|
|||||||
| Latest Uploads |
| Browse Latest Uploads |
| Latest Uploads (Feed) |
| Kindle Download Guide |
| Formats |
| Kindle (MOBI) |
| Sony BBeB (LRF) |
| ePub (EPUB) |
| eBookwise (IMP) |
| Miscellaneous |
| Search Forums |
| Advanced Search |
| Attachment Search |
| Find New Posts |
| All New Posts |
| - w/o E-Book Uploads |
| Last 24 Hours |
| Last 2 Days |
| Last 5 Days |
| Your Posts |
| Go to Page... |
| View Poll Results: Which type of recipes you'd like to have the most? | |||
| Ukrainian sources in Ukrainian |
   
|
1 | 33.33% |
| Ukrainian sources in Russian |
  
|
0 | 0% |
| Russian sources in Russian |
  
|
0 | 0% |
| Russian & Ukrainian sources in English |
  
|
2 | 66.67% |
| Multiple Choice Poll. Voters: 3. You may not vote on this poll | |||
 |
|
|
Thread Tools | Search this Thread |
07-28-2022, 11:03 PM
|
#16 |
|
creator of calibre
  
Posts: 43,860
Karma: 22666666
Join Date: Oct 2006
Location: Mumbai, India
Device: Various
|
that fix was already done when I added the recipe.
|
|
|
|
07-29-2022, 06:38 AM
|
#17 | |
|
Connoisseur
Posts: 65
Karma: 100000
Join Date: Aug 2015
Device: Kindle Keyboard + Kindle Voyage WiFi + Kindle PW11 Kids
|
Quote:
|
|
|
|
|
| Advert | |
|
|
|
08-01-2022, 07:08 AM
|
#18 |
|
Connoisseur
Posts: 65
Karma: 100000
Join Date: Aug 2015
Device: Kindle Keyboard + Kindle Voyage WiFi + Kindle PW11 Kids
|
New recipes (part 06 of ??)
NEW MULTI-LANGUAGE RECIPE (OF UKRAINIAN SOURCE) UkrInform: state information and news agency of Ukraine. Favicon replacement. It seems that the values of 'language' variable are overcomplicated as they cause new redundant categories in recipes list; probably should've left single language code. Ukrainain version: 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 UkrInform(BasicNewsRecipe):
title = '\u0423\u043A\u0440\u0456\u043D\u0444\u043E\u0440\u043C'
__author__ = 'bugmen00t'
description = '\u0423\u043A\u0440\u0430\u0457\u043D\u0441\u044C\u043A\u0435 \u0434\u0435\u0440\u0436\u0430\u0432\u043D\u0435 \u0456\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0456\u0439\u043D\u0435 \u0430\u0433\u0435\u043D\u0442\u0441\u0442\u0432\u043E, \u0434\u0436\u0435\u0440\u0435\u043B\u043E \u0456\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0456\u0457 \u043F\u0440\u043E \u043F\u043E\u043B\u0456\u0442\u0438\u0447\u043D\u0435, \u0435\u043A\u043E\u043D\u043E\u043C\u0456\u0447\u043D\u0435, \u0441\u043E\u0446\u0456\u0430\u043B\u044C\u043D\u0435, \u043D\u0430\u0443\u043A\u043E\u0432\u0435, \u043A\u0443\u043B\u044C\u0442\u0443\u0440\u043D\u0435, \u0441\u0443\u0441\u043F\u0456\u043B\u044C\u043D\u0435 \u0436\u0438\u0442\u0442\u044F \u0432 \u0423\u043A\u0440\u0430\u0457\u043D\u0456 \u0442\u0430 \u0437\u0430 \u043A\u043E\u0440\u0434\u043E\u043D\u043E\u043C.'
publisher = '\u041C\u0456\u043D\u0456\u0441\u0442\u0435\u0440\u0441\u0442\u0432\u043E \u043A\u0443\u043B\u044C\u0442\u0443\u0440\u0438 \u0442\u0430 \u0456\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0456\u0439\u043D\u043E\u0457 \u043F\u043E\u043B\u0456\u0442\u0438\u043A\u0438 \u0423\u043A\u0440\u0430\u0457\u043D\u0438'
category = 'newspaper'
cover_url = u'https://upload.wikimedia.org/wikipedia/commons/thumb/c/ca/Logo_ukr_%281%29.svg/2560px-Logo_ukr_%281%29.svg.png'
language = 'uk'
no_stylesheets = True
remove_javascript = False
auto_cleanup = False
oldest_article = 2
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 = [
('\u041E\u0441\u0442\u0430\u043D\u043D\u0456 \u043D\u043E\u0432\u0438\u043D\u0438', 'https://www.ukrinform.ua/rss/block-lastnews'),
('\u0412\u0456\u0439\u043D\u0430', 'https://www.ukrinform.ua/rss/rubric-ato'),
('#UA\u0440\u0430\u0437\u043E\u043C', 'https://www.ukrinform.ua/rss/rubric-uarazom'),
('\u041F\u043E\u043B\u0456\u0442\u0438\u043A\u0430', 'https://www.ukrinform.ua/rss/rubric-polytics'),
('\u0415\u043A\u043E\u043D\u043E\u043C\u0456\u043A\u0430', 'https://www.ukrinform.ua/rss/rubric-economy'),
('\u0421\u0432\u0456\u0442', 'https://www.ukrinform.ua/rss/rubric-world'),
('\u0421\u0443c\u043F\u0456\u043B\u044Cc\u0442\u0432\u043E', 'https://www.ukrinform.ua/rss/rubric-society'),
('\u041A\u0443\u043B\u044C\u0442\u0443\u0440\u0430', 'https://www.ukrinform.ua/rss/rubric-culture'),
('\u0420\u0435\u0433\u0456\u043E\u043D\u0438', 'https://www.ukrinform.ua/rss/rubric-regions'),
('\u041A\u0438\u0457\u0432', 'https://www.ukrinform.ua/rss/rubric-kyiv'),
('\u041A\u0440\u0438\u043C', 'https://www.ukrinform.ua/rss/rubric-crimea'),
('\u0421\u043F\u043E\u0440\u0442', 'https://www.ukrinform.ua/rss/rubric-sports'),
('\u0414\u0456\u0430c\u043F\u043E\u0440\u0430', 'https://www.ukrinform.ua/rss/rubric-diaspora'),
('\u0422\u0435\u0445\u043D\u043E\u043B\u043E\u0433\u0456\u0457', 'https://www.ukrinform.ua/rss/rubric-technology'),
]
Russian version: 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 UkrInform(BasicNewsRecipe):
title = '\u0423\u043A\u0440\u0438\u043D\u0444\u043E\u0440\u043C'
__author__ = 'bugmen00t'
description = '\u0423\u043A\u0440\u0430\u0438\u043D\u0441\u043A\u043E\u0435 \u0433\u043E\u0441\u0443\u0434\u0430\u0440\u0441\u0442\u0432\u0435\u043D\u043D\u043E\u0435 \u043D\u0430\u0446\u0438\u043E\u043D\u0430\u043B\u044C\u043D\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, \u0438\u0441\u0442\u043E\u0447\u043D\u0438\u043A \u0438\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u0438 \u043E \u043F\u043E\u043B\u0438\u0442\u0438\u0447\u0435\u0441\u043A\u043E\u0439, \u044D\u043A\u043E\u043D\u043E\u043C\u0438\u0447\u0435\u0441\u043A\u043E\u0439, \u0441\u043E\u0446\u0438\u0430\u043B\u044C\u043D\u043E\u0439, \u043D\u0430\u0443\u0447\u043D\u043E\u0439, \u043A\u0443\u043B\u044C\u0442\u0443\u0440\u043D\u043E\u0439, \u043E\u0431\u0449\u0435\u0441\u0442\u0432\u0435\u043D\u043D\u043E\u0439 \u0436\u0438\u0437\u043D\u0438 \u0432 \u0423\u043A\u0440\u0430\u0438\u043D\u0435 \u0438 \u0437\u0430 \u0440\u0443\u0431\u0435\u0436\u043E\u043C.'
publisher = '\u041C\u0438\u043D\u0438\u0441\u0442\u0435\u0440\u0441\u0442\u0432\u043E \u0438\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u043E\u043D\u043D\u043E\u0439 \u043F\u043E\u043B\u0438\u0442\u0438\u043A\u0438 \u0423\u043A\u0440\u0430\u0438\u043D\u044B'
category = 'newspaper'
cover_url = u'https://www.ukrinform.ru/img/logo_rus.svg'
language = 'ru_UK'
no_stylesheets = True
remove_javascript = False
auto_cleanup = False
oldest_article = 3
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 = [
('\u041F\u043E\u0441\u043B\u0435\u0434\u043D\u0438\u0435 \u043D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://www.ukrinform.ru/rss/block-lastnews'),
('\u0412\u043E\u0439\u043D\u0430', 'https://www.ukrinform.ru/rss/rubric-ato'),
('#UA\u0440\u0430\u0437\u043E\u043C', 'https://www.ukrinform.ru/rss/rubric-uarazom'),
('\u041F\u043E\u043B\u0438\u0442\u0438\u043A\u0430', 'https://www.ukrinform.ru/rss/rubric-polytics'),
('\u042D\u043A\u043E\u043D\u043E\u043C\u0438\u043A\u0430', 'https://www.ukrinform.ru/rss/rubric-economy'),
('\u041C\u0438\u0440', 'https://www.ukrinform.ru/rss/rubric-world'),
('\u041E\u0431\u0449\u0435c\u0442\u0432\u043E', 'https://www.ukrinform.ru/rss/rubric-society'),
('\u041A\u0443\u043B\u044C\u0442\u0443\u0440\u0430', 'https://www.ukrinform.ru/rss/rubric-culture'),
('\u0420\u0435\u0433\u0438\u043E\u043D\u044B', 'https://www.ukrinform.ru/rss/rubric-regions'),
('\u041A\u0438\u0435\u0432', 'https://www.ukrinform.ru/rss/rubric-kyiv'),
('\u041A\u0440\u044B\u043C', 'https://www.ukrinform.ru/rss/rubric-crimea'),
('\u0421\u043F\u043E\u0440\u0442', 'https://www.ukrinform.ru/rss/rubric-sports'),
('\u0422\u0435\u0445\u043D\u043E\u043B\u043E\u0433\u0438\u0438', 'https://www.ukrinform.ru/rss/rubric-technology'),
]
English version: 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 UkrInform(BasicNewsRecipe):
title = 'UkrInform (English)'
__author__ = 'bugmen00t'
description = 'State information and news agency of Ukraine.'
publisher = 'Ministry of Culture and Information Policy of Ukraine'
category = 'newspaper'
cover_url = u'https://static.ukrinform.com/photos/2022_05/thumb_files/630_360_1651819943-560.jpg'
language = 'en_UK'
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 = [
('Latest news', 'https://www.ukrinform.net/rss/block-lastnews'),
('War', 'https://www.ukrinform.net/rss/rubric-ato'),
('Politics', 'https://www.ukrinform.net/rss/rubric-polytics'),
('Economy', 'https://www.ukrinform.net/rss/rubric-economy'),
('Defense', 'https://www.ukrinform.net/rss/rubric-defense'),
('Society and Culture', 'https://www.ukrinform.net/rss/rubric-society'),
('Sports', 'https://www.ukrinform.net/rss/rubric-sports'),
('Crime', 'https://www.ukrinform.net/rss/rubric-crime'),
('Accidents and Emergencies', 'https://www.ukrinform.net/rss/rubric-emergencies')
]
Versión en Español: 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 UkrInform(BasicNewsRecipe):
title = 'UkrInform (Espa\u00F1ol)'
__author__ = 'bugmen00t'
description = 'Agencia de noticias nacional de Ucrania, fuente de informaci\u00F3n sobre la vida pol\u00EDtica, econ\u00F3mica, social, cient\u00EDfica, cultural y p\u00FAblica en Ucrania y en el extranjero.'
publisher = 'Ministerio de Cultura y Pol\u00EDtica de Informaci\u00F3n de Ucrania'
category = 'newspaper'
cover_url = u'https://static.ukrinform.com/photos/2022_05/thumb_files/630_360_1651819943-560.jpg'
language = 'es_UK'
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 = [
('\u00DAltimas noticias', 'https://www.ukrinform.es/rss/block-lastnews'),
('Guerra', 'https://www.ukrinform.es/rss/rubric-ato'),
('Pol\u00EDtica', 'https://www.ukrinform.es/rss/rubric-polytics'),
('Econom\u00EDa', 'https://www.ukrinform.es/rss/rubric-economy'),
('Defensa', 'https://www.ukrinform.es/rss/rubric-defense'),
('Sociedad y Cultura', 'https://www.ukrinform.es/rss/rubric-society'),
('Deportes', 'https://www.ukrinform.es/rss/rubric-sports'),
('Crimen', 'https://www.ukrinform.es/rss/rubric-crime'),
('Desastres y emergencias', 'https://www.ukrinform.es/rss/rubric-emergencies')
]
In deutscher Sprache: 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 UkrInform(BasicNewsRecipe):
title = 'UkrInform (Deutsch)'
__author__ = 'bugmen00t'
description = 'Nationale Nachrichtenagentur der Ukraine, eine Informationsquelle \u00FCber das politische, wirtschaftliche, soziale, wissenschaftliche, kulturelle und \u00F6ffentliche Leben in der Ukraine und der Welt.'
