|
Connoisseur
Posts: 82
Karma: 100000
Join Date: Aug 2015
Device: Kindle Keyboard 3G + Kindle Voyage WiFi + Kindle PW11 Kids WiFi
|
New recipes (part 04 of ??)
NEW RUSSIAN RECIPES
Черта: media about prevention of discrimantion, social inequality & violence. 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
class Cherta(BasicNewsRecipe):
title = '\u0427\u0435\u0440\u0442\u0430'
__author__ = 'bugmen00t'
description = ' \u0418\u043D\u0442\u0435\u0440\u0435\u0441\u043D\u044B\u0435, \u0432\u0430\u0436\u043D\u044B\u0435 \u0438 \u0433\u043B\u0443\u0431\u043E\u043A\u0438\u0435 \u0442\u0435\u043A\u0441\u0442\u044B \u043F\u0440\u043E \u043D\u0430\u0441\u0438\u043B\u0438\u0435 \u0438 \u043D\u0435\u0440\u0430\u0432\u0435\u043D\u0441\u0442\u0432\u043E \u0432 \u0420\u043E\u0441\u0441\u0438\u0438.'
publisher = 'cherta.media'
category = 'blog'
cover_url = u'https://cherta.media/wp-content/uploads/2022/01/cherta_snippet2.png'
language = 'ru'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 30
max_articles_per_feed = 30
remove_tags_before = dict(name='div', attrs={'class':'single-story'})
remove_tags_after = dict(name='div', attrs={'class':'single-page__footer-info'})
remove_tags = [
dict(name='div', attrs={'class': 'single-content-link'}),
dict(name='div', attrs={'class': 'single-page__footer-info_links clearfix'}),
dict(name='div', attrs={'class': 'single-article-tags-wrapper'})
]
feeds = [
('\u0418\u0441\u0442\u043E\u0440\u0438\u0438', 'https://cherta.media/story/feed/'),
('\u0418\u043D\u0442\u0435\u0440\u0432\u044C\u044E', 'https://cherta.media/interview/feed/')
]
Горький: collective blog with book reviews, essays, author interviews etc. Favicon.
Fixes needed: - No header images in some articles
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
class Gorky(BasicNewsRecipe):
title = '\u0413\u043E\u0440\u044C\u043A\u0438\u0439'
__author__ = 'bugmen00t'
description = '\u041D\u0435\u043A\u043E\u043C\u043C\u0435\u0440\u0447\u0435\u0441\u043A\u0438\u0439 \u043F\u0440\u043E\u0435\u043A\u0442 \u043E \u043A\u043D\u0438\u0433\u0430\u0445 \u0438 \u0447\u0442\u0435\u043D\u0438\u0438.'
publisher = '\u0410\u041D\u041E "\u0426\u0435\u043D\u0442\u0440 \u043F\u043E \u0441\u043E\u0434\u0435\u0439\u0441\u0442\u0432\u0438\u044E \u0440\u0430\u0437\u0432\u0438\u0442\u0438\u044F \u043A\u0443\u043B\u044C\u0442\u0443\u0440\u044B \u0447\u0442\u0435\u043D\u0438\u044F \u0438 \u043A\u043D\u0438\u0433\u043E\u0438\u0437\u0434\u0430\u043D\u0438\u044F \u00AB\u0413\u043E\u0440\u044C\u043A\u0438\u0439 \u041C\u0435\u0434\u0438\u0430\u00BB"'
category = 'blog'
cover_url = u'https://gorky.media/wp-content/uploads/2016/09/gorky.png'
language = 'ru'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 30
max_articles_per_feed = 30
remove_tags_before = dict(name='div', attrs={'id': 'td-outer-wrap'})
remove_tags_after = dict(name='footer')
remove_tags = [
dict(name='footer'),
dict(name='nav', attrs={'class': 'navbar'}),
dict(name='div', attrs={'class': 'hide'}),
dict(name='div', attrs={'class': 'nav-new'}),
dict(name='div', attrs={'class': 'top-panel '}),
dict(name='div', attrs={'class': 'panel-nav'}),
dict(name='div', attrs={'class': 'panel-nav _hide'}),
dict(name='ul', attrs={'class': 'top-panel__bottom buttons-list _share'}),
dict(name='ul', attrs={'class': 'buttons-list _share d_lg-none'})
]
feeds = [
('\u0420\u0435\u0446\u0435\u043D\u0437\u0438\u0438', 'https://gorky.media/reviews/feed/'),
('\u0424\u0440\u0430\u0433\u043C\u0435\u043D\u0442\u044B', 'https://gorky.media/fragments/feed/'),
('\u041A\u043E\u043D\u0442\u0435\u043A\u0441\u0442', 'https://gorky.media/context/feed/'),
('\u041F\u043E\u0434\u0431\u043E\u0440\u043A\u0438', 'https://gorky.media/books-collection/feed/')
]
The New Times: weekly socio-political online magazine. Favicon.
