dosage/dosagelib/plugins/d.py

345 lines
14 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
2012-06-20 19:58:13 +00:00
2012-10-11 10:03:12 +00:00
from ..scraper import _BasicScraper
2013-03-18 17:15:19 +00:00
from ..helpers import indirectStarter, bounceStarter
2012-12-04 06:02:40 +00:00
from ..util import tagre
2012-06-20 19:58:13 +00:00
2012-12-07 23:45:18 +00:00
class DailyDose(_BasicScraper):
url = 'http://dailydoseofcomics.com/'
starter = indirectStarter(url,
2012-12-07 23:45:18 +00:00
compile(tagre("a", "href", r'(http://dailydoseofcomics\.com/[^"]+)', after="preview")))
stripUrl = url + '%s/'
2012-12-07 23:45:18 +00:00
imageSearch = compile(tagre("img", "src", r'([^"]+)', before="align(?:none|center)"))
prevSearch = compile(tagre("a", "href", r'(http://dailydoseofcomics\.com/[^"]+)', after="prev"))
help = 'Index format: stripname'
2012-06-20 19:58:13 +00:00
2013-04-10 16:19:38 +00:00
class DamnLol(_BasicScraper):
url = 'http://www.damnlol.com/'
rurl = escape(url)
stripUrl = url + '%s.html'
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev"))
imageSearch = (
compile(tagre("img", "src", r'(%si/[^"]+)' % rurl)),
compile(tagre("img", "src", r'(%spics/[^"]+)' % rurl)),
)
help = 'Index format: stripname-number'
2013-04-29 05:35:56 +00:00
description = u'Funny pictures from the internet. Thousands of them.'
2013-04-10 16:19:38 +00:00
starter = bounceStarter(url,
compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="next")))
@classmethod
def namer(cls, imageUrl, pageUrl):
ext = imageUrl.rsplit('.', 1)[1]
path = pageUrl.rsplit('/', 1)[1][:-5]
stripname, number = path.rsplit('-', 1)
return '%s-%s.%s' % (number, stripname, ext)
2012-12-08 20:30:51 +00:00
class Damonk(_BasicScraper):
url = 'http://www.damonk.com/'
stripUrl = url + 'd/%s.html'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '20060522'
2012-12-08 20:30:51 +00:00
imageSearch = compile(tagre("img", "src", r'(/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(/d/\d+\.html)') +
tagre("img", "src", r'/images/previous_day\.gif'))
help = 'Index format: yyyymmdd'
2012-12-13 20:05:27 +00:00
# XXX disallowed /search by robots.txt
class _DandyAndCompany(_BasicScraper):
url = 'http://www.dandyandcompany.com/'
2012-12-04 06:02:40 +00:00
stripUrl = None
multipleImagesPerStrip = True
imageSearch = compile(tagre("a", "href", r'(http://\d+\.bp\.blogspot\.com/[^"]+)', after="imageanchor"))
prevSearch = compile(tagre("a", "href", r"([^']+)", quote="'", after="Older Posts"))
help = 'Index format: none'
2012-06-20 19:58:13 +00:00
class DangerouslyChloe(_BasicScraper):
url = 'http://www.dangerouslychloe.com/'
stripUrl = url + 'strips-dc/%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % 'chapter_1_-_that_damned_girl'
imageSearch = compile(tagre("img", "src", r'([^"]*/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'([^"]*/strips-dc/[^"]+)', before="cn[id]prevt"))
help = 'Index format: name'
2012-06-20 19:58:13 +00:00
class DarkWings(_BasicScraper):
2013-04-14 07:02:14 +00:00
description = u"Dark Wings - You Can't Reach Heaven on Broken Wings"
url = 'http://www.flowerlarkstudios.com/dark-wings/'
rurl = escape(url)
2013-04-10 21:57:09 +00:00
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2008/05/31/page-i'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="navi-prev"))
2012-11-21 20:57:26 +00:00
help = 'Index format: yyyy/mm/dd/page-nn-mm'
2012-06-20 19:58:13 +00:00
2013-08-19 17:18:02 +00:00
class DarthsAndDroids(_BasicScraper):
url = 'http://www.darthsanddroids.net/'
stripUrl = url + 'episodes/%s.html'
firstStripUrl = stripUrl % '0001'
description = u'Darths & Droids is an "RPG screencap comic".'
