Random GoComics.com?

[ppriede]

Hi,
first thing first.
I use Calibre everyday, so, thank you very much to the developer.

Well, now a simple question..

How can i create a random GoComics.com Recipe?

I try to modify and the existing Recipe, but i don't really know that much of Python and maybe that's the only problem.


Here is the Recipe

#!/usr/bin/env  python

__license__   = 'GPL v3'
__copyright__ = 'Copyright 2010 Starson17'
'''
www.gocomics.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
import mechanize, re, random

class GoComics(BasicNewsRecipe):
    title               = 'GoComics L v2+azar'
    __author__          = 'Starson17'
    __version__         = '1.06'
    __date__            = '07 June 2011'
    description         = u'200+ Comics - Customize for more days/comics: Defaults to 7 days, 25 comics - 20 general, 5 editorial.'
    category            = 'news, comics'
    language            = 'en'
    use_embedded_content= False
    no_stylesheets      = True
    remove_javascript   = True
    cover_url           = 'http://paulbuckley14059.files.wordpress.com/2008/06/calvin-and-hobbes.jpg'
    remove_attributes = ['style']

    ####### USER PREFERENCES - COMICS, IMAGE SIZE AND NUMBER OF COMICS TO RETRIEVE ########
    # num_comics_to_get - I've tried up to 99 on Calvin&Hobbes
    num_comics_to_get = 1
    # comic_size 300 is small, 600 is medium, 900 is large, 1500 is extra-large
    comic_size = 900
    # CHOOSE COMIC STRIPS BELOW - REMOVE COMMENT '# ' FROM IN FRONT OF DESIRED STRIPS
    # Please do not overload their servers by selecting all comics and 1000 strips from each!

    conversion_options = {'linearize_tables'  : True
                        , 'comment'           : description
                        , 'tags'              : category
                        , 'language'          : language
                        }

    keep_only_tags     = [dict(name='div', attrs={'class':['feature','banner']}),
                          ]

    remove_tags = [dict(name='a', attrs={'class':['beginning','prev','cal','next','newest']}),
                   dict(name='div', attrs={'class':['tag-wrapper']}),
                   dict(name='a', attrs={'href':re.compile(r'.*mutable_[0-9]+', re.IGNORECASE)}),
                   dict(name='img', attrs={'src':re.compile(r'.*mutable_[0-9]+', re.IGNORECASE)}),
                   dict(name='ul', attrs={'class':['share-nav','feature-nav']}),
                   ]

    def get_browser(self):
        br = BasicNewsRecipe.get_browser(self)
        cookies = mechanize.CookieJar()
        br = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
        br.addheaders = [('Referer','http://www.gocomics.com/')]
        return br

    def parse_index(self):
        feedis =  [
                       #(u"2 Cows and a Chicken", u"http://www.gocomics.com/2cowsandachicken"),
                       (u"9 Chickweed Lane", u"http://www.gocomics.com/9chickweedlane"),
                       (u"9 to 5", u"http://www.gocomics.com/9to5"),
                       (u"Adam At Home", u"http://www.gocomics.com/adamathome"),
                       (u"Agnes", u"http://www.gocomics.com/agnes"),
                       (u"Alley Oop", u"http://www.gocomics.com/alleyoop"),
                       (u"Andy Capp", u"http://www.gocomics.com/andycapp"),
                       (u"Animal Crackers", u"http://www.gocomics.com/animalcrackers"),
                       (u"Annie", u"http://www.gocomics.com/annie"),
                       (u"Arlo & Janis", u"http://www.gocomics.com/arloandjanis"),
                       (u"Ask Shagg", u"http://www.gocomics.com/askshagg"),

                       (u"Back in the Day", u"http://www.gocomics.com/backintheday"),
                       (u"Bad Reporter", u"http://www.gocomics.com/badreporter"),
                       (u"Baldo", u"http://www.gocomics.com/baldo"),
                       (u"Ballard Street", u"http://www.gocomics.com/ballardstreet"),
                       (u"Barkeater Lake", u"http://www.gocomics.com/barkeaterlake"),
                       (u"Basic Instructions", u"http://www.gocomics.com/basicinstructions"),
                       (u"Ben", u"http://www.gocomics.com/ben"),
                       (u"Betty", u"http://www.gocomics.com/betty"),
                       (u"Bewley", u"http://www.gocomics.com/bewley"),
                       (u"Big Nate", u"http://www.gocomics.com/bignate"),
                       (u"Big Top", u"http://www.gocomics.com/bigtop"),
                       (u"Biographic", u"http://www.gocomics.com/biographic"),
                       (u"Birdbrains", u"http://www.gocomics.com/birdbrains"),
                       (u"Bleeker: The Rechargeable Dog", u"http://www.gocomics.com/bleeker"),
                       (u"Bliss", u"http://www.gocomics.com/bliss"),
                       (u"Bloom County", u"http://www.gocomics.com/bloomcounty"),
                       (u"Bo Nanas", u"http://www.gocomics.com/bonanas"),
                       (u"Bob the Squirrel", u"http://www.gocomics.com/bobthesquirrel"),
                       (u"Boomerangs", u"http://www.gocomics.com/boomerangs"),
                       (u"Bottomliners", u"http://www.gocomics.com/bottomliners"),
                       (u"Bound and Gagged", u"http://www.gocomics.com/boundandgagged"),
                       (u"Brainwaves", u"http://www.gocomics.com/brainwaves"),
                       (u"Brenda Starr", u"http://www.gocomics.com/brendastarr"),
                       (u"Brevity", u"http://www.gocomics.com/brevity"),
                       (u"Brewster Rockit", u"http://www.gocomics.com/brewsterrockit"),
                       (u"Broom Hilda", u"http://www.gocomics.com/broomhilda"),

