dosage/dosagelib/plugins/t.py

370 lines
12 KiB
Python
Raw Normal View History

# SPDX-License-Identifier: MIT
2023-07-18 20:06:47 +00:00
# SPDX-FileCopyrightText: © 2004 Tristan Seligmann and Jonathan Jacobs
# SPDX-FileCopyrightText: © 2012 Bastian Kleineidam
# SPDX-FileCopyrightText: © 2015 Tobias Gruetzmacher
# SPDX-FileCopyrightText: © 2019 Daniel Ring
2019-07-14 06:06:31 +00:00
from re import compile, escape, MULTILINE
2024-02-18 16:26:54 +00:00
from functools import cached_property
2016-05-06 23:50:10 +00:00
2022-06-06 14:12:53 +00:00
from ..scraper import _BasicScraper, _ParserScraper, ParserScraper
from ..helpers import indirectStarter, joinPathPartsNamer
from ..util import tagre
2022-06-06 13:33:25 +00:00
from .common import (ComicControlScraper, WordPressScraper, WordPressSpliced,
WordPressNavi, WordPressWebcomic)
2012-06-20 19:58:13 +00:00
class TekMage(WordPressNavi):
2020-11-02 03:28:44 +00:00
url = 'https://tekmagecomic.com/'
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'chapter-1-page-1'
class Tamberlane(WordPressWebcomic):
2019-07-07 03:01:17 +00:00
baseUrl = 'https://www.tamberlanecomic.com/'
url = baseUrl + 'latest/'
stripUrl = baseUrl + 'tamberlane/%s/'
firstStripUrl = stripUrl % 'page-1'
2020-07-16 07:20:37 +00:00
imageSearch = '//div[@id="comic-page"]/img/@src'
prevSearch = '//a[@class="previous-link"]'
2019-07-07 03:01:17 +00:00
class TheBoyWhoFell(ComicControlScraper):
2020-09-13 15:18:42 +00:00
url = 'https://www.boywhofell.com/'
firstStripUrl = url + 'comic/ch00p00'
2016-10-31 05:57:47 +00:00
class TheBrads(_ParserScraper):
url = ('https://web.archive.org/web/20171211154809/'
'http://bradcolbow.com/archive/C4/')
stripUrl = url + '%s/'
firstStripUrl = stripUrl % 'P125'
imageSearch = '//div[d:class("entry")]//img'
prevSearch = '//a[d:class("prev")]'
2013-02-06 21:27:40 +00:00
multipleImagesPerStrip = True
endOfLife = True
2013-02-06 21:27:40 +00:00
2022-05-28 15:52:42 +00:00
class TheChroniclesOfHuxcyn(WordPressScraper):
2021-12-25 01:03:16 +00:00
url = 'https://huxcyn.com/'
stripUrl = url + 'comic/%s'
firstStripUrl = stripUrl % 'opening-001'
def namer(self, imageUrl, pageUrl):
# Fix inconsistent filenames
filename = imageUrl.rsplit('/', 1)[-1]
filename = filename.replace('IMG_0504', 'TCoH109')
filename = filename.replace('tcoh', 'TCoH')
filename = filename.replace('1599151639.xizana_f3a6458e-8d94-4259-bec3-5a92706fe493_jpeg', 'october.2020.cover')
filename = filename.replace('huxonsword', 'october.2020.huxonsword')
filename = filename.replace('New_Canvas100pageswebimage', 'TCoH100')
if filename[0] == '0':
filename = 'TCoH' + filename
elif filename[0] == '3':
pagenum = int(filename.rsplit('.', 1)[0].split('_', 1)[1].split('_', 1)[0])
filename = 'TCoH' + str(40 + pagenum) + filename.rsplit('.', 1)[-1]
return filename
2013-02-06 21:27:40 +00:00
2019-06-23 02:44:15 +00:00
class TheClassMenagerie(_ParserScraper):
stripUrl = 'http://www.theclassm.com/d/%s.html'
url = stripUrl % '20050717'
firstStripUrl = stripUrl % '19990322'
imageSearch = '//img[@class="ksc"]'
prevSearch = '//a[@rel="prev"]'
multipleImagesPerStrip = True
endOfLife = True
class TheDepths(WordPressWebcomic):
2020-03-04 06:03:07 +00:00
url = 'https://www.thedepthscomic.com/'
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'page-01'
