Fix #4876 (Updated recipes)

This commit is contained in:
Kovid Goyal 2010-02-12 09:51:58 -07:00
parent ba2b5056b0
commit a3052cf127
2 changed files with 55 additions and 49 deletions

View File

@ -15,14 +15,14 @@ class Pagina12(BasicNewsRecipe):
publisher = 'La Pagina S.A.' publisher = 'La Pagina S.A.'
category = 'news, politics, Argentina' category = 'news, politics, Argentina'
oldest_article = 2 oldest_article = 2
max_articles_per_feed = 100 max_articles_per_feed = 200
no_stylesheets = True no_stylesheets = True
encoding = 'cp1252' encoding = 'cp1252'
use_embedded_content = False use_embedded_content = False
language = 'es' language = 'es'
remove_empty_feeds = True remove_empty_feeds = True
masthead_url = 'http://www.pagina12.com.ar/commons/imgs/logo-home.gif' 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 = { conversion_options = {
'comment' : description 'comment' : description
@ -45,7 +45,9 @@ class Pagina12(BasicNewsRecipe):
,(u'NO' , u'http://www.pagina12.com.ar/diario/rss/no.xml' ) ,(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'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'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): def print_version(self, url):
@ -60,3 +62,7 @@ class Pagina12(BasicNewsRecipe):
return image['src'] return image['src']
return None return None
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup

View File

@ -1,46 +1,46 @@
#!/usr/bin/env python __license__ = 'GPL v3'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
__license__ = 'GPL v3' '''
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>' www.variety.com
''' '''
www.variety.com
''' from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.web.feeds.recipes import BasicNewsRecipe class Variety(BasicNewsRecipe):
title = 'Variety'
class Variety(BasicNewsRecipe): __author__ = 'Darko Miletic'
title = 'Variety' 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.'
__author__ = 'Darko Miletic' oldest_article = 2
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.' max_articles_per_feed = 100
oldest_article = 2 no_stylesheets = True
max_articles_per_feed = 100 use_embedded_content = False
no_stylesheets = True encoding = 'cp1252'
use_embedded_content = False publisher = 'Red Business Information'
encoding = 'cp1252' category = 'Entertainment Industry News, Daily Variety, Movie Reviews, TV, Awards, Oscars, Cannes, Box Office, Hollywood'
publisher = 'Red Business Information' language = 'en'
category = 'Entertainment Industry News, Daily Variety, Movie Reviews, TV, Awards, Oscars, Cannes, Box Office, Hollywood' masthead_url = 'http://a330.g.akamai.net/7/330/23382/20090528190853/www.variety.com/graphics/variety/Variety_logo_green_tm.gif'
language = 'en' extra_css = ' body{font-family: Georgia,"Times New Roman",Times,Courier,serif } img{margin-bottom: 1em} '
conversion_options = { conversion_options = {
'comments' : description 'comments' : description
,'tags' : category ,'tags' : category
,'language' : language ,'language' : language
,'publisher' : publisher ,'publisher' : publisher
} }
remove_tags = [dict(name=['object','link','map'])] remove_tags = [dict(name=['object','link','map'])]
keep_only_tags = [dict(name='div', attrs={'id':'article'})] keep_only_tags = [dict(name='div', attrs={'id':'article'})]
feeds = [(u'News & Articles', u'http://feeds.feedburner.com/variety/headlines' )] feeds = [(u'News & Articles', u'http://feeds.feedburner.com/variety/headlines' )]
def print_version(self, url): def print_version(self, url):
rpt = url.rpartition('?')[0] rpt = url.rpartition('?')[0]
artid = rpt.rpartition('/')[2] artid = rpt.rpartition('/')[2]
catidr = url.rpartition('categoryid=')[2] catidr = url.rpartition('categoryid=')[2]
catid = catidr.partition('&')[0] catid = catidr.partition('&')[0]
return 'http://www.variety.com/index.asp?layout=print_story&articleid=' + artid + '&categoryid=' + catid 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) def preprocess_html(self, soup):
return self.adeify_images(soup)