NRC EPUB version by veezh

This commit is contained in:
Kovid Goyal 2010-12-22 11:05:12 -07:00
parent bf661325db
commit cea5261e12

View File

@ -0,0 +1,58 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#Based on Lars Jacob's Taz Digiabo recipe
__license__ = 'GPL v3'
__copyright__ = '2010, veezh'
'''
www.nrc.nl
'''
import os, urllib2, zipfile
import time
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ptempfile import PersistentTemporaryFile
class NRCHandelsblad(BasicNewsRecipe):
title = u'NRC Handelsblad'
description = u'De EPUB-versie van NRC'
language = 'nl'
lang = 'nl-NL'
__author__ = 'veezh'
conversion_options = {
'no_default_epub_cover' : True
}
def build_index(self):
today = time.strftime("%Y%m%d")
domain = "http://digitaleeditie.nrc.nl"
url = domain + "/digitaleeditie/helekrant/epub/nrc_" + today + ".epub"
# print url
try:
f = urllib2.urlopen(url)
except urllib2.HTTPError:
self.report_progress(0,_('Kan niet inloggen om editie te downloaden'))
raise ValueError('Krant van vandaag nog niet beschikbaar')
tmp = PersistentTemporaryFile(suffix='.epub')
self.report_progress(0,_('downloading epub'))
tmp.write(f.read())
tmp.close()
zfile = zipfile.ZipFile(tmp.name, 'r')
self.report_progress(0,_('extracting epub'))
zfile.extractall(self.output_dir)
tmp.close()
index = os.path.join(self.output_dir, 'content.opf')
self.report_progress(1,_('epub downloaded and extracted'))
return index