mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-11-01 19:17:02 -04:00
82 lines
2.9 KiB
Python
82 lines
2.9 KiB
Python
#!/usr/bin/env python
|
|
# vim:fileencoding=utf-8
|
|
# License: GPLv3 Copyright: 2015, Kovid Goyal <kovid at kovidgoyal.net>
|
|
|
|
from collections import OrderedDict
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
def absurl(x):
|
|
if x.startswith('/'):
|
|
x = 'http://www.epw.in' + x
|
|
return x
|
|
|
|
|
|
class EconomicAndPoliticalWeekly(BasicNewsRecipe):
|
|
title = 'Economic and Political Weekly'
|
|
__author__ = 'Kovid Goyal'
|
|
description = 'Economic and Political news from India'
|
|
publisher = 'epw.in'
|
|
category = 'news, finances, politics, India'
|
|
oldest_article = 7
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
simultaneous_downloads = 1
|
|
encoding = 'utf-8'
|
|
language = 'en_IN'
|
|
publication_type = 'newspaper'
|
|
masthead_url = 'http://www.epw.in/system/files/epw_masthead.png'
|
|
|
|
keep_only_tags = [
|
|
dict(id=['block-system-main', 'page-title']),
|
|
]
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup('http://www.epw.in/')
|
|
main = soup.find('div', id='main-content')
|
|
sections = OrderedDict()
|
|
current_section = None
|
|
|
|
for div in main.findAll(attrs={'class': lambda x: x and 'views-field-title' in x.split()}):
|
|
section = self.tag_to_string(div.findParent(
|
|
attrs={'class': 'block-inner'}).find('h2'))
|
|
if section != current_section:
|
|
current_section = section
|
|
if section not in sections:
|
|
sections[section] = []
|
|
self.log('\n\n' + section)
|
|
title = self.tag_to_string(div)
|
|
a = div.find('a', href=True)
|
|
url = absurl(a['href'])
|
|
desc = ''
|
|
if a.get('title'):
|
|
desc = a['title']
|
|
else:
|
|
d = div.findNextSibling(
|
|
attrs={'class': lambda x: x and 'views-field-body' in x.split()})
|
|
if d is not None:
|
|
desc = self.tag_to_string(d)
|
|
self.log('\t', title, url)
|
|
self.log('\t\t', desc)
|
|
sections[current_section].append(
|
|
{'title': title, 'url': url, 'description': desc})
|
|
|
|
current_section = 'Web Exclusive'
|
|
sections[current_section] = []
|
|
self.log('\n\n' + current_section)
|
|
for div in main.findAll(attrs={'class': lambda x: x and 'views-field-nothing' in x.split()}):
|
|
title = self.tag_to_string(div)
|
|
elems = div.findAll('a', href=True)
|
|
if len(elems) == 2:
|
|
desc, title = map(self.tag_to_string, elems)
|
|
else:
|
|
title, desc = self.tag_to_string(elems[0]), ''
|
|
url = absurl(elems[-1]['href'])
|
|
self.log('\t', title, url)
|
|
self.log('\t\t', desc)
|
|
sections[current_section].append(
|
|
{'title': title, 'url': url, 'description': desc})
|
|
|
|
return [(t, articles) for t, articles in sections.items() if articles]
|