Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update India Today

Browse Source
This commit is contained in:
Kovid Goyal 2022-01-27 18:11:32 +05:30
parent 7f433e8f30
commit 5706c95ce2
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 31 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
recipes/india_today.recipe
View File

@ -1,4 +1,4 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe, classes
class IndiaToday(BasicNewsRecipe):
@ -7,14 +7,41 @@ class IndiaToday(BasicNewsRecipe):
__author__ = 'Krittika Goyal'
oldest_article = 15 # days
max_articles_per_feed = 25
no_stylesheets = True
auto_cleanup = True
use_embedded_content = False
remove_attributes = ['style']
keep_only_tags = [
dict(name='h1'),
classes('story-kicker story-right'),
dict(itemProp='articleBody'),
]
feeds = [
('The Big Story', 'https://www.indiatoday.in/rss/1206614'),
('Editor\'s Note','https://www.indiatoday.in/rss/1206516'),
('Cover Story', 'https://www.indiatoday.in/rss/1206509'),
('The Big Story', 'https://www.indiatoday.in/rss/1206614'),
('UP Front','https://www.indiatoday.in/rss/1206609'),
('Liesure','https://www.indiatoday.in/rss/1206551'),
('Nation', 'https://www.indiatoday.in/rss/1206514'),
('Health','https://www.indiatoday.in/rss/1206515'),
('Defence','https://www.indiatoday.in/rss/1206517'),
('Guest Column','https://www.indiatoday.in/rss/1206612'),
('States', 'https://www.indiatoday.in/rss/1206500'),
('Economy', 'https://www.indiatoday.in/rss/1206513'),
('Special Report','https://www.indiatoday.in/rss/1206616'),
('Investigation','https://www.indiatoday.in/rss/1206617'),
('Diplomacy','https://www.indiatoday.in/rss/1206512'),
('Sports','https://www.indiatoday.in/rss/1206518'),
]
def preprocess_raw_html(self, raw_html, url):
from calibre.ebooks.BeautifulSoup import BeautifulSoup
soup = BeautifulSoup(raw_html)
for script in soup.findAll('script'):
script.extract()
for style in soup.findAll('style'):
style.extract()
for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src']
return str(soup)