dosage/dosagelib/plugins/c.py

292 lines
12 KiB
Python
Raw Normal View History

# -*- coding: iso-8859-1 -*-
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
2012-11-21 20:57:26 +00:00
# Copyright (C) 2012 Bastian Kleineidam
2012-06-20 19:58:13 +00:00
from re import compile
2012-10-11 10:03:12 +00:00
from ..scraper import _BasicScraper
2012-11-21 20:57:26 +00:00
from ..helpers import bounceStarter, indirectStarter
2012-10-11 10:03:12 +00:00
from ..util import tagre, getQueryParams
2012-06-20 19:58:13 +00:00
class CaptainSNES(_BasicScraper):
2012-11-21 20:57:26 +00:00
latestUrl = 'http://www.captainsnes.com/'
stripUrl = latestUrl + '%s/'
imageSearch = compile(r"<img src='(http://www\.captainsnes\.com/comics/[^']+)'")
prevSearch = compile(r'<a href="(http://www\.captainsnes\.com/[^"]+)"><span class="prev">')
help = 'Index format: yyyy/mm/dd/nnn-stripname'
2012-06-20 19:58:13 +00:00
class CaribbeanBlue(_BasicScraper):
latestUrl = 'http://cblue.katbox.net/'
2012-11-21 20:57:26 +00:00
stripUrl = latestUrl + 'archive/%s'
imageSearch = compile(tagre("img", "src", r'(http://cblue\.katbox\.net/wp-content/webcomic/cblue/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://cblue\.katbox\.net/archive/[^"]+)', after="previous"))
help = 'Index format: nnn-stripname'
2012-06-20 19:58:13 +00:00
class Catena(_BasicScraper):
latestUrl = 'http://catenamanor.com/'
2012-11-14 19:23:30 +00:00
stripUrl = latestUrl + '%s'
2012-11-12 17:59:19 +00:00
imageSearch = compile(tagre("img", "src", r'(http://catenamanor\.com/comics/[^"]+)'))
2012-11-13 18:12:28 +00:00
prevSearch = compile(tagre("a", "href", r'([^"]+)', after='rel="prev"'))
2012-11-14 19:23:30 +00:00
help = 'Index format: yyyy/mm/dd/<name>'
2012-06-20 19:58:13 +00:00
class ChasingTheSunset(_BasicScraper):
latestUrl = 'http://www.fantasycomic.com/'
stripUrl = latestUrl + 'index.php?p=c%s'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'(/cmsimg/.+?)".+?comic-img')
prevSearch = compile(r'<a href="(.+?)" title="" ><img src="(images/eye-prev.png|images/cn-prev.png)"')
help = 'Index format: n'
class CheckerboardNightmare(_BasicScraper):
latestUrl = 'http://www.checkerboardnightmare.com/'
stripUrl = latestUrl + 'd/%s.shtml'
imageSearch=compile(tagre("img", "src", r'(/comic[s|/][^"]+)'))
prevSearch=compile(tagre("a", "href", r'[^"]*(/d/\d+\.s?html)')+r"[^>]+/images/(?:nav_02|previous_day)\.gif")
help='Index format: yyyymmdd'
2012-06-20 19:58:13 +00:00
class Chisuji(_BasicScraper):
latestUrl = 'http://www.chisuji.com/'
stripUrl = latestUrl + '%s'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'<img src="(http://www.chisuji.com/comics/.+?)"')
prevSearch = compile(r'<div class="nav-previous"><a href="(http://www.chisuji.com/.+?)">')
help = 'Index format: yyyy/mm/dd/strip-name'
class ChugworthAcademy(_BasicScraper):
latestUrl = 'http://chugworth.com/'
stripUrl = latestUrl + '?p=%s'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'<img src="(.+?)" alt="Comic')
prevSearch = compile(r'<a href="(http://chugworth.com/\?p=\d{1,4})"[^>]+?title="Previous">')
help = 'Index format: n (unpadded)'
class ChugworthAcademyArchive(_BasicScraper):
latestUrl = 'http://chugworth.com/archive/?strip_id=422'
2012-11-13 18:10:19 +00:00
stripUrl = 'http://chugworth.com/archive/?strip_id=%s'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'<img src=(comics/\d+.+?.\w{1,4})')
prevSearch = compile(r'<a href=\'(.+?)\'><img src=\'images/previous.gif')
help = 'Index format: nnn'
class CigarroAndCerveja(_BasicScraper):
latestUrl = 'http://www.cigarro.ca/'
stripUrl = latestUrl + '?p=%s'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r"(/comics/.+?)'")
