New recipe for nrc•next (subscription version)

[vdHummes]

Here is a recipe for the dutch weekday morning newspaper nrc•next.

You need a subscription to use it. It is based on the recipe for NRCHandelsblad.

#!/usr/bin/env  python2
# -*- coding: utf-8 -*-
# Based on veezh's original recipe, Kovid Goyal's New York Times recipe and Snaabs nrc Handelsblad recipe

__license__   = 'GPL v3'
__copyright__ = '2013, Niels Giesen'

'''
www.nrc.nl
'''
import os, zipfile
import time
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ptempfile import PersistentTemporaryFile


class NRCNext(BasicNewsRecipe):

    title = u'nrc•next'
    description = u'De ePaper-versie van nrc•next'
    language = 'nl'
    lang = 'nl-NL'
    needs_subscription = True

    __author__ = 'Niels Giesen'

    conversion_options = {
        'no_default_epub_cover' : True
    }

    def get_browser(self):
        br = BasicNewsRecipe.get_browser(self)
        if self.username is not None and self.password is not None:
            br.open('http://login.nrc.nl/login')
            br.select_form(nr=0)
            br['username'] = self.username
            br['password'] = self.password
            br.submit()
        return br

    def build_index(self):

        today = time.strftime("%Y%m%d")

        domain = "http://digitaleeditie.nrc.nl"

        url = domain + "/digitaleeditie/helekrant/epub/nn_" + today + ".epub"
        #print url

        try:
            br = self.get_browser()
            f = br.open(url)
        except:
            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())
        f.close()
        br.close()
        if zipfile.is_zipfile(tmp):
            try:
                zfile = zipfile.ZipFile(tmp.name, 'r')
                zfile.extractall(self.output_dir)
                self.report_progress(0,_('extracting epub'))
            except zipfile.BadZipfile:
                self.report_progress(0,_('BadZip error, continuing'))

        tmp.close()
        index = os.path.join(self.output_dir, 'metadata.opf')

        self.report_progress(1,_('epub downloaded and extracted'))

        return index

[kovidgoyal]

Is there some difference to the existing builtin nrc handelsblad recipe?

[vdHummes]

Yes, it is a different newspaper, though by the same publisher (NRC Handelsblad is lengthier and an afternoon paper).

Besides some different names, to differentiate nrc next from NRC Handelsblad, the code functionally differs only marginally: in the URL where the epub file is to be fetched:

*** 44,50 ****
  
          domain = "http://digitaleeditie.nrc.nl"
  
!         url = domain + "/digitaleeditie/helekrant/epub/nrc_" + today + ".epub"
          #print url
  
          try:
--- 44,50 ----
  
          domain = "http://digitaleeditie.nrc.nl"
  
!         url = domain + "/digitaleeditie/helekrant/epub/nn_" + today + ".epub"
          #print url
  
          try:

[kovidgoyal]

Ah, ok, thanks.