dosage/dosagelib/plugins/d.py

249 lines
10 KiB
Python
Raw Normal View History

# -*- coding: iso-8859-1 -*-
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
2013-01-28 17:52:26 +00:00
# Copyright (C) 2012-2013 Bastian Kleineidam
2012-11-21 20:57:26 +00:00
2012-11-19 20:20:34 +00:00
from re import compile
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
2012-12-08 20:30:51 +00:00
class Damonk(_BasicScraper):
url = 'http://www.damonk.com/'
stripUrl = url + 'd/%s.html'
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'
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):
url = 'http://www.flowerlarkstudios.com/dark-wings/'
stripUrl = url + '%s'
2012-11-21 20:57:26 +00:00
imageSearch = compile(tagre("img", "src", r'(http://www\.flowerlarkstudios\.com/dark-wings/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://www\.flowerlarkstudios\.com/dark-wings/[^"]+)', after="navi-prev"))
help = 'Index format: yyyy/mm/dd/page-nn-mm'
2012-06-20 19:58:13 +00:00
2013-03-21 17:33:16 +00:00
class DasLebenIstKeinPonyhof(_BasicScraper):
url = 'http://sarahburrini.com/wordpress/'
stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'mein-erster-webcomic'
imageSearch = compile(tagre("img", "src", r'(http://sarahburrini\.com/wordpress/wp-content/uploads/\d+/\d+/\d+-\d+-\d+[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://sarahburrini\.com/wordpress/comic/[^"]+)', after="navi-prev"))
help = 'Index format: stripname'
lang = 'de'
class DeadWinter(_BasicScraper):
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):
url = 'http://www.dtecomic.com/'
stripUrl = url + '?n=%s'
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):
url = 'http://www.whatisdeepfried.com/'
stripUrl = url + '%s'
2012-11-21 20:57:26 +00:00
imageSearch = compile(tagre("img", "src", r'(http://www\.whatisdeepfried\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://www\.whatisdeepfried\.com/[^"]+)', after="prev"))
2012-06-20 19:58:13 +00:00
help = 'Index format: non'
2013-03-19 19:45:59 +00:00
class DemolitionSquad(_BasicScraper):
url = 'http://www.demolitionsquad.de/'
starter = indirectStarter(url,
compile(tagre("a", "href", r'(no_cache/comicstrips/einzelansicht/archive/[^"]+)')))
stripUrl = url + 'comicstrips/einzelansicht/article/%s/'
firstStripUrl = stripUrl % 'videospiele-hentai-master'
imageSearch = compile(tagre("img", "src", r'(uploads/pics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(comicstrips/einzelansicht/article/[^"]+)') +
tagre("img", "src", r'fileadmin/templates/images/button_back.gif'))
help = 'Index format: stripname'
lang = 'de'
def prevUrlModifier(self, url):
# remove CGI params
return url.split('?')[0]
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'
2013-03-06 19:21:10 +00:00
class DieselSweeties(_BasicScraper):
url = 'http://www.dieselsweeties.com/'
stripUrl = url + 'archive/%s'
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/'
stripUrl = url + '%s/'
2013-03-19 19:45:18 +00:00
firstStripUrl = stripUrl % '1989-04-16'
2013-03-18 17:15:19 +00:00
starter = bounceStarter(url,
compile(tagre("a", "href", r'(/\d+-\d+-\d+/)', after="STR_Next")))
2013-03-06 19:21:10 +00:00
prevSearch = compile(tagre("a", "href", r'(/\d+-\d+-\d+/)', after="STR_Prev"))
imageSearch = compile(tagre("img", "src", r'(/dyn/str_strip/[^"]+\.strip\.zoom\.gif)'))
help = 'Index format: yyyy-mm-dd'
2013-03-06 19:21:20 +00:00
@classmethod
def namer(cls, imageUrl, pageUrl):
ext = imageUrl.rsplit(".", 1)[1]
name = pageUrl.rsplit("/", 2)[1]
return "%s.%s" % (name, ext)
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'
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/'
stripUrl = url + '%s'
prevSearch = compile(tagre("a", "href", r'(http://thedoghousediaries\.com/\d+)', after="previous-comic"))
imageSearch = compile(tagre("img", "src", r'(http://thedoghousediaries\.com/comics/[^"]+)'))
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'
imageSearch = compile(tagre("img", "src", r'(comics/[^"]+)'))
prevSearch = compile(r'"(view.php\?date=[^"]+)".+?prev21')
help = 'Index format: yyyy-mm-dd'
class DorkTower(_BasicScraper):
url = 'http://www.dorktower.com/'
stripUrl = url + '%s/'
2013-03-07 17:24:12 +00:00
imageSearch = compile(tagre("img", "src", r'(http://www\.dorktower\.com/files/\d+/\d+/DorkTower[^"]+)'))
2013-03-06 19:21:10 +00:00
prevSearch = compile(tagre("a", "href", r'(http://www\.dorktower\.com/[^"]+)')+"Previous")
help = 'Index format: yyyy/mm/dd/stripname-dd-mm-yy'
2012-06-20 19:58:13 +00:00
class DrFun(_BasicScraper):
url = 'http://www.ibiblio.org/Dave/ar00502.htm'
2012-11-13 18:10:19 +00:00
stripUrl = 'http://www.ibiblio.org/Dave/ar%s.htm'
2013-01-24 06:53:47 +00:00
imageSearch = compile(r'<A HREF= "(Dr-Fun/df\d+/df[^"]+)">')
2012-12-04 06:02:40 +00:00
multipleImagesPerStrip = True
2012-06-20 19:58:13 +00:00
prevSearch = compile(r'<A HREF="(.+?)">Previous Week,')
help = 'Index format: nnnnn'
class Dracula(_BasicScraper):
url = 'http://draculacomic.net/'
stripUrl = url + 'comic.php?comicID=%s'
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):
url = 'http://dresdencodak.com/'
2012-11-13 18:10:19 +00:00
stripUrl = None
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'<img src="http://dresdencodak.com(/comics/.*?\.jpg)"')
prevSearch = compile(r'<a href="http://dresdencodak.com(/.*?)"><img src=http://dresdencodak.com/m_prev.png>')
starter = indirectStarter('http://dresdencodak.com/', compile(r'<div id="preview"><a href="http://dresdencodak.com/(\d+/\d+/\d+/.*?)">'))
2012-11-26 06:13:32 +00:00
2013-03-25 18:47:44 +00:00
class DrMcNinja(_BasicScraper):
url = 'http://drmcninja.com/'
stripUrl = url + 'archives/comic/%s/'
firstStripUrl = stripUrl % '0p1'
imageSearch = compile(tagre("img", "src", r'(http://drmcninja\.com/comics/\d+-\d+-\d+[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://drmcninja\.com/archives/comic/[^"]+)', after="prev"))
help = 'Index format: episode number and page'
2013-03-06 19:21:10 +00:00
class Drowtales(_BasicScraper):
url = 'http://www.drowtales.com/mainarchive.php'
stripUrl = url + '?sid=%s'
imageSearch = compile(tagre("img", "src", r'(http://www\.drowtales\.com/mainarchive/[^"]+)'))
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/'
stripUrl = url + '%s/'
prevSearch = compile(tagre("a", "href", r'(http://www\.dumbingofage\.com/\d+/[^"]+)', after="prev"))
imageSearch = compile(tagre("img", "src", r'(http://www\.dumbingofage\.com/comics/\d+-\d+-\d+[^"]+)'))
help = 'Index format: yyyy/comic/book-num/seriesname/stripname'