                       (u"Candorville", u"http://www.gocomics.com/candorville"),
                       (u"Cathy", u"http://www.gocomics.com/cathy"),
                       (u"C'est la Vie", u"http://www.gocomics.com/cestlavie"),
                       (u"Cheap Thrills", u"http://www.gocomics.com/cheapthrills"),
                       (u"Chuckle Bros", u"http://www.gocomics.com/chucklebros"),
                       (u"Citizen Dog", u"http://www.gocomics.com/citizendog"),
                       (u"Cleats", u"http://www.gocomics.com/cleats"),
                       (u"Close to Home", u"http://www.gocomics.com/closetohome"),
                       (u"Committed", u"http://www.gocomics.com/committed"),
                       (u"Compu-toon", u"http://www.gocomics.com/compu-toon"),
                       (u"Cornered", u"http://www.gocomics.com/cornered"),
                       (u"Cow & Boy", u"http://www.gocomics.com/cow&boy"),
                       (u"Cul de Sac", u"http://www.gocomics.com/culdesac"),
                       (u"Daddy's Home", u"http://www.gocomics.com/daddyshome"),
                       (u"Deep Cover", u"http://www.gocomics.com/deepcover"),
                       (u"Dick Tracy", u"http://www.gocomics.com/dicktracy"),
                       (u"Dog Eat Doug", u"http://www.gocomics.com/dogeatdoug"),
                       (u"Domestic Abuse", u"http://www.gocomics.com/domesticabuse"),

                       (u"Doonesbury", u"http://www.gocomics.com/doonesbury"),
                       (u"Drabble", u"http://www.gocomics.com/drabble"),
                       (u"Eek!", u"http://www.gocomics.com/eek"),
                       (u"F Minus", u"http://www.gocomics.com/fminus"),
                       (u"Family Tree", u"http://www.gocomics.com/familytree"),
                       (u"Farcus", u"http://www.gocomics.com/farcus"),
                       (u"Fat Cats Classics", u"http://www.gocomics.com/fatcatsclassics"),
                       (u"Ferd'nand", u"http://www.gocomics.com/ferdnand"),
                       (u"Flight Deck", u"http://www.gocomics.com/flightdeck"),
                       (u"Flo and Friends", u"http://www.gocomics.com/floandfriends"),
                       (u"For Better or For Worse", u"http://www.gocomics.com/forbetterorforworse"),
                       (u"For Heaven's Sake", u"http://www.gocomics.com/forheavenssake"),
                       (u"Fort Knox", u"http://www.gocomics.com/fortknox"),
                       (u"FoxTrot Classics", u"http://www.gocomics.com/foxtrotclassics"),
                       (u"FoxTrot", u"http://www.gocomics.com/foxtrot"),
                       (u"Frank & Ernest", u"http://www.gocomics.com/frankandernest"),
                       (u"Frazz", u"http://www.gocomics.com/frazz"),
                       (u"Fred Basset", u"http://www.gocomics.com/fredbasset"),
                       (u"Free Range", u"http://www.gocomics.com/freerange"),
                       (u"Frog Applause", u"http://www.gocomics.com/frogapplause"),


                       (u"Gasoline Alley", u"http://www.gocomics.com/gasolinealley"),
                       (u"Geech Classics", u"http://www.gocomics.com/geechclassics"),

