# -*- coding: iso-8859-1 -*-
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
# Copyright (C) 2012-2013 Bastian Kleineidam
from re import compile, MULTILINE, IGNORECASE, sub
from os.path import splitext
from ..scraper import _BasicScraper
from ..helpers import indirectStarter, bounceStarter
from ..util import tagre
class SailorsunOrg(_BasicScraper):
url = 'http://sailorsun.org/'
stripUrl = url + '?p=%s'
imageSearch = compile(tagre("img", "src", r'(http://sailorsun\.org/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://sailorsun\.org/\?p=\d+)', after="prev"))
help = 'Index format: n (unpadded)'
class SamAndFuzzy(_BasicScraper):
url = 'http://www.samandfuzzy.com/'
stripUrl = 'http://samandfuzzy.com/%s'
imageSearch = compile(r'(/comics/.+?)" alt')
prevSearch = compile(r'"><<', IGNORECASE)
help = 'Index format: nnn'
starter = indirectStarter(url,
compile(r'SEXY LOSERS Latest SL Comic \(#\d+\)', IGNORECASE))
@classmethod
def namer(cls, imageUrl, pageUrl):
index = pageUrl.split('/')[-1].split('.')[0]
title = imageUrl.split('/')[-1].split('.')[0]
return index + '-' + title
class ShadowGirls(_BasicScraper):
url = 'http://www.shadowgirlscomic.com/'
stripUrl = url + 'comics/%s'
imageSearch = compile(tagre("img", "src", r'([^"]*/comics/[^"]*)'))
prevSearch = compile(tagre("a", "href", r'([^"]*)', after='navi-prev'))
help = 'Index format: custom'
starter = indirectStarter(url, compile(tagre("a", "href", r'([^"]*/comics/[^"]+)')))
class Sheldon(_BasicScraper):
url = 'http://www.sheldoncomics.com/'
stripUrl = url + 'archive/%s.html'
imageSearch = compile(tagre("img", "src", r'(/strips/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(/archive/\d+\.html)', after="sidenav-prev"))
help = 'Index format: yymmdd'
class Shivae(_BasicScraper):
url = 'http://shivae.net/'
stripUrl = url + 'blog/%s/'
imageSearch = compile(tagre("img", "src", r'(http://shivae\.net/files/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://shivae\.net/blog/[^"]+)', after="Previous"))
help = 'Index format: yyyy/mm/dd/stripname'
# XXX disallowed by robots.txt
class _Shortpacked(_BasicScraper):
url = 'http://www.shortpacked.com/'
stripUrl = url + '%s/'
imageSearch = compile(tagre("img", "src", r'(http://www\.shortpacked\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://www\.shortpacked\.com/\d+/comic/[^"]+)', after="prev"))
help = 'Index format: yyyy/comic/book-nn/mm-name1/name2'
class SinFest(_BasicScraper):
name = 'KeenSpot/SinFest'
url = 'http://www.sinfest.net/'
stripUrl = url + 'archive_page.php?comicID=%s'
imageSearch = compile(r']+?>')
help = 'Index format: yymmdd'
class SMBC(_BasicScraper):
url = 'http://www.smbc-comics.com/'
stripUrl = url + 'index.php?db=comics&id=%s'
imageSearch = compile(r'')
prevSearch = compile(r'131,13,216,84"\n\s+href="(.+?)#comic"\n>', MULTILINE)
help = 'Index format: nnnn'
class SnowFlakes(_BasicScraper):
url = 'http://www.snowflakescomic.com/'
stripUrl = url + '?id=%s&sl=%s'
firstStripUrl = stripUrl % ('103', '1')
imageSearch = (
compile(tagre("img", "src", r'(comics/[^"]+)')),
compile(tagre("img", "src", r'(http://www.snowflakescomic.com/comics/[^"]+)')),
)
prevSearch = compile(tagre("a", "href", r'(/\?id=\d+\&sl=\d)', quote="") +
tagre("img", "src", r'images/nav_prior-ON\.gif'))
help = 'Index format: number'
@classmethod
def starter(cls):
return cls.stripUrl % ('530', '5')
def getStripIndexUrl(self, index):
return self.stripUrl % (index, index[0])
@classmethod
def namer(cls, imageUrl, pageUrl):
"""Use strip index number for image name."""
index = int(compile(r'id=(\d+)').search(pageUrl).group(1))
ext = imageUrl.rsplit('.', 1)[1]
return "SnowFlakes-%d.%s" % (index, ext)
def shouldSkipUrl(self, url):
"""Skip pages without images."""
