Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Heraldo de Aragon

Browse Source
This commit is contained in:
Kovid Goyal 2011-01-09 11:47:15 -07:00
parent be03e57f2c
commit 9fff468d74
1 changed files with 35 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
resources/recipes/heraldo.recipe
View File

@ -3,29 +3,31 @@ __license__ = 'GPL v3'
__copyright__ = '04 December 2010, desUBIKado' __copyright__ = '04 December 2010, desUBIKado'
__author__ = 'desUBIKado' __author__ = 'desUBIKado'
__description__ = 'Daily newspaper from Aragon' __description__ = 'Daily newspaper from Aragon'
__version__ = 'v0.03' __version__ = 'v0.04'
__date__ = '11, December 2010' __date__ = '6, Januery 2011'
''' '''
[url]http://www.heraldo.es/[/url] [url]http://www.heraldo.es/[/url]
''' '''
import time import time
import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class heraldo(BasicNewsRecipe): class heraldo(BasicNewsRecipe):
__author__ = 'desUBIKado' __author__ = 'desUBIKado'
description = 'Daily newspaper from Aragon' description = 'Daily newspaper from Aragon'
title = u'Heraldo de Aragon' title = u'Heraldo de Aragon'
publisher = 'OJD Nielsen' publisher = 'OJD Nielsen'
category = 'News, politics, culture, economy, general interest' category = 'News, politics, culture, economy, general interest'
language = 'es' language = 'es'
timefmt = '[%a, %d %b, %Y]' timefmt = '[%a, %d %b, %Y]'
oldest_article = 1 oldest_article = 2
delay = 1
max_articles_per_feed = 100 max_articles_per_feed = 100
use_embedded_content = False use_embedded_content = False
remove_javascript = True remove_javascript = True
no_stylesheets = True no_stylesheets = True
recursion = 10
feeds = [ feeds = [
(u'Portadas', u'http://www.heraldo.es/index.php/mod.portadas/mem.rss') (u'Portadas', u'http://www.heraldo.es/index.php/mod.portadas/mem.rss')
@ -37,29 +39,39 @@ class heraldo(BasicNewsRecipe):
remove_tags = [dict(name='a', attrs={'class':['com flo-r','enl-if','enl-df']}), 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']}), dict(name='div', attrs={'class':['brb-b-s con marg-btt','cnt-rel con']}),
dict(name='form', attrs={'class':'form'})] 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_before = dict(name='div' , attrs={'id':'dts'})
remove_tags_after = dict(name='div' , attrs={'id':'com'}) remove_tags_after = dict(name='div' , attrs={'id':'com'})
def get_cover_url(self): def get_cover_url(self):
cover = None cover = None
st = time.localtime() st = time.localtime()
year = str(st.tm_year) year = str(st.tm_year)
month = "%.2d" % st.tm_mon month = "%.2d" % st.tm_mon
day = "%.2d" % st.tm_mday day = "%.2d" % st.tm_mday
#[url]http://oldorigin-www.heraldo.es/20101211/primeras/portada_aragon.pdf[/url] #[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' cover='http://oldorigin-www.heraldo.es/'+ year + month + day +'/primeras/portada_aragon.pdf'
br = BasicNewsRecipe.get_browser() br = BasicNewsRecipe.get_browser()
try: try:
br.open(cover) br.open(cover)
except: except:
self.log("\nPortada no disponible") self.log("\nPortada no disponible")
cover ='http://www.heraldo.es/MODULOS/global/publico/interfaces/img/logo-Heraldo.png' cover ='http://www.heraldo.es/MODULOS/global/publico/interfaces/img/logo-Heraldo.png'
return cover return cover
extra_css = ''' extra_css = '''
h2{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:xx-large;} .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 = [
# To separate the comments with a blank line
(re.compile(r'<div id="com"', re.DOTALL|re.IGNORECASE), lambda match: '<br><div id="com"')
]