dosage/dosagelib/plugins/c.py

384 lines
14 KiB
Python
Raw Normal View History

# -*- coding: iso-8859-1 -*-
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
2013-01-28 17:52:26 +00:00
# Copyright (C) 2012-2013 Bastian Kleineidam
2012-11-21 20:57:26 +00:00
from re import compile, escape
2012-06-20 19:58:13 +00:00
2012-10-11 10:03:12 +00:00
from ..scraper import _BasicScraper
2013-02-22 19:29:05 +00:00
from ..helpers import bounceStarter, indirectStarter
2012-12-04 06:02:40 +00:00
from ..util import tagre
2012-06-20 19:58:13 +00:00
2013-02-21 18:47:21 +00:00
class Caggage(_BasicScraper):
url = 'http://caggagecomic.com/'
rurl = escape(url)
2013-02-21 18:47:21 +00:00
stripUrl = url + 'archives/%s'
firstStripUrl = stripUrl % '77'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%sarchives/\d+)' % rurl, after="prev"))
2013-02-21 18:47:21 +00:00
help = 'Index format: number'
2012-06-20 19:58:13 +00:00
class CaptainSNES(_BasicScraper):
url = 'http://www.captainsnes.com/'
rurl = escape(url)
stripUrl = url + '%s/'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '2001/07/10/the-mistake'
imageSearch = compile(tagre("img", "src", r"(%scomics/[^']+)" % rurl, quote="'"))
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl) + tagre("span", "class", "prev"))
2012-12-02 17:35:06 +00:00
multipleImagesPerStrip = True
2012-11-21 20:57:26 +00:00
help = 'Index format: yyyy/mm/dd/nnn-stripname'
2012-06-20 19:58:13 +00:00
2012-12-08 20:30:51 +00:00
class CaseyAndAndy(_BasicScraper):
url = 'http://www.galactanet.com/comic/'
stripUrl = url + 'view.php?strip=%s'
firstStripUrl = stripUrl % '1'
2012-12-08 20:30:51 +00:00
imageSearch = compile(tagre("img", "src", r'(Strip\d+\.gif)'))
prevSearch = compile(tagre("a", "href", r'(view\.php\?strip=\d+)')
+ tagre("img", "src", r'previous\.gif'))
help = 'Index format: number'
2013-04-10 16:36:33 +00:00
class CasuallyKayla(_BasicScraper):
url = 'http://casuallykayla.com/'
stripUrl = url + '?p=%s'
firstStripUrl = stripUrl % '89'
imageSearch = compile(tagre("img", "src", r'(http://casuallykayla\.com/comics/[^"]+)'))
prevSearch = compile(tagre("div", "class", r'nav-previous') + tagre("a", "href", r'([^"]+)'))
help = 'Index format: nnn'
2012-12-07 23:45:18 +00:00
class Catalyst(_BasicScraper):
baseUrl = "http://catalyst.spiderforest.com/"
rurl = escape(baseUrl)
url = baseUrl + "comic.php?comic_id=415"
2012-12-07 23:45:18 +00:00
stripUrl = baseUrl + "comic.php?comic_id=%s"
firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre("img", "src", r'((?:%s)?comics/[^"]+)' % rurl))
prevSearch = compile("<center>" + tagre("a", "href", r'(%scomic\.php\?comic_id=\d+)' % rurl))
2012-12-07 23:45:18 +00:00
help = 'Index format: number'
2013-04-10 16:36:33 +00:00
class CatAndGirl(_BasicScraper):
url = 'http://catandgirl.com/'
2013-04-10 21:57:09 +00:00
rurl = escape(url)
2013-04-10 16:36:33 +00:00
stripUrl = url + '?p=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1602'
imageSearch = compile(tagre("img", "src", r'(%sarchive/[^"]+)' % rurl))
2013-04-10 16:36:33 +00:00
prevSearch = compile(tagre("a", "href", r'([^"]+)')+r"[^<]+Previous</a>")
help = 'Index format: n (unpadded)'
2012-06-20 19:58:13 +00:00
class Catena(_BasicScraper):
url = 'http://catenamanor.com/'
2013-04-10 21:57:09 +00:00
rurl = escape(url)
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2003/06/17/the-start-of-it-all'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
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
2013-04-10 16:36:33 +00:00
class CatsAndCameras(_BasicScraper):
url = 'http://catsncameras.com/cnc/'
rurl = escape(url)
stripUrl = url + '?p=%s'
2013-04-11 16:27:43 +00:00
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
