dosage/dosagelib/plugins/b.py

346 lines
11 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
# Copyright (C) 2015-2020 Tobias Gruetzmacher
# Copyright (C) 2019-2020 Daniel Ring
from re import compile, escape
2012-06-20 19:58:13 +00:00
from ..util import tagre
from ..scraper import _BasicScraper, _ParserScraper
from ..helpers import indirectStarter
from .common import _ComicControlScraper, _WordPressScraper, _WPNavi, _WPWebcomic
2020-02-18 09:51:52 +00:00
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'
firstStripUrl = stripUrl % '1'
2013-03-06 19:21:10 +00:00
imageSearch = compile(tagre("img", "src", r'(/images/comicsissue[^"]+)'))
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'
class BalderDash(_ComicControlScraper):
url = 'http://www.balderdashcomic.com/'
2019-07-12 08:41:08 +00:00
class BallerinaMafia(_ParserScraper):
2021-01-18 00:25:03 +00:00
url = 'https://web.archive.org/web/20200115230012/http://ballerinamafia.net/'
2019-07-12 08:41:08 +00:00
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
class Bardsworth(_WordPressScraper):
url = 'http://www.bardsworth.com/'
latestSearch = '//a[@rel="bookmark"]'
starter = indirectStarter
2013-03-06 19:21:10 +00:00
class Baroquen(_BasicScraper):
url = 'http://www.baroquencomics.com/'
rurl = escape(url)
2013-03-06 19:21:10 +00:00
stripUrl = url + '%s/'
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'
class Bearmageddon(_WordPressScraper):
url = 'http://bearmageddon.com/bearmo/page-1/'
firstStripUrl = url
latestSearch = '//a[d:class("comic-nav-last")]'
2016-09-28 23:29:01 +00:00
starter = indirectStarter
class Beetlebum(_BasicScraper):
url = 'http://blog.beetlebum.de/'
rurl = escape(url)
stripUrl = url + '%s'
firstStripUrl = stripUrl % '2006/03/10/quiz-fur-ruskiphile'
starter = indirectStarter
multipleImagesPerStrip = True
2015-03-22 16:13:53 +00:00
imageSearch = compile(tagre('img', 'src', r'(http://blog\.beetlebum\.de/wp-content/uploads/[^"]+)'))
prevSearch = compile(tagre('a', 'href',
r'(%s\d{4}/\d{2}/\d{2}/[^"]*)' % rurl,
after='prev'))
latestSearch = compile(tagre('a', 'href',
r'(%s\d{4}/\d{2}/\d{2}/[^"]+)' % rurl,
after='bookmark'))
help = 'Index format: yyyy/mm/dd/striptitle'
lang = 'de'
2015-03-22 16:13:53 +00:00
def namer(self, image_url, page_url):
indexes = tuple(page_url.rstrip('/').split('/')[-4:])
name = '%s-%s-%s-%s' % indexes
return name + '_' + image_url.split('/')[-1]
class Bethellium(_WPWebcomic):
2021-01-21 04:19:59 +00:00
url = 'https://bethellium.darkbluecomics.com/'
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'cover'
2019-06-29 22:06:46 +00:00
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/'
stripUrl = url + 'archives/%s.html'
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):
2021-01-18 00:25:03 +00:00
url = 'https://web.archive.org/web/20201009235642/http://beyondtheveilcomic.com/'
2019-07-13 07:22:05 +00:00
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):
url = 'http://www.biggercheese.com/'
stripUrl = url + 'index.php?comic=%s'
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):
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"]'
endOfLife = True
2013-03-06 19:21:10 +00:00
class BirdBoy(_WordPressScraper):
url = 'https://bird-boy.com/'
stripUrl = url + 'comic/{0}-{1}/'
firstStripUrl = stripUrl.format('volume-i', 'the-sword-of-mali-mani')
help = 'volume-page # Examples: i-the-sword-of-mali-mani, iii-7, synopsis-2'
def getIndexStripUrl(self, index):
(volume, strip) = index.split('-', maxsplit=1)
try:
pageNr = int(strip)
except ValueError:
2021-01-18 00:25:03 +00:00
pageNr = None # Use the string to fetch a cover page
if volume == 'synopsis':
2021-01-18 00:25:03 +00:00
strip = '{0}{1}'.format(pageNr, '-02' if strip in [1, 3] else '')
else:
volume = 'volume-' + volume
if pageNr is not None:
strip = 'page-{0}'.format(pageNr)
return self.stripUrl.format(volume, strip)
def namer(self, imageUrl, pageUrl):
# Fix inconsistent filenames
filename = imageUrl.rsplit('/', 1)[-1]
if filename == 'image.jpg':
[year, month] = imageUrl.rsplit('/', 3)[-3:-1]
pageNr = int(pageUrl.rsplit('/', 1)[-2].rsplit('-', 1)[-1])
filename = '{0}-{1}-Vol2-pg{2}.jpg'.format(year, month, pageNr)
elif filename == '27637.jpg':
filename = 'BB_Vol2_Cover.jpg'
return filename
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'
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")]]'
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/'
firstStripUrl = url + 'comic/public/pit-stop/'
def namer(self, image_url, page_url):
return "_".join(image_url.rsplit('/', 3)[1:])
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/'
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'
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
class BroodHollow(_WordPressScraper):
url = 'https://broodhollow.chainsawsuit.com/'
firstStripUrl = url + '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')
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
2019-06-20 05:23:42 +00:00
class ButImACatPerson(_WordPressScraper):
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
class ButtercupFestival(_ParserScraper):
2013-02-06 21:08:36 +00:00
url = 'http://www.buttercupfestival.com/'
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
2020-09-29 21:31:38 +00:00
)
2013-02-06 21:08:36 +00:00
2012-06-20 19:58:13 +00:00
class ButternutSquash(_BasicScraper):
url = 'http://www.butternutsquash.net/'
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'
2020-09-29 21:04:56 +00:00
class ButterSafe(_ParserScraper):
url = 'https://www.buttersafe.com/'
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"]'
help = 'Index format: yyyy/mm/dd/stripname'
2021-01-29 07:46:46 +00:00
class ByTheBook(_WordPressScraper):
url = 'http://www.btbcomic.com/'
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'chapter-1-page-0'
adult = True