prevSearch = compile(tagre("a", "href", r'(/episodes/\d\d\d\d.html)') + '<PREVIOUS' )
imageSearch = compile(tagre("img", "src", r'(/comics/darths\d\d\d\d\.jpg)'))
2013-03-21 17:33:16 +00:00
class DasLebenIstKeinPonyhof(_BasicScraper):
url = 'http://sarahburrini.com/wordpress/'
rurl = escape(url)
2013-03-21 17:33:16 +00:00
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'mein-erster-webcomic'
imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/\d+-\d+-\d+[^"]+)' % rurl))
2013-04-04 16:30:02 +00:00
multipleImagesPerStrip = True
prevSearch = compile(tagre("a", "href", r'(%scomic/[^"]+)' % rurl, after="navi-prev"))
2013-03-21 17:33:16 +00:00
help = 'Index format: stripname'
lang = 'de'
class DeadWinter(_BasicScraper):
2013-04-19 04:31:12 +00:00
description = u'd e a d . w i n t e r'
url = 'http://deadwinter.cc/'
stripUrl = url + 'page/%s'
firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre("img", "src", r"(/static/page/strip/\d+[^']+)", quote="'"))
prevSearch = compile(tagre("a", "href", r'(/page/\d+)') + "Previous")
help = 'Index format: number'
2012-06-20 19:58:13 +00:00
class DeathToTheExtremist(_BasicScraper):
2013-04-19 04:31:12 +00:00
description = u'Death To The Extremist'
url = 'http://www.dtecomic.com/'
stripUrl = url + '?n=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'"(comics/.*?)"')
prevSearch = compile(r'</a> <a href="(\?n=.*?)"><.+?/aprev.gif"')
help = 'Index format: nnn'
class DeepFried(_BasicScraper):
2013-04-19 04:31:12 +00:00
description = u'Deep Fried-The home of Weapon Brown, Clarissa and Beepo'
url = 'http://www.whatisdeepfried.com/'
rurl = escape(url)
2013-04-10 21:57:09 +00:00
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2001/09/16/new-world-out-of-order'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev"))
2013-04-10 21:57:09 +00:00
help = 'Index format: none'
2012-06-20 19:58:13 +00:00
2013-03-19 19:45:59 +00:00
class DemolitionSquad(_BasicScraper):
2013-04-14 07:02:14 +00:00
description = u'Demolitionsquad.de ist die erste deutsche Videospiel-Webcomic-Seite nach amerikanischen Vorbild und noch viel mehr als das. Auf Demolitionsquad.de findet der wissbegierige, spielebegeisterte Nutzer Comicstrips zu aktuellen Videospielen die ihm die Wartezeit auf den kommenden Top-Titel weiter ves\xfcssen.'
