Okay, I'm not sure what was going wrong. I tried it from the command line, found that sometimes it seemed that it helped if I closed Calibre and reopened it. It works really well now, thank you.
I changed some feeds and ended up with this:
Code:
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
newstatesman.com
'''
class NewStatesman(BasicNewsRecipe):
title = 'New Statesman'
__author__ = 'Darko Miletic'
description = "Britain's award-winning current affairs magazine"
publisher = 'New Statesman'
category = 'news, UK, World'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'cp1252'
remove_javascript = True
cover_url = 'http://media.starbulletin.com/designimages/spacer.gif'
html2lrf_options = [
'--comment' , description
, '--base-font-size', '10'
, '--category' , category
, '--publisher' , publisher
]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"'
keep_only_tags = [dict(name='div', attrs={'class':'content-main'})]
remove_tags = [
dict(name=['object','link','form','ul'])
,dict(name='ul', attrs={'class':'post-article'})
,dict(name='div' , attrs={'class':['tag-nav-container','article-base']})
,dict(name='div' , attrs={'id':['reader-comments']})
]
feeds = [
(u'Politics', u'http://www.newstatesman.com/feeds/topics/politics.rss'), (u'Arts & Culture', u'http://www.newstatesman.com/feeds/topics/arts-and-culture.rss'), (u'Books', u'http://www.newstatesman.com/feeds/topics/books.rss'), (u'Life & Society', u'http://www.newstatesman.com/feeds/topics/life-and-society.rss'), (u'World Affairs', u'http://www.newstatesman.com/feeds/topics/world-affairs.rss'), (u'Columns - Martin Bright', u'http://www.newstatesman.com/feeds/writers/martin_bright.rss'), (u'Columns - Kira Cochrane', u'http://www.newstatesman.com/feeds/writers/kira_cochrane.rss'), (u'Columns - Hunter Davies', u'http://www.newstatesman.com/feeds/topics/world-affairs.rss'), (u'Columns - Noreena Hertz', u'http://www.newstatesman.com/feeds/writers/noreena_hertz.rss'), (u'Columns - Lindsey Hilsum', u'http://www.newstatesman.com/feeds/writers/lindsey_hilsum.rss'), (u'Columns - Darcus Howe', u'http://www.newstatesman.com/feeds/writers/darcus_howe.rss'), (u'Columns - Emma John', u'http://www.newstatesman.com/feeds/writers/emma_john.rss'), (u'Columns - Sadakat Kadri', u'http://www.newstatesman.com/feeds/writers/sadakat_kadri.rss'), (u'Columns - Mark Lynas', u'http://www.newstatesman.com/feeds/writers/mark_lynas.rss'), (u'Columns - Kevin Maguire', u'http://www.newstatesman.com/feeds/writers/kevin_maguire.rss'), (u'Columns - Rageh Omaar', u'http://www.newstatesman.com/feeds/writers/rageh_omaar.rss'), (u'Columns - John Pilger', u'http://www.newstatesman.com/feeds/writers/john_pilger.rss'), (u'Columns - Ziauddin Sardar', u'http://www.newstatesman.com/feeds/writers/ziauddin_sardar.rss'), (u'Columns - Clive Stafford-Smith', u'http://www.newstatesman.com/feeds/writers/clive_stafford_smith.rss'), (u'Columns - Michela Wrong', u'http://www.newstatesman.com/feeds/writers/michela_wrong.rss')
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
mtag = '\n<meta http-equiv="Content-Language" content="en"/>\n'
soup.head.insert(0,mtag)
return soup