dosage/dosagelib/plugins/m.py

205 lines
6.6 KiB
Python
Raw Normal View History

# -*- coding: utf-8 -*-
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
2014-01-05 15:50:57 +00:00
# Copyright (C) 2012-2014 Bastian Kleineidam
# Copyright (C) 2015-2016 Tobias Gruetzmacher
2012-11-21 20:57:26 +00:00
from __future__ import absolute_import, division, print_function
from re import compile, escape, IGNORECASE
2012-06-20 19:58:13 +00:00
2015-04-23 07:12:24 +00:00
from ..scraper import _BasicScraper, _ParserScraper
from ..util import tagre
from .common import _ComicControlScraper, _WordPressScraper
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'
2013-04-25 19:09:42 +00:00
class MadamAndEve(_BasicScraper):
url = 'http://www.madamandeve.co.za/'
stripUrl = None
imageSearch = compile(tagre('img', 'src', r'(/cartoons/me\d{6}\.(gif|jpg))'))
2013-04-25 19:09:42 +00:00
multipleImagesPerStrip = True
2012-06-20 19:58:13 +00:00
2015-04-29 15:36:12 +00:00
2015-04-23 07:12:24 +00:00
class Magellan(_ParserScraper):
url = 'http://magellanverse.com/'
css = True
imageSearch = '#comic-1 > a:first-child img'
prevSearch = '.nav-previous > a'
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'
2015-04-26 11:47:38 +00:00
class ManlyGuysDoingManlyThings(_ParserScraper):
2013-02-13 16:52:49 +00:00
url = 'http://thepunchlineismachismo.com/'
stripUrl = url + 'archives/comic/%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '02222010'
2015-04-26 11:47:38 +00:00
css = True
imageSearch = "#comic img"
prevSearch = ".comic-nav-previous"
2013-02-13 16:52:49 +00:00
help = 'Index format: ddmmyyyy'
2015-04-29 15:36:12 +00:00
class MareInternum(_ParserScraper):
url = 'http://marecomic.com/'
stripUrl = url + 'comics/ch%s'
imageSearch = '//div[@id="comic"]//img'
prevSearch = '//a[@class="comic-nav-base comic-nav-previous"]'
help = 'Index format: <chapter>-page-<pagenum>'
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):
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"))
2013-07-10 16:43:53 +00:00
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)
2015-05-04 12:06:01 +00:00
class MaxOveracts(_ParserScraper):
url = 'http://occasionalcomics.com/'
stripUrl = url + '%s/'
css = True
imageSearch = '#comic img'
prevSearch = '.nav-previous > a'
help = 'Index format: nnn'
2013-07-10 16:43:53 +00:00
2012-06-20 19:58:13 +00:00
class Meek(_WordPressScraper):
url = 'http://www.meekcomic.com/'
2012-06-20 19:58:13 +00:00
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'
class Meiosis(_WordPressScraper):
url = 'http://meiosiswebcomic.com/'
class Melonpool(_WordPressScraper):
url = 'http://www.melonpool.com/'
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 Metacarpolis(_ComicControlScraper):
url = 'http://www.metacarpolis.com'
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
class MistyTheMouse(_WordPressScraper):
url = 'http://www.mistythemouse.com/'
prevSearch = '//a[@rel="prev"]'
firstStripUrl = 'http://www.mistythemouse.com/?p=12'
2014-02-27 16:45:29 +00:00
class MonsieurLeChien(_BasicScraper):
url = 'http://www.monsieur-le-chien.fr/'
stripUrl = url + 'index.php?planche=%s'
firstStripUrl = stripUrl % '2'
2014-02-27 21:30:02 +00:00
lang = 'fr'
2014-02-27 16:45:29 +00:00
imageSearch = compile(tagre("img", "src", r'(i/planches/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'([^"]+)') +
tagre("img", "src", "i/precedent.gif"))
2014-02-27 16:45:29 +00:00
help = 'Index format: n'
class Moonsticks(_ParserScraper):
url = "http://moonsticks.org/"
imageSearch = "//div[@class='entry']//img"
prevSearch = u"//a[text()='« Previous']"
2014-01-24 01:23:24 +00:00
class MrLovenstein(_BasicScraper):
url = 'http://www.mrlovenstein.com/'
stripUrl = url + 'comic/%s#comic'
firstStripUrl = stripUrl % '1'
imageSearch = (
# captures rollover comic
compile(tagre("div", "class", r'comic_image') + "\s*.*\s*" +
tagre("div", "style", r'display: none;') + "\s*.*\s*" +
tagre("img", "src", r'(/images/comics/[^"]+)')),
# captures standard comic
compile(tagre("img", "src", r'(/images/comics/[^"]+)',
before="comic_main_image")),
2014-01-24 01:23:24 +00:00
)
prevSearch = compile(tagre("a", "href", r'([^"]+)') +
tagre("img", "src", "/images/nav_left.png"))
2014-01-24 01:23:24 +00:00
textSearch = compile(r'<meta name="description" content="(.+?)" />')
help = 'Index Format: n'
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
2015-05-31 11:39:04 +00:00
class MysteriesOfTheArcana(_ParserScraper):
url = 'http://mysteriesofthearcana.com/'
2015-05-31 11:39:04 +00:00
imageSearch = '//div[@id="comic"]//img'
prevSearch = '//a[@class="navprevious"]'