calibre/recipes/lr21.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

67 lines
2.0 KiB
Python

#!/usr/bin/env python2
##
# Title: lr21.com.uy News, Sports, and Blog Calibre Recipe
# Contact: Carlos Alves - <carlos@carlosalves.info>
##
# License: GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html
# Copyright: Carlos Alves - <carlos@carlosalves.info>
##
# Written: January 2016
# Last Edited: 2016-01-11
##
__license__ = 'GPL v3'
__author__ = '2016, Carlos Alves <carlos@carlosalves.info>'
'''
lr21.com.uy
'''
from calibre.web.feeds.news import BasicNewsRecipe
class General(BasicNewsRecipe):
title = 'LaRed21'
__author__ = 'Carlos Alves'
description = 'LaRed21 Diario Digital'
tags = 'soccer, futbol, news'
language = 'es_UY'
timefmt = '[%a, %d %b, %Y]'
use_embedded_content = False
recursion = 5
encoding = None
remove_javascript = True
no_stylesheets = True
oldest_article = 10
max_articles_per_feed = 100
keep_only_tags = [
dict(name='h1', attrs={'id': 'article-title'}),
dict(name='h2', attrs={'class': 'copete'}),
dict(name='div', attrs={'class': 'article-content clear bottom-1'})
]
remove_tags = [
dict(name='div', attrs={
'class': ['br', 'hr', 'titlebar', 'navigation']}),
dict(name='dl', attrs={'class': 'gallery-item'}),
dict(name=['object', 'link'])
]
extra_css = '''
h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
p {font-family:Arial,Helvetica,sans-serif;}
'''
feeds = [
(u'LaRed21 Diario Digital', u'http://www.lr21.com.uy/feed')
]
def get_cover_url(self):
pass
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup