calibre/recipes/theonion.recipe
2019-03-22 23:47:49 +05:30

90 lines
3.6 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2009-2013, Darko Miletic <darko.miletic at gmail.com>'
'''
theonion.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class TheOnion(BasicNewsRecipe):
title = 'The Onion'
__author__ = 'Darko Miletic'
description = "The Onion, America's Finest News Source, is an award-winning publication covering world, national, and * local issues. It is updated daily online and distributed weekly in select American cities." # noqa
oldest_article = 2
max_articles_per_feed = 100
publisher = 'Onion, Inc.'
category = 'humor, news, USA'
language = 'en'
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
publication_type = 'newsportal'
needs_subscription = 'optional'
masthead_url = 'http://www.theonion.com/static/onion/img/logo_1x.png'
cover_url = 'http://www.theonion.com/static/onion/img/logo_1x.png'
extra_css = """
body{font-family: Helvetica,Arial,sans-serif}
.section_title{color: gray; text-transform: uppercase}
.title{font-family: Georgia,serif}
.meta{color: gray; display: inline}
.has_caption{display: block}
.caption{font-size: x-small; color: gray; margin-bottom: 0.8em}
"""
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
keep_only_tags = [
dict(attrs={'class': lambda x: x and 'content-wrapper' in x.split()})]
remove_attributes = ['lang', 'rel']
remove_tags = [
dict(name=['object', 'link', 'iframe', 'base', 'meta', 'button', 'footer', 'blockquote', 'figcaption']), dict(attrs={'class': lambda x: x and 'share-tools' in x.split()}), dict(attrs={'class': lambda x: x and 'content-meta' in x.split()}), dict(attrs={'class': 'below-article-tools'}), dict(name='div', attrs={'id': ['topshare', 'bottomshare']}) # noqa
]
feeds = [
(u'Daily', u'http://feeds.theonion.com/theonion/daily'), (u'Sports',
u'http://feeds.theonion.com/theonion/sports')
]
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
br.open('http://www.theonion.com/')
if self.username is not None and self.password is not None:
br.open('https://ui.ppjol.com/login/onion/u/j_spring_security_check')
br.select_form(name='f')
br['j_username'] = self.username
br['j_password'] = self.password
br.submit()
return br
def get_article_url(self, article):
artl = BasicNewsRecipe.get_article_url(self, article)
if artl.startswith('http://www.theonion.com/audio/'):
artl = None
return artl
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('a'):
limg = item.find('img')
if item.string is not None:
str = item.string
item.replaceWith(str)
else:
if limg:
item.name = 'div'
item.attrs = []
if not limg.get('alt'):
limg['alt'] = 'image'
else:
str = self.tag_to_string(item)
item.replaceWith(str)
for item in soup.findAll('img'):
if item.get('data-src'):
item['src'] = item['data-src']
return soup