dosage/dosagelib/plugins/a.py

350 lines
13 KiB
Python
Raw Normal View History

# -*- coding: iso-8859-1 -*-
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
2014-01-05 15:50:57 +00:00
# Copyright (C) 2012-2014 Bastian Kleineidam
2012-11-21 20:57:26 +00:00
from re import compile, escape, MULTILINE
2012-09-26 12:42:28 +00:00
from ..util import tagre
2015-04-16 23:35:21 +00:00
from ..scraper import _BasicScraper, _ParserScraper
2012-12-02 17:35:06 +00:00
from ..helpers import regexNamer, bounceStarter, indirectStarter
2012-06-20 19:58:13 +00:00
class AbleAndBaker(_BasicScraper):
url = 'http://www.jimburgessdesign.com/comics/index.php'
stripUrl = url + '?comic=%s'
firstStripUrl = stripUrl % '1'
2012-09-26 12:42:28 +00:00
imageSearch = compile(tagre('img', 'src', r'(comics/.+)'))
prevSearch = compile(tagre('a', 'href', r'(.+\d+)') + '.+?previous.gif')
2012-06-20 19:58:13 +00:00
help = 'Index format: nnn'
class AbsurdNotions(_BasicScraper):
2013-04-13 18:58:00 +00:00
baseUrl = 'http://www.absurdnotions.org/'
url = baseUrl + 'page129.html'
stripUrl = baseUrl + 'page%s.html'
firstStripUrl = stripUrl % '1'
2012-09-26 12:42:28 +00:00
imageSearch = compile(tagre('img', 'src', r'(an[^"]+)'))
2012-12-02 17:35:06 +00:00
multipleImagesPerStrip = True
2012-09-26 12:42:28 +00:00
prevSearch = compile(tagre('a', 'href', r'([^"]+)') + tagre('img', 'src', 'nprev\.gif'))
2012-06-20 19:58:13 +00:00
help = 'Index format: n (unpadded)'
class AbstruseGoose(_BasicScraper):
2014-01-24 22:17:21 +00:00
url = 'http://abstrusegoose.com/'
rurl = escape(url)
starter = bounceStarter(url, compile(tagre('a', 'href', r'(%s\d+)' % rurl)+"Next »"))
stripUrl = url + '%s'
firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre('img', 'src', r'(http://abstrusegoose\.com/strips/[^<>"]+)'))
prevSearch = compile(tagre('a', 'href', r'(%s\d+)' % rurl) + r'&laquo; Previous')
nextSearch = compile(tagre('a', 'href', r'(%s\d+)' % rurl) + r'Next &raquo;')
2012-06-20 19:58:13 +00:00
help = 'Index format: n (unpadded)'
2013-12-04 02:56:54 +00:00
textSearch = compile(tagre("img", "title", r'([^"]+)'))
2012-06-20 19:58:13 +00:00
@classmethod
def namer(cls, imageUrl, pageUrl):
index = int(pageUrl.rstrip('/').split('/')[-1])
name = imageUrl.split('/')[-1].split('.')[0]
return 'c%03d-%s' % (index, name)
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="") + tagre('img', 'src', 'AVNavBack\.gif'))
2012-06-20 19:58:13 +00:00
help = 'Index format: nnn'
2013-04-10 16:36:33 +00:00
class Achewood(_BasicScraper):
url = 'http://www.achewood.com/'
stripUrl = url + 'index.php?date=%s'
firstStripUrl = stripUrl % '00000000'
imageSearch = compile(tagre("img", "src", r'(/comic\.php\?date=\d+)'))
prevSearch = compile(tagre("a", "href", r'(index\.php\?date=\d+)', after="Previous"))
help = 'Index format: mmddyyyy'
namer = regexNamer(compile(r'date=(\d+)'))
class AfterStrife(_BasicScraper):
2013-04-13 18:58:00 +00:00
baseUrl = 'http://afterstrife.com/'
rurl = escape(baseUrl)
stripUrl = baseUrl + '?p=%s'
2013-04-10 21:57:09 +00:00
url = stripUrl % '262'
firstStripUrl = stripUrl % '1'
imageSearch = compile(r'<img src="(%sstrips/.+?)"' % rurl)
2013-04-10 16:36:33 +00:00
prevSearch = compile(r'<a href="(.+?)" class="navi navi-prev"')
help = 'Index format: nnn'
class AGirlAndHerFed(_BasicScraper):
url = 'http://www.agirlandherfed.com/'
starter = bounceStarter(url,
compile(r'<a href="([^"]+)">[^>]+Back'))
stripUrl = url + '1.%s.html'
firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre("img", "src", r'(img/strip/[^"]+\.jpg)'))
prevSearch = compile(r'<a href="([^"]+)">[^>]+Back')
help = 'Index format: nnn'
2013-03-07 22:51:55 +00:00
class AhoiPolloi(_BasicScraper):
url = 'http://ahoipolloi.blogger.de/'
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'
2013-03-07 22:51:55 +00:00
imageSearch = compile(tagre('img', 'src', r'(/static/antville/ahoipolloi/images/[^"]+)'))
prevSearch = compile(tagre('a', 'href', r'(http://ahoipolloi\.blogger\.de/\?day=\d+)'))
help = 'Index format: yyyymmdd'
@classmethod
def namer(cls, imageUrl, pageUrl):
return imageUrl.rsplit('/', 1)[1]
2013-04-10 16:36:33 +00:00
class AirForceBlues(_BasicScraper):
url = 'http://www.afblues.com/'
stripUrl = url + 'wordpress/%s/'
firstStripUrl = stripUrl % '1997/09/07/need-a-clue-do-ya'
imageSearch = compile(tagre("img", "src", r'(http://www\.afblues\.com/wordpress/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'([^"]+)', after='Previous'))
help = 'Index format: yyyy/mm/dd/stripname'
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")
starter = indirectStarter(url, prevSearch)
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'
2012-06-20 19:58:13 +00:00
class Alice(_BasicScraper):
url = 'http://alice.alicecomics.com/'
rurl = escape(url)