                       (u"Gil Thorp", u"http://www.gocomics.com/gilthorp"),
                       (u"Ginger Meggs", u"http://www.gocomics.com/gingermeggs"),
                       (u"Girls & Sports", u"http://www.gocomics.com/girlsandsports"),
                       (u"Graffiti", u"http://www.gocomics.com/graffiti"),
                       (u"Grand Avenue", u"http://www.gocomics.com/grandavenue"),
                       (u"Haiku Ewe", u"http://www.gocomics.com/haikuewe"),
                       (u"Heart of the City", u"http://www.gocomics.com/heartofthecity"),
                       (u"Heathcliff", u"http://www.gocomics.com/heathcliff"),
                       (u"Herb and Jamaal", u"http://www.gocomics.com/herbandjamaal"),
                       (u"Herman", u"http://www.gocomics.com/herman"),
                       (u"Home and Away", u"http://www.gocomics.com/homeandaway"),
                       (u"Housebroken", u"http://www.gocomics.com/housebroken"),
                       (u"Hubert and Abby", u"http://www.gocomics.com/hubertandabby"),
                       (u"Imagine This", u"http://www.gocomics.com/imaginethis"),
                       (u"In the Bleachers", u"http://www.gocomics.com/inthebleachers"),
                       (u"In the Sticks", u"http://www.gocomics.com/inthesticks"),
                       (u"Ink Pen", u"http://www.gocomics.com/inkpen"),
                       (u"It's All About You", u"http://www.gocomics.com/itsallaboutyou"),
                       (u"Jane's World", u"http://www.gocomics.com/janesworld"),
                       (u"Joe Vanilla", u"http://www.gocomics.com/joevanilla"),
                       (u"Jump Start", u"http://www.gocomics.com/jumpstart"),
                       (u"Kit 'N' Carlyle", u"http://www.gocomics.com/kitandcarlyle"),
                       (u"La Cucaracha", u"http://www.gocomics.com/lacucaracha"),
                       (u"Last Kiss", u"http://www.gocomics.com/lastkiss"),
                       (u"Legend of Bill", u"http://www.gocomics.com/legendofbill"),
                       (u"Liberty Meadows", u"http://www.gocomics.com/libertymeadows"),
                       (u"Li'l Abner Classics", u"http://www.gocomics.com/lilabnerclassics"),
                       (u"Lio", u"http://www.gocomics.com/lio"),
                       (u"Little Dog Lost", u"http://www.gocomics.com/littledoglost"),
                       (u"Little Otto", u"http://www.gocomics.com/littleotto"),
                       (u"Lola", u"http://www.gocomics.com/lola"),
                       (u"Loose Parts", u"http://www.gocomics.com/looseparts"),
                       (u"Love Is...", u"http://www.gocomics.com/loveis"),
                       (u"Luann", u"http://www.gocomics.com/luann"),
                       (u"Maintaining", u"http://www.gocomics.com/maintaining"),
                       (u"Marmaduke", u"http://www.gocomics.com/marmaduke"),
                       (u"Meg! Classics", u"http://www.gocomics.com/megclassics"),
                       (u"Middle-Aged White Guy", u"http://www.gocomics.com/middleagedwhiteguy"),
                       (u"Minimum Security", u"http://www.gocomics.com/minimumsecurity"),
                       (u"Moderately Confused", u"http://www.gocomics.com/moderatelyconfused"),
                       (u"Momma", u"http://www.gocomics.com/momma"),
                       (u"Monty", u"http://www.gocomics.com/monty"),
                       (u"Motley Classics", u"http://www.gocomics.com/motleyclassics"),
                       (u"Mutt & Jeff", u"http://www.gocomics.com/muttandjeff"),
                       (u"Mythtickle", u"http://www.gocomics.com/mythtickle"),
                       (u"Nancy", u"http://www.gocomics.com/nancy"),
                       (u"Natural Selection", u"http://www.gocomics.com/naturalselection"),
                       (u"Nest Heads", u"http://www.gocomics.com/nestheads"),
                       (u"NEUROTICA", u"http://www.gocomics.com/neurotica"),
                       (u"New Adventures of Queen Victoria", u"http://www.gocomics.com/thenewadventuresofqueenvictoria"),
                       (u"Non Sequitur", u"http://www.gocomics.com/nonsequitur"),
                       (u"Off The Mark", u"http://www.gocomics.com/offthemark"),
                       (u"On A Claire Day", u"http://www.gocomics.com/onaclaireday"),
                       (u"One Big Happy Classics", u"http://www.gocomics.com/onebighappyclassics"),
                       (u"One Big Happy", u"http://www.gocomics.com/onebighappy"),
                       (u"Out of the Gene Pool Re-Runs", u"http://www.gocomics.com/outofthegenepool"),
                       (u"Over the Hedge", u"http://www.gocomics.com/overthehedge"),
                       (u"Overboard", u"http://www.gocomics.com/overboard"),
                       (u"PC and Pixel", u"http://www.gocomics.com/pcandpixel"),
                       (u"Peanuts", u"http://www.gocomics.com/peanuts"),
                       (u"Pearls Before Swine", u"http://www.gocomics.com/pearlsbeforeswine"),
                       (u"Pibgorn Sketches", u"http://www.gocomics.com/pibgornsketches"),

