2016-03-31 21:13:54 +00:00
|
|
|
# -*- coding: utf-8 -*-
|
2012-06-20 20:41:04 +00:00
|
|
|
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
|
2014-01-05 15:50:57 +00:00
|
|
|
# Copyright (C) 2012-2014 Bastian Kleineidam
|
2016-03-31 21:13:54 +00:00
|
|
|
# Copyright (C) 2015-2016 Tobias Gruetzmacher
|
2012-11-21 20:57:26 +00:00
|
|
|
|
2016-03-31 21:13:54 +00:00
|
|
|
from __future__ import absolute_import, division, print_function
|
2016-04-03 20:58:01 +00:00
|
|
|
|
2013-04-10 16:19:11 +00:00
|
|
|
from re import compile, escape, IGNORECASE
|
2012-06-20 19:58:13 +00:00
|
|
|
|
2012-10-11 10:03:12 +00:00
|
|
|
from ..helpers import indirectStarter
|
2015-05-31 23:19:02 +00:00
|
|
|
from ..scraper import _BasicScraper, _ParserScraper
|
2012-11-20 17:53:53 +00:00
|
|
|
from ..util import tagre
|
2016-04-10 21:04:34 +00:00
|
|
|
from .common import _WordPressScraper, WP_LATEST_SEARCH, xpath_class
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2015-05-31 23:19:02 +00:00
|
|
|
class EarthsongSaga(_ParserScraper):
|
|
|
|
url = 'http://earthsongsaga.com/index.php'
|
2016-04-13 18:01:51 +00:00
|
|
|
starter = indirectStarter
|
2015-05-31 23:19:02 +00:00
|
|
|
imageSearch = '//div[@id="comic"]//img'
|
|
|
|
prevSearch = '//a[@title="Previous"]'
|
2016-04-12 21:11:39 +00:00
|
|
|
latestSearch = '//div[@id="leftmenu"]/span[1]/a[1]'
|
2015-05-31 23:19:02 +00:00
|
|
|
|
2016-04-21 21:52:31 +00:00
|
|
|
def fetchUrls(self, url, data, urlSearch):
|
|
|
|
urls = super(EarthsongSaga, self).fetchUrls(url, data, urlSearch)
|
2016-03-31 21:13:54 +00:00
|
|
|
return [x.replace('earthsongsaga.com/../',
|
|
|
|
'earthsongsaga.com/') for x in urls]
|
2013-03-06 19:21:10 +00:00
|
|
|
|
2016-04-21 06:20:49 +00:00
|
|
|
def namer(self, image_url, page_url):
|
2016-03-31 21:13:54 +00:00
|
|
|
imgmatch = compile(r'images/vol(\d+)/ch(\d+)/(\d+)\.\w+$',
|
2016-04-21 06:20:49 +00:00
|
|
|
IGNORECASE).search(image_url)
|
2013-05-25 21:24:33 +00:00
|
|
|
if not imgmatch:
|
2016-03-31 21:13:54 +00:00
|
|
|
imgmatch = compile(r'images/vol(\d+)/ch(\d+)/ch(\d+)cover\.\w+$',
|
2016-04-21 06:20:49 +00:00
|
|
|
IGNORECASE).search(image_url)
|
2013-05-25 21:24:33 +00:00
|
|
|
suffix = "cover"
|
|
|
|
else:
|
|
|
|
suffix = ""
|
|
|
|
return 'vol%02d_ch%02d_%02d%s' % (
|
|
|
|
int(imgmatch.group(1)), int(imgmatch.group(2)),
|
|
|
|
int(imgmatch.group(3)), suffix)
|
2013-03-06 19:21:10 +00:00
|
|
|
|
|
|
|
|
2016-04-03 20:58:01 +00:00
|
|
|
class EasilyAmused(_WordPressScraper):
|
|
|
|
url = 'http://www.flowerlarkstudios.com/comic/college-daze/ea01/'
|
|
|
|
firstStripUrl = url
|
2016-04-12 21:11:39 +00:00
|
|
|
latestSearch = WP_LATEST_SEARCH
|
2016-04-13 18:01:51 +00:00
|
|
|
starter = indirectStarter
|
2016-04-03 20:58:01 +00:00
|
|
|
|
|
|
|
|
2013-07-16 16:01:44 +00:00
|
|
|
class EatLiver(_BasicScraper):
|
|
|
|
url = 'http://www.eatliver.com/'
|
|
|
|
rurl = escape(url)
|
2016-04-13 18:01:51 +00:00
|
|
|
starter = indirectStarter
|
2013-07-16 16:01:44 +00:00
|
|
|
stripUrl = url + "i.php?n=%s"
|
|
|
|
firstStripUrl = stripUrl % '1'
|
2016-03-31 21:13:54 +00:00
|
|
|
imageSearch = compile(tagre("link", "href", r'(%simg/\d+/[^"]+)' % rurl,
|
|
|
|
before="image_src"))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(i\.php\?n=\d+)') +
|
|
|
|
"<< Previous")
|
2016-04-12 21:11:39 +00:00
|
|
|
latestSearch = compile(tagre("a", "href", r'(i\.php\?n=\d+)') +
|
|
|
|
tagre("img", "src", r'img/small/[^"]+') +
|
|
|
|
r"</a>\s*<br")
|
2013-07-16 16:01:44 +00:00
|
|
|
|
|
|
|
