import json
import re
from calibre.web.feeds.news import BasicNewsRecipe, classes
class outlook(BasicNewsRecipe):
title = 'Outlook Business Magazine'
__author__ = 'unkn0wn'
description = (
'Outlook Business (Monthly) Magazine produces Business, Market, Startup and Leadership'
' content that is differentiated to offer a deeper understanding of trends shaping India. Read to hone your leadership skills.'
)
language = 'en_IN'
use_embedded_content = False
no_stylesheets = True
remove_javascript = True
remove_attributes = ['height', 'width', 'style']
ignore_duplicate_articles = {'url'}
masthead_url = 'https://imgnew.outlookindia.com/uploadimage/library/free_files/jpg/logo_2022_04_30_092331.jpg'
extra_css = '.author{font-size:small;}'
def parse_index(self):
soup = self.index_to_soup('https://www.outlookbusiness.com/magazine/')
div = soup.find('div', attrs={'class':'SplWapper'})
url = div.find('a', href = True)['href']
self.cover_url = div.find('img', srcset=True)['srcset']
self.timefmt = '['+ self.tag_to_string(div.find('h6')) + ']'
soup = self.index_to_soup('https://www.outlookbusiness.com' + url)
ans = []
for section in soup.findAll(**classes('category-banner-content')):
p = section.find('p', attrs={'class':lambda x: x and x.startswith('styled__Content')})
desc = self.tag_to_string(p)
head = section.find('p', attrs={'class':lambda x: x and x.startswith('styled__Heading')})
title = self.tag_to_string(head)
a = p.findParent('a', href = True)['href']
if a.startswith('/'):
url = 'https://www.outlookbusiness.com' + a
self.log('\t', title, '\n\t', desc, '\n\t\t', url)
ans.append({
'title': title,
'description': desc,
'url': url})
return [('Articles', ans)]
def preprocess_raw_html(self, raw, *a):
m = re.search('id="__NEXT_DATA__" type="application/json">', raw)
raw = raw[m.start():]
raw = raw.split('>', 1)[1]
data = json.JSONDecoder().raw_decode(raw)[0]
data = data['props']['initialState']['dashboard']['ARTICLE_POST_DETAIL_API']['data']['article_data']
title = data['title']
body = data['description']
cat = desc = image = author = ''
if 'category_name' in data:
try:
cat = data['category_name']
except Exception:
cat = ''
if 'excerpt' in data:
desc = ''+ data['excerpt'] + '
'
if 'author' in data:
try:
author = data['author'][0]['name']
except Exception:
author = ''
if 'images' in data:
try:
image = '
'.format(data['images'][0]['image'])
except Exception:
image = ''
html = '
'+ cat + '' + title + '
' + desc + ''+ author + '
' + image + body
return html
calibre_most_common_ua = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.87 Safari/537.36'