                       (u"Pickles", u"http://www.gocomics.com/pickles"),
                       (u"Pinkerton", u"http://www.gocomics.com/pinkerton"),
                       (u"Pluggers", u"http://www.gocomics.com/pluggers"),
                       (u"Pooch Cafe", u"http://www.gocomics.com/poochcafe"),
                       (u"PreTeena", u"http://www.gocomics.com/preteena"),
                       (u"Prickly City", u"http://www.gocomics.com/pricklycity"),
                       (u"Rabbits Against Magic", u"http://www.gocomics.com/rabbitsagainstmagic"),
                       (u"Raising Duncan Classics", u"http://www.gocomics.com/raisingduncanclassics"),
                       (u"Real Life Adventures", u"http://www.gocomics.com/reallifeadventures"),
                       (u"Reality Check", u"http://www.gocomics.com/realitycheck"),
                       (u"Red and Rover", u"http://www.gocomics.com/redandrover"),
                       (u"Red Meat", u"http://www.gocomics.com/redmeat"),
                       (u"Reynolds Unwrapped", u"http://www.gocomics.com/reynoldsunwrapped"),
                       (u"Rip Haywire", u"http://www.gocomics.com/riphaywire"),
                       (u"Ripley's Believe It or Not!", u"http://www.gocomics.com/ripleysbelieveitornot"),
                       (u"Ronaldinho Gaucho", u"http://www.gocomics.com/ronaldinhogaucho"),
                       (u"Rose Is Rose", u"http://www.gocomics.com/roseisrose"),
                       (u"Rubes", u"http://www.gocomics.com/rubes"),
                       (u"Rudy Park", u"http://www.gocomics.com/rudypark"),
                       (u"Scary Gary", u"http://www.gocomics.com/scarygary"),
                       (u"Shirley and Son Classics", u"http://www.gocomics.com/shirleyandsonclassics"),
                       (u"Shoe", u"http://www.gocomics.com/shoe"),
                       (u"Shoecabbage", u"http://www.gocomics.com/shoecabbage"),
                       (u"Skin Horse", u"http://www.gocomics.com/skinhorse"),
                       (u"Slowpoke", u"http://www.gocomics.com/slowpoke"),
                       (u"Soup To Nutz", u"http://www.gocomics.com/souptonutz"),
                       (u"Speed Bump", u"http://www.gocomics.com/speedbump"),
                       (u"Spot The Frog", u"http://www.gocomics.com/spotthefrog"),
                       (u"State of the Union", u"http://www.gocomics.com/stateoftheunion"),
                       (u"Stone Soup", u"http://www.gocomics.com/stonesoup"),
                       (u"Strange Brew", u"http://www.gocomics.com/strangebrew"),
                       (u"Sylvia", u"http://www.gocomics.com/sylvia"),
                       (u"Tank McNamara", u"http://www.gocomics.com/tankmcnamara"),
                       (u"Tarzan Classics", u"http://www.gocomics.com/tarzanclassics"),
                       (u"That's Life", u"http://www.gocomics.com/thatslife"),
                       (u"The Academia Waltz", u"http://www.gocomics.com/academiawaltz"),
                       (u"The Argyle Sweater", u"http://www.gocomics.com/theargylesweater"),
                       (u"The Barn", u"http://www.gocomics.com/thebarn"),
                       (u"The Boiling Point", u"http://www.gocomics.com/theboilingpoint"),
                       (u"The Boondocks", u"http://www.gocomics.com/boondocks"),
                       (u"The Born Loser", u"http://www.gocomics.com/thebornloser"),
                       (u"The Buckets", u"http://www.gocomics.com/thebuckets"),
                       (u"The City", u"http://www.gocomics.com/thecity"),
                       (u"The Dinette Set", u"http://www.gocomics.com/dinetteset"),
                       (u"The Doozies", u"http://www.gocomics.com/thedoozies"),
                       (u"The Duplex", u"http://www.gocomics.com/duplex"),
                       (u"The Elderberries", u"http://www.gocomics.com/theelderberries"),
                       (u"The Flying McCoys", u"http://www.gocomics.com/theflyingmccoys"),
                       (u"The Fusco Brothers", u"http://www.gocomics.com/thefuscobrothers"),
                       (u"The Grizzwells", u"http://www.gocomics.com/thegrizzwells"),
                       (u"The Humble Stumble", u"http://www.gocomics.com/thehumblestumble"),
                       (u"The Knight Life", u"http://www.gocomics.com/theknightlife"),
                       (u"The Meaning of Lila", u"http://www.gocomics.com/meaningoflila"),
                       (u"The Middletons", u"http://www.gocomics.com/themiddletons"),
                       (u"The Norm", u"http://www.gocomics.com/thenorm"),
                       (u"The Other Coast", u"http://www.gocomics.com/theothercoast"),
                       (u"The Quigmans", u"http://www.gocomics.com/thequigmans"),
                       (u"The Sunshine Club", u"http://www.gocomics.com/thesunshineclub"),
                       (u"Tiny Sepuk", u"http://www.gocomics.com/tinysepuk"),
                       (u"TOBY", u"http://www.gocomics.com/toby"),
                       (u"Tom the Dancing Bug", u"http://www.gocomics.com/tomthedancingbug"),
                       (u"Too Much Coffee Man", u"http://www.gocomics.com/toomuchcoffeeman"),
                       (u"Unstrange Phenomena", u"http://www.gocomics.com/unstrangephenomena"),
                       (u"W.T. Duck", u"http://www.gocomics.com/wtduck"),
                       (u"Watch Your Head", u"http://www.gocomics.com/watchyourhead"),
                       (u"Wee Pals", u"http://www.gocomics.com/weepals"),
                       (u"Winnie the Pooh", u"http://www.gocomics.com/winniethepooh"),
                       (u"Wizard of Id", u"http://www.gocomics.com/wizardofid"),
                       (u"Working Daze", u"http://www.gocomics.com/workingdaze"),
                       (u"Working It Out", u"http://www.gocomics.com/workingitout"),
                       (u"Yenny", u"http://www.gocomics.com/yenny"),
                       (u"Zack Hill", u"http://www.gocomics.com/zackhill"),
                       (u"Ziggy", u"http://www.gocomics.com/ziggy"),
                       #
                       ######## EDITORIAL CARTOONS #####################
                       (u"Adam Zyglis", u"http://www.gocomics.com/adamzyglis"),
                       (u"Andy Singer", u"http://www.gocomics.com/andysinger"),
                       (u"Ben Sargent",u"http://www.gocomics.com/bensargent"),
                       (u"Bill Day", u"http://www.gocomics.com/billday"),
                       (u"Bill Schorr", u"http://www.gocomics.com/billschorr"),
                       (u"Bob Englehart", u"http://www.gocomics.com/bobenglehart"),
                       (u"Bob Gorrell",u"http://www.gocomics.com/bobgorrell"),
                       (u"Brian Fairrington", u"http://www.gocomics.com/brianfairrington"),
