2020-04-18 11:45:44 +00:00
|
|
|
# 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 16:38:13 +00:00
|
|
|
# Copyright (C) 2015-2020 Tobias Gruetzmacher
|
2020-01-13 06:34:05 +00:00
|
|
|
# Copyright (C) 2019-2020 Daniel Ring
|
2013-04-10 16:19:11 +00:00
|
|
|
from re import compile, escape
|
2012-06-20 19:58:13 +00:00
|
|
|
|
2016-04-05 21:58:43 +00:00
|
|
|
from ..util import tagre
|
2014-07-23 18:54:00 +00:00
|
|
|
from ..scraper import _BasicScraper, _ParserScraper
|
2020-07-31 20:56:30 +00:00
|
|
|
from ..helpers import indirectStarter
|
2020-02-18 09:51:52 +00:00
|
|
|
from .common import _ComicControlScraper, _WordPressScraper, _WPNavi, _WPNaviIn, _WPWebcomic
|
|
|
|
|
|
|
|
|
|
|
|
class BackOffice(_WPNavi):
|
|
|
|
url = 'https://rawrtacular.com/bo/'
|
|
|
|
stripUrl = url + '?comic=%s'
|
|
|
|
firstStripUrl = stripUrl % 'back-office'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2013-03-06 19:21:10 +00:00
|
|
|
class BadassMuthas(_BasicScraper):
|
|
|
|
url = 'http://badassmuthas.com/pages/comic.php'
|
|
|
|
stripUrl = url + '?%s'
|
2013-04-10 16:19:11 +00:00
|
|
|
firstStripUrl = stripUrl % '1'
|
2013-03-06 19:21:10 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(/images/comicsissue[^"]+)'))
|
2016-03-31 21:13:54 +00:00
|
|
|
prevSearch = compile(tagre("a", "href", r'([^"]+)') +
|
|
|
|
tagre("img", "src", r'/images/comicsbuttonBack\.gif'))
|
2013-03-06 19:21:10 +00:00
|
|
|
help = 'Index format: nnn'
|
|
|
|
|
|
|
|
|
2016-04-26 22:31:27 +00:00
|
|
|
class BadMachinery(_ParserScraper):
|
2020-09-29 19:01:33 +00:00
|
|
|
url = 'https://scarygoround.com/badmachinery/index.php'
|
2013-02-06 21:08:36 +00:00
|
|
|
stripUrl = url + '?date=%s'
|
2020-09-29 19:01:33 +00:00
|
|
|
firstStripUrl = stripUrl % '20090921'
|
2016-04-26 22:31:27 +00:00
|
|
|
imageSearch = '//img[@class="comicimg"]'
|
|
|
|
prevSearch = '//a[contains(text(), "Previous")]'
|
2020-09-29 19:01:33 +00:00
|
|
|
endOfLife = True
|
2013-02-06 21:08:36 +00:00
|
|
|
help = 'Index format: yyyymmdd'
|
|
|
|
|
|
|
|
|
2016-04-03 22:12:53 +00:00
|
|
|
class BalderDash(_ComicControlScraper):
|
|
|
|
url = 'http://www.balderdashcomic.com/'
|
|
|
|
|
|
|
|
|
2019-07-12 08:41:08 +00:00
|
|
|
class BallerinaMafia(_ParserScraper):
|
|
|
|
url = 'http://www.ballerinamafia.net/'
|
|
|
|
stripUrl = url + 'index.php?pid=%s'
|
|
|
|
firstStripUrl = stripUrl % '20100906'
|
|
|
|
imageSearch = ('//img[contains(@alt, "Comic")]',
|
|
|
|
'//a[contains(@href, "comics/")]')
|
|
|
|
prevSearch = '//a[@class="prev"]'
|
|
|
|
adult = True
|
|
|
|
endOfLife = True
|
