.1: AG March 27, 2003
#    Very rough, generally working
# v0.2: AG March 29, 2003
#    Brought together all the fetches into "getItem".
#    Made utility proc for United Media cartoons
#    Made some of the TV show searchs a little more robust
#    Added comments.
#    Added lots of function, cleaned things up
# v0.3: AG April 4, 2003
#    Added a couple of talk shows
#    Removed comments in getItem (this removed some false hits)
# v0.4: AG April 15, 2003 
#    Added documentation and comments
# v0.5: EH April 15, 2003
#    Added too many new comics, made getItem more general
#

#
# HOW TO USE THIS SCRIPT:
#
# I have two shortcuts on my desktop.  One is a shortcut to this
# file, named myweb.pl.  The other is a shortcut to the web page
# it makes (the one pointed to by $webFile below).  Obviously you
# have to run the script once to make that file so you can then
# make a shortcut to it.  Even though the contents of the page
# get updated every day, the name stays the same, so the 
# shortcut stays good.
#
# Every morning, I double-click on the shortcut to the script 
# It opens up a command window, runs perl, and builds the web 
# page.  Then I double-click on the shortcut to the web file, 
# it pops up in my browser, and I read and enjoy.
#
# To customize the script, you need to do three things, named
# under "ATTENTION" a few lines below here.
#
# This script requires perl.  You can get a free copy of perl
# from http://www.activestate.com/Products/ActivePerl/  
# Just download and install it; nothing special is required.
#


# These modules are typically installed as part of perl.
# If yours are out of date, get new ones from www.cpan.org
require LWP::UserAgent;
require HTTP::Request; 

#
# ATTENTION
#
# set these three things 
# 1. myName is your name!
# 2. webFile is the path for the output web page
# 3. pick the content you want in the subroutine getWebContent below
#
   $myName = "Eric";
   $webFile = "C:/my documents/perl/myweb.htm"; # note: use forward slashes

   &makeWebPage;
   exit(1);

# 
# The items below get displayed in the order they're named.
# To remove items, either delete them from the list, or turn them
# into a comment by putting a # sign at the start of the line.
#

sub getWebContent {
   &getDilbert;
   &getFoxTrot;
   &getBizarro;
   &getForBetterOrForWorse;
   &getDoonesbury;
   &getTomTheDancingBug;
   &getStoryMinute;
   &getTroubletown;
   &getPearslBeforeSwine;
   &getTheKChronicles;
   &getDorkTower;
   &getNodwick;
   &getThisModernWorld;
   &getDTWOF;
   &getPatOliphant;
   &getTomToles;
   &getTedRall;
   &getAnnTelnaes;
   &getDavidHorsey;
   &getTonyAuth;
   &getSteveSack;
   &getClayBennett;
   &getKirkAnderson;
   &getCharlieRose;
   &getJonStewart;
   &getJayLeno;
   &getDavidLetterman;
   &getConanOBrien;
   &getCraigKilborn;
   &get9ChickweedLane;
   &getAgnes;
   &getAlleyOop;
   &getAndyCapp;
   &getArloJanis;
   &getBC;
   &getBachelorParty;
   &getBallardStreet;
   &getBen;
   &getBetty;
   &getBigNate;
   &getBornLoser;
   &getBuckets;
   &getBullsNBears;
   &getCharlie;
   &getCheapThrills;
   &getCommitted;
   &getDrabble;
   &getDrawingACrowd;
   &getFatCats;
   &getFerdnand;
   &getFlightDeck;
   &getFloNFriends;
   &getFrankAndErnest;
   &getFrazz;
   &getGeech;
   &getGetFuzzy;
   &getGingerMeggs;
   &getGoFigure;
   &getGraffiti;
   &getGrandAvenue;
   &getTheGrizzwells;
   &getHeathcliff;
   &getHerbAndJamaal;
   &getHerman;
   &getJanesWorld;
   &getJumpStart;
   &getKitNCarlyle;
   &getLibertyMeadows;
   &getLilAbner;
   &getLuann;
   &getLupoAlberto;
   &getMarmaduke;
   &getMeatloafNight;
   &getMeg;
   &getModeratelyConfused;
   &getMomma;
   &getMonty;
   &getMotley;
   &getNancy;
   &getNaturalSelection;
   &getOffTheMark;
   &getOneBigHappy;
   &getTheOtherCoast;
   &getOutOfTheGenePool;
   &getOverTheHedge;
   &getPCAndPixel;
   &getPeanuts;
   &getPearslBeforeSwine;
   &getPibgorn;
   &getPickles;
   &getPotluckParish;
   &getRaisingDuncan;
   &getRealityCheck;
   &getRedAndRover;
   &getRipleys;
   &getRoseIsRose;
   &getRubes;
   &getRudyPark;
   &getSheldon;
   &getShirleyAndSon;
   &getSoupToNutz;
   &getSpeedBump;
   &getStockcarToons;
   &getStrangeBrew;
   &getTarzan;
   &getThatsLife;
   &getTopOfTheWorld;
   &getWizardOfId;
   &getWorkingDaze;
   &getRobertAriail;
   &getChuckAsay;
   &getSteveBenson;
   &getRandyBish;
   &getChipBok;
   &getBillDay;
   &getJerryHolbert;
   &getEttaHulme;
   &getDrewLitton;
   &getMikeLuckovich;
   &getHenryPayne;
   &getRobRogers;
   &getBillSchorr;
   &getMikeSmith;
   &getJeffStahler;
   &getEdStein;
   &getPaulSzep;
   &getGaryVarvel;
   }


