calibre/recipes/ukrinform_ja.recipe

51 lines
2.1 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe
class UkrInform(BasicNewsRecipe):
title = '\u30A6\u30AF\u30EB\u30A4\u30F3\u30D5\u30A9\u30EB\u30E0\uFF08UkrInform\uFF09'
__author__ = 'bugmen00t'
description = '\u30A6\u30AF\u30E9\u30A4\u30CA\u3067\u552F\u4E00\u306E\u56FD\u55B6\u901A\u4FE1\u793E\u3067\u3059\u3001\u56FD\u5185\u6700\u5927\u306E\u5730\u65B9\u652F\u90E8\u30CD\u30C3\u30C8\u30EF\u30FC\u30AF\u3068\u8907\u6570\u306E\u5916\u56FD\u652F\u5C40\u3092\u6709\u3057\u3066\u3044\u307E\u3059\u3002' # noqa
publisher = '\u30A6\u30AF\u30E9\u30A4\u30CA\u6587\u5316\u30FB\u60C5\u5831\u653F\u7B56\u7701'
category = 'newspaper'
cover_url = u'https://static.ukrinform.com/photos/2022_05/thumb_files/630_360_1651819943-560.jpg'
language = 'ja'
no_stylesheets = True
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 30
remove_tags_before = dict(name='article')
remove_tags_after = dict(name='article')
remove_tags = [
dict(name='aside'),
dict(name='img', attrs={'class': 'pixel'}),
dict(name='section', attrs={'class': 'read'}),
dict(name='div', attrs={'data-name': 'int_hidden'})
]
feeds = [
(
'\u65B0\u7740\u30CB\u30E5\u30FC\u30B9',
'https://www.ukrinform.jp/rss/block-lastnews'
), ('\u6226\u4E89', 'https://www.ukrinform.jp/rss/rubric-ato'),
('\u653F\u6CBB', 'https://www.ukrinform.jp/rss/rubric-polytics'),
('\u7D4C\u6E08', 'https://www.ukrinform.jp/rss/rubric-economy'),
('\u9632\u885B', 'https://www.ukrinform.jp/rss/rubric-defense'),
(
'\u793E\u4F1A\u30FB\u6587\u5316',
'https://www.ukrinform.jp/rss/rubric-society'
),
('\u30B9\u30DD\u30FC\u30C4', 'https://www.ukrinform.jp/rss/rubric-sports'),
('\u72AF\u7F6A', 'https://www.ukrinform.jp/rss/rubric-crime'),
(
'\u4E8B\u6545\u30FB\u7DCA\u6025\u4E8B\u614B',
'https://www.ukrinform.jp/rss/rubric-emergencies'
)
]