2012-06-20 20:41:04 +00:00
|
|
|
# -*- 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
|
|
|
|
2012-11-26 06:13:32 +00:00
|
|
|
from re import compile, IGNORECASE
|
2012-06-20 19:58:13 +00:00
|
|
|
|
2012-10-11 10:03:12 +00:00
|
|
|
from ..scraper import _BasicScraper
|
2012-11-26 06:13:32 +00:00
|
|
|
from ..util import tagre
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
|
|
|
class WayfarersMoon(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.wayfarersmoon.com/'
|
|
|
|
stripUrl = url + 'index.php?page=%s'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'<img src="(/admin.+?)"')
|
|
|
|
prevSearch = compile(r'<a href="(.+?)".+?btn_back.gif')
|
|
|
|
help = 'Index format: nn'
|
|
|
|
|
|
|
|
|
2013-02-06 21:08:36 +00:00
|
|
|
class WastedTalent(_BasicScraper):
|
|
|
|
url = 'http://www.wastedtalent.ca/'
|
|
|
|
stripUrl = url + 'comic/%s'
|
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://www\.wastedtalent\.ca/sites/default/files/imagecache/comic_full/comics/\d+/[^"]+)'))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(/comic/[^"]+)', after="comic_prev"))
|
|
|
|
help = 'Index format: stripname'
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class WhiteNinja(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.whiteninjacomics.com/comics.shtml'
|
2012-11-13 18:10:19 +00:00
|
|
|
stripUrl = 'http://www.whiteninjacomics.com/comics/%s.shtml'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'<img src=(/images/comics/(?!t-).+?\.gif) border=0')
|
|
|
|
prevSearch = compile(r'(/comics/.+?shtml).+?previous')
|
|
|
|
help = 'Index format: s (comic name)'
|
|
|
|
|
|
|
|
|
|
|
|
class WhiteNoise(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.wncomic.com/archive.php'
|
2012-11-13 18:10:19 +00:00
|
|
|
stripUrl = 'http://www.wncomic.com/archive_comments.php?strip_id=%s'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'(istrip_files/strips/.+?)"')
|
|
|
|
prevSearch = compile(r'First .+?"(archive.+?)".+?top_back')
|
|
|
|
help = 'Index format: n'
|
|
|
|
|
|
|
|
|
|
|
|
class WhyTheLongFace(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.absurdnotions.org/wtlf200709.html'
|
2012-11-13 18:10:19 +00:00
|
|
|
stripUrl = 'http://www.absurdnotions.org/wtlf%s.html'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'<img src="(http://www.absurdnotions.org/wtlf.+?|lf\d+.\w{1,4})"', IGNORECASE)
|
2012-12-04 06:02:40 +00:00
|
|
|
multipleImagesPerStrip = True
|
2012-06-20 19:58:13 +00:00
|
|
|
prevSearch = compile(r'HREF="(.+?)"><IMG SRC="nprev.gif" ')
|
|
|
|
help = 'Index format: yyyymm'
|
|
|
|
|
|
|
|
|
|
|
|
class Wigu(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://wigucomics.com/'
|
|
|
|
stripUrl = url + 'adventures/index.php?comic=%s'
|
2012-11-26 06:13:32 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(/adventures/comics/[^"]+)'))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(/adventures/index\.php\?comic=\d+)', after="go back"))
|
|
|
|
help = 'Index format: n'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2013-02-06 21:08:36 +00:00
|
|
|
class Wonderella(_BasicScraper):
|
|
|
|
url = 'http://nonadventures.com/'
|
|
|
|
stripUrl = url + '%s/'
|
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://nonadventures\.com/comics/[^"]+)'))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(http://nonadventures\.com/\d+/\d+/\d+/[^"]+)', after="prev"))
|
|
|
|
help = 'Index format: yyyy/mm/dd/name'
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class WotNow(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://shadowburn.binmode.com/wotnow/'
|
|
|
|
stripUrl = url + 'comic.php?comic_id=%s'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'<IMG SRC="(comics/.+?)"')
|
|
|
|
prevSearch = compile(r'<A HREF="(.+?)"><IMG SRC="images/b_prev.gif" ')
|
|
|
|
help = 'Index format: n (unpadded)'
|
|
|
|
|
|
|
|
|
2012-12-13 20:05:27 +00:00
|
|
|
# XXX disallowed by robots.txt
|
|
|
|
class _WorldOfWarcraftEh(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://woweh.com/'
|
2012-11-20 17:53:53 +00:00
|
|
|
stripUrl = None
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'http://woweh.com/(comics/.+?)"')
|
|
|
|
prevSearch = compile(r'woweh.com/(\?p=.+:?)".+:?="prev')
|
|
|
|
|
|
|
|
|
|
|
|
class Wulffmorgenthaler(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://wumocomicstrip.com/'
|
|
|
|
stripUrl = url + '%s/'
|
2012-12-04 06:02:40 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(/img/strip/[^/"]+)'))
|
2012-11-26 06:13:32 +00:00
|
|
|
prevSearch = compile(tagre("a", "href", r'([^"]+)') + "<span>Previous")
|
|
|
|
help = 'Index format: yyyy/mm/dd'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
|
|
|
class WhiteNoise(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.wncomic.com/archive.php'
|
2012-11-13 18:10:19 +00:00
|
|
|
stripUrl = 'http://www.wncomic.com/archive_comments.php?strip_id=%s'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'(istrip_files/strips/.+?)"')
|
|
|
|
prevSearch = compile(r'</a><a href="(.+?)"><img src="images/top_back.jpg" ')
|
|
|
|
help = 'Index format: n'
|
|
|
|
|
|
|
|
|
|
|
|
class WapsiSquare(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://wapsisquare.com/'
|
|
|
|
stripUrl = url + 'comic/%s'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'<img src="(http://wapsisquare.com/comics/.+?)"')
|
|
|
|
prevSearch = compile(r'<a href="(.+?)"[^>]+?>Previous</a>')
|
|
|
|
help = 'Index format: strip-name'
|
|
|
|
|
|
|
|
|
|
|
|
class WeCanSleepTomorrow(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://wecansleeptomorrow.com/'
|
|
|
|
stripUrl = url + '%s/'
|
2012-11-26 06:13:32 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://wecansleeptomorrow\.com/comics/[^"]+)'))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(http://wecansleeptomorrow\.com/[^"]+)', after="prev"))
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: yyyy/mm/dd/stripname'
|
|
|
|
|
|
|
|
|
|
|
|
class Wondermark(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://wondermark.com/'
|
|
|
|
stripUrl = url + '%s/'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'<img src="(http://wondermark.com/c/.+?)"')
|
|
|
|
prevSearch = compile(r'<a href="(.+?)" rel="prev">')
|
|
|
|
help = 'Index format: nnn'
|