2020-04-18 11:45:44 +00:00
|
|
|
# SPDX-License-Identifier: MIT
|
2024-02-18 23:53:36 +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
|
|
|
|
from re import compile, MULTILINE
|
2016-04-10 21:04:34 +00:00
|
|
|
|
2012-09-26 12:42:28 +00:00
|
|
|
from ..util import tagre
|
2024-02-18 23:53:36 +00:00
|
|
|
from ..scraper import ParserScraper, _BasicScraper, _ParserScraper
|
|
|
|
from ..helpers import joinPathPartsNamer, bounceStarter, indirectStarter
|
2022-06-06 10:08:32 +00:00
|
|
|
from .common import WordPressScraper, WordPressNavi, WordPressWebcomic
|
2019-07-10 04:18:09 +00:00
|
|
|
|
|
|
|
|
2024-02-18 23:53:36 +00:00
|
|
|
class AbstruseGoose(ParserScraper):
|
|
|
|
url = 'https://web.archive.org/web/20230930172141/https://abstrusegoose.com/'
|
2016-04-13 18:01:51 +00:00
|
|
|
starter = bounceStarter
|
2013-02-04 20:00:26 +00:00
|
|
|
stripUrl = url + '%s'
|
2013-04-10 16:19:11 +00:00
|
|
|
firstStripUrl = stripUrl % '1'
|
2020-01-09 21:59:12 +00:00
|
|
|
imageSearch = '//img[contains(@src, "/strips/")]'
|
|
|
|
textSearch = imageSearch + '/@title'
|
|
|
|
textOptional = True
|
|
|
|
prevSearch = '//a[contains(text(), "Previous")]'
|
|
|
|
nextSearch = '//a[contains(text(), "Next")]'
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: n (unpadded)'
|
|
|
|
|
2020-01-09 21:59:12 +00:00
|
|
|
def namer(self, imageurl, pageurl):
|
|
|
|
index = int(pageurl.rsplit('/', 1)[1])
|
|
|
|
name = imageurl.rsplit('/', 1)[1]
|
2012-06-20 19:58:13 +00:00
|
|
|
return 'c%03d-%s' % (index, name)
|
|
|
|
|
|
|
|
|
2016-03-31 21:13:54 +00:00
|
|
|
class AbsurdNotions(_BasicScraper):
|
|
|
|
baseUrl = 'http://www.absurdnotions.org/'
|
|
|
|
url = baseUrl + 'page129.html'
|
|
|
|
stripUrl = baseUrl + 'page%s.html'
|
|
|
|
firstStripUrl = stripUrl % '1'
|
|
|
|
imageSearch = compile(tagre('img', 'src', r'(an[^"]+)'))
|
|
|
|
multipleImagesPerStrip = True
|
|
|
|
prevSearch = compile(tagre('a', 'href', r'([^"]+)') +
|
2018-05-22 22:54:40 +00:00
|
|
|
tagre('img', 'src', r'nprev\.gif'))
|
2016-03-31 21:13:54 +00:00
|
|
|
help = 'Index format: n (unpadded)'
|
|
|
|
|
|
|
|
|
2024-02-18 23:53:36 +00:00
|
|
|
class Achewood(ParserScraper):
|
|
|
|
baseUrl = 'https://achewood.com/'
|
|
|
|
stripUrl = baseUrl + '%s/title.html'
|
|
|
|
url = stripUrl % '2016/12/25'
|
|
|
|
firstStripUrl = stripUrl % '2001/10/01'
|
|
|
|
imageSearch = '//img[d:class("comicImage")]'
|
|
|
|
prevSearch = '//a[d:class("comic_prev")]'
|
|
|
|
namer = joinPathPartsNamer(pageparts=range(0, 2))
|
|
|
|
help = 'Index format: yyyy/mm/dd'
|
|
|
|
endOfLife = True
|
2013-04-10 16:36:33 +00:00
|
|
|
|
|
|
|
|
2019-07-13 08:49:30 +00:00
|
|
|
class AdventuresOfFifne(_ParserScraper):
|
|
|
|
stripUrl = 'http://fifine.purrsia.com/%s.html'
|
|
|
|
url = stripUrl % 'COMICS'
|
|
|
|
firstStripUrl = stripUrl % 'Fifine01'
|
|
|
|
imageSearch = '//img[contains(@src, "jpg")]'
|
|
|
|
prevSearch = '//a[text()="PREVIOUS"]'
|
|
|
|
multipleImagesPerStrip = True
|
|
|
|
endOfLife = True
|
|
|
|
|
|
|
|
def namer(self, imageUrl, pageUrl):
|
|
|
|
# Prepend chapter number to image filename
|
|
|
|
filename = imageUrl.rsplit('/', 1)[-1]
|
|
|
|
