calibre/recipes/doghousediaries.recipe
Kovid Goyal 567040ee1e Perform PEP8 compliance checks on the entire codebase
Some bits of PEP 8 are turned off via setup.cfg
2016-07-29 21:25:17 +05:30

60 lines
2.2 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2010-2012, NiLuJe <niluje at ak-team.com>'
'''
Fetch DoghouseDiaries.
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class DoghouseDiaries(BasicNewsRecipe):
title = 'Doghouse Diaries'
description = 'A webcomic.'
__author__ = 'NiLuJe'
language = 'en'
use_embedded_content = False
# 14 comics per fetch (not really days... but we can't easily get the date
# of individual comics, short of parsing each one...)
oldest_article = 14
cover_url = 'http://www.thedoghousediaries.com/logos/logo3.png'
masthead_url = 'http://www.thedoghousediaries.com/logos/logo3.png'
keep_only_tags = [dict(name='img', attrs={'class': re.compile("comic-item*")}), dict(
name='h1'), dict(name='div', attrs={'class': 'entry'}), dict(name='p', id='alttext')]
remove_tags = [dict(name='div', attrs={'class': 'pin-it-btn-wrapper'}), dict(
name='span'), dict(name='div', id='wp_fb_like_button')]
remove_attributes = ['width', 'height']
no_stylesheets = True
# Turn image bubblehelp into a paragraph (NOTE: We run before the
# remove_tags cleanup, so we need to make sure we only parse the
# comic-item img, not the pinterest one pulled by the entry div)
preprocess_regexps = [
(re.compile(r'(<img.*src="http://thedoghousediaries.com/comics/.*title=")([^"]+)(".*>)'),
lambda m: '%s%s<p id="alttext"><strong>%s</strong></p>' % (m.group(1), m.group(3), m.group(2)))
]
def parse_index(self):
INDEX = 'http://www.thedoghousediaries.com/'
soup = self.index_to_soup(INDEX)
articles = []
# Since the feed sucks, and there's no real archive, we use the 'Quick
# Archive' thingie, but we can't get the date from here, so stop after
# 14 comics...
for item in soup.findAll('option', {}, True, None, self.oldest_article + 1):
# Skip the quick archive itself
if (item['value'] != '0'):
articles.append({
'title': self.tag_to_string(item).encode('UTF-8'),
'url': item['value'],
'description': '',
'content': '',
})
return [('Doghouse Diaries', articles)]