home *** CD-ROM | disk | FTP | other *** search
-
- __license__ = 'GPL v3'
- __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
- '''
- boljevac.blogspot.com
- '''
-
- import re
- from calibre.web.feeds.news import BasicNewsRecipe
-
- class AgroGerila(BasicNewsRecipe):
- title = 'Agro Gerila'
- __author__ = 'Darko Miletic'
- description = 'Politicki nekorektan blog.'
- oldest_article = 45
- max_articles_per_feed = 100
- language = 'sr'
- encoding = 'utf-8'
- no_stylesheets = True
- use_embedded_content = True
- publication_type = 'blog'
- extra_css = ' @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: "Trebuchet MS",Trebuchet,Verdana,sans1,sans-serif} .article_description{font-family: sans1, sans-serif} img{margin-bottom: 0.8em; border: 1px solid #333333; padding: 4px } '
-
- conversion_options = {
- 'comment' : description
- , 'tags' : 'film, blog, srbija'
- , 'publisher': 'Dry-Na-Nord'
- , 'language' : language
- }
-
- preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
-
- feeds = [(u'Posts', u'http://boljevac.blogspot.com/feeds/posts/default')]
-
- def preprocess_html(self, soup):
- for item in soup.findAll(style=True):
- del item['style']
- return self.adeify_images(soup)
-
-
-