mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
71 lines
2.7 KiB
Plaintext
71 lines
2.7 KiB
Plaintext
import json
|
|
import re
|
|
|
|
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
|
|
|
|
keep_only_tags = [classes('__story_detail')]
|
|
remove_tags = [
|
|
classes(
|
|
'social_sharing_article left_trending left-sticky __tag_links next_prev_stories downarrow uparrow more_from_author_links next prev'
|
|
)
|
|
]
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup('https://www.outlookindia.com/magazine')
|
|
div = soup.find('div', attrs={'class':'wrapper'})
|
|
a = div.find('a', href=lambda x: x and x.startswith('/magazine/issue/'))
|
|
url = a['href']
|
|
self.log('Downloading issue:', url)
|
|
soup = self.index_to_soup('https://www.outlookindia.com' + url)
|
|
cover = soup.find(**classes('listingPage_lead_story'))
|
|
self.cover_url = cover.find('img', attrs={'src': True})['src']
|
|
ans = []
|
|
|
|
for h3 in soup.findAll(['h3', 'h4'],
|
|
attrs={'class': 'tk-kepler-std-condensed-subhead'}):
|
|
a = h3.find('a', href=lambda x: x)
|
|
url = a['href']
|
|
title = self.tag_to_string(a)
|
|
desc = ''
|
|
p = h3.find_next_sibling('p')
|
|
if p:
|
|
desc = self.tag_to_string(p)
|
|
self.log('\t', title)
|
|
self.log('\t', desc)
|
|
self.log('\t\t', url)
|
|
ans.append({'title': title, 'url': url, 'description': desc})
|
|
return [('Articles', ans)]
|
|
|
|
def preprocess_raw_html(self, raw, *a):
|
|
return raw
|
|
m = re.search('<!-- NewsArticle Schema -->.*?script.*?>', raw, flags=re.DOTALL)
|
|
raw = raw[m.end():].lstrip()
|
|
data = json.JSONDecoder().raw_decode(raw)[0]
|
|
title = data['headline']
|
|
body = data['articleBody']
|
|
body = body.replace('\r\n', '<p>')
|
|
author = ' and '.join(x['name'] for x in data['author'])
|
|
image = desc = ''
|
|
if data.get('image'):
|
|
image = '<p><img src="{}">'.format(data['image']['url'])
|
|
if data.get('description'):
|
|
desc = '<h2>' + data['description'] + '</h2>'
|
|
html = '<html><body><h1>' + title + '</h1>' + desc + '<h3>' + author + '</h3>' + image + '<p>' + body
|
|
return html
|