93 lines
3.3 KiB
Python
93 lines
3.3 KiB
Python
# -*- coding: utf-8 -*-
|
|
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
|
|
# Copyright (C) 2012-2014 Bastian Kleineidam
|
|
# Copyright (C) 2015-2016 Tobias Gruetzmacher
|
|
|
|
from __future__ import absolute_import, division, print_function
|
|
|
|
from re import compile, escape
|
|
|
|
from ..scraper import _BasicScraper, _ParserScraper
|
|
from ..util import tagre
|
|
from ..helpers import bounceStarter
|
|
|
|
|
|
class ZapComic(_ParserScraper):
|
|
url = 'http://www.zapcomic.com/'
|
|
css = True
|
|
imageSearch = 'img.comic-item'
|
|
prevSearch = 'a.previous-comic-link'
|
|
|
|
|
|
class Zapiro(_BasicScraper):
|
|
url = 'http://www.mg.co.za/zapiro/'
|
|
starter = bounceStarter(
|
|
url, compile(tagre("li", "class", r'nav_older') +
|
|
tagre("a", "href", r'(http://mg\.co\.za/cartoon/[^"]+)')))
|
|
stripUrl = 'http://mg.co.za/cartoon/%s'
|
|
firstStripUrl = stripUrl % 'zapiro_681'
|
|
imageSearch = compile(tagre("img", "src", r'(http://cdn\.mg\.co\.za/crop/content/cartoons/[^"]+)'))
|
|
prevSearch = compile(tagre("li", "class", r'nav_older') +
|
|
tagre("a", "href",
|
|
r'(http://mg\.co\.za/cartoon/[^"]+)'))
|
|
help = 'Index format: yyyy-mm-dd-stripname'
|
|
|
|
@classmethod
|
|
def namer(cls, imageUrl, pageUrl):
|
|
name = imageUrl.split('/')[-3]
|
|
return name
|
|
|
|
|
|
class ZenPencils(_BasicScraper):
|
|
url = 'http://zenpencils.com/'
|
|
rurl = escape(url)
|
|
multipleImagesPerStrip = True
|
|
stripUrl = url + 'comic/%s/'
|
|
firstStripUrl = stripUrl % '1-ralph-waldo-emerson-make-them-cry'
|
|
prevSearch = compile(tagre("a", "href", r'(%scomic/[^"]+/)' % rurl,
|
|
after="navi-prev"))
|
|
imageSearch = compile(tagre("img", "src", r'(http://cdn\.zenpencils\.com/wp-content/uploads/\d+[^"]+)'))
|
|
help = 'Index format: num-stripname'
|
|
|
|
|
|
class ZombieHunters(_BasicScraper):
|
|
url = 'http://www.thezombiehunters.com/'
|
|
stripUrl = url + '?strip_id=%s'
|
|
firstStripUrl = stripUrl % '1'
|
|
imageSearch = compile(tagre("img", "src", r'(/istrip_files/strips/[^"]+)'))
|
|
prevSearch = compile(tagre("a", "href", r'(\?strip_id=\d+)') + tagre("img", "id", "prevcomic"))
|
|
help = 'Index format: n(unpadded)'
|
|
|
|
|
|
class Zwarwald(_BasicScraper):
|
|
url = "http://www.zwarwald.de/"
|
|
rurl = escape(url)
|
|
stripUrl = url + 'index.php/page/%s/'
|
|
# anything before page 495 seems to be flash
|
|
firstStripUrl = stripUrl % '495'
|
|
lang = 'de'
|
|
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="'"))
|
|
help = 'Index format: number'
|
|
|
|
def shouldSkipUrl(self, url, data):
|
|
"""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',
|
|
)
|
|
|
|
@classmethod
|
|
def namer(cls, imageUrl, pageUrl):
|
|
prefix, year, month, name = imageUrl.rsplit('/', 3)
|
|
return "%s_%s_%s" % (year, month, name)
|