dosage/dosagelib/plugins/f.py

201 lines
7.9 KiB
Python
Raw Normal View History

# -*- 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
from re import compile, escape, IGNORECASE, MULTILINE
2012-06-20 19:58:13 +00:00
2012-10-11 10:03:12 +00:00
from ..util import tagre
from ..scraper import _BasicScraper
from ..helpers import indirectStarter
2012-06-20 19:58:13 +00:00
class FalconTwin(_BasicScraper):
url = 'http://www.falcontwin.com/'
stripUrl = url + 'index.html?strip=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '0'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'"(strips/.+?)"')
prevSearch = compile(r'"prev"><a href="(index.+?)"')
help = 'Index format: nnn'
2013-03-06 19:21:10 +00:00
class Fallen(_BasicScraper):
2013-04-13 18:58:00 +00:00
baseUrl = 'http://www.fallencomic.com/'
url = baseUrl + 'fal-page.htm'
stripUrl = baseUrl + 'pages/part%s/%s-p%s.htm'
2013-03-06 19:21:10 +00:00
imageSearch = compile(r'<IMG SRC="(page/.+?)"', IGNORECASE)
prevSearch = compile(r'<A HREF="(.+?)"><FONT FACE="Courier">Back', IGNORECASE)
help = 'Index format: nn-m (comicNumber-partNumber)'
starter = indirectStarter(url,
compile(r'\(NEW \d{2}/\d{2}/\d{2}\)\s*\n*\s*<a href="(pages/part\d+/\d+-p\d+\.htm)">\d+</a>', MULTILINE))
2013-03-06 19:21:10 +00:00
@classmethod
def namer(cls, imageUrl, pageUrl):
num = pageUrl.split('/')[-1].split('-')[0]
part = pageUrl.split('-')[-1].split('.')[0]
return '%s-%s' % (part, num)
def getIndexStripUrl(self, index):
index, part = index.split('-')
return self.stripUrl % (part, index, part)
class FantasyRealms(_BasicScraper):
url = 'http://www.fantasyrealmsonline.com/'
stripUrl = url + 'manga/%s.php'
imageSearch = compile(r'<img src="(\d{1,4}.\w{3,4})" width="540"', IGNORECASE)
prevSearch = compile(r'<a href="(.+?)"><img src="../images/nav-back.gif"', IGNORECASE)
help = 'Index format: nnn'
starter = indirectStarter(url,
compile(r'<a href="(manga/.+?)"><img src="preview.jpg"', IGNORECASE))
2013-03-06 19:21:10 +00:00
2012-06-20 19:58:13 +00:00
class FauxPas(_BasicScraper):
url = 'http://www.ozfoxes.net/cgi/pl-fp1.cgi'
stripUrl = url + '?%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'<img .*src="(.*fp/fp.*(png|jpg|gif))"')
prevSearch = compile(r'<a href="(pl-fp1\.cgi\?\d+)">Previous Strip')
help = 'Index format: nnn'
class FeyWinds(_BasicScraper):
2013-04-13 18:58:00 +00:00
baseUrl = 'http://kitsune.rydia.net/'
url = baseUrl + 'index.html'
stripUrl = baseUrl + 'comic/page.php?id=%s'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r"(../comic/pages//.+?)'")
prevSearch = compile(r"(page.php\?id=.+?)'.+?navprevious.png")
help = 'Index format: n (unpadded)'
starter = indirectStarter(url, compile(r'(comic/page.php\?id.+?)"'))
2012-06-20 19:58:13 +00:00
class FilibusterCartoons(_BasicScraper):
2013-04-14 07:02:14 +00:00
description = u'Political cartoons from Canada!'
url = 'http://www.filibustercartoons.com/'
rurl = escape(url)
stripUrl = url + 'index.php/%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '2001/06/28/poor-jean'
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev"))
2012-06-20 19:58:13 +00:00
help = 'Index format: yyyy/mm/dd/name'
2013-02-06 21:27:40 +00:00
class FirstWorldProblems(_BasicScraper):
url = 'http://bradcolbow.com/archive/C5/'
stripUrl = url + '%s/'
firstStripUrl = stripUrl % 'P10'
2013-02-06 21:27:40 +00:00
imageSearch = compile(tagre("img", "src", r'(http://(?:fwpcomics\.s3\.amazonaws\.com|s3\.amazonaws\.com/fwpcomics)/s1-[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(http://bradcolbow\.com/archive/C5/[^"]+)', before="prev"))
multipleImagesPerStrip = True
help = 'Index format: a letter and a number'
2012-06-20 19:58:13 +00:00
class FlakyPastry(_BasicScraper):
2013-04-13 18:58:00 +00:00
baseUrl = 'http://flakypastry.runningwithpencils.com/'
url = baseUrl + 'index.php'
stripUrl = baseUrl + 'comic.php?strip_id=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '0'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'<img src="(comics/.+?)"')
prevSearch = compile(r'<a href="(.+?)".+?btn_back')
help = 'Index format: nnnn'
2012-12-04 06:02:40 +00:00
2012-12-08 20:30:51 +00:00
class Flemcomics(_BasicScraper):
2013-04-14 07:02:14 +00:00
description = u'FLEM Comics - More fun than a sack of dead kittens.'
