Fix #6794 (Updated recipes for Infobae and NSPM)

This commit is contained in:
Kovid Goyal 2010-09-12 11:11:00 -06:00
parent 5ce924d10a
commit 80c976e0f2
2 changed files with 30 additions and 63 deletions

View File

@ -1,12 +1,8 @@
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2008-2009, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
infobae.com
'''
import re
import urllib, urlparse
from calibre.web.feeds.news import BasicNewsRecipe
@ -20,35 +16,24 @@ class Infobae(BasicNewsRecipe):
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
language = 'es'
lang = 'es-AR'
language = 'es'
encoding = 'cp1252'
cover_url = 'http://www.infobae.com/imgs/header/header.gif'
masthead_url = 'http://www.infobae.com/imgs/header/header.gif'
remove_javascript = True
preprocess_regexps = [(re.compile(
r'<meta name="Description" content="[^"]+">'), lambda m:'')]
html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True'
extra_css = '''
.col-center{font-family:Arial,Helvetica,sans-serif;}
h1{font-family:Arial,Helvetica,sans-serif; color:#0D4261;}
.fuenteIntNota{font-family:Arial,Helvetica,sans-serif; color:#1D1D1D; font-size:x-small;}
'''
keep_only_tags = [dict(name='div', attrs={'class':['content']})]
remove_tags = [
dict(name='div', attrs={'class':['options','col-right','controles', 'bannerLibre','tiulo-masleidas','masleidas-h']}),
dict(name='a', attrs={'name' : 'comentario',}),
dict(name='iframe'),
dict(name='img', alt = "Ver galerias de imagenes"),
]
remove_empty_feeds = True
extra_css = '''
body{font-family:Arial,Helvetica,sans-serif;}
.popUpTitulo{color:#0D4261; font-size: xx-large}
'''
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
, 'linearize_tables' : True
}
feeds = [
(u'Noticias' , u'http://www.infobae.com/adjuntos/html/RSS/hoy.xml' )
@ -57,39 +42,14 @@ class Infobae(BasicNewsRecipe):
,(u'Deportes' , u'http://www.infobae.com/adjuntos/html/RSS/deportes.xml' )
]
# def print_version(self, url):
# main, sep, article_part = url.partition('contenidos/')
# article_id, rsep, rrest = article_part.partition('-')
# return u'http://www.infobae.com/notas/nota_imprimir.php?Idx=' + article_id
def get_article_url(self, article):
ans = article.get('link').encode('utf-8')
parts = list(urlparse.urlparse(ans))
parts[2] = urllib.quote(parts[2])
ans = urlparse.urlunparse(parts)
return ans.decode('utf-8')
def preprocess_html(self, soup):
for tag in soup.head.findAll('strong'):
tag.extract()
for tag in soup.findAll('meta'):
del tag['content']
tag.extract()
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">\n<meta http-equiv="Content-Language" content="es-AR"/>\n'
soup.head.insert(0,mtag)
for item in soup.findAll(style=True):
del item['style']
return soup
def print_version(self, url):
article_part = url.rpartition('/')[2]
article_id= article_part.partition('-')[0]
return 'http://www.infobae.com/notas/nota_imprimir.php?Idx=' + article_id
def postprocess_html(self, soup, first):
for tag in soup.findAll(name='strong'):
tag.name = 'b'
return soup

View File

@ -6,6 +6,7 @@ nspm.rs
import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag, NavigableString
class Nspm(BasicNewsRecipe):
title = 'Nova srpska politicka misao'
@ -21,6 +22,7 @@ class Nspm(BasicNewsRecipe):
encoding = 'utf-8'
language = 'sr'
delay = 2
remove_empty_feeds = True
publication_type = 'magazine'
masthead_url = 'http://www.nspm.rs/templates/jsn_epic_pro/images/logol.jpg'
extra_css = """ @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)}
@ -45,8 +47,9 @@ class Nspm(BasicNewsRecipe):
dict(name=['link','object','embed','script','meta','base','iframe'])
,dict(attrs={'class':'buttonheading'})
]
remove_tags_after = dict(attrs={'class':'article_separator'})
remove_attributes = ['width','height']
remove_tags_before = dict(attrs={'class':'contentheading'})
remove_tags_after = dict(attrs={'class':'article_separator'})
remove_attributes = ['width','height']
def get_browser(self):
br = BasicNewsRecipe.get_browser()
@ -67,4 +70,8 @@ class Nspm(BasicNewsRecipe):
def preprocess_html(self, soup):
for item in soup.body.findAll(style=True):
del item['style']
for item in soup.body.findAll('h1'):
nh = NavigableString(item.a.string)
item.a.extract()
item.insert(0,nh)
return self.adeify_images(soup)