|
Connoisseur
Posts: 82
Karma: 100000
Join Date: Aug 2015
Device: Kindle Keyboard 3G + Kindle Voyage WiFi + Kindle PW11 Kids WiFi
|
New Russian Recipes (part 01 of ??)
A couple new recipes. Not sure how to correctly specify the language for those recipes that are being downloaded in Russian but their originating source is outside Russia. To avoid fragmentation, it probably would be easier to change language from " ru_UK", " ru_DE", " ru_GB" back to just " ru".
UNIAN.net ( Russian version): Ukrainian Independent News Agency of News, one of the most cited source of news from across Ukraine. Favicon
Spoiler:
Code:
#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function
from calibre.web.feeds.news import BasicNewsRecipe, classes
class Unian(BasicNewsRecipe):
title = u'\u0423\u041D\u0418\u0410\u041D '
description = u'\u0423\u043A\u0440\u0430\u0438\u043D\u0441\u043A\u043E\u0435 \u041D\u0435\u0437\u0430\u0432\u0438\u0441\u0438\u043C\u043E\u0435 \u0418\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u043E\u043D\u043D\u043E\u0435 \u0410\u0433\u0435\u043D\u0442\u0441\u0442\u0432\u043E \u041D\u043E\u0432\u043E\u0441\u0442\u0435\u0439 \u2013 \u043F\u0435\u0440\u0432\u043E\u0435 \u0432 \u0423\u043A\u0440\u0430\u0438\u043D\u0435 \u0438 \u0441\u0430\u043C\u043E\u0435 \u0431\u043E\u043B\u044C\u0448\u043E\u0435 \u043D\u0435\u0437\u0430\u0432\u0438\u0441\u0438\u043C\u043E\u0435 \u0438\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u043E\u043D\u043D\u043E\u0435 \u0430\u0433\u0435\u043D\u0442\u0441\u0442\u0432\u043E, \u043E\u0441\u043D\u043E\u0432\u0430\u043D\u043D\u043E\u0435 \u0432 1993 \u0433\u043E\u0434\u0443, \u043B\u0438\u0434\u0435\u0440 \u0441\u0440\u0435\u0434\u0438 \u043D\u043E\u0432\u043E\u0441\u0442\u043D\u044B\u0445 \u043C\u0435\u0434\u0438\u0430 \u0441\u0442\u0440\u0430\u043D\u044B, \u0441\u0430\u043C\u044B\u0439 \u0446\u0438\u0442\u0438\u0440\u0443\u0435\u043C\u044B\u0439 \u0438\u0441\u0442\u043E\u0447\u043D\u0438\u043A \u043D\u043E\u0432\u043E\u0441\u0442\u0435\u0439 \u043E \u0441\u043E\u0431\u044B\u0442\u0438\u044F\u0445 \u0432 \u0441\u0442\u0440\u0430\u043D\u0435.'
__author__ = 'bugmen00t'
publication_type = 'newspaper'
oldest_article = 7
max_articles_per_feed = 100
language = 'ru_UK'
cover_url = 'https://www.unian.net/images/unian-512x512.png'
auto_cleanup = False
no_stylesheets = True
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': 'article-text'})
remove_tags = [
dict(name='span', attrs={'class': 'article__info-item comments'}),
dict(name='span', attrs={'class': 'article__info-item views'}),
dict(name='div', attrs={'class': 'read-also-slider'})
]
feeds = [
(u'\u0423\u041D\u0418\u0410\u041D', u'https://rss.unian.net/site/news_rus.rss')
]
Old-Games.ru: community project devoted to preservation of old computer games. Favicon
Fixes needed: - Replace list elements with <div> tags
- Find less brutal way of removing attribute style='display:none ' from all <div> tags rather than just nuking all styles
Spoiler:
Code:
#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function
from calibre.web.feeds.news import BasicNewsRecipe, classes
class OGRU(BasicNewsRecipe):
title = u'Old-Games.RU'
