From a7925b7d2e6ca7d1aa19bdb6a4319ea226b59aef Mon Sep 17 00:00:00 2001 From: unkn0w7n <51942695+unkn0w7n@users.noreply.github.com> Date: Tue, 29 Oct 2024 12:10:43 +0530 Subject: [PATCH] Update indian_express.recipe --- recipes/indian_express.recipe | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/recipes/indian_express.recipe b/recipes/indian_express.recipe index ee9b6f8b66..44d91edc24 100644 --- a/recipes/indian_express.recipe +++ b/recipes/indian_express.recipe @@ -99,16 +99,22 @@ class IndianExpress(BasicNewsRecipe): def articles_from_soup(self, soup): ans = [] - div = soup.find('div', attrs={'class':['nation', 'o-opin']}) - for art in div.findAll(attrs={'class':['articles', 'o-opin-article']}): + div = soup.find('div', attrs={'class': ['nation', 'o-opin', 'myie-nation']}) + for art in div.findAll( + attrs={'class': ['articles', 'o-opin-article', 'myie-articles']} + ): for a in art.findAll('a', href=True): - if not a.find('img') and not ('/profile/' in a['href'] or '/agency/' in a['href']): + if not a.find('img') and not any( + x in a['href'] for x in ['/profile/', '/agency/', '/section/'] + ): url = a['href'] title = self.tag_to_string(a) desc = '' - if p:= art.find('p'): + if p := art.find('p'): desc = self.tag_to_string(p) - if da := art.find('div', attrs={'class':['date', 'o-opin-date']}): + if da := art.find( + 'div', attrs={'class': ['date', 'o-opin-date', 'my-time']} + ): date = parse_date(self.tag_to_string(da)).replace(tzinfo=None) today = datetime.now() if (today - date) > timedelta(self.oldest_article):