dosage/dosagelib/plugins/g.py

183 lines
5.9 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
2022-05-28 15:52:42 +00:00
# Copyright (C) 2015-2022 Tobias Gruetzmacher
# Copyright (C) 2019-2020 Daniel Ring
from re import compile, escape
2012-06-20 19:58:13 +00:00
2015-06-01 03:11:16 +00:00
from ..scraper import _BasicScraper, _ParserScraper
2022-05-28 15:52:42 +00:00
from ..helpers import indirectStarter
from ..util import tagre
from .common import ComicControlScraper, WordPressScraper, WordPressNavi
2012-06-20 19:58:13 +00:00
class Galaxion(WordPressNavi):
url = 'http://galaxioncomics.com/'
stripUrl = url + '%s/'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1-comic/the-story-so-far/the-story-so-far'
2019-07-29 00:59:37 +00:00
multipleImagesPerStrip = True
2012-11-21 20:57:26 +00:00
help = 'Index format: n-comic/book-n/chapter-n/title-nnn'
2012-06-20 19:58:13 +00:00
class Garanos(WordPressScraper):
stripUrl = ('https://web.archive.org/web/20180314181433/'
'http://garanos.alexheberling.com/pages/%s/')
url = stripUrl % 'page-487'
firstStripUrl = stripUrl % 'vol01'
endOfLife = True
2012-06-20 19:58:13 +00:00
class GastroPhobia(_ParserScraper):
2013-03-06 19:21:10 +00:00
url = 'http://www.gastrophobia.com/'
stripUrl = url + 'index.php?date=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '2008-07-30'
imageSearch = '//div[@id="comic"]//img'
prevSearch = '//div[@id="prev"]/a'
2013-03-06 19:21:10 +00:00
help = 'Index format: yyyy-mm-dd'
class Geeks(_ParserScraper):
url = ('https://web.archive.org/web/20190527194921/'
'http://sevenfloorsdown.com/geeks/')
2013-03-06 19:21:10 +00:00
stripUrl = url + 'archives/%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '10'
imageSearch = '//div[@id="comic"]/img'
prevSearch = '//a[contains(text(), "Previous")]'
endOfLife = True
2013-03-06 19:21:10 +00:00
help = 'Index format: nnn'
2012-06-20 19:58:13 +00:00
class GeeksNextDoor(_ParserScraper):
2013-03-11 21:51:45 +00:00
url = 'http://www.geeksnextcomic.com/'
stripUrl = url + '%s.html'
firstStripUrl = stripUrl % '2007-03-27' # '2010-10-04'
imageSearch = '//p/img'
prevSearch = (
'//a[img[contains(@src, "/nav_prev")]]',
'//a[contains(text(), "< prev")]', # start page is different
)
2013-03-11 21:51:45 +00:00
help = 'Index format: yyyy-mm-dd'
class Ginpu(WordPressNavi):
url = 'https://www.ginpu.us/'
2019-07-21 23:47:14 +00:00
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'filler-2'
def namer(self, imageUrl, pageUrl):
filename = imageUrl.rsplit('/', 3)
return '%s-%s_%s' % (filename[1], filename[2], filename[3])
2013-04-25 18:58:24 +00:00
class GirlGenius(_BasicScraper):
baseUrl = 'http://www.girlgeniusonline.com/'
rurl = escape(baseUrl)
url = baseUrl + 'comic.php'
2013-04-26 17:52:45 +00:00
stripUrl = url + '?date=%s'
2013-04-25 18:58:24 +00:00
firstStripUrl = stripUrl % '20021104'
imageSearch = compile(
tagre("img", "src", r"(%sggmain/strips/[^']*)" % rurl, quote="'"))
prevSearch = compile(tagre("a", "id", "topprev", quote="\"",
before=r"(%s[^\"']+)" % rurl))
multipleImagesPerStrip = True
2013-04-25 18:58:24 +00:00
help = 'Index format: yyyymmdd'
2012-06-20 19:58:13 +00:00
class GirlsWithSlingshots(_BasicScraper):
url = 'https://girlswithslingshots.com/'
2013-04-10 21:57:09 +00:00
rurl = escape(url)
stripUrl = url + 'comic/%s'
2014-07-02 17:51:53 +00:00
firstStripUrl = stripUrl % 'gws1'
