# -*- coding: utf-8 -*- __license__ = 'GPL v3' __author__ = 'Luis Hernandez' __copyright__ = 'Luis Hernandez' __version__ = 'v1.0' __date__ = '01 Feb 2011' ''' http://www.promecal.es/ ''' from calibre.web.feeds.news import BasicNewsRecipe class AdvancedUserRecipe1294946868(BasicNewsRecipe): title = u'La Tribuna de' publisher = u'Grupo PROMECAL' __author__ = 'Luis Hernández' description = 'Varios diarios locales del grupo PROMECAL' oldest_article = 3 max_articles_per_feed = 50 remove_javascript = True no_stylesheets = True use_embedded_content = False encoding = 'utf-8' language = 'es' timefmt = '[%a, %d %b, %Y]' keep_only_tags = [ dict(name='div', attrs={'id': ['articulo']}), dict(name='div', attrs={ 'class': ['foto']}), dict(name='p', attrs={'id': ['texto']}) ] remove_tags_before = dict(name='div', attrs={'class': ['comparte']}) remove_tags_after = dict(name='div', attrs={'id': ['relacionadas']}) remove_tags = [ dict(name='div', attrs={'id': ['relacionadas']}), dict( name='h3'), dict(name='h5') ] extra_css = """ p{text-align: justify; font-size: 100%} body{text-align: left; font-family: serif; font-size: 100%} h1{font-family: sans; font-size:150%; font-weight: bold; text-align: justify;} h2{font-family: sans-serif; font-size:85%; font-style: italic; text-align: justify;} h4{font-family: sans; font-size:75%; font-weight: bold; text-align: center;} img{margin-bottom: 0.4em} """ def preprocess_html(self, soup): for alink in soup.findAll('a'): if alink.string is not None: tstr = alink.string alink.replaceWith(tstr) return soup feeds = [ (u'Albacete', u'http://www.latribunadealbacete.es/rss.html'), (u'Avila', u'http://www.diariodeavila.es/rss.html'), (u'Burgos', u'http://www.diariodeburgos.es/rss.html'), (u'Ciudad Real', u'http://www.latribunadeciudadreal.es/rss.html'), (u'Palencia', u'http://www.diariopalentino.es/rss.html'), (u'Puertollano', u'http://www.latribunadepuertollano.es/rss.html'), (u'Talavera de la Reina', u'http://www.latribunadetalavera.es/rss.html'), (u'Toledo', u'http://www.latribunadetoledo.es/rss.html'), (u'Valladolid', u'http://www.eldiadevalladolid.com/rss.html') ]