From b58aa580f76656a76c39d446a32bfc1651e02095 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Thu, 28 Oct 2010 15:38:53 -0600 Subject: [PATCH] Fix #7324 (New recipe for argentinian newsportal Perfil) --- resources/images/news/perfil.png | Bin 0 -> 781 bytes resources/recipes/perfil.recipe | 66 +++++++++++++++++++++++++++++++ 2 files changed, 66 insertions(+) create mode 100644 resources/images/news/perfil.png create mode 100644 resources/recipes/perfil.recipe diff --git a/resources/images/news/perfil.png b/resources/images/news/perfil.png new file mode 100644 index 0000000000000000000000000000000000000000..54c8159e48e6d0b03642ad0889ad224445e94588 GIT binary patch literal 781 zcmeAS@N?(olHy`uVBq!ia0vp^0wB!61SBU+%rFB|oCO|{#X#BvjNMLV+kphj3LMjc zG*~r5%(1nH85o#6JY5_^G|o?*xZhv6P~zD9_jk9Kuf48a9xf1aD@ZD;l~E}1({YBv z11$y?QobHCB?X`L3yKPgFSH7<`}QOTMMju-Nq87^DK6{^GPrQz+q+wj7kuCQdhX$g zQa5XkpZ{%BInP{w=A50~|0TH`yvyb-s9G!KQ;rjj^Tb%q?e2psobL#18 z=at;e;!k(59I)D8zJ0sb)nnh!&R-U{kU>Fp`LR#(`~Mlp*4KRa(>!zb!gp79xB9DE zuXsPRN_C2(*Cm6J^!q!?GII(uRZF8-19aZn%$favwzevxhElqfovLg)!<4=Wn|iD- z3-2tEZ#aMdn#e@%@R<_QC%&5NKK}VfS~qq9!x|U;hU>T8?qt|_GCL^F)=V)D{1~#{ z>G4UChU3Nh3?{ojm-KrSGC0J9mB-etUv|1M^V{EFZaU027=+Gljdsq8D4lAlV!zud zsk7|%#opHR@A-es_P*rbn&iTncx2lxrhSH$`Saagn=E2o>+2V>{O;ll?w3xrywbLd zH+{f<4S877>#92!2Uf4@cm!x4k3xocmyTW?o)3z`+CerfU3Pp6w#XrC0k z{phBNYkC{VN+Z-8vN(C5PcTb)EW6{~RRIUfz@A;p%l}lP> zJaAvcDkYLD#-aP}hsgD}LN6`(7))3q7qTj7ZwZlNc)=slpf{1}0mBiCPuIGcE;!!0 zduZ#!i4yKCfgFmRsum1q691NMeN-XUly^?s`rW37MR~=Cv)<0ODvr3B_i0^qm_xyp zAIx!nua6{I+^hyBFx3**h?11Vl2ohYqEsNoU}RuupbJDs79obFR>o#lCPumjW>y9U rK3qKpC>nC}Q!>*kQ8ZXs85>#|89+3g3=dZYYGCkm^>bP0l+XkKKAJ=k literal 0 HcmV?d00001 diff --git a/resources/recipes/perfil.recipe b/resources/recipes/perfil.recipe new file mode 100644 index 0000000000..7f51485bd0 --- /dev/null +++ b/resources/recipes/perfil.recipe @@ -0,0 +1,66 @@ +__license__ = 'GPL v3' +__copyright__ = '2010, Darko Miletic ' +''' +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' + 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} + """ + + 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'}) + ] + keep_only_tags=[dict(attrs={'class':['bd468a','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 preprocess_html(self, soup): + for item in soup.findAll(style=True): + del item['style'] + return soup