mirror of
https://github.com/kovidgoyal/calibre.git
synced 2026-03-25 02:47:52 -04:00
89 lines
2.9 KiB
Plaintext
89 lines
2.9 KiB
Plaintext
from __future__ import with_statement
|
|
__license__ = 'GPL 3'
|
|
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
import string
|
|
|
|
|
|
class TheHindu(BasicNewsRecipe):
|
|
title = u'The Hindu'
|
|
language = 'en_IN'
|
|
|
|
oldest_article = 1
|
|
__author__ = 'Kovid Goyal'
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
|
|
auto_cleanup = True
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
|
|
extra_css = '.photo-caption { font-size: smaller }'
|
|
|
|
def articles_from_soup(self, soup):
|
|
ans = []
|
|
div = soup.find('section', attrs={'id': 'section_'})
|
|
if div is None:
|
|
return ans
|
|
ul = div.find('ul', attrs={'class': 'archive-list'})
|
|
if ul is not None:
|
|
for x in ul.findAll(['a']):
|
|
title = self.tag_to_string(x)
|
|
url = x.get('href', False)
|
|
if not url or not title:
|
|
continue
|
|
self.log('\t\tFound article:', title)
|
|
self.log('\t\t\t', url)
|
|
ans.append({'title': title, 'url': url,
|
|
'description': '', 'date': ''})
|
|
return ans
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup('http://www.thehindu.com/todays-paper/')
|
|
nav_div = soup.find(id='subnav-tpbar-latest')
|
|
section_list = []
|
|
|
|
# Finding all the section titles that are acceptable
|
|
for x in nav_div.findAll(['a']):
|
|
if self.is_accepted_entry(x):
|
|
section_list.append(
|
|
(string.capwords(self.tag_to_string(x)), x['href']))
|
|
feeds = []
|
|
|
|
# For each section title, fetch the article urls
|
|
for section in section_list:
|
|
section_title = section[0]
|
|
section_url = section[1]
|
|
self.log('Found section:', section_title, section_url)
|
|
soup = self.index_to_soup(section_url)
|
|
articles = self.articles_from_soup(soup)
|
|
if articles:
|
|
feeds.append((section_title, articles))
|
|
|
|
return feeds
|
|
|
|
def is_accepted_entry(self, entry):
|
|
# Those sections in the top nav bar that we will omit
|
|
omit_list = ['tp-tamilnadu',
|
|
'tp-karnataka',
|
|
'tp-kerala',
|
|
'tp-andhrapradesh',
|
|
'tp-telangana',
|
|
'tp-newdelhi',
|
|
'tp-mumbai',
|
|
'tp-otherstates',
|
|
'tp-in-school',
|
|
'tp-metroplus',
|
|
'tp-youngworld',
|
|
'tp-fridayreview',
|
|
'tp-downtown',
|
|
'tp-bookreview',
|
|
'tp-others']
|
|
|
|
is_accepted = True
|
|
for omit_entry in omit_list:
|
|
if entry['href'][0:-1].endswith(omit_entry):
|
|
is_accepted = False
|
|
break
|
|
return is_accepted
|