###########################################
###### Individual content fetches
###########################################

#
# United Comics: their consistent form makes life easier
#

sub getForBetterOrForWorse { &getUnitedComic("For Better Or For Worse", "forbetterorforworse", "fb"); }

sub getTomTheDancingBug { &getUnitedComic("Tom The Dancing Bug", "tomthedancingbug", "td"); }

sub getDoonesbury { &getUnitedComic("Doonesbury", "doonesbury", "db"); }

sub getFoxTrot { &getUnitedComic("FoxTrot", "foxtrot", "ft"); }

sub getPatOliphant { &getUnitedComic("Pat Oliphant", "patoliphant", "po"); }

sub getTomToles { &getUnitedComic("Tom Toles", "tomtoles", "tt"); }

sub getTedRall { &getUnitedComic("Ted Rall", "tedrall", "tr"); }

sub getAnnTelnaes { &getUnitedComic("Ann Telnaes", "anntelnaes", "tmate"); }

sub getTonyAuth { &getUnitedComic("Tony Auth", "tonyauth", "ta"); }

sub getSteveSack { &getUnitedComic("Steve Sack", "stevesack", "tmssa"); }

sub getDavidHorsey { &getUnitedComic("David Horsey", "davidhorsey", "tmdho"); }

# United Media comics

#sub getDilbert { &getUnitedMedia("Dilbert","comics/dilbert","gif"); }
sub get9ChickweedLane { &getUnitedMedia("9 Chickweed Lane","comics/chickweed","jpg"); }
sub getAgnes { &getUnitedMedia("Agnes","creators/agnes","gif"); }
sub getAlleyOop { &getUnitedMedia("Alley Oop","comics/agnes","gif"); }
sub getAndyCapp { &getUnitedMedia("Andy Capp","creators/andycapp","gif"); }
sub getArloJanis { &getUnitedMedia("Arlo & Janis","comics/arlonjanis","gif"); }
sub getBC { &getUnitedMedia("B. C.","creators/bc","gif"); }
sub getBachelorParty { &getUnitedMedia("Bachelor Party","creators/bachelorparty","gif"); }
sub getBallardStreet { &getUnitedMedia("Ballard Street","creators/ballardst","gif"); }
sub getBen { &getUnitedMedia("Ben","comics/ben","gif"); }
sub getBetty { &getUnitedMedia("Betty","comics/betty","gif"); }
sub getBigNate { &getUnitedMedia("Big Nate","comics/bignate","gif"); }
sub getBornLoser { &getUnitedMedia("The Born Loser","comics/bornloser","gif"); }
sub getBuckets { &getUnitedMedia("The Buckets","comics/buckets","gif"); }
sub getBullsNBears { &getUnitedMedia("Bull\$ N Bear\$","comics/bullsnbears","gif"); }
sub getCharlie { &getUnitedMedia("Charlie","creators/charlie","gif"); }
sub getCheapThrills { &getUnitedMedia("Cheap Thrills","wash/cheapthrills","gif"); }
sub getCommitted { &getUnitedMedia("Committed","comics/committed","gif"); }
sub getDrabble { &getUnitedMedia("Drabble","comics/drabble","gif"); }
sub getDrawingACrowd { &getUnitedMedia("Drawing a Crowd","creators/drawingacrowd","gif"); }
sub getFatCats { &getUnitedMedia("Fat Cats","comics/fatcats","gif"); }
sub getFerdnand { &getUnitedMedia("Fred'nand","comics/frednand","gif"); }
sub getFlightDeck { &getUnitedMedia("Flight Deck","creators/flightdeck","gif"); }
sub getFloNFriends { &getUnitedMedia("Flo & Friends","creators/floandfriends","gif"); }
sub getFrankAndErnest { &getUnitedMedia("Frank & Ernest","comics/franknernest","jpg"); }
sub getFrazz { &getUnitedMedia("Frazz","comics/frazz","gif"); }
sub getGeech { &getUnitedMedia("Geech","comics/geech","gif"); }
sub getGetFuzzy { &getUnitedMedia("Get Fuzzy","comics/getfuzzy","gif"); }
sub getGingerMeggs { &getUnitedMedia("Ginger Meggs","comics/gingermeggs","gif"); }
sub getGoFigure { &getUnitedMedia("Go Figure","comics/gofigure","gif"); }
sub getGraffiti { &getUnitedMedia("Graffiti","comics/graffiti","gif"); }
sub getGrandAvenue { &getUnitedMedia("Grand Avenue","comics/grandave","gif"); }
sub getTheGrizzwells { &getUnitedMedia("The Grizzwells","comics/grizzwells","gif"); }
sub getHeathcliff { &getUnitedMedia("Heathcliff","creators/heathcliff","gif"); }
