Hi!!
to say thank you for your support with my recipe (it's still broken
), I write two recipes for you..
1. Attivissimo, debunker
Code:
from calibre.web.feeds.news import BasicNewsRecipe
class Disinformatico(BasicNewsRecipe):
title = u'Il Disinformatico - Paolo Attivissimo'
oldest_article = 7
max_articles_per_feed = 25
auto_cleanup = False
use_embedded_content = False
description = 'Un blog di Paolo Attivissimo, giornalista informatico e cacciatore di bufale'
publisher = 'http://attivissimo.blogspot.it'
language = 'it'
__author__ = 'isspro'
publication_type = 'blog'
conversion_options = { 'title' : title,
'comments' : description,
'language' : language,
'publisher' : 'Paolo Attivissimo',
'authors' : 'Paolo Attivissimo',
'smarten_punctuation' : True
}
keep_only_tags = [
dict(name='div', attrs={'class':'post hentry'})
]
remove_tags = [
dict(name='span', attrs={'id':'NumCom'}),
dict(name='div', attrs={'id':'PostFooter'})
]
extra_css = '''
h1 {font-size:x-large;}
.post-body {margin: 0pt;}
.post-timestamp {margin-right: 0pt;}
'''
def parse_feeds(self):
feeds = BasicNewsRecipe.parse_feeds(self)
# Loop through all feeds.
for feed in feeds:
# Loop through all articles in feed.
for article in feed.articles[:]:
if 'podcast' in article.title:
feed.articles.remove(article)
return feeds
feeds = [(u'Home', u'http://feeds.feedburner.com/Disinformatico')]
2. Wired.it
Code:
import re
from calibre.web.feeds.news import BasicNewsRecipe
class WiredITA(BasicNewsRecipe):
title = u'Wired.it'
oldest_article = 1
max_articles_per_feed = 50
no_stylesheets = True
use_embedded_content = False
auto_cleanup = False
encoding = 'utf8'
masthead_url = 'http://www.wired.com/images/home/wired_logo.gif'
description = 'Wired - Make in Italy. Inventa, sbaglia, innova'
publisher = 'http://www.wired.it/'
language = 'it'
__author__ = 'isspro'
publication_type = 'magazine'
conversion_options = { 'title' : title,
'comments' : description,
'language' : language,
'publisher' : publisher,
'authors' : title,
'smarten_punctuation' : True
}
keep_only_tags = [
dict(name='div', attrs={'id':'main-article'})
]
remove_tags = [
dict(name='img', attrs={'class':'avatar img-circle'}),
dict(name='div', attrs={'class':'topics'}),
dict(name='div', attrs={'class':'social-share hidden-lg'}),
dict(name='span', attrs={'class':'label'})
]
extra_css = '''
h1 {font-size:x-large;}
p.lead {font-size:medium;}
.who {line-height: 0pt; margin: 0pt;}
'''
preprocess_regexps = [
(re.compile(r'Pubblicato'), lambda match: '')
]
feeds = [(u'Attualit\xe0', u'http://www.wired.it/attualita/feed/'),
(u'Internet','http://www.wired.it/internet/feed/'),
(u'Gadget','http://www.wired.it/gadget/feed/'),
(u'Mobile','http://www.wired.it/mobile/feed/'),
(u'Scienza','http://www.wired.it/scienza/feed/'),
(u'Economia','http://www.wired.it/economia/feed/'),
(u'LifeStyle','http://www.wired.it/lifestyle/feed/'),
(u'Play','http://www.wired.it/play/feed/'),
]
I hope you can find them useful!!
best regards