| 1 |
__license__ = 'GPL v3' |
| 2 |
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>' |
| 3 |
''' |
| 4 |
information.dk |
| 5 |
''' |
| 6 |
|
| 7 |
import re |
| 8 |
|
| 9 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 10 |
|
| 11 |
|
| 12 |
class Information_dk(BasicNewsRecipe): |
| 13 |
title = 'Information - Denmark' |
| 14 |
__author__ = 'Darko Miletic' |
| 15 |
description = 'News from Denmark' |
| 16 |
publisher = 'information.dk' |
| 17 |
category = 'news, politics, Denmark' |
| 18 |
oldest_article = 2 |
| 19 |
max_articles_per_feed = 100 |
| 20 |
no_stylesheets = True |
| 21 |
remove_empty_feeds = True |
| 22 |
use_embedded_content = False |
| 23 |
encoding = 'utf8' |
| 24 |
language = 'da' |
| 25 |
|
| 26 |
conversion_options = {'comment': description, 'tags': category, 'publisher': publisher, 'language': language} |
| 27 |
|
| 28 |
feeds = [ |
| 29 |
('Nyheder', 'https://www.information.dk/feed'), |
| 30 |
('Politik', 'https://www.information.dk/emne/politik/feed'), |
| 31 |
('Indland', 'https://www.information.dk/indland/feed'), |
| 32 |
('Udland', 'https://www.information.dk/udland/feed'), |
| 33 |
('Debat', 'https://www.information.dk/debat/feed'), |
| 34 |
('Kunst og kultur', 'https://www.information.dk/kultur/feed'), |
| 35 |
('Literatur', 'https://www.information.dk/litteratur/feed'), |
| 36 |
('Film', 'https://www.information.dk/emne/film/feed'), |
| 37 |
('Kunst', 'https://www.information.dk/emne/kunst/feed'), |
| 38 |
] |
| 39 |
|
| 40 |
keep_only_tags = [dict(name='article', attrs={}), dict(name='div', attrs={'class': 'field-name-body'})] |
| 41 |
remove_tags_before = dict(name='h1', attrs={'class': 'print-title'}) |
| 42 |
remove_tags_after = dict(name='div', attrs={'class': 'print-footer'}) |
| 43 |
|
| 44 |
field_name_best_from_inf = '^.*?field-name-best-from-inf.*?$' |
| 45 |
related_stuff = '^.*?related-stuff.*?$' |
| 46 |
view_iv_seneste = '^.*?view-iv-seneste.*?$' |
| 47 |
view_iv_news_queue = '^.*?view-iv-news-queue.*?$' |
| 48 |
view_footer = '^.*?view-footer.*?$' |
| 49 |
field_name_recommendations = '^.*?field-name-recommendations.*?$' |
| 50 |
field_name_comments_label = '^.*?field-name-comments-label.*?$' |
| 51 |
field_name_no_comments = '^.?field-name-no-comments.*?$' |
| 52 |
comment = '^.*?comment.*?$' |
| 53 |
|
| 54 |
remove_tags = [ |
| 55 |
dict(name=['object', 'link']), |
| 56 |
dict(name='div', attrs={'id': 'node-article-full-group-date'}), |
| 57 |
dict(name='div', attrs={'id': 'node-article-full-group-right'}), |
| 58 |
dict(name='div', attrs={'id': 'node-article-non-subscriber-full-group-date'}), |
| 59 |
dict(name='div', attrs={'id': 'node-article-non-subscriber-full-group-right'}), |
| 60 |
dict(name='div', attrs={'class': re.compile(field_name_best_from_inf, re.IGNORECASE)}), |
| 61 |
dict(name='div', attrs={'class': re.compile(related_stuff, re.IGNORECASE)}), |
| 62 |
dict(name='div', attrs={'class': re.compile(view_iv_seneste, re.IGNORECASE)}), |
| 63 |
dict(name='div', attrs={'class': re.compile(view_iv_news_queue, re.IGNORECASE)}), |
| 64 |
dict(name='div', attrs={'class': re.compile(view_footer, re.IGNORECASE)}), |
| 65 |
dict(name='div', attrs={'class': re.compile(field_name_recommendations, re.IGNORECASE)}), |
| 66 |
dict(name='div', attrs={'class': re.compile(field_name_comments_label, re.IGNORECASE)}), |
| 67 |
dict(name='div', attrs={'class': re.compile(field_name_no_comments, re.IGNORECASE)}), |
| 68 |
dict(name='article', attrs={'class': re.compile(comment, re.IGNORECASE)}), |
| 69 |
dict(name='h2', attrs={'class': 'pane-title'}), |
| 70 |
dict(name='div', attrs={'id': 'comments'}), |
| 71 |
] |