sub getHerbAndJamaal { &getUnitedMedia("Herb and Jamaal","creators/herbnjamaal","gif"); }
sub getHerman { &getUnitedMedia("Herman","comics/herman","jpg"); }
sub getJanesWorld { &getUnitedMedia("Jane's World","comics/janesworld","gif"); }
sub getJumpStart { &getUnitedMedia("Jump Start","comics/jumpstart","gif"); }
sub getKitNCarlyle { &getUnitedMedia("Kit 'N' Carlyle","comics/kitncarlyle","gif"); }
sub getLibertyMeadows { &getUnitedMedia("Liberty Meadows","creators/liberty","gif"); }
sub getLilAbner { &getUnitedMedia("Li'l Abner","comics/lilabner","gif"); }
sub getLuann { &getUnitedMedia("Luann","comics/luann","gif"); }
sub getLupoAlberto { &getUnitedMedia("Lupo Alberto","comics/lupo","gif"); }
sub getMarmaduke { &getUnitedMedia("Marmaduke","comics/marmaduke","gif"); }
sub getMeatloafNight { &getUnitedMedia("Meatloaf Night","comics/meatloaf","gif"); }
sub getMeg { &getUnitedMedia("Meg!","comics/meg","gif"); }
sub getModeratelyConfused { &getUnitedMedia("Moderately Confused","comics/moderatelyconfused","gif"); }
sub getMomma { &getUnitedMedia("Momma","creators/momma","gif"); }
sub getMonty { &getUnitedMedia("Monty","comics/monty","gif"); }
sub getMotley { &getUnitedMedia("Motley","comics/motley","gif"); }
sub getNancy { &getUnitedMedia("Nancy","comics/nancy","gif"); }
sub getNaturalSelection { &getUnitedMedia("Natural Selection","creators/naturalselection","gif"); }
sub getOffTheMark { &getUnitedMedia("Off The Mark","comics/offthemark","gif"); }
sub getOneBigHappy { &getUnitedMedia("One Big Happy","creators/onebighappy","gif"); }
sub getTheOtherCoast { &getUnitedMedia("The Other Coast","creators/othercoast","gif"); }
sub getOutOfTheGenePool { &getUnitedMedia("Out of the Gene Pool","wash/genepool","gif"); }
sub getOverTheHedge { &getUnitedMedia("Over the Hedge","comics/hedge","gif"); }
sub getPCAndPixel { &getUnitedMedia("PC and Pixel","wash/pcnpixel","gif"); }
sub getPeanuts { &getUnitedMedia("Peanuts","comics/peanuts","gif"); }
sub getPearslBeforeSwine { &getUnitedMedia("Pearls Before Swine","comics/pearls","gif"); }
sub getPibgorn { &getUnitedMedia("Pibgorn","comics/pibgorn","jpg"); }
sub getPickles { &getUnitedMedia("Pickles","wash/pickles","gif"); }
sub getPotluckParish { &getUnitedMedia("Potluck Parish","comics/potluck","gif"); }
sub getRaisingDuncan { &getUnitedMedia("Raising Duncan","comics/raisingduncan","gif"); }
sub getRealityCheck { &getUnitedMedia("Reality Check","comics/reality","gif"); }
sub getRedAndRover { &getUnitedMedia("Red & Rover","wash/redandrover","gif"); }
sub getRipleys { &getUnitedMedia("Ripley's Believe It or Not!","comics/ripleys","gif"); }
sub getRoseIsRose { &getUnitedMedia("Rose Is Rose","comics/roseisrose","gif"); }
sub getRubes { &getUnitedMedia("Rubes","creators/rubes","gif"); }
sub getRudyPark { &getUnitedMedia("Rudy Park","comics/rudypark","gif"); }
sub getSheldon { &getUnitedMedia("Sheldon","comics/sheldon","gif"); }
sub getShirleyAndSon { &getUnitedMedia("Shirly And Son","comics/shirleynson","gif"); }
sub getSoupToNutz { &getUnitedMedia("Soup To Nutz","comics/soup2nutz","gif"); }
sub getSpeedBump { &getUnitedMedia("Speed Bump","creators/speedbump","gif"); }
sub getStockcarToons { &getUnitedMedia("StockcarToons","comics/stockcartoons","gif"); }
sub getStrangeBrew { &getUnitedMedia("Strange Brew","creators/strangebrew","gif"); }
sub getTarzan { &getUnitedMedia("Tarzan","comics/tarzan","gif"); }
sub getThatsLife { &getUnitedMedia("That's Life","wash/thatslife","gif"); }
sub getTopOfTheWorld { &getUnitedMedia("Top of the World!","comics/topofworld","gif"); }
sub getWizardOfId { &getUnitedMedia("Wizard of Id","creators/wizardofid","gif"); }
sub getWorkingDaze { &getUnitedMedia("Working Daze","comics/workingdaze","gif"); }

