home *** CD-ROM | disk | FTP | other *** search
- __license__ = 'GPL v3'
- __copyright__ = '2010-2011, Darko Miletic <darko.miletic at gmail.com>'
- '''
- perfil.com
- '''
-
- from calibre.web.feeds.news import BasicNewsRecipe
-
- class Perfil(BasicNewsRecipe):
- title = 'Perfil'
- __author__ = 'Darko Miletic'
- description = 'Noticias de Argentina y el resto del mundo'
- publisher = 'perfil.com'
- category = 'news, politics, Argentina'
- oldest_article = 2
- max_articles_per_feed = 200
- no_stylesheets = True
- encoding = 'cp1252'
- use_embedded_content = False
- language = 'es_AR'
- remove_empty_feeds = True
- masthead_url = 'http://www.perfil.com/export/sites/diarioperfil/arte/10/logo_perfilcom_mm.gif'
- extra_css = """
- body{font-family: Arial,Helvetica,sans-serif }
- .seccion{border-bottom: 1px dotted #666666; text-transform: uppercase; font-size: x-large}
- .foto1 h1{font-size: x-small}
- h1{font-family: Georgia,"Times New Roman",serif}
- img{margin-bottom: 0.4em}
- .hora{font-size: x-small; color: red}
- """
-
- conversion_options = {
- 'comment' : description
- , 'tags' : category
- , 'publisher' : publisher
- , 'language' : language
- }
-
- remove_tags = [
- dict(name=['iframe','embed','object','base','meta','link'])
- ,dict(name='a', attrs={'href':'#comentarios'})
- ,dict(name='div', attrs={'class':'foto3'})
- ,dict(name='img', attrs={'alt':['ampliar','Ampliar']})
- ]
- keep_only_tags=[dict(attrs={'class':['articulo','cuerpoSuperior']})]
- remove_attributes=['onload','lang','width','height','border']
-
- feeds = [
- (u'Ultimo momento' , u'http://www.perfil.com/rss/ultimomomento.xml')
- ,(u'Politica' , u'http://www.perfil.com/rss/politica.xml' )
- ,(u'Policia' , u'http://www.perfil.com/rss/policia.xml' )
- ,(u'Internacionales', u'http://www.perfil.com/rss/internacional.xml')
- ,(u'Economia' , u'http://www.perfil.com/rss/economia.xml' )
- ,(u'Deportes' , u'http://www.perfil.com/rss/deportes.xml' )
- ,(u'Opinion' , u'http://www.perfil.com/rss/columnistas.xml' )
- ,(u'Sociedad' , u'http://www.perfil.com/rss/sociedad.xml' )
- ,(u'Cultura' , u'http://www.perfil.com/rss/cultura.xml' )
- ,(u'Espectaculos' , u'http://www.perfil.com/rss/espectaculos.xml' )
- ,(u'Ciencia' , u'http://www.perfil.com/rss/ciencia.xml' )
- ,(u'Salud' , u'http://www.perfil.com/rss/salud.xml' )
- ,(u'Tecnologia' , u'http://www.perfil.com/rss/tecnologia.xml' )
- ]
-
- def get_article_url(self, article):
- return article.get('guid', None)
-
- def preprocess_html(self, soup):
- for item in soup.findAll(style=True):
- del item['style']
- for item in soup.findAll('a'):
- limg = item.find('img')
- if item.string is not None:
- str = item.string
- item.replaceWith(str)
- else:
- if limg:
- item.name = 'div'
- item.attrs = []
- else:
- str = self.tag_to_string(item)
- item.replaceWith(str)
- for item in soup.findAll('img'):
- if not item.has_key('alt'):
- item['alt'] = 'image'
- return soup
-