2013-03-19 19:45:59 +00:00
url = 'http://www.demolitionsquad.de/'
2014-01-20 18:01:47 +00:00
stripUrl = url + '?comicbeitrag=%s'
firstStripUrl = stripUrl % '181'
2013-03-19 19:45:59 +00:00
imageSearch = compile(tagre("img", "src", r'(uploads/pics/[^"]+)'))
2014-01-20 18:01:47 +00:00
prevSearch = compile(tagre("a", "href", r'(\?comicbeitrag=[^"]+)') +
tagre("img", "src", r'grafik/system/blaettern_zuruck_n\.gif'))
help = 'Index format: number'
2013-03-19 19:45:59 +00:00
lang = 'de'
2013-03-21 17:33:16 +00:00
class DerTodUndDasMaedchen(_BasicScraper):
url = 'http://www.cartoontomb.de/deutsch/tod2.php'
stripUrl = url + '?bild=%s.jpg'
firstStripUrl = stripUrl % '00_01_01'
imageSearch = compile(tagre("img", "src", r"(\.\./images/tod/teil2/[^']+)", quote="'"))
prevSearch = compile(tagre("a", "href", r"(/deutsch/tod2\.php\?bild=[^']+)", quote="'") + "zur&uuml;ck")
help = 'Index format: nn_nn_nn'
lang = 'de'
2014-02-18 20:00:19 +00:00
class DieFruehreifen(_BasicScraper):
url = 'http://www.die-fruehreifen.de/index.php'
stripUrl = url + '?id=%s&order=DESC'
firstStripUrl = stripUrl % '1'
2014-07-31 19:18:15 +00:00
imageSearch = compile(tagre("img", "src", r'([^"]*/strips/[Ff]rueh_?[Ss]trip_\d+.jpg)'))
2014-02-18 20:00:19 +00:00
prevSearch = compile(tagre("a", "href", r"(index\.php\?id=\d+&order=DESC)") + tagre("img","id",r"naechster"))
help = 'Index format: n (unpadded)'
lang = 'de'
2013-03-06 19:21:10 +00:00
class DieselSweeties(_BasicScraper):
2013-04-19 04:31:12 +00:00
description = u'diesel sweeties : robot webcomic & geeky music t-shirts'
2013-03-06 19:21:10 +00:00
url = 'http://www.dieselsweeties.com/'
stripUrl = url + 'archive/%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
2013-03-06 19:21:10 +00:00
imageSearch = compile(tagre("img", "src", r'(/hstrips/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(/archive/\d+)') +
tagre("img", "src", r'(?:http://www\.dieselsweeties\.com/ximages/blackbackarrow160.png|/ximages/prev\.gif)'))
help = 'Index format: n (unpadded)'
@classmethod
def namer(cls, imageUrl, pageUrl):
index = int(imageUrl.split('/')[-1].split('.')[0])
return 'sw%02d' % (index,)
class Dilbert(_BasicScraper):
url = 'http://dilbert.com/'
2015-01-16 18:05:53 +00:00
stripUrl = url + '/strip/%s/'
2013-03-19 19:45:18 +00:00
firstStripUrl = stripUrl % '1989-04-16'
2015-01-16 18:05:53 +00:00
starter = indirectStarter(url, compile(tagre("a", "href", r'(http://dilbert.com/strip/[0-9-]*)', after="Click to see")))
prevSearch = compile(tagre("a", "href", r'(/strip/\d+-\d+-\d+)', after="Older Strip"))
imageSearch = compile(tagre("img", "src", r'(http://assets.amuniversal.com/\w+)'))
2013-03-06 19:21:10 +00:00
help = 'Index format: yyyy-mm-dd'
2013-04-29 05:35:56 +00:00
description = u'A comic featuring satirical office humor about a white-collar, micromanaged office featuring the engineer Dilbert as the title character.'
