Merge from trunk

This commit is contained in:
Charles Haley 2013-04-15 14:58:17 +02:00
commit 86f3177958
8 changed files with 347 additions and 478 deletions

View File

@ -16,7 +16,7 @@ class EcoGeek(BasicNewsRecipe):
language = 'en'
category = 'news, ecology, blog'
oldest_article = 7
oldest_article = 30
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = True
@ -28,5 +28,5 @@ class EcoGeek(BasicNewsRecipe):
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
feeds = [(u'Posts', u'http://feeds2.feedburner.com/EcoGeek')]

View File

@ -1,448 +1,229 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = 'Copyright 2010 Starson17'
'''
www.gocomics.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
import mechanize, re
class GoComics(BasicNewsRecipe):
title = 'GoComics'
class Comics(BasicNewsRecipe):
title = 'Comics.com'
__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'
description = 'Comics from comics.com. You should customize this recipe to fetch only the comics you are interested in'
language = 'en'
use_embedded_content= False
no_stylesheets = True
oldest_article = 24
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
cover_url = 'http://www.bsb.lib.tx.us/images/comics.com.gif'
recursions = 0
max_articles_per_feed = 10
num_comics_to_get = 7
# 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!
simultaneous_downloads = 1
# delay = 3
conversion_options = {'linearize_tables' : True
, 'comment' : description
, 'tags' : category
, 'language' : language
}
keep_only_tags = [dict(name='div', attrs={'class':['feature','banner']}),
keep_only_tags = [dict(name='h1'),
dict(name='p', attrs={'class':'feature_item'})
]
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):
feeds = []
for title, url in [
(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"B.C.", u"http://www.gocomics.com/bc"),
#(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"Calvin and Hobbes", u"http://www.gocomics.com/calvinandhobbes"),
#(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"Doodles", u"http://www.gocomics.com/doodles"),
(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"Garfield Minus Garfield", u"http://www.gocomics.com/garfieldminusgarfield"),
(u"Garfield", u"http://www.gocomics.com/garfield"),
#(u"Gasoline Alley", u"http://www.gocomics.com/gasolinealley"),
#(u"Geech Classics", u"http://www.gocomics.com/geechclassics"),
#(u"Get Fuzzy", u"http://www.gocomics.com/getfuzzy"),
#(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"Pibgorn", u"http://www.gocomics.com/pibgorn"),
(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"),
("9 Chickweed Lane", "http://gocomics.com/9_chickweed_lane"),
("Agnes", "http://gocomics.com/agnes"),
("Alley Oop", "http://gocomics.com/alley_oop"),
("Andy Capp", "http://gocomics.com/andy_capp"),
("Arlo & Janis", "http://gocomics.com/arlo&janis"),
("B.C.", "http://gocomics.com/bc"),
("Ballard Street", "http://gocomics.com/ballard_street"),
# ("Ben", "http://comics.com/ben"),
# ("Betty", "http://comics.com/betty"),
# ("Big Nate", "http://comics.com/big_nate"),
# ("Brevity", "http://comics.com/brevity"),
# ("Candorville", "http://comics.com/candorville"),
# ("Cheap Thrills", "http://comics.com/cheap_thrills"),
# ("Committed", "http://comics.com/committed"),
# ("Cow & Boy", "http://comics.com/cow&boy"),
# ("Daddy's Home", "http://comics.com/daddys_home"),
# ("Dog eat Doug", "http://comics.com/dog_eat_doug"),
# ("Drabble", "http://comics.com/drabble"),
# ("F Minus", "http://comics.com/f_minus"),
# ("Family Tree", "http://comics.com/family_tree"),
# ("Farcus", "http://comics.com/farcus"),
# ("Fat Cats Classics", "http://comics.com/fat_cats_classics"),
# ("Ferd'nand", "http://comics.com/ferdnand"),
# ("Flight Deck", "http://comics.com/flight_deck"),
# ("Flo & Friends", "http://comics.com/flo&friends"),
# ("Fort Knox", "http://comics.com/fort_knox"),
# ("Frank & Ernest", "http://comics.com/frank&ernest"),
# ("Frazz", "http://comics.com/frazz"),
# ("Free Range", "http://comics.com/free_range"),
# ("Geech Classics", "http://comics.com/geech_classics"),
# ("Get Fuzzy", "http://comics.com/get_fuzzy"),
# ("Girls & Sports", "http://comics.com/girls&sports"),
# ("Graffiti", "http://comics.com/graffiti"),
# ("Grand Avenue", "http://comics.com/grand_avenue"),
# ("Heathcliff", "http://comics.com/heathcliff"),
# "Heathcliff, a street-smart and mischievous cat with many adventures."