|
2014-01-13 00:03:49 +00:00
|
|
|
class EatThatToast(_BasicScraper):
|
|
|
|
url = 'http://eatthattoast.com/'
|
|
|
|
rurl = escape(url)
|
|
|
|
stripUrl = url + 'comic/%s'
|
|
|
|
firstStripUrl = stripUrl % 'thewizard/'
|
2016-04-03 20:58:01 +00:00
|
|
|
imageSearch = compile(tagre("div", "id", r'comic') + "\s*.*\s*" + tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/[^"]+)' % rurl))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl,
|
|
|
|
after='comic-nav-base comic-nav-previous'))
|
|
|
|
textSearch = compile(tagre("div", "id", r'comic') + "\s*.*\s*" +
|
|
|
|
tagre("img", "alt", r'([^"]+)'))
|
2014-01-13 00:03:49 +00:00
|
|
|
help = 'Index Format: name'
|
|
|
|
|
|
|
|
|
2012-12-08 20:30:51 +00:00
|
|
|
class EdibleDirt(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://eddirt.frozenreality.co.uk/'
|
|
|
|
stripUrl = url + 'index.php?id=%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '0'
|
2012-12-08 20:30:51 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(strips/[^"]+)'))
|
2016-04-03 20:58:01 +00:00
|
|
|
prevSearch = compile(tagre("a", "href", r"(index\.php\?id=\d+)") +
|
|
|
|
"Previous")
|
2012-12-08 20:30:51 +00:00
|
|
|
help = 'Index format: number'
|
|
|
|
|
2016-03-31 21:13:54 +00:00
|
|
|
|
2016-04-10 21:04:34 +00:00
|
|
|
class EdmundFinney(_WordPressScraper):
|
2013-12-10 18:50:21 +00:00
|
|
|
url = 'http://eqcomics.com/'
|
2016-03-14 07:32:18 +00:00
|
|
|
firstStripUrl = url + '2009/03/08/sunday-aliens/'
|
2016-04-10 21:04:34 +00:00
|
|
|
prevSearch = '//a[%s]' % xpath_class('navi-prev')
|
2012-12-08 20:30:51 +00:00
|
|
|
|
2016-03-31 21:13:54 +00:00
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class EerieCuties(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.eeriecuties.com/'
|
|
|
|
stripUrl = url + 'strips-ec/%s'
|
2012-11-21 20:57:26 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://ace\.eeriecuties\.com/comics/[^"]+)'))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'([^"]+)', before="prev"))
|
|
|
|
help = 'Index format: stripname'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2012-12-08 20:30:51 +00:00
|
|
|
class ElfOnlyInn(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.elfonlyinn.net/'
|
|
|
|
stripUrl = url + 'd/%s.html'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '20020523'
|
2012-12-08 20:30:51 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(/comics/[^"]+)'))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(/d/\d+\.html)') +
|
2016-03-31 21:13:54 +00:00
|
|
|
tagre("img", "src", r'/images/previous_day\.gif'))
|
2012-12-08 20:30:51 +00:00
|
|
|
help = 'Index format: yyyymmdd'
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class ElGoonishShive(_BasicScraper):
|
|
|
|
name = 'KeenSpot/ElGoonishShive'
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.egscomics.com/'
|
2013-11-12 17:33:14 +00:00
|
|
|
stripUrl = url + 'index.php?id=%s'
|
2016-03-31 21:13:54 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(comics/[^"]+)',
|
|
|
|
after="comic"))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(/index\.php\?id=\d+)',
|
|
|
|
after="prev"))
|
2013-11-12 17:33:14 +00:00
|
|
|
help = 'Index format: number'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
|
|
|
class ElGoonishShiveNP(_BasicScraper):
|
|
|
|
name = 'KeenSpot/ElGoonishShiveNP'
|
2013-11-12 17:33:14 +00:00
|
|
|
url = 'http://www.egscomics.com/egsnp.php'
|
|
|
|
stripUrl = url + '?id=%s'
|
2016-03-31 21:13:54 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(comics/[^"]+)',
