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

Update The Financial Express

Browse Source
This commit is contained in:
Kovid Goyal 2019-05-18 15:34:29 +05:30
parent 6e414d293b
commit 166f16374b
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 25 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
recipes/fe_india.recipe
View File

@ -7,6 +7,12 @@ financialexpress.com
from calibre.web.feeds.news import BasicNewsRecipe
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class FE_India(BasicNewsRecipe):
title = 'The Financial Express'
__author__ = 'Darko Miletic'
@ -16,29 +22,35 @@ class FE_India(BasicNewsRecipe):
oldest_article = 30
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'cp1252'
encoding = 'utf-8'
use_embedded_content = False
language = 'en_IN'
remove_empty_feeds = True
masthead_url = 'http://static.expressindia.com/frontend/fe/images/fe_logo.jpg'
publication_type = 'magazine'
extra_css = ' body{font-family: Arial,Helvetica,sans-serif } '
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
keep_only_tags = [dict(attrs={'class': 'txt'})]
keep_only_tags = [classes('post-title place-line leftstory')]
remove_attributes = ['width', 'height']
feeds = [(u'Articles', u'http://www.expressindia.com/syndications/fe.xml')]
feeds = [
('Latest news', 'https://www.financialexpress.com/feed/'),
('Economy', 'https://www.financialexpress.com/economy/feed/'),
('Industry', 'https://www.financialexpress.com/industry/feed/'),
('Banking & finance', 'https://www.financialexpress.com/industry/banking-finance/feed/'),
('Companies', 'https://www.financialexpress.com/industry/companies/feed/'),
('Jobs', 'https://www.financialexpress.com/industry/jobs/feed/'),
('Tech', 'https://www.financialexpress.com/industry/tech/feed/'),
('Lifestyle', 'https://www.financialexpress.com/industry/lifestyle/feed/'),
('Health', 'https://www.financialexpress.com/industry/health/feed/'),
('Science', 'https://www.financialexpress.com/industry/science/feed/'),
('Sports', 'https://www.financialexpress.com/industry/sports/feed/'),
('Fe Columnist', 'https://www.financialexpress.com/industry/fe-columnist/feed/'),
]
def print_version(self, url):
article_raw = url.rpartition('/')[0]
article_id = article_raw.rpartition('/')[2]
return 'http://www.financialexpress.com/printer/news/' + article_id + '/'
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
def preprocess_html(self, soup, *a):
for img in soup.findAll(attrs={'data-src': True}):
img['src'] = img['data-src']
return soup