|
|
|
|
|
|
|
|
2016-04-01 22:14:31 +00:00
|
|
|
class Bardsworth(_WordPressScraper):
|
|
|
|
url = 'http://www.bardsworth.com/'
|
2016-04-12 21:11:39 +00:00
|
|
|
latestSearch = '//a[@rel="bookmark"]'
|
2016-04-13 18:01:51 +00:00
|
|
|
starter = indirectStarter
|
2016-04-01 22:14:31 +00:00
|
|
|
|
|
|
|
|
2013-03-06 19:21:10 +00:00
|
|
|
class Baroquen(_BasicScraper):
|
|
|
|
url = 'http://www.baroquencomics.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-03-06 19:21:10 +00:00
|
|
|
stripUrl = url + '%s/'
|
2013-04-10 16:19:11 +00:00
|
|
|
firstStripUrl = stripUrl % '2008/11/05/raise-the-curtains'
|
|
|
|
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: yyyy/mm/dd/strip-name'
|
|
|
|
|
|
|
|
|
2016-04-10 21:04:34 +00:00
|
|
|
class Bearmageddon(_WordPressScraper):
|
2017-11-27 00:04:35 +00:00
|
|
|
url = 'http://bearmageddon.com/bearmo/page-1/'
|
|
|
|
firstStripUrl = url
|
2020-07-31 20:56:30 +00:00
|
|
|
latestSearch = '//a[d:class("comic-nav-last")]'
|
2016-09-28 23:29:01 +00:00
|
|
|
starter = indirectStarter
|
2013-03-06 19:00:30 +00:00
|
|
|
|
|
|
|
|
2015-02-01 00:07:35 +00:00
|
|
|
class Beetlebum(_BasicScraper):
|
|
|
|
url = 'http://blog.beetlebum.de/'
|
|
|
|
rurl = escape(url)
|
|
|
|
stripUrl = url + '%s'
|
|
|
|
firstStripUrl = stripUrl % '2006/03/10/quiz-fur-ruskiphile'
|
2016-04-13 18:01:51 +00:00
|
|
|
starter = indirectStarter
|
2015-02-01 00:07:35 +00:00
|
|
|
multipleImagesPerStrip = True
|
2015-03-22 16:13:53 +00:00
|
|
|
imageSearch = compile(tagre('img', 'src', r'(http://blog\.beetlebum\.de/wp-content/uploads/[^"]+)'))
|
2016-03-31 21:13:54 +00:00
|
|
|
prevSearch = compile(tagre('a', 'href',
|
|
|
|
r'(%s\d{4}/\d{2}/\d{2}/[^"]*)' % rurl,
|
|
|
|
after='prev'))
|
2016-04-12 21:11:39 +00:00
|
|
|
latestSearch = compile(tagre('a', 'href',
|
|
|
|
r'(%s\d{4}/\d{2}/\d{2}/[^"]+)' % rurl,
|
|
|
|
after='bookmark'))
|
2015-02-01 00:07:35 +00:00
|
|
|
help = 'Index format: yyyy/mm/dd/striptitle'
|
|
|
|
lang = 'de'
|
2015-03-22 16:13:53 +00:00
|
|
|
|
2016-04-21 06:20:49 +00:00
|
|
|
def namer(self, image_url, page_url):
|
|
|
|
indexes = tuple(page_url.rstrip('/').split('/')[-4:])
|
2015-02-01 00:07:35 +00:00
|
|
|
name = '%s-%s-%s-%s' % indexes
|
2016-04-21 06:20:49 +00:00
|
|
|
name = name + '_' + image_url.split('/')[-1]
|
2015-02-01 00:07:35 +00:00
|
|
|
return name
|
|
|
|
|
|
|
|
|
2019-10-18 07:49:55 +00:00
|
|
|
class Bethellium(_WPWebcomic):
|
2019-06-29 22:06:46 +00:00
|
|
|
stripUrl = 'http://dbcomics.darkblueworkshop.com/bethellium/%s/'
|
2020-05-24 01:17:42 +00:00
|
|
|
