dosage/dosagelib/plugins/e.py

239 lines
9.5 KiB
Python
Raw Normal View History

# -*- coding: iso-8859-1 -*-
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
2013-02-05 18:51:46 +00:00
# Copyright (C) 2012-2013 Bastian Kleineidam
2012-11-21 20:57:26 +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
from ..scraper import _BasicScraper
from ..util import tagre
2012-06-20 19:58:13 +00:00
2013-03-06 19:21:10 +00:00
class EarthsongSaga(_BasicScraper):
2013-04-19 04:31:12 +00:00
description = u'Earthsong - An Online Graphic Novel by Crystal Yates'
2013-03-06 19:21:10 +00:00
url = 'http://www.earthsongsaga.com/'
starter = indirectStarter(url, compile(tagre("a", "href", r'([^"]+)') + tagre("img", "src", r'[^"]+current\.jpg')))
stripUrl = None
2013-04-10 21:57:09 +00:00
firstStripUrl = url + 'vol1/vol1cover.html'
2013-05-25 21:24:33 +00:00
imageSearch = (
compile(tagre("img", "src", r'((?:\.\./)?images/vol\d+/ch\d+/\d+\.\w+)')),
compile(tagre("img", "src", r'((?:\.\./)?images/vol\d+/ch\d+/ch\d+cover\.\w+)')),
)
2013-03-06 19:21:10 +00:00
prevSearch = compile(tagre("a", "href", r'([^"]+)', after="Previous"))
@classmethod
def namer(cls, imageUrl, pageUrl):
imgmatch = compile(r'images/vol(\d+)/ch(\d+)/(\d+)\.\w+$', IGNORECASE).search(imageUrl)
2013-05-25 21:24:33 +00:00
if not imgmatch:
imgmatch = compile(r'images/vol(\d+)/ch(\d+)/ch(\d+)cover\.\w+$', IGNORECASE).search(imageUrl)
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
2013-07-16 16:01:44 +00:00
class EatLiver(_BasicScraper):
description = u'Crazy funny pictures of insane internet'
url = 'http://www.eatliver.com/'
rurl = escape(url)
starter = indirectStarter(url, compile(tagre("a", "href", r'(i\.php\?n=\d+)') +
tagre("img", "src", r'img/small/[^"]+') + r"</a>\s*<br"))
stripUrl = url + "i.php?n=%s"
firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre("link", "href", r'(%simg/\d+/[^"]+)' % rurl, before="image_src"))
prevSearch = compile(tagre("a", "href", r'(i\.php\?n=\d+)') + "&#060;&#060; Previous")
2012-12-08 20:30:51 +00:00
class EdibleDirt(_BasicScraper):
2013-04-19 04:31:12 +00:00
description = u'Edible Dirt, by Matt Rosemier'
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/[^"]+)'))
prevSearch = compile(tagre("a", "href", r"(index\.php\?id=\d+)")+"Previous")
help = 'Index format: number'
class EdmundFinney(_BasicScraper):
description = u"Edmund Finney's Quest to Find the Meaning of Life"
url = 'http://eqcomics.com/'
rurl = escape(url)
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2009/03/08/sunday-aliens'
imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+-[^"/]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/\d+/[^"/]+/)' % rurl, after="navi navi-prev"))
help = 'Index format: yyyy/mm/dd/stripname'
2012-12-08 20:30:51 +00:00
2012-06-20 19:58:13 +00:00
class EerieCuties(_BasicScraper):
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
class Eriadan(_BasicScraper):
url = 'http://www.shockdom.com/webcomics/eriadan/'
2013-04-11 16:27:43 +00:00
rurl = escape(url)
stripUrl = url + '%s/'
2013-03-26 16:34:56 +00:00
multipleImagesPerStrip = True
2013-04-11 16:27:43 +00:00
imageSearch = compile(tagre("img", "src", r'(%sfiles/[^"]+)' % rurl, after='width="[68]00"'))
2012-11-21 20:57:26 +00:00
prevSearch = compile(tagre("a", "href", r'([^"]+)', after="prev"))
help = 'Index format: yyyy/mm/dd/nnn (unpadded)'
2012-06-20 19:58:13 +00:00
2013-04-11 16:27:43 +00:00
def shouldSkipUrl(self, url):
return url in (
self.stripUrl % "2013/04/02/istruzioni-per-il-non-uso", # video
)
2012-06-20 19:58:13 +00:00
2012-12-08 20:30:51 +00:00
class ElfOnlyInn(_BasicScraper):
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)') +
tagre("img", "src", r'/images/previous_day\.gif'))
help = 'Index format: yyyymmdd'
2012-06-20 19:58:13 +00:00
class ElGoonishShive(_BasicScraper):
2013-04-14 07:02:14 +00:00
description = u'Fantasy sci-fi comic about a group of teenagers and the bizarre, strange and supernatural circumstances of their lives.'
