dosage/dosagelib/plugins/c.py

397 lines
14 KiB
Python
Raw Normal View History

# -*- coding: utf-8 -*-
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
2014-01-05 15:50:57 +00:00
# Copyright (C) 2012-2014 Bastian Kleineidam
# Copyright (C) 2015-2016 Tobias Gruetzmacher
2015-11-03 22:40:45 +00:00
from __future__ import absolute_import, division, print_function
2012-11-21 20:57:26 +00:00
from re import compile, escape
2012-06-20 19:58:13 +00:00
2015-05-20 10:58:13 +00:00
from ..scraper import _BasicScraper, _ParserScraper
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
from .common import _WordPressScraper, _ComicPressScraper
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'
2014-01-06 04:05:00 +00:00
class CampComic(_BasicScraper):
url = 'http://campcomic.com/comic/'
rurl = escape(url)
stripUrl = url + '%s'
firstStripUrl = stripUrl % '6'
imageSearch = compile(tagre("img", "src", r'(http://hw1\.pa-cdn\.com/camp/assets/img/katie/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, before="btn btnPrev"))
help = 'Index Format: number'
2013-02-21 18:47:21 +00:00
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
2013-04-25 18:40:15 +00:00
class Carciphona(_BasicScraper):
url = 'http://carciphona.com/'
imageSearch = compile(tagre("div", "style",
r'background-image:url\((_pages[^)]*)\)'))
prevSearch = compile(tagre("a", "href", r'(view\.php\?[^"]*)',
after="prevarea"))
latestSearch = compile(tagre("a", "href",
r'(view\.php\?page=[0-9]+[^"]*)'))
2013-04-25 18:40:15 +00:00
starter = indirectStarter(url, latestSearch)
@classmethod
def namer(cls, imageUrl, pageUrl):
ip = imageUrl.split('/')
return "volume_%s_page_%s" % (ip[-2], ip[-1])
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'))
2012-12-08 20:30:51 +00:00
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'([^"]+)'))
2013-04-10 16:36:33 +00:00
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))
prevSearch = compile(tagre("a", "href", r'([^"]+)') + r"[^<]+Previous</a>")
2013-04-10 16:36:33 +00:00
help = 'Index format: n (unpadded)'
2014-02-10 20:58:26 +00:00
def shouldSkipUrl(self, url, data):
2013-11-12 17:33:14 +00:00
"""Skip pages without images."""
return url in (
self.stripUrl % '4299',
)
class Catena(_WordPressScraper):
url = 'http://catenamanor.com/'
class CatNine(_WordPressScraper):
2015-11-02 22:29:56 +00:00
url = 'http://cat-nine.net'
firstStripUrl = 'http://cat-nine.net/comic/episode-1/first-day-for-everything/'
class CatsAndCameras(_WordPressScraper):
url = 'http://catsncameras.com/'
2015-07-30 10:16:34 +00:00
class CatVersusHuman(_ParserScraper):
url = 'http://www.catversushuman.com'
multipleImagesPerStrip = True
imageSearch = '//div[@class="post-body entry-content"]//img'
prevSearch = '//a[@class="blog-pager-older-link"]'
2013-04-10 16:36:33 +00:00
2015-05-26 07:53:04 +00:00
class ChainsawSuit(_ParserScraper):
2013-02-06 21:08:36 +00:00
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'
2015-05-26 07:53:04 +00:00
imageSearch = '//div[@id="comic"]//img'
prevSearch = '//img[@alt="previous"]/..'