# editorial cartoons
sub getRobertAriail { &getUnitedMedia("Robert Ariail","editoons/ariail ","gif"); }
sub getChuckAsay { &getUnitedMedia("Chuck Asay","editoons/asay","gif"); }
sub getSteveBenson { &getUnitedMedia("Steve Benson","editoons/benson","gif"); }
sub getRandyBish { &getUnitedMedia("Randy Bish","editoons/bish","jpg"); }
sub getChipBok { &getUnitedMedia("Chip Bok","editoons/bok","gif"); }
sub getBillDay { &getUnitedMedia("Bill Day","editoons/day","gif"); }
sub getJerryHolbert { &getUnitedMedia("Jerry Holbert","editoons/holbert","gif"); }
sub getEttaHulme { &getUnitedMedia("Etta Hulme","editoons/hulme","gif"); }
sub getDrewLitton { &getUnitedMedia("Draw Litton","editoons/litton","gif"); }
sub getMikeLuckovich { &getUnitedMedia("Mike Luckovich","editoons/luckovich","gif"); }
sub getHenryPayne { &getUnitedMedia("Henry Payne","editoons/payne","gif"); }
sub getRobRogers { &getUnitedMedia("Rob Rogers","editoons/rogers","gif"); }
sub getBillSchorr { &getUnitedMedia("Bill Schorr","editoons/schorr","gif"); }
sub getMikeSmith { &getUnitedMedia("Mike Smith","editoons/smith","gif"); }
sub getJeffStahler { &getUnitedMedia("Jeff Stahler","editoons/stahler","gif"); }
sub getEdStein { &getUnitedMedia("Ed Stein","editoons/stein","gif"); }
sub getPaulSzep { &getUnitedMedia("Paul Szep","editoons/szep","gif"); }
sub getGaryVarvel { &getUnitedMedia("Gary Varvel","editoons/varvel","gif"); }

