dosage/dosagelib/plugins/z.py

97 lines
3.7 KiB
Python
Raw Normal View History

# -*- coding: iso-8859-1 -*-
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
2014-01-05 15:50:57 +00:00
# Copyright (C) 2012-2014 Bastian Kleineidam
2012-11-21 20:57:26 +00:00
from re import compile, escape
2012-10-11 10:03:12 +00:00
from ..scraper import _BasicScraper
2012-11-26 06:13:32 +00:00
from ..util import tagre
from ..helpers import bounceStarter
2012-06-20 19:58:13 +00:00
2012-12-07 23:45:18 +00:00
class ZapComic(_BasicScraper):
url = 'http://www.zapcomic.com/'
2013-04-11 16:27:43 +00:00
rurl = escape(url[:-1]) # without trailing slash
stripUrl = url + '%s/'
2013-04-11 16:27:43 +00:00
imageSearch = compile(tagre("img", "src", r'(%s\?comic_object\=\d+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s/[^"]+)' % rurl, after="previous-comic-link"))
2012-12-07 23:45:18 +00:00
help = 'Index format: yyyy/mm/nnn-stripname'
2012-06-20 19:58:13 +00:00
class Zapiro(_BasicScraper):
url = 'http://www.mg.co.za/zapiro/'
starter = bounceStarter(url,
2013-07-18 18:39:53 +00:00
compile(tagre("li", "class", r'nav_older') +
tagre("a", "href", r'(http://mg\.co\.za/cartoon/[^"]+)')))
2012-11-26 06:13:32 +00:00
stripUrl = 'http://mg.co.za/cartoon/%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % 'zapiro_681'
2012-11-26 06:13:32 +00:00
imageSearch = compile(tagre("img", "src", r'(http://cdn\.mg\.co\.za/crop/content/cartoons/[^"]+)'))
2013-07-18 18:39:53 +00:00
prevSearch = compile(tagre("li", "class", r'nav_older') +
tagre("a", "href", r'(http://mg\.co\.za/cartoon/[^"]+)'))
2012-11-26 06:13:32 +00:00
help = 'Index format: yyyy-mm-dd-stripname'
2012-06-20 19:58:13 +00:00
2012-12-04 06:02:40 +00:00
@classmethod
def namer(cls, imageUrl, pageUrl):
name = imageUrl.split('/')[-3]
return name
2012-06-20 19:58:13 +00:00
2012-12-07 23:45:18 +00:00
class ZebraGirl(_BasicScraper):
url = 'http://www.zebragirl.net/'
stripUrl = url + '?date=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '2000-05-06'
2012-12-07 23:45:18 +00:00
imageSearch = compile(tagre("img", "src", r"(comics/[^']+)", quote="'"))
prevSearch = compile(tagre("link", "href", r"(/\?date=[^']+)", quote="'", before='Previous'))
help = 'Index format: yyyy-mm-dd'
2013-04-09 17:38:47 +00:00
class ZenPencils(_BasicScraper):
url = 'http://zenpencils.com/'
rurl = escape(url)
2013-04-09 17:38:47 +00:00
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % '1-ralph-waldo-emerson-make-them-cry'
prevSearch = compile(tagre("a", "href", r'(%scomic/[^"]+/)' % rurl, after="navi-prev"))
2014-06-08 11:40:42 +00:00
imageSearch = compile(tagre("img", "src", r'(http://zenpencils\.com/comics/\d+-\d+-\d+[^"]+)'))
2013-04-09 17:38:47 +00:00
help = 'Index format: num-stripname'
description = u'Inspirational quotes from famous people adapted into cartoons.'
2012-06-20 19:58:13 +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):
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) +
2013-04-10 18:14:43 +00:00
tagre("img", "src", r'http://zwarwald\.de/images/prev\.jpg', quote="'"))
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',
)
@classmethod
def namer(cls, imageUrl, pageUrl):
prefix, year, month, name = imageUrl.rsplit('/', 3)
return "%s_%s_%s" % (year, month, name)