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):
2013-04-13 18:58:00 +00:00
baseUrl = 'http://jedcollins.com/champ2010/'
rurl = escape(baseUrl)
2013-04-10 16:36:33 +00:00
# the latest URL is hard coded since the comic is discontinued
2013-04-13 18:58:00 +00:00
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"))
2013-04-10 16:36:33 +00:00
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/'
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'
2015-05-25 10:19:36 +00:00
class CheckerboardNightmare(_ParserScraper):
url = 'http://www.checkerboardnightmare.com/'
2015-05-25 10:19:36 +00:00
stripUrl = url + 'd/%s'
firstStripUrl = stripUrl % '20001110.html'
imageSearch = '//td[@colspan="4"]//img'
prevSearch = '//td[2]/a'
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'
2015-05-20 10:58:13 +00:00
class CigarroAndCerveja(_ParserScraper):
url = 'http://www.cigarro.ca/'
2015-05-20 10:58:13 +00:00
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'reacquaintance'
imageSearch = '//div[@id="comic"]//img',
prevSearch = '//a[contains(text()," Prev")]',
2012-06-20 19:58:13 +00:00
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"))
2013-04-10 16:36:33 +00:00
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))
2013-04-10 21:57:09 +00:00
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
2015-05-26 09:32:25 +00:00
class CorydonCafe(_ParserScraper):
2013-04-10 16:36:33 +00:00
url = 'http://corydoncafe.com/'
2015-05-26 09:32:25 +00:00
starter = indirectStarter(url, '//ul//a')
2013-04-10 16:36:33 +00:00
stripUrl = url + '%s.php'
2015-05-26 09:32:25 +00:00
imageSearch = "//center[2]//img"
prevSearch = '//a[@title="prev"]'
2013-04-10 16:36:33 +00:00
help = 'Index format: yyyy/stripname'
@classmethod
def namer(cls, imageUrl, pageUrl):
return pageUrl.split('/')[-1].split('.')[0]
class CourtingDisaster(_WordPressScraper):
url = 'http://www.courting-disaster.com/'
firstStripUrl = 'http://www.courting-disaster.com/comic/courting-disaster-17/'
class CowboyJedi(_WordPressScraper):
url = 'http://www.cowboyjedi.com/'
class CraftedFables(_ComicPressScraper):
url = 'http://www.caf-fiends.net/comicpress/'
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 CrimsonDark(_BasicScraper):
url = 'http://www.davidcsimon.com/crimsondark/'
stripUrl = url + 'index.php?view=comic&strip_id=%s'
firstStripUrl = stripUrl % '1'
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)'
2012-06-20 19:58:13 +00:00
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'
2013-04-25 17:01:21 +00:00
@classmethod
def namer(cls, imageUrl, pageUrl):
"""Remove random junk from image names."""
imgname = imageUrl.split('/')[-1]
imgbase = imgname.rsplit('-', 1)[0]
imgext = imgname.rsplit('.', 1)[1]
return '%s.%s' % (imgbase, imgext)
2012-06-20 19:58:13 +00:00
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 CucumberQuest(_BasicScraper):
url = 'http://cucumber.gigidigi.com/'
rurl = escape(url)
2013-04-28 17:58:38 +00:00
stripUrl = url + 'cq/%s/'
2013-04-10 16:36:33 +00:00
firstStripUrl = stripUrl % 'page-1'
starter = indirectStarter(url + 'recent.html',
compile(r'window\.location="(/cq/[^"]+/)"'))
2013-04-28 17:58:38 +00:00
imageSearch = (
compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/\d+[^"]+)' % rurl)),
compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/ch\d+[^"]+)' % rurl)),
compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/bonus[^"]+)' % rurl)),
)
prevSearch = compile(tagre("a", "href", r'(%scq/[^"]+/)' % rurl, after="previous"))
2013-04-10 16:36:33 +00:00
help = 'Index format: stripname'
2013-04-25 18:46:05 +00:00
class Curtailed(_BasicScraper):
url = 'http://curtailedcomic.com/'
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2012/04/08/sneeze'
rurl = escape(url)
imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/[0-9]+/[^"]*)' % rurl))
prevSearch = compile('<a href="([^"]*)" class="comic-nav-base comic-nav-previous"')
2013-04-25 18:46:05 +00:00
help = 'Index format: yyyy/mm/dd/stripname'
2015-05-26 07:47:31 +00:00
class Curvy(_ParserScraper):
url = 'http://www.c.urvy.org/'
stripUrl = url + '?date=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '20080329'
2015-05-26 07:47:31 +00:00
imageSearch = '//div[@id="theActualComic"]//img'
prevSearch = '//div[@class="aNavbar"]//p[2]/a'
2012-06-20 19:58:13 +00:00
help = 'Index format: yyyymmdd'
class CyanideAndHappiness(_BasicScraper):
url = 'http://www.explosm.net/comics/'
starter = bounceStarter(url, compile(tagre("a", "href", r"(/comics/\d+/)", after="next-comic")))
stripUrl = url + '%s/'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '15'
imageSearch = compile(tagre("img", "src", r'(//files.explosm.net/comics/[^"]+)', before="main-comic"))
prevSearch = compile(tagre("a", "href", r'(/comics/\d+/)', after="previous-comic"))
2012-06-20 19:58:13 +00:00
help = 'Index format: n (unpadded)'
2014-02-10 20:58:26 +00:00
def shouldSkipUrl(self, url, data):
"""Skip pages without images."""
return "/comics/play-button.png" in data[0]
@classmethod
def namer(cls, imageUrl, pageUrl):
imgname = imageUrl.split('/')[-1]
# only get the first 100 chars for the image name
imgname = imgname[:100]
imgnum = pageUrl.split('/')[-2]
return '%s_%s' % (imgnum, imgname)