stripUrl = url + '%s/'
imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/\d+-\d+-\d+[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%salicecomics/[^"]+)' % rurl, after="previous"))
help = 'Index format: name'
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'
2012-12-02 17:35:06 +00:00
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
2013-04-10 16:36:33 +00:00
class AlienShores(_BasicScraper):
2013-04-13 18:58:00 +00:00
baseUrl = 'http://alienshores.com/'
rurl = escape(baseUrl)
url = baseUrl + 'alienshores_band/'
2013-04-10 16:36:33 +00:00
stripUrl = url + '%s'
2013-04-10 21:57:09 +00:00
imageSearch = compile(tagre("img", "src", r'(%salienshores_band/wp-content/uploads/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev"))
2013-04-10 16:36:33 +00:00
help = 'Index format: yyyy/mm/dd/p<nn>/'
class AllTheGrowingThings(_BasicScraper):
url = 'http://growingthings.typodmary.com/'
rurl = escape(url)
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2009/04/21/all-the-growing-things'
2013-11-12 17:33:14 +00:00
imageSearch = compile(tagre("img", "src", r'(%sfiles/[^"]+)' % rurl))
2013-04-10 16:36:33 +00:00
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev"))
help = 'Index format: yyyy/mm/dd/strip-name'
2013-02-20 22:34:55 +00:00
class AlphaLuna(_BasicScraper):
url = 'http://www.alphaluna.net/'
stripUrl = url + 'issue-%s/'
firstStripUrl = stripUrl % '1/cover'
2013-02-20 22:34:55 +00:00
imageSearch = compile(tagre("a", "href", r'[^"]*/(?:issue-|support/upcoming)[^"]+') + tagre("img", "src", r'([^"]*/PAGINAS/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'([^"]+)') + tagre("img", "alt", "Prev"))
help = 'Index format: issue/page (e.g. 4/05)'
class AlphaLunaSpanish(AlphaLuna):
name = 'AlphaLuna/Spanish'
2013-03-08 21:33:05 +00:00
lang = 'es'
2013-02-20 22:34:55 +00:00
url = 'http://alphaluna.net/spanish/'
stripUrl = url + 'issue-%s/'
firstStripUrl = stripUrl % '1/portada'
2013-02-20 22:34:55 +00:00
2013-04-10 16:36:33 +00:00
class AlsoBagels(_BasicScraper):
url = 'http://alsobagels.com/'
rurl = escape(url)
stripUrl = url + 'index.php/comic/%s/'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%sindex\.php/comic/[^"]+)' % rurl, after="Previous"))
help = 'Index format: strip-name'
2012-06-20 19:58:13 +00:00
class Altermeta(_BasicScraper):
url = 'http://altermeta.net/'
2013-04-10 21:57:09 +00:00
rurl = escape(url)
stripUrl = url + 'archive.php?comic=%s'
firstStripUrl = stripUrl % '0'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'<img src="(comics/[^"]+)" />')
2013-04-10 21:57:09 +00:00
prevSearch = compile(r'<a href="([^"]+)"><img src="%stemplate/default/images/sasha/back\.png' % rurl)
2012-06-20 19:58:13 +00:00
help = 'Index format: n (unpadded)'
class AltermetaOld(Altermeta):
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'
2012-06-20 19:58:13 +00:00
prevSearch = compile(r'<a href="([^"]+)">Back')
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
2013-04-10 16:36:33 +00:00
class Amya(_BasicScraper):
url = 'http://www.amyachronicles.com/'
rurl = escape(url)
stripUrl = url + 'archives/%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '117'
2013-04-10 16:36:33 +00:00
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%sarchives/\d+)' % rurl, after="Previous"))
help = 'Index format: n'
class Angband(_BasicScraper):
url = 'http://angband.calamarain.net/'
stripUrl = url + 'view.php?date=%s'
firstStripUrl = stripUrl % '2005-12-30'
imageSearch = compile(tagre("img", "src", r'(comics/Scroll[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(view\.php\?date\=[^"]+)')+"Previous")
help = 'Index format: yyyy-mm-dd'
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="'"))
2012-11-19 20:20:34 +00:00
prevSearch = compile(tagre("a", "href", r'([^"]+)')+"&laquo; 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
2013-04-10 16:36:33 +00:00
class Annyseed(_BasicScraper):
2013-04-13 18:58:00 +00:00
baseUrl = 'http://www.colourofivy.com/'
rurl = escape(baseUrl)
url = baseUrl + 'annyseed_webcomic_latest.htm'
stripUrl = baseUrl + 'annyseed_webcomic%s.htm'
2013-04-10 16:36:33 +00:00
imageSearch = compile(tagre("img", "src", r'(Annyseed[^"]+)'))
2013-04-10 21:57:09 +00:00
prevSearch = compile(r'<a href="(%s[^"]+)"><img src="Last.gif"' % rurl)
2013-04-10 16:36:33 +00:00
help = 'Index format: nnn'
2013-02-06 21:08:36 +00:00
class Antics(_BasicScraper):
url = 'http://www.anticscomic.com/'
rurl = escape(url)
2013-02-06 21:08:36 +00:00
stripUrl = url + '?p=%s'
firstStripUrl = stripUrl % '3'
imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after='prev'))
2013-02-06 21:08:36 +00:00
help = 'Index format: number'
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)
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.*?'))
