mirror of
https://github.com/kovidgoyal/calibre.git
synced 2026-06-06 22:15:22 -04:00
Kovid Goyal
93 lines
3.3 KiB
Plaintext
93 lines
3.3 KiB
Plaintext
'''
|
|
www.business-standard.com
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
|
|
|
|
|
class BusinessStandard(BasicNewsRecipe):
|
|
title = 'Business Standard | Print Edition'
|
|
__author__ = 'unkn0wn'
|
|
description = "India's most respected business daily"
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
encoding = 'utf-8'
|
|
publisher = 'Business Standard Limited'
|
|
category = 'news, business, money, india, world'
|
|
language = 'en_IN'
|
|
extra_css = '''
|
|
.article__desc{font-size:small;}
|
|
.article_image{font-size:small; font-style:italic;}
|
|
.article__dateline{font-size:small;}
|
|
.full-img{font-size:small; font-style:italic; text-align:center;}
|
|
.pubDate{font-size:small; text-align:center;}
|
|
'''
|
|
|
|
masthead_url = 'https://bsmedia.business-standard.com/include/_mod/site/html5/images/business-standard-logo.png'
|
|
|
|
def get_cover_url(self):
|
|
soup = self.index_to_soup(
|
|
'https://www.magzter.com/IN/Business-Standard-Private-Ltd/Business-Standard/Newspaper/'
|
|
)
|
|
for citem in soup.findAll(
|
|
'meta', content=lambda s: s and s.endswith('view/3.jpg')
|
|
):
|
|
return citem['content']
|
|
|
|
remove_attributes = ['width', 'height', 'style']
|
|
|
|
keep_only_tags = [
|
|
classes(
|
|
'article__title article__content article_content article_image article__dateline headline'
|
|
' alternativeHeadline full-img article-content__img pubDate'
|
|
),
|
|
dict(name='section', attrs={'subscriptions-section': 'content'}),
|
|
dict(name='span', attrs={'class': 'p-content'})
|
|
]
|
|
remove_tags = [
|
|
classes('also-read-panel related-keyword more-stories-pagination'),
|
|
dict(name='br')
|
|
]
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup('https://www.business-standard.com/todays-paper')
|
|
ans = self.bs_parse_index(soup)
|
|
return ans
|
|
|
|
def bs_parse_index(self, soup):
|
|
feeds = []
|
|
div = soup.find('div', attrs={'class': 'main-cont-left'})
|
|
for section in div.findAll('div', attrs={'class': 'row-inner'}):
|
|
h2 = section.find('h2')
|
|
secname = self.tag_to_string(h2)
|
|
self.log(secname)
|
|
articles = []
|
|
for a in section.findAll(
|
|
'a', href=lambda x: x and x.startswith('/article/')
|
|
):
|
|
url = a['href'].replace('article', 'article-amp')
|
|
url = 'https://wap.business-standard.com' + url
|
|
title = self.tag_to_string(a).strip().replace('Premium Content', '')
|
|
articles.append({'title': title, 'url': url})
|
|
self.log('\t', title, '\n\t\t', url)
|
|
if articles:
|
|
feeds.append((secname, articles))
|
|
return feeds
|
|
|
|
def preprocess_html(self, soup):
|
|
subs = soup.find('section', attrs={'subscriptions-section': 'content'})
|
|
if subs:
|
|
art = soup.find(**classes('article_image'))
|
|
if art:
|
|
art.extract()
|
|
div = soup.find(**classes('article_content'))
|
|
if div:
|
|
div.extract()
|
|
h2 = soup.find('h2')
|
|
if h2:
|
|
h2.name = 'h4'
|
|
for img in soup.findAll('amp-img', src=True):
|
|
img.name = 'img'
|
|
img['src'] = img['src'].replace('\\', '').split('?')[0]
|
|
return soup
|