SOVA: Tbilisi-based media about life & society in Georgia. Favicon replacement.
Fixes needed: - No secondary text lead and header image in some articles
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
class Sova(BasicNewsRecipe):
title = 'SOVA'
__author__ = 'bugmen00t'
description = ' \u0420\u0443\u0441\u0441\u043A\u043E\u044F\u0437\u044B\u0447\u043D\u043E\u0435 \u043D\u0435\u0437\u0430\u0432\u0438\u0441\u0438\u043C\u043E\u0435 \u043E\u043D\u043B\u0430\u0439\u043D-\u0438\u0437\u0434\u0430\u043D\u0438\u0435, \u043E\u0441\u043D\u043E\u0432\u0430\u043D\u043D\u043E\u0435 \u0432 \u0422\u0431\u0438\u043B\u0438\u0441\u0438 \u0432 2016 \u0433\u043E\u0434\u0443 \u0433\u0440\u0443\u043F\u043F\u043E\u0439 \u043F\u0440\u043E\u0444\u0435\u0441\u0441\u0438\u043E\u043D\u0430\u043B\u044C\u043D\u044B\u0445 \u0436\u0443\u0440\u043D\u0430\u043B\u0438\u0441\u0442\u043E\u0432, \u043F\u0440\u0435\u0434\u043E\u0441\u0442\u0430\u0432\u043B\u044F\u044E\u0449\u0435\u0435 \u043A\u0430\u0447\u0435\u0441\u0442\u0432\u0435\u043D\u043D\u0443\u044E \u0438\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u044E \u043E \u043F\u043E\u043B\u0438\u0442\u0438\u043A\u0435, \u044D\u043A\u043E\u043D\u043E\u043C\u0438\u043A\u0435 \u0438 \u0434\u0440\u0443\u0433\u0438\u0445 \u043D\u0435\u043E\u0442\u044A\u0435\u043C\u043B\u0435\u043C\u044B\u0445 \u0430\u0441\u043F\u0435\u043A\u0442\u0430\u0445 \u0436\u0438\u0437\u043D\u0438 \u0441\u043E\u0432\u0440\u0435\u043C\u0435\u043D\u043D\u043E\u0433\u043E \u0447\u0435\u043B\u043E\u0432\u0435\u043A\u0430 \u0432 \u0413\u0440\u0443\u0437\u0438\u0438 \u0438 \u0440\u0435\u0433\u0438\u043E\u043D\u0435 \u0432 \u0446\u0435\u043B\u043E\u043C.'
