This commit is contained in:
unkn0w7n 2023-10-16 08:00:18 +05:30
parent 1b8872aae9
commit bb58d98eea
3 changed files with 73 additions and 3 deletions

Binary file not shown.

After

Width:  |  Height:  |  Size: 633 B

70
recipes/newsminute.recipe Normal file
View File

@ -0,0 +1,70 @@
from calibre.web.feeds.news import BasicNewsRecipe, classes
from calibre.ptempfile import PersistentTemporaryFile
class newsminute(BasicNewsRecipe):
title = 'The News Minute'
__author__ = 'unkn0wn'
description = (
'The News Minute is a digital news platform reporting and writing on issues in India, with a '
'specific focus on the 5 southern states. Our content includes news, ground reportage, news '
'analysis, opinion and blogs. Our core strengths include our deep access in the southern states, '
'incisive editorial acumen and insightful news analysis and opinions.'
)
language = 'en_IN'
no_stylesheets = True
remove_javascript = True
masthead_url = 'https://pkcindia.com/wp-content/uploads/2021/09/TMN-Logo-1.png'
ignore_duplicate_articles = {'title', 'url'}
resolve_internal_links = True
remove_empty_feeds = True
remove_attributes = ['style', 'height', 'width']
articles_are_obfuscated = True
def get_obfuscated_article(self, url):
br = self.get_browser()
try:
br.open(url)
except Exception as e:
url = e.hdrs.get('location')
soup = self.index_to_soup(url)
link = soup.find('a', href=True)
skip_sections =[ # add sections you want to skip
'/video/', '/videos/', '/media/', 'podcast-'
]
if any(x in link['href'] for x in skip_sections):
self.log('Aborting Article ', link['href'])
self.abort_article('skipping video links')
self.log('Downloading ', link['href'])
html = br.open(link['href']).read()
pt = PersistentTemporaryFile('.html')
pt.write(html)
pt.close()
return pt.name
keep_only_tags = [
classes(
'arr--section-name arr--story--headline-h1 arr--sub-headline arr--hero-image author-card-wrapper arr--story-page-card-wrapper'
),
]
feeds = []
sections = [
'tamil-nadu', 'telangana', 'andhra-pradesh', 'karnataka', 'kerala'
]
for sec in sections:
a = 'https://news.google.com/rss/search?q=when:27h+allinurl:https%3A%2F%2Fwww.thenewsminute.com{}&hl=en-IN&gl=IN&ceid=IN:en'
feeds.append((sec.capitalize(), a.format('%2F' + sec + '%2F')))
feeds.append(('Others', a.format('')))
def populate_article_metadata(self, article, soup, first):
article.title = article.title.replace(' - The News Minute', '')
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src':True}):
img['src'] = img['data-src']
return soup

View File

@ -61,9 +61,9 @@ class projectsynd(BasicNewsRecipe):
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'old-src':True}):
img['src'] = img['old-src'].replace('medium', 'xlarge')
if abs := soup.find(attrs={'itemprop':'abstract'}):
abs.name = 'p'
abs['class'] = 'sub'
if abst := soup.find(attrs={'itemprop':'abstract'}).find('div'):
abst.name = 'p'
abst['class'] = 'sub'
for div in soup.findAll('div', attrs={'data-line-id':True}):
div.name = 'p'
for a in soup.findAll('a', href=True):