#
# Disparate comics
#
# Dilbert has a slightly different archive, even though it's United Media, like above
sub getDilbert {
   &getItem("Dilbert",
      "http://www.unitedmedia.com/comics/dilbert/", 
      "src=.(\/comics\/dilbert\/archive\/images.*?gif)",
      "<center><p><a href=\"http://www.unitedmedia.com/comics/dilbert/archive\"><IMG SRC=\"http://www.unitedmedia.com",
      "\"></a></center><P>", 0);
}

sub getClayBennett {
   &getItem("Clay Bennett",
      "http://www.christiansciencemonitor.com/commentary/index.html",
      "today.s cartoon.*?img.src=.(\/.*?csmimg.cartoon.jpg)",
      "<center><p><IMG SRC=\"http://www.christiansciencemonitor.com",
      "\"><p></center>", 0);
}

sub getDorkTower {
   &getItem("Dork Tower",
      "http://www.gamespy.com/comics/dorktower/",
      "src=.(images\/comics\/DorkTower.*?jpg)",
      "<center><p><a href=\"http://www.gamespy.com/comics/dorktower/archive.asp?nextform=listdatecomic&id=7\"><IMG SRC=\"http://www.gamespy.com/comics/dorktower/",
      "\"></a><p></center>", 0);
}

sub getStoryMinute {
   &getItem("Story Minute",
      "http://www.waylay.com/Store/OrigPages/Originals.html",
      "src=\"(\.\.\/\.\.\/Images\/Strips\/.*?gif)",
      "<center><p><a href=\"http://www.buzzle.com/chapters/escape-hatch_cartoons-and-comics.asp\"><IMG SRC=\"http://www.waylay.com/Store/OrigPages/",
      "\"></a><p></center>", 0);
}

sub getDTWOF {
   &getItem("Dykes To Watch Out For",
      "http://www.planetout.com/entertainment/comics/splash.html",
      "c:\/entertainment\/comics\/dtwof\/archive\/(.*?)html",
      "<center><p><a href=\"http://www.planetout.com/pno/entertainment/comics/splash.html\"><IMG SRC=\"http://www.planetout.com/images/newsplanet/comics/new_size/dtwof/",
      "gif\"></a><p></center>", 0);
}

# Doesn't work: the php grab comes from off-site, so they send a "no image available" GIF instead. Clever.
sub getBizarro {
#   &getItem("Bizarro",
#      "http://www.kingfeatures.com/features/comics/bizarro/aboutMaina.php",
#      "(date=.*?)'",
#      "<center><p><IMG SRC=\"http://est.rbma.com/content/Bizarro\?",
#      "\"><p></center>", 0);
    printf WEBFILE "<table cellpadding=2 cellspacing=0 border=0 width=\"100%\">\n";
    printf WEBFILE "<tr valign=middle><td width=50";
    printf WEBFILE '%'; # silly - is there a better way to print a percentage sign?
    printf WEBFILE " bgcolor=#CCCCCC>\n";
    printf WEBFILE "<b><font size=+2>Bizarro</font></b></td><tr></table>\n";
    printf WEBFILE "<center><p>Sorry, you've got to click <a href=\"http://www.kingfeatures.com/features/comics/bizarro/aboutMaina.php\">this link</a>.<p></center>\n";
}

sub getThisModernWorld {
   my $urlstring;
   $urlstring = &getStringFromPage("http://www.workingforchange.com/column_lst.cfm?AuthrId=43",
      "itemid=(\\d+)\"");
#     better, but can't quite quote it right: "article.cfm?itemid=(.*?)\&");
   &getItem("This Modern World",
      "http://www.workingforchange.com/article.cfm?itemid=" . $urlstring,
      "(http:\/\/workingforchange.speedera.net\/www.workingforchange.com\/webgraphics\/wfc\/TMW.*?gif)\"",
      "<center><p><a href=\"http://www.workingforchange.com/column_lst.cfm?AuthrId=43\"><IMG SRC=\"",
      "\"></a><p></center>", 0);
}

sub getTroubletown {
   &getItem("Troubletown",
      "http://www.troubletown.com/cartoons/index.html",
      "SRC=\"(cartoons/ttown.*?gif)",
      "<center><p><a href=\"http://www.troubletown.com/cartoons/index.html\"><IMG SRC=\"http://www.troubletown.com/cartoons/",
      "\"></a><p></center>", 0);
}

