mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
93 lines
3.5 KiB
Python
93 lines
3.5 KiB
Python
#!/usr/bin/env python
|
|
# vim:fileencoding=utf-8
|
|
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
|
|
|
|
|
class outlook(BasicNewsRecipe):
|
|
title = 'Outlook Magazine'
|
|
__author__ = 'unkn0wn'
|
|
description = (
|
|
'Outlook covers the latest India news, analysis, business news and long-form stories on culture,'
|
|
' money market and personal finance. Read India\'s best online magazine.'
|
|
)
|
|
language = 'en_IN'
|
|
use_embedded_content = False
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
remove_attributes = ['height', 'width', 'style']
|
|
ignore_duplicate_articles = {'url'}
|
|
resolve_internal_links = True
|
|
masthead_url = 'https://images.assettype.com/outlookindia/2024-02/96fb06ce-1cc8-410e-ad6c-da4de57405f8/Outlook.svg'
|
|
extra_css = '''
|
|
.subcap-story {font-style:italic; color:#202020;}
|
|
.story-slug, .article-name-date {font-size:small; color:#404040;}
|
|
.main-img-div, .sb-image {font-size:small; text-align:center;}
|
|
em { color:#202020; }
|
|
'''
|
|
|
|
keep_only_tags = [
|
|
# classes('story-slug story-title subcap-story article-name-date main-img-div sb-article')
|
|
classes('story-slug story-title subcap-story article-name-date w-93')
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name='svg'),
|
|
dict(name='a', attrs={'href':lambda x: x and x.startswith('https://www.whatsapp.com/')}),
|
|
classes('ads-box info-img-absolute mobile-info-id story-dec-time-mobile sb-also-read ads-box1')
|
|
]
|
|
|
|
recipe_specific_options = {
|
|
'date': {
|
|
'short': 'The date of the edition to download (DD-Month-YYYY format)',
|
|
'long': 'For example, 10-june-2024'
|
|
}
|
|
}
|
|
|
|
def get_browser(self):
|
|
return BasicNewsRecipe.get_browser(self, user_agent='common_words/based', verify_ssl_certificates=False)
|
|
|
|
def parse_index(self):
|
|
self.log(
|
|
'\n***\nif this recipe fails, report it on: '
|
|
'https://www.mobileread.com/forums/forumdisplay.php?f=228\n***\n'
|
|
)
|
|
|
|
d = self.recipe_specific_options.get('date')
|
|
if d and isinstance(d, str):
|
|
url = 'https://www.outlookindia.com/magazine/' + d
|
|
else:
|
|
soup = self.index_to_soup('https://www.outlookindia.com/magazine')
|
|
a = soup.find('a', attrs={'aria-label':'magazine-cover-image'})
|
|
url = a['href']
|
|
|
|
self.log('Downloading issue:', url)
|
|
|
|
soup = self.index_to_soup(url)
|
|
cov = soup.find(attrs={'aria-label':'magazine-cover-image'})
|
|
self.cover_url = cov.img['src'].split('?')[0]
|
|
summ = soup.find(attrs={'data-test-id':'magazine-summary'})
|
|
if summ:
|
|
self.description = self.tag_to_string(summ)
|
|
tme = soup.find(attrs={'class':'arr__timeago'})
|
|
if tme:
|
|
self.timefmt = ' [' + self.tag_to_string(tme).split('-')[-1].strip() + ']'
|
|
|
|
ans = []
|
|
|
|
for div in soup.findAll(attrs={'class': 'article-heading-two'}):
|
|
a = div.a
|
|
url = a['href']
|
|
title = self.tag_to_string(a)
|
|
desc = ''
|
|
p = div.find_next_sibling('p', attrs={'class':lambda x: x and 'article-desc' in x.split()})
|
|
if p:
|
|
desc = self.tag_to_string(p)
|
|
auth = div.find_next_sibling('p', attrs={'class':'author'})
|
|
if auth:
|
|
desc = self.tag_to_string(auth) + ' | ' + desc
|
|
self.log('\t', title)
|
|
self.log('\t', desc)
|
|
self.log('\t\t', url)
|
|
ans.append({'title': title, 'url': url, 'description': desc})
|
|
return [('Articles', ans)]
|