|
Connoisseur
Posts: 82
Karma: 100000
Join Date: Aug 2015
Device: Kindle Keyboard 3G + Kindle Voyage WiFi + Kindle PW11 Kids WiFi
|
New Recipes (part 02 of ??)
NEW ENGLISH RECIPES (OF RUSSIAN SOURCES)
Novaya Gazeta Europe ( English version): European re-incarnation of Novaya Gazeta 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'Novaya Gazeta Europe'
__author__ = 'bugmen00t'
description = u'English edition of Novaya Gazeta Europe: news, analytics, expert opinions, special reports and investigative journalism.'
publisher = 'Kirill Martynov'
category = 'news'
language = 'en_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'News', 'https://novayagazeta.eu/feed/rss/en')
]
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
Meduza ( English version): Latvia-based media founded by a group of former employees of the then independent Lenta.ru news website. 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 Meduza(BasicNewsRecipe):
title = u'Meduza'
description = u'Russian- and English-language independent news website, based in Latvia. It was founded in 2014 by a group of former employees of the then independent Lenta.ru news website. Every day we bring you the most important news and feature stories from hundreds of sources in Russia and across the former Soviet Union.'
__author__ = 'bugmen00t'
publisher = 'Medusa Project SIA'
publication_type = 'blog'
oldest_article = 21
max_articles_per_feed = 100
language = 'en_RU'
cover_url = 'https://meduza.io/impro/E_cJMv0IQxOC45z-YXeGuzuPB2kQ_A1XsZYrdByOCnk/fill/1200/0/ce/0/aHR0cHM6Ly9tZWR1/emEuaW8vaW1hZ2Uv/YXR0YWNobWVudHMv/aW1hZ2VzLzAwNi83/MTgvODcyL29yaWdp/bmFsLzVPSmRDdWc1/bC1JVG9lTXBqSHFH/ZXcucG5n.png'
auto_cleanup = False
no_stylesheets = False
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': 'GeneralMaterial-article'})
remove_tags = [
dict(name='div', attrs={'id': 'div-gpt-ad'}),
]
feeds = [
(u'News', 'https://meduza.io/rss2/en/news'),
(u'Feature stories', 'https://meduza.io/rss2/en/stories'),
]
Holod ( English version): Taisiya Bekbulatova's project with longreads, podcasts and videos on social and political topics about Russia. No updates since June 2022. Favicon replacement.
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 Kholod(BasicNewsRecipe):
title = u'Holod Media'
description = u'Internet media whose authors search for exciting stories all over Russia and then tell them to readers.'
__author__ = 'bugmen00t'
publisher = 'Taisiya Bekbulatova'
publication_type = 'blog'
oldest_article = 60
max_articles_per_feed = 100
language = 'en_RU'
cover_url = 'https://image.simplecastcdn.com/images/93a97011-6988-4787-8242-e202b2840fde/08e85f64-9901-44e1-b20c-7da01c5ce0c0/holodpodcastlogo.jpg'
auto_cleanup = False
no_stylesheets = False
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': 'article__content the-content text-column'})
remove_tags = [
dict(name='div', attrs={'class': 'inlinemore'})
]
feeds = [
(u'Spotlight', 'https://holod.media/en/sections/spotlight/feed/'),
(u'Opinion', 'https://holod.media/en/sections/opinion/feed/'),
(u'Interview', 'https://holod.media/en/sections/interview/feed/')
]
NEW RUSSIAN RECIPES
Медуза: Latvia-based media founded by a group of former employees of the then independent Lenta.ru news website. 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 Meduza(BasicNewsRecipe):
title = u'Meduza'
description = u'\u041C\u0435\u0436\u0434\u0443\u043D\u0430\u0440\u043E\u0434\u043D\u043E\u0435 \u0440\u0443\u0441\u0441\u043A\u043E\u044F\u0437\u044B\u0447\u043D\u043E\u0435 \u0438\u0437\u0434\u0430\u043D\u0438\u0435. \u041C\u044B \u0432\u044B\u0431\u0438\u0440\u0430\u0435\u043C \u0434\u043B\u044F \u0432\u0430\u0441 \u0441\u0430\u043C\u044B\u0435 \u0432\u0430\u0436\u043D\u044B\u0435 \u043D\u043E\u0432\u043E\u0441\u0442\u0438 \u0438 \u0433\u043E\u0442\u043E\u0432\u0438\u043C \u043B\u0443\u0447\u0448\u0438\u0435 \u0442\u0435\u043A\u0441\u0442\u044B \u043E \u0442\u043E\u043C, \u0447\u0442\u043E \u043F\u0440\u043E\u0438\u0441\u0445\u043E\u0434\u0438\u0442 \u0432 \u0420\u043E\u0441\u0441\u0438\u0438 \u0438 \u043C\u0438\u0440\u0435.'