                       (u"Bruce Beattie", u"http://www.gocomics.com/brucebeattie"),
                       (u"Cam Cardow", u"http://www.gocomics.com/camcardow"),
                       (u"Chan Lowe",u"http://www.gocomics.com/chanlowe"),
                       (u"Chip Bok",u"http://www.gocomics.com/chipbok"),
                       (u"Chris Britt",u"http://www.gocomics.com/chrisbritt"),
                       (u"Chuck Asay",u"http://www.gocomics.com/chuckasay"),
                       (u"Clay Bennett",u"http://www.gocomics.com/claybennett"),
                       (u"Clay Jones",u"http://www.gocomics.com/clayjones"),
                       (u"Dan Wasserman",u"http://www.gocomics.com/danwasserman"),
                       (u"Dana Summers",u"http://www.gocomics.com/danasummers"),
                       (u"Daryl Cagle", u"http://www.gocomics.com/darylcagle"),
                       (u"David Fitzsimmons", u"http://www.gocomics.com/davidfitzsimmons"),
                       (u"Dick Locher",u"http://www.gocomics.com/dicklocher"),
                       (u"Don Wright",u"http://www.gocomics.com/donwright"),
                       (u"Donna Barstow",u"http://www.gocomics.com/donnabarstow"),
                       (u"Drew Litton", u"http://www.gocomics.com/drewlitton"),
                       (u"Drew Sheneman",u"http://www.gocomics.com/drewsheneman"),
                       (u"Ed Stein", u"http://www.gocomics.com/edstein"),
                       (u"Eric Allie", u"http://www.gocomics.com/ericallie"),
                       (u"Gary Markstein", u"http://www.gocomics.com/garymarkstein"),
                       (u"Gary McCoy", u"http://www.gocomics.com/garymccoy"),
                       (u"Gary Varvel", u"http://www.gocomics.com/garyvarvel"),
                       (u"Glenn McCoy",u"http://www.gocomics.com/glennmccoy"),
                       (u"Henry Payne", u"http://www.gocomics.com/henrypayne"),
                       (u"Jack Ohman",u"http://www.gocomics.com/jackohman"),
                       (u"JD Crowe", u"http://www.gocomics.com/jdcrowe"),
                       (u"Jeff Danziger",u"http://www.gocomics.com/jeffdanziger"),
                       (u"Jeff Parker", u"http://www.gocomics.com/jeffparker"),
                       (u"Jeff Stahler", u"http://www.gocomics.com/jeffstahler"),
                       (u"Jerry Holbert", u"http://www.gocomics.com/jerryholbert"),
                       (u"Jim Morin",u"http://www.gocomics.com/jimmorin"),
                       (u"Joel Pett",u"http://www.gocomics.com/joelpett"),
                       (u"John Cole", u"http://www.gocomics.com/johncole"),
                       (u"John Darkow", u"http://www.gocomics.com/johndarkow"),
                       (u"John Deering",u"http://www.gocomics.com/johndeering"),
                       (u"John Sherffius", u"http://www.gocomics.com/johnsherffius"),
                       (u"Ken Catalino",u"http://www.gocomics.com/kencatalino"),
                       (u"Kerry Waghorn",u"http://www.gocomics.com/facesinthenews"),
                       (u"Kevin Kallaugher",u"http://www.gocomics.com/kevinkallaugher"),
                       (u"Lalo Alcaraz",u"http://www.gocomics.com/laloalcaraz"),
                       (u"Larry Wright", u"http://www.gocomics.com/larrywright"),
                       (u"Lisa Benson", u"http://www.gocomics.com/lisabenson"),
                       (u"Marshall Ramsey", u"http://www.gocomics.com/marshallramsey"),
                       (u"Matt Bors", u"http://www.gocomics.com/mattbors"),
                       (u"Matt Davies",u"http://www.gocomics.com/mattdavies"),
                       (u"Michael Ramirez", u"http://www.gocomics.com/michaelramirez"),
                       (u"Mike Keefe", u"http://www.gocomics.com/mikekeefe"),
                       (u"Mike Luckovich", u"http://www.gocomics.com/mikeluckovich"),
                       (u"MIke Thompson", u"http://www.gocomics.com/mikethompson"),
                       (u"Monte Wolverton", u"http://www.gocomics.com/montewolverton"),
                       (u"Mr. Fish", u"http://www.gocomics.com/mrfish"),
                       (u"Nate Beeler", u"http://www.gocomics.com/natebeeler"),
                       (u"Nick Anderson", u"http://www.gocomics.com/nickanderson"),
                       (u"Pat Bagley", u"http://www.gocomics.com/patbagley"),
                       (u"Pat Oliphant",u"http://www.gocomics.com/patoliphant"),
                       (u"Paul Conrad",u"http://www.gocomics.com/paulconrad"),
                       (u"Paul Szep", u"http://www.gocomics.com/paulszep"),
                       (u"RJ Matson", u"http://www.gocomics.com/rjmatson"),
                       (u"Rob Rogers", u"http://www.gocomics.com/robrogers"),
                       (u"Robert Ariail", u"http://www.gocomics.com/robertariail"),
                       (u"Scott Stantis", u"http://www.gocomics.com/scottstantis"),
                       (u"Signe Wilkinson", u"http://www.gocomics.com/signewilkinson"),
                       (u"Small World",u"http://www.gocomics.com/smallworld"),
                       (u"Steve Benson", u"http://www.gocomics.com/stevebenson"),
                       (u"Steve Breen", u"http://www.gocomics.com/stevebreen"),
                       (u"Steve Kelley", u"http://www.gocomics.com/stevekelley"),
                       (u"Steve Sack", u"http://www.gocomics.com/stevesack"),
                       (u"Stuart Carlson",u"http://www.gocomics.com/stuartcarlson"),
                       (u"Ted Rall",u"http://www.gocomics.com/tedrall"),
                       (u"(Th)ink", u"http://www.gocomics.com/think"),
                       (u"Tom Toles",u"http://www.gocomics.com/tomtoles"),
                       (u"Tony Auth",u"http://www.gocomics.com/tonyauth"),
                       (u"Views of the World",u"http://www.gocomics.com/viewsoftheworld"),
                       (u"ViewsAfrica",u"http://www.gocomics.com/viewsafrica"),
                       (u"ViewsAmerica",u"http://www.gocomics.com/viewsamerica"),
                       (u"ViewsAsia",u"http://www.gocomics.com/viewsasia"),
                       (u"ViewsBusiness",u"http://www.gocomics.com/viewsbusiness"),
                       (u"ViewsEurope",u"http://www.gocomics.com/viewseurope"),
                       (u"ViewsLatinAmerica",u"http://www.gocomics.com/viewslatinamerica"),
                       (u"ViewsMidEast",u"http://www.gocomics.com/viewsmideast"),
                       (u"Walt Handelsman",u"http://www.gocomics.com/walthandelsman"),
                       (u"Wayne Stayskal",u"http://www.gocomics.com/waynestayskal"),
                       (u"Wit of the World",u"http://www.gocomics.com/witoftheworld"),
                             ]

