2012-06-20 20:41:04 +00:00
|
|
|
# -*- coding: iso-8859-1 -*-
|
|
|
|
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
|
2014-01-05 15:50:57 +00:00
|
|
|
# Copyright (C) 2012-2014 Bastian Kleineidam
|
2012-11-21 20:57:26 +00:00
|
|
|
|
2013-11-07 20:22:49 +00:00
|
|
|
from re import compile, escape, IGNORECASE, sub
|
2012-06-20 19:58:13 +00:00
|
|
|
from os.path import splitext
|
2014-10-13 20:45:25 +00:00
|
|
|
from ..scraper import _BasicScraper, _ParserScraper
|
2013-03-06 19:00:30 +00:00
|
|
|
from ..helpers import indirectStarter, bounceStarter
|
2013-04-25 19:14:32 +00:00
|
|
|
from ..util import tagre, getPageContent
|
|
|
|
|
|
|
|
|
|
|
|
class SabrinaOnline(_BasicScraper):
|
2013-04-26 04:53:05 +00:00
|
|
|
url = 'http://sabrina-online.com/'
|
2013-04-25 19:14:32 +00:00
|
|
|
imageSearch = compile(tagre("a", "href", r'(strips/[^"]*)'))
|
|
|
|
prevSearch = compile(tagre("a", "href", r"(\d\d\d\d-\d\d.html)") +
|
|
|
|
tagre("img", "src", "b_back.gif"))
|
|
|
|
help = 'Index format: n (unpadded)'
|
|
|
|
adult = True
|
|
|
|
multipleImagesPerStrip = True
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
def starter(cls):
|
|
|
|
"""Pick last one in a list of archive pages."""
|
2013-04-26 04:53:05 +00:00
|
|
|
archive = cls.url + 'archive.html'
|
|
|
|
data = getPageContent(archive, cls.session)[0]
|
2013-04-25 19:14:32 +00:00
|
|
|
search = compile(tagre("a", "href", r"(\d\d\d\d-\d\d.html)"))
|
|
|
|
archivepages = search.findall(data)
|
2013-04-26 04:53:05 +00:00
|
|
|
return cls.url + archivepages[-1]
|
2012-06-20 19:58:13 +00:00
|
|
|
|
2014-06-17 05:05:11 +00:00
|
|
|
class SafelyEndangered(_BasicScraper):
|
|
|
|
url = 'http://www.safelyendangered.com/'
|
|
|
|
stripUrl = url + 'comic/%s'
|
|
|
|
firstStripUrl = stripUrl % 'ignored'
|
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://www\.safelyendangered\.com/wp-content/uploads/\d+/\d+/[^"]+\.[a-z]+).*'))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'([^"]+)', after="navi navi-prev"))
|
|
|
|
textSearch = compile(tagre("img", "title", r'([^"]+)', before=r'http://www\.safelyendangered\.com/wp-content/uploads'))
|
|
|
|
help = 'Index format: yyyy/mm/stripname'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
class SailorsunOrg(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://sailorsun.org/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-02-04 20:00:26 +00:00
|
|
|
stripUrl = url + '?p=%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '21'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev"))
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: n (unpadded)'
|
|
|
|
|
|
|
|
|
|
|
|
class SamAndFuzzy(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.samandfuzzy.com/'
|
2012-11-13 18:10:19 +00:00
|
|
|
stripUrl = 'http://samandfuzzy.com/%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '1'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'(/comics/.+?)" alt')
|
|
|
|
prevSearch = compile(r'"><a href="(.+?)"><img src="imgint/nav_prev.gif"')
|
|
|
|
help = 'Index format: nnnn'
|
|
|
|
|
2013-04-20 16:51:06 +00:00
|
|
|
class SandraOnTheRocks(_BasicScraper):
|
|
|
|
url = 'http://www.sandraontherocks.com/'
|
2013-04-20 17:59:01 +00:00
|
|
|
stripUrl = url + 'strips-sotr/%s'
|
2013-04-20 16:51:06 +00:00
|
|
|
firstStripUrl = stripUrl % 'start_by_running'
|
|
|
|
imageSearch = compile(tagre("img", "src", r'([^"]*/comics/[^"]+)'))
|
2013-04-20 17:59:01 +00:00
|
|
|
prevSearch = compile(tagre("a", "href", r'([^"]*/strips-sotr/[^"]+)', before="cn[id]prev"))
|
2013-04-20 16:51:06 +00:00
|
|
|
help = 'Index format: name'
|
2013-03-19 19:54:16 +00:00
|
|
|
|
2013-12-10 18:50:21 +00:00