firstStripUrl = stripUrl % 'chapter-1/cover'
|
2019-06-29 22:06:46 +00:00
|
|
|
url = firstStripUrl
|
2020-05-24 01:17:42 +00:00
|
|
|
latestSearch = '//main' + _WPWebcomic.latestSearch
|
2019-06-29 22:06:46 +00:00
|
|
|
starter = indirectStarter
|
|
|
|
|
2020-04-16 08:31:59 +00:00
|
|
|
def getPrevUrl(self, url, data):
|
|
|
|
prevUrl = super(Bethellium, self).getPrevUrl(url, data)
|
|
|
|
return prevUrl.replace('%webcomic2_storyline%', 'chapter-2-the-hemlocks-scar')
|
|
|
|
|
2019-06-29 22:06:46 +00:00
|
|
|
def namer(self, imageUrl, pageUrl):
|
|
|
|
# Prepend chapter title to page filenames
|
|
|
|
chapter = pageUrl.rstrip('/').rsplit('/', 3)[-2]
|
|
|
|
chapter = chapter.replace('chapter-1', 'chapter-1-the-magic-city')
|
|
|
|
page = imageUrl.rsplit('/', 1)[-1]
|
|
|
|
return chapter + '_' + page
|
|
|
|
|
|
|
|
|
2019-06-13 02:22:15 +00:00
|
|
|
class BetterDays(_ParserScraper):
|
2020-09-29 19:35:41 +00:00
|
|
|
url = 'https://web.archive.org/web/20200201203404/http://jaynaylor.com/betterdays/'
|
2013-02-04 20:00:26 +00:00
|
|
|
stripUrl = url + 'archives/%s.html'
|
2013-04-10 16:19:11 +00:00
|
|
|
firstStripUrl = stripUrl % '2003/04/post-2'
|
2019-06-13 02:22:15 +00:00
|
|
|
imageSearch = '//img[contains(@src, "/betterdays/comic/")]'
|
|
|
|
prevSearch = '//a[contains(text(), "Previous")]'
|
2020-04-19 08:50:00 +00:00
|
|
|
adult = True
|
2019-06-13 02:22:15 +00:00
|
|
|
endOfLife = True
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2020-09-29 20:22:55 +00:00
|
|
|
class BetweenFailures(_WPWebcomic):
|
|
|
|
url = 'https://betweenfailures.com/'
|
2013-04-28 17:58:38 +00:00
|
|
|
stripUrl = url + 'comics1/%s'
|
2020-09-29 20:22:55 +00:00
|
|
|
firstStripUrl = stripUrl % 'every-story-has-to-start-somewhere'
|
2013-04-28 17:58:38 +00:00
|
|
|
help = 'Index format: stripname'
|
2013-03-06 19:21:10 +00:00
|
|
|
|
|
|
|
|
2019-07-13 07:22:05 +00:00
|
|
|
class BeyondTheVeil(_WordPressScraper):
|
|
|
|
url = 'http://beyondtheveilcomic.com/'
|
|
|
|
stripUrl = url + '?comic=%s'
|
|
|
|
firstStripUrl = stripUrl % '01252010'
|
|
|
|
endOfLife = True
|
|
|
|
|
|
|
|
def namer(self, imageUrl, pageUrl):
|
|
|
|
# Fix inconsistent filenames
|
|
|
|
filename = imageUrl.rsplit('/', 1)[-1]
|
|
|
|
filename = filename.replace('BtV_pg43_bw', '2014-04-25-BtV_pg43_bw')
|
|
|
|
filename = filename.replace('BtVpg28Ch7b', '2014-07-04-BtVpg28Ch7b')
|
|
|
|
return filename
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class BiggerThanCheeses(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.biggercheese.com/'
|
|
|
|
stripUrl = url + 'index.php?comic=%s'