url = 'http://www.flemcomics.com/'
stripUrl = url + 'd/%s.html'
2012-12-08 20:30:51 +00:00
imageSearch = compile(tagre("img", "src", r'(/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(/d/\d+\.html)') +
tagre("img", "src", r'/images/previous_day\.jpg'))
help = 'Index format: yyyymmdd'
2012-06-20 19:58:13 +00:00
class Flipside(_BasicScraper):
url = 'http://flipside.keenspot.com/comic.php'
rurl = escape(url)
stripUrl = url + '?i=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
2012-12-04 06:02:40 +00:00
imageSearch = compile(tagre("img", "src", r'(http://cdn\.flipside\.keenspot\.com/comic/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(%s\?i=\d+)' % rurl, after="prev"))
2012-06-20 19:58:13 +00:00
help = 'Index format: nnnn'
2013-03-12 19:49:46 +00:00
class FonFlatter(_BasicScraper):
2013-04-14 07:02:14 +00:00
description = u'Fred, eine stets zuversichtliche, einfallsreiche, zumeist aber alberne und etwas naive Fledermaus, flattert bereits seit 2005 t\xe4glich durch das weltweite Netz'
2013-03-12 19:49:46 +00:00
url = 'http://www.fonflatter.de/'
rurl = escape(url)
2013-03-12 19:49:46 +00:00
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2005/09/20/01-begegnung-mit-batman'
lang = 'de'
imageSearch = compile(r'src="(%s\d+/fred_\d+-\d+-\d+[^"]+)' % rurl)
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev"))
2013-03-12 19:49:46 +00:00
help = 'Index format: yyyy/mm/dd/number-stripname'
2013-03-13 17:31:58 +00:00
def shouldSkipUrl(self, url):
return url in (
self.stripUrl % "2006/11/30/adventskalender",
self.stripUrl % "2006/09/21/danke",
self.stripUrl % "2006/08/23/zgf-zuweilen-gestellte-fragen",
self.stripUrl % "2005/10/19/naq-never-asked-questions",
2013-03-13 17:31:58 +00:00
)
2013-03-12 19:49:46 +00:00
2012-06-20 19:58:13 +00:00
class Footloose(_BasicScraper):
2013-04-14 07:02:14 +00:00
description = u'Footloose, a Webcomic By alice Nuttall and Emily Brady'
url = 'http://footloosecomic.com/footloose/today.php'
2012-11-13 18:10:19 +00:00
stripUrl = 'http://footloosecomic.com/footloose/pages.php?page=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'<img src="/footloose/(.+?)"')
prevSearch = compile(r'(?:first.+?[^>]).+?(/footloose/.+?)".+?(?:prev)')
help = 'Index format: n (unpadded)'
2013-04-10 16:20:39 +00:00
class ForLackOfABetterComic(_BasicScraper):
url = 'http://forlackofabettercomic.com/'
rurl = escape(url)
stripUrl = url + '?id=%s'
firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre("img", "src", r'(%simg/comic/\d+[^"]+)' % rurl, after="comicimg"))
prevSearch = compile(tagre("a", "href", r'(%s\?id\=\d+)' % rurl) + r'Prev')
help = 'Index format: number'
description = 'A hand drawn comic about everyday life situations.'
2012-06-20 19:58:13 +00:00
class Freefall(_BasicScraper):
url = 'http://freefall.purrsia.com/default.htm'
2012-11-13 18:10:19 +00:00
stripUrl = 'http://freefall.purrsia.com/ff%s/fc%s.htm'
2012-06-20 19:58:13 +00:00
imageSearch = compile(r'<img src="(/ff\d+/.+?.\w{3,4})"')
prevSearch = compile(r'<A HREF="(/ff\d+/.+?.htm)">Previous</A>')
help = 'Index format: nnnn/nnnnn'
2012-09-27 19:55:16 +00:00
class FredoAndPidjin(_BasicScraper):
2013-02-05 18:51:46 +00:00
url = 'http://www.pidjin.net/'
2013-04-10 21:57:09 +00:00
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2006/02/19/goofy-monday'
2012-09-27 19:55:16 +00:00
help = 'Index format: yyyy/mm/dd/name'
2013-04-11 16:27:43 +00:00
imageSearch = compile(tagre('img', 'src', '(http://cdn\.pidjin\.net/wp-content/uploads/\d+/\d+/[^"]+\.[a-z]+)'))
2012-12-04 06:02:40 +00:00
multipleImagesPerStrip = True
2012-09-27 19:55:16 +00:00
prevSearch = compile(tagre('a', 'href', '([^"]+)')+"Prev</a>")
2013-02-05 18:51:46 +00:00
starter = indirectStarter(url,
compile(tagre('a', 'href', "("+url+r'\d\d\d\d/\d\d/\d\d/[^"]+/)')))
2013-03-11 21:45:30 +00:00
class FullFrontalNerdity(_BasicScraper):
2013-04-14 07:02:14 +00:00
description = u'Full Frontal Nerdity by Aaron Williams - Comics about liking all things gaming, technological, mythological, and internetological.'
2013-03-11 21:45:30 +00:00
url = 'http://ffn.nodwick.com/'
rurl = escape(url)
2013-03-11 21:45:30 +00:00
stripUrl = url + '?p=%s'
firstStripUrl = stripUrl % '6'
imageSearch = compile(tagre("img", "src", r'(%sffnstrips/\d+-\d+-\d+\.[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev"))
2013-03-11 21:45:30 +00:00
help = 'Index format: number'
class FunInJammies(_BasicScraper):
url = 'http://www.funinjammies.com/'
stripUrl = url + 'comic.php?issue=%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
2013-03-11 21:45:30 +00:00
imageSearch = compile(r'(/comics/.+?)"')
prevSearch = compile(r'(/comic.php.+?)" id.+?prev')
help = 'Index format: n (unpadded)'