|
|
|
class ScandinaviaAndTheWorld(_BasicScraper):
|
|
|
|
url = 'http://satwcomic.com/'
|
|
|
|
rurl = escape(url)
|
2014-07-02 17:51:53 +00:00
|
|
|
stripUrl = url + '%s'
|
2013-12-10 18:50:21 +00:00
|
|
|
firstStripUrl = stripUrl % 'sweden-denmark-and-norway'
|
|
|
|
imageSearch = compile(tagre("img", "src", r'(%sart/[^"/]+)' % rurl))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%s[^"/]+)' % rurl)+"\s*"+tagre('span', 'class', 'spritePrevious'))
|
|
|
|
help = 'Index format: stripname'
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class ScaryGoRound(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.scarygoround.com/'
|
|
|
|
stripUrl = url + '?date=%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '20090918'
|
2012-11-21 20:57:26 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(strips/\d+\.png)'))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(\?date=\d+)') + "Previous")
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: n (unpadded)'
|
|
|
|
|
|
|
|
|
2013-02-06 21:08:36 +00:00
|
|
|
class ScenesFromAMultiverse(_BasicScraper):
|
|
|
|
url = 'http://amultiverse.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-02-06 21:08:36 +00:00
|
|
|
stripUrl = url + '%s/'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '2010/06/14/parenthood'
|
2013-11-12 17:33:14 +00:00
|
|
|
imageSearch = (
|
|
|
|
compile(tagre("div", "id", "comic") + r"\s*" +
|
|
|
|
tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/[^"]+)' % rurl)),
|
|
|
|
compile(tagre("div", "id", "comic") + r"\s*" + tagre("a", "href", r'[^"]*') +
|
|
|
|
tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/[^"]+)' % rurl)),
|
|
|
|
)
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%scomic/\d+\d+/\d+/\d+/[^"]+)' % rurl, after="prev"))
|
2013-02-06 21:08:36 +00:00
|
|
|
help = 'Index format: yyyy/mm/dd/stripname'
|
|
|
|
|
|
|
|
|
2012-11-20 17:53:53 +00:00
|
|
|
class SchlockMercenary(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.schlockmercenary.com/'
|
|
|
|
stripUrl = url + '%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '2000-06-12'
|
2012-11-21 20:57:26 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://static\.schlockmercenary\.com/comics/[^"]+)'))
|
2012-12-04 06:02:40 +00:00
|
|
|
multipleImagesPerStrip = True
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(/\d+-\d+-\d+)', quote="'", after="nav-previous"))
|
2012-11-21 20:57:26 +00:00
|
|
|
help = 'Index format: yyyy-mm-dd'
|
2012-11-20 17:53:53 +00:00
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
class SchoolBites(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://schoolbites.net/'
|
|
|
|
stripUrl = url + 'd/%s.html'
|
2012-11-21 20:57:26 +00:00
|
|
|
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"))
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: yyyymmdd'
|
|
|
|
|
|
|
|
|
2013-03-25 18:48:32 +00:00
|
|
|
class Schuelert(_BasicScraper):
|
|
|
|
url = 'http://www.schuelert.de/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-04-10 21:57:09 +00:00
|
|
|
stripUrl = url + 'index.php?paged=%s'
|
|
|
|
firstStripUrl = stripUrl % '5'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r"(%swp-content/[^']+)" % rurl, quote="'"))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%sindex\.php\?paged=\d+)' % rurl) + "«")
|
2013-03-25 18:48:32 +00:00
|
|
|
multipleImagesPerStrip = True
|
|
|
|
help = 'Index format: none'
|
|
|
|
lang = 'de'
|
|
|
|
|
|
|
|
|
2013-04-09 17:38:16 +00:00
|
|
|
class Science(_BasicScraper):
|
|
|
|
url = 'http://sci-ence.org/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-04-09 17:38:16 +00:00
|
|
|
stripUrl = url + '%s/'
|
|
|
|