2013-04-10 16:36:33 +00:00
prevSearch = compile(tagre("div", "class", r'nav-previous') +
2013-04-11 16:27:43 +00:00
tagre("a", "href", r'(%s[^"]+)' % rurl))
2013-04-10 16:36:33 +00:00
help = 'Index format: nnn'
2013-02-06 21:08:36 +00:00
class ChainsawSuit(_BasicScraper):
url = 'http://chainsawsuit.com/'
rurl = escape(url)
2013-02-06 21:08:36 +00:00
stripUrl = url + '%s/'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '2008/03/12/strip-338'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+)' % rurl, after="prev"))
2013-02-06 21:08:36 +00:00
help = 'Index format: yyyy/mm/dd/stripname'
2013-04-10 16:36:33 +00:00
class Champ2010(_BasicScraper):
baseurl = 'http://jedcollins.com/champ2010/'
rurl = escape(baseurl)
# the latest URL is hard coded since the comic is discontinued
url = baseurl + 'champ-12-30-10.html'
stripUrl = baseurl + '%s.html'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % 'champ1-1-10-fuck'
2013-04-10 16:36:33 +00:00
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="Previous"))
help = 'Index format: yy-dd-mm'
2013-02-06 21:08:36 +00:00
class ChannelAte(_BasicScraper):
url = 'http://www.channelate.com/'
rurl = escape(url)
2013-02-06 21:08:36 +00:00
stripUrl = url + '%s/'
2013-04-11 16:27:43 +00:00
imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+)' % rurl, after="prev"))
2013-02-06 21:08:36 +00:00
help = 'Index format: yyyy/mm/dd/name'
2012-06-20 19:58:13 +00:00
class ChasingTheSunset(_BasicScraper):
url = 'http://www.fantasycomic.com/'
stripUrl = url + 'index.php?p=c%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
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):
url = 'http://www.checkerboardnightmare.com/'
stripUrl = url + 'd/%s.shtml'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '20001110'
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
2013-04-10 16:36:33 +00:00
class Chester5000XYV(_BasicScraper):
url = 'http://jessfink.com/Chester5000XYV/'
stripUrl = url + '?p=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '34'
2013-04-10 16:36:33 +00:00
imageSearch = compile(tagre("img", "src", r'(http://jessfink\.com/Chester5000XYV/comics/[^"]+)'))
prevSearch = compile(r'<a href="(.+?)"><span class="prev">')
help = 'Index format: nnn'
2012-06-20 19:58:13 +00:00
class Chisuji(_BasicScraper):
url = 'http://www.chisuji.com/'
2013-04-10 21:57:09 +00:00
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2009/05/02/chisujiposter01'
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'
2013-04-10 16:36:33 +00:00
class Chucklebrain(_BasicScraper):
url = 'http://www.chucklebrain.com/main.php'
starter = indirectStarter(url,
compile(tagre("a", "href", r'(/main\.php\?img\=\d+)', quote="'") +
tagre("img", "src", r'/images/last\.jpg', quote="'")))
stripUrl = url + '?img=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '19'
2013-04-10 16:36:33 +00:00
imageSearch = compile(tagre("img", "src", r'(/images/strip[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(/main\.php\?img\=\d+)', quote="'") +
tagre("img", "src", r'/images/previous\.jpg', quote="'"))
help = 'Index format: nnn'
2012-06-20 19:58:13 +00:00
class ChugworthAcademy(_BasicScraper):
url = 'http://chugworth.com/'
stripUrl = url + '?p=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '12'
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):
url = 'http://chugworth.com/archive/?strip_id=422'
2012-11-13 18:10:19 +00:00
stripUrl = 'http://chugworth.com/archive/?strip_id=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '0'
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):
url = 'http://www.cigarro.ca/'
stripUrl = url + '?p=%s'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r"(/comics/.+?)'")