publisher = 'Ministerium f\u00FCr Kultur und Informationspolitik der Ukraine'
category = 'newspaper'
cover_url = u'https://static.ukrinform.com/photos/2022_05/thumb_files/630_360_1651819943-560.jpg'
language = 'de_UK'
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 = [
('Aktuelle Nachrichten', 'https://www.ukrinform.de/rss/block-lastnews'),
('Krieg', 'https://www.ukrinform.de/rss/rubric-ato'),
('Politik', 'https://www.ukrinform.de/rss/rubric-polytics'),
('Wirtschaft', 'https://www.ukrinform.de/rss/rubric-economy'),
('Milit\u00E4r', 'https://www.ukrinform.de/rss/rubric-defense'),
('Gesellschaft und Kultur', 'https://www.ukrinform.de/rss/rubric-society'),
('Sport', 'https://www.ukrinform.de/rss/rubric-sports'),
('Kriminalit\u00E4t', 'https://www.ukrinform.de/rss/rubric-crime'),
('Notstand und Notf\u00E4lle', 'https://www.ukrinform.de/rss/rubric-emergencies')
]
Version en français: 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 UkrInform(BasicNewsRecipe):
title = 'UkrInform (Fran\u00E7ais)'
__author__ = 'bugmen00t'
description = 'Agence de presse nationale de l\u0027Ukraine. C\u2019est une source d\u0027informations sur la vie politique, \u00E9conomique, scientifique, culturelle et sociale en Ukraine et \u00E0 l\u0027\u00E9tranger.'
publisher = 'Minist\u00E8re de la culture et de la politique d\u0027information de l\u0027Ukraine'
category = 'newspaper'
cover_url = u'https://static.ukrinform.com/photos/2022_05/thumb_files/630_360_1651819943-560.jpg'
language = 'fr_UK'
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 = [
('Derni\u00E8res infos', 'https://www.ukrinform.fr/rss/block-lastnews'),
('Guerre', 'https://www.ukrinform.fr/rss/rubric-ato'),
('Politique', 'https://www.ukrinform.fr/rss/rubric-polytics'),
('\u00C9conomie', 'https://www.ukrinform.fr/rss/rubric-economy'),
('D\u00E9fense', 'https://www.ukrinform.fr/rss/rubric-defense'),
('Soci\u00E9t\u00E9 et culture', 'https://www.ukrinform.fr/rss/rubric-society'),
('Sport', 'https://www.ukrinform.fr/rss/rubric-sports'),
('Criminalit\u00E9', 'https://www.ukrinform.fr/rss/rubric-crime'),
('Accidents', 'https://www.ukrinform.fr/rss/rubric-emergencies')
]
日本語: 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 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'
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_UK'
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')
]
Wersja polska: 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 UkrInform(BasicNewsRecipe):
title = 'UkrInform (polska)'
__author__ = 'bugmen00t'
description = 'Krajowa agencja informacyjna Ukrainy, \u017Ar\u00F3d\u0142o informacji o \u017Cyciu politycznym, gospodarczym, spo\u0142ecznym, naukowym, kulturalnym i spo\u0142ecznym na Ukrainie i za granic\u0105.'
publisher = 'Ministerstwo Kultury i Polityki Informacyjnej Ukrainy'
category = 'newspaper'
cover_url = u'https://static.ukrinform.com/photos/2022_05/thumb_files/630_360_1651819943-560.jpg'
language = 'pl_UK'
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 = [
('Najnowsze wiadomo\u015Bci', 'https://www.ukrinform.pl/rss/block-lastnews'),
('Wojna', 'https://www.ukrinform.pl/rss/rubric-ato'),
('Polityka', 'https://www.ukrinform.pl/rss/rubric-polytics'),
('Gospodarka', 'https://www.ukrinform.pl/rss/rubric-economy'),
('Obrona', 'https://www.ukrinform.pl/rss/rubric-defense'),
('Spo\u0142ecze\u0144stwo i kultura', 'https://www.ukrinform.pl/rss/rubric-society'),
('Sport', 'https://www.ukrinform.pl/rss/rubric-sports'),
('Wydarzenia kryminalne', 'https://www.ukrinform.pl/rss/rubric-crime'),
('Zdarzenia i bezpiecze\u0144stwo', 'https://www.ukrinform.pl/rss/rubric-emergencies')
]
Last edited by bugmen00t; 08-01-2022 at 07:13 AM. |
|
|
|
|
08-02-2022, 06:03 AM
|
#19 |
|
Connoisseur
Posts: 65
Karma: 100000
Join Date: Aug 2015
Device: Kindle Keyboard + Kindle Voyage WiFi + Kindle PW11 Kids
|
New recipes (part 07 of ??)
Keep on going, this time Ukrainian sources.
NEW MULTI-LANGUAGE RECIPES (OF UKRAINIAN SOURCES) Освіта.ua: education in Ukraine and abroad. Favicon. Fixes needed:
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 Osvita(BasicNewsRecipe):
title = '\u041E\u0441\u0432\u0456\u0442\u0430.ua'
__author__ = 'bugmen00t'
description = '\u0423\u0441\u0435 \u043F\u0440\u043E \u043E\u0441\u0432\u0456\u0442\u0443 \u0432 \u0423\u043A\u0440\u0430\u0457\u043D\u0456 \u0442\u0430 \u0437\u0430 \u043A\u043E\u0440\u0434\u043E\u043D\u043E\u043C: \u0442\u0435\u043C\u0430\u0442\u0438\u0447\u043D\u0438\u0439 \u0440\u0435\u0441\u0443\u0440\u0441, \u043F\u0440\u0438\u0441\u0432\u044F\u0447\u0435\u043D\u0438\u0439 \u043E\u0441\u0432\u0456\u0442\u0456 \u0432 \u0423\u043A\u0440\u0430\u0457\u043D\u0456 \u0442\u0430 \u0437\u0430 \u0457\u0457 \u043C\u0435\u0436\u0430\u043C\u0438, \u0454 \u0430\u043A\u0442\u0443\u0430\u043B\u044C\u043D\u0438\u043C \u0434\u0436\u0435\u0440\u0435\u043B\u043E\u043C \u0456\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0456\u0457 \u0443 \u0446\u0456\u0439 \u0441\u0444\u0435\u0440\u0456.'
publisher = '\u041E\u0441\u0432\u0456\u0442\u0430.ua'
category = 'blog'
cover_url = u'http://osvita.ua/doc/i/Contacts-logo.jpg'
language = 'uk'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 30
remove_tags_before = dict(name='div', attrs={'id': 'body'})
remove_tags_after = dict(name='div', attrs={'id': 'body'})
remove_tags = [
# Unable to fetch images, removing them completely
dict(name='img'),
dict(name='p', attrs={'class': 'info'})
]
feeds = [
('\u041D\u043E\u0432\u0438\u043D\u0438', 'https://osvita.ua/rss/')
]
def print_version(self, url):
return url + 'print'
Russian version: 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 Osvita(BasicNewsRecipe):
title = '\u041E\u0441\u0432\u0456\u0442\u0430.ua'
__author__ = 'bugmen00t'
description = '\u0422\u0435\u043C\u0430\u0442\u0438\u0447\u0435\u0441\u043A\u0438\u0439 \u0440\u0435\u0441\u0443\u0440\u0441, \u043F\u043E\u0441\u0432\u044F\u0449\u0451\u043D\u043D\u044B\u0439 \u043E\u0431\u0440\u0430\u0437\u043E\u0432\u0430\u043D\u0438\u044E \u0432 \u0423\u043A\u0440\u0430\u0438\u043D\u0435 \u0438 \u0437\u0430 \u0440\u0443\u0431\u0435\u0436\u043E\u043C.'
publisher = '\u041E\u0441\u0432\u0456\u0442\u0430.ua'
category = 'blog'
cover_url = u'http://osvita.ua/doc/i/Contacts-logo.jpg'
language = 'ru_uk'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 30
remove_tags_before = dict(name='div', attrs={'id': 'body'})
remove_tags_after = dict(name='div', attrs={'id': 'body'})
remove_tags = [
# Unable to fetch images, removing them completely
dict(name='img'),
dict(name='p', attrs={'class': 'info'})
]
feeds = [
('\u041D\u043E\u0432\u0438\u043D\u0438', 'https://ru.osvita.ua/rss/')
]
def print_version(self, url):
return url + 'print'
ЛІГА.net: business news from Ukraine. Favicon. Ukrainian version: 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 LigaNet(BasicNewsRecipe):
title = '\u041B\u0406\u0413\u0410.net (UA)'
__author__ = 'bugmen00t'
description = '\u0414\u0456\u043B\u043E\u0432\u0438\u0439 \u043D\u043E\u0432\u0438\u043D\u043D\u0438\u0439 \u043F\u043E\u0440\u0442\u0430\u043B'
publisher = 'Ligamedia'
category = 'blog'
cover_url = u'https://www.liga.net/design/images/logo_liga.png'
language = 'uk'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 30
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'id': 'news-text'})
remove_tags = [
dict(name='footer'),
dict(name='div', attrs={'class': 'more-link red'}),
dict(name='div', attrs={'class': 'read-too'}),
dict(name='div', attrs={'class': 'to-send-row'}),
dict(name='div', attrs={'class': 'hint-row'}),
dict(name='div', attrs={'class': 'chronicle-top-eye'}),
dict(name='div', attrs={'class': 'chronicle-top-comm comm-btns'}),
dict(name='div', attrs={'class': 'chronicle-news m-t-30'}),
dict(name='div', attrs={'class': 'right-inner-content'}),
dict(name='div', attrs={'class': 'right-part'}),
dict(name='div', attrs={'class': 'hreflang-link'}),
dict(name='div', attrs={'class': 'vakansii-block-article'}),
dict(name='div', attrs={'class': 'col-12 col-md p-side-10 sp-card-paddings'}),
dict(name='div', attrs={'class': 'social-shares d-flex justify-content-center'}),
dict(name='div', attrs={'class': 'social-shares d-block'}),
dict(name='div', attrs={'class': 'social-likes clearfix hidden-1280 '}),
dict(name='div', attrs={'class': 'soc-item comm-btns'}),
dict(name='div', attrs={'class': 'soc-buttons'}),
dict(name='div', attrs={'class': 'warning m-t-20 d-none d-md-none d-lg-block'}),
dict(name='div', attrs={'id': 'news-list-right'}),
dict(name='div', attrs={'id': 'premium_mobile'}),
dict(name='div', attrs={'id': 'premium2_mobile'}),
dict(name='div', attrs={'class': 'marketing-block'}),
dict(name='span', attrs={'class': 'social-likes__button'}),
dict(name='div', attrs={'class': 'marketing-block'})
]
feeds = [
('\u041D\u043E\u0432\u0438\u043D\u0438: \u0433\u043E\u043B\u043E\u0432\u043D\u0456 \u043C\u0430\u0442\u0435\u0440\u0456\u0430\u043B\u0438', 'https://www.liga.net/newsua/top/rss.xml'),
('\u041D\u043E\u0432\u0438\u043D\u0438: \u0432\u0441\u0456 \u043C\u0430\u0442\u0435\u0440\u0456\u0430\u043B\u0438', 'https://www.liga.net/newsua/all/rss.xml')
]
Russian version: 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 LigaNet(BasicNewsRecipe):
title = '\u041B\u0406\u0413\u0410.net'
__author__ = 'bugmen00t'
description = '\u0414\u0456\u043B\u043E\u0432\u0438\u0439 \u043D\u043E\u0432\u0438\u043D\u043D\u0438\u0439 \u043F\u043E\u0440\u0442\u0430\u043B'
publisher = 'Ligamedia'
category = 'blog'
cover_url = u'https://www.liga.net/design/images/logo_liga.png'
language = 'ru_UK'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 30
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'id': 'news-text'})
remove_tags = [
dict(name='footer'),
dict(name='div', attrs={'class': 'more-link red'}),
dict(name='div', attrs={'class': 'read-too'}),
dict(name='div', attrs={'class': 'to-send-row'}),
dict(name='div', attrs={'class': 'hint-row'}),
dict(name='div', attrs={'class': 'chronicle-top-eye'}),
dict(name='div', attrs={'class': 'chronicle-top-comm comm-btns'}),
dict(name='div', attrs={'class': 'chronicle-news m-t-30'}),
dict(name='div', attrs={'class': 'right-inner-content'}),
dict(name='div', attrs={'class': 'right-part'}),
dict(name='div', attrs={'class': 'hreflang-link'}),
dict(name='div', attrs={'class': 'vakansii-block-article'}),
dict(name='div', attrs={'class': 'col-12 col-md p-side-10 sp-card-paddings'}),
dict(name='div', attrs={'class': 'social-shares d-flex justify-content-center'}),
dict(name='div', attrs={'class': 'social-shares d-block'}),
dict(name='div', attrs={'class': 'social-likes clearfix hidden-1280 '}),
dict(name='div', attrs={'class': 'soc-item comm-btns'}),
dict(name='div', attrs={'class': 'soc-buttons'}),
dict(name='div', attrs={'class': 'warning m-t-20 d-none d-md-none d-lg-block'}),
dict(name='div', attrs={'id': 'news-list-right'}),
dict(name='div', attrs={'id': 'premium_mobile'}),
dict(name='div', attrs={'id': 'premium2_mobile'}),
dict(name='div', attrs={'class': 'marketing-block'}),
dict(name='span', attrs={'class': 'social-likes__button'}),
dict(name='div', attrs={'class': 'marketing-block'})
]
feeds = [
