| 1 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 2 |
|
| 3 |
|
| 4 |
def absurl(url): |
| 5 |
if url.startswith('/'): |
| 6 |
return 'https://www.deccanherald.com' + url |
| 7 |
|
| 8 |
|
| 9 |
class herald(BasicNewsRecipe): |
| 10 |
title = 'Deccan Herald' |
| 11 |
__author__ = 'unkn0wn' |
| 12 |
description = 'Deccan Herald is an Indian English language daily newspaper published from the Indian state of Karnataka.' |
| 13 |
language = 'en_IN' |
| 14 |
no_stylesheets = True |
| 15 |
remove_attributes = ['height', 'width', 'style'] |
| 16 |
ignore_duplicate_articles = {'url', 'title'} |
| 17 |
encoding = 'utf-8' |
| 18 |
|
| 19 |
keep_only_tags = [classes('article-title article-author__name'), dict(name='div', attrs={'id': 'main-content'})] |
| 20 |
|
| 21 |
remove_tags = [ |
| 22 |
classes( |
| 23 |
'storyShare social-media-icons in_article_video static_text' |
| 24 |
' nl-optin-mobile dk_only article-banner-adver-wrapper wb_holder' |
| 25 |
' field-name-field-tags section-full strip--business' |
| 26 |
) |
| 27 |
] |
| 28 |
|
| 29 |
def parse_index(self): |
| 30 |
index = 'https://www.deccanherald.com/' |
| 31 |
sections = ['india', 'world', 'elections', 'opinion', 'specials', 'business', 'sports'] |
| 32 |
feeds = [] |
| 33 |
|
| 34 |
for sec in sections: |
| 35 |
soup = self.index_to_soup(index + sec) |
| 36 |
section = sec.capitalize() |
| 37 |
self.log(section) |
| 38 |
articles = [] |
| 39 |
for a in soup.findAll('a', attrs={'href': lambda x: x and x.startswith('/' + sec + '/')}): |
| 40 |
url = absurl(a['href'].split('?')[0]) |
| 41 |
if url in {index + sec + '/', index + sec}: |
| 42 |
continue |
| 43 |
title = self.tag_to_string(a) |
| 44 |
self.log('\t', title, '\n\t\t', url) |
| 45 |
articles.append({'title': title, 'url': url}) |
| 46 |
if articles: |
| 47 |
feeds.append((section, articles)) |
| 48 |
return feeds |