imageSearch = '//div[contains(@class, "webcomic-media")]//img'
adult = True
def namer(self, imageUrl, pageUrl):
# Fix inconsistent filenames
filename = imageUrl.rsplit('/', 1)[-1]
filename = filename.replace('pg', 'page_')
filename = filename.replace('page_', 'the_depths_')
filename = filename.replace('-web', '')
return filename
class TheDevilsPanties(WordPressNavi):
url = 'https://thedevilspanties.com/'
stripUrl = url + 'archives/%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '300'
2012-12-08 20:30:51 +00:00
help = 'Index format: number'
class TheDreamlandChronicles(WordPressScraper):
url = 'http://www.thedreamlandchronicles.com/'
class TheForgottenOrder(ComicControlScraper):
2020-09-13 15:14:52 +00:00
url = 'http://www.forgottenordercomic.com/'
firstStripUrl = url + 'comic/prolouge-01-book-1'
2022-06-06 13:33:25 +00:00
class TheGamerCat(WordPressSpliced):
2019-07-03 07:18:55 +00:00
url = 'https://thegamercat.com/'
2022-06-06 13:33:25 +00:00
firstStripUrl = url + 'comic/06102011/'
2013-04-25 19:20:48 +00:00
2014-01-31 03:32:07 +00:00
class TheGentlemansArmchair(WordPressScraper):
url = 'http://thegentlemansarmchair.com/'
class TheGentleWolf(WordPressScraper):
2019-07-06 06:05:23 +00:00
url = 'https://thegentlewolf.net/'
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'tgw-001'
def namer(self, imageUrl, pageUrl):
# Fix duplicate filename
filename = imageUrl.rsplit('/', 1)[-1]
if pageUrl == self.stripUrl % 'tgw-271':
filename = filename.replace('272', '271')
return filename
class TheGlassScientists(ComicControlScraper):
2020-09-13 15:28:19 +00:00
url = 'https://www.theglassscientists.com/'
firstStripUrl = url + 'comic/chapter-i'
class TheJunkHyenasDiner(WordPressScraper):
2019-07-20 05:02:44 +00:00
url = 'http://junkhyenasdiner.com/'
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'intro'
class TheLandscaper(_ParserScraper):
stripUrl = ('https://web.archive.org/web/20171129163510/'
'http://landscaper.visual-assault.net/comic/%s')
2016-05-06 23:50:10 +00:00
url = stripUrl % 'latest'
2014-02-18 20:00:43 +00:00
firstStripUrl = stripUrl % '1'
imageSearch = '//article[d:class("comic")]//img[1]'
prevSearch = '//a[contains(text(), "Previous")]'
endOfLife = True
2014-02-18 20:00:43 +00:00
class TheMelvinChronicles(WordPressScraper):
url = 'http://melvin.jeaniebottle.com/'
2020-06-21 06:19:02 +00:00
class TheNightBelongsToUs(_ParserScraper):
url = 'https://tnbtu.com/'
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % '01-00'
imageSearch = '//div[@id="spliced-comic"]//img'
prevSearch = '//a[./img[contains(@src, "nav-prev")]]'
latestSearch = '//a[contains(@class, "main-link")]'
starter = indirectStarter
adult = True
class TheNoob(WordPressScraper):
2016-05-06 23:50:10 +00:00
url = 'http://thenoobcomic.com/'
stripUrl = url + 'comic/%s/'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
2016-05-06 23:50:10 +00:00
help = 'Index format: n (unpadded)'
2012-06-20 19:58:13 +00:00
2019-07-04 10:18:39 +00:00
class TheOldVictorian(_ParserScraper):
url = 'http://theoldvictorianwebcomic.com/'
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'the-old-victorian-cover'
imageSearch = '//div[@id="comic"]//img'
prevSearch = '//a[contains(@class, "comic-nav-previous")]'
def namer(self, imageUrl, pageUrl):
filename = imageUrl.rsplit('/', 1)[-1].replace('_', '-')
filename = filename.replace('TOV00', 'TOV-00')