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438: \u0433\u043B\u0430\u0432\u043D\u044B\u0435 \u043C\u0430\u0442\u0435\u0440\u0438\u0430\u043B\u044B', 'https://www.liga.net/news/top/rss.xml'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438: \u043D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://www.liga.net/news/rss.xml'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438: \u0441\u0442\u0430\u0442\u044C\u0438', 'https://www.liga.net/news/articles/rss.xml'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438: \u0438\u043D\u0442\u0435\u0440\u0432\u044C\u044E', 'https://www.liga.net/news/interview/rss.xml'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438: \u043C\u043D\u0435\u043D\u0438\u044F', 'https://www.liga.net/news/opinion/rss.xml'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438: \u0444\u043E\u0442\u043E\u043C\u0430\u0442\u0435\u0440\u0438\u0430\u043B\u044B', 'https://www.liga.net/news/photo/rss.xml'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438: \u043F\u043E\u043B\u0438\u0442\u0438\u043A\u0430', 'https://www.liga.net/news/politics/rss.xml'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438: \u044D\u043A\u043E\u043D\u043E\u043C\u0438\u043A\u0430', 'https://www.liga.net/news/economics/rss.xml'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438: \u043E\u0431\u0449\u0435\u0441\u0442\u0432\u043E', 'https://www.liga.net/news/society/rss.xml'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438: \u043C\u0438\u0440', 'https://www.liga.net/news/world/rss.xml'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438: \u0441\u0442\u043E\u043B\u0438\u0446\u0430', 'https://www.liga.net/news/capital/rss.xml'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438: \u0441\u043F\u043E\u0440\u0442', 'https://www.liga.net/news/sport/rss.xml'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438: \u0437\u0434\u043E\u0440\u043E\u0432\u044C\u0435', 'https://www.liga.net/news/health/rss.xml'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438: \u043A\u0443\u043B\u044C\u0442\u0443\u0440\u0430', 'https://www.liga.net/news/culture/rss.xml'),
('\u0412\u0441\u0435 \u043C\u043D\u0435\u043D\u0438\u044F', 'https://www.liga.net/opinion/rss.xml'),
('\u0411\u0438\u0437\u043D\u0435\u0441: \u0433\u043B\u0430\u0432\u043D\u044B\u0435 \u043C\u0430\u0442\u0435\u0440\u0438\u0430\u043B\u044B', 'https://www.liga.net/biz/top/rss.xml'),
('\u0411\u0438\u0437\u043D\u0435\u0441: \u043D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://www.liga.net/biz/news/rss.xml'),
('\u0411\u0438\u0437\u043D\u0435\u0441: \u0441\u0442\u0430\u0442\u044C\u0438', 'https://www.liga.net/biz/articles/rss.xml'),
('\u0411\u0438\u0437\u043D\u0435\u0441: \u0438\u043D\u0442\u0435\u0440\u0432\u044C\u044E', 'https://www.liga.net/biz/interview/rss.xml'),
('\u0411\u0438\u0437\u043D\u0435\u0441: \u043C\u043D\u0435\u043D\u0438\u044F', 'https://www.liga.net/biz/opinion/rss.xml'),
('\u0411\u0438\u0437\u043D\u0435\u0441: \u0444\u043E\u0442\u043E\u043C\u0430\u0442\u0435\u0440\u0438\u0430\u043B\u044B', 'https://www.liga.net/biz/photo/rss.xml'),
('\u0424\u0438\u043D\u0430\u043D\u0441\u044B: \u0433\u043B\u0430\u0432\u043D\u044B\u0435 \u043C\u0430\u0442\u0435\u0440\u0438\u0430\u043B\u044B', 'https://www.liga.net/fin/export/top.xml'),
('\u0424\u0438\u043D\u0430\u043D\u0441\u044B: \u043C\u043D\u0435\u043D\u0438\u044F', 'https://www.liga.net/fin/opinion/rss.xml'),
('\u0424\u0438\u043D\u0430\u043D\u0441\u044B: \u0431\u0430\u043D\u043A\u0438', 'https://www.liga.net/fin/export/bank.xml'),
('\u0424\u0438\u043D\u0430\u043D\u0441\u044B: \u0441\u0442\u0440\u0430\u0445\u043E\u0432\u0430\u043D\u0438\u0435', 'https://www.liga.net/fin/export/insurance.xml'),
('\u0424\u0438\u043D\u0430\u043D\u0441\u044B: \u043A\u0440\u0438\u043F\u0442\u043E\u044D\u043A\u043E\u043D\u043E\u043C\u0438\u043A\u0430', 'https://www.liga.net/fin/crypto/rss.xml'),
('\u0424\u0438\u043D\u0430\u043D\u0441\u044B: \u0444\u043E\u043D\u0434\u044B', 'https://www.liga.net/fin/export/funds.xml'),
('Tech: \u0433\u043B\u0430\u0432\u043D\u044B\u0435 \u043C\u0430\u0442\u0435\u0440\u0438\u0430\u043B\u044B', 'https://www.liga.net/tech/top/rss.xml'),
('Tech: \u0442\u0435\u0445\u043D\u043E\u043B\u043E\u0433\u0438\u0438', 'https://www.liga.net/tech/technology/rss.xml'),
('Tech: \u0442\u0435\u043B\u0435\u043A\u043E\u043C', 'https://www.liga.net/tech/telecom/rss.xml'),
('Tech: \u0433\u0430\u0434\u0436\u0435\u0442\u044B', 'https://www.liga.net/tech/gadgets/rss.xml'),
('Tech: \u0441\u0432\u043E\u0439 \u0431\u0438\u0437\u043D\u0435\u0441', 'https://www.liga.net/tech/own-business/rss.xml'),
('Tech: \u0431\u0430\u0442\u0442\u043B\u044B', 'https://www.liga.net/tech/battles/rss.xml'),
('\u0411\u043B\u043E\u0433\u0438: \u0432\u0441\u0435 \u043C\u0430\u0442\u0435\u0440\u0438\u0430\u043B\u044B', 'https://www.liga.net/rss/blog.xml')
]
UNN: Ukrainian news agency, with emphasis on politics, social problems and economics. Favicon. Ukrainian version: 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 UNN(BasicNewsRecipe):
title = '\u0423\u043A\u0440\u0430\u0457\u043D\u0441\u044C\u043A\u0456 \u041D\u0430\u0446\u0456\u043E\u043D\u0430\u043B\u044C\u043D\u0456 \u041D\u043E\u0432\u0438\u043D\u0438'
__author__ = 'bugmen00t'
description = '\u0423\u041D\u041D: \u0423\u043A\u0440\u0430\u0457\u043D\u0441\u044C\u043A\u0456 \u041D\u0430\u0446\u0456\u043E\u043D\u0430\u043B\u044C\u043D\u0456 \u041D\u043E\u0432\u0438\u043D\u0438'
publisher = '\u0406\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0456\u0439\u043D\u0435 \u0430\u0433\u0435\u043D\u0442\u0441\u0442\u0432\u043E \u00AB\u0423\u043A\u0440\u0430\u0457\u043D\u0441\u044C\u043A\u0456 \u041D\u0430\u0446\u0456\u043E\u043D\u0430\u043B\u044C\u043D\u0456 \u041D\u043E\u0432\u0438\u043D\u0438\u00BB'
category = 'newspaper'
cover_url = u'https://pechersk.kyivcity.gov.ua/done_img/b/11289.jpg'
language = 'uk'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 50
remove_tags_before = dict(name='span', attrs={'itemprop': 'datePublished'})
remove_tags_after = dict(name='div', attrs={'class': 'b-news-full'})
remove_tags = [
dict(name='span', attrs={'class': 'view'}),
dict(name='div', attrs={'class': 'b-news-tags'}),
dict(name='div', attrs={'class': 'b-news-source'}),
dict(name='div', attrs={'class': 'b-news-footer'}),
dict(name='div', attrs={'class': 'b-notice-msg'})
]
feeds = [
('\u041E\u043F\u0435\u0440\u0430\u0442\u0438\u0432\u043D\u0456 \u043D\u043E\u0432\u0438\u043D\u0438', 'https://www.unn.com.ua/rss/news_uk.xml'),
('\u041F\u0443\u0431\u043B\u0456\u043A\u0430\u0446\u0456\u0457', 'https://www.unn.com.ua/rss/publication_uk.xml'),
('\u0415\u043A\u0441\u043A\u043B\u044E\u0437\u0438\u0432\u043D\u0456 \u043D\u043E\u0432\u0438\u043D\u0438', 'https://www.unn.com.ua/rss/exclusive_uk.xml'),
('\u041F\u043E\u043B\u0456\u0442\u0438\u043A\u0430', 'https://www.unn.com.ua/rss/news_politics_uk.xml'),
('\u0415\u043A\u043E\u043D\u043E\u043C\u0456\u043A\u0430', 'https://www.unn.com.ua/rss/news_economics_uk.xml'),
('\u0410\u0433\u0440\u043E\u043D\u043E\u0432\u0438\u043D\u0438', 'https://www.unn.com.ua/rss/news_agronews_uk.xml'),
('\u041E\u0434\u0435\u0441\u0430', 'https://www.unn.com.ua/rss/news_odesa_uk.xml'),
('\u041A\u0438\u0457\u0432', 'https://www.unn.com.ua/rss/news_kiev_uk.xml'),
('COVID-19', 'https://www.unn.com.ua/rss/news_covid19_uk.xml'),
('\u0421\u0443\u0441\u043F\u0456\u043B\u044C\u0441\u0442\u0432\u043E', 'https://www.unn.com.ua/rss/news_society_uk.xml'),
('\u0417\u0434\u043E\u0440\u043E\u0432\u0027\u044F', 'https://www.unn.com.ua/rss/news_health_uk.xml'),
('\u0412\u0456\u0439\u043D\u0430', 'https://www.unn.com.ua/rss/news_war_uk.xml'),
('\u041A\u0440\u0438\u043C\u0456\u043D\u0430\u043B \u0442\u0430 \u041D\u041F', 'https://www.unn.com.ua/rss/news_criminal_uk.xml'),
('\u0423\u041D\u041D Lite', 'https://www.unn.com.ua/rss/news_lite_uk.xml'),
('\u041D\u043E\u0432\u0438\u043D\u0438 \u0421\u0432\u0456\u0442\u0443', 'https://www.unn.com.ua/rss/news_world_uk.xml'),
('\u0422\u0435\u0445\u043D\u043E\u043B\u043E\u0433\u0456\u0457', 'https://www.unn.com.ua/rss/news_tech_uk.xml'),
('\u0421\u043F\u043E\u0440\u0442', 'https://www.unn.com.ua/rss/news_sport_uk.xml'),
('\u041A\u0443\u043B\u044C\u0442\u0443\u0440\u0430', 'https://www.unn.com.ua/rss/news_culture_uk.xml'),
('\u041C\u0443\u043B\u044C\u0442\u0438\u043C\u0435\u0434\u0456\u0430', 'https://www.unn.com.ua/rss/news_media_uk.xml')
]
def print_version(self, url):
return url + '?_part=main&_print=1'
Russian version: 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 UNN(BasicNewsRecipe):
title = '\u0423\u043A\u0440\u0430\u0438\u043D\u0441\u043A\u0438\u0435 \u041D\u0430\u0446\u0438\u043E\u043D\u0430\u043B\u044C\u043D\u044B\u0435 \u041D\u043E\u0432\u043E\u0441\u0442\u0438'
__author__ = 'bugmen00t'
description = '\u0423\u041D\u041D: \u0423\u043A\u0440\u0430\u0438\u043D\u0441\u043A\u0438\u0435 \u041D\u0430\u0446\u0438\u043E\u043D\u0430\u043B\u044C\u043D\u044B\u0435 \u041D\u043E\u0432\u043E\u0441\u0442\u0438'
publisher = '\u0406\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0456\u0439\u043D\u0435 \u0430\u0433\u0435\u043D\u0442\u0441\u0442\u0432\u043E \u00AB\u0423\u043A\u0440\u0430\u0457\u043D\u0441\u044C\u043A\u0456 \u041D\u0430\u0446\u0456\u043E\u043D\u0430\u043B\u044C\u043D\u0456 \u041D\u043E\u0432\u0438\u043D\u0438\u00BB'
category = 'newspaper'
cover_url = u'https://argentum.ua/uploads/portfolio/2012/c043e0e18fd9f89df5fb421ab28cf609197011c2.png'
language = 'ru_UK'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 50
remove_tags_before = dict(name='span', attrs={'itemprop': 'datePublished'})
remove_tags_after = dict(name='div', attrs={'class': 'b-news-full'})
remove_tags = [
dict(name='span', attrs={'class': 'view'}),
dict(name='div', attrs={'class': 'b-news-tags'}),
dict(name='div', attrs={'class': 'b-news-source'}),
dict(name='div', attrs={'class': 'b-news-footer'}),
dict(name='div', attrs={'class': 'b-notice-msg'})
]
feeds = [
('\u041E\u043F\u0435\u0440\u0430\u0442\u0438\u0432\u043D\u044B\u0435 \u043D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://www.unn.com.ua/rss/news_ru.xml'),
('\u041F\u0443\u0431\u043B\u0438\u043A\u0430\u0446\u0438\u0438', 'https://www.unn.com.ua/rss/publication_ru.xml'),
('\u042D\u043A\u0441\u043A\u043B\u044E\u0437\u0438\u0432\u043D\u044B\u0435 \u043D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://www.unn.com.ua/rss/exclusive_ru.xml'),
('\u041F\u043E\u043B\u0438\u0442\u0438\u043A\u0430', 'https://www.unn.com.ua/rss/news_politics_ru.xml'),
('\u042D\u043A\u043E\u043D\u043E\u043C\u0438\u043A\u0430', 'https://www.unn.com.ua/rss/news_economics_ru.xml'),
('\u0410\u0433\u0440\u043E\u043D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://www.unn.com.ua/rss/news_agronews_ru.xml'),
('\u041E\u0434\u0435\u0441\u0441\u0430', 'https://www.unn.com.ua/rss/news_odesa_ru.xml'),
('\u041A\u0438\u0435\u0432', 'https://www.unn.com.ua/rss/news_kiev_ru.xml'),
('COVID-19', 'https://www.unn.com.ua/rss/news_covid19_ru.xml'),
('\u041E\u0431\u0449\u0435\u0441\u0442\u0432\u043E', 'https://www.unn.com.ua/rss/news_society_ru.xml'),
('\u0417\u0434\u043E\u0440\u043E\u0432\u044C\u0435', 'https://www.unn.com.ua/rss/news_health_ru.xml'),
('\u0412\u043E\u0439\u043D\u0430', 'https://www.unn.com.ua/rss/news_war_ru.xml'),
('\u041A\u0440\u0438\u043C\u0438\u043D\u0430\u043B \u0438 \u0427\u041F', 'https://www.unn.com.ua/rss/news_criminal_ru.xml'),
('\u0423\u041D\u041D Lite', 'https://www.unn.com.ua/rss/news_lite_ru.xml'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438 \u041C\u0438\u0440\u0430', 'https://www.unn.com.ua/rss/news_world_ru.xml'),
('\u0422\u0435\u0445\u043D\u043E\u043B\u043E\u0433\u0438\u0438', 'https://www.unn.com.ua/rss/news_tech_ru.xml'),
('\u0421\u043F\u043E\u0440\u0442', 'https://www.unn.com.ua/rss/news_sport_ru.xml'),
('\u041A\u0443\u043B\u044C\u0442\u0443\u0440\u0430', 'https://www.unn.com.ua/rss/news_culture_ru.xml'),
('\u041C\u0443\u043B\u044C\u0442\u0438\u043C\u0435\u0434\u0438\u0430', 'https://www.unn.com.ua/rss/news_media_ru.xml')
]
def print_version(self, url):
return url + '?_part=main&_print=1'
|
|
|
|
|
08-04-2022, 06:24 AM
|
#20 |
|
Connoisseur
Posts: 65
Karma: 100000
Join Date: Aug 2015
Device: Kindle Keyboard + Kindle Voyage WiFi + Kindle PW11 Kids
|
New recipes (part 08 of ??)
