home *** CD-ROM | disk | FTP | other *** search
- #!/usr/bin/env python
-
- __license__ = 'GPL v3'
- __author__ = 'Mori'
- __version__ = 'v. 0.1'
- '''
- www.runa.pl/blog
- '''
-
- from calibre.web.feeds.news import BasicNewsRecipe
- import re
-
- class FantazmatyRecipe(BasicNewsRecipe):
- __author__ = 'Mori'
- language = 'pl'
-
- title = u'Fantazmaty'
- publisher = u'Agencja Wydawnicza Runa'
- description = u'Blog Agencji Wydawniczej Runa'
-
- no_stylesheets = True
- remove_javascript = True
- encoding = 'utf-8'
-
- oldest_article = 100
- max_articles_per_feed = 100
-
- extra_css = '''
- img{float: left; padding-right: 10px; padding-bottom: 5px;}
- '''
-
- feeds = [
- (u'Fantazmaty', u'http://www.runa.pl/blog/rss.xml')
- ]
-
- remove_tags = [
- dict(name = 'div', attrs = {'class' : 'path'}),
- dict(name = 'div', attrs = {'class' : 'drdot'}),
- dict(name = 'div', attrs = {'class' : 'picture'})
- ]
-
- remove_tags_after = [
- dict(name = 'div', attrs = {'class' : 'content'})
- ]
-
- preprocess_regexps = [
- (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
- [
- (r'<body>.*?<div id="primary"', lambda match: '<body><div id="primary"'),
- (r'<!--.*?-->', lambda match: '')
- ]
- ]