if filename[0] == 'p':
|
|
|
|
filename = filename.replace('p', '1_p')
|
|
|
|
filename = filename.replace('TIL', '2_TIL')
|
|
|
|
filename = filename.replace('NS', '3_NS')
|
|
|
|
filename = filename.replace('LG', '4_LG')
|
|
|
|
filename = filename.replace('WM', '5_WM')
|
|
|
|
return filename
|
|
|
|
|
|
|
|
def getPrevUrl(self, url, data):
|
|
|
|
# Fix broken navigation links
|
|
|
|
if url == self.stripUrl % 'lg06':
|
|
|
|
return self.stripUrl % 'lg05'
|
|
|
|
return super(AdventuresOfFifne, self).getPrevUrl(url, data)
|
|
|
|
|
|
|
|
|
2022-06-06 10:08:32 +00:00
|
|
|
class AfterStrife(WordPressNavi):
|
2013-04-13 18:58:00 +00:00
|
|
|
baseUrl = 'http://afterstrife.com/'
|
|
|
|
stripUrl = baseUrl + '?p=%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
url = stripUrl % '262'
|
|
|
|
firstStripUrl = stripUrl % '1'
|
2013-04-10 16:36:33 +00:00
|
|
|
help = 'Index format: nnn'
|
2016-04-10 21:04:34 +00:00
|
|
|
endOfLife = True
|
2013-04-10 16:36:33 +00:00
|
|
|
|
|
|
|
|
2019-06-14 03:07:19 +00:00
|
|
|
class AGirlAndHerFed(_ParserScraper):
|
|
|
|
url = 'https://agirlandherfed.com/'
|
2013-04-10 16:36:33 +00:00
|
|
|
stripUrl = url + '1.%s.html'
|
|
|
|
firstStripUrl = stripUrl % '1'
|
2019-06-14 03:07:19 +00:00
|
|
|
imageSearch = '//div[@id="comic-image"]/img'
|
|
|
|
prevSearch = '//div[@id="comic-nav"]/a[.//img[contains(@src, "back")]]'
|
2013-04-10 16:36:33 +00:00
|
|
|
help = 'Index format: nnn'
|
|
|
|
|
|
|
|
|
2016-04-06 20:22:22 +00:00
|
|
|
class AhoiPolloi(_ParserScraper):
|
2016-04-07 21:21:31 +00:00
|
|
|
url = 'https://ahoipolloi.blogger.de/'
|
2013-03-07 22:51:55 +00:00
|
|
|
stripUrl = url + '?day=%s'
|
2013-04-10 16:19:11 +00:00
|
|
|
firstStripUrl = stripUrl % '20060306'
|
2013-03-07 22:51:55 +00:00
|
|
|
multipleImagesPerStrip = True
|
2013-03-08 21:33:05 +00:00
|
|
|
lang = 'de'
|
2016-04-06 20:22:22 +00:00
|
|
|
imageSearch = '//img[contains(@src, "/static/antville/ahoipolloi/")]'
|
|
|
|
prevSearch = '//a[contains(@href, "/?day=")]'
|
2013-03-07 22:51:55 +00:00
|
|
|
help = 'Index format: yyyymmdd'
|
|
|
|
|
|
|
|
|
2022-06-06 10:08:32 +00:00
|
|
|
class AirForceBlues(WordPressScraper):
|
2024-02-18 23:53:36 +00:00
|
|
|
url = 'https://web.archive.org/web/20210102113825/http://farvatoons.com/'
|
2016-04-07 21:21:31 +00:00
|
|
|
firstStripUrl = url + 'comic/in-texas-there-are-texans/'
|
2013-04-10 16:36:33 +00:00
|
|
|
|
|
|
|
|
2013-03-06 19:21:10 +00:00
|
|
|
class ALessonIsLearned(_BasicScraper):
|
|
|
|
url = 'http://www.alessonislearned.com/'
|
2016-03-31 21:13:54 +00:00
|
|
|
prevSearch = compile(tagre("a", "href", r"(index\.php\?comic=\d+)",
|
2016-04-01 22:14:31 +00:00
|
|
|
quote="'") + r"[^>]+previous")
|
2013-03-06 19:21:10 +00:00
|
|
|
stripUrl = url + 'index.php?comic=%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"(cmx/lesson\d+\.[a-z]+)"))
|
|
|
|
help = 'Index format: nnn'
|
|
|
|
|
|
|
|
|
2022-06-06 10:08:32 +00:00
|
|
|
class Alice(WordPressScraper):
|
2021-08-30 22:11:28 +00:00
|
|
|
url = 'https://web.archive.org/web/20210115132313/http://www.alicecomics.com/'
|
2016-04-12 21:11:39 +00:00
|
|
|
latestSearch = '//a[text()="Latest Alice!"]'