NEW RUSSIAN SOURCES Тайга.инфо: Siberian regional news portal. 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 Tayga(BasicNewsRecipe):
title = '\u0422\u0430\u0439\u0433\u0430.\u0438\u043D\u0444\u043E'
__author__ = 'bugmen00t'
description = '\u0418\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u043E\u043D\u043D\u043E-\u0430\u043D\u0430\u043B\u0438\u0442\u0438\u0447\u0435\u0441\u043A\u043E\u0435 \u0438\u043D\u0442\u0435\u0440\u043D\u0435\u0442-\u0438\u0437\u0434\u0430\u043D\u0438\u0435 \u043E \u043F\u043E\u043B\u0438\u0442\u0438\u0447\u0435\u0441\u043A\u0438\u0445 \u0438 \u044D\u043A\u043E\u043D\u043E\u043C\u0438\u0447\u0435\u0441\u043A\u0438\u0445 \u0441\u043E\u0431\u044B\u0442\u0438\u044F\u0445 \u0421\u0438\u0431\u0438\u0440\u0441\u043A\u043E\u0433\u043E \u0444\u0435\u0434\u0435\u0440\u0430\u043B\u044C\u043D\u043E\u0433\u043E \u043E\u043A\u0440\u0443\u0433\u0430.'
publisher = '\u0422\u0430\u0439\u0433\u0430.\u0438\u043D\u0444\u043E'
category = 'blog'
cover_url = u'https://tayga.info/design/logo.svg'
language = 'ru'
no_stylesheets = True
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 60
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': 'news_content'})
remove_tags = [
dict(name='p', attrs={'class': 't_left'})
]
feeds = [
('\u0422\u0430\u0439\u0433\u0430.\u0438\u043D\u0444\u043E', 'https://tayga.info/rss')
]
Новая вкладка: blog about life in Russian regions. Favicon. Fixes needed:
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 NewTab(BasicNewsRecipe):
title = '\u041D\u043E\u0432\u0430\u044F \u0432\u043A\u043B\u0430\u0434\u043A\u0430'
__author__ = 'bugmen00t'
description = '\u041F\u043B\u043E\u0449\u0430\u0434\u043A\u0430 \u0434\u043B\u044F \u043F\u0443\u0431\u043B\u0438\u043A\u0430\u0446\u0438\u0438 \u0440\u0435\u043F\u043E\u0440\u0442\u0430\u0436\u0435\u0439 \u0438 \u0437\u0430\u043C\u0435\u0442\u043E\u043A \u043E \u0442\u043E\u043C, \u043A\u0430\u043A \u043C\u0435\u043D\u044F\u044E\u0442\u0441\u044F \u0440\u0435\u0433\u0438\u043E\u043D\u044B \u0420\u043E\u0441\u0441\u0438\u0438 \u043F\u043E\u0441\u043B\u0435 24 \u0444\u0435\u0432\u0440\u0430\u043B\u044F 2022 \u0433\u043E\u0434\u0430.'
publisher = '\u041C\u0438\u0445\u0430\u0438\u043B \u0414\u0430\u043D\u0438\u043B\u043E\u0432\u0438\u0447'
category = 'blog'
cover_url = u'https://static.tildacdn.com/tild3765-3961-4337-b366-323437626331/thenewtab-sn.jpg'
language = 'ru'
no_stylesheets = True
remove_javascript = False
auto_cleanup = False
oldest_article = 30
max_articles_per_feed = 20
remove_tags_before = dict(name='h1')
remove_tags = [
dict(name='div', attrs={'class': 't-popup'}),
dict(name='div', attrs={'class': 't185'}),
dict(name='div', attrs={'class': 't403'}),
dict(name='div', attrs={'class': 't404'}),
dict(name='div', attrs={'class': 't134'}),
]
feeds = [
('\u041D\u043E\u0432\u0430\u044F \u0432\u043A\u043B\u0430\u0434\u043A\u0430', 'https://thenewtab.io/rss.xml')
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-original': True}):
img['src'] = img['data-original']
return soup
Сноб: bimonthly magazine about art, culture, science and society. Favicon. Fixes needed:
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 Snob(BasicNewsRecipe):
title = '\u0421\u043D\u043E\u0431'
__author__ = 'bugmen00t'
description = '\u0414\u0438\u0441\u043A\u0443\u0441\u0441\u0438\u043E\u043D\u043D\u043E\u0435, \u0438\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u043E\u043D\u043D\u043E\u0435 \u0438 \u043E\u0431\u0449\u0435\u0441\u0442\u0432\u0435\u043D\u043D\u043E\u0435 \u043F\u0440\u043E\u0441\u0442\u0440\u0430\u043D\u0441\u0442\u0432\u043E \u0434\u043B\u044F \u043B\u044E\u0434\u0435\u0439, \u043A\u043E\u0442\u043E\u0440\u044B\u0435 \u0436\u0438\u0432\u0443\u0442 \u0432 \u0440\u0430\u0437\u043D\u044B\u0445 \u0441\u0442\u0440\u0430\u043D\u0430\u0445, \u0433\u043E\u0432\u043E\u0440\u044F\u0442 \u043D\u0430 \u0440\u0430\u0437\u043D\u044B\u0445 \u044F\u0437\u044B\u043A\u0430\u0445, \u043D\u043E \u0434\u0443\u043C\u0430\u044E\u0442 \u043F\u043E-\u0440\u0443\u0441\u0441\u043A\u0438.'
publisher = '\u041E\u041E\u041E \u00AB\u0421\u043D\u043E\u0431 \u041C\u0435\u0434\u0438\u0430\u00BB'
category = 'magazine'
cover_url = u'https://snob.ru/indoc/tilda/995317/images/tild3233-6631-4664-b663-353636373235__e3057a5fee932ada1aaf.png'
language = 'ru'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 5
max_articles_per_feed = 50
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='article')
remove_tags = [
dict(name='div', attrs={'class': 'entry__tags'}),
dict(name='div', attrs={'class': 'entry__likes'})
]
feeds = [
('\u0421\u043D\u043E\u0431', 'https://snob.ru/rss/')
]
def get_article_url(self, article):
link = article.get('link', None)
return link.split('?utm')[0]
Новый Калининград: regional news of Kaliningrad city and Kaliningrad district. 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 NewKaliningrad(BasicNewsRecipe):
title = '\u041D\u043E\u0432\u044B\u0439 \u041A\u0430\u043B\u0438\u043D\u0438\u043D\u0433\u0440\u0430\u0434'
__author__ = 'bugmen00t'
description = '\u0420\u0435\u0433\u0438\u043E\u043D\u0430\u043B\u044C\u043D\u044B\u0439 \u0438\u043D\u0442\u0435\u0440\u043D\u0435\u0442-\u043F\u043E\u0440\u0442\u0430\u043B \u041A\u0430\u043B\u0438\u043D\u0438\u043D\u0433\u0440\u0430\u0434\u0441\u043A\u043E\u0439 \u043E\u0431\u043B\u0430\u0441\u0442\u0438 \u0438 \u0433\u043E\u0440\u043E\u0434\u0430 \u041A\u0430\u043B\u0438\u043D\u0438\u043D\u0433\u0440\u0430\u0434\u0430.'
publisher = '\u0417\u0410\u041E "\u0422\u0432\u0438\u043A \u041C\u0430\u0440\u043A\u0435\u0442\u0438\u043D\u0433"'
category = 'news'
cover_url = u'https://www.newkaliningrad.ru/images/logo.gif'
language = 'ru'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 3
max_articles_per_feed = 100
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': 'content'})
remove_tags = [
dict(name='div', attrs={'class': 'continue-box'})
]
feeds = [
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://www.newkaliningrad.ru/news/rss.xml')
]
NEW UKRAINIAN SOURCES РБК-Украина: business and finances news agency. Favicon replacemet. Fixes needed:
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 RBCUA(BasicNewsRecipe):
title = '\u0420\u0411\u041A-\u0423\u043A\u0440\u0430\u0457\u043D\u0430'
__author__ = 'bugmen00t'
description = '\u0423\u043A\u0440\u0430\u0457\u043D\u0441\u044C\u043A\u0435 \u0456\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0456\u0439\u043D\u0435 \u0430\u0433\u0435\u043D\u0442\u0441\u0442\u0432\u043E.'
publisher = '\u0422\u041E\u0412 \u00AB\u042E\u0431\u0456\u0442\u0456 \u041C\u0435\u0434\u0456\u0430\u00BB'
category = 'news'
cover_url = u'https://www.rbc.ua/static/img/r/b/rbc_pic_best_news_650x410_2_650x410_1_650x410_1_480x270.jpg'
language = 'uk'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 3
max_articles_per_feed = 20
remove_tags_before = dict(name='article')
remove_tags_after = dict(name='article')
remove_tags = [
dict(name='span', attrs={'class': 'lang-publication'}),
dict(name='div', attrs={'class': 'share'}),
dict(name='ins'),
dict(name='div', attrs={'class': 'read-in-google'}),
dict(name='div', attrs={'class': 'intext-tags'})
]
feeds = [
('\u0420\u0411\u041A', 'https://www.rbc.ua/static/rss/all.ukr.rss.xml')
]
Russian version: 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 RBCUA(BasicNewsRecipe):
title = '\u0420\u0411\u041A-\u0423\u043A\u0440\u0430\u0438\u043D\u0430'
__author__ = 'bugmen00t'
description = '\u0423\u043A\u0440\u0430\u0438\u043D\u0441\u043A\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, \u0441\u043F\u0435\u0446\u0438\u0430\u043B\u0438\u0437\u0438\u0440\u0443\u044E\u0449\u0435\u0435\u0441\u044F \u043D\u0430 \u0444\u0438\u043D\u0430\u043D\u0441\u043E\u0432\u044B\u0445, \u044D\u043A\u043E\u043D\u043E\u043C\u0438\u0447\u0435\u0441\u043A\u0438\u0445 \u0438 \u043F\u043E\u043B\u0438\u0442\u0438\u0447\u0435\u0441\u043A\u0438\u0445 \u043D\u043E\u0432\u043E\u0441\u0442\u044F\u0445 \u0423\u043A\u0440\u0430\u0438\u043D\u044B.'
