mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
78 lines
2.4 KiB
Python
78 lines
2.4 KiB
Python
#!/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__ = '2014 Niels Giesen'
|
|
|
|
'''
|
|
www.nrc.nl
|
|
'''
|
|
import os
|
|
import zipfile
|
|
import re
|
|
from io import BytesIO
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from datetime import date, timedelta
|
|
|
|
|
|
class NRCNext(BasicNewsRecipe):
|
|
|
|
title = u'nrc•next'
|
|
description = u'De ePaper-versie van nrc•next'
|
|
language = 'nl'
|
|
needs_subscription = True
|
|
requires_version = (1, 24, 0)
|
|
|
|
__author__ = 'Niels Giesen'
|
|
|
|
conversion_options = {
|
|
'no_default_epub_cover': True
|
|
}
|
|
|
|
def build_index(self):
|
|
import mechanize
|
|
br = mechanize.Browser()
|
|
br.open('https://login.nrc.nl/login', timeout=60)
|
|
br.select_form(nr=0)
|
|
br['username'] = self.username
|
|
br['password'] = self.password
|
|
response2 = br.submit()
|
|
raw = response2.get_data()
|
|
if b'niet ingelogd' in raw: # in body class
|
|
raise ValueError('Failed to login, check username and password')
|
|
epubraw = None
|
|
for today in (date.today(), date.today() - timedelta(days=1),):
|
|
url = 'http://digitaleeditie.nrc.nl/digitaleeditie/helekrant/epub/nn_%s.epub' \
|
|
% today.strftime('%Y%m%d')
|
|
self.log('Trying to download epub from:', url)
|
|
try:
|
|
response3 = br.open(url, timeout=60)
|
|
epubraw = response3.get_data()
|
|
break
|
|
except mechanize.HTTPError:
|
|
self.log('%r not available yet' % url)
|
|
continue
|
|
|
|
if epubraw is None:
|
|
raise ValueError('Krant van vandaag nog niet beschikbaar')
|
|
|
|
zfile = zipfile.ZipFile(BytesIO(epubraw), 'r')
|
|
zfile.extractall(self.output_dir)
|
|
namelist = zfile.namelist()
|
|
emre = re.compile("<em(?:.*)>(.*)</em>")
|
|
subst = '\\1'
|
|
for name in namelist:
|
|
_, ext = os.path.splitext(name)
|
|
if (ext == '.html') or (ext == '.ncx'):
|
|
fname = os.path.join(self.output_dir, name)
|
|
with open(fname) as f:
|
|
s = f.read()
|
|
s = emre.sub(subst, s)
|
|
with open(fname, 'w') as f:
|
|
f.write(s)
|
|
index = os.path.join(self.output_dir, 'metadata.opf')
|
|
return index
|