__author__ = 'bugmen00t'
publisher = 'Medusa Project SIA'
publication_type = 'blog'
oldest_article = 7
max_articles_per_feed = 100
language = 'ru'
cover_url = 'https://meduza.io/impro/E_cJMv0IQxOC45z-YXeGuzuPB2kQ_A1XsZYrdByOCnk/fill/1200/0/ce/0/aHR0cHM6Ly9tZWR1/emEuaW8vaW1hZ2Uv/YXR0YWNobWVudHMv/aW1hZ2VzLzAwNi83/MTgvODcyL29yaWdp/bmFsLzVPSmRDdWc1/bC1JVG9lTXBqSHFH/ZXcucG5n.png'
auto_cleanup = False
no_stylesheets = False
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': 'GeneralMaterial-article'})
remove_tags = [
dict(name='div', attrs={'id': 'div-gpt-ad'})
]
feeds = [
(u'\u041D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://meduza.io/rss2/news'),
(u'\u0418\u0441\u0442\u043E\u0440\u0438\u0438', 'https://meduza.io/rss2/articles'),
]
Собеседник: Russian weekly socio-political newspaper. Favicon.
Холод: Taisiya Bekbulatova's project with longreads, podcasts and videos on social and political topics. Favicon replacement.
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 Kholod(BasicNewsRecipe):
title = u'\u0425\u043E\u043B\u043E\u0434'
description = u'\u0418\u0441\u0442\u043E\u0440\u0438\u0438 \u043E \u0420\u043E\u0441\u0441\u0438\u0438: \u043C\u044B \u0438\u0449\u0435\u043C \u0437\u0430\u0445\u0432\u0430\u0442\u044B\u0432\u0430\u044E\u0449\u0438\u0435 \u0438\u0441\u0442\u043E\u0440\u0438\u0438 \u043F\u043E \u0432\u0441\u0435\u0439 \u0420\u043E\u0441\u0441\u0438\u0438, \u0430 \u043F\u043E\u0442\u043E\u043C \u0440\u0430\u0441\u0441\u043A\u0430\u0437\u044B\u0432\u0430\u0435\u043C \u0432\u0430\u043C.'
__author__ = 'bugmen00t'
publisher = '\u0422\u0430\u0438\u0441\u0438\u044F \u0411\u0435\u043A\u0431\u0443\u043B\u0430\u0442\u043E\u0432\u0430'
publication_type = 'blog'
oldest_article = 14
max_articles_per_feed = 200
language = 'ru'
cover_url = 'https://image.simplecastcdn.com/images/93a97011-6988-4787-8242-e202b2840fde/08e85f64-9901-44e1-b20c-7da01c5ce0c0/holodpodcastlogo.jpg'
auto_cleanup = False
no_stylesheets = False
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': 'article__content the-content text-column'})
remove_tags = [
dict(name='div', attrs={'class': 'inlinemore'})
]
feeds = [
(u'\u0410\u043A\u0442\u0443\u0430\u043B\u044C\u043D\u043E', 'https://holod.media/sections/daily/feed/'),
(u'\u0418\u0441\u0442\u043E\u0440\u0438\u0438', 'https://holod.media/sections/stories/feed/'),
(u'\u041C\u043D\u0435\u043D\u0438\u044F', 'https://holod.media/sections/opinions/feed/'),
(u'\u0418\u043D\u0442\u0435\u0440\u0432\u044C\u044E', 'https://holod.media/sections/interviews/feed/'),
(u'\u041E\u0431\u044A\u044F\u0441\u043D\u044F\u0435\u043C', 'https://holod.media/sections/explainers/feed/')
]
Важные истории: Russian website specialising in investigative journalism. Favicon replacement #1, Favicon replacement #2.
Fixes needed: - No article header image
- No images in some 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 IStories(BasicNewsRecipe):
title = u'\u0412\u0430\u0436\u043D\u044B\u0435 \u0438\u0441\u0442\u043E\u0440\u0438\u0438'
description = u'\u0418\u043D\u0442\u0435\u0440\u043D\u0435\u0442-\u0438\u0437\u0434\u0430\u043D\u0438\u0435, \u0441\u043F\u0435\u0446\u0438\u0430\u043B\u0438\u0437\u0438\u0440\u0443\u044E\u0449\u0435\u0435\u0441\u044F \u043D\u0430 \u0436\u0443\u0440\u043D\u0430\u043B\u0438\u0441\u0442\u0441\u043A\u0438\u0445 \u0440\u0430\u0441\u0441\u043B\u0435\u0434\u043E\u0432\u0430\u043D\u0438\u044F\u0445. \u041E\u0441\u043D\u043E\u0432\u0430\u043D\u043E \u0432 2020 \u0433\u043E\u0434\u0443 \u0440\u043E\u0441\u0441\u0438\u0439\u0441\u043A\u0438\u043C\u0438 \u0436\u0443\u0440\u043D\u0430\u043B\u0438\u0441\u0442\u0430\u043C\u0438 \u0420\u043E\u043C\u0430\u043D\u043E\u043C \u0410\u043D\u0438\u043D\u044B\u043C \u0438 \u041E\u043B\u0435\u0441\u0435\u0439 \u0428\u043C\u0430\u0433\u0443\u043D.'