sub getTheKChronicles {
   my $grabbit;
   $grabbit = &getStringFromPage("http://www.buzzle.com/chapters/escape-hatch_cartoons-and-comics.asp",
        "a href=\"..(/editorials/.*?asp)\">the K Chronicles");
   &getItem("The K Chronicles",
      "http://www.buzzle.com" . $grabbit,
      "\.\.(/pix/articleImages/.*?jpg)",
      "<center><p><a href=\"http://www.buzzle.com/chapters/escape-hatch_cartoons-and-comics.asp\"><IMG SRC=\"http://www.buzzle.com",
      "\"></a><p></center>", 0);
}

sub getNodwick {
   &getItem("Nodwick",
      "http://www.gamespy.com/comics/nodwick/gamespyarchive/newnodwick.html",
      "src=.(Nodwick1.*?jpg)",
      "<center><p><a href=\"http://www.gamespy.com/comics/nodwick/\"><IMG SRC=\"http://www.gamespy.com/comics/nodwick/gamespyarchive/",
      "\"></a><p></center>", 0);
}

# this is an easy special case - just point to the URL
sub getKirkAnderson {
   &makeBanner("Kirk Anderson");
   print WEBFILE "<p><center>\n";
   print WEBFILE "<img src=\"http://cagle.slate.msn.com/comics/updating/kirk.jpg\">\n";
   print WEBFILE "</center><p>\n";
}

# The talk shows are all slightly different and idiosyncratic

sub getCharlieRose {
   &getItem("Charlie Rose", 
   "http://www.charlierose.com/index.shtm",
   "producers.*(<table.*?Email your questions.*?\/table>)", "", "", 1);
}

sub getJonStewart {
   &getItem("Jon Stewart", 
   "http://www.comedycentral.com/tv_shows/thedailyshowwithjonstewart/",
   "TONIGHT:(.*?)<", "<p>", "<p>", 1);
}

sub getJayLeno {
   &getItem("Jay Leno", 
   "http://www.nbc.com/nbc/The_Tonight_Show_with_Jay_Leno/",
   "whitebold..(.*?)..span", "<p>", "<p>", 1);
}

sub getDavidLetterman {
   &getItem("David Letterman", 
   "http://www.cbs.com/latenight/lateshow/",
   "Tonight.s Guests.*?:<\/b>(.*?)<br>", "<p>", "<p>", 1);
}

sub getConanOBrien {
   &getItem("Conan O\'Brien", 
   "http://www.nbc.com/Late_Night_with_Conan_O'Brien/index.html",
   "Tonight Conan welcomes (.*?)<b>", "<p>", "<p>", 1);
}

sub getCraigKilborn {
   &getItem("Craig Kilborn", 
   "http://www.cbs.com/latenight/latelate/",
   "<font class=.guest.>(.*?)<", "<p>", "<p>", 1);
}

###########################################
### Subroutines
###########################################

# 
# The basic routine that drives the others.
# Open up the web file, fill it with content, and close it up
#
sub makeWebPage {
   ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime();
   $dayname = ("Monday", "Tuesday", "Wednesday", "Thursday", 
      "Friday", "Saturday", "Sunday")[$wday-1];
   $monthName = ("January", "February", "March", "April", "May", "June", "July",
      "August", "September", "October", "November", "December")[$mon];
   $fullYear = $year+1900;
   open (WEBFILE, ">$webFile") || die "Error opening web htm file $webFile\n";
   print WEBFILE "<html>\n<head>\n<!-- my custom file -->\n";
   print WEBFILE "<title>$myName\'s Custom Webpage</title>\n</head>\n";
   print WEBFILE "<body bgcolor=#EEEEEE>\n";
   print WEBFILE "<center><h1>$myName\'s Custom Webpage</h1></center>\n";
   print WEBFILE "<center><h2>$dayname, $monthName $mday, $fullYear</h2></center>\n";

   &makeUserAgent;
   &getWebContent;
   &makeBanner(" ");

   print WEBFILE "</body>\n<\html>\n";
   close WEBFILE;
}
	
#
# Create the user agent so we can fetch web pages
#
sub makeUserAgent {
   $ua = LWP::UserAgent->new;
}

#
# Make a horizontal banner to identify the content.
# Parameters: bannerTitle....the string to go in the banner
#
sub makeBanner {
   ($bannerTitle) = @_;
   print WEBFILE "<table cellpadding=2 cellspacing=0 border=0 width=\"100%\">\n";
   print WEBFILE "<tr valign=middle><td width=50% bgcolor=#CCCCCC>\n";
   print WEBFILE "<b><font size=+2>$bannerTitle</font></b></td><tr></table>\n";
   }

