Update horizons.recipe

remove empty p tags
This commit is contained in:
unkn0w7n 2025-03-24 11:06:11 +05:30
parent d72d746c1a
commit 1526d0d06f

View File

@ -1,8 +1,8 @@
#!/usr/bin/env python
# vim:fileencoding=utf-8
'''
"""
https://www.cirsd.org/en/horizons
'''
"""
from calibre.web.feeds.news import BasicNewsRecipe, classes
@ -10,10 +10,12 @@ from calibre.web.feeds.news import BasicNewsRecipe, classes
class horizons(BasicNewsRecipe):
title = 'Horizons'
__author__ = 'unkn0wn'
description = (' Horizons Journal of International Relations and Sustainable Development.'
' Horizons serves as a high-level platform for influential voices from around the world to'
' provide informed analysis and conduct reasoned exchanges on the full spectrum of issues'
' that shape international developments.')
description = (
' Horizons Journal of International Relations and Sustainable Development.'
' Horizons serves as a high-level platform for influential voices from around the world to'
' provide informed analysis and conduct reasoned exchanges on the full spectrum of issues'
' that shape international developments.'
)
no_stylesheets = True
use_embedded_content = False
encoding = 'utf-8'
@ -22,13 +24,12 @@ class horizons(BasicNewsRecipe):
masthead_url = 'https://www.cirsd.org/bundles/olpublic/images/horizons-logo.jpg'
ignore_duplicate_articles = {'url'}
extra_css = 'em{color:#404040;}'
simultaneous_downloads = 1
keep_only_tags = [
dict(name='div', attrs={'class':'article'})
]
keep_only_tags = [dict(name='div', attrs={'class': 'article'})]
remove_tags = [
classes('back-link'),
dict(name='div', attrs={'class':'single-post-footer'})
dict(name='div', attrs={'class': 'single-post-footer'}),
]
recipe_specific_options = {
@ -38,6 +39,9 @@ class horizons(BasicNewsRecipe):
}
}
def preprocess_raw_html(self, raw, *a):
return raw.replace('<p>&nbsp;</p>', '')
def get_browser(self):
return BasicNewsRecipe.get_browser(self, verify_ssl_certificates=False)
@ -47,7 +51,7 @@ class horizons(BasicNewsRecipe):
url = d
else:
soup = self.index_to_soup('https://www.cirsd.org/en/horizons')
a = soup.findAll('a', href=True, attrs={'class':'horizon-gallery-box'})[0] # use 1 for previous edition
a = soup.find('a', href=True, attrs={'class':'horizon-gallery-box'})
url = a['href']
if url.startswith('/'):
url = 'https://www.cirsd.org' + url
@ -58,26 +62,23 @@ class horizons(BasicNewsRecipe):
soup = self.index_to_soup(url)
feeds = []
for section in soup.findAll('h2', attrs={'class':'mt-3'}):
for section in soup.findAll('h2', attrs={'class': 'mt-3'}):
secname = self.tag_to_string(section).strip()
self.log(secname)
articles = []
div = section.findNext('div', attrs={'class':'mb-3'})
for li in div.findAll('li', attrs={'class':'mb-2'}):
div = section.findNext('div', attrs={'class': 'mb-3'})
for li in div.findAll('li', attrs={'class': 'mb-2'}):
a = li.find('a', href=True)
url = a['href']
if url.startswith('/'):
url = 'https://www.cirsd.org' + url
title = self.tag_to_string(a)
span = li.find('span', attrs={'class':'section-author'})
span = li.find('span', attrs={'class': 'section-author'})
desc = ''
if span:
desc = self.tag_to_string(span).strip()
self.log('\t', title, '\n\t', desc, '\n\t\t', url)
articles.append({
'title': title,
'url': url,
'description': desc})
articles.append({'title': title, 'url': url, 'description': desc})
if articles:
feeds.append((secname, articles))
return feeds