| 1 |
__license__ = 'GPL v3' |
| 2 |
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>' |
| 3 |
''' |
| 4 |
bianet.com.tr |
| 5 |
''' |
| 6 |
|
| 7 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 8 |
|
| 9 |
|
| 10 |
class Radikal_tr(BasicNewsRecipe): |
| 11 |
title = 'Bianet' |
| 12 |
__author__ = 'Osman Kaysan' |
| 13 |
description = 'Independent News from Turkey' |
| 14 |
publisher = 'Bianet' |
| 15 |
category = 'news, politics, Turkey' |
| 16 |
oldest_article = 7 |
| 17 |
max_articles_per_feed = 120 |
| 18 |
masthead_url = 'http://bianet.org/images/bianet_logo.gif' |
| 19 |
language = 'tr' |
| 20 |
no_stylesheets = True |
| 21 |
|
| 22 |
conversion_options = { |
| 23 |
'comments': description, |
| 24 |
'tags': category, |
| 25 |
'language': language, |
| 26 |
'publisher': publisher, |
| 27 |
'linearize_tables': True, |
| 28 |
'remove_paragraph_spacing': True, |
| 29 |
} |
| 30 |
|
| 31 |
remove_tags_before = dict(name='div', attrs={'class': 'manset'}) |
| 32 |
remove_tags = [ |
| 33 |
dict(name='ul', attrs={'class': ['altul']}), |
| 34 |
dict(name='div', attrs={'id': ['habermenu']}), |
| 35 |
dict(name='div', attrs={'class': ['mail']}), |
| 36 |
dict(name='div', attrs={'class': ['from']}), |
| 37 |
] |
| 38 |
remove_tags_after = dict(name='div', attrs={'id': 'habermenu'}) |
| 39 |
|
| 40 |
feeds = [('Bianet', 'http://bianet.org/bianet.rss')] |
| 41 |
|
| 42 |
def preprocess_html(self, soup): |
| 43 |
return self.adeify_images(soup) |