| 1 |
#!/usr/bin/env python |
| 2 |
|
| 3 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 4 |
|
| 5 |
|
| 6 |
class LiveHindustan(BasicNewsRecipe): |
| 7 |
title = 'हिंदुस्तान' |
| 8 |
description = 'भरोसा नए हिन्दुस्तान का। दुनिया भर में रहने वाले हिन्दीभाषी लोगों को हिन्दुस्तान समाचार पत्र के व्यापक नेटवर्क. ' |
| 9 |
language = 'hi' |
| 10 |
__author__ = 'unkn0wn' |
| 11 |
oldest_article = 1 # days |
| 12 |
max_articles_per_feed = 50 |
| 13 |
encoding = 'utf-8' |
| 14 |
use_embedded_content = False |
| 15 |
masthead_url = 'https://www.livehindustan.com/static/images/new/logo/livehindustan.svg' |
| 16 |
no_stylesheets = True |
| 17 |
remove_attributes = ['style', 'height', 'width'] |
| 18 |
ignore_duplicate_articles = {'url'} |
| 19 |
|
| 20 |
keep_only_tags = [ |
| 21 |
classes('page-hdng stry-shrt-head img-hgt-blk athr-info tm-stmp stry-bdy'), |
| 22 |
] |
| 23 |
|
| 24 |
remove_tags = [ |
| 25 |
classes('prlads ads'), |
| 26 |
dict(name='section', attrs={'class': 'glry-cnt mostvdtm main-wdgt glry-bg'}), |
| 27 |
] |
| 28 |
remove_tags_after = [classes('stry-bdy')] |
| 29 |
|
| 30 |
feeds = [ |
| 31 |
('प्रमुख खबरें', 'https://feed.livehindustan.com/rss/3127'), |
| 32 |
('देश', 'https://feed.livehindustan.com/rss/4911'), |
| 33 |
('विदेश', 'https://feed.livehindustan.com/rss/4913'), |
| 34 |
('ओपिनियन', 'https://feed.livehindustan.com/rss/5165'), |
| 35 |
('बिजनेस', 'https://feed.livehindustan.com/rss/4950'), |
| 36 |
('क्रिकेट', 'https://feed.livehindustan.com/rss/4925'), |
| 37 |
('खेल', 'https://feed.livehindustan.com/rss/4931'), |
| 38 |
('विज्ञान', 'https://feed.livehindustan.com/rss/1349437'), |
| 39 |
('गैजेट्स', 'https://feed.livehindustan.com/rss/4955'), |
| 40 |
('क्राइम', 'https://feed.livehindustan.com/rss/469651'), |
| 41 |
('करियर', 'https://feed.livehindustan.com/rss/4979'), |
| 42 |
# https://www.livehindustan.com/rss/#collapseOne3116 |
| 43 |
] |
| 44 |
|
| 45 |
def get_cover_url(self): |
| 46 |
soup = self.index_to_soup('https://www.magzter.com/IN/HT-Digital-Streams-Ltd./Hindustan-Times-Hindi-New-Delhi/Newspaper/') |
| 47 |
return soup.find('img', id=lambda s: s and 'mgd__lhd__cover' in s.split())['src'] |