# ("Herb and Jamaal", "http://comics.com/herb_and_jamaal"),
# ("Herman", "http://comics.com/herman"),
# ("Home and Away", "http://comics.com/home_and_away"),
# ("It's All About You", "http://comics.com/its_all_about_you"),
# ("Jane's World", "http://comics.com/janes_world"),
# ("Jump Start", "http://comics.com/jump_start"),
# ("Kit 'N' Carlyle", "http://comics.com/kit_n_carlyle"),
# ("Li'l Abner Classics", "http://comics.com/lil_abner_classics"),
# ("Liberty Meadows", "http://comics.com/liberty_meadows"),
# ("Little Dog Lost", "http://comics.com/little_dog_lost"),
# ("Lola", "http://comics.com/lola"),
# ("Luann", "http://comics.com/luann"),
# ("Marmaduke", "http://comics.com/marmaduke"),
# ("Meg! Classics", "http://comics.com/meg_classics"),
# ("Minimum Security", "http://comics.com/minimum_security"),
# ("Moderately Confused", "http://comics.com/moderately_confused"),
# ("Momma", "http://comics.com/momma"),
# ("Monty", "http://comics.com/monty"),
# ("Motley Classics", "http://comics.com/motley_classics"),
# ("Nancy", "http://comics.com/nancy"),
# ("Natural Selection", "http://comics.com/natural_selection"),
# ("Nest Heads", "http://comics.com/nest_heads"),
# ("Off The Mark", "http://comics.com/off_the_mark"),
# ("On a Claire Day", "http://comics.com/on_a_claire_day"),
# ("One Big Happy Classics", "http://comics.com/one_big_happy_classics"),
# ("Over the Hedge", "http://comics.com/over_the_hedge"),
# ("PC and Pixel", "http://comics.com/pc_and_pixel"),
# ("Peanuts", "http://comics.com/peanuts"),
# ("Pearls Before Swine", "http://comics.com/pearls_before_swine"),
# ("Pickles", "http://comics.com/pickles"),
# ("Prickly City", "http://comics.com/prickly_city"),
# ("Raising Duncan Classics", "http://comics.com/raising_duncan_classics"),
# ("Reality Check", "http://comics.com/reality_check"),
# ("Red & Rover", "http://comics.com/red&rover"),
# ("Rip Haywire", "http://comics.com/rip_haywire"),
# ("Ripley's Believe It or Not!", "http://comics.com/ripleys_believe_it_or_not"),
# ("Rose Is Rose", "http://comics.com/rose_is_rose"),
# ("Rubes", "http://comics.com/rubes"),
# ("Rudy Park", "http://comics.com/rudy_park"),
# ("Scary Gary", "http://comics.com/scary_gary"),
# ("Shirley and Son Classics", "http://comics.com/shirley_and_son_classics"),
# ("Soup To Nutz", "http://comics.com/soup_to_nutz"),
# ("Speed Bump", "http://comics.com/speed_bump"),
# ("Spot The Frog", "http://comics.com/spot_the_frog"),
# ("State of the Union", "http://comics.com/state_of_the_union"),
# ("Strange Brew", "http://comics.com/strange_brew"),
# ("Tarzan Classics", "http://comics.com/tarzan_classics"),
# ("That's Life", "http://comics.com/thats_life"),
# ("The Barn", "http://comics.com/the_barn"),
# ("The Born Loser", "http://comics.com/the_born_loser"),
# ("The Buckets", "http://comics.com/the_buckets"),
# ("The Dinette Set", "http://comics.com/the_dinette_set"),
# ("The Grizzwells", "http://comics.com/the_grizzwells"),
# ("The Humble Stumble", "http://comics.com/the_humble_stumble"),
# ("The Knight Life", "http://comics.com/the_knight_life"),
# ("The Meaning of Lila", "http://comics.com/the_meaning_of_lila"),
# ("The Other Coast", "http://comics.com/the_other_coast"),
# ("The Sunshine Club", "http://comics.com/the_sunshine_club"),
# ("Unstrange Phenomena", "http://comics.com/unstrange_phenomena"),
# ("Watch Your Head", "http://comics.com/watch_your_head"),
# ("Wizard of Id", "http://comics.com/wizard_of_id"),
# ("Working Daze", "http://comics.com/working_daze"),
# ("Working It Out", "http://comics.com/working_it_out"),
# ("Zack Hill", "http://comics.com/zack_hill"),
# ("(Th)ink", "http://comics.com/think"),
# "Tackling the political and social issues impacting communities of color."
# ("Adam Zyglis", "http://comics.com/adam_zyglis"),
# "Known for his excellent caricatures, as well as independent and incisive imagery. "
# ("Andy Singer", "http://comics.com/andy_singer"),
# ("Bill Day", "http://comics.com/bill_day"),
# "Powerful images on sensitive issues."