2012-06-20 19:58:13 +00:00
name = 'KeenSpot/ElGoonishShive'
url = 'http://www.egscomics.com/'
2013-11-12 17:33:14 +00:00
stripUrl = url + 'index.php?id=%s'
imageSearch = compile(tagre("img", "src", r'(comics/[^"]+)', after="comic"))
prevSearch = compile(tagre("a", "href", r'(/index\.php\?id=\d+)', after="prev"))
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'
imageSearch = compile(tagre("img", "src", r'(comics/[^"]+)', after="comic"))
prevSearch = compile(tagre("a", "href", r'(/egsnp\.php\?id=\d+)', after="prev"))
help = 'Index format: number'
2012-06-20 19:58:13 +00:00
2013-03-06 19:21:10 +00:00
class Ellerbisms(_BasicScraper):
2013-04-14 07:02:14 +00:00
description = u'Ellerbisms - A diary comic by Marc Ellerby'
2013-03-06 19:21:10 +00:00
url = 'http://www.ellerbisms.com/'
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'
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):
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
2012-12-13 20:05:27 +00:00
# XXX disallowed by robots.txt
class _ErrantStory(_BasicScraper):
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="(.+?)">&lt;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
class EverybodyLovesEricRaymond(_BasicScraper):
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'&laquo; <a href="(http://geekz.co.uk/lovesraymond/archive/[^/"]*)">')
help = 'Index format: name-of-old-comic'
2013-04-10 16:20:08 +00:00
class EverydayBlues(_BasicScraper):
url = 'http://everydayblues.everydayblues.net/'
rurl = escape(url)
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2010/02/11/sometimes'
prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+/)' % rurl, after="navi-prev"))
imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+-[^"]+)' % rurl))
help = 'Index format: yyyy/mm/dd/stripname'
2013-04-29 05:35:56 +00:00
description = u'A daily webcomic about the ups and downs of love, relationships and singledom.'
2013-04-10 16:20:08 +00:00
2012-06-20 19:58:13 +00:00
class EvilDiva(_BasicScraper):
2013-04-19 04:31:12 +00:00
description = u'Evil Diva'
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
class EvilInc(_BasicScraper):
2013-04-14 07:02:14 +00:00
description = u'Evil Inc. by Brad Guigar - Daily Super-Villain Webcomic and Comics Blog'
2013-11-12 17:33:14 +00:00
url = 'http://evil-inc.com/'
stripUrl = url + 'comic/%s'
firstStripUrl = stripUrl % 'monday-3'
imageSearch = compile(tagre("img", "src", r'(http://i\d\.wp\.com/evil-inc\.com/wp-content/uploads/[^"]+)'))
prevSearch = compile(tagre("span", "class", "mininav-prev") +
tagre("a", "href", r'([^"]+)'))
help = 'Index format: stripname'
2012-06-20 19:58:13 +00:00
class Exiern(_BasicScraper):
2013-04-14 07:02:14 +00:00
description = u'Barbarian Typhan-Knee defeated the wizard...and became Tiffany!'
url = 'http://www.exiern.com/'
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'
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
2013-03-06 19:21:10 +00:00
class ExploitationNow(_BasicScraper):
2013-04-14 07:02:14 +00:00
description = u'Exploitation Now - That somewhat naughty webcomic classic by Michael Poe'
2013-03-06 19:21:10 +00:00
url = 'http://www.exploitationnow.com/'
rurl = escape(url)
2013-03-06 19:21:10 +00:00
stripUrl = url + '%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '2000-07-07/9'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="navi-prev"))
2013-03-06 19:21:10 +00:00
help = 'Index format: yyyy-mm-dd/num'
2012-06-20 19:58:13 +00:00
class ExtraLife(_BasicScraper):
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/'
rurl = escape(url)
2013-04-09 17:36:51 +00:00
stripUrl = url + '%s'
firstStripUrl = stripUrl % '01'
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):
2013-04-19 04:31:12 +00:00
description = u'The Eye of Ramalach'
url = 'http://theeye.katbox.net/'
rurl = escape(url)
2013-02-19 19:58:04 +00:00
stripUrl = url + 'comic/%s/'
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'