| 1 |
#!/usr/bin/env python |
| 2 |
# -*- coding: utf-8 -*- |
| 3 |
# Based on veezh's original recipe, Kovid Goyal's New York Times |
| 4 |
# recipe and Snaabs nrc Handelsblad recipe |
| 5 |
|
| 6 |
__license__ = 'GPL v3' |
| 7 |
__copyright__ = '2014 Niels Giesen' |
| 8 |
|
| 9 |
''' |
| 10 |
www.nrc.nl |
| 11 |
''' |
| 12 |
import os |
| 13 |
import re |
| 14 |
import zipfile |
| 15 |
from datetime import date, timedelta |
| 16 |
from io import BytesIO |
| 17 |
|
| 18 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 19 |
|
| 20 |
|
| 21 |
class NRCNext(BasicNewsRecipe): |
| 22 |
title = 'nrc•next' |
| 23 |
description = 'De ePaper-versie van nrc•next' |
| 24 |
language = 'nl' |
| 25 |
needs_subscription = True |
| 26 |
requires_version = (1, 24, 0) |
| 27 |
|
| 28 |
__author__ = 'Niels Giesen' |
| 29 |
|
| 30 |
conversion_options = {'no_default_epub_cover': True} |
| 31 |
|
| 32 |
def build_index(self): |
| 33 |
import mechanize |
| 34 |
|
| 35 |
br = mechanize.Browser() |
| 36 |
br.open('https://login.nrc.nl/login', timeout=60) |
| 37 |
br.select_form(nr=0) |
| 38 |
br['username'] = self.username |
| 39 |
br['password'] = self.password |
| 40 |
response2 = br.submit() |
| 41 |
raw = response2.get_data() |
| 42 |
if b'niet ingelogd' in raw: # in body class |
| 43 |
raise ValueError('Failed to login, check username and password') |
| 44 |
epubraw = None |
| 45 |
for today in ( |
| 46 |
date.today(), |
| 47 |
date.today() - timedelta(days=1), |
| 48 |
): |
| 49 |
url = 'http://digitaleeditie.nrc.nl/digitaleeditie/helekrant/epub/nn_%s.epub' % today.strftime('%Y%m%d') |
| 50 |
self.log('Trying to download epub from:', url) |
| 51 |
try: |
| 52 |
response3 = br.open(url, timeout=60) |
| 53 |
epubraw = response3.get_data() |
| 54 |
break |
| 55 |
except mechanize.HTTPError: |
| 56 |
self.log('%r not available yet' % url) |
| 57 |
continue |
| 58 |
|
| 59 |
if epubraw is None: |
| 60 |
raise ValueError('Krant van vandaag nog niet beschikbaar') |
| 61 |
|
| 62 |
zfile = zipfile.ZipFile(BytesIO(epubraw), 'r') |
| 63 |
zfile.extractall(self.output_dir) |
| 64 |
namelist = zfile.namelist() |
| 65 |
emre = re.compile(r'<em(?:.*)>(.*)</em>') |
| 66 |
subst = '\\1' |
| 67 |
for name in namelist: |
| 68 |
_, ext = os.path.splitext(name) |
| 69 |
if ext in {'.html', '.ncx'}: |
| 70 |
fname = os.path.join(self.output_dir, name) |
| 71 |
with open(fname) as f: |
| 72 |
s = f.read() |
| 73 |
s = emre.sub(subst, s) |
| 74 |
with open(fname, 'w') as f: |
| 75 |
f.write(s) |
| 76 |
index = os.path.join(self.output_dir, 'metadata.opf') |
| 77 |
return index |