dosage/dosagelib/plugins/kemonocafe.py

60 lines
2.3 KiB
Python
Raw Normal View History

2019-09-08 02:03:01 +00:00
# -*- coding: utf-8 -*-
# Copyright (C) 2019-2020 Tobias Gruetzmacher
# Copyright (C) 2019-2020 Daniel Ring
2019-09-08 02:03:01 +00:00
from ..scraper import _ParserScraper
class KemonoCafe(_ParserScraper):
imageSearch = '//div[@id="comic"]//img'
prevSearch = '//a[contains(@class, "comic-nav-previous")]'
def __init__(self, name, sub, first, last=None, adult=False):
super(KemonoCafe, self).__init__('KemonoCafe/' + name)
self.url = 'https://%s.kemono.cafe/' % sub
self.stripUrl = self.url + 'comic/%s/'
self.firstStripUrl = self.stripUrl % first
if last:
self.url = self.stripUrl % last
self.endOfLife = True
if adult:
self.adult = True
def namer(self, imageUrl, pageUrl):
# Strip date from filenames
filename = imageUrl.rsplit('/', 1)[-1]
if filename[4] == '-' and filename[7] == '-':
filename = filename[10:]
if filename[0] == '-' or filename[0] == '_':
filename = filename[1:]
# Fix duplicate filenames
if 'paprika' in pageUrl and '69-2' in pageUrl:
filename = filename.replace('69', '69-2')
elif 'rascals' in pageUrl and '89-2' in pageUrl:
filename = filename.replace('89', '90')
elif 'rascals' in pageUrl and '133-2' in pageUrl:
filename = filename.replace('133', '134')
2019-09-11 02:52:08 +00:00
# Fix unordered filenames
if 'addictivescience' in pageUrl:
page = self.getPage(pageUrl)
num = int(page.xpath('//div[@id="comic-wrap"]/@class')[0].replace('comic-id-', ''))
filename = '%04d_%s' % (num, filename)
2019-09-08 02:03:01 +00:00
return filename
@classmethod
def getmodules(cls):
return (
2019-09-11 02:52:08 +00:00
cls('AddictiveScience', 'addictivescience', 'page0001'),
2019-09-08 02:03:01 +00:00
cls('CaribbeanBlue', 'cb', 'page000', last='page325'),
cls('IMew', 'imew', 'imew00', last='imew50'),
cls('Knighthood', 'knighthood', 'kh0001'),
cls('LasLindas', 'laslindas', 'll0001', adult=True),
cls('Paprika', 'paprika', 'page000'),
cls('PracticeMakesPerfect', 'pmp', 'title-001'),
cls('Rascals', 'rascals', 'rascals-pg-0', adult=True),
cls('TheEyeOfRamalach', 'theeye', 'theeye-page01'),
cls('TinaOfTheSouth', 'tots', 'tos-01-01'),
)