dosage/dosagelib/plugins/z.py

76 lines
2.6 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) 2015-2022 Tobias Gruetzmacher
from re import compile, escape
from ..scraper import BasicScraper, ParserScraper
2012-11-26 06:13:32 +00:00
from ..util import tagre
from ..helpers import bounceStarter, joinPathPartsNamer
from .common import WordPressNavi
2012-06-20 19:58:13 +00:00
class ZapComic(ParserScraper):
url = 'http://www.zapcomic.com/'
css = True
imageSearch = 'img.comic-item'
prevSearch = 'a.previous-comic-link'
2012-12-07 23:45:18 +00:00
class Zapiro(ParserScraper):
2016-05-16 21:16:29 +00:00
url = 'http://mg.co.za/zapiro/'
starter = bounceStarter
2017-05-21 22:30:31 +00:00
imageSearch = '//div[@id="cartoon"]/img'
prevSearch = '//a[d:class("left")]'
nextSearch = '//a[d:class("right")]'
namer = joinPathPartsNamer(pageparts=(-1,))
2012-12-04 06:02:40 +00:00
2012-06-20 19:58:13 +00:00
class ZenPencils(WordPressNavi):
url = 'https://web.archive.org/web/20200723091741/https://zenpencils.com/'
multipleImagesPerStrip = True
firstStripUrl = url + 'comic/1-ralph-waldo-emerson-make-them-cry/'
starter = bounceStarter
prevSearch = '//a[d:class("navi-prev")]'
nextSearch = '//a[d:class("navi-next")]'
endOfLife = True
2013-04-09 17:38:47 +00:00
class ZombieHunters(BasicScraper):
url = 'http://www.thezombiehunters.com/'
stripUrl = url + '?strip_id=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
2012-11-26 06:13:32 +00:00
imageSearch = compile(tagre("img", "src", r'(/istrip_files/strips/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(\?strip_id=\d+)') + tagre("img", "id", "prevcomic"))
2012-06-20 19:58:13 +00:00
help = 'Index format: n(unpadded)'
2013-03-07 22:51:55 +00:00
class Zwarwald(BasicScraper):
2013-03-07 22:51:55 +00:00
url = "http://www.zwarwald.de/"
rurl = escape(url)
2013-03-07 22:51:55 +00:00
stripUrl = url + 'index.php/page/%s/'
2013-03-08 21:33:05 +00:00
# anything before page 495 seems to be flash
firstStripUrl = stripUrl % '495'
lang = 'de'
2013-04-10 18:14:43 +00:00
imageSearch = (
compile(tagre("img", "src", r'(%simages/\d+/\d+/[^"]+)' % rurl)),
compile(tagre("img", "src", r'(http://wp1163540\.wp190\.webpack\.hosteurope\.de/wordpress/images/\d+/\d+/[^"]+)')),
)
prevSearch = compile(tagre("a", "href", r'(%sindex\.php/page/\d+/)' % rurl) +
tagre("img", "src",
r'http://zwarwald\.de/images/prev\.jpg',
quote="'"))
namer = joinPathPartsNamer(imageparts=(-3, -2, -1))
2013-03-07 22:51:55 +00:00
help = 'Index format: number'
def shouldSkipUrl(self, url, data):
2013-03-08 21:33:05 +00:00
"""Some pages have flash content."""
return url in (
self.stripUrl % "112",
self.stripUrl % "222",
self.stripUrl % "223",
self.stripUrl % "246",
self.stripUrl % "368",
self.stripUrl % '495',
)