dosage/dosagelib/plugins/a.py

392 lines
13 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, MULTILINE
2012-09-26 12:42:28 +00:00
from ..util import tagre
from ..scraper import BasicScraper, _BasicScraper, _ParserScraper
2017-05-21 23:17:05 +00:00
from ..helpers import regexNamer, bounceStarter, indirectStarter
from .common import WordPressScraper, WordPressNavi, WordPressWebcomic
2019-07-10 04:18:09 +00:00
2020-01-09 21:59:12 +00:00
class AbstruseGoose(_ParserScraper):
url = 'https://abstrusegoose.com/'
starter = bounceStarter
stripUrl = url + '%s'
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)
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'))
help = 'Index format: n (unpadded)'
2012-06-20 19:58:13 +00:00
class AcademyVale(_BasicScraper):
url = 'http://www.imagerie.com/vale/'
stripUrl = url + 'avarch.cgi?%s'
firstStripUrl = stripUrl % '001'
2012-11-13 05:51:54 +00:00
imageSearch = compile(tagre('img', 'src', r'(avale\d{4}-\d{2}\.gif)'))
prevSearch = compile(tagre('a', 'href', r'(avarch[^">]+)', quote="") +
2018-05-22 22:54:40 +00:00
tagre('img', 'src', r'AVNavBack\.gif'))
2012-06-20 19:58:13 +00:00
help = 'Index format: nnn'
2020-09-26 07:42:48 +00:00
class Achewood(_ParserScraper):
url = 'https://www.achewood.com/'
2013-04-10 16:36:33 +00:00
stripUrl = url + 'index.php?date=%s'
firstStripUrl = stripUrl % '10012001'
2020-09-26 07:42:48 +00:00
imageSearch = '//p[@id="comic_body"]//img'
prevSearch = '//span[d:class("left")]/a[d:class("dateNav")]'
2013-04-10 16:36:33 +00:00
help = 'Index format: mmddyyyy'
namer = regexNamer(compile(r'date=(\d+)'))
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)
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'
endOfLife = True
2013-04-10 16:36:33 +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'
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'
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'
firstStripUrl = stripUrl % '20060306'
2013-03-07 22:51:55 +00:00
multipleImagesPerStrip = True
2013-03-08 21:33:05 +00:00
lang = 'de'
imageSearch = '//img[contains(@src, "/static/antville/ahoipolloi/")]'
prevSearch = '//a[contains(@href, "/?day=")]'
2013-03-07 22:51:55 +00:00
help = 'Index format: yyyymmdd'
class AhoyEarth(WordPressNavi):
url = 'http://www.ahoyearth.com/'
class AirForceBlues(WordPressScraper):
2016-04-07 21:21:31 +00:00
url = 'http://farvatoons.com/'
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/'
prevSearch = compile(tagre("a", "href", r"(index\.php\?comic=\d+)",
quote="'") + r"[^>]+previous")
2013-03-06 19:21:10 +00:00
stripUrl = url + 'index.php?comic=%s'
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'
class Alice(WordPressScraper):
url = 'https://web.archive.org/web/20210115132313/http://www.alicecomics.com/'
latestSearch = '//a[text()="Latest Alice!"]'