return url in (
self.stripUrl % ('279', '2'), # no comic
self.stripUrl % ('278', '2'), # no comic
self.stripUrl % ('277', '2'), # no comic
self.stripUrl % ('276', '2'), # no comic
self.stripUrl % ('275', '2'), # no comic
self.stripUrl % ('214', '2'), # no comic
)
class SnowFlame(_BasicScraper):
url = 'http://www.snowflamecomic.com/'
stripUrl = url + '?comic=snowflame-%s-%s'
firstStripUrl = stripUrl % ('01', '01')
imageSearch = compile(tagre("img", "src", r'(http://www\.snowflamecomic\.com/wp-content/uploads/\d+/\d+/[^"]+)'))
prevSearch = compile(tagre("span", "class", "mininav-prev") +
tagre("a", "href", r'(http://www\.snowflamecomic\.com/\?comic=snowflame[^"]+)'))
starter = bounceStarter(url,
compile(tagre("span", "class", "mininav-next") +
tagre("a", "href", r'(http://www\.snowflamecomic\.com/\?comic=snowflame[^"]+)')))
help = 'Index format: chapter-page'
def getStripIndexUrl(self, index):
return self.stripUrl % index.split('-')
@classmethod
def namer(cls, imageUrl, pageUrl):
prefix, filename = imageUrl.rsplit('/', 1)
ro = compile(r'snowflame-([^-]+)-([^-]+)')
mo = ro.search(pageUrl)
chapter = mo.group(1)
page = mo.group(2)
return "%s-%s-%s" % (chapter, page, filename)
class SodiumEyes(_BasicScraper):
url = 'http://sodiumeyes.com/'
stripUrl = url + '%s/'
imageSearch = compile(tagre("img", "src", r'(http://sodiumeyes\.com/comic/[^ ]+)', quote=""))
prevSearch = compile(tagre("a", "href", r'(http://sodiumeyes\.com/[^"]+)', after="prev"))
help = 'Index format: yyyy/mm/dd/stripname'
class Sorcery101(_BasicScraper):
url = 'http://www.sorcery101.net/sorcery-101/'
stripUrl = url + '%s/'
imageSearch = compile(tagre("img", "src", r'(http://www\.sorcery101\.net/wp-content/uploads/\d+/\d+/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://www\.sorcery101\.net/sorcery-101/[^"]+)', after="previous-"))
help = 'Index format: stripname'
class SpaceTrawler(_BasicScraper):
url = 'http://spacetrawler.com/'
stripUrl = url + '%s/'
imageSearch = compile(tagre("img", "src", r'(http://spacetrawler\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://spacetrawler\.com/\d+/\d+/\d+/[^"]+)', after="navi-prev"))
help = 'Index format: yyyy/mm/dd/stripname'
class SpareParts(_BasicScraper):
baseUrl = 'http://www.sparepartscomics.com/'
url = baseUrl + 'comics/?date=20080328'
stripUrl = baseUrl + 'comics/index.php?date=%s'
imageSearch = compile(tagre("img", "src", r'(http://www\.sparepartscomics\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(index\.php\?date=\d+)', quote="'") + "Previous Comic")
help = 'Index format: yyyymmdd'
class Spinnerette(_BasicScraper):
url = 'http://www.spinnyverse.com/'
stripUrl = url + '%s/'
imageSearch = compile(tagre("img", "src", r'(http://www\.spinnyverse\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://www\.spinnyverse\.com/[^"]+)', before="Previous Comic"))
help = 'Index format: number'
class SPQRBlues(_BasicScraper):
url = 'http://spqrblues.com/IV/'
stripUrl = url + '?p=%s'
imageSearch = compile(tagre("img", "src", r'(http://spqrblues\.com/IV/comics/\d+\.png)'))
prevSearch = compile(tagre("a", "href", r'(http://spqrblues\.com/IV/\?p=\d+)', after="prev"))
help = 'Index format: number'
# XXX disallowed by robots.txt
class _StationV3(_BasicScraper):
url = 'http://www.stationv3.com/'
stripUrl = url + 'd/%s.html'
imageSearch = compile(tagre("img", "src", r'(http://www\.stationv3\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://www\.stationv3\.com/d/\d+\.html)') +
tagre("img", "src", r'http://www\.stationv3\.com/images/previous\.gif'))
help = 'Index format: yyyymmdd'
class StickyDillyBuns(_BasicScraper):
url = 'http://www.stickydillybuns.com/'
stripUrl = url + 'strips-sdb/%s'
imageSearch = compile(tagre("img", "src", r'([^"]*/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'([^"]*/strips-sdb/[^"]+)', before="cn[id]prev"))
help = 'Index format: name'
class Stubble(_BasicScraper):
url = 'http://stubblecomics.com/'
stripUrl = url + '?p=%s'
imageSearch = compile(tagre("img", "src", r'(http://stubblecomics\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://stubblecomics\.com/\?p=\d+)', after="navi-prev"))
help = 'Index format: number'
class StuffNoOneToldMe(_BasicScraper):
url = 'http://www.snotm.com/'
stripUrl = url + '%s.html'
firstStripUrl = stripUrl % '2010/05/01'
olderHref = r"(http://www\.snotm\.com/\d+/\d+/[^']+\.html)"
starter = indirectStarter(url,
compile(tagre("a", "href", olderHref, quote="'")))
imageSearch = (
compile(tagre("img", "src", r'(http://i\.imgur\.com/[^"]+)') + r"(?:|
)"),
compile(tagre("img", "src", r'(http://\d+\.bp\.blogspot\.com/[^"]+)') + r"(?:(?: )?|)"),
compile(tagre("img", "src", r'(https://lh\d+\.googleusercontent\.com/[^"]+)') + r""),
)
prevSearch = compile(tagre("a", "href", olderHref, quote="'", before="older-link"))
multipleImagesPerStrip = True
help = 'Index format: yyyy/mm/stripname'
@classmethod
def namer(cls, imageUrl, pageUrl):
"""Use page URL to construct meaningful image name."""
