import re from calibre.web.feeds.news import BasicNewsRecipe class ABCRecipe(BasicNewsRecipe): title = u'ABC Linuxu' oldest_article = 5 max_articles_per_feed = 3 # 5 __author__ = 'Funthomas' language = 'cs' feeds = [ # (u'Blogy', u'http://www.abclinuxu.cz/auto/blogDigest.rss'), (u'Články', u'http://www.abclinuxu.cz/auto/abc.rss'), (u'Zprávičky', 'http://www.abclinuxu.cz/auto/zpravicky.rss') ] remove_javascript = True no_stylesheets = True remove_attributes = ['width', 'height'] remove_tags_before = dict(name='h1') remove_tags = [ dict(attrs={'class': ['meta-vypis', 'page_tools', 'cl_perex']}), dict(attrs={'class': ['cl_nadpis-link', 'komix-nav']}) ] remove_tags_after = [ dict(name='div', attrs={'class': ['cl_perex', 'komix-nav']}), dict(attrs={'class': ['meta-vypis', 'page_tools']}), dict(name='', attrs={'': ''}), ] preprocess_regexps = [ (re.compile(r'.*

', re.DOTALL), lambda match: '

') ] def print_version(self, url): return url + '?varianta=print&noDiz' extra_css = ''' h1 {font-size:130%; font-weight:bold} h3 {font-size:111%; font-weight:bold} '''