Hi there,
I bring an update to heraldo.es
Spoiler:
Code:
#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '04 December 2010, desUBIKado'
__author__ = 'desUBIKado'
__description__ = 'Daily newspaper from Aragon'
__version__ = 'v0.05'
__date__ = '5, Februery 2012'
'''
http://www.heraldo.es/
'''
import time
import re
from calibre.web.feeds.news import BasicNewsRecipe
class heraldo(BasicNewsRecipe):
author = 'desUBIKado'
description = 'Daily newspaper from Aragon'
title = u'Heraldo de Aragon'
publisher = 'OJD Nielsen'
category = 'News, politics, culture, economy, general interest'
language = 'es'
timefmt = '[%a, %d %b, %Y]'
oldest_article = 2
delay = 1
max_articles_per_feed = 100
use_embedded_content = False
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={'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']}),
dict(name='form', attrs={'class':'form'}),
dict(name='ul', attrs={'id':['cont-tags','pag-1']})]
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
#http://oldorigin-www.heraldo.es/2010...ada_aragon.pdf
cover='http://oldorigin-www.heraldo.es/'+ year + month + day +'/primeras/portada_aragon.pdf'
br = BasicNewsRecipe.get_browser()
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;}
.con h2{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:30px;}
.con span{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:12px;}
.ent {font-family:Arial,Helvetica,sans-serif; font-weight:normal; font-style:italic; font-size:18px;}
img{margin-bottom: 0.4em}
'''
preprocess_regexps = [
# Para separar los comentarios con una linea en blanco
(re.compile(r'<div id="com"', re.DOTALL|re.IGNORECASE), lambda match: '<br><div id="com"')
]
Greetings