calibre/recipes/alternet.recipe
2013-01-01 09:31:44 +05:30

39 lines
1.2 KiB
Plaintext

from calibre.ptempfile import PersistentTemporaryFile
from calibre.web.feeds.news import BasicNewsRecipe
class Alternet(BasicNewsRecipe):
title = u'Alternet'
__author__= 'rty'
oldest_article = 7
max_articles_per_feed = 100
publisher = 'alternet.org'
category = 'News, Magazine'
description = 'News magazine and online community'
feeds = [
(u'Front Page', u'http://feeds.feedblitz.com/alternet')
]
remove_attributes = ['width', 'align','cellspacing']
remove_javascript = True
use_embedded_content = True
no_stylesheets = True
language = 'en'
encoding = 'UTF-8'
temp_files = []
articles_are_obfuscated = True
def get_article_url(self, article):
return article.get('link', None)
def get_obfuscated_article(self, url):
br = self.get_browser()
br.open(url)
response = br.follow_link(url_regex = r'/printversion/[0-9]+', nr = 0)
html = response.read()
self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write(html)
self.temp_files[-1].close()
return self.temp_files[-1].name
conversion_options = {'linearize_tables': True}