publisher = '\u041E\u041E\u041E \u00AB\u042E\u0431\u0438\u0442\u0438 \u041C\u0435\u0434\u0438\u0430\u00BB'
category = 'news'
cover_url = u'https://www.rbc.ua/static/common/imgs/logo650.jpg'
language = 'ru_UK'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 3
max_articles_per_feed = 20
remove_tags_before = dict(name='article')
remove_tags_after = dict(name='article')
remove_tags = [
dict(name='span', attrs={'class': 'lang-publication'}),
dict(name='div', attrs={'class': 'share'}),
dict(name='ins'),
dict(name='div', attrs={'class': 'read-in-google'}),
dict(name='div', attrs={'class': 'intext-tags'})
]
feeds = [
('\u0420\u0411\u041A', 'https://www.rbc.ua/static/rss/all.rus.rss.xml')
]
НВ: information and news resource Favicon. Fixes needed:
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 NV(BasicNewsRecipe):
title = '\u041D\u0412 (\u00AB\u041D\u043E\u0432\u0438\u0439 \u0427\u0430\u0441\u00BB)'
__author__ = 'bugmen00t'
description = '\u0429\u043E\u0442\u0438\u0436\u043D\u0435\u0432\u0438\u0439 \u0441\u0443\u0441\u043F\u0456\u043B\u044C\u043D\u043E-\u043F\u043E\u043B\u0456\u0442\u0438\u0447\u043D\u0438\u0439 \u0456\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0456\u0439\u043D\u043E-\u043D\u043E\u0432\u0438\u043D\u043D\u0438\u0439 \u0441\u0430\u0439\u0442.'
publisher = '\u0422\u041E\u0412 \u00AB\u0412\u0438\u0434\u0430\u0432\u043D\u0438\u0447\u0438\u0439 \u0434\u0456\u043C \u00AB\u041C\u0435\u0434\u0456\u0430-\u0414\u041A\u00BB'
category = 'magazine'
cover_url = u'https://static.nv.ua/shared/system/Article/posters/002/467/576/600x300/272ab80cd01e4022dcb4c691c9073e97.jpg'
language = 'uk'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 40
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='article')
remove_tags = [
dict(name='div', attrs={'class': 'article__content__footer'}),
dict(name='div', attrs={'class': 'article__head__additional_views'}),
dict(name='div', attrs={'class': 'show_two_positions '}),
dict(name='div', attrs={'class': 'media__also__news'}),
dict(name='div', attrs={'class': 'media__also__news_link'}),
dict(name='blockquote', attrs={'class': 'code'}),
dict(name='section', attrs={'class': 'article-share'}),
dict(name='div', attrs={'class': 'nts-video-wrapper'}),
dict(name='footer'),
dict(name='div', attrs={'class': 'longread_tags'}),
dict(name='div', attrs={'class': 'col-md-6 col-lg-3'}),
dict(name='div', attrs={'class': 'copyright'}),
dict(name='div', attrs={'class': 'media__video'}),
dict(name='div', attrs={'class': 'media__embed'})
]
feeds = [
('\u0412\u0441\u0456 \u043D\u043E\u0432\u0438\u043D\u0438', 'https://nv.ua/ukr/rss/all.xml'),
('\u0423\u043A\u0440\u0430\u0457\u043D\u0430', 'https://nv.ua/ukr/rss/2283.xml'),
('\u0421\u0432\u0456\u0442', 'https://nv.ua/ukr/rss/2318.xml'),
('\u041F\u043E\u0433\u043B\u044F\u0434\u0438', 'https://nv.ua/ukr/rss/2671.xml'),
('\u041A\u0438\u0457\u0432', 'https://nv.ua/ukr/rss/108.xml'),
('\u0410\u0440\u0442', 'https://nv.ua/ukr/rss/52.xml'),
('\u0414\u043E\u0441\u044C\u0454', 'https://nv.ua/ukr/rss/230.xml'),
('\u0411\u0456\u0437\u043D\u0435\u0441', 'https://nv.ua/ukr/rss/2292.xml'),
('\u041B\u043E\u043D\u0433\u0440\u0456\u0434\u0438', 'https://nv.ua/ukr/rss/2790.xml'),
('\u041A\u0430\u0440\u0442\u043A\u0438', 'https://nv.ua/ukr/rss/48.xml'),
('\u0422\u0435\u0445\u043D\u043E', 'https://nv.ua/ukr/rss/2346.xml'),
('\u0420\u0435\u0433\u0456\u043E\u043D\u0438', 'https://nv.ua/ukr/rss/231.xml'),
('\u0410\u0432\u0442\u043E', 'https://nv.ua/ukr/rss/154.xml'),
('Life', 'https://nv.ua/ukr/rss/2325.xml'),
('\u0417\u0434\u043E\u0440\u043E\u0432\u0027\u044F', 'https://nv.ua/ukr/rss/90.xml'),
('\u0421\u043F\u043E\u0440\u0442', 'https://nv.ua/ukr/rss/2371.xml'),
('\u0410\u0437\u0430\u0440\u0442', 'https://nv.ua/ukr/rss/178.xml'),
('\u0428\u043E\u043F\u0456\u043D\u0433', 'https://nv.ua/ukr/rss/131.xml'),
('LOL', 'https://nv.ua/ukr/rss/2365.xml'),
('\u041F\u0440\u0438\u0445\u043E\u0432\u0430\u043D\u0438\u0439 \u0440\u043E\u0437\u0434\u0456\u043B', 'https://nv.ua/ukr/rss/118.xml'),
('\u0424\u041E\u0422\u041E', 'https://nv.ua/ukr/rss/2384.xml'),
('\u0420\u0430\u0434\u0456\u043E \u041D\u0412', 'https://nv.ua/ukr/rss/3050.xml'),
('BBC', 'https://nv.ua/ukr/rss/2836.xml'),
('\u0426\u0438\u0442\u0430\u0442\u0430 \u0434\u043D\u044F', 'https://nv.ua/ukr/rss/2672.xml'),
('\u0414\u043D\u0456\u043F\u0440\u043E', 'https://nv.ua/ukr/rss/232.xml'),
('\u041A\u0440\u0443\u043F\u043D\u0438\u043C \u043F\u043B\u0430\u043D\u043E\u043C', 'https://nv.ua/ukr/rss/2383.xml'),
('\u0411\u043B\u043E\u0433 \u041D\u0412', 'https://nv.ua/ukr/rss/225.xml'),
('\u041B\u044C\u0432\u0456\u0432', 'https://nv.ua/ukr/rss/233.xml'),
('\u041E\u0434\u0435\u0441\u0430', 'https://nv.ua/ukr/rss/234.xml'),
('\u0425\u0430\u0440\u043A\u0456\u0432', 'https://nv.ua/ukr/rss/235.xml'),
('\u0410\u043D\u0435\u043A\u0434\u043E\u0442\u0438', 'https://nv.ua/ukr/rss/2765.xml'),
('\u0415\u043A\u0441\u043A\u043B\u044E\u0437\u0438\u0432\u0438 \u041D\u0412', 'https://nv.ua/ukr/rss/119.xml')
]
Russian version: 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 NV(BasicNewsRecipe):
title = '\u041D\u0412 (\u00AB\u041D\u043E\u0432\u043E\u0435 \u0432\u0440\u0435\u043C\u044F\u00BB)'
__author__ = 'bugmen00t'
description = '\u0415\u0436\u0435\u043D\u0435\u0434\u0435\u043B\u044C\u043D\u044B\u0439 \u043E\u0431\u0449\u0435\u0441\u0442\u0432\u0435\u043D\u043D\u043E-\u043F\u043E\u043B\u0438\u0442\u0438\u0447\u0435\u0441\u043A\u0438\u0439 \u0438 \u0438\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u043E\u043D\u043D\u043E-\u043D\u043E\u0432\u043E\u0441\u0442\u043D\u043E\u0439 \u0438\u043D\u0442\u0435\u0440\u043D\u0435\u0442-\u0440\u0435\u0441\u0443\u0440\u0441.'
publisher = '\u041E\u041E\u041E \u00AB\u0418\u0437\u0434\u0430\u0442\u0435\u043B\u044C\u0441\u043A\u0438\u0439 \u0434\u043E\u043C \u00AB\u041C\u0435\u0434\u0438\u0430-\u0414\u041A\u00BB'
category = 'magazine'
cover_url = u'https://yes-ukraine.org/imglib/_newimage/Yalta-annual-meeting/11th-yalta-annual-meeting/partners/media-partneri/nv_logo.png'
language = 'ru_UK'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 40
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='article')
remove_tags = [
dict(name='div', attrs={'class': 'article__content__footer'}),
dict(name='div', attrs={'class': 'article__head__additional_views'}),
dict(name='div', attrs={'class': 'show_two_positions '}),
dict(name='div', attrs={'class': 'media__also__news'}),
dict(name='div', attrs={'class': 'media__also__news_link'}),
dict(name='blockquote', attrs={'class': 'code'}),
dict(name='section', attrs={'class': 'article-share'}),
dict(name='div', attrs={'class': 'nts-video-wrapper'}),
dict(name='footer'),
dict(name='div', attrs={'class': 'longread_tags'}),
dict(name='div', attrs={'class': 'col-md-6 col-lg-3'}),
dict(name='div', attrs={'class': 'copyright'}),
dict(name='div', attrs={'class': 'media__video'}),
dict(name='div', attrs={'class': 'media__embed'})
]
feeds = [
('\u0412\u0441\u0435 \u043D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://nv.ua/rss/all.xml'),
('\u0423\u043A\u0440\u0430\u0438\u043D\u0430', 'https://nv.ua/rss/2283.xml'),
('\u041C\u0438\u0440', 'https://nv.ua/rss/2318.xml'),
('\u041C\u043D\u0435\u043D\u0438\u044F', 'https://nv.ua/rss/2671.xml'),
('\u041A\u0438\u0435\u0432', 'https://nv.ua/rss/108.xml'),
('\u0410\u0440\u0442', 'https://nv.ua/rss/52.xml'),
('\u0414\u043E\u0441\u044C\u0435', 'https://nv.ua/rss/230.xml'),
('\u0411\u0438\u0437\u043D\u0435\u0441', 'https://nv.ua/rss/2292.xml'),
('\u041B\u043E\u043D\u0433\u0440\u0438\u0434\u044B', 'https://nv.ua/rss/2790.xml'),
('\u041A\u0430\u0440\u0442\u043E\u0447\u043A\u0438', 'https://nv.ua/rss/48.xml'),
('\u0422\u0435\u0445\u043D\u043E', 'https://nv.ua/rss/2346.xml'),
('\u0420\u0435\u0433\u0438\u043E\u043D\u044B', 'https://nv.ua/rss/231.xml'),
('\u0410\u0432\u0442\u043E', 'https://nv.ua/rss/154.xml'),
('Life', 'https://nv.ua/rss/2325.xml'),
('\u0417\u0434\u043E\u0440\u043E\u0432\u044C\u0435', 'https://nv.ua/rss/90.xml'),
('\u0421\u043F\u043E\u0440\u0442', 'https://nv.ua/rss/2371.xml'),
('\u0410\u0437\u0430\u0440\u0442', 'https://nv.ua/rss/178.xml'),
('\u0428\u043E\u043F\u043F\u0438\u043D\u0433', 'https://nv.ua/rss/131.xml'),
('LOL', 'https://nv.ua/rss/2365.xml'),
('\u0421\u043A\u0440\u044B\u0442\u044B\u0439 \u0440\u0430\u0437\u0434\u0435\u043B', 'https://nv.ua/rss/118.xml'),
('\u0424\u041E\u0422\u041E', 'https://nv.ua/rss/2384.xml'),
('\u0420\u0430\u0434\u0438\u043E \u041D\u0412', 'https://nv.ua/rss/3050.xml'),
('BBC', 'https://nv.ua/rss/2836.xml'),
('\u0426\u0438\u0442\u0430\u0442\u0430 \u0434\u043D\u044F', 'https://nv.ua/rss/2672.xml'),
('\u0414\u043D\u0435\u043F\u0440', 'https://nv.ua/rss/232.xml'),
('\u041A\u0440\u0443\u043F\u043D\u044B\u043C \u043F\u043B\u0430\u043D\u043E\u043C', 'https://nv.ua/rss/2383.xml'),
('\u0411\u043B\u043E\u0433 \u041D\u0412', 'https://nv.ua/rss/225.xml'),
('\u041B\u044C\u0432\u043E\u0432', 'https://nv.ua/rss/233.xml'),
('\u041E\u0434\u0435\u0441\u0441\u0430', 'https://nv.ua/rss/234.xml'),
('\u0425\u0430\u0440\u044C\u043A\u043E\u0432', 'https://nv.ua/rss/235.xml'),
('\u0410\u043D\u0435\u043A\u0434\u043E\u0442\u044B', 'https://nv.ua/rss/2765.xml'),
('\u042D\u043A\u0441\u043A\u043B\u044E\u0437\u0438\u0432\u044B \u041D\u0412', 'https://nv.ua/rss/119.xml')
]
English version: 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 NV(BasicNewsRecipe):
title = 'NV (The New Voice of Ukraine)'
__author__ = 'bugmen00t'
description = 'Independent Ukrainian socio-political magazine and news resource.'