|
|
|
|
after="comic"))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(/egsnp\.php\?id=\d+)',
|
|
|
|
after="prev"))
|
2013-11-12 17:33:14 +00:00
|
|
|
help = 'Index format: number'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2013-03-06 19:21:10 +00:00
|
|
|
class Ellerbisms(_BasicScraper):
|
|
|
|
url = 'http://www.ellerbisms.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-03-06 19:21:10 +00:00
|
|
|
stripUrl = url + '?p=%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '15'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev"))
|
2013-03-06 19:21:10 +00:00
|
|
|
help = 'Index format: nnn'
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class EmergencyExit(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.eecomics.net/'
|
|
|
|
stripUrl = url + "?strip_id=%s"
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '1'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'"(comics/.+?)"')
|
2012-12-04 06:02:40 +00:00
|
|
|
prevSearch = compile(tagre("a", "href", r'(\?strip_id=\d+)') + tagre("img", "alt", r"Prior"))
|
|
|
|
help = 'Index format: n'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2015-07-17 23:21:29 +00:00
|
|
|
class ErrantStory(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.errantstory.com/'
|
|
|
|
stripUrl = url + '%s'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'<img[^>]+?src="([^"]*?comics/.+?)"')
|
|
|
|
prevSearch = compile(r'><a href="(.+?)"><Previous</a>')
|
2012-11-21 20:57:26 +00:00
|
|
|
help = 'Index format: yyyy-mm-dd/num'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2016-04-10 21:04:34 +00:00
|
|
|
class Erstwhile(_WordPressScraper):
|
2016-03-31 21:13:54 +00:00
|
|
|
url = 'http://www.erstwhiletales.com/'
|
2016-04-10 21:04:34 +00:00
|
|
|
prevSearch = '//a[%s]' % xpath_class('navi-prev')
|
|
|
|
endOfLife = True
|
2016-03-31 21:13:54 +00:00
|
|
|
|
|
|
|
|
2016-04-03 20:58:01 +00:00
|
|
|
class Eryl(_WordPressScraper):
|
|
|
|
url = 'http://www.flowerlarkstudios.com/comic/prologue-migration/page-i/'
|
|
|
|
firstStripUrl = url
|
2016-04-12 21:11:39 +00:00
|
|
|
latestSearch = WP_LATEST_SEARCH
|
2016-04-13 18:01:51 +00:00
|
|
|
starter = indirectStarter
|
2016-04-03 20:58:01 +00:00
|
|
|
help = 'This was known as DarkWings in previous Dosage versions'
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class EverybodyLovesEricRaymond(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://geekz.co.uk/lovesraymond/'
|
|
|
|
stripUrl = url + 'archive/%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % 'slashdotted'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'<img src="((?:http://geekz.co.uk)?/lovesraymond/wp-content(?:/images)/ep\d+\w?\.jpg)"', IGNORECASE)
|
|
|
|
prevSearch = compile(r'« <a href="(http://geekz.co.uk/lovesraymond/archive/[^/"]*)">')
|
|
|
|
help = 'Index format: name-of-old-comic'
|
|
|
|
|
|
|
|
|
2016-04-10 21:04:34 +00:00
|
|
|
class EverydayBlues(_WordPressScraper):
|
2013-04-10 16:20:08 +00:00
|
|
|
url = 'http://everydayblues.everydayblues.net/'
|
2016-04-10 21:04:34 +00:00
|
|
|
firstStripUrl = url + '2010/02/11/sometimes/'
|
|
|
|
prevSearch = '//a[%s]' % xpath_class('navi-prev')
|
2013-04-10 16:20:08 +00:00
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class EvilDiva(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.evildivacomics.com/'
|
|
|
|
stripUrl = url + '?p=%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '145'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'(/comics/.+?)"')