__author__ = 'bugmen00t'
description = u'Old-Games.RU \u2014 \u043A\u0440\u0443\u043F\u043D\u0435\u0439\u0448\u0438\u0439 \u0440\u043E\u0441\u0441\u0438\u0439\u0441\u043A\u0438\u0439 \u0430\u0440\u0445\u0438\u0432 \u0441\u0442\u0430\u0440\u044B\u0445 \u043A\u043E\u043C\u043F\u044C\u044E\u0442\u0435\u0440\u043D\u044B\u0445 \u0438\u0433\u0440. \u041C\u044B \u043D\u0435 \u0441\u0442\u0430\u0432\u0438\u043C \u043F\u0435\u0440\u0435\u0434 \u0441\u043E\u0431\u043E\u0439 \u0446\u0435\u043B\u0438 \u0441\u043E\u0431\u0440\u0430\u0442\u044C \u0432\u0441\u0435 \u0438\u0433\u0440\u044B, \u0447\u0442\u043E \u0435\u0441\u0442\u044C \u0432 \u043C\u0438\u0440\u0435, \u043D\u043E \u043C\u044B \u0441\u0442\u0430\u0440\u0430\u0435\u043C\u0441\u044F, \u0447\u0442\u043E\u0431\u044B \u043D\u0430 \u0441\u0430\u0439\u0442\u0435 \u0431\u044B\u043B\u043E \u043F\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043B\u0435\u043D\u043E \u0431\u043E\u043B\u044C\u0448\u0438\u043D\u0441\u0442\u0432\u043E \u0448\u0435\u0434\u0435\u0432\u0440\u043E\u0432, \u0440\u0435\u0434\u043A\u043E\u0441\u0442\u0435\u0439 \u0438 \u043F\u0440\u043E\u0441\u0442\u043E \u0438\u043D\u0442\u0435\u0440\u0435\u0441\u043D\u044B\u0445 \u043F\u0440\u043E\u0435\u043A\u0442\u043E\u0432 \u043F\u0440\u043E\u0448\u043B\u044B\u0445 \u043B\u0435\u0442. \u0421 \u0442\u0435\u0447\u0435\u043D\u0438\u0435\u043C \u0432\u0440\u0435\u043C\u0435\u043D\u0438 \u0433\u0440\u0430\u0444\u0438\u0447\u0435\u0441\u043A\u043E\u0435 \u0438 \u0437\u0432\u0443\u043A\u043E\u0432\u043E\u0435 \u043E\u0444\u043E\u0440\u043C\u043B\u0435\u043D\u0438\u0435 \u0438\u0433\u0440 \u043D\u0430\u0448\u0435\u0433\u043E \u0430\u0440\u0445\u0438\u0432\u0430 \u0437\u0430\u043C\u0435\u0442\u043D\u043E \u0443\u0441\u0442\u0430\u0440\u0435\u043B\u043E, \u043D\u043E \u0438\u0433\u0440\u043E\u0432\u043E\u0439 \u043F\u0440\u043E\u0446\u0435\u0441\u0441 \u043E\u0441\u0442\u0430\u043B\u0441\u044F \u043F\u0440\u0435\u0436\u043D\u0438\u043C, \u0438 \u043F\u043E\u0440\u043E\u0439 \u043E\u043D \u0433\u043E\u0440\u0430\u0437\u0434\u043E \u0438\u043D\u0442\u0435\u0440\u0435\u0441\u043D\u0435\u0435, \u0447\u0435\u043C \u0432\u043E \u043C\u043D\u043E\u0433\u0438\u0445 \u0441\u043E\u0432\u0440\u0435\u043C\u0435\u043D\u043D\u044B\u0445 \u00AB\u0445\u0438\u0442\u0430\u0445\u00BB.'
publisher = 'Old-Games.RU'
publication_type = 'blog'
category = 'news, games, retro'
language = 'ru'
cover_url = 'https://www.old-games.ru/forum/styles/default/old-games/logo.og.png'
oldest_article = 50
max_articles_per_feed = 50
no_stylesheets = True
auto_cleanup = False
remove_tags_before = dict(name='article')
remove_tags_after = dict(name='article')
remove_attributes = ['style']
remove_tags = [
dict(name='p', attrs={'id': 'pageDescription'}),
dict(name='div', attrs={'class': 'pageNavLinkGroup'}),
dict(name='div', attrs={'class': 'tagBlock TagContainer'}),
dict(name='div', attrs={'class': 'NoAutoHeader PollContainer'}),
dict(name='div', attrs={'class': 'likesSummary secondaryContent'}),
dict(name='div', attrs={'class': 'editDate'}),
dict(name='div', attrs={'class': 'attachedFiles'}),
dict(name='div', attrs={'class': 'item muted postNumber hashPermalink OverlayTrigger'}),
dict(name='div', attrs={'class': 'messageUserInfo'})
]
feeds = [
(u'\u041D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://feeds.feedburner.com/Old-games-ru-news'),
(u'\u0421\u0442\u0430\u0442\u044C\u0438', 'https://feeds.feedburner.com/Old-games-ru-articles')
]
Новая Газета. Европа ( Russian version): European re-incarnation of Новая Газета newspaper. Favicon
Fixes needed: - No images in articles (webp format)
Spoiler:
Code:
#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function
from calibre.web.feeds.news import BasicNewsRecipe, classes
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.'
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
Вёрстка: socio-political online media researching Russian society. Favicon.