firstStripUrl = stripUrl % 'periodic-table-element-ass'
|
2013-04-10 16:19:11 +00:00
|
|
|
prevSearch = compile(tagre("a", "href", r'(%s[^"]+/)' % rurl, after="prev"))
|
|
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+[^"]+)' % rurl))
|
2013-04-09 17:38:16 +00:00
|
|
|
help = 'Index format: stripname'
|
|
|
|
|
|
|
|
|
2013-01-29 20:23:32 +00:00
|
|
|
class SequentialArt(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.collectedcurios.com/sequentialart.php'
|
|
|
|
stripUrl = url + '?s=%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '1'
|
2013-01-29 20:23:32 +00:00
|
|
|
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'
|
|
|
|
|
|
|
|
|
2013-03-06 19:21:10 +00:00
|
|
|
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
|
|
|
|
|
|
|
|
|
2013-04-28 17:58:38 +00:00
|
|
|
# XXX site has been hacked
|
|
|
|
class _ShadowGirls(_BasicScraper):
|
2013-03-03 16:46:57 +00:00
|
|
|
url = 'http://www.shadowgirlscomic.com/'
|
|
|
|
stripUrl = url + 'comics/%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % 'book-1/chapter-1-broken-dreams/welcome'
|
2013-03-03 16:46:57 +00:00
|
|
|
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/[^"]+)')))
|
|
|
|
|
|
|
|
|
2012-11-20 17:53:53 +00:00
|
|
|
class Sheldon(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.sheldoncomics.com/'
|
2013-07-09 20:21:17 +00:00
|
|
|
rurl = escape(url)
|
2013-02-04 20:00:26 +00:00
|
|
|
stripUrl = url + 'archive/%s.html'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '011130'
|
2013-07-09 20:21:17 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://cdn\.sheldoncomics\.com/strips/[^"]+)'))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%sarchive/\d+\.html)' % rurl, after="sidenav-prev"))
|
2012-11-21 20:57:26 +00:00
|
|
|
help = 'Index format: yymmdd'
|
2012-11-20 17:53:53 +00:00
|
|
|
|
|
|
|
|
2013-07-04 18:20:26 +00:00
|
|
|
class ShermansLagoon(_BasicScraper):
|
|
|
|
url = 'http://shermanslagoon.com/'
|
|
|
|
stripUrl = url + 'comics/%s'
|
|
|
|
firstStripUrl = stripUrl % '/december-29-2003/'
|
2014-11-14 19:37:06 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://safr\.kingfeatures\.com/idn/test/zone/xml/content\.php\?file=.+?)'))
|
|
|
|
prevSearch = compile(r'id="previouscomic" class="button white"><a href="(%scomics/[a-z0-9-]+/)"' % url)
|
|
|
|
help = 'Index format: monthname-day-year'
|
2013-07-04 18:20:26 +00:00
|
|
|
|
|
|
|
@classmethod
|
|
|
|
def namer(cls, imageUrl, pageUrl):
|
2014-11-14 19:37:06 +00:00
|
|
|
name = pageUrl.rsplit('/', 3)[2]
|
|
|
|
if name == "shermanslagoon.com":
|
|
|
|
import datetime
|
|
|
|
name = datetime.date.today().strftime("%B-%d-%Y").lower()
|
2013-07-04 18:20:26 +00:00
|
|
|
# name is monthname-day-year
|
|
|
|
month, day, year = name.split('-')
|
|
|
|
return "%s-%s-%s" % (year, month, day)
|
|
|
|
|
|
|
|
|
2012-12-08 20:30:51 +00:00
|
|
|
class Shivae(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://shivae.net/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-02-04 20:00:26 +00:00
|
|
|
stripUrl = url + 'blog/%s/'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '2007/09/21/09212007'
|
2013-11-12 17:33:14 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%swp-content/blogs\.dir/\d+/files/\d+/\d+/[^"]+)' % rurl))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%sblog/[^"]+)' % rurl, after="navi-prev"))
|
2012-12-08 20:30:51 +00:00
|
|
|
help = 'Index format: yyyy/mm/dd/stripname'
|
|
|
|
|
|
|
|
|
2012-12-12 16:41:29 +00:00
|
|
|
# XXX disallowed by robots.txt
|
|
|
|
class _Shortpacked(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.shortpacked.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-02-04 20:00:26 +00:00