2013-03-06 19:21:20 +00:00
@classmethod
def namer(cls, imageUrl, pageUrl):
2015-01-16 18:05:53 +00:00
name = pageUrl.rsplit("/", 1)[1]
return "%s" % name
2013-03-06 19:21:10 +00:00
2012-12-07 23:45:18 +00:00
class DMFA(_BasicScraper):
url = 'http://www.missmab.com/'
stripUrl = url + 'Comics/Vol_%s.php'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '001'
2012-12-07 23:45:18 +00:00
imageSearch = compile(tagre("img", "src", r'((?:Comics/|Vol)[^"]+)'))
multipleImagesPerStrip = True
prevSearch = compile(tagre("a", "href", r'((?:Comics/)?Vol[^"]+)')+
tagre("img", "src", r'(?:../)?Images/comicprev\.gif'))
help = 'Index format: nnn (normally, some specials)'
2012-06-20 19:58:13 +00:00
class DoemainOfOurOwn(_BasicScraper):
url = 'http://www.doemain.com/'
stripUrl = url + 'index.cgi/%s'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r"<img border='0' width='\d+' height='\d+' src='(/strips/\d{4}/\d{6}-[^\']+)'")
prevSearch = compile(r'<a href="(/index\.cgi/\d{4}-\d{2}-\d{2})"><img width="\d+" height="\d+" border="\d+" alt="Previous Strip"')
help = 'Index format: yyyy-mm-dd'
2013-03-15 06:04:19 +00:00
class DogHouseDiaries(_BasicScraper):
url = 'http://thedoghousediaries.com/'
rurl = escape(url)
2013-03-15 06:04:19 +00:00
stripUrl = url + '%s'
2015-04-15 16:51:45 +00:00
firstStripUrl = stripUrl % '34'
prevSearch = compile(r"<a id='previouslink' href='(http://thedoghousediaries.com/\d+)'")
2015-04-15 16:56:03 +00:00
imageSearch = compile(r"<img src='(dhdcomics/[^']+)'")
2013-03-15 06:04:19 +00:00
help = 'Index format: number'
2013-03-06 19:21:10 +00:00
class DominicDeegan(_BasicScraper):
url = 'http://www.dominic-deegan.com/'
stripUrl = url + 'view.php?date=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '2002-05-21'
2013-03-06 19:21:10 +00:00
imageSearch = compile(tagre("img", "src", r'(comics/[^"]+)'))
prevSearch = compile(r'"(view.php\?date=[^"]+)".+?prev21')
help = 'Index format: yyyy-mm-dd'
class DorkTower(_BasicScraper):
2013-04-14 07:02:14 +00:00
description = u'The Place for All Things Dork'
2013-03-06 19:21:10 +00:00
url = 'http://www.dorktower.com/'
rurl = escape(url)
2013-03-06 19:21:10 +00:00
stripUrl = url + '%s/'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1997/01/01/shadis-magazine-strip-1'
imageSearch = compile(tagre("div", "class", "entry-content") + "\s*<p>\s*" + tagre("img", "src", r'(%sfiles/[0-9]+/[0-9]+/[^"]*Dork[^"]+\.(?:gif|jpg))' % rurl, after=' alt'))
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl)+"Previous")
2013-03-06 19:21:10 +00:00
help = 'Index format: yyyy/mm/dd/stripname-dd-mm-yy'
2012-06-20 19:58:13 +00:00
class Dracula(_BasicScraper):
url = 'http://draculacomic.net/'
stripUrl = url + 'comic.php?comicID=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '0'
imageSearch = compile(tagre("img", "src", r'(comics/[^"]+)'))
2012-06-20 19:58:13 +00:00
prevSearch = compile(r'&nbsp;<a class="archivelink" href="(.+?)">&laquo; Prev</a>')
help = 'Index format: nnn'
class DreamKeepersPrelude(_BasicScraper):
url = 'http://www.dreamkeeperscomic.com/Prelude.php'
stripUrl = url + '?pg=%s'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'(images/PreludeNew/.+?)"')
prevSearch = compile(r'(Prelude.php\?pg=.+?)"')
help = 'Index format: n'
class DresdenCodak(_BasicScraper):
2013-04-19 04:31:12 +00:00
description = u'Dresden Codak'
url = 'http://dresdencodak.com/'
rurl = escape(url)
2012-11-13 18:10:19 +00:00
stripUrl = None
2013-04-10 21:57:09 +00:00
firstStripUrl = url + '2007/02/08/pom/'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
2013-04-10 21:57:09 +00:00
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl) +
2013-04-11 16:27:43 +00:00
tagre("img", "src", r"%sm_prev2?\.png" % rurl, quote=""))
starter = indirectStarter(url, compile(tagre("div", "id", "preview") +
tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+)' % rurl)))
2012-06-20 19:58:13 +00:00
2012-11-26 06:13:32 +00:00
2013-04-10 21:57:09 +00:00
class DrFun(_BasicScraper):
2013-04-13 18:58:00 +00:00
baseUrl = 'http://www.ibiblio.org/Dave/'
url = baseUrl + 'ar00502.htm'
stripUrl = baseUrl + 'ar%s.htm'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '00001'
imageSearch = compile(tagre("a", "href", r'(Dr-Fun/df\d+/df[^"]+)'))
multipleImagesPerStrip = True
prevSearch = compile(tagre("a", "href", r'([^"]+)') + 'Previous Week,')
help = 'Index format: nnnnn'
2013-04-29 05:35:56 +00:00
description = u'A series of bizarre one-panel gags. Topics range from the mundane to the obscure.'