Spoiler:
Code:
#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function
from calibre.web.feeds.news import BasicNewsRecipe, classes
class Verstka(BasicNewsRecipe):
title = u'\u0412\u0451\u0440\u0441\u0442\u043A\u0430'
description = u'\u041E\u0431\u0449\u0435\u0441\u0442\u0432\u0435\u043D\u043D\u043E-\u043F\u043E\u043B\u0438\u0442\u0438\u0447\u0435\u0441\u043A\u043E\u0435 \u0438\u0437\u0434\u0430\u043D\u0438\u0435, \u043A\u043E\u0442\u043E\u0440\u043E\u0435 \u0438\u0441\u0441\u043B\u0435\u0434\u0443\u0435\u0442 \u0438 \u043E\u043F\u0438\u0441\u044B\u0432\u0430\u0435\u0442, \u043A\u0430\u043A \u0444\u0443\u043D\u043A\u0446\u0438\u043E\u043D\u0438\u0440\u0443\u0435\u0442 \u043E\u0431\u0449\u0435\u0441\u0442\u0432\u043E \u0432 \u0420\u043E\u0441\u0441\u0438\u0438.'
__author__ = 'bugmen00t'
publication_type = 'newspaper'
oldest_article = 21
max_articles_per_feed = 20
language = 'ru'
cover_url = 'https://secureservercdn.net/160.153.137.128/yji.7dd.myftpupload.com/wp-content/uploads/2022/04/Screenshot-2022-04-26-at-22.19.30-300x68.png'
auto_cleanup = False
no_stylesheets = False
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': 'wp-block-spacer'})
feeds = [
(u'\u041D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://verstka.media/category/news/feed/'),
(u'\u0421\u0442\u0430\u0442\u044C\u0438', 'https://verstka.media/category/article/feed/'),
(u'\u041A\u043E\u043B\u043E\u043D\u043A\u0438', 'https://verstka.media/category/column/feed/'),
(u'\u0418\u043D\u0442\u0435\u0440\u0432\u044C\u044E', 'https://verstka.media/category/interview/feed/')
]
Кедр: independent environmental media. Favicon.
Fixes needed: - No images in some articles (<figure> tag and/or webp format)
Spoiler:
Code:
#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function
from calibre.web.feeds.news import BasicNewsRecipe, classes
class Cedar(BasicNewsRecipe):
title = u'\u041A\u0435\u0434\u0440'
description = u'\u041D\u0435\u0437\u0430\u0432\u0438\u0441\u0438\u043C\u043E\u0435 \u043C\u0435\u0434\u0438\u0430 \u043E\u0431 \u043E\u043A\u0440\u0443\u0436\u0430\u044E\u0449\u0435\u0439 \u0441\u0440\u0435\u0434\u0435'
__author__ = 'bugmen00t'
publication_type = 'blog'
oldest_article = 30
max_articles_per_feed = 20
language = 'ru'
cover_url = 'https://kedr.media/wp-content/themes/kedrmedia_gutenberg/assets/img/logo-bg.svg'
auto_cleanup = True
no_stylesheets = False
remove_tags_before = dict(name='div', attrs={'class': 'post-header'})
remove_tags_after = dict(name='div', attrs={'class': 'post-content'})
feeds = [
(u'\u0418\u0441\u0441\u043B\u0435\u0434\u043E\u0432\u0430\u043D\u0438\u044F', 'https://kedr.media/category/research/feed'),
(u'\u0418\u0441\u0442\u043E\u0440\u0438\u0438', 'https://kedr.media/category/stories/feed'),
(u'\u041C\u043D\u0435\u043D\u0438\u044F', 'https://kedr.media/category/opinions/feed'),
(u'\u0418\u043D\u0442\u0435\u0440\u0432\u044C\u044E', 'https://kedr.media/category/interview/feed'),
(u'\u041E\u0431\u044A\u044F\u0441\u043D\u044F\u0435\u043C', 'https://kedr.media/category/explain/feed')
]
Deutsche Welle на русском: Russian version of Deutsche Welle. Favicon.
