mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
45 lines
1.3 KiB
Python
45 lines
1.3 KiB
Python
#!/usr/bin/env python2
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
chicagobreakingnews.com
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class ChicagoBreakingNews(BasicNewsRecipe):
|
|
title = 'Chicago Breaking News'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Breaking News from Chicago'
|
|
oldest_article = 1
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
use_embedded_content = True
|
|
publisher = 'Chicago Breaking News'
|
|
category = 'news, politics, USA, Chicago'
|
|
encoding = 'utf8'
|
|
language = 'en'
|
|
|
|
html2lrf_options = [
|
|
'--comment', description, '--category', category, '--publisher', publisher
|
|
]
|
|
|
|
html2epub_options = 'publisher="' + publisher + \
|
|
'"\ncomments="' + description + '"\ntags="' + category + '"'
|
|
|
|
feeds = [(u'Breaking news', u'http://feeds2.feedburner.com/ChicagoBreakingNews/')]
|
|
|
|
def preprocess_html(self, soup):
|
|
for item in soup.findAll('a'):
|
|
if item['href'].find('http://feedads.googleadservices.com') > -1:
|
|
item.extract()
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
for item in soup.findAll(color=True):
|
|
del item['color']
|
|
for item in soup.findAll(size=True):
|
|
del item['size']
|
|
return soup
|