mirror of
				https://github.com/kovidgoyal/calibre.git
				synced 2025-10-30 18:22:25 -04:00 
			
		
		
		
	
		
			
				
	
	
		
			50 lines
		
	
	
		
			2.0 KiB
		
	
	
	
		
			Plaintext
		
	
	
	
	
	
			
		
		
	
	
			50 lines
		
	
	
		
			2.0 KiB
		
	
	
	
		
			Plaintext
		
	
	
	
	
	
| __license__   = 'GPL v3'
 | |
| __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
 | |
| '''
 | |
| abc.com.py
 | |
| '''
 | |
| 
 | |
| from calibre.web.feeds.news import BasicNewsRecipe
 | |
| 
 | |
| class ABC_py(BasicNewsRecipe):
 | |
|     title                 = 'ABC digital'
 | |
|     __author__            = 'Darko Miletic'
 | |
|     description           = 'Noticias de Paraguay y el resto del mundo'
 | |
|     publisher             = 'ABC'
 | |
|     category              = 'news, politics, Paraguay'
 | |
|     oldest_article        = 2
 | |
|     max_articles_per_feed = 200
 | |
|     no_stylesheets        = True
 | |
|     encoding              = 'cp1252'
 | |
|     use_embedded_content  = False
 | |
|     language              = 'es_PY'
 | |
|     remove_empty_feeds    = True
 | |
|     publication_type      = 'newspaper'
 | |
|     extra_css             = ' body{font-family: Arial,Helvetica,sans-serif } img{margin-bottom: 0.4em} '
 | |
| 
 | |
|     conversion_options = {
 | |
|                           'comment'   : description
 | |
|                         , 'tags'      : category
 | |
|                         , 'publisher' : publisher
 | |
|                         , 'language'  : language
 | |
|                         }
 | |
| 
 | |
|     remove_tags       = [dict(name=['form','iframe','embed','object','link','base','table']),dict(attrs={'class':'toolbox'})]
 | |
|     remove_tags_after = dict(attrs={'class':'date'})
 | |
|     keep_only_tags    = [dict(attrs={'class':'zcontent'})]
 | |
| 
 | |
| 
 | |
|     feeds = [
 | |
|                (u'Ultimo momento'      , u'http://www.abc.com.py/ultimo-momento.xml'      )
 | |
|               ,(u'Nacionales'          , u'http://www.abc.com.py/nacionales.xml'          )
 | |
|               ,(u'Internacionales'     , u'http://www.abc.com.py/internacionales.xml'     )
 | |
|               ,(u'Deportes'            , u'http://www.abc.com.py/deportes.xml'            )
 | |
|               ,(u'Espectaculos'        , u'http://www.abc.com.py/espectaculos.xml'        )
 | |
|               ,(u'Ciencia y Tecnologia', u'http://www.abc.com.py/ciencia-y-tecnologia.xml')
 | |
|             ]
 | |
| 
 | |
|     def preprocess_html(self, soup):
 | |
|         for item in soup.findAll(style=True):
 | |
|             del item['style']
 | |
|         return soup
 |