mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Update India Today
This commit is contained in:
parent
ae0f3a86db
commit
5201987d62
@ -2,14 +2,22 @@ from calibre.web.feeds.news import BasicNewsRecipe, classes
|
||||
|
||||
|
||||
class IndiaToday(BasicNewsRecipe):
|
||||
title = u'India Today'
|
||||
title = u'India Today Magaine'
|
||||
language = 'en_IN'
|
||||
__author__ = 'Krittika Goyal'
|
||||
oldest_article = 15 # days
|
||||
max_articles_per_feed = 25
|
||||
__author__ = 'unkn0wn'
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
remove_attributes = ['style']
|
||||
remove_attributes = ['style','height','width']
|
||||
ignore_duplicate_articles = {'url'}
|
||||
extra_css = '[itemprop^="description"] {font-size: small; font-style: italic;}'
|
||||
description = ('India’s Most Reputed, Credible and Popular news magazine.'
|
||||
' Read the most preferred magazine of 9.5 million Indians to access highly researched and unbiased content.')
|
||||
masthead_url = 'https://akm-img-a-in.tosshub.com/sites/all/themes/itg/logo.png'
|
||||
|
||||
def get_cover_url(self):
|
||||
soup = self.index_to_soup('https://www.magzter.com/IN/India-Today-Group/India-Today/News/')
|
||||
for citem in soup.findAll('meta', content=lambda s: s and s.endswith('view/3.jpg')):
|
||||
return citem['content']
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='h1'),
|
||||
@ -17,30 +25,36 @@ class IndiaToday(BasicNewsRecipe):
|
||||
dict(itemProp='articleBody'),
|
||||
]
|
||||
|
||||
feeds = [
|
||||
('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 parse_index(self):
|
||||
soup = self.index_to_soup('https://www.indiatoday.in/magazine')
|
||||
ans = self.it_parse_index(soup)
|
||||
return ans
|
||||
|
||||
extra_css = '[itemprop^="description"] {font-size: small; font-style: italic;}'
|
||||
|
||||
def get_cover_url(self):
|
||||
soup = self.index_to_soup('https://www.magzter.com/IN/India-Today-Group/India-Today/News/')
|
||||
for citem in soup.findAll('meta', content=lambda s: s and s.endswith('view/3.jpg')):
|
||||
return citem['content']
|
||||
def it_parse_index(self, soup):
|
||||
feeds = []
|
||||
for section in soup.findAll('div', attrs={'class':['magazin-top-left', 'section-ordering']}):
|
||||
sec = section.find('span')
|
||||
secname = self.tag_to_string(sec)
|
||||
self.log(secname)
|
||||
articles = []
|
||||
for a in section.findAll('a', href=lambda x: x and x.startswith(("/magazine/cover-story/story/", "https://www.indiatoday.in/magazine/"))):
|
||||
url = a['href']
|
||||
if url.startswith('https'):
|
||||
url = url
|
||||
else:
|
||||
url = 'https://www.indiatoday.in' + url
|
||||
title = self.tag_to_string(a)
|
||||
empty = " "
|
||||
if title is empty:
|
||||
url = ''
|
||||
self.log('\t', title)
|
||||
self.log('\t\t', url)
|
||||
articles.append({
|
||||
'title': title,
|
||||
'url': url})
|
||||
if articles:
|
||||
feeds.append((secname, articles))
|
||||
return feeds
|
||||
|
||||
def preprocess_raw_html(self, raw_html, url):
|
||||
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
||||
|
Loading…
x
Reference in New Issue
Block a user