mirror of
https://github.com/kovidgoyal/calibre.git
synced 2026-03-06 08:53:40 -05:00
86 lines
2.8 KiB
Plaintext
86 lines
2.8 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
|
|
|
|
|
class BT(BasicNewsRecipe):
|
|
title = u'Business Today Magazine'
|
|
language = 'en_IN'
|
|
__author__ = 'unkn0wn'
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
remove_attributes = ['style', 'height', 'width']
|
|
ignore_duplicate_articles = {'url'}
|
|
description = (
|
|
'Business Today is an Indian fortnightly business magazine published by Living Media India Limited,'
|
|
' in publication since 1992. Best downloaded on Sundays, at the end and the middle of the month'
|
|
)
|
|
masthead_url = 'https://akm-img-a-in.tosshub.com/businesstoday/resource/img/logo.png'
|
|
|
|
keep_only_tags = [
|
|
dict(name='h1'),
|
|
dict(name='h2'),
|
|
classes('brand-detial-main main-img story-with-main-sec'),
|
|
]
|
|
remove_tags = [
|
|
dict(name='a', attrs={'title': 'videos'}),
|
|
classes('tranding-topics-main newsltter-iframe hedlineteg')
|
|
]
|
|
extra_css = 'a[href^="https://www.businesstoday.in/videos"]{display: none;}'
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup('https://www.businesstoday.in/magazine')
|
|
issue = soup.find(attrs={'class': 'view-id-latest_issue_magzine'})
|
|
a = issue.findAll('a', href=lambda x: x and x.startswith('/magazine/issue/'))[1]
|
|
url = a['href']
|
|
self.log('issue =', url)
|
|
soup = self.index_to_soup('https://www.businesstoday.in' + url)
|
|
tag = soup.find(attrs={'class': 'issue-image'})
|
|
if tag:
|
|
self.cover_url = tag.find('img')['src']
|
|
section = None
|
|
sections = {}
|
|
|
|
for tag in soup.findAll(
|
|
'div', attrs={'class': ['magazin-top-left', 'section-ordering']}
|
|
):
|
|
sec = tag.find(('span', 'h1'))
|
|
section = self.tag_to_string(sec)
|
|
self.log(section)
|
|
sections[section] = []
|
|
|
|
for a in tag.findAll(
|
|
'a',
|
|
href=lambda x: x and x.
|
|
startswith('https://www.businesstoday.in/magazine/')
|
|
):
|
|
url = a['href']
|
|
title = self.tag_to_string(a)
|
|
self.log('\t', title)
|
|
self.log('\t\t', url)
|
|
sections[section].append({'title': title, 'url': url})
|
|
|
|
feeds = []
|
|
|
|
# Insert feeds in specified order, if available
|
|
|
|
feedSort = ['Editors Note']
|
|
for i in feedSort:
|
|
if i in sections:
|
|
feeds.append((i, sections[i]))
|
|
|
|
# Done with the sorted feeds
|
|
|
|
for i in feedSort:
|
|
del sections[i]
|
|
|
|
# Append what is left over...
|
|
|
|
for i in sections:
|
|
feeds.append((i, sections[i]))
|
|
|
|
return feeds
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', attrs={'data-src': True}):
|
|
img['src'] = img['data-src'].split('?')[0]
|
|
return soup
|