Spoiler:
Code:
#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function
from calibre.web.feeds.news import BasicNewsRecipe, classes
class DeutscheWelle(BasicNewsRecipe):
title = u'Deutsche Welle \u043D\u0430 \u0440\u0443\u0441\u0441\u043A\u043E\u043C'
description = u'\u0420\u0443\u0441\u0441\u043A\u0430\u044F \u0440\u0435\u0434\u0430\u043A\u0446\u0438\u044F Deutsche Welle: \u043D\u043E\u0432\u043E\u0441\u0442\u0438, \u0430\u043D\u0430\u043B\u0438\u0442\u0438\u043A\u0430, \u043A\u043E\u043C\u043C\u0435\u043D\u0442\u0430\u0440\u0438\u0438 \u0438 \u0440\u0435\u043F\u043E\u0440\u0442\u0430\u0436\u0438 \u0438\u0437 \u0413\u0435\u0440\u043C\u0430\u043D\u0438\u0438 \u0438 \u0415\u0432\u0440\u043E\u043F\u044B, \u043D\u0435\u043C\u0435\u0446\u043A\u0438\u0439 \u0438 \u0435\u0432\u0440\u043E\u043F\u0435\u0439\u0441\u043A\u0438\u0439 \u0432\u0437\u0433\u043B\u044F\u0434 \u043D\u0430 \u0441\u043E\u0431\u044B\u0442\u0438\u044F \u0432 \u0420\u043E\u0441\u0441\u0438\u0438 \u0438 \u043C\u0438\u0440\u0435, \u043F\u0440\u0430\u043A\u0442\u0438\u0447\u0435\u0441\u043A\u0438\u0435 \u0441\u043E\u0432\u0435\u0442\u044B \u0434\u043B\u044F \u0442\u0443\u0440\u0438\u0441\u0442\u043E\u0432 \u0438 \u0442\u0435\u0445, \u043A\u0442\u043E \u0436\u0435\u043B\u0430\u0435\u0442 \u0443\u0447\u0438\u0442\u044C\u0441\u044F \u0438\u043B\u0438 \u0440\u0430\u0431\u043E\u0442\u0430\u0442\u044C \u0432 \u0413\u0435\u0440\u043C\u0430\u043D\u0438\u0438 \u0438 \u0434\u0440\u0443\u0433\u0438\u0445 \u0441\u0442\u0440\u0430\u043D\u0430\u0445 \u0415\u0432\u0440\u043E\u0441\u043E\u044E\u0437\u0430.'
__author__ = 'bugmen00t'
publication_type = 'newspaper'
oldest_article = 14
max_articles_per_feed = 100
language = 'ru_DE'
cover_url = 'https://www.dw.com/cssi/dwlogo-print.gif'
auto_cleanup = False
no_stylesheets = False
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': 'longText'})
feeds = [
(u'\u0412\u0435\u0441\u044C \u0441\u0430\u0439\u0442', 'https://rss.dw.com/xml/rss-ru-all'),
(u'\u041D\u043E\u0432\u043E\u0441\u0442\u0438', 'http://rss.dw.de/xml/rss-ru-news'),
(u'\u041F\u043E\u043B\u0438\u0442\u0438\u043A\u0430 \u0438 \u043E\u0431\u0449\u0435\u0441\u0442\u0432\u043E', 'http://rss.dw.de/xml/rss-ru-pol'),
(u'\u042D\u043A\u043E\u043D\u043E\u043C\u0438\u043A\u0430', 'http://rss.dw.de/xml/rss-ru-eco'),
(u'\u0410\u0432\u0442\u043E\u043C\u043E\u0431\u0438\u043B\u044C', 'http://rss.dw.de/xml/rss-ru-auto'),
(u'\u041A\u0443\u043B\u044C\u0442\u0443\u0440\u0430 \u0438 \u0441\u0442\u0438\u043B\u044C \u0436\u0438\u0437\u043D\u0438', 'http://rss.dw.de/xml/rss-ru-cul'),
(u'\u0420\u043E\u0441\u0441\u0438\u044F', 'http://rss.dw.de/xml/rss-ru-rus'),
(u'\u0413\u0435\u0440\u043C\u0430\u043D\u0438\u044F', 'http://rss.dw.de/xml/rss-ru-ger'),
(u'\u0415\u0432\u0440\u043E\u043F\u0430', 'http://rss.dw.de/xml/rss-ru-eu'),
(u'\u0411\u0435\u043B\u0430\u0440\u0443\u0441\u044C', 'http://rss.dw.de/xml/rss-ru-bel'),
(u'\u0423\u0447\u0435\u0431\u0430 \u0438 \u043A\u0430\u0440\u044C\u0435\u0440\u0430', 'http://rss.dw.de/xml/rss-ru-campus-karriere'),
(u'\u0423\u0447\u0435\u0431\u0430 ', 'http://rss.dw.de/xml/rss-ru-campus'),
(u'\u041A\u0430\u0440\u044C\u0435\u0440\u0430 ', 'http://rss.dw.de/xml/rss-ru-karriere'),
(u'\u0422\u0443\u0440\u0438\u0441\u0442\u0443 \u043D\u0430 \u0437\u0430\u043C\u0435\u0442\u043A\u0443', 'http://rss.dw.de/xml/rss-ru-discover-ger')
]
Русская служба BBC: BBC News in Russian. Favicon.
Fixes needed: - No images in some articles (lazyload)
- No images in some articles (webp format)
Last edited by bugmen00t; 07-21-2022 at 04:18 PM.
|