Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

pep8

Browse Source
This commit is contained in:
Kovid Goyal 2022-12-15 17:27:26 +05:30
parent 3537db5a8c
commit d47fa7a629
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 19 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
recipes/indian_express.recipe
View File

@ -1,7 +1,8 @@
from calibre.web.feeds.news import BasicNewsRecipe, classes from calibre.web.feeds.news import BasicNewsRecipe, classes
from datetime import date, datetime, timedelta from datetime import datetime, timedelta
from calibre.utils.date import parse_date from calibre.utils.date import parse_date
class IndianExpress(BasicNewsRecipe): class IndianExpress(BasicNewsRecipe):
title = u'Indian Express' title = u'Indian Express'
language = 'en_IN' language = 'en_IN'
@ -14,7 +15,7 @@ class IndianExpress(BasicNewsRecipe):
use_embedded_content = False use_embedded_content = False
remove_attributes = ['style', 'height', 'width'] remove_attributes = ['style', 'height', 'width']
ignore_duplicate_articles = {'url'} ignore_duplicate_articles = {'url'}
extra_css = ''' extra_css = '''
#storycenterbyline {font-size:small;} #storycenterbyline {font-size:small;}
#img-cap {font-size:small;} #img-cap {font-size:small;}
@ -23,7 +24,7 @@ class IndianExpress(BasicNewsRecipe):
#sub-d{color:#202020; font-style:italic;} #sub-d{color:#202020; font-style:italic;}
.ie-authorbox{font-size:small;} .ie-authorbox{font-size:small;}
''' '''
resolve_internal_links = True resolve_internal_links = True
remove_empty_feeds = True remove_empty_feeds = True
@ -41,31 +42,31 @@ class IndianExpress(BasicNewsRecipe):
' custom-share o-story-paper-quite ie-network-commenting audio-player-tts-sec' ' custom-share o-story-paper-quite ie-network-commenting audio-player-tts-sec'
) )
] ]
def parse_index(self): def parse_index(self):
section_list = [ section_list = [
('Front Page', 'https://indianexpress.com/print/front-page/'), ('Front Page', 'https://indianexpress.com/print/front-page/'),
('India', 'https://indianexpress.com/section/india/'), ('India', 'https://indianexpress.com/section/india/'),
#('Express Network', 'https://indianexpress.com/print/express-network/'), # ('Express Network', 'https://indianexpress.com/print/express-network/'),
('Delhi Confidential', 'https://indianexpress.com/section/delhi-confidential/'), ('Delhi Confidential', 'https://indianexpress.com/section/delhi-confidential/'),
('Opinion', 'http://indianexpress.com/section/opinion/'), ('Opinion', 'http://indianexpress.com/section/opinion/'),
('UPSC-CSE Key', 'https://indianexpress.com/section/upsc-current-affairs/'), ('UPSC-CSE Key', 'https://indianexpress.com/section/upsc-current-affairs/'),
('Explained', 'https://indianexpress.com/section/explained/'), ('Explained', 'https://indianexpress.com/section/explained/'),
('Business', 'https://indianexpress.com/section/business/'), ('Business', 'https://indianexpress.com/section/business/'),
#('Political Pulse', 'https://indianexpress.com/section/political-pulse/'), # ('Political Pulse', 'https://indianexpress.com/section/political-pulse/'),
('Sunday Eye', 'https://indianexpress.com/section/express-sunday-eye/'), ('Sunday Eye', 'https://indianexpress.com/section/express-sunday-eye/'),
('World', 'https://indianexpress.com/section/world/'), ('World', 'https://indianexpress.com/section/world/'),
#('Education', 'https://indianexpress.com/section/education/'), # ('Education', 'https://indianexpress.com/section/education/'),
#('Gadgets', 'https://indianexpress.com/section/technology/gadgets/'), # ('Gadgets', 'https://indianexpress.com/section/technology/gadgets/'),
('Tech Review', 'https://indianexpress.com/section/technology/tech-reviews/'), ('Tech Review', 'https://indianexpress.com/section/technology/tech-reviews/'),
#('Techhook', 'https://indianexpress.com/section/technology/techook/'), # ('Techhook', 'https://indianexpress.com/section/technology/techook/'),
#('Laptops', 'https://indianexpress.com/section/technology/laptops/'), # ('Laptops', 'https://indianexpress.com/section/technology/laptops/'),
#('Mobiles & Tabs', 'https://indianexpress.com/section/technology/mobile-tabs/'), # ('Mobiles & Tabs', 'https://indianexpress.com/section/technology/mobile-tabs/'),
('Science', 'https://indianexpress.com/section/technology/science/'), ('Science', 'https://indianexpress.com/section/technology/science/'),
('Movie Review', 'https://indianexpress.com/section/entertainment/movie-review/'), ('Movie Review', 'https://indianexpress.com/section/entertainment/movie-review/'),
] ]
feeds = [] feeds = []
# For each section title, fetch the article urls # For each section title, fetch the article urls
@ -81,24 +82,24 @@ class IndianExpress(BasicNewsRecipe):
if articles: if articles:
feeds.append((section_title, articles)) feeds.append((section_title, articles))
return feeds return feeds
def articles_from_page(self, soup): def articles_from_page(self, soup):
ans = [] ans = []
for div in soup.findAll(attrs={'class':['northeast-topbox', 'explained-section-grid']}): for div in soup.findAll(attrs={'class':['northeast-topbox', 'explained-section-grid']}):
for a in div.findAll('a', href=True): for a in div.findAll('a', href=True):
if not a.find('img') and not '/section/' in a['href']: if not a.find('img') and '/section/' not in a['href']:
url = a['href'] url = a['href']
title = self.tag_to_string(a) title = self.tag_to_string(a)
self.log('\t', title, '\n\t\t', url) self.log('\t', title, '\n\t\t', url)
ans.append({'title': title, 'url': url, 'description': ''}) ans.append({'title': title, 'url': url, 'description': ''})
return ans return ans
def articles_from_soup(self, soup): def articles_from_soup(self, soup):
ans = [] ans = []
div = soup.find('div', attrs={'class':['nation', 'o-opin']}) div = soup.find('div', attrs={'class':['nation', 'o-opin']})
for art in div.findAll(attrs={'class':['articles', 'o-opin-article']}): for art in div.findAll(attrs={'class':['articles', 'o-opin-article']}):
for a in art.findAll('a', href=True): for a in art.findAll('a', href=True):
if not a.find('img') and not '/profile/' in a['href']: if not a.find('img') and '/profile/' not in a['href']:
url = a['href'] url = a['href']
title = self.tag_to_string(a) title = self.tag_to_string(a)
desc = '' desc = ''
@ -140,4 +141,4 @@ class IndianExpress(BasicNewsRecipe):
today = datetime.now() today = datetime.now()
if (today - date) > timedelta(self.oldest_article): if (today - date) > timedelta(self.oldest_article):
self.abort_article('Skipping old article') self.abort_article('Skipping old article')
return soup return soup