prevSearch = compile(r'(/\?p=.+?)">&laq')
help = 'Index format: non'
2013-04-10 16:36:33 +00:00
class Collar6(_BasicScraper):
url = 'http://collar6.com/'
rurl = escape(url)
stripUrl = url + 'archive/%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % 'collar-6-187'
2013-04-10 16:36:33 +00:00
imageSearch = compile(tagre("img", "src", r'(%swp-content/webcomic/collar6/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%sarchive/[^"]+)' % rurl, after="previous"))
help = 'Index format: <name>'
2012-06-20 19:58:13 +00:00
class Comedity(_BasicScraper):
url = 'http://www.comedity.com/'
stripUrl = url + 'index.php?strip_id=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
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):
url = 'http://www.commissionedcomic.com/'
rurl = escape(url)
stripUrl = url + '?p=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '139'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev"))
2012-06-20 19:58:13 +00:00
help = 'Index format: n'
2013-04-10 21:57:09 +00:00
class CompanyY(_BasicScraper):
url = 'http://company-y.com/'
rurl = escape(url)
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2009/08/14/coming-soon'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("div", "class", r"nav-previous") +
tagre("a", "href", r'(%s[^"]+)' % rurl))
help = 'Index format: yyyy/mm/dd/strip-name'
2012-12-07 23:45:18 +00:00
class Concession(_BasicScraper):
url = 'http://concessioncomic.com/'
rurl = escape(url)
stripUrl = url + 'index.php?pid=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '20060701'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl, after="Comic"))
prevSearch = compile(tagre("a", "href", r'(%sindex\.php\?pid=\d+)' % rurl, after="nav-prev"))
2012-12-07 23:45:18 +00:00
help = 'Index format: number'
2012-06-20 19:58:13 +00:00
class CoolCatStudio(_BasicScraper):
url = 'http://www.coolcatstudio.com/'
rurl = escape(url)
2013-04-10 21:57:09 +00:00
stripUrl = url + 'strips-cat/%s'
firstStripUrl = stripUrl % 'first'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%sstrips-cat/[^"]+)' % rurl, before="prev"))
2013-04-10 21:57:09 +00:00
help = 'Index format: ccsyyyymmdd'
2012-06-20 19:58:13 +00:00
2013-04-10 16:36:33 +00:00
class CorydonCafe(_BasicScraper):
url = 'http://corydoncafe.com/'
starter = indirectStarter(url,
compile(tagre("a", "href", r'(\./\d+/[^"]+)')))
stripUrl = url + '%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'
@classmethod
def namer(cls, imageUrl, pageUrl):
return pageUrl.split('/')[-1].split('.')[0]
2012-06-20 19:58:13 +00:00
class CourtingDisaster(_BasicScraper):
url = 'http://www.courting-disaster.com/'
stripUrl = url + 'archive/%s.html'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '20050112'
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'
2013-04-10 16:36:33 +00:00
class CowboyJedi(_BasicScraper):
url = 'http://www.cowboyjedi.com/'
rurl = escape(url)
2013-04-10 21:57:09 +00:00
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2009/08/10/a-new-webcomic'
2013-04-10 16:36:33 +00:00
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="navi-prev"))
help = 'Index format: yyyy/mm/dd/strip-name'
2012-06-20 19:58:13 +00:00
class CrapIDrewOnMyLunchBreak(_BasicScraper):
url = 'http://crap.jinwicked.com/'
2013-04-10 21:57:09 +00:00