# ("Bill Schorr", "http://comics.com/bill_schorr"),
# ("Bob Englehart", "http://comics.com/bob_englehart"),
# ("Brian Fairrington", "http://comics.com/brian_fairrington"),
# ("Bruce Beattie", "http://comics.com/bruce_beattie"),
# ("Cam Cardow", "http://comics.com/cam_cardow"),
# ("Chip Bok", "http://comics.com/chip_bok"),
# ("Chris Britt", "http://comics.com/chris_britt"),
# ("Chuck Asay", "http://comics.com/chuck_asay"),
# ("Clay Bennett", "http://comics.com/clay_bennett"),
# ("Daryl Cagle", "http://comics.com/daryl_cagle"),
# ("David Fitzsimmons", "http://comics.com/david_fitzsimmons"),
# "David Fitzsimmons is a new editorial cartoons on comics.com. He is also a staff writer and editorial cartoonist for the Arizona Daily Star. "
# ("Drew Litton", "http://comics.com/drew_litton"),
# "Drew Litton is an artist who is probably best known for his sports cartoons. He received the National Cartoonist Society Sports Cartoon Award for 1993. "
# ("Ed Stein", "http://comics.com/ed_stein"),
# "Winner of the Fischetti Award in 2006 and the Scripps Howard National Journalism Award, 1999, Ed Stein has been the editorial cartoonist for the Rocky Mountain News since 1978. "
# ("Eric Allie", "http://comics.com/eric_allie"),
# "Eric Allie is an editorial cartoonist with the Pioneer Press and CNS News. "
# ("Gary Markstein", "http://comics.com/gary_markstein"),
# ("Gary McCoy", "http://comics.com/gary_mccoy"),
# "Gary McCoy is known for his editorial cartoons, humor and inane ramblings. He is a 2 time nominee for Best Magazine Cartoonist of the Year by the National Cartoonists Society. He resides in Belleville, IL. "
# ("Gary Varvel", "http://comics.com/gary_varvel"),
# ("Henry Payne", "http://comics.com/henry_payne"),
# ("JD Crowe", "http://comics.com/jd_crowe"),
# ("Jeff Parker", "http://comics.com/jeff_parker"),
# ("Jeff Stahler", "http://comics.com/jeff_stahler"),
# ("Jerry Holbert", "http://comics.com/jerry_holbert"),
# ("John Cole", "http://comics.com/john_cole"),
# ("John Darkow", "http://comics.com/john_darkow"),
# "John Darkow is a contributing editorial cartoonist for the Humor Times as well as editoiral cartoonist for the Columbia Daily Tribune, Missouri"
# ("John Sherffius", "http://comics.com/john_sherffius"),
# ("Larry Wright", "http://comics.com/larry_wright"),
# ("Lisa Benson", "http://comics.com/lisa_benson"),
# ("Marshall Ramsey", "http://comics.com/marshall_ramsey"),
# ("Matt Bors", "http://comics.com/matt_bors"),
# ("Michael Ramirez", "http://comics.com/michael_ramirez"),
# ("Mike Keefe", "http://comics.com/mike_keefe"),
# ("Mike Luckovich", "http://comics.com/mike_luckovich"),
# ("MIke Thompson", "http://comics.com/mike_thompson"),
# ("Monte Wolverton", "http://comics.com/monte_wolverton"),
# "Unique mix of perspectives"
# ("Mr. Fish", "http://comics.com/mr_fish"),
# "Side effects may include swelling"
# ("Nate Beeler", "http://comics.com/nate_beeler"),
# "Middle America meets the Beltway."
# ("Nick Anderson", "http://comics.com/nick_anderson"),
# ("Pat Bagley", "http://comics.com/pat_bagley"),
# "Unfair and Totally Unbalanced."
# ("Paul Szep", "http://comics.com/paul_szep"),
# ("RJ Matson", "http://comics.com/rj_matson"),
# "Power cartoons from NYC and Capitol Hill"
# ("Rob Rogers", "http://comics.com/rob_rogers"),
# "Humorous slant on current events"
# ("Robert Ariail", "http://comics.com/robert_ariail"),
# "Clever and unpredictable"
# ("Scott Stantis", "http://comics.com/scott_stantis"),
# ("Signe Wilkinson", "http://comics.com/signe_wilkinson"),
# ("Steve Benson", "http://comics.com/steve_benson"),
# ("Steve Breen", "http://comics.com/steve_breen"),
# ("Steve Kelley", "http://comics.com/steve_kelley"),
# ("Steve Sack", "http://comics.com/steve_sack"),
]:
print 'Working on: ', title
articles = self.make_links(url)
if articles:
feeds.append((title, articles))
return feeds
def make_links(self, url):
title = 'Temp'
soup = self.index_to_soup(url)
# print 'soup: ', soup
title = ''
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
from datetime import datetime, timedelta
now = datetime.now()
dates = [(now-timedelta(days=d)).strftime('%Y/%m/%d') for d in range(self.num_comics_to_get)]
for page in dates:
page_url = url + '/' + str(page)
print(page_url)
soup = self.index_to_soup(page_url)
if soup:
strip_tag = self.tag_to_string(soup.find('a'))
if strip_tag:
print 'strip_tag: ', strip_tag
title = strip_tag
print 'title: ', title
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;}
'''