|
2016-04-13 18:01:51 +00:00
|
|
|
starter = indirectStarter
|
2021-08-30 22:11:28 +00:00
|
|
|
endOfLife = True
|
2016-04-01 22:14:31 +00:00
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class AlienLovesPredator(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://alienlovespredator.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
stripUrl = url + '%s/'
|
|
|
|
firstStripUrl = stripUrl % '2004/10/12/unavoidable-delay'
|
2016-03-31 21:13:54 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'([^"]+)',
|
|
|
|
after='border="1" alt="" width="750"'))
|
2012-11-20 17:53:53 +00:00
|
|
|
prevSearch = compile(tagre("a", "href", r'([^"]+)', after="prev"))
|
2013-04-10 16:19:11 +00:00
|
|
|
help = 'Index format: yyyy/mm/dd/name'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2022-06-06 10:08:32 +00:00
|
|
|
class AlienShores(WordPressScraper):
|
2016-04-07 21:21:31 +00:00
|
|
|
url = 'http://alienshores.com/alienshores_band/'
|
|
|
|
firstStripUrl = url + 'AScomic/updated-cover/'
|
2013-04-10 16:36:33 +00:00
|
|
|
|
|
|
|
|
2022-06-06 10:08:32 +00:00
|
|
|
class AllTheGrowingThings(WordPressScraper):
|
2020-01-09 16:38:13 +00:00
|
|
|
url = ('https://web.archive.org/web/20160611212229/'
|
|
|
|
'http://growingthings.typodmary.com/')
|
2013-04-10 16:36:33 +00:00
|
|
|
stripUrl = url + '%s/'
|
2020-01-09 16:38:13 +00:00
|
|
|
firstStripUrl = stripUrl % 'all-the-growing-things'
|
|
|
|
endOfLife = True
|
2013-04-10 16:36:33 +00:00
|
|
|
|
|
|
|
|
2023-06-07 04:00:32 +00:00
|
|
|
class AlphaLuna(ParserScraper):
|
|
|
|
url = 'https://alphalunacomic.net/'
|
2019-06-24 05:24:20 +00:00
|
|
|
stripUrl = url + 'comic/%s/'
|
|
|
|
firstStripUrl = stripUrl % 'issue-1-cover'
|
|
|
|
imageSearch = '//main[@id="comic"]//img'
|
|
|
|
prevSearch = '//a[@rel="prev"]'
|
|
|
|
|
|
|
|
|
2023-06-07 04:00:32 +00:00
|
|
|
class AlphaLunaSpanish(ParserScraper):
|
2013-02-20 22:34:55 +00:00
|
|
|
name = 'AlphaLuna/Spanish'
|
2013-03-08 21:33:05 +00:00
|
|
|
lang = 'es'
|
2023-06-07 04:00:32 +00:00
|
|
|
url = 'https://alphalunacomic.net/spanish/'
|
2019-06-24 05:24:20 +00:00
|
|
|
stripUrl = url + 'comic/%s/'
|
|
|
|
firstStripUrl = stripUrl % 'issue-1-cover'
|
|
|
|
imageSearch = '//main[@id="comic"]//img'
|
|
|
|
prevSearch = '//a[@rel="prev"]'
|
2013-02-20 22:34:55 +00:00
|
|
|
|
|
|
|
|
2019-06-24 05:28:30 +00:00
|
|
|
class Altermeta(_ParserScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://altermeta.net/'
|
|
|
|
stripUrl = url + 'archive.php?comic=%s'
|
2013-04-10 16:19:11 +00:00
|
|
|
firstStripUrl = stripUrl % '0'
|
2019-06-24 05:28:30 +00:00
|
|
|
imageSearch = '//img[contains(@src, "comics/")]'
|
|
|
|
prevSearch = '//a[./img[contains(@src, "back")]]'
|
|
|
|
nextSearch = '//a[./img[contains(@src, "forward")]]'
|
|
|
|
starter = bounceStarter
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: n (unpadded)'
|
|
|
|
|
2019-06-24 05:28:30 +00:00
|
|
|
def namer(self, imageUrl, pageUrl):
|
|
|
|