|
|
|
|
prevSearch = compile(r'http.+?com/(.+?)".+?"prev')
|
2012-11-21 20:57:26 +00:00
|
|
|
help = 'Index format: n (unpadded)'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
2013-04-10 21:57:09 +00:00
|
|
|
|
2012-11-20 17:53:53 +00:00
|
|
|
class EvilInc(_BasicScraper):
|
2013-11-12 17:33:14 +00:00
|
|
|
url = 'http://evil-inc.com/'
|
|
|
|
stripUrl = url + 'comic/%s'
|
|
|
|
firstStripUrl = stripUrl % 'monday-3'
|
2016-03-31 21:13:54 +00:00
|
|
|
imageSearch = compile(
|
|
|
|
tagre("div", "id", "comic") +
|
|
|
|
r'\s*.*\s*' + # filter out the variant href tag
|
|
|
|
tagre("img", "src",
|
|
|
|
r'(http://i\d\.wp\.com/evil-inc\.com/wp-content/uploads/[^"]+)'))
|
2013-11-12 17:33:14 +00:00
|
|
|
prevSearch = compile(tagre("span", "class", "mininav-prev") +
|
2016-03-31 21:13:54 +00:00
|
|
|
tagre("a", "href", r'([^"]+)'))
|
2013-11-12 17:33:14 +00:00
|
|
|
help = 'Index format: stripname'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2016-05-02 20:32:14 +00:00
|
|
|
class Evilish(_ParserScraper):
|
|
|
|
url = 'http://evilish.pensandtales.com/'
|
|
|
|
stripUrl = url + '?date=%s'
|
|
|
|
firstStripUrl = stripUrl % '20020630'
|
|
|
|
imageSearch = '//img[@alt="Today\'s Comics"]'
|
|
|
|
prevSearch = '//a[img[@alt="Previous Comic"]]'
|
|
|
|
endOfLife = True
|
|
|
|
help = 'Index format: yyyymmdd'
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class Exiern(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.exiern.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-02-19 19:58:04 +00:00
|
|
|
stripUrl = url + '%s/'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '2005/09/06/so-far'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev"))
|
2013-02-19 19:58:04 +00:00
|
|
|
help = 'Index format: yyyy/mm/dd/stripname'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2016-04-10 21:04:34 +00:00
|
|
|
class ExploitationNow(_WordPressScraper):
|
2013-03-06 19:21:10 +00:00
|
|
|
url = 'http://www.exploitationnow.com/'
|
2016-04-10 21:04:34 +00:00
|
|
|
firstStripUrl = url + '2000-07-07/9'
|
|
|
|
prevSearch = '//a[%s]' % xpath_class('navi-prev')
|
|
|
|
endOfLife = True
|
2013-03-06 19:21:10 +00:00
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class ExtraLife(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.myextralife.com/'
|
|
|
|
stripUrl = url + 'comic/%s/'
|
2013-04-04 16:30:02 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://www\.myextralife\.com/wp-content/uploads/[^"]+)', before="comic"))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'([^"]+)', before="prev_comic"))
|
2012-11-21 20:57:26 +00:00
|
|
|
help = 'Index format: stripname'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2013-04-09 17:36:51 +00:00
|
|
|
class ExtraOrdinary(_BasicScraper):
|
2013-04-11 16:27:43 +00:00
|
|
|
url = 'http://www.exocomics.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-04-09 17:36:51 +00:00
|
|
|
stripUrl = url + '%s'
|
|
|
|
firstStripUrl = stripUrl % '01'
|
2013-04-10 16:19:11 +00:00
|
|
|
prevSearch = compile(tagre("a", "href", r'(%s\d+)' % rurl, before="prev"))
|
|
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/comics/\d+\.[^"]+)' % rurl))
|
2013-04-09 17:36:51 +00:00
|
|
|
help = 'Index format: number'
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class EyeOfRamalach(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://theeye.katbox.net/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-02-19 19:58:04 +00:00
|
|
|
stripUrl = url + 'comic/%s/'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/[^"]+)' % rurl, after="data-webcomic-parent"))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%scomic/[^"]+)' % rurl, after="previous"))
|
2013-02-19 19:58:04 +00:00
|
|
|
help = 'Index format: stripname'
|