View File

@ -0,0 +1,11 @@
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1366025923(BasicNewsRecipe):
title = u'Lightspeed Magazine'
language = 'en'
__author__ = 'Jose Pinto'
oldest_article = 7
max_articles_per_feed = 100
auto_cleanup = True
use_embedded_content = False
feeds = [(u'Lastest Stories', u'http://www.lightspeedmagazine.com/rss-2/')]

View File

@ -716,11 +716,13 @@ class DB(object):
tables['size'] = SizeTable('size', self.field_metadata['size'].copy())
self.FIELD_MAP = {'id':0, 'title':1, 'authors':2, 'timestamp':3,
'size':4, 'rating':5, 'tags':6, 'comments':7, 'series':8,
'publisher':9, 'series_index':10, 'sort':11, 'author_sort':12,
'formats':13, 'path':14, 'pubdate':15, 'uuid':16, 'cover':17,
'au_map':18, 'last_modified':19, 'identifiers':20}
self.FIELD_MAP = {
'id':0, 'title':1, 'authors':2, 'timestamp':3, 'size':4,
'rating':5, 'tags':6, 'comments':7, 'series':8, 'publisher':9,
'series_index':10, 'sort':11, 'author_sort':12, 'formats':13,
'path':14, 'pubdate':15, 'uuid':16, 'cover':17, 'au_map':18,
'last_modified':19, 'identifiers':20, 'languages':21,
}
for k,v in self.FIELD_MAP.iteritems():
self.field_metadata.set_field_record_index(k, v, prefer_custom=False)
@ -766,6 +768,8 @@ class DB(object):
self.field_metadata.set_field_record_index('ondevice', base, prefer_custom=False)
self.FIELD_MAP['marked'] = base = base+1
self.field_metadata.set_field_record_index('marked', base, prefer_custom=False)
self.FIELD_MAP['series_sort'] = base = base+1
self.field_metadata.set_field_record_index('series_sort', base, prefer_custom=False)
# }}}

