dosage/dosagelib/plugins/e.py

233 lines
8 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
2017-02-05 23:05:05 +00:00
# Copyright (C) 2015-2017 Tobias Gruetzmacher
2012-11-21 20:57:26 +00:00
from __future__ import absolute_import, division, print_function
2016-10-05 22:42:50 +00:00
import os
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
from ..util import tagre
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'
starter = indirectStarter
2015-05-31 23:19:02 +00:00
imageSearch = '//div[@id="comic"]//img'
prevSearch = '//a[@title="Previous"]'
latestSearch = '//div[@id="leftmenu"]/span[1]/a[1]'
2015-05-31 23:19:02 +00:00
def fetchUrls(self, url, data, urlSearch):
urls = super(EarthsongSaga, self).fetchUrls(url, data, urlSearch)
return [x.replace('earthsongsaga.com/../',
'earthsongsaga.com/') for x in urls]
2013-03-06 19:21:10 +00:00
def namer(self, image_url, page_url):
2017-02-05 23:05:05 +00:00
imgmatch = compile(r'images/vol(\d+)/ch(\d+)/(.*)\.\w+$',
IGNORECASE).search(image_url)
2017-02-05 23:05:05 +00:00
return 'vol%02d_ch%02d_%s' % (
int(imgmatch.group(1)), int(imgmatch.group(2)), imgmatch.group(3))
2013-03-06 19:21:10 +00:00
class EasilyAmused(_WordPressScraper):
url = 'http://www.flowerlarkstudios.com/comic/college-daze/ea01/'
firstStripUrl = url
latestSearch = WP_LATEST_SEARCH
starter = indirectStarter
2016-05-16 21:16:29 +00:00
class EatLiver(_ParserScraper):
2013-07-16 16:01:44 +00:00
url = 'http://www.eatliver.com/'
starter = indirectStarter
2016-05-16 21:16:29 +00:00
multipleImagesPerStrip = True
imageSearch = '//div[%s]//img' % xpath_class('post-content')
prevSearch = '//a[@rel="prev"]'
latestSearch = '//a[@rel="bookmark"]'
2013-07-16 16:01:44 +00:00
2016-10-31 05:57:47 +00:00
class EatThatToast(_WordPressScraper):
2014-01-13 00:03:49 +00:00
url = 'http://eatthattoast.com/'
2016-10-31 05:57:47 +00:00
firstStripUrl = url + 'comic/thewizard/'
textSearch = _WordPressScraper.imageSearch + '/@alt'
2014-01-13 00:03:49 +00:00
2012-12-08 20:30:51 +00:00
class EdibleDirt(_BasicScraper):
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")
2012-12-08 20:30:51 +00:00
help = 'Index format: number'
class EdmundFinney(_WordPressScraper):
url = 'http://eqcomics.com/'
2016-03-14 07:32:18 +00:00
firstStripUrl = url + '2009/03/08/sunday-aliens/'
prevSearch = '//a[%s]' % xpath_class('navi-prev')
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
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'))
2012-12-08 20:30:51 +00:00
help = 'Index format: yyyymmdd'
2012-06-20 19:58:13 +00:00
class ElGoonishShive(_BasicScraper):
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"))
2013-11-12 17:33:14 +00:00
help = 'Index format: number'
2012-06-20 19:58:13 +00:00
class ElGoonishShiveNP(_BasicScraper):
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"))
2013-11-12 17:33:14 +00:00
help = 'Index format: number'
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
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 Erstwhile(_WordPressScraper):
url = 'http://www.erstwhiletales.com/'
prevSearch = '//a[%s]' % xpath_class('navi-prev')
endOfLife = True
class Eryl(_WordPressScraper):
url = 'http://www.flowerlarkstudios.com/comic/prologue-migration/page-i/'
firstStripUrl = url
latestSearch = WP_LATEST_SEARCH
starter = indirectStarter
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'
2016-09-29 22:15:45 +00:00
# Seems to be GeoBlocked from Europe?
2012-06-20 19:58:13 +00:00
class EvilDiva(_BasicScraper):
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
2016-05-16 21:16:29 +00:00
class EvilInc(_WordPressScraper):
2013-11-12 17:33:14 +00:00
url = 'http://evil-inc.com/'
2016-05-16 21:16:29 +00:00
firstStripUrl = url + 'comic/monday-3/'
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):
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
class ExploitationNow(_WordPressScraper):
2013-03-06 19:21:10 +00:00
url = 'http://www.exploitationnow.com/'
firstStripUrl = url + '2000-07-07/9'
prevSearch = '//a[%s]' % xpath_class('navi-prev')
endOfLife = True
2013-03-06 19:21:10 +00:00
2016-10-04 15:06:50 +00:00
class ExtraFabulousComics(_WordPressScraper):
url = 'http://extrafabulouscomics.com/comic/buttfly/'
firstStripUrl = url
latestSearch = '//a[%s]' % xpath_class('navi-last')
starter = indirectStarter
multipleImagesPerStrip = True
2016-10-05 22:42:50 +00:00
def namer(self, image_url, page_url):
imagename = os.path.basename(image_url)
pagepart = compile(r'/comic/([^/]+)/$').search(page_url).group(1)
return '_'.join((pagepart, imagename))
2017-02-05 23:05:05 +00:00
def shouldSkipUrl(self, url, data):
return data.xpath('//div[@id="comic"]//iframe')
2016-10-04 15:06:50 +00:00
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
2016-10-31 05:57:47 +00:00
class ExtraOrdinary(_ParserScraper):
2013-04-11 16:27:43 +00:00
url = 'http://www.exocomics.com/'
2013-04-09 17:36:51 +00:00
stripUrl = url + '%s'
firstStripUrl = stripUrl % '01'
2016-10-31 05:57:47 +00:00
prevSearch = '//a[%s]' % xpath_class('prev')
imageSearch = '//img[%s]' % xpath_class('image-style-main-comic')
2013-04-09 17:36:51 +00:00
help = 'Index format: number'
2012-06-20 19:58:13 +00:00
class EyeOfRamalach(_BasicScraper):
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'