        random.shuffle(feedis)
        feeds = feedis[0:20]

        for title, url in feeds:
            print 'Working on: ', title
            articles = self.make_links(url)
            if articles:
                feeds.append((title, articles))
        return feeds

    def make_links(self, url):
        title = 'Temp'
        current_articles = []
        pages = range(1, self.num_comics_to_get+1)
        for page in pages:
            page_soup = self.index_to_soup(url)
            if page_soup:
                try:
                  strip_title = page_soup.find(name='div', attrs={'class':'top'}).h1.a.string
                except:
                  strip_title = 'Error - no Title found'
                try:
                  date_title = page_soup.find('ul', attrs={'class': 'feature-nav'}).li.string
                  if not date_title:
                      date_title = page_soup.find('ul', attrs={'class': 'feature-nav'}).li.string
                except:
                  date_title = 'Error - no Date found'
                title = strip_title + ' - ' + date_title
                for i in range(2):
                  try:
                    strip_url_date = page_soup.find(name='div', attrs={'class':'top'}).h1.a['href']
                    break #success - this is normal exit
                  except:
                    strip_url_date = None
                    continue #try to get strip_url_date again
                for i in range(2):
                  try:
                    prev_strip_url_date = page_soup.find('a', attrs={'class': 'prev'})['href']
                    break #success - this is normal exit
                  except:
                    prev_strip_url_date = None
                    continue #try to get prev_strip_url_date again
                if strip_url_date:
                  page_url = 'http://www.gocomics.com' + strip_url_date
                else:
                  continue
                if prev_strip_url_date:
                  prev_page_url = 'http://www.gocomics.com' + prev_strip_url_date
                else:
                  continue
            current_articles.append({'title': title, 'url': page_url, 'description':'', 'date':''})
            url = prev_page_url
        current_articles.reverse()
        return current_articles

    def preprocess_html(self, soup):
        if soup.title:
            title_string = soup.title.string.strip()
            _cd = title_string.split(',',1)[1]
            comic_date = ' '.join(_cd.split(' ', 4)[0:-1])
        if soup.h1.span:
            artist = soup.h1.span.string
            soup.h1.span.string.replaceWith(comic_date + artist)
        feature_item = soup.find('p',attrs={'class':'feature_item'})
        if feature_item.a:
            a_tag = feature_item.a
            a_href = a_tag["href"]
            img_tag = a_tag.img
            img_tag["src"] = a_href
            img_tag["width"] = self.comic_size
            img_tag["height"] = None
        return self.adeify_images(soup)

    extra_css = '''
                    h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
                    h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
                    img {max-width:100%; min-width:100%;}
                    p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
                    body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
		'''

So, I create an Array (feedis) with all the urls
Then excute a simple shuffle and chop it to 2 elements (for this test)

And this is part of the log...

