calibre/recipes/technology_review_de.recipe
Kovid Goyal 29cd8d64ea
Change shebangs to python from python2
Also remove a few other miscellaneous references to python2
2020-08-22 18:47:51 +05:30

69 lines
1.9 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function
__license__ = 'GPL v3'
__copyright__ = '2010, Anton Gillert <atx at binaryninja.de>'
'''
Technology Review (deutsch) - heise.de/tr
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class TechnologyReviewDe(BasicNewsRecipe):
title = 'Technology Review'
__author__ = 'Anton Gillert, schuster'
description = 'Technology news from Germany'
language = 'de'
oldest_article = 14
max_articles_per_feed = 50
use_embedded_content = False
no_stylesheets = True
remove_javascript = True
masthead_url = 'http://1.f.ix.de/imgs/02/3/0/8/5/2/8/tr_logo-544bd18881c81263.png'
feeds = [
('News', 'http://www.heise.de/tr/rss/news-atom.xml'),
('Blog', 'http://www.heise.de/tr/rss/blog-atom.xml')
]
keep_only_tags = [
dict(name='article')
]
remove_tags = [
dict(name='nav'),
dict(name='figure', attrs={'class': 'logo'}),
dict(name='hr')
]
extra_css = '.bild_zentriert {font-size: 0.6em} \
.source {font-size: 0.6em}'
def get_cover_url(self):
self.cover_url = ''
soup = self.index_to_soup('http://www.heise.de/tr/magazin/')
img = soup.find('img', alt=re.compile(
'Titelbild Technology Review'), src=True)
if img:
self.cover_url = 'http://www.heise.de' + img['src']
return self.cover_url
def print_version(self, url):
return url + '?view=print'
def preprocess_html(self, soup):
# remove style attributes
for item in soup.findAll(attrs={'style': True}):
del item['style']
# remove reference to article source
for p in soup.findAll('p'):
if 'URL dieses Artikels:' in self.tag_to_string(p):
p.extract()
return soup