477 lines
19 KiB
Python
477 lines
19 KiB
Python
# -*- coding: iso-8859-1 -*-
|
|
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
|
|
# Copyright (C) 2012-2013 Bastian Kleineidam
|
|
|
|
from re import compile, escape, 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/'
|
|
rurl = escape(url)
|
|
stripUrl = url + '?p=%s'
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
rurl = escape(url)
|
|
prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, 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'"><a href="(.+?)"><img src="imgint/nav_prev.gif"')
|
|
help = 'Index format: nnnn'
|
|
|
|
|
|
class SandraAndWoo(_BasicScraper):
|
|
url = 'http://www.sandraandwoo.com/'
|
|
rurl = escape(url)
|
|
stripUrl = url + '%s/'
|
|
firstStripUrl = stripUrl % '2000/01/01/welcome-to-sandra-and-woo'
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+-[^"]+)' % rurl))
|
|
prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+/)' % rurl, after="prev"))
|
|
help = 'Index format: yyyy/mm/dd/number-stripname'
|
|
|
|
|
|
class SandraAndWooGerman(_BasicScraper):
|
|
url = 'http://www.sandraandwoo.com/woode/'
|
|
rurl = escape(url)
|
|
stripUrl = url + '%s/'
|
|
firstStripUrl = stripUrl % '2008/10/19/ein-ausgefuchster-waschbar'
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+-[^"]+)' % rurl))
|
|
prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+/)' % rurl, after="prev"))
|
|
help = 'Index format: yyyy/mm/dd/number-stripname'
|
|
lang = 'de'
|
|
|
|
|
|
class ScaryGoRound(_BasicScraper):
|
|
url = 'http://www.scarygoround.com/'
|
|
stripUrl = url + '?date=%s'
|
|
imageSearch = compile(tagre("img", "src", r'(strips/\d+\.png)'))
|
|
prevSearch = compile(tagre("a", "href", r'(\?date=\d+)') + "Previous")
|
|
help = 'Index format: n (unpadded)'
|
|
|
|
|
|
class ScenesFromAMultiverse(_BasicScraper):
|
|
url = 'http://amultiverse.com/'
|
|
rurl = escape(url)
|
|
stripUrl = url + '%s/'
|
|
imageSearch = compile(tagre("img", "src", r'(%sfiles/comics/[^"]+)' % rurl))
|
|
prevSearch = compile(tagre("a", "href", r'(%s\d+\d+/\d+/\d+/[^"]+)' % rurl, after="prev"))
|
|
help = 'Index format: yyyy/mm/dd/stripname'
|
|
|
|
|
|
class SchlockMercenary(_BasicScraper):
|
|
url = 'http://www.schlockmercenary.com/'
|
|
stripUrl = url + '%s'
|
|
imageSearch = compile(tagre("img", "src", r'(http://static\.schlockmercenary\.com/comics/[^"]+)'))
|
|
multipleImagesPerStrip = True
|
|
prevSearch = compile(tagre("a", "href", r'(/\d+-\d+-\d+)', quote="'", after="nav-previous"))
|
|
help = 'Index format: yyyy-mm-dd'
|
|
|
|
|
|
class SchoolBites(_BasicScraper):
|
|
url = 'http://schoolbites.net/'
|
|
stripUrl = url + 'd/%s.html'
|
|
imageSearch = compile(tagre("img", "src", r'(http://cdn\.schoolbites\.net/comics/[^"]+)'))
|
|
prevSearch = compile(tagre("a", "href", r'(http://schoolbites\.net/d/\d+\.html)', after="prev"))
|
|
help = 'Index format: yyyymmdd'
|
|
|
|
|
|
class Schuelert(_BasicScraper):
|
|
url = 'http://www.schuelert.de/'
|
|
rurl = escape(url)
|
|
stripUrl = None
|
|
imageSearch = compile(tagre("img", "src", r"(%swp-content/[^']+)" % rurl, quote="'"))
|
|
prevSearch = compile(tagre("a", "href", r'(%sindex\.php\?paged=\d+)' % rurl) + "«")
|
|
multipleImagesPerStrip = True
|
|
help = 'Index format: none'
|
|
lang = 'de'
|
|
|
|
|
|
class Science(_BasicScraper):
|
|
url = 'http://sci-ence.org/'
|
|
rurl = escape(url)
|
|
stripUrl = url + '%s/'
|
|
firstStripUrl = stripUrl % 'periodic-table-element-ass'
|
|
prevSearch = compile(tagre("a", "href", r'(%s[^"]+/)' % rurl, after="prev"))
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+[^"]+)' % rurl))
|
|
help = 'Index format: stripname'
|
|
description = u'A comic about science, technology, skepticism, geekery, video games, atheism, and more.'