View File

@ -7,6 +7,7 @@ __license__ = 'GPL v3'
__copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
import os
from functools import partial
from calibre.db.backend import DB
from calibre.db.cache import Cache
@ -14,6 +15,8 @@ from calibre.db.view import View
class LibraryDatabase(object):
''' Emulate the old LibraryDatabase2 interface '''
PATH_LIMIT = DB.PATH_LIMIT
WINDOWS_LIBRARY_PATH_LIMIT = DB.WINDOWS_LIBRARY_PATH_LIMIT
@ -30,12 +33,22 @@ class LibraryDatabase(object):
backend = self.backend = DB(library_path, default_prefs=default_prefs,
read_only=read_only, restore_all_prefs=restore_all_prefs,
progress_callback=progress_callback)
cache = Cache(backend)
cache = self.new_api = Cache(backend)
cache.init()
self.data = View(cache)
self.get_property = self.data.get_property
self.all_ids = self.data.cache.all_book_ids
for prop in (
'author_sort', 'authors', 'comment', 'comments',
'publisher', 'rating', 'series', 'series_index', 'tags',
'title', 'timestamp', 'uuid', 'pubdate', 'ondevice',
'metadata_last_modified', 'languages',
):
fm = {'comment':'comments', 'metadata_last_modified':
'last_modified', 'title_sort':'sort'}.get(prop, prop)
setattr(self, prop, partial(self.get_property,
loc=self.FIELD_MAP[fm]))
def close(self):
self.backend.close()
@ -43,7 +56,7 @@ class LibraryDatabase(object):
def break_cycles(self):
self.data.cache.backend = None
self.data.cache = None
self.data = self.backend = self.field_metadata = self.prefs = self.listeners = self.refresh_ondevice = None
self.data = self.backend = self.new_api = self.field_metadata = self.prefs = self.listeners = self.refresh_ondevice = None
# Library wide properties {{{
@property
@ -72,6 +85,10 @@ class LibraryDatabase(object):
@property
def FIELD_MAP(self):
return self.backend.FIELD_MAP
def all_ids(self):
for book_id in self.data.cache.all_book_ids():
yield book_id
# }}}

View File

@ -14,16 +14,21 @@ class LegacyTest(BaseTest):
def test_library_wide_properties(self): # {{{
'Test library wide properties'
old = self.init_old()
def get_props(db):
props = ('user_version', 'is_second_db', 'library_id', 'field_metadata',
'custom_column_label_map', 'custom_column_num_map')
oldvals = {x:getattr(old, x) for x in props}
oldvals['last_modified'] = old.last_modified()
fprops = ('last_modified', )
ans = {x:getattr(db, x) for x in props}
ans.update({x:getattr(db, x)() for x in fprops})
ans['all_ids'] = frozenset(db.all_ids())
return ans
old = self.init_old()
oldvals = get_props(old)
old.close()
old = None
del old
db = self.init_legacy()
newvals = {x:getattr(db, x) for x in props}
newvals['last_modified'] = db.last_modified()
newvals = get_props(db)
self.assertEqual(oldvals, newvals)
db.close()
# }}}
@ -38,6 +43,14 @@ class LegacyTest(BaseTest):
label = type('')(label)
ans[label] = tuple(db.get_property(i, index_is_id=True, loc=loc)
for i in db.all_ids())
if label in ('id', 'title', '#tags'):
with self.assertRaises(IndexError):
db.get_property(9999, loc=loc)
with self.assertRaises(IndexError):
db.get_property(9999, index_is_id=True, loc=loc)
if label in {'tags', 'formats'}:
# Order is random in the old db for these
ans[label] = tuple(set(x.split(',')) if x else x for x in ans[label])
return ans
old = self.init_old()

