calibre/recipes/businessworldin.recipe

77 lines
2.5 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
www.businessworld.in
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class BusinessWorldMagazine(BasicNewsRecipe):
title = 'Business World Magazine'
__author__ = 'Kovid Goyal'
description = 'News from India'
publisher = 'ABP Pvt Ltd Publication'
category = 'news, politics, finances, India, Asia'
delay = 1
no_stylesheets = True
INDEX = 'http://www.businessworld.in/businessworld/magazine_latest_issue.php'
ROOT = 'http://www.businessworld.in'
encoding = 'utf-8'
language = 'en_IN'
auto_cleanup = True
def parse_index(self):
br = self.browser
br.open(self.ROOT)
raw = br.open(br.click_link(text_regex=re.compile('Current.*Issue',
re.I))).read()
soup = self.index_to_soup(raw)
mc = soup.find(attrs={'class':'mag_cover'})
if mc is not None:
img = mc.find('img', src=True)
if img is not None:
self.cover_url = img['src']
feeds = []
current_section = None
articles = []
for tag in soup.findAll(['h3', 'h2']):
inner_a = tag.find('a')
if tag.name == 'h3' and inner_a is not None:
continue
if tag.name == 'h2' and (inner_a is None or current_section is
None):
continue
if tag.name == 'h3':
if current_section is not None and articles:
feeds.append((current_section, articles))
current_section = self.tag_to_string(tag)
self.log('Found section:', current_section)
articles = []
elif tag.name == 'h2':
url = inner_a.get('href', None)
if url is None: continue
if url.startswith('/'): url = self.ROOT + url
title = self.tag_to_string(inner_a)
h1 = tag.findPreviousSibling('h1')
if h1 is not None:
title = self.tag_to_string(h1) + title
self.log('\tFound article:', title)
articles.append({'title':title, 'url':url, 'date':'',
'description':''})
if current_section and articles:
feeds.append((current_section, articles))
return feeds