prevSearch = compile(r'(/\?p=.+?)">&laq')
help = 'Index format: non'
class Comedity(_BasicScraper):
latestUrl = 'http://www.comedity.com/'
stripUrl = latestUrl + 'index.php?strip_id=%s'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'<img src="(Comedity_files/.+?)"')
prevSearch = compile(r'<a href="(/?index.php\?strip_id=\d+?)"> *<img alt=\"Prior Strip')
help = 'Index format: n (no padding)'
class Commissioned(_BasicScraper):
latestUrl = 'http://www.commissionedcomic.com/'
2012-11-21 20:57:26 +00:00
stripUrl = latestUrl + '?p=%s'
imageSearch = compile(tagre("img", "src", r'(http://www\.commissionedcomic\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://www\.commissionedcomic\.com/\?p=\d+)', after="prev"))
2012-06-20 19:58:13 +00:00
help = 'Index format: n'
class CoolCatStudio(_BasicScraper):
latestUrl = 'http://www.coolcatstudio.com/'
stripUrl = latestUrl + 'strips-cat/ccs%s'
2012-11-21 20:57:26 +00:00
imageSearch = compile(tagre("img", "src", r'(http://www\.coolcatstudio\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://www\.coolcatstudio\.com/strips-cat/[^"]+)', before="prev"))
2012-11-14 05:22:08 +00:00
help = 'Index format: yyyymmdd'
2012-06-20 19:58:13 +00:00
class CourtingDisaster(_BasicScraper):
latestUrl = 'http://www.courting-disaster.com/'
stripUrl = latestUrl + 'archive/%s.html'
2012-11-21 20:57:26 +00:00
imageSearch = compile(tagre("img", "src", r'(/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(/archive/\d+\.html)') + tagre("img", "src", r'/images/previous\.gif'))
2012-06-20 19:58:13 +00:00
help = 'Index format: yyyymmdd'
class CrapIDrewOnMyLunchBreak(_BasicScraper):
latestUrl = 'http://crap.jinwicked.com/'
2012-11-14 19:23:30 +00:00
stripUrl = latestUrl + '%s'
imageSearch = compile(tagre("img", "src", r'(http://crap\.jinwicked\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'([^"]+)', after="prev"))
2012-06-20 19:58:13 +00:00
help = 'Index format: yyyy/mm/dd/name'
class CtrlAltDel(_BasicScraper):
latestUrl = 'http://www.cad-comic.com/cad/'
2012-11-14 19:23:30 +00:00
stripUrl = latestUrl + '%s'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'<img src="(/comics/\w+/\d{8}\..+?)"')
prevSearch = compile(r'<a href="(/\w+/\d{8})" class="nav-back')
help = 'Index format: yyyymmdd'
class CtrlAltDelSillies(CtrlAltDel):
name = 'CtrlAltDel/Sillies'
latestUrl = 'http://www.cad-comic.com/sillies/'
2012-11-14 19:23:30 +00:00
stripUrl = latestUrl + '%s'
2012-06-20 19:58:13 +00:00
class Curvy(_BasicScraper):
latestUrl = 'http://www.c.urvy.org/'
stripUrl = latestUrl + '?date=%s'
2012-11-21 20:57:26 +00:00
imageSearch = compile(tagre("img", "src", r'(/c/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(/\?date=\d+)') + tagre("img", "src", "/nav/prev\.png"))