InputFormatPlugin: Recipe Input running
Working on:  Chan Lowe

Working on:  Skin Horse

Working on:  Chan Lowe
Python function terminated unexpectedly
  expected string or buffer (Error Code: 1)
Traceback (most recent call last):
  File "site.py", line 132, in main
  File "site.py", line 109, in run_entry_point
  File "site-packages\calibre\utils\ipc\worker.py", line 187, in main
  File "site-packages\calibre\gui2\convert\gui_conversion.py", line 25, in gui_convert
  File "site-packages\calibre\ebooks\conversion\plumber.py", line 959, in run
  File "site-packages\calibre\customize\conversion.py", line 204, in __call__
  File "site-packages\calibre\web\feeds\input.py", line 105, in convert
  File "site-packages\calibre\web\feeds\news.py", line 824, in download
  File "site-packages\calibre\web\feeds\news.py", line 968, in build_index
  File "c:\users\-----\appdata\local\temp\calibre_0.8.27_tmp_8cn8y4\md5n3m_recipes\recipe0.py", line 380, in parse_index
    articles = self.make_links(url)
  File "c:\users\----\appdata\local\temp\calibre_0.8.27_tmp_8cn8y4\md5n3m_recipes\recipe0.py", line 390, in make_links
    page_soup = self.index_to_soup(url)
  File "site-packages\calibre\web\feeds\news.py", line 536, in index_to_soup
  File "re.py", line 137, in match
TypeError: expected string or buffer

I don't understand were to look (or to fix) in the last line.
I suspect that maybe some loop is missing (to properly check the array)

Any help would be great.
Thanks.

[NotTaken]

Probably not wise to modify the object you are iterating on, plus your feeds list would be badly formed as you are adding tuples of two different forms. I couldn't test but is it any better if you use this code fragment?

        random.shuffle(feedis)
        feedis = feedis[0:20]
        feeds = []
        
        for title, url in feedis:
            print 'Working on: ', title
            articles = self.make_links(url)
            if articles:
                feeds.append((title, articles))
        return feeds

[ppriede]

IT WORKS!
thank you very much NotTaken

Here is the Random GoComics.com Recipe ILTR20RCATEOTD Edition (AKA I Like To Read 20 Random Comics At The End Of The Day Edition)

[NotTaken]

Thanks for sharing. One thing I did notice is that a few of the urls aren't current and it ends up getting the comic on the front page. A couple that I noticed:

(u"Larry Wright", u"http://www.gocomics.com/larrywright"),
(u"Grand Avenue", u"http://www.gocomics.com/grandavenue"),

I believe Grand Avenue should be,

 (u"Grand Avenue", u"http://www.gocomics.com/grand-avenue")

If they change often it might be nice to parse a page of links to populate your feeds.

[ppriede]

Nice idea NotTaken

Well, now i found a simple way to get the URL from updated comics from GoComics.com

With Dapper
http://open.dapper.net/transform.php...com%2Ffeatures

or with Feed43.com (only loads 100KB of the HTML, but is something)
http://www.feed43.com/random_gocomics.xml

With Dapper, only show the updated comics and with Feed43 in the content is a "Status: " that show if is updated or not (updated or empty)


BUT!
Now, i'm really lost..

I know i have to download the RSS first, then shuffle it, and the chop it (to 20 elements for example), and then pass it to the GoComics Recipe to clean it..

I try to read the the tutorial on Recipes, but really don't find a good example to understand the way the fetching is done.

Is possible to shuffle a RSS an then pass it to the other functions of the GoComics Recipe? (make_links(self, url), preprocess_html(self, soup))

I think the parse_index(self) is no longer needed.. or it is?


any information would be appreciated
Thanks.

[NotTaken]

Could do something like this:

#!/usr/bin/env  python



__license__   = 'GPL v3'

__copyright__ = 'Copyright 2010 Starson17'

'''

www.gocomics.com

'''

from calibre.web.feeds.news import BasicNewsRecipe

import mechanize, re, random
from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag, NavigableString



class GoComicsRandom(BasicNewsRecipe):

    title               = 'Random GoComics.com'

    __author__          = 'ppriede - based on Starson17, with the help of NotTaken'

    __version__         = '1.07'

    __date__            = '29 November 2011'

    description         = u'200+ Comics - Customize for more days/comics: Defaults to 7 days, 25 comics - 20 general, 5 editorial.'