help = 'Index format: nn'
2015-04-16 23:35:21 +00:00
class ASofterWorld(_ParserScraper):
2013-03-06 19:21:10 +00:00
url = 'http://www.asofterworld.com/'
stripUrl = url + 'index.php?id=%s'
firstStripUrl = stripUrl % '1'
2015-04-16 23:35:21 +00:00
imageSearch = '//div[@id="comicimg"]//img'
prevSearch = '//div[@id="previous"]/a'
2013-03-06 19:21:10 +00:00
help = 'Index format: n (unpadded)'
2015-04-16 23:35:21 +00:00
2012-06-20 19:58:13 +00:00
class AstronomyPOTD(_BasicScraper):
2013-04-13 18:58:00 +00:00
baseUrl = 'http://antwrp.gsfc.nasa.gov/apod/'
url = baseUrl + 'astropix.html'
starter = bounceStarter(url,
2013-02-20 19:52:37 +00:00
compile(tagre("a", "href", r'(ap\d{6}\.html)') + "&gt;</a>"))
2013-04-13 18:58:00 +00:00
stripUrl = baseUrl + 'ap%s.html'
firstStripUrl = stripUrl % '061012'
2013-02-20 19:52:37 +00:00
imageSearch = compile(tagre("a", "href", r'(image/\d{4}/[^"]+)'))
2012-12-07 23:45:18 +00:00
multipleImagesPerStrip = True
2013-02-20 19:52:37 +00:00
prevSearch = compile(tagre("a", "href", r'(ap\d{6}\.html)') + "&lt;</a>")
2012-06-20 19:58:13 +00:00
help = 'Index format: yymmdd'
def shouldSkipUrl(self, url, data):
"""Skip pages without images."""
return url in (
2013-03-08 05:47:00 +00:00
self.stripUrl % '130217', # video
self.stripUrl % '130218', # video
self.stripUrl % '130226', # video
2013-04-28 17:58:38 +00:00
self.stripUrl % '130424', # video
)
2012-06-20 19:58:13 +00:00
@classmethod
def namer(cls, imageUrl, pageUrl):
return '%s-%s' % (pageUrl.split('/')[-1].split('.')[0][2:],
imageUrl.split('/')[-1].split('.')[0])
class ASkeweredParadise(_BasicScraper):
url = 'http://aspcomics.net/'
stripUrl = url + 'comic/%s'
firstStripUrl = stripUrl % '001'
2012-10-11 15:39:38 +00:00
imageSearch = compile(tagre("img", "src", r'(http://aspcomics\.net/sites/default/files[^"]*/asp\d+\.jpg)[^"]+'))
prevSearch = compile(tagre("a", "href", "(/comic/\d+)")+r"[^>]+Previous")
2012-06-20 19:58:13 +00:00
help = 'Index format: nnn'
class AxeCop(_BasicScraper):
url = 'http://axecop.com/'
rurl = escape(url)
2013-07-18 18:39:53 +00:00
starter = bounceStarter(url,
2013-11-12 17:33:14 +00:00
(
2014-01-24 22:17:21 +00:00
compile(tagre("a", "href", r'(%scomic/page-\d+-[^"]+/)' % rurl, after="navi-next")),
compile(tagre("a", "href", r'(%scomic/[^"]+/)' % rurl, after="navi-next")),
2013-11-12 17:33:14 +00:00
)
)
stripUrl = url + 'comic/%s/'
2013-07-18 18:39:53 +00:00
firstStripUrl = stripUrl % '0'
imageSearch = compile(tagre("img", "src", r'(http://mainsite\.axecop\.wpengine\.com/wp-content/uploads/sites/\d+/\d+/\d+/[^"]+)'))
2014-01-24 22:17:21 +00:00
prevSearch = compile(tagre("a", "href", r'(%scomic/[^"]+/)' % rurl, after="navi-prev"))
2013-11-18 21:01:30 +00:00
help = 'Index format: usually stripname'