From 2b14ebe86fbb9e1e91454d89597959be9ef19afb Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Fri, 8 Aug 2025 06:49:08 +0530 Subject: [PATCH] pep8 --- recipes/1843.recipe | 2 +- recipes/economist_news.recipe | 2 +- recipes/economist_search.recipe | 2 +- recipes/economist_world_ahead.recipe | 2 +- recipes/indian_express.recipe | 81 +--------------------------- 5 files changed, 5 insertions(+), 84 deletions(-) diff --git a/recipes/1843.recipe b/recipes/1843.recipe index 07f6659614..3ad6cdf29d 100644 --- a/recipes/1843.recipe +++ b/recipes/1843.recipe @@ -6,8 +6,8 @@ from urllib.parse import quote, urlencode from uuid import uuid4 from html5_parser import parse -from mechanize import Request from lxml import etree +from mechanize import Request from calibre import browser from calibre.ptempfile import PersistentTemporaryFile diff --git a/recipes/economist_news.recipe b/recipes/economist_news.recipe index 4fad01311b..4d87211ece 100644 --- a/recipes/economist_news.recipe +++ b/recipes/economist_news.recipe @@ -8,8 +8,8 @@ from urllib.parse import quote, urlencode from uuid import uuid4 from html5_parser import parse -from mechanize import Request from lxml import etree +from mechanize import Request from calibre import browser from calibre.ptempfile import PersistentTemporaryFile diff --git a/recipes/economist_search.recipe b/recipes/economist_search.recipe index 42aa04b00e..1eb7f81b68 100644 --- a/recipes/economist_search.recipe +++ b/recipes/economist_search.recipe @@ -6,8 +6,8 @@ from urllib.parse import quote, urlencode from uuid import uuid4 from html5_parser import parse -from mechanize import Request from lxml import etree +from mechanize import Request from calibre import browser from calibre.ptempfile import PersistentTemporaryFile diff --git a/recipes/economist_world_ahead.recipe b/recipes/economist_world_ahead.recipe index 2a13885cf4..1dde240a18 100644 --- a/recipes/economist_world_ahead.recipe +++ b/recipes/economist_world_ahead.recipe @@ -7,8 +7,8 @@ from urllib.parse import quote, urlencode from uuid import uuid4 from html5_parser import parse -from mechanize import Request from lxml import etree +from mechanize import Request from calibre import browser from calibre.ptempfile import PersistentTemporaryFile diff --git a/recipes/indian_express.recipe b/recipes/indian_express.recipe index 85697b32cf..fb73b47c27 100644 --- a/recipes/indian_express.recipe +++ b/recipes/indian_express.recipe @@ -82,85 +82,6 @@ class IndianExpress(BasicNewsRecipe): 'https://indianexpress.com/feed', ] - # def parse_index(self): - - # section_list = [ - # ('Daily Briefing', 'https://indianexpress.com/section/live-news/'), - # ('Front Page', 'https://indianexpress.com/print/front-page/'), - # ('India', 'https://indianexpress.com/section/india/'), - # # ('Express Network', 'https://indianexpress.com/print/express-network/'), - # ('Delhi Confidential', 'https://indianexpress.com/section/delhi-confidential/'), - # ('Editorials', 'https://indianexpress.com/section/opinion/editorials/'), - # ('Columns', 'https://indianexpress.com/section/opinion/columns/'), - # ('UPSC-CSE Key', 'https://indianexpress.com/section/upsc-current-affairs/'), - # ('Explained', 'https://indianexpress.com/section/explained/'), - # ('Business', 'https://indianexpress.com/section/business/'), - # # ('Political Pulse', 'https://indianexpress.com/section/political-pulse/'), - # ('Sunday Eye', 'https://indianexpress.com/section/express-sunday-eye/'), - # ('World', 'https://indianexpress.com/section/world/'), - # # ('Education', 'https://indianexpress.com/section/education/'), - # # ('Gadgets', 'https://indianexpress.com/section/technology/gadgets/'), - # ('Tech Review', 'https://indianexpress.com/section/technology/tech-reviews/'), - # # ('Techhook', 'https://indianexpress.com/section/technology/techook/'), - # # ('Laptops', 'https://indianexpress.com/section/technology/laptops/'), - # # ('Mobiles & Tabs', 'https://indianexpress.com/section/technology/mobile-tabs/'), - # ('Science', 'https://indianexpress.com/section/technology/science/'), - # ('Movie Review', 'https://indianexpress.com/section/entertainment/movie-review/'), - # ] - - # feeds = [] - - # # For each section title, fetch the article urls - # for section in section_list: - # section_title = section[0] - # section_url = section[1] - # self.log(section_title, section_url) - # soup = self.index_to_soup(section_url) - # if '/world/' in section_url or '/explained/' in section_url: - # articles = self.articles_from_page(soup) - # else: - # articles = self.articles_from_soup(soup) - # if articles: - # feeds.append((section_title, articles)) - # return feeds - - # def articles_from_page(self, soup): - # ans = [] - # for div in soup.findAll(attrs={'class': ['northeast-topbox', 'explained-section-grid']}): - # for a in div.findAll('a', href=True): - # if not a.find('img') and '/section/' not in a['href']: - # url = a['href'] - # title = self.tag_to_string(a) - # self.log('\t', title, '\n\t\t', url) - # ans.append({'title': title, 'url': url, 'description': ''}) - # return ans - - # def articles_from_soup(self, soup): - # ans = [] - # div = soup.find('div', attrs={'class': ['nation', 'o-opin', 'myie-nation', 'opinion-more-wrapper']}) - # 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 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') or art.find(attrs={'class': 'opinion-news-para'})): - # desc = self.tag_to_string(p) - # if da := art.find( - # attrs={'class': ['date', 'o-opin-date', 'opinion-date', 'my-time']} - # ): - # date = parse_date(self.tag_to_string(da)).replace(tzinfo=None) - # today = datetime.now() - # if (today - date) > timedelta(self.oldest_article): - # continue - # self.log('\t', title, '\n\t', desc, '\n\t\t', url) - # ans.append({'title': title, 'url': url, 'description': desc}) - # return ans - def get_cover_url(self): soup = self.index_to_soup( 'https://www.readwhere.com/newspaper/indian-express/Nagpur/38726' @@ -186,7 +107,7 @@ class IndianExpress(BasicNewsRecipe): # date = parse_date(span['content']).replace(tzinfo=None) # today = datetime.now() # if (today - date) > timedelta(self.oldest_article): - # self.abort_article('Skipping old article') + # self.abort_article('Skipping old article') for img in soup.findAll('img', attrs={'src': True}): img['src'] = img['src'].split('?')[0] + '?w=' + width return soup