2013-04-10 21:57:09 +00:00
imageSearch = (
compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)),
compile(tagre("img", "src",
r'(http://cdn\.girlswithslingshots\.com/comics/[^"]+)')),
2013-04-10 21:57:09 +00:00
)
prevSearch = compile(tagre("a", "href", r'(%scomic/[^"]+)' % rurl,
before='rel="prev"'))
2014-07-02 17:51:53 +00:00
help = 'Index format: stripname'
2012-06-20 19:58:13 +00:00
class GleefulNihilism(WordPressScraper):
url = ('https://web.archive.org/web/20170911203122/'
'http://gleefulnihilism.com/')
2013-11-12 17:33:14 +00:00
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'amoeba'
endOfLife = True
2013-11-12 17:33:14 +00:00
help = 'Index format: stripname'
2012-06-20 19:58:13 +00:00
class GoblinsComic(ComicControlScraper):
2013-07-09 20:21:17 +00:00
url = 'http://www.goblinscomic.org/'
2013-04-09 17:37:24 +00:00
class GodChild(WordPressScraper):
2016-10-13 22:14:53 +00:00
url = 'http://godchild.keenspot.com/'
class GoGetARoomie(ComicControlScraper):
url = 'http://www.gogetaroomie.com'
2012-06-20 19:58:13 +00:00
class GoneWithTheBlastwave(_BasicScraper):
2013-02-05 18:51:46 +00:00
url = 'http://www.blastwave-comic.com/index.php?p=comic&nro=1'
starter = indirectStarter
2013-02-05 18:51:46 +00:00
stripUrl = url[:-1] + '%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'<img.+src=".+(/comics/.+?)"')
prevSearch = compile(r'href="(index.php\?p=comic&amp;nro=\d+)">' +
r'<img src="images/page/default/previous')
latestSearch = compile(r'href="(index.php\?p=comic&amp;nro=\d+)">' +
r'<img src="images/page/default/latest')
2012-06-20 19:58:13 +00:00
help = 'Index format: n'
def namer(self, image_url, page_url):
return '%02d' % int(compile(r'nro=(\d+)').search(page_url).group(1))
2012-06-20 19:58:13 +00:00
class GrrlPower(WordPressScraper):
url = 'https://grrlpowercomic.com/'
2019-06-13 06:04:09 +00:00
stripUrl = url + 'archives/comic/%s/'
firstStripUrl = stripUrl % 'gp0001'
2013-01-29 20:42:10 +00:00
2021-03-19 23:52:28 +00:00
def __init__(self, name):
super().__init__(name)
self.session.add_throttle('grrlpowercomic.com', 1.0, 1.5)
2013-01-29 20:42:10 +00:00
class GuildedAge(WordPressScraper):
2020-09-13 14:52:38 +00:00
url = 'http://guildedage.net/'
firstStripUrl = url + 'comic/chapter-1-cover/'
class GUComics(_BasicScraper):
url = 'http://www.gucomics.com/'
stripUrl = url + '%s'
firstStripUrl = stripUrl % '20000710'
imageSearch = compile(tagre("img", "src", r'(/comics/\d{4}/gu_[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(/\d+)') +
tagre("img", "src", r'/images/nav/prev\.png'))
help = 'Index format: yyyymmdd'
2019-06-12 04:26:42 +00:00
class GunnerkriggCourt(_ParserScraper):
url = 'http://www.gunnerkrigg.com/'
stripUrl = url + '?p=%s'
2019-06-12 04:26:42 +00:00
firstStripUrl = stripUrl % '1'
imageSearch = '//img[@class="comic_image"]'
prevSearch = '//a[./img[contains(@src, "prev")]]'
2013-01-29 18:00:29 +00:00
help = 'Index format: number'
2012-06-20 19:58:13 +00:00
class Gunshow(_BasicScraper):
url = 'http://gunshowcomic.com/'
stripUrl = url + '%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre("img", "src",
r'(http://gunshowcomic\.com/comics/[^"]+)'))
2012-12-04 06:02:40 +00:00
multipleImagesPerStrip = True
prevSearch = compile(
tagre("a", "href", r'([^"]+)') +
tagre("img", "src", r'[^"]*menu/small/previous\.gif'))
2012-11-21 20:57:26 +00:00
help = 'Index format: n'