publisher = 'Vydavnychyy Dim Media-DK LLC'
category = 'magazine'
cover_url = u'https://static.nv.ua/shared/system/Article/posters/002/439/752/600x300/65730a3918ebad6c86167b53f2b3e98a.jpg'
language = 'en'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 30
max_articles_per_feed = 40
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='article')
remove_tags = [
dict(name='div', attrs={'class': 'article__content__footer'}),
dict(name='div', attrs={'class': 'article__head__additional_views'}),
dict(name='div', attrs={'class': 'show_two_positions '}),
dict(name='div', attrs={'class': 'media__also__news'}),
dict(name='div', attrs={'class': 'media__also__news_link'}),
dict(name='blockquote', attrs={'class': 'code'}),
dict(name='section', attrs={'class': 'article-share'}),
dict(name='div', attrs={'class': 'nts-video-wrapper'}),
dict(name='footer'),
dict(name='div', attrs={'class': 'longread_tags'}),
dict(name='div', attrs={'class': 'top_donate'}),
dict(name='div', attrs={'class': 'col-md-6 col-lg-3'}),
dict(name='div', attrs={'class': 'copyright'}),
dict(name='div', attrs={'class': 'media__video'}),
dict(name='div', attrs={'class': 'media__embed'})
]
feeds = [
('All News', 'https://english.nv.ua/rss/all_english.xml'),
('Life', 'https://english.nv.ua/rss/239.xml'),
('Business', 'https://english.nv.ua/rss/238.xml'),
('Nation', 'https://english.nv.ua/rss/237.xml'),
('Opinion', 'https://english.nv.ua/rss/240.xml')
]
|
|
|
|
| Advert | |
|
|
|
08-09-2022, 01:41 PM
|
#21 |
|
Connoisseur
Posts: 65
Karma: 100000
Join Date: Aug 2015
Device: Kindle Keyboard + Kindle Voyage WiFi + Kindle PW11 Kids
|
New recipes (part 09 of ??)
More Russian recipes
Люди Байкала: blog about life in rural Siberia. Favicon. Fixes needed:
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 BaikalJournal(BasicNewsRecipe):
title = '\u041B\u044E\u0434\u0438 \u0411\u0430\u0439\u043A\u0430\u043B\u0430'
__author__ = 'bugmen00t'
description = '\u041D\u0435\u0437\u0430\u0432\u0438\u0441\u0438\u043C\u044B\u0439 \u0430\u0432\u0442\u043E\u0440\u0441\u043A\u0438\u0439 \u0438\u043D\u0442\u0435\u0440\u043D\u0435\u0442-\u0436\u0443\u0440\u043D\u0430\u043B \u043E \u0436\u0438\u0437\u043D\u0438 \u0432 \u0421\u0438\u0431\u0438\u0440\u0438 \u0438 \u0432\u043E\u043A\u0440\u0443\u0433 \u0411\u0430\u0439\u043A\u0430\u043B\u0430, \u043E\u043F\u0438\u0441\u044B\u0432\u0430\u044E\u0449\u0438\u0439 \u0436\u0438\u0437\u043D\u044C \u0432 \u0441\u0438\u0431\u0438\u0440\u0441\u043A\u043E\u0439 \u0433\u043B\u0443\u0431\u0438\u043D\u043A\u0435.'
publisher = '\u041E\u043B\u044C\u0433\u0430 \u041C\u0443\u0442\u043E\u0432\u0438\u043D\u0430, \u0415\u043B\u0435\u043D\u0430 \u0422\u0440\u0438\u0444\u043E\u043D\u043E\u0432\u0430'
category = 'blog'
cover_url = u'https://baikal-journal.ru/wp-content/themes/baikal/assets/img/logo-full.svg'
language = 'ru'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 30
max_articles_per_feed = 10
remove_tags = [
dict(name='div', attrs={'class': 'distance-badge'}),
dict(name='div', attrs={'class': 'lead-footer__sharing'}),
dict(name='div', attrs={'class': 'm-block-ctaline'}),
dict(name='div', attrs={'class': 'm-block-readmore format-inline'}),
dict(name='footer'),
dict(name='div', attrs={'class': 'related-block'}),
dict(name='div', attrs={'class': 'selection-block'}),
dict(name='div', attrs={'class': 'last-cta'})
]
feeds = [
('\u041B\u044E\u0434\u0438 \u0411\u0430\u0439\u043A\u0430\u043B\u0430', 'https://baikal-journal.ru/feed/')
]
Настоящее время: Prague-based Russian-language TV channel founded by RFE/RL & VoA. Favicon. Fixes needed:
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 CurrentTime(BasicNewsRecipe):
title = '\u041D\u0430\u0441\u0442\u043E\u044F\u0449\u0435\u0435 \u0432\u0440\u0435\u043C\u044F'
__author__ = 'bugmen00t'
description = '\u0422\u0435\u043B\u0435\u043A\u0430\u043D\u0430\u043B "\u041D\u0430\u0441\u0442\u043E\u044F\u0449\u0435\u0435 \u0412\u0440\u0435\u043C\u044F" \u0440\u0430\u0441\u0441\u043A\u0430\u0437\u044B\u0432\u0430\u0435\u0442 \u043E \u0432\u0430\u0436\u043D\u044B\u0445 \u043D\u043E\u0432\u043E\u0441\u0442\u044F\u0445 \u0438 \u0437\u043B\u043E\u0431\u043E\u0434\u043D\u0435\u0432\u043D\u044B\u0445 \u0442\u0435\u043C\u0430\u0445, \u043F\u0440\u0435\u0434\u043E\u0441\u0442\u0430\u0432\u043B\u044F\u044F \u0430\u0443\u0434\u0438\u0442\u043E\u0440\u0438\u0438 \u0442\u043E, \u0447\u0442\u043E \u043D\u0435 \u0432\u0441\u0435\u0433\u0434\u0430 \u043C\u043E\u0433\u0443\u0442 \u043E\u0431\u0435\u0441\u043F\u0435\u0447\u0438\u0442\u044C \u043C\u0435\u0441\u0442\u043D\u044B\u0435 \u0421\u041C\u0418: \u043D\u043E\u0432\u043E\u0441\u0442\u0438 \u0431\u0435\u0437 \u0446\u0435\u043D\u0437\u0443\u0440\u044B, \u043E\u0442\u0432\u0435\u0442\u0441\u0442\u0432\u0435\u043D\u043D\u044B\u0439 \u043E\u0431\u043C\u0435\u043D \u043C\u043D\u0435\u043D\u0438\u044F\u043C\u0438, \u043E\u0442\u043A\u0440\u044B\u0442\u043E\u0435 \u043E\u0431\u0441\u0443\u0436\u0434\u0435\u043D\u0438\u0435 \u043F\u0440\u043E\u0431\u043B\u0435\u043C.'
publisher = 'RFE/RL ("\u0420\u0430\u0434\u0438\u043E \u0421\u0432\u043E\u0431\u043E\u0434\u043D\u0430\u044F \u0415\u0432\u0440\u043E\u043F\u0430"/"\u0420\u0430\u0434\u0438\u043E \u0421\u0432\u043E\u0431\u043E\u0434\u0430") \u043F\u0440\u0438 \u0443\u0447\u0430\u0441\u0442\u0438\u0438 VoA ("\u0413\u043E\u043B\u043E\u0441 \u0410\u043C\u0435\u0440\u0438\u043A\u0438")'
category = 'newspaper'
cover_url = u'https://www.currenttime.tv/Content/responsive/RFE/ru-RU-TV/img/top_logo_news.png'
language = 'ru'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
remove_empty_feeds = True
oldest_article = 14
max_articles_per_feed = 20
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': 'body-container'})
remove_tags = [
dict(name='div', attrs={'class': 'publishing-details '}),
dict(name='div', attrs={'class': 'separator'}),
dict(name='div', attrs={'class': 'links'}),
dict(name='div', attrs={'class': 'share--box'}),
dict(name='aside'),
dict(name='div', attrs={'class': 'media-block also-read'}),
dict(name='div', attrs={'class': 'media-block-wrap'}),
dict(name='div', attrs={'class': 'media-download'}),
dict(name='div', attrs={'class': 'wsw__embed'}),
dict(name='div', attrs={'class': 'share--box'}),
dict(name='div', attrs={'class': 'prog-hdr'}),
dict(name='div', attrs={'class': 'dropdown__holder'}),
dict(name='div', attrs={'id': 'ymla-section'}),
dict(name='div', attrs={'id': 'comments'}),
dict(name='a', attrs={'class': 'back-to-top-link'}),
dict(name='footer'),
dict(name='li', attrs={'class': 'socials block-socials'}),
dict(name='div', attrs={'data-sp_api': 'pangea-video'})
]
feeds = [
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://www.currenttime.tv/api/zgbip_e_tpp_'),
('\u0421\u0435\u043C\u044C \u0441\u043E\u0440\u043E\u043A', 'https://www.currenttime.tv/api/ztktpyeimupt'),
('\u042D\u043A\u0441\u043A\u043B\u044E\u0437\u0438\u0432', 'https://www.currenttime.tv/api/zpyomoe-rimi'),
('\u0412\u044B\u0431\u043E\u0440 \u0440\u0435\u0434\u0430\u043A\u0446\u0438\u0438', 'https://www.currenttime.tv/api/zqk-poekpbpo'),
('\u0420\u043E\u0441\u0441\u0438\u044F', 'https://www.currenttime.tv/api/zuvmpvepo_pv'),
('\u0423\u043A\u0440\u0430\u0438\u043D\u0430', 'https://www.currenttime.tv/api/zkvmptemo_pt'),
('\u0411\u0435\u043B\u0430\u0440\u0443\u0441\u044C', 'https://www.currenttime.tv/api/zvvmm_eoo_mt'),
('\u0410\u0437\u0438\u044F', 'https://www.currenttime.tv/api/zbvtpqetoupq'),
('\u0415\u0432\u0440\u043E\u043F\u0430', 'https://www.currenttime.tv/api/z-vmpoevo_pi'),
('\u0410\u043C\u0435\u0440\u0438\u043A\u0430', 'https://www.currenttime.tv/api/zbvmpieto_pp'),
('\u0411\u043B\u0438\u0436\u043D\u0438\u0439 \u0412\u043E\u0441\u0442\u043E\u043A', 'https://www.currenttime.tv/api/zrvtppeuqupm'),
('\u041B\u043E\u043D\u0433\u0440\u0438\u0434\u044B', 'https://www.currenttime.tv/api/zibmmyejv_my'),
('\u0420\u0435\u043F\u043E\u0440\u0442\u0430\u0436', 'https://www.currenttime.tv/api/zrpppqeujppo'),
('\u0420\u0435\u043F\u043E\u0440\u0442\u0430\u0436\u0438 \u043F\u0440\u043E\u0433\u0440\u0430\u043C\u043C\u044B \u0412\u0435\u0447\u0435\u0440', 'https://www.currenttime.tv/api/zvrrmoeourmp'),
('\u0418\u043D\u0442\u0435\u0440\u0432\u044C\u044E', 'https://www.currenttime.tv/api/zqpppoekjppi'),
('\u0418\u043D\u0444\u043E\u0433\u0440\u0430\u0444\u0438\u043A\u0430', 'https://www.currenttime.tv/api/zmqmpyebumpv')
]
Фонтанка: Saint Petersburg news portal. Favicon. Fixes needed:
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 Fontanka(BasicNewsRecipe):
title = '\u0424\u043E\u043D\u0442\u0430\u043D\u043A\u0430'
__author__ = 'bugmen00t'
description = '\u0415\u0436\u0435\u0434\u043D\u0435\u0432\u043D\u043E\u0435 \u043F\u0435\u0442\u0435\u0440\u0431\u0443\u0440\u0433\u0441\u043A\u043E\u0435 \u043E\u0431\u0449\u0435\u0441\u0442\u0432\u0435\u043D\u043D\u043E-\u043F\u043E\u043B\u0438\u0442\u0438\u0447\u0435\u0441\u043A\u043E\u0435 \u0441\u0435\u0442\u0435\u0432\u043E\u0435 \u0438\u0437\u0434\u0430\u043D\u0438\u0435.'
