calibre/recipes/der_standard.recipe
Kovid Goyal 567040ee1e Perform PEP8 compliance checks on the entire codebase
Some bits of PEP 8 are turned off via setup.cfg
2016-07-29 21:25:17 +05:30

108 lines
4.3 KiB
Python

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
from __future__ import unicode_literals, division, absolute_import, print_function
__license__ = 'GPL v3'
__copyright__ = '2009, Gerhard Aigner <gerhard.aigner at gmail.com>'
''' http://www.derstandard.at - Austrian Newspaper '''
import re
import random
from calibre.web.feeds.news import BasicNewsRecipe
class DerStandardRecipe(BasicNewsRecipe):
title = u'derStandard'
__author__ = 'Gerhard Aigner and Sujata Raman and Marcel Jira and Peter Reschenhofer'
description = u'Nachrichten aus Österreich'
publisher = 'derStandard.at'
category = 'news, politics, nachrichten, Austria'
use_embedded_content = False
remove_empty_feeds = True
no_stylesheets = True
encoding = 'utf-8'
language = 'de_AT'
oldest_article = 1
max_articles_per_feed = 100
ignore_duplicate_articles = {'title', 'url'}
masthead_url = 'http://images.derstandard.at/2012/06/19/derStandardat_1417x274.gif'
feeds = [
(u'Newsroom', u'http://derStandard.at/?page=rss&ressort=Seite1'),
(u'Inland', u'http://derstandard.at/?page=rss&ressort=InnenPolitik'),
(u'International', u'http://derstandard.at/?page=rss&ressort=InternationalPolitik'),
(u'Wirtschaft', u'http://derStandard.at/?page=rss&ressort=Wirtschaft'),
(u'Web', u'http://derStandard.at/?page=rss&ressort=Web'),
(u'Sport', u'http://derStandard.at/?page=rss&ressort=Sport'),
(u'Panorama', u'http://derStandard.at/?page=rss&ressort=Panorama'),
(u'Etat', u'http://derStandard.at/?page=rss&ressort=Etat'),
(u'Kultur', u'http://derStandard.at/?page=rss&ressort=Kultur'),
(u'Wissenschaft', u'http://derStandard.at/?page=rss&ressort=Wissenschaft'),
(u'Gesundheit', u'http://derStandard.at/?page=rss&ressort=Gesundheit'),
(u'Bildung', u'http://derStandard.at/?page=rss&ressort=Bildung'),
(u'Meinung', u'http://derStandard.at/?page=rss&ressort=Meinung'),
(u'Lifestyle', u'http://derStandard.at/?page=rss&ressort=Lifestyle'),
(u'Reisen', u'http://derStandard.at/?page=rss&ressort=Reisen'),
(u'Familie', u'http://derstandard.at/?page=rss&ressort=Familie'),
(u'Greenlife', u'http://derStandard.at/?page=rss&ressort=Greenlife'),
(u'Karriere', u'http://derStandard.at/?page=rss&ressort=Karriere'),
(u'Immobilien', u'http://derstandard.at/?page=rss&ressort=Immobilien'),
(u'Automobil', u'http://derstandard.at/?page=rss&ressort=Automobil'),
(u'dieStandard', u'http://dieStandard.at/?page=rss&ressort=diestandard'),
(u'daStandard', u'http://daStandard.at/?page=rss&ressort=dastandard')
]
keep_only_tags = [
dict(name='div', attrs={'class': re.compile('^artikel')})
]
remove_tags = [
dict(name=['link', 'iframe', 'style', 'hr']),
dict(attrs={'class': ['lookup-links', 'media-list']}),
dict(name='form', attrs={'name': 'sitesearch'}),
dict(name='div', attrs={'class': ['socialsharing', 'block video',
'blog-browsing section',
'diashow', 'supplemental']}),
dict(name='div', attrs={'id': 'highlighted'})
]
remove_attributes = ['width', 'height']
preprocess_regexps = [
(re.compile(r'\[[\d]*\]', re.DOTALL |
re.IGNORECASE), lambda match: ''),
(re.compile(r'bgcolor="#\w{3,6}"',
re.DOTALL | re.IGNORECASE), lambda match: '')
]
filter_regexps = [r'/r[1-9]*']
def get_article_url(self, article):
matchObj = re.search(re.compile(
r'/r' + '[1-9]*', flags=0), article.link, flags=0)
if matchObj:
return None
return article.link
def preprocess_html(self, soup):
if soup.find('div', {'class': re.compile('^artikel')}) is None:
self.abort_article()
for t in soup.findAll(['ul', 'li']):
t.name = 'div'
return soup
def get_cover_url(self):
base_url = 'https://epaper.derstandard.at/'
url = base_url + 'shelf.act?s=' + str(random.random() * 10000)
soup = self.index_to_soup(url)
img = soup.find(
'img', {'class': re.compile('^thumbnailBig'), 'src': True})
if img and img['src']:
cover_url = base_url + img['src']
return cover_url