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2003/07/30/jin-and-josh-decide-to-move'
2012-11-14 19:23:30 +00:00
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):
url = 'http://www.cad-comic.com/cad/'
stripUrl = url + '%s'
2012-12-02 17:35:06 +00:00
imageSearch = compile(tagre("img", "src", r'(http://v\.cdn\.cad-comic\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'([^"]+)', after="nav-back"))
2012-06-20 19:58:13 +00:00
help = 'Index format: yyyymmdd'
class CtrlAltDelSillies(CtrlAltDel):
name = 'CtrlAltDel/Sillies'
url = 'http://www.cad-comic.com/sillies/'
stripUrl = url + '%s'
2012-11-14 19:23:30 +00:00
2012-06-20 19:58:13 +00:00
2013-04-10 16:36:33 +00:00
class CrimsonDark(_BasicScraper):
url = 'http://www.davidcsimon.com/crimsondark/'
stripUrl = url + 'index.php?view=comic&strip_id=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
2013-04-10 16:36:33 +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 CraftedFables(_BasicScraper):
url = 'http://www.craftedfables.com/'
2013-04-10 21:57:09 +00:00
baseurl = 'http://www.caf-fiends.net/'
rurl = escape(baseurl)
stripUrl = baseurl + 'craftedfables/?p=%s'
imageSearch = compile(tagre("img", "src", r'(%scraftedfables/comics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%scraftedfables/[^"]+)' % rurl) +
tagre("span", "class", r"prev"))
2013-04-10 16:36:33 +00:00
help = 'Index format: nnn'
class CucumberQuest(_BasicScraper):
url = 'http://cucumber.gigidigi.com/'
rurl = escape(url)
stripUrl = url + 'archive/%s/'
firstStripUrl = stripUrl % 'page-1'
starter = indirectStarter(url + 'recent.html',
compile(r'window\.location="(/archive/[^"]+/)"'))
imageSearch = compile(tagre("img", "src", r'(%swp-content/webcomic/cq/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%sarchive/[^"]+/)' % rurl, after="previous"))
help = 'Index format: stripname'
2012-06-20 19:58:13 +00:00
class Curvy(_BasicScraper):
url = 'http://www.c.urvy.org/'
stripUrl = url + '?date=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '20080329'
2012-11-21 20:57:26 +00:00
imageSearch = compile(tagre("img", "src", r'(/c/[^"]+)'))
2013-04-04 16:30:27 +00:00
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'
2013-04-04 16:30:27 +00:00
starter = bounceStarter(url,
compile(tagre("a", "href", r'(/\?date=\d+)') +
tagre("img", "src", "/nav/next\.png")))
def shouldSkipUrl(self, url):
"""Skip pages without images."""
return url in (
self.stripUrl % '20130402',
)
2012-06-20 19:58:13 +00:00
class CyanideAndHappiness(_BasicScraper):
url = 'http://www.explosm.net/comics/'
starter = bounceStarter(url, compile(tagre("a", "href", r"(/comics/\d+/)", before="next")))
stripUrl = url + '%s/'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '15'
imageSearch = compile(tagre("img", "src", r'(http://(?:www\.)?explosm\.net/db/files/[^"]+)', before="a daily webcomic"))
2012-11-21 20:57:26 +00:00
prevSearch = compile(tagre("a", "href", r'(/comics/\d+/)', before="prev"))
2012-06-20 19:58:13 +00:00
help = 'Index format: n (unpadded)'
def shouldSkipUrl(self, url):
"""Skip pages without images."""
2013-03-08 05:47:00 +00:00
return url in (self.stripUrl % "3082",)
@classmethod
def namer(cls, imageUrl, pageUrl):
imgname = imageUrl.split('/')[-1]
imgnum = pageUrl.split('/')[-2]
return '%s_%s' % (imgnum, imgname)