dosage/dosagelib/plugins/n.py

231 lines
7.8 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
2016-05-05 18:55:14 +00:00
from ..scraper import _BasicScraper, _ParserScraper
from ..helpers import indirectStarter, bounceStarter
2012-11-21 20:57:26 +00:00
from ..util import tagre
from .common import _ComicControlScraper, _WordPressScraper, _WPNavi, _WPWebcomic
2012-06-20 19:58:13 +00:00
class Namesake(_ComicControlScraper):
2013-03-03 21:41:11 +00:00
url = 'http://namesakecomic.com/'
2019-09-08 00:45:52 +00:00
stripUrl = url + 'comic/%s'
firstStripUrl = stripUrl % 'the-journey-begins'
2013-03-03 21:41:11 +00:00
2013-07-10 16:43:53 +00:00
class NatalieDee(_BasicScraper):
url = 'http://www.nataliedee.com/'
rurl = escape(url)
2013-07-18 18:39:53 +00:00
stripUrl = url + '%s'
2013-07-10 16:43:53 +00:00
firstStripUrl = stripUrl % '022806'
imageSearch = compile(tagre("img", "src", r'(%s\d+/[^"]+)' % rurl,
before="overflow"))
2013-07-10 16:43:53 +00:00
prevSearch = compile(tagre("a", "href", r'([^"]+)') + "<< Yesterday")
help = 'Index format: mmddyy'
def namer(self, image_url, page_url):
unused, date, filename = image_url.rsplit('/', 2)
2013-07-10 16:43:53 +00:00
return '%s-%s' % (date, filename)
class Nedroid(_WordPressScraper):
url = 'http://nedroid.com/'
prevSearch = '//a[@rel="prev"]'
2019-07-06 06:47:53 +00:00
class NeoCTC(_ParserScraper):
url = 'http://www.hirezfox.com/neoctc/'
stripUrl = url + 'd/%s.html'
firstStripUrl = stripUrl % '20071205'
imageSearch = '//img[contains(@src, "neoctc/comics")]'
prevSearch = '//a[./img[@alt="Previous Day"]]'
multipleImagesPerStrip = True
2012-06-20 19:58:13 +00:00
class NeoEarth(_BasicScraper):
url = 'http://www.neo-earth.com/NE/'
stripUrl = url + 'index.php?date=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '2007-03-23'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'<img src="(strips/.+?)"')
prevSearch = compile(r'<a href="(.+?)">Previous</a>')
help = 'Index format: yyyy-mm-dd'
class NerfNow(_WordPressScraper):
url = 'https://www.nerfnow.com/'
prevSearch = '//li[@id="nav_previous"]/a'
2019-07-10 08:05:36 +00:00
class Newshounds(_ParserScraper):
stripUrl = 'http://www.newshounds.com/%s.html'
url = stripUrl % 'nh2/20140929'
firstStripUrl = stripUrl % 'nh1/19971101'
imageSearch = '//img[@class="ksc"]'
prevSearch = '//a[./img[@alt="Previous comic"]]'
endOfLife = True
def getPrevUrl(self, url, data):
# Add navigation link between comic and graphic novel
if url == self.stripUrl % 'nh2/20070201':
return self.stripUrl % 'nh1/20061208'
return super(Newshounds, self).getPrevUrl(url, data)
2019-07-10 08:05:36 +00:00
class NewWorld(_WordPressScraper):
url = ('https://web.archive.org/web/20190718012133/'
'http://www.tfsnewworld.com/')
2013-04-10 21:57:09 +00:00
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2007/08/30/63'
prevSearch = '//a[@rel="prev"]'
endOfLife = True
2012-06-20 19:58:13 +00:00
help = 'Index format: yyyy/mm/dd/stripn'
2020-09-13 15:04:02 +00:00
class NeverSatisfied(_ComicControlScraper):
url = 'https://www.neversatisfiedcomic.com/'
stripUrl = url + 'comic/%s'
firstStripUrl = stripUrl % 'never-satisfied'
2012-06-20 19:58:13 +00:00
class NichtLustig(_BasicScraper):
url = 'https://joscha.com/'
starter = bounceStarter
stripUrl = url + 'nichtlustig/%s/'
firstStripUrl = stripUrl % '000501'
2013-03-08 21:33:05 +00:00
lang = 'de'
imageSearch = compile(tagre("img", "src", r'(https://joscha.com/data/media/cartoons/[0-9a-f-_]+.png)'))
prevSearch = compile(tagre("a", "href", r'(https://joscha.com/nichtlustig/\d+/)', after="next"))
nextSearch = compile(tagre("a", "href", r'(https://joscha.com/nichtlustig/\d+/)', after="prev"))
2012-06-20 19:58:13 +00:00
help = 'Index format: yymmdd'
def namer(self, image_url, page_url):
unused, filename, unused2 = page_url.rsplit('/', 2)
return '%s' % (filename)
2012-06-20 19:58:13 +00:00
2017-05-21 23:17:05 +00:00
class Nicky510(_WPNavi):
url = ('https://web.archive.org/web/20160510215718/'
'http://www.nickyitis.com/')
endOfLife = True
2020-06-20 04:34:49 +00:00
class Nightshift(_WPWebcomic):
2020-04-29 07:43:55 +00:00
url = 'https://poecatcomix.com/nightshift-static/'
2020-06-20 04:34:49 +00:00
stripUrl = 'https://poecatcomix.com/nightshift/%s/'
firstStripUrl = stripUrl % 'ns-cover'