return pageUrl.rsplit('=', 1)[-1] + '_' + imageUrl.rsplit('/', 1)[-1]
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
|
2020-01-09 16:41:07 +00:00
|
|
|
class AltermetaOld(_ParserScraper):
|
2013-04-10 21:57:09 +00:00
|
|
|
url = Altermeta.url + 'oldarchive/index.php'
|
|
|
|
stripUrl = Altermeta.url + 'oldarchive/archive.php?comic=%s'
|
2013-04-10 16:19:11 +00:00
|
|
|
firstStripUrl = stripUrl % '0'
|
2020-01-09 16:41:07 +00:00
|
|
|
imageSearch = '//img[contains(@src, "comics/")]'
|
|
|
|
prevSearch = '//a[text()="Back"]'
|
|
|
|
help = 'Index format: n (unpadded)'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2024-02-18 23:53:36 +00:00
|
|
|
class AmazingSuperPowers(WordPressNavi):
|
|
|
|
url = 'https://www.amazingsuperpowers.com/'
|
2013-02-04 20:00:26 +00:00
|
|
|
stripUrl = url + '%s/'
|
2013-04-10 16:19:11 +00:00
|
|
|
firstStripUrl = stripUrl % '2007/09/heredity'
|
2024-02-18 23:53:36 +00:00
|
|
|
imageSearch = '//div[d:class("comicpane")]/img'
|
2012-12-28 04:41:26 +00:00
|
|
|
|
2014-02-10 20:58:09 +00:00
|
|
|
def shouldSkipUrl(self, url, data):
|
2013-05-25 21:24:33 +00:00
|
|
|
"""Skip pages without images."""
|
|
|
|
return url in (
|
|
|
|
# video
|
|
|
|
self.stripUrl % '2013/05/orbital-deathray-kickstarter',
|
|
|
|
)
|
|
|
|
|
2012-12-28 04:41:26 +00:00
|
|
|
|
2019-07-14 06:31:24 +00:00
|
|
|
class AmbersNoBrainers(_ParserScraper):
|
|
|
|
baseUrl = 'https://foxyverse.com/'
|
|
|
|
url = baseUrl + 'comics/'
|
|
|
|
stripUrl = baseUrl + 'ambers-no-brainers-%s/'
|
|
|
|
firstStripUrl = stripUrl % '1'
|
|
|
|
imageSearch = '//img[contains(@src, "Page")]'
|
|
|
|
latestSearch = '//a[contains(@href, "ambers-no-brainers")]'
|
|
|
|
starter = indirectStarter
|
|
|
|
|
|
|
|
def getPrevUrl(self, url, data):
|
|
|
|
# Replace missing navigation links
|
|
|
|
pageNum = int(url.rstrip('/').rsplit('-', 1)[-1])
|
|
|
|
return self.stripUrl % str(pageNum - 1)
|
|
|
|
|
|
|
|
|
2022-06-06 10:08:32 +00:00
|
|
|
class Amya(WordPressScraper):
|
2016-04-01 22:14:31 +00:00
|
|
|
url = 'http://www.amyachronicles.com/'
|
|
|
|
|
|
|
|
|
2021-01-18 00:25:03 +00:00
|
|
|
class Angband(_ParserScraper):
|
2013-04-10 16:36:33 +00:00
|
|
|
url = 'http://angband.calamarain.net/'
|
2021-01-18 00:25:03 +00:00
|
|
|
stripUrl = url + '%s'
|
|
|
|
imageSearch = '//img'
|
|
|
|
multipleImagesPerStrip = True
|
|
|
|
endOfLife = True
|
|
|
|
|
|
|
|
def starter(self):
|
|
|
|
page = self.getPage(self.url)
|
|
|
|
self.pages = page.xpath('//p/a[not(contains(@href, "cast"))]/@href')
|
|
|
|
self.firstStripUrl = self.pages[0]
|
|
|
|
return self.pages[-1]
|
|
|
|
|
|
|
|
def getPrevUrl(self, url, data):
|
|
|
|
return self.pages[self.pages.index(url) - 1]
|
2013-04-10 16:36:33 +00:00
|
|
|
|
|
|
|
|
2016-04-07 21:21:31 +00:00
|
|
|
class Annyseed(_ParserScraper):
|
2020-01-09 16:38:13 +00:00
|
|
|
baseUrl = ('https://web.archive.org/web/20190511031451/'
|
|
|
|
'http://www.mirrorwoodcomics.com/')
|
2016-04-07 21:21:31 +00:00
|
|
|
stripUrl = baseUrl + 'Annyseed%s.htm'
|
