dosage/dosagelib/plugins/e.py

261 lines
8.6 KiB
Python
Raw Normal View History

# SPDX-License-Identifier: MIT
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
2020-01-09 20:13:54 +00:00
# Copyright (C) 2015-2020 Tobias Gruetzmacher
# Copyright (C) 2019-2020 Daniel Ring
2016-10-05 22:42:50 +00:00
import os
2020-01-12 21:09:03 +00:00
from re import compile, IGNORECASE
2012-06-20 19:58:13 +00:00
from ..helpers import bounceStarter, indirectStarter, xpath_class
2015-05-31 23:19:02 +00:00
from ..scraper import _BasicScraper, _ParserScraper
from ..util import tagre
from .common import _ComicControlScraper, _WordPressScraper, _WPNavi
2012-06-20 19:58:13 +00:00
2015-05-31 23:19:02 +00:00
class EarthsongSaga(_ParserScraper):
2017-05-16 22:11:29 +00:00
url = 'http://earthsongsaga.com/vol5/epilogue5.php'
2015-05-31 23:19:02 +00:00
imageSearch = '//div[@id="comic"]//img'
prevSearch = '//a[@title="Previous"]'
2017-05-16 22:11:29 +00:00
endOfLife = True
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/comicpage/college-daze/ea01/'
firstStripUrl = url
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'
2017-05-21 23:17:05 +00:00
class EdmundFinney(_WPNavi):
url = 'http://eqcomics.com/'
2016-03-14 07:32:18 +00:00
firstStripUrl = url + '2009/03/08/sunday-aliens/'
2012-12-08 20:30:51 +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'
class ElGoonishShive(_ComicControlScraper):
url = 'http://www.egscomics.com/'
2012-06-20 19:58:13 +00:00
class ElGoonishShiveNP(_ComicControlScraper):
2013-11-12 17:33:14 +00:00
url = 'http://www.egscomics.com/egsnp.php'
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
2019-08-05 09:00:56 +00:00
class Erfworld(_ParserScraper):
stripUrl = 'https://archives.erfworld.com/%s'
url = stripUrl % 'getLatestPage.php'
firstStripUrl = stripUrl % 'Book+0/1'
imageSearch = '//div[@class="page_content"]//img'
textSearch = '//div[@class="page_content"]'
prevSearch = '//li[@class="previous"]/a'
nextSearch = '//li[@class="next"]/a'
multipleImagesPerStrip = True
textOptional = True
starter = bounceStarter
def fetchUrls(self, url, data, urlSearch):
# Return the main logo for text-only pages
try:
imageUrls = super(Erfworld, self).fetchUrls(url, data, urlSearch)
except ValueError:
imageUrls = super(Erfworld, self).fetchUrls(url, data, '//li[@class="erf-logo"]//img')
return imageUrls
def namer(self, imageUrl, pageUrl):
# Fix inconsistent filenames
filename = imageUrl.rsplit('/', 1)[-1]
page = pageUrl.replace('+', '-').rsplit('/', 2)
return '%s_%s_%s' % (page[1], page[2], filename)
def getPrevUrl(self, url, data):
# Fix missing navigation links between books
if url == self.stripUrl % 'Book+5/1':
return self.stripUrl % 'Book+4/203'
elif url == self.stripUrl % 'Book+4/1':
return self.stripUrl % 'Book+3/145'
elif url == self.stripUrl % 'Book+3/1':
return self.stripUrl % 'Book+2/231'
elif url == self.stripUrl % 'Book+2/1':
return self.stripUrl % 'Book+1/184'
if url == self.stripUrl % 'Book+1/1':
return self.stripUrl % 'Book+0/81'
return super(Erfworld, self).getPrevUrl(url, data)
2019-07-03 06:34:52 +00:00
class ErmaFelnaEDF(_ParserScraper):
stripUrl = 'https://www.stevegallacci.com/archive/edf/%s'
firstStripUrl = stripUrl % '0000/00/00'
url = firstStripUrl
imageSearch = '//img[@id="comic-container"]'
prevSearch = '//a[@title="Previous Comic"]'
latestSearch = '//a[@title="Current Comic"]'
starter = indirectStarter
def namer(self, imageUrl, pageUrl):
# Fix inconsistent filenames
postDate = pageUrl.rsplit('/', 3)
filename = imageUrl.rsplit('/', 1)[-1]
return '%s-%s-%s_%s' % (postDate[1], postDate[2], postDate[3], filename)
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
2017-05-21 23:17:05 +00:00
class Erstwhile(_WPNavi):
url = 'http://www.erstwhiletales.com/'
endOfLife = True
class Eryl(_WordPressScraper):
url = 'http://www.flowerlarkstudios.com/comicpage/prologue-migration/page-i/'
firstStripUrl = url
starter = indirectStarter
2019-07-03 06:41:50 +00:00
class Everblue(_ParserScraper):
url = 'http://www.everblue-comic.com/comic/'
stripUrl = url + '%s'
firstStripUrl = stripUrl % '1'
imageSearch = '//article[@id="comic"]//img'
prevSearch = '//a[contains(@class, "prev")]'
2017-05-16 22:11:29 +00:00
class EverybodyLovesEricRaymond(_ParserScraper):
url = 'http://geekz.co.uk/lovesraymond/'
2017-05-16 22:11:29 +00:00
firstStripUrl = url + 'archive/slashdotted'
imageSearch = '//div[%s]//img' % xpath_class('entry-content')
prevSearch = '//a[@rel="prev"]'
2012-06-20 19:58:13 +00:00
2017-05-16 22:11:29 +00:00
class EvilDiva(_WordPressScraper):
url = ('https://web.archive.org/web/20190221223751/'
'https://www.evildivacomics.com/')
2017-05-16 22:11:29 +00:00
firstStripUrl = url + 'comic/evil-diva-issue-1-cover/'
endOfLife = True
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'
2019-06-23 00:51:29 +00:00
class Evon(_WordPressScraper):
url = 'http://evoncomics.com/'
stripUrl = url + '?comic=%s'
firstStripUrl = stripUrl % 'chapter-1'
adult = True
2020-01-09 20:13:54 +00:00
class Exiern(_WordPressScraper):
url = 'http://www.exiern.com/'
2017-05-16 22:11:29 +00:00
firstStripUrl = url + '2005/09/06/so-far/'
2012-06-20 19:58:13 +00:00
2017-05-21 23:17:05 +00:00
class ExploitationNow(_WPNavi):
2013-03-06 19:21:10 +00:00
url = 'http://www.exploitationnow.com/'
firstStripUrl = url + '2000-07-07/9'
endOfLife = True
2013-03-06 19:21:10 +00:00
2020-03-08 06:54:37 +00:00
class Exvulnerum(_ParserScraper):
url = 'https://zules.com/exvulnerum/'
stripUrl = url + 'comic.php?page=%s'
firstStripUrl = stripUrl.replace('comic', 'newprologue') % '1'
imageSearch = ('//img[contains(@src, "pages/")]',
'//img[contains(@src, "newprologue/")]')
prevSearch = '//a[./img[contains(@src, "nav_prev")]]'
2016-10-04 15:06:50 +00:00
class ExtraFabulousComics(_WordPressScraper):
url = 'https://extrafabulouscomics.com/'
firstStripUrl = url + 'comic/buttfly/'
starter = bounceStarter
2016-10-04 15:06:50 +00:00
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):
url = 'https://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'