Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-11 09:13:57 -04:00
Code Issues Packages Projects Releases Wiki Activity

pep8

Browse Source
This commit is contained in:
Kovid Goyal 2025-08-08 06:49:08 +05:30
parent 8a94d59a0b
commit 2b14ebe86f
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
5 changed files with 5 additions and 84 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
recipes/1843.recipe
View File

@ -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

2
recipes/economist_news.recipe
View File

@ -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

2
recipes/economist_search.recipe
View File

@ -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

2
recipes/economist_world_ahead.recipe
View File

@ -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

81
recipes/indian_express.recipe
View File

@ -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