2020-01-09 16:38:13 +00:00
|
|
|
url = stripUrl % 'Latest'
|
|
|
|
firstStripUrl = stripUrl % '000'
|
2016-04-07 21:21:31 +00:00
|
|
|
imageSearch = '//div/img[contains(@src, "Annyseed")]'
|
|
|
|
prevSearch = '//a[img[@name="Previousbtn"]]'
|
2020-01-09 16:38:13 +00:00
|
|
|
endOfLife = True
|
2013-04-10 16:36:33 +00:00
|
|
|
help = 'Index format: nnn'
|
2017-02-05 23:05:05 +00:00
|
|
|
FIX_RE = compile(r'Annyseed/Finished%20For%20Print/')
|
|
|
|
|
|
|
|
def imageUrlModifier(self, image_url, data):
|
|
|
|
return self.FIX_RE.sub('', image_url)
|
2013-04-10 16:36:33 +00:00
|
|
|
|
2017-11-27 00:04:35 +00:00
|
|
|
def link_modifier(self, fromurl, tourl):
|
|
|
|
"""Fix circular link."""
|
|
|
|
if 'Annyseed150' in fromurl and 'Annyseed150' in tourl:
|
|
|
|
return self.stripUrl % '149'
|
|
|
|
return tourl
|
2013-04-10 16:36:33 +00:00
|
|
|
|
2018-05-22 22:54:40 +00:00
|
|
|
|
2019-08-03 07:10:29 +00:00
|
|
|
class AntiheroForHire(_ParserScraper):
|
|
|
|
stripUrl = 'https://www.giantrobot.club/antihero-for-hire/%s'
|
|
|
|
firstStripUrl = stripUrl % '2016/6/8/entrance-vigil'
|
|
|
|
url = firstStripUrl
|
|
|
|
imageSearch = '//div[@class="image-wrapper"]//img[not(@class="thumb-image")]'
|
|
|
|
multipleImagesPerStrip = True
|
|
|
|
endOfLife = True
|
|
|
|
|
|
|
|
def starter(self):
|
|
|
|
# Build list of chapters for navigation
|
|
|
|
page = self.getPage(self.url)
|
2020-04-29 08:39:17 +00:00
|
|
|
self.chapters = page.xpath('//ul[@class="archive-group-list"]//a[contains(@class, "archive-item-link")]/@href')
|
|
|
|
return self.chapters[0]
|
2019-08-03 07:10:29 +00:00
|
|
|
|
|
|
|
def getPrevUrl(self, url, data):
|
|
|
|
# Retrieve previous chapter from list
|
2020-04-29 08:39:17 +00:00
|
|
|
index = self.chapters.index(url) + 1
|
|
|
|
return self.chapters[index] if index < len(self.chapters) else None
|
2019-08-03 07:10:29 +00:00
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class AppleGeeks(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.applegeeks.com/'
|
|
|
|
stripUrl = url + 'comics/viewcomic.php?issue=%s'
|
2013-04-10 16:19:11 +00:00
|
|
|
firstStripUrl = stripUrl % '1'
|
2012-12-02 17:35:06 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'((?:/comics/)?issue\d+\.jpg)'))
|
2012-06-20 19:58:13 +00:00
|
|
|
prevSearch = compile(r'<div class="caption">Previous Comic</div>\s*<p><a href="([^"]+)">', MULTILINE)
|
2016-11-01 17:25:02 +00:00
|
|
|
allow_errors = (404,)
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: n (unpadded)'
|
|
|
|
|
|
|
|
|
2013-04-25 18:37:27 +00:00
|
|
|
class ARedTailsDream(_BasicScraper):
|
|
|
|
baseUrl = 'http://www.minnasundberg.fi/'
|
|
|
|
stripUrl = baseUrl + 'comic/page%s.php'
|
|
|
|
firstStripUrl = stripUrl % '00'
|
|
|
|
url = baseUrl + 'comic/recent.php'
|
|
|
|
imageSearch = compile(tagre('img', 'src', r'(chapter.+?/eng[^"]*)'))
|
|
|
|
prevSearch = compile(tagre('a', 'href', r'(page\d+\.php)') +
|
2016-03-31 21:13:54 +00:00
|
|
|
tagre("img", "src", r'.*?aprev.*?'))