if filename.replace('oldvic', '')[0].isdigit():
filename = filename.replace('oldvic', 'TOV-00')
if 'TOV-000' in filename and len(filename) > 12:
filename = filename[:8] + '-' + filename[8:]
return filename
2020-03-18 06:40:47 +00:00
class TheOrderOfTheStick(_ParserScraper):
url = 'https://www.giantitp.com/'
stripUrl = url + 'comics/oots%s.html'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '0001'
2020-03-18 06:40:47 +00:00
imageSearch = '//img[contains(@src, "/comics/oots/")]'
prevSearch = '//a[./img[@alt="Previous Comic"]]'
latestSearch = '//a[@class="SideBar" and contains(@href, "/comics/oots")]'
2012-06-20 19:58:13 +00:00
help = 'Index format: n (unpadded)'
starter = indirectStarter
2012-06-20 19:58:13 +00:00
def namer(self, image_url, page_url):
return page_url.rsplit('/', 1)[-1][:-5]
2012-06-20 19:58:13 +00:00
class TheRockCocks(ComicControlScraper):
url = 'https://rockcocks.slipshine.net/'
firstStripUrl = url + 'the-rock-cocks/page-1'
2019-06-30 17:46:39 +00:00
adult = True
2017-05-21 22:30:31 +00:00
class TheWhiteboard(_ParserScraper):
2019-06-13 06:42:12 +00:00
BROKEN_PAGE_MIDDLE = compile(r'</body></html>\n<')
url = 'http://www.the-whiteboard.com/'
2019-06-13 06:42:12 +00:00
stripUrl = url + 'auto%s.html'
firstStripUrl = stripUrl % 'wb001'
imageSearch = '//img[contains(@src, "auto")]'
prevSearch = '//a[.//img[contains(@src, "previous")]]'
2017-05-21 22:30:31 +00:00
def _parse_page(self, data):
2019-06-13 06:42:12 +00:00
# Ugly hack to fix broken HTML
2017-05-21 22:30:31 +00:00
data = self.BROKEN_PAGE_MIDDLE.sub('<', data)
return super(TheWhiteboard, self)._parse_page(data)
2020-03-18 07:00:33 +00:00
def imageUrlModifier(self, url, data):
return self.url + url
def link_modifier(self, fromurl, tourl):
return self.url + tourl
class TheWotch(WordPressScraper):
url = 'http://www.thewotch.com/'
2016-05-06 23:50:10 +00:00
firstStripUrl = url + '?comic=enter-the-wotch'
2012-06-20 19:58:13 +00:00
2013-02-06 21:08:36 +00:00
class ThisIsIndexed(_BasicScraper):
url = 'http://thisisindexed.com/'
rurl = escape(url)
2013-02-06 21:08:36 +00:00
stripUrl = url + 'page/%s'
imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/card[^"]+)' % rurl))
2013-02-06 21:08:36 +00:00
multipleImagesPerStrip = True
prevSearch = compile(tagre("div", "class", "nav-previous") +
2013-04-11 16:27:43 +00:00
tagre("a", "href", r'(%spage/\d+/)[^"]*' % rurl))
2013-02-06 21:08:36 +00:00
help = 'Index format: number'
class ThreePanelSoul(ComicControlScraper):
url = 'http://threepanelsoul.com/'
2016-05-06 23:50:10 +00:00
firstStripUrl = url + 'comic/a-test-comic'
2019-07-14 09:14:15 +00:00
class TinyDickAdventures(_ParserScraper):
url = 'https://www.lfg.co/'
stripUrl = url + 'tda/strip/%s/'
firstStripUrl = stripUrl % '1'
imageSearch = '//div[@id="comic-img"]//img'
prevSearch = '//a[@class="comic-nav-prev"]'
latestSearch = '//div[@id="feature-tda-footer"]/a[contains(@href, "tda/strip/")]'
starter = indirectStarter
def namer(self, imageUrl, pageUrl):
page = pageUrl.rstrip('/').rsplit('/', 1)[-1]
ext = imageUrl.rsplit('.', 1)[-1]
return page + '.' + ext
2022-06-06 14:12:53 +00:00
class ToonHole(ParserScraper):
url = 'https://toonhole.com/'
firstStripUrl = url + '2010/01/smart-questions-get-smart-answers/'
imageSearch = '//img[d:class("wp-post-image")]'