publisher = '\u0410\u041E "\u0410\u0416\u0423\u0420-\u041C\u0415\u0414\u0418\u0410"'
category = 'blog'
cover_url = u'https://www.fontanka.ru/longreads/69505589/2015/images/tild3834-3362-4166-b239-366134363733____-01.png'
language = 'ru'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 30
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='section', attrs={'itemprop': 'articleBody'})
remove_tags = [
dict(name='div', attrs={'class': 'ADdj ADc5'}),
dict(name='div', attrs={'class': 'DLj1'}),
dict(name='div', attrs={'class': 'DTrp'}),
dict(name='div', attrs={'class': 'EHed'}),
dict(name='div', attrs={'class': 'FHwp'}),
dict(name='div', attrs={'class': 'ENr-'}),
dict(name='div', attrs={'class': 'ENt7'}),
dict(name='div', attrs={'class': 't004'}),
dict(name='div', attrs={'class': 't120'}),
dict(name='div', attrs={'class': 't123'}),
dict(name='div', attrs={'class': 't405'}),
dict(name='div', attrs={'class': 't463'}),
# For articles from https://doctorpiter.ru
dict(name='div', attrs={'class': 'article__block article__block_type-links'}),
dict(name='div', attrs={'class': 'feedback-request-form__before'}),
dict(name='div', attrs={'class': 'related-entities-container'}),
dict(name='div', attrs={'class': 'tags article-footer__tags'}),
dict(name='hr', attrs={'class': 'article-footer-divider'})
]
feeds = [
('Fontanka.ru', 'https://www.fontanka.ru/fontanka.rss')
]
The Bell: business news Favicon. Fixes needed:
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 TheBell(BasicNewsRecipe):
title = 'The Bell'
__author__ = 'bugmen00t'
description = '\u0418\u043D\u0442\u0435\u0440\u043D\u0435\u0442-\u0438\u0437\u0434\u0430\u043D\u0438\u0435 \u0438 \u0438\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u043E\u043D\u043D\u044B\u0439 \u0431\u044E\u043B\u043B\u0435\u0442\u0435\u043D\u044C, \u0441\u043F\u0435\u0446\u0438\u0430\u043B\u0438\u0437\u0438\u0440\u0443\u044E\u0449\u0435\u0435\u0441\u044F \u043D\u0430 \u0431\u0438\u0437\u043D\u0435\u0441-\u043D\u043E\u0432\u043E\u0441\u0442\u044F\u0445.'
publisher = '\u0415\u043B\u0438\u0437\u0430\u0432\u0435\u0442\u0430 \u041E\u0441\u0435\u0442\u0438\u043D\u0441\u043A\u0430\u044F, \u0418\u0440\u0438\u043D\u0430 \u041C\u0430\u043B\u043A\u043E\u0432\u0430'
category = 'newspaper'
cover_url = u'https://thebell.io/wp-content/uploads/2018/03/thebell-cover.png'
language = 'ru'
no_stylesheets = True
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 20
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': 'post'})
remove_tags = [
dict(name='div', attrs={'class': 'post_bottom ng-tns-c84-1 ng-star-inserted'}),
dict(name='div', attrs={'class': 'post_tags ng-tns-c84-1 ng-star-inserted'}),
dict(name='div', attrs={'class': 'post_subscribe ng-tns-c84-1 ng-star-inserted'}),
dict(name='div', attrs={'class': 'author__content_image author__content_image_small ng-star-inserted'}),
dict(name='div', attrs={'class': 'email email_small ng-star-inserted'}),
dict(name='div', attrs={'class': 'post_share ng-tns-c84-1'}),
dict(name='div', attrs={'class': 'social_media'})
]
feeds = [
('The Bell', 'https://thebell.io/feed')
]
Fixed recipe for Сноб (snob.recipe): URL transformation subroutine lacked the last line 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 Snob(BasicNewsRecipe):
title = '\u0421\u043D\u043E\u0431'
__author__ = 'bugmen00t'
description = '\u0414\u0438\u0441\u043A\u0443\u0441\u0441\u0438\u043E\u043D\u043D\u043E\u0435, \u0438\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u043E\u043D\u043D\u043E\u0435 \u0438 \u043E\u0431\u0449\u0435\u0441\u0442\u0432\u0435\u043D\u043D\u043E\u0435 \u043F\u0440\u043E\u0441\u0442\u0440\u0430\u043D\u0441\u0442\u0432\u043E \u0434\u043B\u044F \u043B\u044E\u0434\u0435\u0439, \u043A\u043E\u0442\u043E\u0440\u044B\u0435 \u0436\u0438\u0432\u0443\u0442 \u0432 \u0440\u0430\u0437\u043D\u044B\u0445 \u0441\u0442\u0440\u0430\u043D\u0430\u0445, \u0433\u043E\u0432\u043E\u0440\u044F\u0442 \u043D\u0430 \u0440\u0430\u0437\u043D\u044B\u0445 \u044F\u0437\u044B\u043A\u0430\u0445, \u043D\u043E \u0434\u0443\u043C\u0430\u044E\u0442 \u043F\u043E-\u0440\u0443\u0441\u0441\u043A\u0438.'
publisher = '\u041E\u041E\u041E \u00AB\u0421\u043D\u043E\u0431 \u041C\u0435\u0434\u0438\u0430\u00BB'
category = 'magazine'
cover_url = u'https://snob.ru/indoc/tilda/995317/images/tild3233-6631-4664-b663-353636373235__e3057a5fee932ada1aaf.png'
language = 'ru'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 5
max_articles_per_feed = 50
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='article')
remove_tags = [
dict(name='div', attrs={'class': 'entry__tags'}),
dict(name='div', attrs={'class': 'entry__likes'})
]
feeds = [
('\u0421\u043D\u043E\u0431', 'https://snob.ru/rss/')
]
def get_article_url(self, article):
link = article.get('link', None)
if 'utm_source' in link:
return link.split('?utm')[0]
|
|
|
|
|
08-10-2022, 08:15 AM
|
#22 |
|
Connoisseur
Posts: 65
Karma: 100000
Join Date: Aug 2015
Device: Kindle Keyboard + Kindle Voyage WiFi + Kindle PW11 Kids
|
New recipes (part 10 of ??)
Another bunch of Russian recipes, and a few unrelated ones.
Wonderzine: style, beauty, fashion and lifestyle blog. Favicon. Fixes needed:
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 Wonderzine(BasicNewsRecipe):
title = 'Wonderzine'
__author__ = 'bugmen00t'
description = '\u041E\u043D\u043B\u0430\u0439\u043D-\u0438\u0437\u0434\u0430\u043D\u0438\u0435 \u0434\u043B\u044F \u0441\u043E\u0432\u0440\u0435\u043C\u0435\u043D\u043D\u044B\u0445 \u0436\u0435\u043D\u0449\u0438\u043D \u0438 \u0438\u0445 \u0434\u0440\u0443\u0437\u0435\u0439. \u041C\u044B \u043F\u0438\u0448\u0435\u043C \u043E \u043C\u043E\u0434\u0435 \u0438 \u043F\u043E\u043B\u0438\u0442\u0438\u043A\u0435, \u043E\u0431\u0449\u0435\u0441\u0442\u0432\u0435\u043D\u043D\u044B\u0445 \u0442\u0435\u043D\u0434\u0435\u043D\u0446\u0438\u044F\u0445 \u0438 \u0440\u0430\u0437\u0432\u043B\u0435\u0447\u0435\u043D\u0438\u044F\u0445, \u0437\u0434\u043E\u0440\u043E\u0432\u044C\u0435 \u0438 \u0441\u0435\u043A\u0441\u0435, \u044D\u0442\u0438\u043A\u0435 \u0438 \u0432\u043E\u0437\u043C\u043E\u0436\u043D\u043E\u0441\u0442\u044F\u0445, \u043E\u0441\u043E\u0437\u043D\u0430\u043D\u043D\u044B\u0445 \u0442\u0440\u0430\u0442\u0430\u0445 \u0438 \u0440\u0430\u0437\u043D\u043E\u043E\u0431\u0440\u0430\u0437\u0438\u0438 \u043A\u0440\u0430\u0441\u043E\u0442\u044B.'
publisher = 'Redefine Media holding'
category = 'blog'
cover_url = u'https://lamcdn.net/wonderzine.com/post-og_image/WQRiRGqLlcKyEHsnOS-sUw.png'
language = 'ru'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 14
max_articles_per_feed = 20
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': 'is_article_end'})
remove_tags = [
dict(name='ul', attrs={'class': 'post-meta'}),
dict(name='a', attrs={'class': 'flow'}),
dict(name='a', attrs={'class': 'banner-ad-link'}),
dict(name='div', attrs={'class': 'share-buttons-bar'}),
dict(name='div', attrs={'class': 'pseudosidebar'})
]
feeds = [
('\u0412\u0441\u0435 \u043C\u0430\u0442\u0435\u0440\u0438\u0430\u043B\u044B', 'https://www.wonderzine.com/feeds/posts.atom'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://www.wonderzine.com/feeds/posts.atom?news=only'),
('\u0416\u0438\u0437\u043D\u044C', 'https://www.wonderzine.com/feeds/posts.atom?topic=life'),
('\u0417\u0434\u043E\u0440\u043E\u0432\u044C\u0435', 'https://www.wonderzine.com/feeds/posts.atom?topic=health'),
('\u041A\u0440\u0430\u0441\u043E\u0442\u0430', 'https://www.wonderzine.com/feeds/posts.atom?topic=beauty'),
('\u0420\u0430\u0437\u0432\u043B\u0435\u0447\u0435\u043D\u0438\u044F', 'https://www.wonderzine.com/feeds/posts.atom?topic=entertainment'),
('\u0421\u0442\u0438\u043B\u044C', 'https://www.wonderzine.com/feeds/posts.atom?topic=style'),
('\u0412\u043E\u0437\u043C\u043E\u0436\u043D\u043E\u0441\u0442\u0438', 'https://www.wonderzine.com/feeds/posts.atom?topic=opportunities')
]
Vedomosit: daily newspaper; non-paywlled content only. 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 Vedomosti(BasicNewsRecipe):
title = '\u0412\u0435\u0434\u043E\u043C\u043E\u0441\u0442\u0438'
__author__ = 'bugmen00t'
description = '\u0415\u0436\u0435\u0434\u043D\u0435\u0432\u043D\u0430\u044F \u0434\u0435\u043B\u043E\u0432\u0430\u044F \u0433\u0430\u0437\u0435\u0442\u0430.'
publisher = '\u0410\u041E \u00AB\u0411\u0438\u0437\u043D\u0435\u0441 \u041D\u044C\u044E\u0441 \u041C\u0435\u0434\u0438\u0430\u00BB'
category = 'newspaper'
cover_url = u'https://id.vedomosti.ru/assets/chopick-13077eee55066e639f3a037834ecf11279d3f402e9f5cac7162d13183dfd9d20.jpg'
language = 'ru'
no_stylesheets = True
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 200
remove_tags_before = dict(name='header', attrs={'class': 'article__header'})
remove_tags_after = dict(name='div', attrs={'class': 'article__main'})
remove_tags = [
dict(name='div', attrs={'class': 'article__tools'}),
dict(name='div', attrs={'class': 'box-inset-link box-inset-link--card'}),
dict(name='div', attrs={'class': 'box-inset-link box-inset-link--card box-inset-link--link'})
]
feeds = [
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://www.vedomosti.ru/rss/news')
]
Bellingcat: OSINT investigaton and citizen journalism blog. Favicon. English version: 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 Bellingcat(BasicNewsRecipe):
title = 'Bellingcat'
__author__ = 'bugmen00t'
description = 'Bellingcat is an independent international collective of researchers, investigators and citizen journalists using open source and social media investigation to probe a variety of subjects – from Mexican drug lords and crimes against humanity, to tracking the use of chemical weapons and conflicts worldwide. With staff and contributors in more than 20 countries around the world, we operate in a unique field where advanced technology, forensic research, journalism, investigations, transparency and accountability come together.'
