mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
39 lines
2.1 KiB
Python
39 lines
2.1 KiB
Python
#!/usr/bin/env python
|
|
# vim:fileencoding=utf-8
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class NovayaGazetaEurope(BasicNewsRecipe):
|
|
title = u'\u041D\u043E\u0432\u0430\u044F \u0413\u0430\u0437\u0435\u0442\u0430. \u0415\u0432\u0440\u043E\u043F\u0430'
|
|
__author__ = 'bugmen00t'
|
|
description = u'\u0413\u043E\u0432\u043E\u0440\u0438\u043C \u043A\u0430\u043A \u0435\u0441\u0442\u044C. \u041F\u0438\u0448\u0435\u043C \u043E \u043F\u0440\u043E\u0438\u0441\u0445\u043E\u0434\u044F\u0449\u0435\u043C \u0432 \u0420\u043E\u0441\u0441\u0438\u0438, \u0423\u043A\u0440\u0430\u0438\u043D\u0435 \u0438 \u0415\u0432\u0440\u043E\u043F\u0435. \u041D\u043E\u0432\u043E\u0441\u0442\u0438, \u0430\u043D\u0430\u043B\u0438\u0442\u0438\u043A\u0430, \u043C\u043D\u0435\u043D\u0438\u044F \u044D\u043A\u0441\u043F\u0435\u0440\u0442\u043E\u0432, \u0441\u043F\u0435\u0446\u0438\u0430\u043B\u044C\u043D\u044B\u0435 \u0440\u0435\u043F\u043E\u0440\u0442\u0430\u0436\u0438 \u0438 \u0436\u0443\u0440\u043D\u0430\u043B\u0438\u0441\u0442\u0441\u043A\u0438\u0435 \u0440\u0430\u0441\u0441\u043B\u0435\u0434\u043E\u0432\u0430\u043D\u0438\u044F.' # noqa: E501
|
|
publisher = '\u041A\u0438\u0440\u0438\u043B\u043B \u041C\u0430\u0440\u0442\u044B\u043D\u043E\u0432'
|
|
publication_type = 'newspaper'
|
|
category = 'news'
|
|
language = 'ru'
|
|
cover_url = 'https://bucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com/public/images/5dc71e2d-9763-4f05-8f4e-92049fa32af7_513x513.png'
|
|
oldest_article = 15
|
|
max_articles_per_feed = 50
|
|
auto_cleanup = False
|
|
|
|
remove_tags_before = dict(name='h1')
|
|
|
|
remove_tags_after = dict(
|
|
name='div', attrs={'class': 'ArticleBlocks_wrapperNoAside__11_bu'}
|
|
)
|
|
|
|
remove_tags = [dict(name='div', attrs={'class': 'EmbedNative_root__2lgsH'})]
|
|
|
|
feeds = [(
|
|
u'\u041D\u043E\u0432\u043E\u0441\u0442\u0438',
|
|
'https://novayagazeta.eu/feed/rss/ru'
|
|
)]
|
|
|
|
def preprocess_html(self, soup):
|
|
for alink in soup.findAll('a'):
|
|
if alink.string is not None:
|
|
tstr = alink.string
|
|
alink.replaceWith(tstr)
|
|
return soup
|