2016-03-31 21:13:54 +00:00
|
|
|
# -*- coding: utf-8 -*-
|
2012-06-20 20:41:04 +00:00
|
|
|
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
|
2014-01-05 15:50:57 +00:00
|
|
|
# Copyright (C) 2012-2014 Bastian Kleineidam
|
2016-03-31 21:13:54 +00:00
|
|
|
# Copyright (C) 2015-2016 Tobias Gruetzmacher
|
2012-06-20 19:58:13 +00:00
|
|
|
|
2016-03-31 21:13:54 +00:00
|
|
|
from __future__ import absolute_import, division, print_function
|
2016-04-03 20:58:01 +00:00
|
|
|
|
2013-04-10 16:19:11 +00:00
|
|
|
from re import compile, escape
|
2016-04-03 20:58:01 +00:00
|
|
|
|
2015-05-14 10:42:04 +00:00
|
|
|
from ..scraper import _BasicScraper, _ParserScraper
|
|
|
|
from ..helpers import indirectStarter
|
2012-11-21 20:57:26 +00:00
|
|
|
from ..util import tagre
|
2016-04-10 21:04:34 +00:00
|
|
|
from .common import (_ComicControlScraper, _WordPressScraper, WP_LATEST_SEARCH,
|
|
|
|
xpath_class)
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2016-04-03 22:12:53 +00:00
|
|
|
class Namesake(_ComicControlScraper):
|
2013-03-03 21:41:11 +00:00
|
|
|
url = 'http://namesakecomic.com/'
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class NamirDeiter(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.namirdeiter.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-02-04 20:00:26 +00:00
|
|
|
stripUrl = url + 'comics/index.php?date=%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '19991128'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r"'?(%scomics/\d+\.jpg)'?" % rurl, quote=""))
|
2016-04-01 22:14:31 +00:00
|
|
|
prevSearch = compile(tagre("a", "href", r'(%scomics/index\.php\?date=\d+)' % rurl, quote="'") + "Previous")
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: yyyymmdd'
|
|
|
|
|
|
|
|
|
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'
|
2016-03-31 21:13:54 +00:00
|
|
|
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'
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
def namer(cls, imageUrl, pageUrl):
|
|
|
|
unused, date, filename = imageUrl.rsplit('/', 2)
|
|
|
|
return '%s-%s' % (date, filename)
|
|
|
|
|
|
|
|
|
2016-04-01 22:14:31 +00:00
|
|
|
class Nedroid(_WordPressScraper):
|
|
|
|
url = 'http://nedroid.com/'
|
|
|
|
prevSearch = '//a[@rel="prev"]'
|
|
|
|
|
|
|
|
|
2016-03-31 21:13:54 +00:00
|
|
|
class NekkoAndJoruba(_BasicScraper):
|
|
|
|
url = 'http://www.nekkoandjoruba.com/'
|
|
|
|
stripUrl = url + '?p=%s'
|
|
|
|
firstStripUrl = stripUrl % '7'
|
|
|
|
imageSearch = compile(r'<img src="(http://www\.nekkoandjoruba\.com/comics/.+?)"')
|
|
|
|
prevSearch = compile(r'<a href="(.+?)">‹</a>')
|
|
|
|
help = 'Index format: nnn'
|
|
|
|
|
|
|
|
|
|
|
|
class NekoTheKitty(_ParserScraper):
|
|
|
|
url = 'http://www.nekothekitty.net/'
|
|
|
|
stripUrl = url + 'comics/%s'
|
|
|
|
firstStripUrl = stripUrl % '936393/001-video-games'
|
|
|
|
imageSearch = '//a[@id="comic_image"]/img'
|
|
|
|
prevSearch = '//a[text()="<-"]'
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class NeoEarth(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
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'
|
|
|
|
|
|
|
|
|
2016-04-01 22:14:31 +00:00
|
|
|
class NerfNow(_WordPressScraper):
|
|
|
|
url = 'https://www.nerfnow.com/'
|
|
|
|
prevSearch = '//li[@id="nav_previous"]/a'
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class NewAdventuresOfBobbin(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.bobbin-comic.com/bobbin_strips/'
|
2012-11-21 20:57:26 +00:00
|
|
|
imageSearch = compile(tagre("a", "href", r'(\d+\.gif)'))
|
2012-12-07 23:45:18 +00:00
|
|
|
multipleImagesPerStrip = True
|
2012-11-21 20:57:26 +00:00
|
|
|
help = 'Index format: none'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
|
|
|
class NewWorld(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.tfsnewworld.com/'
|
2013-04-10 21:57:09 +00:00
|
|
|
stripUrl = url + '%s/'
|
|
|
|
firstStripUrl = stripUrl % '2007/08/30/63'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'<img src="(http://www.tfsnewworld.com/comics/.+?)"')
