Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

update Business Standard Print Edition

Browse Source
This commit is contained in:
Kovid Goyal 2022-08-20 09:23:53 +05:30
parent 5880ff34b1
commit e25fc241d5
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 36 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
recipes/business_standard_print_edition.recipe
View File

@ -2,15 +2,7 @@
www.business-standard.com www.business-standard.com
''' '''
import re from calibre.web.feeds.news import BasicNewsRecipe, classes
from calibre.web.feeds.recipes import BasicNewsRecipe
def classes(classes):
q = frozenset(classes.split(' '))
return dict(
attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}
)
class BusinessStandard(BasicNewsRecipe): class BusinessStandard(BasicNewsRecipe):
@ -23,6 +15,13 @@ class BusinessStandard(BasicNewsRecipe):
publisher = 'Business Standard Limited' publisher = 'Business Standard Limited'
category = 'news, business, money, india, world' category = 'news, business, money, india, world'
language = 'en_IN' 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' masthead_url = 'https://bsmedia.business-standard.com/include/_mod/site/html5/images/business-standard-logo.png'
@ -39,12 +38,15 @@ class BusinessStandard(BasicNewsRecipe):
keep_only_tags = [ keep_only_tags = [
classes( classes(
'headline alternativeHeadline full-img article-content__img pubDate' 'article__title article__content article_content article_image article__dateline headline'
' alternativeHeadline full-img article-content__img pubDate'
), ),
dict(name='span', attrs={'class': 'p-content'}), dict(name='section', attrs={'subscriptions-section': 'content'}),
dict(name='span', attrs={'class': 'p-content'})
] ]
remove_tags = [ remove_tags = [
classes('also-read-panel related-keyword more-stories-pagination') classes('also-read-panel related-keyword more-stories-pagination'),
dict(name='br')
] ]
def parse_index(self): def parse_index(self):
@ -54,7 +56,8 @@ class BusinessStandard(BasicNewsRecipe):
def bs_parse_index(self, soup): def bs_parse_index(self, soup):
feeds = [] feeds = []
for section in soup.findAll('div', attrs={'class': 'row-inner'}): div = soup.find('div', attrs={'class': 'main-cont-left'})
for section in div.findAll('div', attrs={'class': 'row-inner'}):
h2 = section.find('h2') h2 = section.find('h2')
secname = self.tag_to_string(h2) secname = self.tag_to_string(h2)
self.log(secname) self.log(secname)
@ -62,16 +65,28 @@ class BusinessStandard(BasicNewsRecipe):
for a in section.findAll( for a in section.findAll(
'a', href=lambda x: x and x.startswith('/article/') 'a', href=lambda x: x and x.startswith('/article/')
): ):
url = a['href'] url = a['href'].replace('article', 'article-amp')
url = 'https://www.business-standard.com' + url url = 'https://wap.business-standard.com' + url
ti = self.tag_to_string(a) title = self.tag_to_string(a).strip().replace('Premium Content', '')
title = re.sub('Premium Content', 'Premium Content : ', ti)
articles.append({'title': title, 'url': url}) articles.append({'title': title, 'url': url})
self.log('\t', title) self.log('\t', title, '\n\t\t', url)
self.log('\t\t', url)
if articles: if articles:
feeds.append((secname, articles)) feeds.append((secname, articles))
return feeds return feeds
def preprocess_html(self, soup):
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' 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