2012-06-20 19:58:13 +00:00
help = 'Index format: yyyymmdd'
def cloneManga(name, shortName, lastStrip=None):
2012-11-12 17:59:19 +00:00
url = 'http://manga.clone-army.org'
baseUrl = '%s/%s.php' % (url, shortName)
2012-06-20 19:58:13 +00:00
def namer(self, imageUrl, pageUrl):
2012-11-12 17:59:19 +00:00
return '%03d' % int(getQueryParams(pageUrl)['page'][0])
2012-06-20 19:58:13 +00:00
2012-11-21 20:57:26 +00:00
attrs = dict(
name='CloneManga/' + name,
stripUrl = baseUrl + '?page=%s',
imageSearch=compile(tagre("img", "src", r'((?:%s/)?%s/[^"]+)' % (url, shortName), after="center")),
prevSearch=compile(tagre("a", "href", r'([^"]+)')+tagre("img", "src", r"previous\.gif")),
help='Index format: n',
namer=namer,
2012-06-20 19:58:13 +00:00
)
2012-11-21 20:57:26 +00:00
if lastStrip is None:
attrs['starter'] = indirectStarter(baseUrl, compile(tagre("a", "href", r'([^"]+)')+tagre("img", "src", r"last\.gif")))
else:
attrs['latestUrl'] = attrs['stripUrl'] % lastStrip
return type('CloneManga_%s' % name, (_BasicScraper,), attrs)
2012-06-20 19:58:13 +00:00
anm = cloneManga('AprilAndMay', 'anm')
kanami = cloneManga('Kanami', 'kanami')
momoka = cloneManga('MomokaCorner', 'momoka')
nana = cloneManga('NanasEverydayLife', 'nana', '78')
pxi = cloneManga('PaperEleven', 'pxi', '311')
t42r = cloneManga('Tomoyo42sRoom', 't42r')
penny = cloneManga('PennyTribute', 'penny')
class CatAndGirl(_BasicScraper):
latestUrl = 'http://catandgirl.com/'
stripUrl = latestUrl + '?p=%s'
2012-10-11 19:32:15 +00:00
imageSearch = compile(tagre("img", "src", r'(http://catandgirl\.com/archive/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'([^"]+)')+r"[^<]+Previous</a>")
2012-06-20 19:58:13 +00:00
help = 'Index format: n (unpadded)'
class CyanideAndHappiness(_BasicScraper):
2012-11-21 20:57:26 +00:00
latestUrl = 'http://www.explosm.net/comics/'
stripUrl = latestUrl + '%s/'
imageSearch = compile(tagre("img", "src", r'(http:\/\/www\.explosm\.net/db/files/Comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(/comics/\d+/)', before="prev"))
2012-06-20 19:58:13 +00:00
help = 'Index format: n (unpadded)'
class CrimsonDark(_BasicScraper):
latestUrl = 'http://www.davidcsimon.com/crimsondark/'
stripUrl = latestUrl + 'index.php?view=comic&strip_id=%s'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'src="(.+?strips/.+?)"')
prevSearch = compile(r'<a href=[\'"](/crimsondark/index\.php\?view=comic&amp;strip_id=\d+)[\'"]><img src=[\'"]themes/cdtheme/images/active_prev.png[\'"]')
help = 'Index format: n (unpadded)'
class CatsAndCameras(_BasicScraper):
latestUrl = 'http://catsncameras.com/cnc/'
2012-11-14 19:23:30 +00:00
stripUrl = latestUrl + '?p=%s'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'<img src="(http://catsncameras.com/cnc/comics/.+?)"')
