mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
64 lines
2.2 KiB
Plaintext
64 lines
2.2 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2008 - 2011, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
thenation.com
|
|
'''
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class Thenation(BasicNewsRecipe):
|
|
title = 'The Nation'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Unconventional Wisdom Since 1865'
|
|
publisher = 'The Nation'
|
|
category = 'news, politics, USA'
|
|
oldest_article = 120
|
|
encoding = 'utf-8'
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
language = 'en'
|
|
use_embedded_content = False
|
|
delay = 1
|
|
masthead_url = 'http://www.thenation.com/sites/default/themes/thenation/images/logo-main.gif'
|
|
login_url = 'http://www.thenation.com/user?destination=%3Cfront%3E'
|
|
publication_type = 'magazine'
|
|
needs_subscription = 'optional'
|
|
exra_css = """
|
|
body{font-family: Arial,Helvetica,sans-serif;}
|
|
.print-created{font-size: small;}
|
|
.caption{display: block; font-size: x-small;}
|
|
"""
|
|
|
|
conversion_options = {
|
|
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
|
|
}
|
|
|
|
keep_only_tags = [dict(
|
|
attrs={'class': ['print-title', 'print-created', 'print-content', 'print-links']})]
|
|
remove_tags = [
|
|
dict(name=['link', 'iframe', 'base', 'meta', 'object', 'embed'])]
|
|
remove_attributes = ['lang']
|
|
|
|
feeds = [(u"Articles", u'http://www.thenation.com/rss/articles')]
|
|
|
|
def print_version(self, url):
|
|
return url.replace('.thenation.com/', '.thenation.com/print/')
|
|
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser(self)
|
|
br.open('http://www.thenation.com/')
|
|
if self.username is not None and self.password is not None:
|
|
br.open(self.login_url)
|
|
br.select_form(nr=1)
|
|
br['name'] = self.username
|
|
br['pass'] = self.password
|
|
br.submit()
|
|
return br
|
|
|
|
def get_cover_url(self):
|
|
soup = self.index_to_soup('http://www.thenation.com/issue/')
|
|
item = soup.find('div', attrs={'id': 'cover-wrapper'})
|
|
if item:
|
|
return item.img['src']
|
|
return None
|