|
|
|
|
prevSearch = compile(r'<div class="nav-previous"><a href="([^"]+)" rel="prev">')
|
|
|
|
help = 'Index format: yyyy/mm/dd/stripn'
|
|
|
|
|
|
|
|
|
|
|
|
class NichtLustig(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.nichtlustig.de/main.html'
|
2012-12-04 06:02:40 +00:00
|
|
|
stripUrl = 'http://static.nichtlustig.de/toondb/%s.html'
|
2013-03-08 21:33:05 +00:00
|
|
|
lang = 'de'
|
2012-11-21 20:57:26 +00:00
|
|
|
imageSearch = compile('background-image:url\((http://static\.nichtlustig\.de/comics/full/\d+\.jpg)')
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(http://static\.nichtlustig\.de/toondb/\d+\.html)'))
|
2016-04-12 21:11:39 +00:00
|
|
|
latestSearch = compile(tagre("a", "href", r'([^"]*toondb/\d+\.html)'))
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: yymmdd'
|
2016-04-12 21:11:39 +00:00
|
|
|
starter = indirectStarter()
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2016-04-01 22:14:31 +00:00
|
|
|
class Nicky510(_WordPressScraper):
|
|
|
|
url = 'http://www.nickyitis.com/'
|
2016-04-10 21:04:34 +00:00
|
|
|
prevSearch = '//a[%s]' % xpath_class('navi-prev')
|
2016-04-01 22:14:31 +00:00
|
|
|
|
|
|
|
|
2014-12-08 13:28:37 +00:00
|
|
|
class Nimona(_BasicScraper):
|
|
|
|
url = 'http://gingerhaze.com/nimona/'
|
|
|
|
stripUrl = url + '%s/'
|
|
|
|
firstStripUrl = stripUrl % "comic/page-1"
|
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://gingerhaze\.com/sites/default/files/nimona-pages/.+?)'))
|
|
|
|
prevSearch = compile(r'<a href="(/nimona/comic/[^"]+)"><img src="http://gingerhaze\.com/sites/default/files/comicdrop/comicdrop_prev_label_file\.png"')
|
|
|
|
help = 'Index format: stripname'
|
|
|
|
endOfLife = True
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class NobodyScores(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://nobodyscores.loosenutstudio.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-02-04 20:00:26 +00:00
|
|
|
stripUrl = url + 'index.php?id=%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '4'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%scomix/[^"]+)' % rurl))
|
2012-12-04 06:02:40 +00:00
|
|
|
multipleImagesPerStrip = True
|
2013-04-10 16:19:11 +00:00
|
|
|
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
|
|
|
|
|
|
|
|
2016-04-03 20:58:01 +00:00
|
|
|
class NoMoreSavePoints(_WordPressScraper):
|
|
|
|
url = 'http://www.flowerlarkstudios.com/comic/no-more-save-points/mushroom-hopping/'
|
|
|
|
firstStripUrl = url
|
2016-04-12 21:11:39 +00:00
|
|
|
latestSearch = WP_LATEST_SEARCH
|
|
|
|
starter = indirectStarter()
|
2016-04-03 20:58:01 +00:00
|
|
|
|
|
|
|
|
2013-03-06 19:21:10 +00:00
|
|
|
class NoNeedForBushido(_BasicScraper):
|
2013-11-12 17:33:14 +00:00
|
|
|
url = 'http://nn4b.com/'
|
|
|
|
rurl = escape(url)
|
|
|
|
stripUrl = url + '?webcomic1=%s'
|
|
|
|
imageSearch = compile(
|
|
|
|
tagre("a", "rel", "next") +
|
|
|
|
tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/[^"]+)' % rurl,
|
2016-03-31 21:13:54 +00:00
|
|
|
after="attachment-full"))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%s\?webcomic1=[^"]+)' % rurl,
|
|
|
|
after="previous-webcomic"))
|
2016-04-12 21:11:39 +00:00
|
|
|
latestSearch = compile(tagre("a", "href", r'(%s\?webcomic1=[^"]+)' % rurl,
|
|
|
|
after="last-webcomic"))
|
2013-11-12 17:33:14 +00:00
|
|
|
help = 'Index format: nnn'
|
2016-04-12 21:11:39 +00:00
|
|
|
starter = indirectStarter()
|
2016-03-31 21:13:54 +00:00
|
|
|
|
2013-03-06 19:21:10 +00:00
|
|
|
|
2013-12-10 18:50:21 +00:00
|
|
|
class NotInventedHere(_BasicScraper):
|
|
|
|
url = 'http://notinventedhe.re/'
|
|
|
|
rurl = escape(url)
|
|
|
|
stripUrl = url + '%s/'
|
|
|
|
firstStripUrl = stripUrl % 'on/2009-9-21'
|
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://thiswas.notinventedhe.re/on/\d+-\d+-\d+)'))
|
2016-04-01 22:14:31 +00:00
|
|
|
prevSearch = compile(tagre("a", "href", r'(/on/\d+-\d+-\d+)') +
|
|
|
|
'\s*Previous')
|
2013-12-10 18:50:21 +00:00
|
|
|
help = 'Index format: yyyy-mm-dd'
|
2013-03-06 19:21:10 +00:00
|
|
|
|
2016-03-31 21:13:54 +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'
|