dosage/dosagelib/plugins/o.py

171 lines
5.5 KiB
Python
Raw Normal View History

# SPDX-License-Identifier: MIT
2016-10-28 22:21:41 +00:00
# Copyright (C) 2004-2008 Tristan Seligmann and Jonathan Jacobs
2014-01-05 15:50:57 +00:00
# Copyright (C) 2012-2014 Bastian Kleineidam
# Copyright (C) 2015-2020 Tobias Gruetzmacher
# Copyright (C) 2019-2020 Daniel Ring
from re import compile, escape
2019-07-03 07:32:45 +00:00
from ..helpers import bounceStarter, indirectStarter
2015-04-26 11:32:22 +00:00
from ..scraper import _BasicScraper, _ParserScraper
2014-03-26 18:59:42 +00:00
from ..util import tagre
from .common import _WordPressScraper, _WPNavi
2012-06-20 19:58:13 +00:00
2015-05-14 11:06:12 +00:00
class OctopusPie(_ParserScraper):
url = 'http://www.octopuspie.com/'
rurl = escape(url)
2013-04-10 21:57:09 +00:00
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2007-05-14/001-pea-wiggle'
2015-05-14 11:06:12 +00:00
imageSearch = '//img[@title]'
prevSearch = '//a[@rel="prev"]'
2012-06-20 19:58:13 +00:00
help = 'Index format: yyyy-mm-dd/nnn-strip-name'
2019-07-03 07:32:45 +00:00
class OffWhite(_ParserScraper):
stripUrl = 'http://off-white.eu/comic/%s/'
firstStripUrl = stripUrl % 'prologue-page-1-2'
url = firstStripUrl
imageSearch = '//img[@class="comic-page"]'
prevSearch = '//a[@rel="prev"]'
latestSearch = '//a[text()="A"]'
starter = indirectStarter
endOfLife = True
def fetchUrls(self, url, data, urlSearch):
# Fix missing page
if url == self.stripUrl % 'page-37':
return ['http://off-white.eu/ow_v2/wp-content/uploads/2011/01/new-037.jpg']
return super(OffWhite, self).fetchUrls(url, data, urlSearch)
def getPrevUrl(self, url, data):
# Fix missing page
if url == self.stripUrl % 'page-37':
return self.stripUrl % 'page-36'
return super(OffWhite, self).getPrevUrl(url, data)
class Oglaf(_ParserScraper):
2013-03-06 19:21:10 +00:00
url = 'http://oglaf.com/'
stripUrl = url + '%s/'
firstStripUrl = stripUrl % 'cumsprite'
imageSearch = '//img[@id="strip"]'
prevSearch = '//a[@rel="prev"]'
nextSearch = '//a[@rel="next"]'
multipleImagesPerStrip = True
2013-04-04 16:30:02 +00:00
adult = True
def fetchUrls(self, url, data, search):
urls = []
urls.extend(super(Oglaf, self).fetchUrls(url, data, search))
if search == self.imageSearch:
try:
nexturls = self.fetchUrls(url, data, self.nextSearch)
except ValueError:
pass
else:
while nexturls and nexturls[0].startswith(url):
data = self.getPage(nexturls[0])
urls.extend(super(Oglaf, self).fetchUrls(nexturls, data, search))
nexturls = self.fetchUrls(url, data, self.nextSearch)
return urls
2013-03-06 19:21:10 +00:00
2017-05-21 23:17:05 +00:00
class OhJoySexToy(_WPNavi):
2014-01-31 03:45:50 +00:00
url = 'http://www.ohjoysextoy.com/'
firstStripUrl = url + 'introduction/'
textSearch = '//div[@id="comic"]//img/@alt'
2014-01-31 03:45:50 +00:00
adult = True
2013-03-06 19:21:10 +00:00
class OkCancel(_BasicScraper):
url = 'http://okcancel.com/'
rurl = escape(url)
2013-03-06 19:21:10 +00:00
stripUrl = url + 'comic/%s.html'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre("img", "src", r'(%sstrips/okcancel\d{8}\.gif)' % rurl))
prevSearch = compile(tagre("div", "class", "previous") +
tagre("a", "href", r'(%scomic/\d{1,4}\.html)' % rurl))
