# -*- coding: utf-8 -*- # Copyright (C) 2004-2008 Tristan Seligmann and Jonathan Jacobs # Copyright (C) 2012-2014 Bastian Kleineidam # Copyright (C) 2015-2019 Tobias Gruetzmacher from __future__ import absolute_import, division, print_function from re import compile, escape from ..scraper import _BasicScraper, _ParserScraper from ..helpers import indirectStarter from ..util import tagre from .common import _ComicControlScraper, _WordPressScraper, _WPNavi class Namesake(_ComicControlScraper): url = 'http://namesakecomic.com/' stripUrl = url + 'comic/%s' firstStripUrl = stripUrl % 'the-journey-begins' class NamirDeiter(_ParserScraper): baseUrl = 'https://www.namirdeiter.com/comics/' stripUrl = baseUrl + 'index.php?date=%s' url = stripUrl % '20150410' firstStripUrl = baseUrl imageSearch = '//a/img' prevSearch = '//a[text()="Previous"]' endOfLife = True help = 'Index format: yyyymmdd' class NatalieDee(_BasicScraper): url = 'http://www.nataliedee.com/' rurl = escape(url) stripUrl = url + '%s' firstStripUrl = stripUrl % '022806' imageSearch = compile(tagre("img", "src", r'(%s\d+/[^"]+)' % rurl, before="overflow")) 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) return '%s-%s' % (date, filename) class Nedroid(_WordPressScraper): url = 'http://nedroid.com/' prevSearch = '//a[@rel="prev"]' 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 class NeoEarth(_BasicScraper): url = 'http://www.neo-earth.com/NE/' stripUrl = url + 'index.php?date=%s' firstStripUrl = stripUrl % '2007-03-23' imageSearch = compile(r'Previous') help = 'Index format: yyyy-mm-dd' class NerfNow(_WordPressScraper): url = 'https://www.nerfnow.com/' prevSearch = '//li[@id="nav_previous"]/a' class NewWorld(_BasicScraper): url = 'http://www.tfsnewworld.com/' stripUrl = url + '%s/' firstStripUrl = stripUrl % '2007/08/30/63' imageSearch = compile(r'the one before ' % rurl) help = 'Index format: nnn' class NoMoreSavePoints(_WordPressScraper): url = 'http://www.flowerlarkstudios.com/comicpage/no-more-save-points/mushroom-hopping/' firstStripUrl = url starter = indirectStarter class NoNeedForBushido(_ParserScraper): url = 'http://nn4b.com/' stripUrl = url + 'comic/%s' imageSearch = '//div[@id="comic-image"]//img' prevSearch = '//a[@rel="prev"]' help = 'Index format: nnn' 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(_ParserScraper): url = 'http://navcomic.com/' stripUrl = url + 'not-a-villain/%s/' firstStripUrl = stripUrl % 'v1-001' imageSearch = '//div[@class="webcomic-image"]//img' prevSearch = '//a[contains(@class, "previous-webcomic-link")]' 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 class NotInventedHere(_ParserScraper): url = 'http://notinventedhe.re/' 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' class Nukees(_BasicScraper): url = 'http://www.nukees.com/' stripUrl = url + 'd/%s' firstStripUrl = stripUrl % '19970121' imageSearch = compile(r'"comic".+?"(/comics/.+?)"') prevSearch = compile(r'"(/d/.+?)".+?previous') help = 'Index format: yyyymmdd.html'