calibre/recipes/daily_mail.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

58 lines
2.0 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
# License: GPLv3 Copyright: 2016, Kovid Goyal <kovid at kovidgoyal.net>
from __future__ import absolute_import, division, print_function, unicode_literals
from calibre.web.feeds.news import BasicNewsRecipe
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class TheDailyMail(BasicNewsRecipe):
title = u'The Daily Mail'
oldest_article = 2
language = 'en_GB'
__author__ = 'Kovid Goyal'
simultaneous_downloads = 1
max_articles_per_feed = 50
use_embedded_content = False
compress_news_images = True
compress_news_images_auto_size = 8
no_stylesheets = True
keep_only_tags = [
dict(name='h1'),
classes('author-section byline-section'),
dict(itemprop='articleBody'),
]
remove_tags = [
classes('related-carousel')
]
feeds = [
(u'Home', u'http://www.dailymail.co.uk/home/index.rss'),
(u'News', u'http://www.dailymail.co.uk/news/index.rss'),
(u'Sport', u'http://www.dailymail.co.uk/sport/index.rss'),
(u'TV and Showbiz', u'http://www.dailymail.co.uk/tvshowbiz/index.rss'),
(u'Femail', u'http://www.dailymail.co.uk/femail/index.rss'),
(u'Health', u'http://www.dailymail.co.uk/health/index.rss'),
(u'Science and Technology', u'http://www.dailymail.co.uk/sciencetech/index.rss'),
(u'Money', u'http://www.dailymail.co.uk/money/index.rss'),
(u'Property', u'http://www.dailymail.co.uk/property/index.rss'),
(u'Motoring', u'http://www.dailymail.co.uk/motoring/index.rss'),
(u'Travel', u'http://www.dailymail.co.uk/travel/index.rss')
]
def preprocess_html(self, soup):
for img in soup.findAll(attrs={'data-src':True}):
img['src'] = img['data-src']
all_h1s = soup.findAll('h1')
for h1 in all_h1s[1:]:
h1.extract()
return soup