starter = indirectStarter
endOfLife = True
2012-06-20 19:58:13 +00:00
class AlienLovesPredator(_BasicScraper):
url = 'http://alienlovespredator.com/'
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2004/10/12/unavoidable-delay'
imageSearch = compile(tagre("img", "src", r'([^"]+)',
after='border="1" alt="" width="750"'))
prevSearch = compile(tagre("a", "href", r'([^"]+)', after="prev"))
help = 'Index format: yyyy/mm/dd/name'
2012-06-20 19:58:13 +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
class AllTheGrowingThings(WordPressScraper):
url = ('https://web.archive.org/web/20160611212229/'
'http://growingthings.typodmary.com/')
2013-04-10 16:36:33 +00:00
stripUrl = url + '%s/'
firstStripUrl = stripUrl % 'all-the-growing-things'
endOfLife = True
2013-04-10 16:36:33 +00:00
2019-06-24 05:24:20 +00:00
class AlphaLuna(_ParserScraper):
url = 'https://alphaluna.net/'
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'issue-1-cover'
imageSearch = '//main[@id="comic"]//img'
prevSearch = '//a[@rel="prev"]'
class AlphaLunaSpanish(_ParserScraper):
2013-02-20 22:34:55 +00:00
name = 'AlphaLuna/Spanish'
2013-03-08 21:33:05 +00:00
lang = 'es'
2019-06-24 05:24:20 +00:00
url = 'https://alphaluna.net/spanish/'
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):
url = 'http://altermeta.net/'
stripUrl = url + 'archive.php?comic=%s'
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'
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
2012-12-28 04:41:26 +00:00
class AmazingSuperPowers(_BasicScraper):
url = 'http://www.amazingsuperpowers.com/'
rurl = escape(url)
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2007/09/heredity'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev"))
2012-12-28 04:41:26 +00:00
help = 'Index format: yyyy/mm/name'
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)
class Amya(WordPressScraper):
url = 'http://www.amyachronicles.com/'
2019-07-06 04:47:16 +00:00
class Anaria(_ParserScraper):
url = 'https://www.leahbriere.com/anaria-the-witchs-dream/'
firstStripUrl = url
imageSearch = '//div[contains(@class, "gallery")]//a'
multipleImagesPerStrip = True
endOfLife = True
def namer(self, imageUrl, pageUrl):
filename = imageUrl.rsplit('/', 1)[-1]
return filename.replace('00.jpg', 'new00.jpg').replace('new', '1')
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
2012-06-20 19:58:13 +00:00
class Angels2200(_BasicScraper):
url = 'http://www.janahoffmann.com/angels/'
stripUrl = url + '%s'
2012-12-02 17:35:06 +00:00
imageSearch = compile(tagre("img", "src", r"(http://www\.janahoffmann\.com/angels/comics/[^']+)", quote="'"))
prevSearch = compile(tagre("a", "href", r'([^"]+)') + "« Previous")
2012-11-14 05:22:08 +00:00
help = 'Index format: yyyy/mm/dd/part-<n>-comic-<n>'
2012-06-20 19:58:13 +00:00
2016-04-07 21:21:31 +00:00
class Annyseed(_ParserScraper):
baseUrl = ('https://web.archive.org/web/20190511031451/'
'http://www.mirrorwoodcomics.com/')
2016-04-07 21:21:31 +00:00
stripUrl = baseUrl + 'Annyseed%s.htm'
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"]]'
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
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):
url = 'http://www.applegeeks.com/'
stripUrl = url + 'comics/viewcomic.php?issue=%s'
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)
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)') +
tagre("img", "src", r'.*?aprev.*?'))
2013-04-25 18:37:27 +00:00
help = 'Index format: nn'
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'
starter = bounceStarter
2013-04-13 18:58:00 +00:00
stripUrl = baseUrl + 'ap%s.html'
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()="<"]'
nextSearch = '//a[text()=">"]'
2012-06-20 19:58:13 +00:00
help = 'Index format: yymmdd'
def shouldSkipUrl(self, url, data):
"""Skip pages without images."""
2016-04-07 21:21:31 +00:00
return data.xpath('//iframe') # videos
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])
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
class AwkwardZombie(BasicScraper):
url = 'https://www.awkwardzombie.com/'
rurl = escape(url)
stripUrl = url + 'awkward-zombie/%s'
firstStripUrl = stripUrl % 'coin-battle'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%sawkward-zombie/[a-zA-Z-]+)' % rurl, before="prev"))
help = 'Index format: variable :('
class AxeCop(WordPressScraper):
url = 'http://axecop.com/comic/season-two/'