dosage/dosagelib/plugins/r.py

105 lines
3.4 KiB
Python
Raw Normal View History

# -*- coding: utf-8 -*-
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
2017-02-13 21:41:17 +00:00
# Copyright (C) 2015-2017 Tobias Gruetzmacher
from __future__ import absolute_import, division, print_function
2012-06-20 19:58:13 +00:00
2016-05-05 18:55:14 +00:00
from re import compile
from six.moves.urllib.parse import urljoin
2017-02-13 21:41:17 +00:00
from ..helpers import xpath_class
from ..scraper import _BasicScraper, _ParserScraper
2012-11-21 20:57:26 +00:00
from ..util import tagre
2017-02-13 21:41:17 +00:00
from .common import _WordPressScraper
2012-06-20 19:58:13 +00:00
class RadioactivePanda(_BasicScraper):
url = 'http://www.radioactivepanda.com/'
stripUrl = url + 'comic/%s'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'<img src="(/Assets/.*?)".+?"comicimg"')
prevSearch = compile(r'<a href="(/comic/.*?)".+?previous_btn')
help = 'Index format: n (no padding)'
2016-05-05 18:55:14 +00:00
class RalfTheDestroyer(_WordPressScraper):
2015-04-21 17:12:40 +00:00
url = 'http://ralfthedestroyer.com/'
2012-06-20 19:58:13 +00:00
2016-05-16 21:55:41 +00:00
class RaynaOnTheRiver(_WordPressScraper):
url = 'http://www.catomix.com/rayna/'
firstStripUrl = url + 'archives/comic/teaser-poster'
2016-05-05 18:55:14 +00:00
class RealLife(_WordPressScraper):
2013-07-18 18:39:53 +00:00
url = 'http://reallifecomics.com/'
stripUrl = url + 'comic.php?comic=%s'
2016-05-05 18:55:14 +00:00
firstStripUrl = stripUrl % 'title-1'
help = 'Index format: monthname-dd-yyyy'
def getPrevUrl(self, url, data):
# "Parse" JavaScript
prevtag = data.find_class('comic-nav-previous')
if not prevtag:
return None
target = prevtag[0].get('onclick').split("'")[1]
return urljoin(url, target)
2012-06-20 19:58:13 +00:00
2013-04-09 17:37:47 +00:00
class RealmOfAtland(_BasicScraper):
url = 'http://www.realmofatland.com/'
stripUrl = url + '?p=%s'
firstStripUrl = stripUrl % '1'
prevSearch = compile(tagre("a", "href", r'(\?p=\d+)', after="cg_back"))
imageSearch = compile(tagre("img", "src", r'(images/strips/atland\d+.[^"]+)'))
help = 'Index format: nnn'
2016-05-05 18:55:14 +00:00
class RedMeat(_ParserScraper):
url = 'http://www.redmeat.com/max-cannon/FreshMeat'
imageSearch = '//div[@class="comicStrip"]//img'
prevSearch = '//a[@class="prev"]'
2013-03-06 19:21:10 +00:00
2016-05-05 18:55:14 +00:00
def namer(self, image_url, page_url):
parts = image_url.rsplit('/', 2)
return '_'.join(parts[1:3])
2013-03-06 19:21:10 +00:00
2012-06-20 19:58:13 +00:00
class RedString(_BasicScraper):
url = 'http://www.redstring.strawberrycomics.com/'
stripUrl = url + 'index.php?id=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '434'
2012-12-04 06:02:40 +00:00
imageSearch = compile(tagre("img", "src", r'(comics/[^"]+)'))
2012-11-21 20:57:26 +00:00
prevSearch = compile(tagre("a", "href", r'(/index\.php\?id=\d+)', after="prev"))
2012-06-20 19:58:13 +00:00
help = 'Index format: nnn'
2016-05-05 18:55:14 +00:00
class RomanticallyApocalyptic(_ParserScraper):
url = 'http://romanticallyapocalyptic.com/'
2016-05-05 18:55:14 +00:00
stripUrl = url + '%s'
firstStripUrl = stripUrl % '0'
imageSearch = '//div[%s]/center//img' % xpath_class('comicpanel')
prevSearch = '//a[@accesskey="p"]'
help = 'Index format: n'
adult = True
2016-05-05 18:55:14 +00:00
class Roza(_ParserScraper):
url = 'http://www.junglestudio.com/roza/index.php'
stripUrl = url + '?date=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '2007-05-01'
2016-05-05 18:55:14 +00:00
imageSearch = '//img[contains(@src, "pages/")]'
prevSearch = '//a[img[contains(@src, "navtable_01.gif")]]'
2012-06-20 19:58:13 +00:00
help = 'Index format: yyyy-mm-dd'
2013-03-12 19:49:46 +00:00
class Ruthe(_BasicScraper):
url = 'http://ruthe.de/'
2016-05-05 18:55:14 +00:00
stripUrl = url + 'cartoon/%s/datum/asc/'
2013-03-12 19:49:46 +00:00
firstStripUrl = stripUrl % '1'
lang = 'de'
2014-07-31 19:27:49 +00:00
imageSearch = compile(tagre("img", "src", r'(/?cartoons/strip_\d+[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(/cartoon/\d+/datum/asc/)') +
'vorheriger')
2013-03-12 19:49:46 +00:00
help = 'Index format: number'