|
2013-04-10 16:19:11 +00:00
|
|
|
firstStripUrl = stripUrl % '1'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'src="(comics/.+?)" alt')
|
|
|
|
prevSearch = compile(r'"(index.php\?comic=.+?)".+?_back')
|
|
|
|
help = 'Index format: n (unpadded)'
|
|
|
|
|
|
|
|
|
2016-04-26 22:31:27 +00:00
|
|
|
class BillyTheDunce(_ParserScraper):
|
2020-01-09 16:38:13 +00:00
|
|
|
stripUrl = ('https://web.archive.org/web/20180404142544/'
|
|
|
|
'http://www.duncepress.com/%s/')
|
|
|
|
url = stripUrl % '2012/02/losing-more'
|
|
|
|
firstStripUrl = stripUrl % '2009/06/an-introduction-of-sorts'
|
2016-04-26 22:31:27 +00:00
|
|
|
imageSearch = '//div[@class="entry"]/p[1]/a'
|
|
|
|
prevSearch = '//a[@rel="prev"]'
|
2020-01-09 16:38:13 +00:00
|
|
|
endOfLife = True
|
2013-03-06 19:21:10 +00:00
|
|
|
|
|
|
|
|
2019-07-11 07:46:57 +00:00
|
|
|
class BittersweetCandyBowl(_ParserScraper):
|
|
|
|
url = 'https://www.bittersweetcandybowl.com/'
|
|
|
|
stripUrl = url + '%s.html'
|
|
|
|
firstStripUrl = stripUrl % 'c1/p1'
|
|
|
|
imageSearch = '//img[@id="page_img"]'
|
|
|
|
prevSearch = '//a[@rel="prev"]'
|
|
|
|
|
|
|
|
def namer(self, imageUrl, pageUrl):
|
|
|
|
filename = imageUrl.rsplit('/', 2)
|
|
|
|
return filename[1] + '_' + filename[2]
|
|
|
|
|
|
|
|
|
2017-05-14 22:27:28 +00:00
|
|
|
class BlankIt(_ParserScraper):
|
2013-03-06 19:21:10 +00:00
|
|
|
url = 'http://blankitcomics.com/'
|
2017-05-14 22:27:28 +00:00
|
|
|
firstStripUrl = url + 'comic/well-what-would-you-do'
|
|
|
|
imageSearch = '//div[@id="comic"]//img'
|
2020-07-31 20:56:30 +00:00
|
|
|
prevSearch = '//a[d:class("comic-nav-previous")]'
|
|
|
|
latestSearch = '//a[d:class("comic-nav-last")]'
|
2017-05-14 22:27:28 +00:00
|
|
|
starter = indirectStarter
|
2013-03-06 19:21:10 +00:00
|
|
|
|
|
|
|
|
2019-12-02 23:14:57 +00:00
|
|
|
class BlondeSunrise(_ParserScraper):
|
|
|
|
url = 'https://blondesunrise.com/comic.php?page=latest'
|
|
|
|
firstStripUrl = 'https://blondesunrise.com/comic/comic.php?page=1'
|
|
|
|
imageSearch = '//img[contains(@src, "comic_imgs/")]'
|
|
|
|
prevSearch = '//a[img[contains(@src, "previous")]]'
|
|
|
|
|
|
|
|
|
2016-04-01 22:14:31 +00:00
|
|
|
class BloodBound(_WordPressScraper):
|
|
|
|
url = 'http://bloodboundcomic.com/'
|
|
|
|
firstStripUrl = 'http://bloodboundcomic.com/comic/06112006/'
|
|
|
|
|
|
|
|
|
2019-06-23 08:35:10 +00:00
|
|
|
class Bloodline(_WordPressScraper):
|
|
|
|
url = 'http://w0lfmare.xepher.net/'
|
|
|
|
stripUrl = url + 'comic/%s'
|
|
|
|
firstStripUrl = stripUrl % 'pg-1-2'
|
|
|
|