|
|
|
stripUrl = url + '%s/'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%s\d+/comic/[^"]+)' % rurl, after="prev"))
|
2012-12-02 17:35:06 +00:00
|
|
|
help = 'Index format: yyyy/comic/book-nn/mm-name1/name2'
|
2012-11-20 17:53:53 +00:00
|
|
|
|
|
|
|
|
2014-09-28 13:29:02 +00:00
|
|
|
class ShotgunShuffle(_BasicScraper):
|
|
|
|
url = 'http://shotgunshuffle.com/'
|
|
|
|
stripUrl = url + 'comic/%s'
|
|
|
|
firstStripUrl = stripUrl % 'pilot/'
|
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://shotgunshuffle.com/wp-content/uploads/\d+/\d+/\d+-[^"]+)'))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'([^"]+)', after="navi navi-prev"))
|
2014-09-29 02:48:26 +00:00
|
|
|
help = 'Index format: stripname'
|
2014-09-28 13:29:02 +00:00
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class SinFest(_BasicScraper):
|
2015-01-15 23:16:28 +00:00
|
|
|
name = 'KeenSpot/SinFest'
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.sinfest.net/'
|
2014-12-16 17:01:54 +00:00
|
|
|
stripUrl = url + 'view.php?date=%s'
|
|
|
|
imageSearch = compile(tagre("img","src", r'(btphp/comics/.+)', after="alt"))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(view\.php\?date=.+)') + '\\s*' + tagre("img", "src", r'\.\./images/prev\.gif'))
|
|
|
|
help = 'Index format: yyyy-mm-dd'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2013-04-05 05:20:50 +00:00
|
|
|
# XXX disallowed by robots.txt
|
2013-04-05 16:47:51 +00:00
|
|
|
class _Sketchesnatched(_BasicScraper):
|
2013-04-05 05:20:50 +00:00
|
|
|
url = 'http://sketchesnatched.blogspot.com/'
|
|
|
|
stripUrl = url + 'search?updated-max=%s%%2B01:00&max-results=1'
|
2013-04-05 05:31:22 +00:00
|
|
|
firstStripUrl = stripUrl % '2011-01-27T08:32:00'
|
2013-04-05 05:20:50 +00:00
|
|
|
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'
|
|
|
|
|
|
|
|
|
2013-02-07 22:02:54 +00:00
|
|
|
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'
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class SlightlyDamned(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.sdamned.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-02-04 20:00:26 +00:00
|
|
|
stripUrl = url + '%s/'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '2004/03/03142004'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev"))
|
2012-11-21 20:57:26 +00:00
|
|
|
help = 'Index format: yyyy/mm/number'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
|
|
|
class SluggyFreelance(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.sluggy.com/'
|
|
|
|
stripUrl = url + 'comics/archives/daily/%s'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'<img src="(/images/comics/.+?)"')
|
|
|
|
prevSearch = compile(r'<a href="(.+?)"[^>]+?><span class="ui-icon ui-icon-seek-prev">')
|
2014-01-28 18:08:39 +00:00
|
|
|
multipleImagesPerStrip = True
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: yymmdd'
|
|
|
|
|
|
|
|
|
2013-03-06 19:21:10 +00:00
|
|
|
class SMBC(_BasicScraper):
|
|
|
|
url = 'http://www.smbc-comics.com/'
|
2013-04-25 18:32:21 +00:00
|
|
|
rurl = escape(url)
|
2013-07-18 18:39:53 +00:00
|
|
|
stripUrl = url + '?id=%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '1'
|
2013-04-25 18:32:21 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r"(%scomics/\d{8}(?:\w2?|-\d)?\.\w{3})\s*" % rurl, quote="'"))
|
2013-07-18 18:39:53 +00:00
|
|
|
prevSearch = compile(tagre("a", "href", r'([^"]+)#comic', after="backRollover"))
|
2013-03-06 19:21:10 +00:00
|
|
|
help = 'Index format: nnnn'
|
|
|
|
|
2014-02-10 20:58:09 +00:00
|
|
|
def shouldSkipUrl(self, url, data):
|
2013-04-25 18:32:21 +00:00
|
|
|
"""Skip promo or missing update pages."""
