calibre/recipes/indian_express.recipe
2020-09-07 13:01:45 +05:30

63 lines
2.0 KiB
Plaintext

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 IndianExpress(BasicNewsRecipe):
title = u'Indian Express'
language = 'en_IN'
__author__ = 'Krittika Goyal'
oldest_article = 1 # days
max_articles_per_feed = 25
encoding = 'utf-8'
no_stylesheets = True
use_embedded_content = False
keep_only_tags = [
classes('heading-part full-details')
]
remove_tags = [
classes('share-social appstext story-tags')
]
feeds = [
('Front Page',
'http://indianexpress.com/print/front-page/feed/'),
('Editorials',
'http://indianexpress.com/section/opinion/editorials/feed/'),
('Crime',
'http://indianexpress.com/section/india/crime/feed/'),
('Cricket',
'http://indianexpress.com/section/sports/cricket/feed/'),
('Health',
'http://www.indianexpress.com/lifestyle/health/feed/'),
('Asia',
'http://indianexpress.com/section/world/asia/'),
('Politics',
'http://indianexpress.com/section/india/politics/feed/'),
('Mumbai',
'http://www.indianexpress.com/cities/mumbai/feed/'),
('Op-Ed',
'http://indianexpress.com/section/opinion/feed/'),
('Lifestyle',
'http://indianexpress.com/section/lifestyle/feed/'),
('Science & Technology',
'http://indianexpress.com/section/technology/feed/'),
('Bollywood',
'http://indianexpress.com/section/entertainment/bollywood/feed/'),
]
def preprocess_html(self, soup):
for img in soup.findAll('img'):
noscript = img.findParent('noscript')
if noscript is not None:
lazy = noscript.findPreviousSibling('img')
if lazy is not None:
lazy.extract()
noscript.name = 'div'
return soup