    category            = 'news, comics'

    language            = 'en'

    use_embedded_content= False

    no_stylesheets      = True

    remove_javascript   = True

    cover_url           = 'http://assets.gocomics.com/images/logo-uclick-gocomics-stacked.png'

    remove_attributes = ['style']
    



####### USER PREFERENCES - COMICS, IMAGE SIZE AND NUMBER OF COMICS TO RETRIEVE ########
    # num_comics_to_get - I've tried up to 99 on Calvin&Hobbes
    num_comics_to_get = 1
    # comic_size 300 is small, 600 is medium, 900 is large, 1500 is extra-large
    comic_size = 900
    # CHOOSE COMIC STRIPS BELOW - REMOVE COMMENT '# ' FROM IN FRONT OF DESIRED STRIPS
    # Please do not overload their servers by selecting all comics and 1000 strips from each!

    conversion_options = {'linearize_tables'  : True
                        , 'comment'           : description
                        , 'tags'              : category
                        , 'language'          : language
                        }

    keep_only_tags     = [dict(name='div', attrs={'class':['feature','banner']}),
                          ]

    remove_tags = [dict(name='a', attrs={'class':['beginning','prev','cal','next','newest']}),
                   dict(name='div', attrs={'class':['tag-wrapper']}),
                   dict(name='a', attrs={'href':re.compile(r'.*mutable_[0-9]+', re.IGNORECASE)}),
                   dict(name='img', attrs={'src':re.compile(r'.*mutable_[0-9]+', re.IGNORECASE)}),
                   dict(name='ul', attrs={'class':['share-nav','feature-nav']}),
                   ]

    def get_browser(self):
        br = BasicNewsRecipe.get_browser(self)
        cookies = mechanize.CookieJar()
        br = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
        br.addheaders = [('Referer','http://www.gocomics.com/')]
        return br

    def parse_index(self):
        
        feedis = []
        
        soup = self.index_to_soup("http://open.dapper.net/transform.php?dappName=GoComicscomupdated&transformer=RSS&extraArg_title=Title&extraArg_fixDates=1&applyToUrl=http%3A%2F%2Fwww.gocomics.com%2Ffeatures")
        for item in soup.findAll('item'):
            title = None
            url = None
            for contents in item:
                if isinstance(contents,NavigableString):
                    url = contents
                    break
            try:
                title = item.title.contents[0]
            except:
                continue                
            if title and url:
                feedis.append((title,url))       
        
        random.shuffle(feedis)
        feedis = feedis[0:20]
        feeds = []
        
        for title, url in feedis:
            print 'Working on: ', title
            articles = self.make_links(url)
            if articles:
                feeds.append((title, articles))
        return feeds

    def make_links(self, url):
        title = 'Temp'
        current_articles = []
        pages = range(1, self.num_comics_to_get+1)
        for page in pages:
            page_soup = self.index_to_soup(url)
            if page_soup:
                try:
                  strip_title = page_soup.find(name='div', attrs={'class':'top'}).h1.a.string
                except:
                  strip_title = 'Error - no Title found'
                try:
                  date_title = page_soup.find('ul', attrs={'class': 'feature-nav'}).li.string
                  if not date_title:
                      date_title = page_soup.find('ul', attrs={'class': 'feature-nav'}).li.string
                except:
                  date_title = 'Error - no Date found'
                title = strip_title + ' - ' + date_title
                for i in range(2):
                  try:
                    strip_url_date = page_soup.find(name='div', attrs={'class':'top'}).h1.a['href']
                    break #success - this is normal exit
                  except:
                    strip_url_date = None
                    continue #try to get strip_url_date again
                for i in range(2):
                  try:
                    prev_strip_url_date = page_soup.find('a', attrs={'class': 'prev'})['href']
                    break #success - this is normal exit
                  except:
                    prev_strip_url_date = None
                    continue #try to get prev_strip_url_date again
                if strip_url_date:
                  page_url = 'http://www.gocomics.com' + strip_url_date
                else:
                  continue
                if prev_strip_url_date:
                  prev_page_url = 'http://www.gocomics.com' + prev_strip_url_date
                else:
                  continue
            current_articles.append({'title': title, 'url': page_url, 'description':'', 'date':''})
            url = prev_page_url
        current_articles.reverse()
        return current_articles

    def preprocess_html(self, soup):
        if soup.title:
            title_string = soup.title.string.strip()
            _cd = title_string.split(',',1)[1]
            comic_date = ' '.join(_cd.split(' ', 4)[0:-1])
        if soup.h1.span:
            artist = soup.h1.span.string
            soup.h1.span.string.replaceWith(comic_date + artist)
        feature_item = soup.find('p',attrs={'class':'feature_item'})
        if feature_item.a:
            a_tag = feature_item.a
            a_href = a_tag["href"]
            img_tag = a_tag.img
            img_tag["src"] = a_href
            img_tag["width"] = self.comic_size
            img_tag["height"] = None
        return self.adeify_images(soup)

    extra_css = '''
                    h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
                    h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
                    img {max-width:100%; min-width:100%;}
                    p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
                    body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
		'''

This allows you to make use of Starson's user preferences or you could just shuffle and cut down the feeds in parse_feeds.