#
# A little convenience proc for those comics provided by United Comics
# Parameters:
#    name.......The name of the cartoonist
#    dir........The UC directory for that person's webpage
#    inits......The cartoonist's initials used by UC to find the image
#
sub getUnitedComic {
   ($name, $dir, $inits) = @_;
   $reqURL = "http://www.ucomics.com/$dir/index.phtml";
   $pattern = "img src=.(http:..images.ucomics.com.comics.$inits.*?gif)";
   &getItem($name, $reqURL, $pattern, "<center><p><a href=\"http://www.ucomics.com/$dir/index.phtml\"><IMG SRC=\"", "\"></a><p></center>", 0);
}

# united media has lots, too
sub getUnitedMedia {
   ($name, $dir, $ext) = @_;
   &getItem($name,
      "http://www.unitedmedia.com/".$dir."/", 
      "src=.(/".$dir."\/archive\/images.*?".$ext.")",
      "<center><p><a href=\"http://www.unitedmedia.com/"
        .$dir.
        "\"><IMG SRC=\"http://www.unitedmedia.com",
      "\"></a></center><P>", 0);
}
###########################################
#
# Subroutine getItem is the heart of the program.  It goes off 
# and fetches a web page, extracts the pattern match, removes
# links, optionally removes embedded images, and then writes
# the extracted pattern out to the custom web page with the
# given prefix and suffix.
#
# Try to avoid using explicit double quotes in the pattern.
# Use . in their place instead - it's less confusing.
#
# parameters:
#  title..........The string that appears in the banner on the web page
#  reqURL.........The URL with the content we want to extract
#  pattern........Specifies which content to extract.  This is a perl
#                    regular expression.  It will be interpreted in a
#                    case-insensitive way.  The actual content to be
#                    placed on the web page should be enclosed in round
#                    parentheses, e.g. "stuff(get this)stuff".  Note as
#                    above that you should avoid using double-quotes in
#                    this string, because they're confusing while trying
#                    to debug the pattern.
#  prefix.........This gets placed in front of the material found by the
#                    pattern when it's written to the web page.
#  suffix.........This comes after the matched material.
#  removeImages...Set this to 1 for text-only extractions, like talk
#                    shows and TV listings.  Set to 0 when you want to
#                    retain pictures, like comics.
#
###########################################

sub getItem {
   # unpack the procedure arguments
   ($title, $reqURL, $pattern, $prefix, $suffix, $removeImages) = @_;

   # get the contents of the web page named by the URL
   my $insstring;
   $insstring = &getStringFromPage( $reqURL, $pattern );
   if ($insstring ne "") {
         $bannerTitle = $title; 
         &makeBanner;
         print WEBFILE "$prefix$insstring$suffix\n";
    }
}

#
# A generally handy subroutine: pulls in a web page, searches for a string,
# returns the matched string if found, else returns nothing and warns the user.
#
sub getStringFromPage {
   # unpack the procedure arguments
   ($reqURL, $pattern) = @_;

   my $srcline;
   my $grabbedString;
   $grabbedString = "";

   # get the contents of the web page named by the URL
   $request = HTTP::Request->new(GET => $reqURL);
   $answer = $ua->request($request);
   if ($answer->is_success) {
      $plaintext = $answer->as_string;
      $nobreak = $plaintext;    
      $nobreak=~s/\n/ /g;       # remove newlines
      $nobreak=~s/\r/ /g;       # remove carriage returns
      $nobreak=~/$pattern/i;    # now match the pattern
      $srcline = $1;            # srcline holds what was in the parens

      # remove any hrefs (the refs might be local to the site)
      $srcline=~s/<a.*?a>//ig;
      if ($removeImages != 0) {
         $srcline=~s/<img.*?>//ig;
      }
      $srcline=~s/ +/ /g;    # reduce big chunks of blanks to singles

      if ($srcline ne "") {
          $grabbedString = $srcline;
      } else {
          printf "ERROR: no pattern \"$pattern\" found in $reqURL\n";
      }
   }
   return $grabbedString;
}