imageSearch = '//div[contains(@class, "webcomic-media")]//img'
2019-06-30 02:46:15 +00:00
adult = True
2020-04-29 07:43:55 +00:00
def starter(self):
2020-06-20 04:34:49 +00:00
# Build list of chapters for naming
2020-04-29 07:43:55 +00:00
indexPage = self.getPage(self.url)
self.chapters = indexPage.xpath('//a[./img[contains(@class, "attachment-large")]]/@href')
2020-06-20 04:34:49 +00:00
latestPage = self.chapters[0]
self.chapters = self.chapters[1:]
self.currentChapter = len(self.chapters)
return latestPage
2020-04-29 07:43:55 +00:00
2019-06-30 02:46:15 +00:00
def namer(self, imageUrl, pageUrl):
2020-06-20 04:34:49 +00:00
page = pageUrl.rstrip('/').rsplit('/', 1)[-1]
page = page.replace('blood-brothers', 'bloodbrothers').replace('bb-2', 'bb2').replace('ns7-', 'page-')
filename = 'ns%d-%s.%s' % (self.currentChapter, page, imageUrl.rsplit('.', 1)[-1])
if pageUrl in self.chapters:
self.currentChapter = self.currentChapter - 1
return filename
2019-06-30 02:46:15 +00:00
class Nimona(_ParserScraper):
url = ('https://web.archive.org/web/20141008095502/'
'http://gingerhaze.com/nimona/')
2016-05-05 18:55:14 +00:00
stripUrl = url + 'comic/%s'
firstStripUrl = stripUrl % "page-1"
imageSearch = '//div[d:class("field-name-field-comic-page")]//img'
prevSearch = '//a[img[contains(@src, "/comicdrop_prev_label")]]'
2014-12-08 13:28:37 +00:00
endOfLife = True
2019-06-20 06:26:48 +00:00
class NineToNine(_ParserScraper):
url = 'https://www.tigerknight.com/99'
stripUrl = url + '/%s'
firstStripUrl = stripUrl % '2014-01-01'
imageSearch = '//img[@class="comic-image"]'
prevSearch = '//a[@class="prev"]'
multipleImagesPerStrip = True
2012-06-20 19:58:13 +00:00
class NobodyScores(_BasicScraper):
url = 'http://nobodyscores.loosenutstudio.com/'
rurl = escape(url)
stripUrl = url + 'index.php?id=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '4'
imageSearch = compile(tagre("img", "src", r'(%scomix/[^"]+)' % rurl))
2012-12-04 06:02:40 +00:00
multipleImagesPerStrip = True
prevSearch = compile(r'<a href="(%sindex.php.+?)">the one before </a>' % rurl)
2012-06-20 19:58:13 +00:00
help = 'Index format: nnn'
2013-03-06 19:21:10 +00:00
class NoMoreSavePoints(_WordPressScraper):
url = 'http://www.flowerlarkstudios.com/comicpage/no-more-save-points/mushroom-hopping/'
firstStripUrl = url
starter = indirectStarter
2016-05-05 18:55:14 +00:00
class NoNeedForBushido(_ParserScraper):
2013-11-12 17:33:14 +00:00
url = 'http://nn4b.com/'
2016-05-05 18:55:14 +00:00
stripUrl = url + 'comic/%s'
imageSearch = '//div[@id="comic-image"]//img'
prevSearch = '//a[@rel="prev"]'
2013-11-12 17:33:14 +00:00
help = 'Index format: nnn'
2013-03-06 19:21:10 +00:00
2019-07-14 09:14:07 +00:00
class NonPlayerCharacter(_ParserScraper):
url = 'https://www.lfg.co/'
stripUrl = url + 'npc/tale/%s/'
firstStripUrl = stripUrl % '1-1'
imageSearch = '//div[@id="comic-img"]//img'
prevSearch = '//a[@class="comic-nav-prev"]'
latestSearch = '//div[@id="feature-npc-footer"]/a[contains(@href, "npc/tale/")]'
starter = indirectStarter
def namer(self, imageUrl, pageUrl):
return pageUrl.rstrip('/').rsplit('/', 1)[-1]
class NotAVillain(_WPWebcomic):
2019-06-21 06:51:39 +00:00
url = 'http://navcomic.com/'
stripUrl = url + 'not-a-villain/%s/'
firstStripUrl = stripUrl % 'v1-001'
def namer(self, imageUrl, pageUrl):
filename = imageUrl.rsplit('/', 1)[-1]
# Fix filenames missing "Page"
if filename[2].isdigit():
filename = filename[0] + '-Page' + filename[2:]
# Fix filenames of early comics
filename = filename.replace('Page-', '1-Page')
if filename.startswith('0-Page'):
filename = '1' + filename[1:]
return filename
2016-05-05 18:55:14 +00:00
class NotInventedHere(_ParserScraper):
url = 'http://notinventedhe.re/'
2016-05-05 18:55:14 +00:00
stripUrl = url + 'on/%s'
firstStripUrl = stripUrl % '2009-9-21'
imageSearch = '//div[@id="comic-content"]//img'
prevSearch = '//a[@id="nav-previous"]'
help = 'Index format: yyyy-m-d'
2013-03-06 19:21:10 +00:00
2013-03-06 19:21:10 +00:00
class Nukees(_BasicScraper):
url = 'http://www.nukees.com/'
stripUrl = url + 'd/%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '19970121'
2013-03-06 19:21:10 +00:00
imageSearch = compile(r'"comic".+?"(/comics/.+?)"')
prevSearch = compile(r'"(/d/.+?)".+?previous')
help = 'Index format: yyyymmdd.html'