parts, year, month, stripname = pageUrl.rsplit('/', 3)
stripname = stripname.rsplit('.', 1)[0]
parts, imagename = imageUrl.rsplit('/', 1)
return '%s-%s-%s-%s' % (year, month, stripname, imagename)
def shouldSkipUrl(self, url):
"""Skip pages without images."""
return url in (
self.stripUrl % '2012/08/self-rant', # no comic
self.stripUrl % '2012/06/if-you-wonder-where-ive-been', # video
self.stripUrl % '2011/10/i-didnt-make-this-nor-have-anything-to', # video
self.stripUrl % '2010/12/first-snotm-fans-in-sao-paulo', # no comic
self.stripUrl % '2010/11/ear-infection', # no comic
)
class StrawberryDeathCake(_BasicScraper):
url = 'http://strawberrydeathcake.com/'
stripUrl = url + 'archive/%s/'
imageSearch = compile(tagre("img", "src", r'(http://strawberrydeathcake\.com/wp-content/webcomic/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://strawberrydeathcake\.com/archive/[^"]+)', after="previous"))
help = 'Index format: stripname'
class SuburbanTribe(_BasicScraper):
url = 'http://www.pixelwhip.com/'
stripUrl = url + '?p=%s'
imageSearch = compile(tagre("img", "src", r'(http://www\.pixelwhip\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://www\.pixelwhip\.com/\?p=\d+)', after="prev"))
help = 'Index format: nnnn'
class SomethingPositive(_BasicScraper):
url = 'http://www.somethingpositive.net/'
stripUrl = url + 'sp%s.shtml'
imageSearch = compile(tagre("img", "src", r'(sp\d+\.png)'))
prevSearch = compile(tagre("a", "href", r'(sp\d+\.shtml)') +
"(?:" + tagre("img", "src", r'images/previous\.gif') + "|Previous)")
help = 'Index format: mmddyyyy'
class StarCrossdDestiny(_BasicScraper):
url = 'http://www.starcrossd.net/comic.html'
stripUrl = 'http://www.starcrossd.net/archives/%s.html'
imageSearch = compile(tagre("img", "src", r'(http://www\.starcrossd\.net/(?:ch1|strips|book2)/[^"]+)'))
prevSearch = compile(r']*"[^"]*"[^>]*>prev', IGNORECASE)
help = 'Index format: nnnnnnnn'
@classmethod
def namer(cls, imageUrl, pageUrl):
if imageUrl.find('ch1') == -1:
# At first all images were stored in a strips/ directory but that was changed with the introduction of book2
imageUrl = sub('(?:strips)|(?:images)','book1',imageUrl)
elif not imageUrl.find('strips') == -1:
imageUrl = imageUrl.replace('strips/','')
directory, filename = imageUrl.split('/')[-2:]
filename, extension = splitext(filename)
return directory + '-' + filename
class Spamusement(_BasicScraper):
url = 'http://spamusement.com/'
stripUrl = url + 'index.php/comics/view/%s'
imageSearch = compile(r'', IGNORECASE)
help = 'Index format: n (unpadded)'
starter = indirectStarter(url, prevSearch)
# XXX disallowed by robots.txt
class _StrangeCandy(_BasicScraper):
url = 'http://www.strangecandy.net/'
stripUrl = url + 'd/%s.html'
imageSearch = compile(tagre("img", "src", r'(/comics/\d+\.jpg)'))
prevSearch = compile(tagre("a", "href", r'(/d/\d+\.html)') + tagre("img", "alt", "Previous comic"))
help = 'Index format: yyyyddmm'
class SupernormalStep(_BasicScraper):
url = 'http://supernormalstep.com/'
stripUrl = url + '?p=%s'
imageSearch = compile(tagre("img", "src", r'(http://supernormalstep\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://supernormalstep\.com/\?p=\d+)', after="prev"))
help = 'Index format: number'