2013-04-29 18:29:56 +00:00
endOfLife = True
2013-04-10 21:57:09 +00:00
2015-01-26 09:21:24 +00:00
class Drive(_BasicScraper):
description = u'DRIVE tells the story of a second Spanish empire, a galactic empire, and its looming war with a race called The Continuum of Makers.'
2015-01-26 09:21:24 +00:00
url = 'http://www.drivecomic.com/'
rurl = escape(url)
stripUrl = url + 'archive/%s.html'
firstStripUrl = stripUrl % '090815'
imageSearch = compile(tagre("img", "src", r'(http://cdn\.drivecomic\.com/strips/main/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(%sarchive/\d+\.html)' % rurl) + "Previous")
help = 'Index format: yymmdd'
2013-05-25 21:24:33 +00:00
# XXX navigation works only with JavaScript
class _DrMcNinja(_BasicScraper):
2013-04-19 04:31:12 +00:00
description = u'The Adventures of Dr. McNinja'
2013-03-25 18:47:44 +00:00
url = 'http://drmcninja.com/'
rurl = escape(url)
2013-03-25 18:47:44 +00:00
stripUrl = url + 'archives/comic/%s/'
firstStripUrl = stripUrl % '0p1'
imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%sarchives/comic/[^"]+)' % rurl, after="prev"))
2013-03-25 18:47:44 +00:00
help = 'Index format: episode number and page'
2013-03-06 19:21:10 +00:00
class Drowtales(_BasicScraper):
2013-04-13 18:58:00 +00:00
baseUrl = 'http://www.drowtales.com/'
rurl = escape(baseUrl)
url = baseUrl + 'mainarchive.php'
2013-03-06 19:21:10 +00:00
stripUrl = url + '?sid=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '4192'
2013-04-11 16:27:43 +00:00
imageSearch = (
compile(tagre("img", "src", r'(%smainarchive/[^"]+)' % rurl)),
compile(r'background-image:url\((mainarchive/[^\)]+center\.jpg)'),
)
2013-03-06 19:21:10 +00:00
prevSearch = compile(tagre("a", "href", r'(\?sid=\d+)', before="link_prev_top"))
help = 'Index format: number'
2013-02-06 21:08:36 +00:00
# XXX disallowed by robots.txt
class _DumbingOfAge(_BasicScraper):
url = 'http://www.dumbingofage.com/'
rurl = escape(url)
2013-02-06 21:08:36 +00:00
stripUrl = url + '%s/'
prevSearch = compile(tagre("a", "href", r'(%s\d+/[^"]+)' % rurl, after="prev"))
imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+[^"]+)' % rurl))
2013-02-06 21:08:36 +00:00
help = 'Index format: yyyy/comic/book-num/seriesname/stripname'
2014-02-27 14:08:07 +00:00
class DungeonsAndDenizens(_BasicScraper):
url = 'http://dungeond.com/'
2014-07-02 17:51:53 +00:00
stripUrl = url + r'\d+/\d+/\d+/%s/'
2014-02-27 14:08:07 +00:00
firstStripUrl = stripUrl % '08232005'
imageSearch = compile(tagre("img", "src", r'(%sfiles//comics/[^"]+)' % url))
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % url) + "Previous")
help = 'Index format: ddmmyyyy'