publisher = '\u041D\u0435\u043F\u0440\u0430\u0432\u0438\u0442\u0435\u043B\u044C\u0441\u0442\u0432\u0435\u043D\u043D\u0430\u044F \u043E\u0440\u0433\u0430\u043D\u0438\u0437\u0430\u0446\u0438\u044F Sova News'
category = 'blog'
cover_url = u'https://i0.wp.com/sova.news/wp-content/uploads/2021/08/sova@512.png'
language = 'ru'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 60
max_articles_per_feed = 30
remove_tags_before = dict(name='div', attrs={'class':'site-wrapper header-7'})
remove_tags_after = dict(name='div', attrs={'class':'single-body entry-content typography-copy'})
remove_tags = [
dict(name='nav', attrs={'aria-label': 'breadcrumbs'}),
dict(name='header', attrs={'class': 'site-header site-header--skin-5'}),
dict(name='footer'),
dict(name='ins'),
dict(name='div', attrs={'class': 'entry-interaction__left'}),
dict(name='div', attrs={'class': 'entry-interaction__right'}),
dict(name='div', attrs={'id': 'mnmd-sticky-header'}),
dict(name='div', attrs={'id': 'mnmd-offcanvas-primary'}),
dict(name='div', attrs={'id': 'mnmd-offcanvas-mobile'}),
dict(name='div', attrs={'class': 'entry-interaction__right'}),
dict(name='blockquote', attrs={'class': 'wp-embedded-content'})
]
feeds = [
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://sova.news/news/feed/'),
('\u041F\u043E\u043B\u0438\u0442\u0438\u043A\u0430', 'https://sova.news/analytics/politics/feed/'),
('\u042D\u043A\u043E\u043D\u043E\u043C\u0438\u043A\u0430', 'https://sova.news/analytics/economy/feed/'),
('\u041E\u0431\u0449\u0435\u0441\u0442\u0432\u043E', 'https://sova.news/analytics/society/feed/'),
('\u0418\u043D\u0442\u0435\u0440\u0432\u044C\u044E', 'https://sova.news/interview/feed/'),
('Unfake', 'https://sova.news/unfake/feed/'),
('\u0414\u0440\u0443\u0433\u0430\u044F \u0421\u043E\u0432\u0430', 'https://sova.news/sova-other/feed/'),
('\u0418\u0441\u043A\u0443\u0441\u0441\u0442\u0432\u043E', 'https://sova.news/sova-other/art/feed/'),
('\u0422\u0443\u0440\u0438\u0437\u043C', 'https://sova.news/sova-other/tourism/feed/'),
('#weekendnavigator', 'https://sova.news/weekendnavigator/feed/'),
('\u0421\u043E\u0441\u0435\u0434\u0438', 'https://sova.news/sova-other/neighbours/feed/'),
('\u041D\u0435\u0434\u0435\u043B\u044F \u0432 \u0433\u043E\u0440\u043E\u0434\u0435', 'https://sova.news/week-in-the-city/feed/'),
('\u0424\u043E\u0442\u043E\u043F\u0440\u043E\u0433\u0443\u043B\u043A\u0438', 'https://sova.news/photowalks/feed/'),
('\u0424\u043E\u0442\u043E', 'https://sova.news/photo/feed/')
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src']
return soup
StopGame: gaming community portal with news, reviews, streams and blogs. 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
class StopGame(BasicNewsRecipe):
title = 'StopGame'
__author__ = 'bugmen00t'
description = ' \u0420\u043E\u0441\u0441\u0438\u0439\u0441\u043A\u0438\u0439 \u0438\u0433\u0440\u043E\u0432\u043E\u0439 \u0438\u043D\u0442\u0435\u0440\u043D\u0435\u0442-\u043F\u043E\u0440\u0442\u0430\u043B, \u043D\u0430 \u043A\u043E\u0442\u043E\u0440\u043E\u043C \u043A\u043E\u043B\u043B\u0435\u043A\u0442\u0438\u0432 \u0430\u0432\u0442\u043E\u0440\u043E\u0432 \u0440\u0430\u0441\u0441\u043A\u0430\u0437\u044B\u0432\u0430\u0435\u0442 \u0432\u0441\u0435\u043C \u0436\u0435\u043B\u0430\u044E\u0449\u0438\u043C \u043E \u0432\u0438\u0434\u0435\u043E\u0438\u0433\u0440\u0430\u0445. '
publisher = 'StopGame.ru'
category = 'blog'
cover_url = u'https://images.stopgame.ru/blogs/2020/01/29/U7R7t5rQ.jpg'
language = 'ru'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 50
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': '_end-info_zp673_1113'})
remove_tags = [
dict(name='section', attrs={'id': 'comments'}),
dict(name='footer'),
dict(name='section', attrs={'class': '_page-section_xdzdd_387 _additional-reads_zp673_1348'})
]
feeds = [
('\u0412\u0441\u0435 \u0440\u0430\u0437\u0434\u0435\u043B\u044B', 'https://rss.stopgame.ru/rss_all.xml'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://rss.stopgame.ru/rss_news.xml'),
('\u0421\u0442\u0430\u0442\u044C\u0438', 'https://rss.stopgame.ru/articles.xml'),
('\u0412\u0438\u0434\u0435\u043E', 'https://rss.stopgame.ru/videos.xml'),
('\u0411\u043B\u043E\u0433\u0438', 'https://rss.stopgame.ru/all_topics.xml')
]
Also uploading recipes' code & icon as separate files, maybe it will be easier for Dr. Goyal to add them into Calibre that way.
|