dosage/dosagelib/plugins/x.py

45 lines
1.4 KiB
Python
Raw Normal View History

# -*- coding: utf-8 -*-
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
2014-01-05 15:50:57 +00:00
# Copyright (C) 2012-2014 Bastian Kleineidam
# Copyright (C) 2015-2016 Tobias Gruetzmacher
from __future__ import absolute_import, division, print_function
2012-11-21 20:57:26 +00:00
2012-06-20 19:58:13 +00:00
from re import compile
2012-10-11 10:03:12 +00:00
from ..scraper import _BasicScraper
from ..helpers import bounceStarter
2012-11-26 06:13:32 +00:00
from ..util import tagre
2012-10-11 10:03:12 +00:00
2012-06-20 19:58:13 +00:00
2016-04-05 22:47:47 +00:00
class Xkcd(_BasicScraper):
name = 'xkcd'
url = 'http://xkcd.com/'
starter = bounceStarter
stripUrl = url + '%s/'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
2016-04-05 22:47:47 +00:00
imageSearch = compile(tagre("img", "src",
r'(//imgs\.xkcd\.com/comics/[^"]+)'))
2012-11-26 06:13:32 +00:00
prevSearch = compile(tagre("a", "href", r'(/\d+/)', before="prev"))
nextSearch = compile(tagre("a", "href", r'(/\d+/)', before="next"))
2012-06-20 19:58:13 +00:00
help = 'Index format: n (unpadded)'
2016-04-05 22:47:47 +00:00
textSearch = compile(tagre("img", "title", r'([^"]+)',
before=r'//imgs\.xkcd\.com/comics/'))
2012-06-20 19:58:13 +00:00
@classmethod
2016-04-05 22:47:47 +00:00
def namer(cls, image_url, page_url):
index = int(page_url.rstrip('/').rsplit('/', 1)[-1])
name = image_url.rsplit('/', 1)[-1].split('.')[0]
2012-11-26 06:13:32 +00:00
return '%03d-%s' % (index, name)
2013-12-04 16:56:54 +00:00
@classmethod
def imageUrlModifier(cls, url, data):
if url and '/large/' in data:
return url.replace(".png", "_large.png")
return url
2016-04-05 22:47:47 +00:00
def shouldSkipUrl(self, url, data):
return url in (
self.stripUrl % '1663', # Garden
)