mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
40 lines
1.2 KiB
Plaintext
40 lines
1.2 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
www.thewaythefutureblogs.com
|
|
Frederik Pohl's Blog
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class TheWayTheFutureBlogs(BasicNewsRecipe):
|
|
title = 'The Way the Future Blogs'
|
|
__author__ = 'Darko Miletic'
|
|
description = "Frederik Pohl's blog"
|
|
publisher = 'Frederik Pohl'
|
|
category = 'news, SF, books'
|
|
oldest_article = 30
|
|
max_articles_per_feed = 200
|
|
no_stylesheets = True
|
|
encoding = 'utf8'
|
|
use_embedded_content = False
|
|
language = 'en'
|
|
remove_empty_feeds = True
|
|
extra_css = ' body{font-family: Georgia,serif } '
|
|
|
|
conversion_options = {
|
|
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
|
|
}
|
|
remove_tags = [
|
|
dict(name=['meta', 'object', 'embed', 'iframe', 'base', 'link'])]
|
|
keep_only_tags = [dict(attrs={'class': ['post', 'commentlist']})]
|
|
remove_attributes = ['width', 'height', 'lang', 'border']
|
|
|
|
feeds = [(u'Posts', u'http://www.thewaythefutureblogs.com/feed/')]
|
|
|
|
def preprocess_html(self, soup):
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
return soup
|