|
|
|
|
|
|
class SequentialArt(_BasicScraper):
|
|
url = 'http://www.collectedcurios.com/sequentialart.php'
|
|
stripUrl = url + '?s=%s'
|
|
imageSearch = compile(tagre("img", "src", r'([^"]+)', before="strip"))
|
|
prevSearch = compile(tagre("a", "href", r'(/sequentialart\.php\?s=\d+)')
|
|
+ tagre("img", "src", "Nav_BackOne\.gif"))
|
|
help = 'Index format: name'
|
|
|
|
|
|
class SexyLosers(_BasicScraper):
|
|
adult = True
|
|
url = 'http://www.sexylosers.com/'
|
|
stripUrl = url + '%s.html'
|
|
imageSearch = compile(r'<img src\s*=\s*"\s*(comics/[\w\.]+?)"', IGNORECASE)
|
|
prevSearch = compile(r'<a href="(/\d{3}\.\w+?)"><font color = FFAAAA><<', IGNORECASE)
|
|
help = 'Index format: nnn'
|
|
starter = indirectStarter(url,
|
|
compile(r'SEXY LOSERS <A HREF="(.+?)">Latest SL Comic \(#\d+\)</A>', 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/'
|
|
rurl = escape(url)
|
|
stripUrl = url + 'blog/%s/'
|
|
imageSearch = compile(tagre("img", "src", r'(%sfiles/comics/[^"]+)' % rurl))
|
|
prevSearch = compile(tagre("a", "href", r'(%sblog/[^"]+)' % rurl, after="Previous"))
|
|
help = 'Index format: yyyy/mm/dd/stripname'
|
|
|
|
|
|
# XXX disallowed by robots.txt
|
|
class _Shortpacked(_BasicScraper):
|
|
url = 'http://www.shortpacked.com/'
|
|
rurl = escape(url)
|
|
stripUrl = url + '%s/'
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
prevSearch = compile(tagre("a", "href", r'(%s\d+/comic/[^"]+)' % rurl, 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'<img src=".+?(/comikaze/comics/.+?)"')
|
|
prevSearch = compile(r'(/archive_page.php\?comicID=.+?)".+?prev_a')
|
|
help = 'Index format: n (unpadded)'
|
|
|
|
|
|
# XXX disallowed by robots.txt
|
|
class _Sketchesnatched(_BasicScraper):
|
|
url = 'http://sketchesnatched.blogspot.com/'
|
|
stripUrl = url + 'search?updated-max=%s%%2B01:00&max-results=1'
|
|
firstStripUrl = stripUrl % '2011-01-27T08:32:00'
|
|
imageSearch = compile(tagre("meta", "content", r"(http://\d+\.bp\.blogspot\.com/[^']+)",
|
|
after=r'image_url', quote="'"))
|
|
prevSearch = compile(tagre("a", "href", r"(http://sketchesnatched\.blogspot\.[a-z]+/search[^']+)",
|
|
before=r"blog-pager-older-link", quote="'"))
|
|
help = 'Index format: yyyy-mm-ddThh:mm:ss'
|
|
description = u"Artwork by Massimo Carnevale"
|
|
|
|
|
|
class SkinDeep(_BasicScraper):
|
|
url = 'http://www.skindeepcomic.com/'
|
|
stripUrl = url + 'archive/%s/'
|
|
imageSearch = compile(r'<span class="webcomic-object[^>]*><img src="([^"]*)"')
|
|
prevSearch = compile(tagre("a", "href", r'([^"]+)', after="previous-webcomic-link"))
|
|
help = 'Index format: custom'
|
|
|
|
|
|
class SlightlyDamned(_BasicScraper):
|
|
url = 'http://www.sdamned.com/'
|
|
rurl = escape(url)
|
|
stripUrl = url + '%s/'
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev"))
|
|
help = 'Index format: yyyy/mm/number'
|
|
|
|
|
|
class SluggyFreelance(_BasicScraper):
|
|
url = 'http://www.sluggy.com/'
|
|
stripUrl = url + 'comics/archives/daily/%s'
|
|
imageSearch = compile(r'<img src="(/images/comics/.+?)"')
