diff --git a/resources/recipes/pagina12.recipe b/resources/recipes/pagina12.recipe index a5ee18a7ed..da16c1697b 100644 --- a/resources/recipes/pagina12.recipe +++ b/resources/recipes/pagina12.recipe @@ -15,14 +15,14 @@ class Pagina12(BasicNewsRecipe): publisher = 'La Pagina S.A.' category = 'news, politics, Argentina' oldest_article = 2 - max_articles_per_feed = 100 + max_articles_per_feed = 200 no_stylesheets = True encoding = 'cp1252' use_embedded_content = False language = 'es' remove_empty_feeds = True masthead_url = 'http://www.pagina12.com.ar/commons/imgs/logo-home.gif' - extra_css = ' body{font-family: Arial,Helvetica,sans-serif } h2{color: #028CCD} img{margin-bottom: 0.4em} .epigrafe{font-size: x-small; background-color: #EBEAE5; color: #565144 } .intro{font-size: 1.1em} ' + extra_css = ' body{font-family: Arial,Helvetica,sans-serif } img{margin-bottom: 0.4em} #autor{font-weight: bold} #fecha,#epigrafe{font-size: 0.9em; margin: 5px} #imagen{border: 1px solid black; margin: 0 0 1.25em 1.25em; width: 232px } ' conversion_options = { 'comment' : description @@ -45,7 +45,9 @@ class Pagina12(BasicNewsRecipe): ,(u'NO' , u'http://www.pagina12.com.ar/diario/rss/no.xml' ) ,(u'Las/12' , u'http://www.pagina12.com.ar/diario/rss/las12.xml' ) ,(u'Soy' , u'http://www.pagina12.com.ar/diario/rss/soy.xml' ) - ,(u'M2' , u'http://www.pagina12.com.ar/diario/rss/futuro.xml' ) + ,(u'Futuro' , u'http://www.pagina12.com.ar/diario/rss/futuro.xml' ) + ,(u'M2' , u'http://www.pagina12.com.ar/diario/rss/m2.xml' ) + ,(u'Rosario/12' , u'http://www.pagina12.com.ar/diario/rss/rosario.xml' ) ] def print_version(self, url): @@ -60,3 +62,7 @@ class Pagina12(BasicNewsRecipe): return image['src'] return None + def preprocess_html(self, soup): + for item in soup.findAll(style=True): + del item['style'] + return soup \ No newline at end of file diff --git a/resources/recipes/variety.recipe b/resources/recipes/variety.recipe index 7321e0ad33..9f0c445e6b 100644 --- a/resources/recipes/variety.recipe +++ b/resources/recipes/variety.recipe @@ -1,46 +1,46 @@ -#!/usr/bin/env python - -__license__ = 'GPL v3' -__copyright__ = '2009, Darko Miletic ' -''' -www.variety.com -''' - -from calibre.web.feeds.recipes import BasicNewsRecipe - -class Variety(BasicNewsRecipe): - title = 'Variety' - __author__ = 'Darko Miletic' - description = 'Breaking entertainment movie news, movie reviews, entertainment industry events, news and reviews from Cannes, Oscars, and Hollywood awards. Featuring box office charts, archives and more.' - oldest_article = 2 - max_articles_per_feed = 100 - no_stylesheets = True - use_embedded_content = False - encoding = 'cp1252' - publisher = 'Red Business Information' - category = 'Entertainment Industry News, Daily Variety, Movie Reviews, TV, Awards, Oscars, Cannes, Box Office, Hollywood' - language = 'en' - - conversion_options = { - 'comments' : description - ,'tags' : category - ,'language' : language - ,'publisher' : publisher - } - - remove_tags = [dict(name=['object','link','map'])] - - keep_only_tags = [dict(name='div', attrs={'id':'article'})] - - feeds = [(u'News & Articles', u'http://feeds.feedburner.com/variety/headlines' )] - - def print_version(self, url): - rpt = url.rpartition('?')[0] - artid = rpt.rpartition('/')[2] - catidr = url.rpartition('categoryid=')[2] - catid = catidr.partition('&')[0] - return 'http://www.variety.com/index.asp?layout=print_story&articleid=' + artid + '&categoryid=' + catid - - def get_article_url(self, article): - return article.get('feedburner_origlink', None) - +__license__ = 'GPL v3' +__copyright__ = '2009-2010, Darko Miletic ' +''' +www.variety.com +''' + +from calibre.web.feeds.recipes import BasicNewsRecipe + +class Variety(BasicNewsRecipe): + title = 'Variety' + __author__ = 'Darko Miletic' + description = 'Breaking entertainment movie news, movie reviews, entertainment industry events, news and reviews from Cannes, Oscars, and Hollywood awards. Featuring box office charts, archives and more.' + oldest_article = 2 + max_articles_per_feed = 100 + no_stylesheets = True + use_embedded_content = False + encoding = 'cp1252' + publisher = 'Red Business Information' + category = 'Entertainment Industry News, Daily Variety, Movie Reviews, TV, Awards, Oscars, Cannes, Box Office, Hollywood' + language = 'en' + masthead_url = 'http://a330.g.akamai.net/7/330/23382/20090528190853/www.variety.com/graphics/variety/Variety_logo_green_tm.gif' + extra_css = ' body{font-family: Georgia,"Times New Roman",Times,Courier,serif } img{margin-bottom: 1em} ' + + conversion_options = { + 'comments' : description + ,'tags' : category + ,'language' : language + ,'publisher' : publisher + } + + remove_tags = [dict(name=['object','link','map'])] + + keep_only_tags = [dict(name='div', attrs={'id':'article'})] + + feeds = [(u'News & Articles', u'http://feeds.feedburner.com/variety/headlines' )] + + def print_version(self, url): + rpt = url.rpartition('?')[0] + artid = rpt.rpartition('/')[2] + catidr = url.rpartition('categoryid=')[2] + catid = catidr.partition('&')[0] + return 'http://www.variety.com/index.asp?layout=print_story&articleid=' + artid + '&categoryid=' + catid + + + def preprocess_html(self, soup): + return self.adeify_images(soup)