|
|
|
|
return url in (
|
|
|
|
self.stripUrl % '2865',
|
|
|
|
self.stripUrl % '2653',
|
|
|
|
self.stripUrl % '2424',
|
|
|
|
self.stripUrl % '2226',
|
|
|
|
self.stripUrl % '2069',
|
|
|
|
self.stripUrl % '1895',
|
|
|
|
self.stripUrl % '1896',
|
|
|
|
self.stripUrl % '1589',
|
|
|
|
)
|
|
|
|
|
2013-03-06 19:21:10 +00:00
|
|
|
|
2013-04-03 18:30:16 +00:00
|
|
|
class SnowFlakes(_BasicScraper):
|
|
|
|
url = 'http://www.snowflakescomic.com/'
|
|
|
|
stripUrl = url + '?id=%s&sl=%s'
|
|
|
|
firstStripUrl = stripUrl % ('103', '1')
|
2013-04-29 18:31:07 +00:00
|
|
|
endOfLife = True
|
2013-04-03 18:30:16 +00:00
|
|
|
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')
|
|
|
|
|
2014-07-19 11:23:42 +00:00
|
|
|
def getIndexStripUrl(self, index):
|
2013-04-03 18:30:16 +00:00
|
|
|
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)
|
|
|
|
|
2014-02-10 20:58:09 +00:00
|
|
|
def shouldSkipUrl(self, url, data):
|
2013-04-03 18:30:16 +00:00
|
|
|
"""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
|
|
|
|
)
|
|
|
|
|
|
|
|
|
2013-03-06 19:00:30 +00:00
|
|
|
class SnowFlame(_BasicScraper):
|
|
|
|
url = 'http://www.snowflamecomic.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-03-06 19:00:30 +00:00
|
|
|
stripUrl = url + '?comic=snowflame-%s-%s'
|
|
|
|
firstStripUrl = stripUrl % ('01', '01')
|
2013-11-12 17:33:14 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/[^"]+)' % rurl, after="Snow[Ff]lame "))
|
2013-03-06 19:00:30 +00:00
|
|
|
prevSearch = compile(tagre("span", "class", "mininav-prev") +
|
2013-04-10 16:19:11 +00:00
|
|
|
tagre("a", "href", r'(%s\?comic=snowflame[^"]+)' % rurl))
|
2013-03-06 19:00:30 +00:00
|
|
|
starter = bounceStarter(url,
|
|
|
|
compile(tagre("span", "class", "mininav-next") +
|
2013-04-10 16:19:11 +00:00
|
|
|
tagre("a", "href", r'(%s\?comic=snowflame[^"]+)' % rurl)))
|
2013-03-06 19:00:30 +00:00
|
|
|
help = 'Index format: chapter-page'
|
|
|
|
|
2014-07-19 11:23:42 +00:00
|
|
|
def getIndexStripUrl(self, index):
|
|
|
|
return self.stripUrl % tuple(index.split('-'))
|
2013-03-06 19:00:30 +00:00
|
|
|
|
|
|
|
@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)
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class SodiumEyes(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://sodiumeyes.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-02-04 20:00:26 +00:00
|
|
|
stripUrl = url + '%s/'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '2007/11/08/damning-evidence'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%scomic/[^ ]+)' % rurl, quote=""))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev"))
|
2012-11-21 20:57:26 +00:00
|
|
|
help = 'Index format: yyyy/mm/dd/stripname'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2012-12-08 20:30:51 +00:00
|
|
|
class Sorcery101(_BasicScraper):
|
2013-04-13 18:58:00 +00:00
|
|
|
baseUrl = 'http://www.sorcery101.net/'
|
|
|
|
url = baseUrl + 'sorcery-101/'
|
|
|
|
rurl = escape(baseUrl)
|
2013-02-27 18:40:54 +00:00
|
|
|
stripUrl = url + '%s/'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/[^"]+)' % rurl))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%ssorcery-101/[^"]+)' % rurl, after="previous-"))
|
2012-12-08 20:30:51 +00:00
|
|
|
help = 'Index format: stripname'
|
|
|
|
|
|
|
|
|
2013-02-06 21:08:36 +00:00
|
|
|
class SpaceTrawler(_BasicScraper):
|
|
|
|
url = 'http://spacetrawler.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-02-06 21:08:36 +00:00
|
|
|
stripUrl = url + '%s/'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '2010/01/01/spacetrawler-4'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+)' % rurl, after="navi-prev"))
|
2013-02-06 21:08:36 +00:00
|
|
|
help = 'Index format: yyyy/mm/dd/stripname'
|
|
|
|
|
|
|
|
|
2013-04-10 16:36:33 +00:00
|
|
|
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)
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class SpareParts(_BasicScraper):
|
2012-11-21 20:57:26 +00:00
|
|
|
baseUrl = 'http://www.sparepartscomics.com/'
|
2013-02-04 20:00:26 +00:00
|
|
|
url = baseUrl + 'comics/?date=20080328'
|
2012-12-04 06:02:40 +00:00
|
|
|
stripUrl = baseUrl + 'comics/index.php?date=%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '20031022'
|
2012-12-04 06:02:40 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://www\.sparepartscomics\.com/comics/[^"]+)'))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(index\.php\?date=\d+)', quote="'") + "Previous Comic")