|
|
prevSearch = compile(r'<a href="(.+?)"[^>]+?><span class="ui-icon ui-icon-seek-prev">')
|
|
help = 'Index format: yymmdd'
|
|
|
|
|
|
class SMBC(_BasicScraper):
|
|
url = 'http://www.smbc-comics.com/'
|
|
stripUrl = url + 'index.php?db=comics&id=%s'
|
|
imageSearch = compile(r'<img src=\'(.+?\d{8}.\w{1,4})\'>')
|
|
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/'
|
|
rurl = escape(url)
|
|
stripUrl = url + '?comic=snowflame-%s-%s'
|
|
firstStripUrl = stripUrl % ('01', '01')
|
|
imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/[^"]+)' % rurl, after="Snow[Ff]lame the fan made"))
|
|
prevSearch = compile(tagre("span", "class", "mininav-prev") +
|
|
tagre("a", "href", r'(%s\?comic=snowflame[^"]+)' % rurl))
|
|
starter = bounceStarter(url,
|
|
compile(tagre("span", "class", "mininav-next") +
|
|
tagre("a", "href", r'(%s\?comic=snowflame[^"]+)' % rurl)))
|
|
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/'
|
|
rurl = escape(url)
|
|
stripUrl = url + '%s/'
|
|
imageSearch = compile(tagre("img", "src", r'(%scomic/[^ ]+)' % rurl, quote=""))
|
|
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev"))
|
|
help = 'Index format: yyyy/mm/dd/stripname'
|
|
|
|
|
|
class Sorcery101(_BasicScraper):
|
|
baseurl = 'http://www.sorcery101.net/'
|
|
url = baseurl + 'sorcery-101/'
|
|
rurl = escape(baseurl)
|
|
stripUrl = url + '%s/'
|
|
imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/[^"]+)' % rurl))
|
|
prevSearch = compile(tagre("a", "href", r'(%ssorcery-101/[^"]+)' % rurl, after="previous-"))
|
|
help = 'Index format: stripname'
|
|
|
|
|
|
class SpaceTrawler(_BasicScraper):
|
|
url = 'http://spacetrawler.com/'
|
|
rurl = escape(url)
|
|
stripUrl = url + '%s/'
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+)' % rurl, after="navi-prev"))
|
|
help = 'Index format: yyyy/mm/dd/stripname'
|
|
|
|
|
|
class Spamusement(_BasicScraper):
|
|
url = 'http://spamusement.com/'
|
|
rurl = escape(url)
|
|
stripUrl = url + 'index.php/comics/view/%s'
|
|
imageSearch = compile(r'<img src="(%sgfx/\d+\..+?)"' % rurl, IGNORECASE)
|
|
prevSearch = compile(r'<a href="(%sindex.php/comics/view/.+?)">' % rurl, IGNORECASE)
|
|
help = 'Index format: n (unpadded)'
|
|
starter = indirectStarter(url, prevSearch)
|
|
|
|
|
|
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/'
|
|
rurl = escape(url)
|
|
stripUrl = url + '%s/'
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, before="Previous Comic"))
|
|
help = 'Index format: number'
|
|
|
|
|
|
class SPQRBlues(_BasicScraper):
|
|
url = 'http://spqrblues.com/IV/'
|
|
rurl = escape(url)
|
|
stripUrl = url + '?p=%s'
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/\d+\.png)' % rurl))
|
|
prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev"))
|
|
help = 'Index format: number'
|
|
|
|
|
|
# XXX disallowed by robots.txt
|
|
class _StationV3(_BasicScraper):
|
|
url = 'http://www.stationv3.com/'
|
|
rurl = escape(url)
|
|
stripUrl = url + 'd/%s.html'
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
prevSearch = compile(tagre("a", "href", r'(%sd/\d+\.html)' % rurl) +
|
|
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/'
|
|
rurl = escape(url)
|
|
stripUrl = url + '?p=%s'
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, 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"(?:</a>|<br />)"),
|
|
compile(tagre("img", "src", r'(http://\d+\.bp\.blogspot\.com/[^"]+)') + r"(?:(?: )?</a>|<span |<br />)"),
|
|
compile(tagre("img", "src", r'(https://lh\d+\.googleusercontent\.com/[^"]+)') + r"</a>"),
|
|
)
|
|
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/'
|
|
rurl = escape(url)
|
|
stripUrl = url + 'archive/%s/'
|
|
imageSearch = compile(tagre("img", "src", r'(%swp-content/webcomic/[^"]+)' % rurl))
|
|
prevSearch = compile(tagre("a", "href", r'(%sarchive/[^"]+)' % rurl, after="previous"))
|
|
help = 'Index format: stripname'
|
|
|
|
|
|
class SuburbanTribe(_BasicScraper):
|
|
url = 'http://www.pixelwhip.com/'
|
|
rurl = escape(url)
|
|
stripUrl = url + '?p=%s'
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, 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'<a href="(http://www\.starcrossd\.net/(?:ch1/)?archives/\d+\.html)"[^>]*"[^"]*"[^>]*>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
|
|
|
|
|
|
# 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/'
|
|
rurl = escape(url)
|
|
stripUrl = url + '?p=%s'
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev"))
|
|
help = 'Index format: number'
|