|
2013-04-25 18:37:27 +00:00
|
|
|
help = 'Index format: nn'
|
|
|
|
|
|
|
|
|
2022-06-06 10:08:32 +00:00
|
|
|
class ArtificialIncident(WordPressWebcomic):
|
2019-08-27 07:55:38 +00:00
|
|
|
url = 'https://www.artificialincident.com/'
|
|
|
|
stripUrl = url + 'comic/%s/'
|
|
|
|
firstStripUrl = stripUrl % 'issue-one-life-changing'
|
|
|
|
|
|
|
|
|
2016-04-07 21:21:31 +00:00
|
|
|
class AstronomyPOTD(_ParserScraper):
|
|
|
|
baseUrl = 'http://apod.nasa.gov/apod/'
|
2013-04-13 18:58:00 +00:00
|
|
|
url = baseUrl + 'astropix.html'
|
2016-04-13 18:01:51 +00:00
|
|
|
starter = bounceStarter
|
2013-04-13 18:58:00 +00:00
|
|
|
stripUrl = baseUrl + 'ap%s.html'
|
2013-04-10 16:19:11 +00:00
|
|
|
firstStripUrl = stripUrl % '061012'
|
2016-04-07 21:21:31 +00:00
|
|
|
imageSearch = '//a/img'
|
2012-12-07 23:45:18 +00:00
|
|
|
multipleImagesPerStrip = True
|
2016-04-07 21:21:31 +00:00
|
|
|
prevSearch = '//a[text()="<"]'
|
2016-04-12 21:11:39 +00:00
|
|
|
nextSearch = '//a[text()=">"]'
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: yymmdd'
|
|
|
|
|
2014-02-10 20:58:09 +00:00
|
|
|
def shouldSkipUrl(self, url, data):
|
2013-03-06 19:00:30 +00:00
|
|
|
"""Skip pages without images."""
|
2016-04-07 21:21:31 +00:00
|
|
|
return data.xpath('//iframe') # videos
|
2013-03-06 19:00:30 +00:00
|
|
|
|
2016-04-21 06:20:49 +00:00
|
|
|
def namer(self, image_url, page_url):
|
2016-04-07 21:21:31 +00:00
|
|
|
return '%s-%s' % (page_url.split('/')[-1].split('.')[0][2:],
|
|
|
|
image_url.split('/')[-1].split('.')[0])
|
2016-04-01 22:14:31 +00:00
|
|
|
|
|
|
|
|
2022-06-06 10:08:32 +00:00
|
|
|
class ATaleOfTails(WordPressScraper):
|
2019-06-20 05:00:34 +00:00
|
|
|
url = 'http://www.feretta.net/'
|
|
|
|
stripUrl = url + 'comic/%s/'
|
|
|
|
firstStripUrl = stripUrl % 'a-tale-of-tails-1-0'
|
|
|
|
adult = True
|
|
|
|
|
|
|
|
|
2023-06-13 21:46:23 +00:00
|
|
|
class Awaken(ParserScraper):
|
|
|
|
url = "https://www.awakencomic.com/"
|
|
|
|
stripUrl = url + 'comic/%s'
|
|
|
|
firstStripUrl = stripUrl % 'comic-cover'
|
|
|
|
imageSearch = '//div[@id="cc-comicbody"]//img'
|
|
|
|
prevSearch = '//a[@rel="prev"]'
|
|
|
|
help = 'Index format: chapter-n-page-n (unpadded)'
|
|
|
|
|
|
|
|
|
|
|
|
class AwkwardZombie(ParserScraper):
|
2023-06-01 21:59:11 +00:00
|
|
|
url = 'https://www.awkwardzombie.com/'
|
|
|
|
stripUrl = url + 'awkward-zombie/%s'
|
|
|
|
firstStripUrl = stripUrl % 'coin-battle'
|
2023-06-13 21:46:23 +00:00
|
|
|
imageSearch = '//div[@id="cc-comicbody"]//img'
|
|
|
|
prevSearch = '//a[@rel="prev"]'
|
2023-06-01 21:59:11 +00:00
|
|
|
help = 'Index format: variable :('
|
|
|
|
|
|
|
|
|
2022-06-06 10:08:32 +00:00
|
|
|
class AxeCop(WordPressScraper):
|
2016-04-01 22:14:31 +00:00
|
|
|
url = 'http://axecop.com/comic/season-two/'
|