Update Heraldo de Aragon

This commit is contained in:
Kovid Goyal 2013-12-03 07:58:57 +05:30
parent aa0521803f
commit 8ee2c08747

View File

@ -3,10 +3,10 @@ __license__ = 'GPL v3'
__copyright__ = '04 December 2010, desUBIKado'
__author__ = 'desUBIKado'
__description__ = 'Daily newspaper from Aragon'
__version__ = 'v0.05'
__date__ = '5, Februery 2012'
__version__ = 'v0.06'
__date__ = '01, December 2013'
'''
[url]http://www.heraldo.es/[/url]
http://www.heraldo.es/
'''
import time
@ -17,7 +17,7 @@ class heraldo(BasicNewsRecipe):
__author__ = 'desUBIKado'
description = 'Daily newspaper from Aragon'
title = u'Heraldo de Aragon'
publisher = 'OJD Nielsen'
publisher = 'Grupo Heraldo'
category = 'News, politics, culture, economy, general interest'
language = 'es'
timefmt = '[%a, %d %b, %Y]'
@ -25,42 +25,44 @@ class heraldo(BasicNewsRecipe):
delay = 1
max_articles_per_feed = 100
use_embedded_content = False
masthead_url = 'http://www.heraldo.es/MODULOS/global/publico/interfaces/img/logo-Heraldo.png'
remove_empty_feeds = True
remove_javascript = True
no_stylesheets = True
feeds = [
(u'Portadas', u'http://www.heraldo.es/index.php/mod.portadas/mem.rss')
]
keep_only_tags = [dict(name='div', attrs={'class':['row-f2 brd-row-f4 bck-row-f1-f1 padd-t padd-btt con n-marg-btt']}),
dict(name='div', attrs={'id':['dts','com']})]
keep_only_tags = [dict(name='div', attrs={'id':['dts','com']})]
remove_tags = [dict(name='a', attrs={'class':['com flo-r','enl-if','enl-df']}),
dict(name='div', attrs={'class':['brb-b-s con marg-btt','cnt-rel con','col5-f1']}),
remove_tags = [dict(name='a', attrs={'class':['com flo-r','enl-if','enl-df','next_com']}),
dict(name='div', attrs={'class':['brb-b-s con marg-btt','cnt-rel con','col5-f1','tit txt-wh f-s con','con cont-top ']}),
dict(name='div', attrs={'id':['cont-Top-8760','caj-pub','8760-cpt1']}),
dict(name='form', attrs={'class':'form'}),
dict(name='ul', attrs={'id':['cont-tags','pag-1']})]
dict(name='ul', attrs={'class':['tabs-nav','lst-not-f2 con']}),
dict(name='span', attrs={'class':['flo-r']}),
dict(name='ul', attrs={'id':['cont-tags','pag-1','pag-cnt-I-']})]
remove_tags_before = dict(name='div' , attrs={'id':'dts'})
remove_tags_after = dict(name='div' , attrs={'id':'com'})
def get_cover_url(self):
cover = None
st = time.localtime()
year = str(st.tm_year)
month = "%.2d" % st.tm_mon
day = "%.2d" % st.tm_mday
#[url]http://oldorigin-www.heraldo.es/20101211/primeras/portada_aragon.pdf[/url]
cover='http://oldorigin-www.heraldo.es/'+ year + month + day +'/primeras/portada_aragon.pdf'
br = BasicNewsRecipe.get_browser(self)
try:
br.open(cover)
except:
self.log("\nPortada no disponible")
cover ='http://www.heraldo.es/MODULOS/global/publico/interfaces/img/logo-Heraldo.png'
return cover
cover = None
st = time.localtime()
year = str(st.tm_year)
month = "%.2d" % st.tm_mon
day = "%.2d" % st.tm_mday
# http://oldorigin-www.heraldo.es/20101211/primeras/portada_aragon.pdf
cover='http://oldorigin-www.heraldo.es/'+ year + month + day +'/primeras/portada_aragon.pdf'
br = BasicNewsRecipe.get_browser(self)
try:
br.open(cover)
except:
self.log("\nPortada no disponible")
cover ='http://www.heraldo.es/MODULOS/global/publico/interfaces/img/logo-Heraldo.png'
return cover
extra_css = '''
.con strong{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:16px;}
@ -76,5 +78,3 @@ class heraldo(BasicNewsRecipe):
(re.compile(r'<div id="com"', re.DOTALL|re.IGNORECASE), lambda match: '<br><div id="com"')
]