dosage/dosagelib/plugins/m.py

151 lines
5.6 KiB
Python
Raw Normal View History

# -*- coding: iso-8859-1 -*-
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
2013-02-05 18:51:46 +00:00
# Copyright (C) 2012-2013 Bastian Kleineidam
2012-11-21 20:57:26 +00:00
from re import compile, escape, IGNORECASE
2012-06-20 19:58:13 +00:00
2012-10-11 10:03:12 +00:00
from ..scraper import _BasicScraper
from ..util import tagre
2012-06-20 19:58:13 +00:00
2013-04-10 21:57:09 +00:00
class MacHall(_BasicScraper):
url = 'http://www.machall.com/'
stripUrl = url + 'view.php?date=%s'
firstStripUrl = stripUrl % '2000-11-07'
imageSearch = compile(r'<img src="(comics/.+?)"')
prevSearch = compile(r'<a href="(.+?)"><img[^>]+?src=\'drop_shadow/previous.gif\'>')
help = 'Index format: yyyy-mm-dd'
2012-11-21 20:57:26 +00:00
# broken links - disable for now
2013-04-25 19:09:42 +00:00
class MadamAndEve(_BasicScraper):
url = 'http://www.madamandeve.co.za/week_of_cartns.php'
stripUrl = None
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'<IMG BORDER="0" SRC="(cartoons/me\d{6}\.(gif|jpg))">')
prevSearch = compile(r'<a href="(weekend_cartoon.php)"')
2013-04-25 19:09:42 +00:00
multipleImagesPerStrip = True
2012-06-20 19:58:13 +00:00
class MagickChicks(_BasicScraper):
url = 'http://www.magickchicks.com/'
stripUrl = url + 'strips-mc/%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % 'tis_but_a_trifle'
imageSearch = compile(tagre("img", "src", r'([^"]*/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'([^"]*/strips-mc/[^"]+)', before="cn[id]prevt"))
help = 'Index format: name'
2013-02-13 16:52:49 +00:00
class ManlyGuysDoingManlyThings(_BasicScraper):
2013-04-14 07:02:14 +00:00
description = u'Manly Guys Doing Manly Things \xbb Updated Mondays or whenever I feel like it'
2013-02-13 16:52:49 +00:00
url = 'http://thepunchlineismachismo.com/'
rurl = escape(url)
2013-02-13 16:52:49 +00:00
stripUrl = url + 'archives/comic/%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '02222010'
imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/\d+-\d+-\d+[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%sarchives/comic/[^"]+)' % rurl, after="previous"))
2013-02-13 16:52:49 +00:00
help = 'Index format: ddmmyyyy'
2012-06-20 19:58:13 +00:00
class Marilith(_BasicScraper):
url = 'http://www.marilith.com/'
stripUrl = url + 'archive.php?date=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '20041215'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'<img src="(comics/.+?)" border')
prevSearch = compile(r'<a href="(archive\.php\?date=.+?)"><img border=0 name=previous_day')
help = 'Index format: yyyymmdd'
2013-07-10 16:43:53 +00:00
class MarriedToTheSea(_BasicScraper):
description = u'comics by Drew & Natalie Dee - Updates daily at midnight'
url = 'http://www.marriedtothesea.com/'
rurl = escape(url)
2013-07-18 18:39:53 +00:00
stripUrl = url + '%s'
2013-07-10 16:43:53 +00:00
firstStripUrl = stripUrl % '022806'
imageSearch = compile(tagre("img", "src", r'(%s\d+/[^"]+)' % rurl, before="overflow"))
prevSearch = compile(tagre("a", "href", r'([^"]+)') + "&lt;&lt; Yesterday")
help = 'Index format: mmddyy'
@classmethod
def namer(cls, imageUrl, pageUrl):
unused, date, filename = imageUrl.rsplit('/', 2)
return '%s-%s' % (date, filename)
2012-06-20 19:58:13 +00:00
class Meek(_BasicScraper):
url = 'http://www.meekcomic.com/'
stripUrl = url + '%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '2008/12/27/chapter-1-cover '
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'meekcomic.com(/comics/.+?)"')
prevSearch = compile(r'\s.+?(http://www.meekcomic.com/.+?)".+?Previous<')
help = 'Index format: yyyy/mm/dd/ch-p/'
class MegaTokyo(_BasicScraper):
url = 'http://megatokyo.com/'
stripUrl = url + 'strip/%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'"(strips/.+?)"', IGNORECASE)
prevSearch = compile(r'"(./strip/\d+?)">Prev')
help = 'Index format: nnnn'
2012-12-08 20:30:51 +00:00
class Meiosis(_BasicScraper):
url = 'http://meiosiswebcomic.com/'
rurl = escape(url)
stripUrl = url + '%s/'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '2006/10/10142006'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="navi-prev"))
2012-12-08 20:30:51 +00:00
help = 'Index format: yyyy/mm/ddmmyyyy'
class MenageA3(_BasicScraper):
adult = True
url = 'http://www.ma3comic.com/'
stripUrl = url + 'strips-ma3/%s'
imageSearch = compile(tagre("img", "src", r'([^"]*/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'([^"]*/strips-ma3/[^"]+)', before="cn[id]prev"))
help = 'Index format: name'
class Melonpool(_BasicScraper):
2013-04-14 07:02:14 +00:00
description = u"Star Trek Meets Gilligan's Island"
url = 'http://www.melonpool.com/'
rurl = escape(url)
stripUrl = url + '?p=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '41'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev"))
2012-11-21 20:57:26 +00:00
help = 'Index format: n'
2012-06-20 19:58:13 +00:00
class Misfile(_BasicScraper):
url = 'http://www.misfile.com/'
stripUrl = url + '?date=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '2004-02-22'
2012-12-04 06:02:40 +00:00
imageSearch = compile(tagre("img", "src", r"(comics/[^']+)", quote="'"))
prevSearch = compile(tagre("link", "href", r"([^']+)", quote="'", before="Previous"))
2012-11-21 20:57:26 +00:00
help = 'Index format: yyyy-mm-dd'
2012-06-20 19:58:13 +00:00
2013-03-20 20:42:04 +00:00
class MyCartoons(_BasicScraper):
url = 'http://mycartoons.de/'
rurl = escape(url)
stripUrl = url + 'page/%s'
imageSearch = (
compile(tagre("img", "src", r'(%swp-content/cartoons/(?:[^"]+/)?\d+-\d+-\d+[^"]+)' % rurl)),
compile(tagre("img", "src", r'(%scartoons/[^"]+/\d+-\d+-\d+[^"]+)' % rurl)),
)
prevSearch = compile(tagre("a", "href", r'(%spage/[^"]+)' % rurl) + "&laquo;")
help = 'Index format: number'
lang = 'de'
2013-03-20 20:42:04 +00:00
2012-06-20 19:58:13 +00:00
class MysteriesOfTheArcana(_BasicScraper):
url = 'http://mysteriesofthearcana.com/'
stripUrl = url + 'index.php?action=comics&cid=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
2012-11-21 20:57:26 +00:00
imageSearch = compile(tagre("img", "src", r'(image\.php\?type=com&i=[^"]+)'))
2012-12-04 06:02:40 +00:00
prevSearch = compile(tagre("a", "href", r'(index\.php[^"]+)', after="navprevious"))
2012-06-20 19:58:13 +00:00
help = 'Index format: n (unpadded)'