2013-03-06 19:21:10 +00:00
help = 'Index format: yyyymmdd'
2015-04-26 11:32:22 +00:00
class OmakeTheater(_ParserScraper):
2016-05-05 18:55:14 +00:00
url = 'http://omaketheater.com/comic/'
stripUrl = url + '%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
2015-04-26 11:32:22 +00:00
css = True
imageSearch = ".comicImage img"
prevSearch = ".previous a"
2013-02-06 21:27:40 +00:00
help = 'Index format: number (unpadded)'
class OnTheEdge(_WordPressScraper):
url = 'http://ontheedgecomics.com/'
firstStripUrl = 'http://ontheedgecomics.com/comic/ote0001/'
2016-10-30 09:57:50 +00:00
class OopsComicAdventure(_WordPressScraper):
url = ('https://web.archive.org/web/20190102215141/'
'http://oopscomicadventure.com/')
endOfLife = True
2016-10-30 09:57:50 +00:00
2017-05-21 23:17:05 +00:00
class Optipess(_WPNavi):
2014-09-29 02:41:29 +00:00
url = 'http://www.optipess.com/'
firstStripUrl = url + '2008/12/01/jason-friend-of-the-butterflies/'
textSearch = '//div[@id="comic"]//img/@alt'
2016-05-16 21:16:29 +00:00
textOptional = True
2014-09-29 02:41:29 +00:00
2019-06-20 05:01:12 +00:00
class OrderOfTheBlackDog(_WordPressScraper):
url = 'http://orderoftheblackdog.com/'
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'issue-1-cover'
starter = bounceStarter
def namer(self, imageUrl, pageUrl):
# Fix inconsistent filenames
return '%s.%s' % (pageUrl.rsplit('/', 2)[-2], imageUrl.rsplit('.', 1)[-1])
2019-06-13 02:22:28 +00:00
class OriginalLife(_ParserScraper):
2020-10-01 01:22:43 +00:00
url = 'https://web.archive.org/web/20200201203404/http://jaynaylor.com/originallife/'
2019-06-13 02:22:28 +00:00
stripUrl = url + 'archives/%s.html'
firstStripUrl = stripUrl % '2009/06/001'
imageSearch = '//img[contains(@src, "/originallife/comic/")]'
prevSearch = '//a[contains(text(), "Previous")]'
2020-04-19 08:50:00 +00:00
adult = True
2020-07-07 07:47:56 +00:00
endOfLife = True
2019-06-13 02:22:28 +00:00
2017-02-12 01:16:38 +00:00
class OurHomePlanet(_ParserScraper):
url = 'http://www.ourhomeplanet.net/'
stripUrl = url + 'comic/%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '01'
2017-02-12 01:16:38 +00:00
imageSearch = '//a[@rel="next"]/img'
prevSearch = '//a[@rel="prev"]'
2012-06-20 19:58:13 +00:00
help = 'Index format: n (unpadded)'
2019-06-21 08:10:11 +00:00
class OutOfPlacers(_WordPressScraper):
url = 'http://www.valsalia.com/'
stripUrl = url + 'comic/%s/'
2019-06-21 08:10:11 +00:00
firstStripUrl = stripUrl % 'prologue/01'
2020-04-19 08:50:00 +00:00
adult = True
2019-06-21 08:10:11 +00:00
2012-06-20 19:58:13 +00:00
class OverCompensating(_BasicScraper):
url = 'http://www.overcompensating.com/'
2013-11-12 17:33:14 +00:00
stripUrl = url + 'oc/index.php?comic=%s'
2013-07-18 18:39:53 +00:00
firstStripUrl = stripUrl % '0'
2013-11-12 17:33:14 +00:00
imageSearch = compile(tagre("img", "src", r'(/oc/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(/oc/index\.php\?comic=\d+)',
after="go back"))
2013-07-18 18:39:53 +00:00
help = 'Index format: number'
2019-07-12 05:37:55 +00:00
class OzyAndMillie(_WordPressScraper):
stripUrl = 'https://ozyandmillie.org/comic/%s/'
url = stripUrl % 'ozy-and-millie-2131'
firstStripUrl = stripUrl % 'ozy-and-millie-2'
endOfLife = True