| 1 |
__license__ = 'GPL v3' |
| 2 |
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>' |
| 3 |
''' |
| 4 |
njuz.net |
| 5 |
''' |
| 6 |
import re |
| 7 |
|
| 8 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 9 |
|
| 10 |
|
| 11 |
class NjuzNet(BasicNewsRecipe): |
| 12 |
title = 'Njuz.net' |
| 13 |
__author__ = 'Darko Miletic' |
| 14 |
description = 'Iscasene vesti iz Srbije, regiona i sveta' |
| 15 |
publisher = 'njuz.net' |
| 16 |
category = 'news, politics, humor, Serbia' |
| 17 |
oldest_article = 2 |
| 18 |
max_articles_per_feed = 100 |
| 19 |
no_stylesheets = True |
| 20 |
use_embedded_content = False |
| 21 |
encoding = 'utf8' |
| 22 |
language = 'sr' |
| 23 |
publication_type = 'newsportal' |
| 24 |
masthead_url = 'http://www.njuz.net/njuznet.jpg' |
| 25 |
extra_css = ''' |
| 26 |
@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} |
| 27 |
body{font-family: serif1, serif} |
| 28 |
.articledescription{font-family: serif1, serif} |
| 29 |
.wp-caption-text{font-size: x-small} |
| 30 |
''' |
| 31 |
|
| 32 |
conversion_options = {'comment': description, 'tags': category, 'publisher': publisher, 'language': language} |
| 33 |
|
| 34 |
preprocess_regexps = [(re.compile('\u0110'), lambda match: '\u00d0')] # noqa: RUF039 |
| 35 |
|
| 36 |
keep_only_tags = [dict(attrs={'id': 'entryMeta'}), dict(attrs={'class': 'post'})] |
| 37 |
|
| 38 |
remove_tags = [dict(name=['embed', 'link', 'base', 'iframe', 'object', 'meta', 'fb:like']), dict(name='div', attrs={'id': 'tagsandcats'})] |
| 39 |
remove_tags_after = dict(name='div', attrs={'id': 'tagsandcats'}) |
| 40 |
remove_attributes = ['lang'] |
| 41 |
feeds = [('Clanci', 'http://www.njuz.net/feed/')] |
| 42 |
|
| 43 |
def preprocess_html(self, soup): |
| 44 |
for item in soup.findAll(style=True): |
| 45 |
del item['style'] |
| 46 |
for alink in soup.findAll('a'): |
| 47 |
if alink.string is not None: |
| 48 |
tstr = alink.string |
| 49 |
alink.replaceWith(tstr) |
| 50 |
return soup |