prevSearch = '//a[@rel="prev"]'
latestSearch = '//a[@rel="bookmark"]'
starter = indirectStarter
namer = joinPathPartsNamer(imageparts=(-3, -2, -1))
2013-03-07 17:22:24 +00:00
2013-02-06 21:08:36 +00:00
class TrippingOverYou(_BasicScraper):
url = 'http://www.trippingoveryou.com/'
stripUrl = url + 'comic/%s'
firstStripUrl = stripUrl % 'wiggle-room'
imageSearch = compile(tagre("img", "src", r'([^"]+/comics/[^"]+)'))
prevSearch = compile(r'<a class="cc-prev" rel="prev" href="(.+?)">')
help = 'Index format: stripname'
class TumbleDryComics(WordPressScraper):
url = 'https://www.tumbledrycomics.com/'
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'we-need-to-get-high-jpg'
textSearch = '//div[@id="comic"]//img/@alt'
multipleImagesPerStrip = True
adult = True
help = 'Index format: name'
def namer(self, image_url, page_url):
# Most images have the date they were posted in the filename
# For those that don't we can get the month and year from the image url
parts = image_url.rsplit('/', 3)
year = parts[1]
month = parts[2]
filename = parts[3]
if not filename.startswith(year):
filename = year + "-" + month + "-" + filename
return filename
2019-07-14 06:06:31 +00:00
class Turnoff(_ParserScraper):
name = 'turnoff'
url = 'https://turnoff.us/'
imageSearch = '//article[d:class("post-content")]//img'
prevSearch = '//div[d:class("prev")]//a'
2019-07-14 06:06:31 +00:00
stripUrl = url + 'geek/%s'
firstStripUrl = stripUrl % 'tcp-buddies'
multipleImagesPerStrip = True
@cached_property
def comics_order(self):
# Neither the images nor the pages contain information about dates or indices.
# However we can extract the order of the images from the JavaScript.
html = self.session.get(self.url).text
list_regex = compile(r"""^\s*"/geek/(.*)",\s*$""", flags=MULTILINE)
return list(reversed(list_regex.findall(html)))
def namer(self, image_url, page_url):
comic_name = page_url.split('/')[-1]
try:
index = self.comics_order.index(comic_name) + 1
except ValueError:
index = len(self.comics_order)
file_name = image_url.split('/')[-1]
return "%03d-%s" % (index, file_name)
class TwinDragons(WordPressScraper):
2019-07-13 06:31:36 +00:00
url = 'http://www.twindragonscomic.com/'
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'the-beginning'
multipleImagesPerStrip = True
2023-07-18 20:06:47 +00:00
class TwoGuysAndGuy(ComicControlScraper):
url = 'https://twogag.com/'
2013-04-25 19:23:31 +00:00
stripUrl = url + 'archives/%s'
firstStripUrl = stripUrl % '4'
2023-07-18 20:06:47 +00:00
help = 'Index format: number[-name]'
2013-04-25 19:23:31 +00:00
adult = True
2016-10-13 22:14:53 +00:00
class Twokinds(_ParserScraper):
url = 'http://twokinds.keenspot.com/'
2017-04-15 23:06:41 +00:00
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % '1'
imageSearch = '//article[d:class("comic")]//img'
prevSearch = '//a[d:class("navprev")]'
2017-04-15 23:06:41 +00:00
help = 'Index format: n (unpadded)'
2016-10-13 22:14:53 +00:00
2019-11-04 06:28:53 +00:00
class TwokindsSketches(Twokinds):
name = 'Twokinds/Sketches'
imageSearch = '//article[contains(@class, "comic")]/a'
class TwoLumps(_BasicScraper):
url = 'http://www.twolumps.net/'
stripUrl = url + 'd/%s.html'
imageSearch = compile(tagre("img", "src", r'(/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(/d/\d+\.html)', after="prev"))
help = 'Index format: yyyymmdd'