__author__ = 'bugmen00t'
publisher = 'Roman Anin & Olesya Shmagun'
publication_type = 'blog'
oldest_article = 21
max_articles_per_feed = 50
language = 'ru'
cover_url = 'https://static.istories.media/public/cover.png'
auto_cleanup = False
no_stylesheets = True
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='article')
remove_tags = [
dict(name='header'),
dict(name='footer'),
dict(name='form', attrs={'class': 'subscr'}),
dict(name='div', attrs={'class': 'row'}),
dict(name='div', attrs={'class': 'arrow-black'}),
dict(name='div', attrs={'class': 'article-foot'}),
dict(name='div', attrs={'class': 'article-toggle'}),
dict(name='div', attrs={'class': 'article-soc'})
]
feeds = [
(u'\u0438\u0441\u0442\u043E\u0440\u0438\u0438', 'https://istories.media/rss/all.xml')
]
N+1: science & technology news. 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 AdvancedUserRecipe1467724863(BasicNewsRecipe):
title = 'N+1'
__author__ = 'bugmen00t'
description = '\u041D\u0430\u0443\u0447\u043D\u043E-\u043F\u043E\u043F\u0443\u043B\u044F\u0440\u043D\u043E\u0435 \u0440\u0430\u0437\u0432\u043B\u0435\u043A\u0430\u0442\u0435\u043B\u044C\u043D\u043E\u0435 \u0438\u0437\u0434\u0430\u043D\u0438\u0435 \u043E \u0442\u043E\u043C, \u0447\u0442\u043E \u043F\u0440\u043E\u0438\u0441\u0445\u043E\u0434\u0438\u0442 \u0432 \u043D\u0430\u0443\u043A\u0435, \u0442\u0435\u0445\u043D\u0438\u043A\u0435 \u0438 \u0442\u0435\u0445\u043D\u043E\u043B\u043E\u0433\u0438\u044F\u0445 \u043F\u0440\u044F\u043C\u043E \u0441\u0435\u0439\u0447\u0430\u0441. \u041D\u043E\u0432\u043E\u0441\u0442\u0438, \u0431\u043E\u043B\u044C\u0448\u0438\u0435 \u0441\u0442\u0430\u0442\u044C\u0438, \u0431\u043B\u043E\u0433\u0438 \u2014 \u044D\u0442\u043E \u0432\u0441\u0435 \u043F\u0440\u043E \u043D\u0430\u0441. \u041C\u044B \u0438\u0449\u0435\u043C \u0441\u0430\u043C\u043E\u0435 \u0438\u043D\u0442\u0435\u0440\u0435\u0441\u043D\u043E\u0435 \u0438 \u0434\u043E\u0441\u0442\u0430\u0432\u043B\u044F\u0435\u043C \u044D\u0442\u043E \u0447\u0438\u0442\u0430\u0442\u0435\u043B\u044F\u043C \u0432 \u043F\u043E\u043D\u044F\u0442\u043D\u043E\u0439, \u044F\u0441\u043D\u043E\u0439, \u043F\u0440\u0438\u0432\u043B\u0435\u043A\u0430\u0442\u0435\u043B\u044C\u043D\u043E\u0439 (\u0438 \u0441 \u0432\u0438\u0437\u0443\u0430\u043B\u044C\u043D\u043E\u0439 \u0442\u043E\u0447\u043A\u0438 \u0437\u0440\u0435\u043D\u0438\u044F) \u0444\u043E\u0440\u043C\u0435. \u041C\u044B \u2014 \u0447\u0443\u0442\u044C \u0431\u043E\u043B\u044C\u0448\u0435, \u0447\u0435\u043C \u043F\u0440\u043E\u0441\u0442\u043E \u043D\u0430\u0443\u043A\u0430!'
publisher = 'N+1'
category = 'news'
cover_url = u'https://nplus1.ru/i/logo.png'
language = 'ru'
no_stylesheets = False
remove_javascript = True
auto_cleanup = False
oldest_article = 14
max_articles_per_feed = 100
# remove_tags_before = dict(name='article', attrs={'class':'content'})
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class':'body'})
remove_tags = [
dict(name='div', attrs={'class': 'share-incut'}),
dict(name='div', attrs={'class': 'share-mobile'})
]
feeds = [
('\u041d\u043e\u0432\u043e\u0441\u0442\u0438 \u043d\u0430\u0443\u043a\u0438', 'https://nplus1.ru/rss'),
]
NEW UKRAINIAN RECIPES
BBC News Україна: BBC News in Ukrainian. Favicon.
Fixes needed: - No images in some articles (lazyload)
- No images in some articles (webp format)
Last edited by bugmen00t; 07-23-2022 at 02:58 AM.
Reason: Small fix for Meduza (ru) recipe
|