dosage/dosagelib/plugins/wlpcomics.py

107 lines
3.3 KiB
Python
Raw Permalink 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) 2015-2022 Tobias Gruetzmacher
# Copyright (C) 2019-2020 Daniel Ring
2016-11-01 01:27:29 +00:00
import re
from ..scraper import ParserScraper
from ..helpers import bounceStarter
2012-11-26 06:13:32 +00:00
class WLPComics(ParserScraper):
imageSearch = '//img[contains(@alt, " Comic")]'
2016-04-10 23:07:21 +00:00
prevSearch = '//a[contains(text(), "Previous ")]'
nextSearch = '//a[contains(text(), "Next ")]'
starter = bounceStarter
2016-04-10 23:07:21 +00:00
help = 'Index format: nnn'
def __init__(self, name):
super().__init__('WLP/' + name)
2016-04-10 23:07:21 +00:00
def namer(self, image_url, page_url):
2016-04-10 23:07:21 +00:00
return (page_url.rsplit('/', 1)[-1].split('.')[0] + '_' +
image_url.rsplit('/', 1)[-1])
class ChichiChan(WLPComics):
2016-04-10 23:07:21 +00:00
url = 'http://www.wlpcomics.com/adult/chichi/'
stripUrl = url + '%s.html'
2016-04-10 23:07:21 +00:00
adult = True
class ChocolateMilkMaid(WLPComics):
2016-04-10 23:07:21 +00:00
# Newer pages seem to be broken
stripUrl = 'http://www.wlpcomics.com/adult/cm/%s.html'
url = stripUrl % '264'
2016-04-10 23:07:21 +00:00
adult = True
2016-11-01 01:27:29 +00:00
def link_modifier(self, fromurl, tourl):
"""Bugfix for self-referencing pages..."""
if tourl == fromurl:
return re.sub(r'/(\d+)\.ht',
lambda m: '/%03i.ht' % (int(m.group(1)) - 1), tourl)
if '263.html' in fromurl and '265.html' in tourl:
return self.stripUrl % '264'
2016-11-01 01:27:29 +00:00
return tourl
2016-04-10 23:07:21 +00:00
class MaidAttack(WLPComics):
2016-04-10 23:07:21 +00:00
url = 'http://www.wlpcomics.com/general/maidattack/'
stripUrl = url + '%s.html'
2016-04-10 23:07:21 +00:00
class PeterIsTheWolfAdult(WLPComics):
2019-12-17 09:33:48 +00:00
stripUrl = 'http://www.peteristhewolf.com/adult/%s.html'
# navigation to newest page is broken
url = stripUrl % '427'
2019-12-17 09:33:48 +00:00
firstStripUrl = stripUrl % '001'
multipleImagesPerStrip = True
2016-04-10 23:07:21 +00:00
adult = True
endOfLife = True
2016-04-10 23:07:21 +00:00
2019-06-27 04:19:24 +00:00
def namer(self, imageUrl, pageUrl):
name = pageUrl.rsplit('/', 1)[-1].split('.')[0] + '_' + imageUrl.rsplit('/', 1)[-1]
if 'adult' in imageUrl:
name = name.split('.')
return name[0] + '_adult.' + name[1]
return name
2019-12-17 09:33:48 +00:00
def getPrevUrl(self, url, data):
# Fix loop in site navigation
if url == self.stripUrl % '194':
return self.stripUrl % '193'
return super(PeterIsTheWolfAdult, self).getPrevUrl(url, data)
2016-04-10 23:07:21 +00:00
class PeterIsTheWolfGeneral(WLPComics):
stripUrl = 'http://www.peteristhewolf.com/general/%s.html'
# navigation to newest page is broken
url = stripUrl % '427'
2019-12-17 09:33:48 +00:00
firstStripUrl = stripUrl % '001'
endOfLife = True
2019-12-17 09:33:48 +00:00
def getPrevUrl(self, url, data):
# Fix loops in site navigation
if url == self.stripUrl % '406':
return self.stripUrl % '405'
if url == self.stripUrl % '230':
return self.stripUrl % '229'
if url == self.stripUrl % '229':
return self.stripUrl % '228'
if url == self.stripUrl % '153':
return self.stripUrl % '152'
return super(PeterIsTheWolfGeneral, self).getPrevUrl(url, data)
2016-04-10 23:07:21 +00:00
class Stellar(WLPComics):
2016-04-10 23:07:21 +00:00
url = 'http://www.wlpcomics.com/adult/stellar/'
stripUrl = url + '%s.html'
2016-04-10 23:07:21 +00:00
adult = True
2012-11-26 06:13:32 +00:00
def link_modifier(self, fromurl, tourl):
2016-04-10 23:07:21 +00:00
"""Bugfix for empty page..."""
if tourl == self.url + '075.html':
return self.url + '074.html'
return tourl