calibre/recipes/business_today.recipe
un-pogaz 7f6a11a368 useless dict operation (auto-fix)
ruff 'RUF051,RUF056'
2025-01-24 11:14:20 +01:00

128 lines
4.1 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
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_javascript = True
encoding = 'utf-8'
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 = [
classes('story-heading sab-head-tranlate-sec brand-detial-main main-img field--name-body'),
]
remove_tags = [
dict(name=['link', 'meta', 'svg', 'button', 'script']),
dict(name='a', attrs={'title': 'videos'}),
classes(
'tranding-topics-main newsltter-iframe hedlineteg stoybday-ad story-recommended-chunk '
'banner_content'
)
]
recipe_specific_options = {
'date': {
'short': 'The date of the edition to download (YYYY-MM-DD format)',
'long': 'For example, 2024-07-07'
}
}
extra_css = '''
img {display:block; margin:0 auto;}
em { color:#202020; }
.main-img { font-size:small; text-align:center; }
.summary {font-style:italic; color:#202020; }
'''
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.businesstoday.in/magazine/issue/' + d
else:
soup = self.index_to_soup('https://www.businesstoday.in')
a = soup.findAll('a', attrs={'class':'mag_sld_img'})[1]
url = a['href']
self.cover_url = a.img['data-src'].split('?')[0]
self.log('issue =', url)
self.timefmt = ' [' + url.split('/')[-1] + ']'
soup = self.index_to_soup(url)
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 = ["Editor's Note", 'Editors note']
for i in feedSort:
if i in sections:
feeds.append((i, sections[i]))
# Done with the sorted feeds
for i in feedSort:
sections.pop(i, None)
# Append what is left over...
for i in sections:
feeds.append((i, sections[i]))
return feeds
def preprocess_html(self, soup):
auth = soup.find(**classes('brand-detial-main'))
if auth:
ul = auth.find('ul')
if ul:
ul.decompose()
for vid in soup.findAll('a', attrs={
'href': lambda x: x and 'businesstoday.in/videos' in x
}):
vid.decompose()
summ = soup.find(**classes('summary'))
if summ:
h2 = summ.find('h2')
if h2:
h2.name = 'p'
for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src'].split('?')[0]
return soup