|
2012-11-20 17:53:53 +00:00
|
|
|
help = 'Index format: yyyymmdd'
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
|
2013-01-29 20:52:26 +00:00
|
|
|
class Spinnerette(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.spinnyverse.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-11-12 17:33:14 +00:00
|
|
|
stripUrl = url + 'index.php?id=%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '2010/02/09/02092010'
|
2013-11-12 17:33:14 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(comics/[^"]+)', after="comic"))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(/index\.php\?id=[^"]+)', after="prev"))
|
2013-01-29 20:52:26 +00:00
|
|
|
help = 'Index format: number'
|
|
|
|
|
|
|
|
|
2012-12-08 20:30:51 +00:00
|
|
|
class SPQRBlues(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://spqrblues.com/IV/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-02-04 20:00:26 +00:00
|
|
|
stripUrl = url + '?p=%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '1467'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/\d+\.png)' % rurl))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev"))
|
2012-12-08 20:30:51 +00:00
|
|
|
help = 'Index format: number'
|
|
|
|
|
|
|
|
|
2014-01-08 03:47:58 +00:00
|
|
|
class StandStillStaySilent(_BasicScraper):
|
|
|
|
url = 'http://www.sssscomic.com/comic.php'
|
|
|
|
rurl = escape(url)
|
|
|
|
stripUrl = url + '?page=%s'
|
|
|
|
firstStripUrl = stripUrl % '1'
|
2014-06-04 05:58:16 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(comicpages/[^"]+)', before="comicnormal"))
|
|
|
|
prevSearch = compile(tagre("a", "href", r"([^']+)", quote="'") + tagre("div", "id", r'navprev'))
|
2014-01-08 03:47:58 +00:00
|
|
|
help = 'Index Format: number'
|
|
|
|
|
|
|
|
|
2012-12-13 20:05:27 +00:00
|
|
|
# XXX disallowed by robots.txt
|
|
|
|
class _StationV3(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.stationv3.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-02-04 20:00:26 +00:00
|
|
|
stripUrl = url + 'd/%s.html'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%sd/\d+\.html)' % rurl) +
|
2012-12-08 20:30:51 +00:00
|
|
|
tagre("img", "src", r'http://www\.stationv3\.com/images/previous\.gif'))
|
|
|
|
help = 'Index format: yyyymmdd'
|
|
|
|
|
|
|
|
|
2013-03-03 21:03:27 +00:00
|
|
|
class StickyDillyBuns(_BasicScraper):
|
|
|
|
url = 'http://www.stickydillybuns.com/'
|
|
|
|
stripUrl = url + 'strips-sdb/%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % 'awesome_leading_man'
|
2013-03-03 21:03:27 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'([^"]*/comics/[^"]+)'))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'([^"]*/strips-sdb/[^"]+)', before="cn[id]prev"))
|
|
|
|
help = 'Index format: name'
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class Stubble(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://stubblecomics.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-02-04 20:00:26 +00:00
|
|
|
stripUrl = url + '?p=%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '4'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="navi-prev"))
|
2012-11-21 20:57:26 +00:00
|
|
|
help = 'Index format: number'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2013-04-03 18:30:29 +00:00
|
|
|
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)
|
|
|
|
|
2014-02-10 20:58:09 +00:00
|
|
|
def shouldSkipUrl(self, url, data):
|
2013-04-03 18:30:29 +00:00
|
|
|
"""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
|
|
|
|
)
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class StrawberryDeathCake(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://strawberrydeathcake.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-02-04 20:00:26 +00:00
|
|
|
stripUrl = url + 'archive/%s/'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%swp-content/webcomic/[^"]+)' % rurl))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%sarchive/[^"]+)' % rurl, after="previous"))
|
2012-11-21 20:57:26 +00:00
|
|
|
help = 'Index format: stripname'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2014-10-13 20:45:25 +00:00
|
|
|
class StrongFemaleProtagonist(_ParserScraper):
|
|
|
|
url = 'http://strongfemaleprotagonist.com/'
|
|
|
|
stripUrl = url + '%s/'
|
|
|
|
css = True
|
|
|
|
imageSearch = 'article p:first-child img'
|
|
|
|
prevSearch = 'div.nav-previous > a'
|
|
|
|
help = 'Index format: issue-?/page-??'
