View Single Post
Old 05-18-2011, 03:42 PM   #1
schuster
Zealot
schuster doesn't litterschuster doesn't litter
 
Posts: 119
Karma: 100
Join Date: Jan 2011
Location: Germany / NRW /Köln
Device: prs-650 / prs-350 /kindle 3
recipe for Impulse.de - german

Code:
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1305470859(BasicNewsRecipe):
    title                 = u'Impulse.de'
    language              = 'de'
    __author__            = 'schuster'
    oldest_article        =14
    max_articles_per_feed = 100
    no_stylesheets        = True
    remove_javascript     = True
    use_embedded_content  = False
    cover_url = 'http://www.bvk.de/files/image/bilder/Logo%20Impulse.jpg'

    extra_css = '''
                    h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
                    h4{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
                    img {min-width:300px; max-width:600px; min-height:300px; max-height:800px}
                    p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
                    body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
	'''
    def print_version(self, url):
        return url.replace ('#utm_source=rss2&utm_medium=rss_feed&utm_campaign=/', '?mode=print')
    remove_tags_bevor = [dict(name='h1', attrs={'class':'h2'})]
    remove_tags_after = [dict(name='div', attrs={'class':'artikelfuss'})]

    feeds = [   (u'impulstest', u'http://www.impulse.de/rss/')]


    remove_tags = [dict(attrs={'class':['navSeitenAlle', 'kommentieren', 'teaserheader', 'teasercontent', 'info', 'zwischenhead', 'kasten_artikel']}),
                dict(id=['metaNav', 'impKopf', 'impTopNav', 'impSubNav', 'footerRahmen', 'gatrixx_marktinformationen', 'pager', 'weitere', 'socialmedia', 'rating_open']),
                dict(span=['ratingtext', 'Gesamtranking', 'h3','']),
	dict(rel=['canonical'])]

Last edited by schuster; 05-18-2011 at 03:48 PM.
schuster is offline   Reply With Quote