imageSearch = '//div[@id="comic"]//img[not(contains(@src, "TWC-vote-image"))]'
|
|
|
|
|
|
|
|
def namer(self, imageUrl, pageUrl):
|
|
|
|
# Fix filenames of early comics
|
|
|
|
return imageUrl.rsplit('/', 1)[-1].replace('gen-6', 'Bloodline')
|
|
|
|
|
|
|
|
|
2017-05-21 23:17:05 +00:00
|
|
|
class BloomingFaeries(_WordPressScraper):
|
2015-09-02 14:13:42 +00:00
|
|
|
adult = True
|
|
|
|
url = 'http://www.bloomingfaeries.com/'
|
2016-04-05 21:58:43 +00:00
|
|
|
firstStripUrl = url + 'comic/public/pit-stop/'
|
2016-03-31 21:13:54 +00:00
|
|
|
|
2016-04-21 06:20:49 +00:00
|
|
|
def namer(self, image_url, page_url):
|
2016-04-05 21:58:43 +00:00
|
|
|
return "_".join(image_url.rsplit('/', 3)[1:])
|
2016-03-31 21:13:54 +00:00
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
|
2020-09-29 18:30:44 +00:00
|
|
|
class BMovieComic(_ParserScraper):
|
|
|
|
url = 'https://bmoviecomic.com/'
|
|
|
|
stripUrl = url + '%s/'
|
|
|
|
firstStripUrl = stripUrl % 'chapter-1-strip-1'
|
|
|
|
multipleImagesPerStrip = True
|
|
|
|
imageSearch = '//div[d:class("entry-content")]//img'
|
|
|
|
prevSearch = '//a[@rel="prev"]'
|
|
|
|
help = 'Index format: pagename'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2016-06-05 16:31:30 +00:00
|
|
|
class BobWhite(_ParserScraper):
|
|
|
|
url = 'http://www.bobwhitecomics.com/'
|
2020-07-31 20:56:30 +00:00
|
|
|
imageSearch = '//span[d:class("webcomic-object")]/img'
|
2016-06-05 16:31:30 +00:00
|
|
|
prevSearch = '//a[@rel="previous"]'
|
|
|
|
|
|
|
|
|
2020-09-29 20:27:32 +00:00
|
|
|
class BookOfBiff(_WordPressScraper):
|
|
|
|
url = 'https://thebookofbiff.com/'
|
|
|
|
stripUrl = url + 'comic/%s/'
|
|
|
|
firstStripUrl = stripUrl % '4'
|
2013-03-06 19:21:10 +00:00
|
|
|
|
|
|
|
|
2020-09-29 20:35:09 +00:00
|
|
|
class BoredAndEvil(_ParserScraper):
|
|
|
|
url = 'http://orphanedcomics.com/boredandevil/'
|
|
|
|
stripUrl = url + 'webcomic-%s.html'
|
2013-04-10 16:36:33 +00:00
|
|
|
firstStripUrl = stripUrl % '2004-06-07'
|
2020-09-29 20:35:09 +00:00
|
|
|
imageSearch = '//img[d:class("webcomic")]'
|
|
|
|
prevSearch = '//a[img[@title="Previous"]]'
|
|
|
|
endOfLife = True
|
2013-04-10 16:36:33 +00:00
|
|
|
help = 'Index format: yyyy-mm-dd'
|
|
|
|
|
|
|
|
|
2016-04-01 22:14:31 +00:00
|
|
|
class BratHalla(_WordPressScraper):
|
|
|
|
url = 'http://brat-halla.com/'
|
|
|
|
|
|
|
|
|
2020-09-29 20:52:11 +00:00
|
|
|
class Brink(_WordPressScraper):
|
|
|
|
stripUrl = 'https://paperfangs.com/brink/?comic=%s'
|
|
|
|
firstStripUrl = stripUrl % 'chapter1coversmall'
|
|
|
|
url = stripUrl % 'brink639small'
|
|
|
|
endOfLife = True
|
