mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
50 lines
1.6 KiB
Plaintext
50 lines
1.6 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
|
|
|
|
|
class stuffconz(BasicNewsRecipe):
|
|
title = u'stuff.co.nz'
|
|
language = 'en_NZ'
|
|
__author__ = 'Krittika Goyal'
|
|
oldest_article = 1 # days
|
|
max_articles_per_feed = 25
|
|
|
|
remove_stylesheets = True
|
|
remove_tags_after = dict(name='div', attrs={'id': 'related_box'})
|
|
remove_tags = [
|
|
dict(name='iframe'),
|
|
dict(name='div', attrs={'class': ['story_feature_title']}),
|
|
dict(name='div', attrs={
|
|
'id': ['toolbox', 'related_box', 'adSTORYBODY']}),
|
|
dict(name='span', attrs={
|
|
'class': ['related_link', 'slideshowcontrols']}),
|
|
]
|
|
|
|
feeds = [
|
|
('Dominion Post',
|
|
'http://www.stuff.co.nz/rss/dominion-post'),
|
|
('National',
|
|
'http://www.stuff.co.nz/rss/national'),
|
|
('World',
|
|
'http://www.stuff.co.nz/rss/world'),
|
|
('Business',
|
|
'http://www.stuff.co.nz/rss/business'),
|
|
('Technology',
|
|
'http://www.stuff.co.nz/rss/technology'),
|
|
('Sport',
|
|
'http://www.stuff.co.nz/rss/sport'),
|
|
('Entertainment',
|
|
'http://www.stuff.co.nz/rss/entertainment'),
|
|
('Life and Style',
|
|
'http://www.stuff.co.nz/rss/life-style'),
|
|
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
story = soup.find(name='div', attrs={'id': 'left_col'})
|
|
soup = BeautifulSoup(
|
|
'<html><head><title>t</title></head><body></body></html>')
|
|
body = soup.find(name='body')
|
|
body.insert(0, story)
|
|
return soup
|