View File

@ -11,6 +11,9 @@ import weakref
from functools import partial
from itertools import izip, imap
from calibre.ebooks.metadata import title_sort
from calibre.utils.config_base import tweaks
def sanitize_sort_field_name(field_metadata, field):
field = field_metadata.search_term_to_field_key(field.lower().strip())
# translate some fields to their hidden equivalent
@ -40,6 +43,18 @@ class TableRow(list):
else:
return view._field_getters[obj](self.book_id)
def format_is_multiple(x, sep=',', repl=None):
if not x:
return None
if repl is not None:
x = (y.replace(sep, repl) for y in x)
return sep.join(x)
def format_identifiers(x):
if not x:
return None
return ','.join('%s:%s'%(k, v) for k, v in x.iteritems())
class View(object):
''' A table view of the database, with rows and columns. Also supports
@ -53,21 +68,44 @@ class View(object):
self.search_restriction_name = self.base_restriction_name = ''
self._field_getters = {}
for col, idx in cache.backend.FIELD_MAP.iteritems():
if isinstance(col, int):
label = self.cache.backend.custom_column_num_map[col]['label']
label = (self.cache.backend.field_metadata.custom_field_prefix
+ label)
self._field_getters[idx] = partial(self.get, label)
else:
try:
self._field_getters[idx] = {
label, fmt = col, lambda x:x
func = {
'id': self._get_id,
'au_map': self.get_author_data,
'ondevice': self.get_ondevice,
'marked': self.get_marked,
}[col]
except KeyError:
self._field_getters[idx] = partial(self.get, col)
'series_sort':self.get_series_sort,
}.get(col, self._get)
if isinstance(col, int):
label = self.cache.backend.custom_column_num_map[col]['label']
label = (self.cache.backend.field_metadata.custom_field_prefix
+ label)
if label.endswith('_index'):
try:
num = int(label.partition('_')[0])
except ValueError:
pass # series_index
else:
label = self.cache.backend.custom_column_num_map[num]['label']
label = (self.cache.backend.field_metadata.custom_field_prefix
+ label + '_index')
fm = self.field_metadata[label]
fm
if label == 'authors':
fmt = partial(format_is_multiple, repl='|')
elif label in {'tags', 'languages', 'formats'}:
fmt = format_is_multiple
elif label == 'cover':
fmt = bool
elif label == 'identifiers':
fmt = format_identifiers
elif fm['datatype'] == 'text' and fm['is_multiple']:
sep = fm['is_multiple']['cache_to_list']
if sep not in {'&','|'}:
sep = '|'
fmt = partial(format_is_multiple, sep=sep)
self._field_getters[idx] = partial(func, label, fmt=fmt) if func == self._get else func
self._map = tuple(self.cache.all_book_ids())
self._map_filtered = tuple(self._map)
@ -81,6 +119,8 @@ class View(object):
return self.cache.field_metadata
def _get_id(self, idx, index_is_id=True):
if index_is_id and idx not in self.cache.all_book_ids():
raise IndexError('No book with id %s present'%idx)
return idx if index_is_id else self.index_to_id(idx)
def __getitem__(self, row):
@ -112,9 +152,21 @@ class View(object):
def index_to_id(self, idx):
return self._map_filtered[idx]
def get(self, field, idx, index_is_id=True, default_value=None):
def _get(self, field, idx, index_is_id=True, default_value=None, fmt=lambda x:x):
id_ = idx if index_is_id else self.index_to_id(idx)
return self.cache.field_for(field, id_)
if index_is_id and id_ not in self.cache.all_book_ids():
raise IndexError('No book with id %s present'%idx)
return fmt(self.cache.field_for(field, id_, default_value=default_value))
def get_series_sort(self, idx, index_is_id=True, default_value=''):
book_id = idx if index_is_id else self.index_to_id(idx)
with self.cache.read_lock:
lang_map = self.cache.fields['languages'].book_value_map
lang = lang_map.get(book_id, None) or None
if lang:
lang = lang[0]
return title_sort(self.cache._field_for('series', book_id, default_value=''),
order=tweaks['title_series_sorting'], lang=lang)
def get_ondevice(self, idx, index_is_id=True, default_value=''):
id_ = idx if index_is_id else self.index_to_id(idx)
@ -124,26 +176,15 @@ class View(object):
id_ = idx if index_is_id else self.index_to_id(idx)
return self.marked_ids.get(id_, default_value)
def get_author_data(self, idx, index_is_id=True, default_value=()):
'''
Return author data for all authors of the book identified by idx as a
tuple of dictionaries. The dictionaries should never be empty, unless
there is a bug somewhere. The list could be empty if idx point to an
non existent book, or book with no authors (though again a book with no
authors should never happen).
Each dictionary has the keys: name, sort, link. Link can be an empty
string.
default_value is ignored, this method always returns a tuple
'''
def get_author_data(self, idx, index_is_id=True, default_value=None):
id_ = idx if index_is_id else self.index_to_id(idx)
with self.cache.read_lock:
ids = self.cache._field_ids_for('authors', id_)
ans = []
for id_ in ids:
ans.append(self.cache._author_data(id_))
return tuple(ans)
data = self.cache._author_data(id_)
ans.append(':::'.join((data['name'], data['sort'], data['link'])))
return ':#:'.join(ans) if ans else default_value
def multisort(self, fields=[], subsort=False, only_ids=None):
fields = [(sanitize_sort_field_name(self.field_metadata, x), bool(y)) for x, y in fields]