2016-03-31 21:13:54 +00:00
|
|
|
|
|
|
|
|
2016-04-01 22:14:31 +00:00
|
|
|
class BroodHollow(_WordPressScraper):
|
|
|
|
url = 'http://broodhollow.chainsawsuit.com/'
|
|
|
|
firstStripUrl = 'http://broodhollow.chainsawsuit.com/page/2012/10/06/book-1-curious-little-thing'
|
|
|
|
|
2016-09-28 23:29:01 +00:00
|
|
|
def shouldSkipUrl(self, url, data):
|
|
|
|
return data.xpath('//div[@id="comic"]//iframe')
|
|
|
|
|
2016-04-01 22:14:31 +00:00
|
|
|
|
|
|
|
class Buni(_WordPressScraper):
|
|
|
|
url = 'http://www.bunicomic.com/'
|
|
|
|
|
|
|
|
|
2020-09-29 21:00:15 +00:00
|
|
|
class BusinessCat(_ParserScraper):
|
|
|
|
url = 'https://www.businesscatcomic.com/'
|
|
|
|
imageSearch = '//div[d:class("comic-image")]//img'
|
|
|
|
prevSearch = '//a[@rel="prev"]'
|
|
|
|
endOfLife = True
|
2016-04-01 22:14:31 +00:00
|
|
|
|
|
|
|
|
2019-06-20 05:23:42 +00:00
|
|
|
class ButImACatPerson(_WordPressScraper):
|
2019-12-31 00:44:19 +00:00
|
|
|
url = 'https://www.bicatperson.com/'
|
|
|
|
stripUrl = url + 'comic/%s/'
|
2019-06-20 05:23:42 +00:00
|
|
|
firstStripUrl = 'sketches-1'
|
2020-03-06 05:44:20 +00:00
|
|
|
endOfLife = True
|
|
|
|
|
2019-06-20 05:23:42 +00:00
|
|
|
|
2015-07-17 23:21:29 +00:00
|
|
|
class ButtercupFestival(_ParserScraper):
|
2013-02-06 21:08:36 +00:00
|
|
|
url = 'http://www.buttercupfestival.com/'
|
2015-07-17 23:21:29 +00:00
|
|
|
stripUrl = url + '%s.htm'
|
|
|
|
firstStripUrl = stripUrl % '2-1'
|
|
|
|
imageSearch = '//center/img'
|
2020-09-29 21:31:38 +00:00
|
|
|
prevSearch = (
|
|
|
|
'//a[img[contains(@src, "previous")]]', # 3-x
|
|
|
|
'//a[text()="previous"]' # 2-x
|
|
|
|
)
|
2013-02-06 21:08:36 +00:00
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class ButternutSquash(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.butternutsquash.net/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
|
|
|
stripUrl = url + '%s/'
|
|
|
|
firstStripUrl = stripUrl % '2003/04/16/meet-da-punks'
|
|
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev"))
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: yyyy/mm/dd/strip-name-author-name'
|
2016-03-31 21:13:54 +00:00
|
|
|
|
|
|
|
|
2020-09-29 21:04:56 +00:00
|
|
|
class ButterSafe(_ParserScraper):
|
|
|
|
url = 'https://www.buttersafe.com/'
|
2016-03-31 21:13:54 +00:00
|
|
|
stripUrl = url + '%s/'
|
|
|
|
firstStripUrl = stripUrl % '2007/04/03/breakfast-sad-turtle'
|
2020-09-29 21:04:56 +00:00
|
|
|
imageSearch = '//div[@id="comic"]/img'
|
|
|
|
prevSearch = '//a[@rel="prev"]'
|
2016-03-31 21:13:54 +00:00
|
|
|
help = 'Index format: yyyy/mm/dd/stripname'
|