prevSearch = compile(r'<div class="nav-previous"><a href="(http://catsncameras.com/cnc/.+?)">')
help = 'Index format: nnn'
class CowboyJedi(_BasicScraper):
latestUrl = 'http://www.cowboyjedi.com/'
stripUrl = latestUrl + '%s'
imageSearch = compile(tagre("img", "src", r'(http://www\.cowboyjedi.\com/comics/[^"]+)'))
2012-06-20 19:58:13 +00:00
prevSearch = compile(r'<a href="(http://www.cowboyjedi.com/.+?)" class="navi navi-prev"')
help = 'Index format: yyyy/mm/dd/strip-name'
class CasuallyKayla(_BasicScraper):
latestUrl = 'http://casuallykayla.com/'
stripUrl = latestUrl + '?p=%s'
imageSearch = compile(tagre("img", "src", r'(http://casuallykayla\.com/comics/[^"]+)'))
prevSearch = compile(tagre("div", "class", r'nav-previous') + tagre("a", "href", r'([^"]+)'))
2012-06-20 19:58:13 +00:00
help = 'Index format: nnn'
class Collar6(_BasicScraper):
latestUrl = 'http://collar6.com/'
stripUrl = latestUrl + 'archive/%s'
2012-11-13 05:51:54 +00:00
imageSearch = compile(tagre("img", "src", r'(http://collar6\.com/wp-content/webcomic/collar6/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://collar6\.com/archive/[^"]+)', after="previous"))
2012-11-14 05:22:08 +00:00
help = 'Index format: <name>'
2012-06-20 19:58:13 +00:00
class Chester5000XYV(_BasicScraper):
latestUrl = 'http://jessfink.com/Chester5000XYV/'
stripUrl = latestUrl + '?p=%s'
imageSearch = compile(tagre("img", "src", r'(http://jessfink\.com/Chester5000XYV/comics/[^"]+)'))
2012-06-20 19:58:13 +00:00
prevSearch = compile(r'<a href="(.+?)"><span class="prev">')
help = 'Index format: nnn'
class CalamitiesOfNature(_BasicScraper):
latestUrl = 'http://www.calamitiesofnature.com/'
stripUrl = latestUrl + 'archive/?c=%s'
imageSearch = compile(tagre("img", "src", r'(archive/\d+[^"]+|http://www\.calamitiesofnature\.com/archive/\d+[^"]+)'))
2012-06-20 19:58:13 +00:00
prevSearch = compile(r'<a id="previous" href="(http://www.calamitiesofnature.com/archive/\?c\=\d+)">')
help = 'Index format: nnn'
class Champ2010(_BasicScraper):
2012-11-21 20:57:26 +00:00
# the latest URL is hard coded since the comic is discontinued
latestUrl = 'http://jedcollins.com/champ2010/champ-12-30-10.html'
stripUrl = 'http://jedcollins.com/champ2010/champ-%s.html'
imageSearch = compile(tagre("img", "src", r'(http://jedcollins\.com/champ2010/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://jedcollins\.com/champ2010/[^"]+)', after="Previous"))
help = 'Index format: yy-dd-mm'
2012-06-20 19:58:13 +00:00
class Chucklebrain(_BasicScraper):
latestUrl = 'http://www.chucklebrain.com/main.php'
stripUrl = latestUrl + '?img=%s'
imageSearch = compile(tagre("img", "src", r'(/images/strip[^"]+)'))
2012-06-20 19:58:13 +00:00
prevSearch = compile(r'<a href=\'(/main.php\?img\=\d+)\'><img src=\'/images/previous.jpg\'')
help = 'Index format: nnn'
class CompanyY(_BasicScraper):
latestUrl = 'http://company-y.com/'
stripUrl = latestUrl + '%s/'
imageSearch = compile(tagre("img", "src", r'(http://company-y\.com/comics/[^"]+)'))
2012-06-20 19:58:13 +00:00
prevSearch = compile(r'<div class="nav-previous"><a href="(http://company-y.com/.+?)"')
help = 'Index format: yyyy/mm/dd/strip-name'
class CorydonCafe(_BasicScraper):
2012-11-21 20:57:26 +00:00
starter = bounceStarter('http://corydoncafe.com/', compile(tagre("a", "href", r"(http://corydoncafe\.com/\d+/[^']+)", after="next", quote="'")))
stripUrl = 'http://corydoncafe.com/%s.php'
imageSearch = compile(tagre("img", "src", r"(\./[^']+)", quote="'"))
prevSearch = compile(tagre("a", "href", r"(http://corydoncafe\.com/\d+/[^']+)", after="prev", quote="'"))
help = 'Index format: yyyy/stripname'
2012-06-20 19:58:13 +00:00
@classmethod
def namer(cls, imageUrl, pageUrl):
return pageUrl.split('/')[-1].split('.')[0]
class CraftedFables(_BasicScraper):
latestUrl = 'http://www.craftedfables.com/'
2012-11-13 18:10:19 +00:00
stripUrl = 'http://www.caf-fiends.net/craftedfables/?p=%s'
imageSearch = compile(tagre("img", "src", r'(http://www\.caf-fiends\.net/craftedfables/comics/[^"]+)'))
2012-06-20 19:58:13 +00:00
prevSearch = compile(r'<a href="(http://www.caf-fiends.net/craftedfables/.+?)"><span class="prev">')
help = 'Index format: nnn'