View File

@ -77,7 +77,7 @@ class Container(object):
# Map of relative paths with '/' separators from root of unzipped ePub
# to absolute paths on filesystem with os-specific separators
opfpath = os.path.abspath(opfpath)
opfpath = os.path.abspath(os.path.realpath(opfpath))
for dirpath, _dirnames, filenames in os.walk(self.root):
for f in filenames:
path = join(dirpath, f)
@ -407,7 +407,8 @@ class Container(object):
remove.add(child)
except AttributeError:
continue # Happens for XML comments
for child in remove: mdata.remove(child)
for child in remove:
mdata.remove(child)
if len(mdata) > 0:
mdata[-1].tail = '\n '
@ -473,17 +474,17 @@ class EpubContainer(Container):
book_type = 'epub'
META_INF = {
'container.xml' : True,
'manifest.xml' : False,
'encryption.xml' : False,
'metadata.xml' : False,
'signatures.xml' : False,
'rights.xml' : False,
'container.xml': True,
'manifest.xml': False,
'encryption.xml': False,
'metadata.xml': False,
'signatures.xml': False,
'rights.xml': False,
}
def __init__(self, pathtoepub, log):
self.pathtoepub = pathtoepub
tdir = self.root = PersistentTemporaryDirectory('_epub_container')
tdir = self.root = os.path.abspath(os.path.realpath(PersistentTemporaryDirectory('_epub_container')))
with open(self.pathtoepub, 'rb') as stream:
try:
zf = ZipFile(stream)
@ -616,7 +617,7 @@ class AZW3Container(Container):
def __init__(self, pathtoazw3, log):
self.pathtoazw3 = pathtoazw3
tdir = self.root = PersistentTemporaryDirectory('_azw3_container')
tdir = self.root = os.path.abspath(os.path.realpath(PersistentTemporaryDirectory('_azw3_container')))
with open(pathtoazw3, 'rb') as stream:
raw = stream.read(3)
if raw == b'TPZ':
@ -670,7 +671,8 @@ class AZW3Container(Container):
# }}}
def get_container(path, log=None):
if log is None: log = default_log
if log is None:
log = default_log
ebook = (AZW3Container if path.rpartition('.')[-1].lower() in {'azw3', 'mobi'}
else EpubContainer)(path, log)
return ebook