calibre/recipes/eenadu.recipe
2022-06-08 07:25:42 +05:30

145 lines
4.5 KiB
Plaintext

from calibre.web.feeds.news import BasicNewsRecipe, classes
from datetime import date
class eenadu(BasicNewsRecipe):
title = 'ఈనాడు'
__author__ = 'unkn0wn'
description = 'THE LARGEST CIRCULATED TELUGU DAILY'
language = 'te'
use_embedded_content = False
remove_javascript = True
no_stylesheets = True
remove_attributes = ['height', 'width', 'style']
ignore_duplicate_articles = {"title", "url"}
masthead_url = 'https://dxxd96tbpm203.cloudfront.net//img/logo.png'
cover_url = 'https://d66zsp32hue2v.cloudfront.net/Eenadu/2022/06/07/TEL/5_01/9de49f18_01_mr.jpg'
encoding = 'utf-8'
keep_only_tags = [
dict(name='h1'),
classes('eng-body grey pub-t text-justify contlist-cont'),
dict(name='span', attrs={'id': 'PDSAIApbreak'}),
]
remove_tags = [classes('sshare-c')]
def articles_from_soup(self, soup):
ans = []
for link in soup.findAll(attrs={'class': ['telugu_uni_body', 'thumb-content-more', 'owl-carousel']}):
for a in link.findAll('a', attrs={'href': True}):
url = a['href']
if url.startswith('https') is False:
url = 'https://www.eenadu.net/' + url
else:
url = url
for h3 in a.findAll('h3'):
title = self.tag_to_string(h3)
if not url or not title:
continue
self.log('\t', title)
self.log('\t\t', url)
ans.append({
'title': title,
'url': url})
return ans
def parse_index(self):
soup = self.index_to_soup('https://www.eenadu.net/')
nav_div = soup.find(id='navbar')
section_list = [
('సంపాదకీయం', 'https://www.eenadu.net/telangana/editorial'),
]
# Finding all the section titles that are acceptable
for x in nav_div.findAll(['a']):
if self.is_accepted_entry(x):
section_list.append(
(self.tag_to_string(x), x['href'])
)
feeds = []
# For each section title, fetch the article urls
for section in section_list:
section_title = section[0]
section_url = section[1]
self.log(section_title, section_url)
soup = self.index_to_soup(section_url)
articles = self.articles_from_soup(soup)
if articles:
feeds.append((section_title, articles))
return feeds
def is_accepted_entry(self, entry):
# Those sections in the top nav bar that we will omit
# https://www.eenadu.net/nri
is_sunday = date.today().weekday() == 6
if is_sunday:
omit_list = [
'net/',
'javascript:void(0)',
'#',
'sports',
'movies',
'women',
'technology',
'business',
'stories.eenadu.net',
'calendar',
'devotional',
'youth',
'recipes',
'real-estate',
'temples',
'kathalu',
'viral-videos',
'Nri',
'videos',
'explained',
'agriculture',
'crime',
'health',
'photos',
'kids-stories',
'education',
]
else:
omit_list = [
'net/',
'javascript:void(0)',
'#',
'sports',
'movies',
'women',
'technology',
'business',
'stories.eenadu.net',
'calendar',
'devotional',
'youth',
'recipes',
'real-estate',
'temples',
'kathalu',
'viral-videos',
'Nri',
'videos',
'explained',
'agriculture',
'sunday-magazine',
'crime',
'health',
'photos',
'kids-stories',
'education',
]
is_accepted = True
for omit_entry in omit_list:
if entry['href'].endswith(omit_entry):
is_accepted = False
break
return is_accepted