mirror of
https://github.com/kovidgoyal/calibre.git
synced 2026-05-08 10:32:28 +00:00
Kovid Goyal
60 lines
2.0 KiB
Python
60 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
|
|
delay = 2
|
|
browser_type = 'webengine'
|
|
|
|
keep_only_tags = [
|
|
dict(name='h1'),
|
|
classes('author-section byline-section'),
|
|
dict(itemprop='articleBody'),
|
|
]
|
|
remove_tags = [
|
|
classes('related-carousel')
|
|
]
|
|
|
|
feeds = [
|
|
(u'Home', u'https://www.dailymail.co.uk/home/index.rss'),
|
|
(u'News', u'https://www.dailymail.co.uk/news/index.rss'),
|
|
(u'Sport', u'https://www.dailymail.co.uk/sport/index.rss'),
|
|
(u'TV and Showbiz', u'https://www.dailymail.co.uk/tvshowbiz/index.rss'),
|
|
(u'Health', u'https://www.dailymail.co.uk/health/index.rss'),
|
|
(u'Science and Technology', u'https://www.dailymail.co.uk/sciencetech/index.rss'),
|
|
(u'Money', u'https://www.dailymail.co.uk/money/index.rss'),
|
|
(u'Property', u'https://www.dailymail.co.uk/property/index.rss'),
|
|
(u'Motoring', u'https://www.dailymail.co.uk/motoring/index.rss'),
|
|
(u'Travel', u'https://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
|