|
|
|
|
|
|
|
|
def shouldSkipUrl(self, url, data):
|
|
|
|
"""Skip hiatus & non-comic pages."""
|
|
|
|
return url in (
|
|
|
|
self.stripUrl % 'guest-art/tuesday',
|
|
|
|
self.stripUrl % 'guest-art/friday',
|
|
|
|
self.stripUrl % 'guest-art/wednesday',
|
|
|
|
self.stripUrl % 'issue-5/newspaper',
|
|
|
|
self.stripUrl % 'issue-5/hiatus-1',
|
|
|
|
self.stripUrl % 'issue-5/hiatus-2',
|
|
|
|
)
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class SuburbanTribe(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.pixelwhip.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-02-04 20:00:26 +00:00
|
|
|
stripUrl = url + '?p=%s'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev"))
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: nnnn'
|
|
|
|
|
|
|
|
|
|
|
|
class SomethingPositive(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.somethingpositive.net/'
|
|
|
|
stripUrl = url + 'sp%s.shtml'
|
2013-04-11 16:27:43 +00:00
|
|
|
imageSearch = (
|
|
|
|
compile(tagre("img", "src", r'(sp\d+\.png)')),
|
|
|
|
compile(tagre("img", "src", r'(twither\.gif)')),
|
|
|
|
)
|
2012-12-12 16:41:29 +00:00
|
|
|
prevSearch = compile(tagre("a", "href", r'(sp\d+\.shtml)') +
|
2012-12-04 06:02:40 +00:00
|
|
|
"(?:" + tagre("img", "src", r'images/previous\.gif') + "|Previous)")
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: mmddyyyy'
|
|
|
|
|
|
|
|
|
|
|
|
class StarCrossdDestiny(_BasicScraper):
|
2013-04-13 18:58:00 +00:00
|
|
|
baseUrl = 'http://www.starcrossd.net/'
|
|
|
|
rurl = escape(baseUrl)
|
|
|
|
url = baseUrl + 'comic.html'
|
|
|
|
stripUrl = baseUrl + 'archives/%s.html'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '00000001'
|
2013-05-25 21:24:33 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://(?:www\.)?starcrossd\.net/(?:ch1|strips|book2)/[^"]+)'))
|
2013-04-10 21:57:09 +00:00
|
|
|
prevSearch = compile(r'<a href="(%s(?:ch1/)?archives/\d+\.html)"[^>]*"[^"]*"[^>]*>prev' % rurl, IGNORECASE)
|
2012-06-20 19:58:13 +00:00
|
|
|
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
|
|
|
|
|
|
|
|
|
2012-12-13 20:05:27 +00:00
|
|
|
# XXX disallowed by robots.txt
|
|
|
|
class _StrangeCandy(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://www.strangecandy.net/'
|
|
|
|
stripUrl = url + 'd/%s.html'
|
2012-11-21 20:57:26 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(/comics/\d+\.jpg)'))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(/d/\d+\.html)') + tagre("img", "alt", "Previous comic"))
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: yyyyddmm'
|
|
|
|
|
|
|
|
|
2013-02-13 16:53:11 +00:00
|
|
|
class SupernormalStep(_BasicScraper):
|
|
|
|
url = 'http://supernormalstep.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-02-13 16:53:11 +00:00
|
|
|
stripUrl = url + '?p=%s'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '8'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev"))
|
2013-02-13 16:53:11 +00:00
|
|
|
help = 'Index format: number'
|