publisher = 'Stichting Bellingcat'
category = 'blog'
cover_url = u'https://www.bellingcat.com/app/uploads/2018/04/bellingcat_HP_logo_black.jpg'
language = 'en'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 60
max_articles_per_feed = 10
remove_tags_before = dict(name='div', attrs={'class': 'container'})
remove_tags_after = dict(name='div', attrs={'class': 'container'})
remove_tags = [
dict(name='div', attrs={'class': 'social social--share'}),
dict(name='div', attrs={'class': 'singular__related'})
]
feeds = [
('Bellingcat', 'https://www.bellingcat.com/feed/')
]
Russian version: 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 Bellingcat(BasicNewsRecipe):
title = '\u0411\u0435\u043B\u043B\u0438\u043D\u0433\u043A\u044D\u0442 (bell\u00BFngcat)'
__author__ = 'bugmen00t'
description = 'Bellingcat \u2014 \u044D\u0442\u043E \u043D\u0435\u0437\u0430\u0432\u0438\u0441\u0438\u043C\u0430\u044F \u043C\u0435\u0436\u0434\u0443\u043D\u0430\u0440\u043E\u0434\u043D\u0430\u044F \u043A\u043E\u043C\u0430\u043D\u0434\u0430 \u0440\u0430\u0441\u0441\u043B\u0435\u0434\u043E\u0432\u0430\u0442\u0435\u043B\u0435\u0439 \u0438 \u0433\u0440\u0430\u0436\u0434\u0430\u043D\u0441\u043A\u0438\u0445 \u0436\u0443\u0440\u043D\u0430\u043B\u0438\u0441\u0442\u043E\u0432, \u043A\u043E\u0442\u043E\u0440\u044B\u0435 \u0438\u0441\u043F\u043E\u043B\u044C\u0437\u0443\u044E\u0442 \u043E\u0442\u043A\u0440\u044B\u0442\u044B\u0435 \u0438\u0441\u0442\u043E\u0447\u043D\u0438\u043A\u0438 \u0438 \u0441\u043E\u0446\u0438\u0430\u043B\u044C\u043D\u044B\u0435 \u0441\u0435\u0442\u0438 \u0434\u043B\u044F \u0440\u0430\u0441\u0441\u043B\u0435\u0434\u043E\u0432\u0430\u043D\u0438\u0439 \u043D\u0430 \u0440\u0430\u0437\u043B\u0438\u0447\u043D\u044B\u0435 \u0442\u0435\u043C\u044B \u2014 \u043E\u0442 \u043C\u0435\u043A\u0441\u0438\u043A\u0430\u043D\u0441\u043A\u0438\u0445 \u043D\u0430\u0440\u043A\u043E\u043A\u0430\u0440\u0442\u0435\u043B\u0435\u0439 \u0438 \u043F\u0440\u0435\u0441\u0442\u0443\u043F\u043B\u0435\u043D\u0438\u0439 \u043F\u0440\u043E\u0442\u0438\u0432 \u0447\u0435\u043B\u043E\u0432\u0435\u0447\u0435\u0441\u0442\u0432\u0430 \u0434\u043E \u043E\u0442\u0441\u043B\u0435\u0436\u0438\u0432\u0430\u043D\u0438\u044F \u0438\u0441\u043F\u043E\u043B\u044C\u0437\u043E\u0432\u0430\u043D\u0438\u044F \u0445\u0438\u043C\u0438\u0447\u0435\u0441\u043A\u043E\u0433\u043E \u043E\u0440\u0443\u0436\u0438\u044F \u0438 \u043A\u043E\u043D\u0444\u043B\u0438\u043A\u0442\u043E\u0432 \u043F\u043E \u0432\u0441\u0435\u043C\u0443 \u043C\u0438\u0440\u0443 \u2014 \u0441\u043E\u0447\u0435\u0442\u0430\u044F \u0441\u043E\u0432\u0440\u0435\u043C\u0435\u043D\u043D\u044B\u0435 \u0442\u0435\u0445\u043D\u043E\u043B\u043E\u0433\u0438\u0438, \u043A\u0440\u0438\u043C\u0438\u043D\u0430\u043B\u0438\u0441\u0442\u0438\u0447\u0435\u0441\u043A\u0438\u0435 \u044D\u043A\u0441\u043F\u0435\u0440\u0442\u0438\u0437\u044B, \u0436\u0443\u0440\u043D\u0430\u043B\u0438\u0441\u0442\u0438\u043A\u0443, \u0440\u0430\u0441\u0441\u043B\u0435\u0434\u043E\u0432\u0430\u043D\u0438\u044F \u0438 \u0431\u043E\u0440\u044C\u0431\u0443 \u0437\u0430 \u043F\u0440\u043E\u0437\u0440\u0430\u0447\u043D\u043E\u0441\u0442\u044C \u0438 \u043E\u0442\u0432\u0435\u0442\u0441\u0442\u0432\u0435\u043D\u043D\u043E\u0441\u0442\u044C.'
publisher = 'Stichting Bellingcat'
category = 'blog'
cover_url = u'https://www.bellingcat.com/app/uploads/2018/04/bellingcat_HP_logo_black.jpg'
language = 'ru'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 60
max_articles_per_feed = 10
remove_tags_before = dict(name='div', attrs={'class': 'container'})
remove_tags_after = dict(name='div', attrs={'class': 'container'})
remove_tags = [
dict(name='div', attrs={'class': 'social social--share'}),
dict(name='div', attrs={'class': 'singular__related'})
]
feeds = [
('Bellingcat', 'https://ru.bellingcat.com/feed/')
]
Ukrainian version: 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 Bellingcat(BasicNewsRecipe):
title = '\u0411\u0435\u043B\u043B\u0456\u043D\u0433\u043A\u0435\u0442 (bell\u00BFngcat)'
__author__ = 'bugmen00t'
description = '\u0411\u0435\u043B\u043B\u0456\u043D\u0433\u043A\u0435\u0442 \u2014 \u043D\u0435\u0437\u0430\u043B\u0435\u0436\u043D\u0438\u0439 \u043C\u0456\u0436\u043D\u0430\u0440\u043E\u0434\u043D\u0438\u0439 \u043A\u043E\u043B\u0435\u043A\u0442\u0438\u0432 \u0434\u043E\u0441\u043B\u0456\u0434\u043D\u0438\u043A\u0456\u0432, \u0441\u043B\u0456\u0434\u0447\u0438\u0445 \u0456 \u0433\u0440\u043E\u043C\u0430\u0434\u044F\u043D\u0441\u044C\u043A\u0438\u0445 \u0436\u0443\u0440\u043D\u0430\u043B\u0456\u0441\u0442\u0456\u0432, \u044F\u043A\u0456 \u0432\u0438\u043A\u043E\u0440\u0438\u0441\u0442\u043E\u0432\u0443\u044E\u0442\u044C \u0432\u0456\u0434\u043A\u0440\u0438\u0442\u0456 \u0434\u0436\u0435\u0440\u0435\u043B\u0430 \u0442\u0430 \u0441\u043E\u0446\u0456\u0430\u043B\u044C\u043D\u0456 \u043C\u0435\u0440\u0435\u0436\u0456 \u0434\u043B\u044F \u0440\u043E\u0437\u0441\u043B\u0456\u0434\u0443\u0432\u0430\u043D\u043D\u044F \u0440\u0456\u0437\u043D\u043E\u043C\u0430\u043D\u0456\u0442\u043D\u0438\u0445 \u0442\u0435\u043C \u2014 \u0432\u0456\u0434 \u043C\u0435\u043A\u0441\u0438\u043A\u0430\u043D\u0441\u044C\u043A\u0438\u0445 \u043D\u0430\u0440\u043A\u043E\u0431\u0430\u0440\u043E\u043D\u0456\u0432 \u0456 \u0437\u043B\u043E\u0447\u0438\u043D\u0456\u0432 \u043F\u0440\u043E\u0442\u0438 \u043B\u044E\u0434\u0441\u0442\u0432\u0430, \u0434\u043E \u0432\u0456\u0434\u0441\u0442\u0435\u0436\u0435\u043D\u043D\u044F \u0432\u0438\u043A\u043E\u0440\u0438\u0441\u0442\u0430\u043D\u043D\u044F \u0445\u0456\u043C\u0456\u0447\u043D\u043E\u0457 \u0437\u0431\u0440\u043E\u0457 \u0442\u0430 \u043A\u043E\u043D\u0444\u043B\u0456\u043A\u0442\u0456\u0432 \u0443 \u0432\u0441\u044C\u043E\u043C\u0443 \u0441\u0432\u0456\u0442\u0456. \u041C\u0438 \u043F\u0440\u0430\u0446\u044E\u0454\u043C\u043E \u0432 \u0443\u043D\u0456\u043A\u0430\u043B\u044C\u043D\u0456\u0439 \u0441\u0444\u0435\u0440\u0456, \u0434\u0435 \u043F\u0435\u0440\u0435\u0434\u043E\u0432\u0456 \u0442\u0435\u0445\u043D\u043E\u043B\u043E\u0433\u0456\u0457, \u0441\u0443\u0434\u043E\u0432\u043E-\u043C\u0435\u0434\u0438\u0447\u043D\u0456 \u0434\u043E\u0441\u043B\u0456\u0434\u0436\u0435\u043D\u043D\u044F, \u0436\u0443\u0440\u043D\u0430\u043B\u0456\u0441\u0442\u0438\u043A\u0430, \u0440\u043E\u0437\u0441\u043B\u0456\u0434\u0443\u0432\u0430\u043D\u043D\u044F, \u043F\u0440\u043E\u0437\u043E\u0440\u0456\u0441\u0442\u044C \u0456 \u0432\u0456\u0434\u043F\u043E\u0432\u0456\u0434\u0430\u043B\u044C\u043D\u0456\u0441\u0442\u044C \u043E\u0431\u2019\u0454\u0434\u043D\u0443\u044E\u0442\u044C\u0441\u044F.'
publisher = 'Stichting Bellingcat'
category = 'blog'
cover_url = u'https://www.bellingcat.com/app/uploads/2018/04/bellingcat_HP_logo_black.jpg'
language = 'uk'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 60
max_articles_per_feed = 10
remove_tags_before = dict(name='div', attrs={'class': 'container'})
remove_tags_after = dict(name='div', attrs={'class': 'container'})
remove_tags = [
dict(name='div', attrs={'class': 'social social--share'}),
dict(name='div', attrs={'class': 'singular__related'})
]
feeds = [
('Bellingcat', 'https://uk.bellingcat.com/feed/')
]
Version en français (no updates since 2021): 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 Bellingcat(BasicNewsRecipe):
title = 'Bellingcat'
__author__ = 'bugmen00t'
description = 'Bellingcat est un groupe international ind\u00E9pendant de chercheurs, d\u0027enqu\u00EAteurs et de journalistes citoyens utilisant \u00E0 la fois: enqu\u00EAtes \u0027open source\u0027 et r\u00E9seaux sociaux, pour sonder une vari\u00E9t\u00E9 de sujets - trafiquants de drogue mexicains, crimes contre l\u0027humanit\u00E9, suivi de l\u0027utilisation d\u0027armes chimiques et conflits dans le monde entier. Nous op\u00E9rons dans un domaine unique dans lequel technologie de pointe, recherche m\u00E9dico-l\u00E9gale, journalisme, enqu\u00EAtes, transparence et responsabilit\u00E9 se rencontrent.'
publisher = 'Stichting Bellingcat'
category = 'blog'
cover_url = u'https://www.bellingcat.com/app/uploads/2018/04/bellingcat_HP_logo_black.jpg'
language = 'fr'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 300
max_articles_per_feed = 10
remove_tags_before = dict(name='div', attrs={'class': 'container'})
remove_tags_after = dict(name='div', attrs={'class': 'container'})
remove_tags = [
dict(name='div', attrs={'class': 'social social--share'}),
dict(name='div', attrs={'class': 'singular__related'})
]
feeds = [
('Bellingcat', 'https://fr.bellingcat.com/feed/')
]
Versión en Español (no updates since 2021): 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 Bellingcat(BasicNewsRecipe):
title = 'Bellingcat'
__author__ = 'bugmen00t'
description = 'Bellingcat es un colectivo internacional independiente de investigadores y periodistas ciudadanos que usan informaci\u00F3n de fuente abierta y redes sociales para investigar una gran variedad de temas, desde carteles de droga en M\u00E9xico y cr\u00EDmenes de lesa humanidad hasta el rastreo de armas qu\u00EDmicas en zonas de conflicto alrededor del mundo. Nosotros operamos en un campo \u00FAnico donde la tecnolog\u00EDa avanzada, las investigaciones forenses, el periodismo, y la transparencia y responsabilidad se unen.'
publisher = 'Stichting Bellingcat'
category = 'blog'
cover_url = u'https://www.bellingcat.com/app/uploads/2018/04/bellingcat_HP_logo_black.jpg'
language = 'es'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 300
max_articles_per_feed = 10
remove_tags_before = dict(name='div', attrs={'class': 'container'})
remove_tags_after = dict(name='div', attrs={'class': 'container'})
remove_tags = [
dict(name='div', attrs={'class': 'social social--share'}),
dict(name='div', attrs={'class': 'singular__related'})
]
feeds = [
('Bellingcat', 'https://es.bellingcat.com/feed/')
]
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 Rosbalt(BasicNewsRecipe):
title = '\u0420\u043E\u0441\u0431\u0430\u043B\u0442'
__author__ = 'bugmen00t'
description = '\u0424\u0435\u0434\u0435\u0440\u0430\u043B\u044C\u043D\u043E\u0435 \u0438\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u043E\u043D\u043D\u043E-\u0430\u043D\u0430\u043B\u0438\u0442\u0438\u0447\u0435\u0441\u043A\u043E\u0435 \u0430\u0433\u0435\u043D\u0442\u0441\u0442\u0432\u043E. \u041A\u0440\u0443\u0433\u043B\u043E\u0441\u0443\u0442\u043E\u0447\u043D\u043E \u0441\u043B\u0435\u0434\u0438\u043C \u0437\u0430 \u0441\u043E\u0431\u044B\u0442\u0438\u044F\u043C\u0438 \u0432 \u0441\u0442\u0440\u0430\u043D\u0435 \u0438 \u043C\u0438\u0440\u0435, \u043F\u0443\u0431\u043B\u0438\u043A\u0443\u0435\u043C \u0441\u0430\u043C\u044B\u0435 \u0441\u0432\u0435\u0436\u0438\u0435 \u043D\u043E\u0432\u043E\u0441\u0442\u0438, \u043A\u043E\u043C\u043C\u0435\u043D\u0442\u0430\u0440\u0438\u0438 \u0432\u0435\u0434\u0443\u0449\u0438\u0445 \u044D\u043A\u0441\u043F\u0435\u0440\u0442\u043E\u0432, \u0430\u043D\u0430\u043B\u0438\u0442\u0438\u0447\u0435\u0441\u043A\u0438\u0435 \u0441\u0442\u0430\u0442\u044C\u0438, \u0438\u043D\u0442\u0435\u0440\u0432\u044C\u044E \u0441 \u0432\u0435\u0434\u0443\u0449\u0438\u043C\u0438 \u043F\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u0442\u0435\u043B\u044F\u043C\u0438 \u0440\u043E\u0441\u0441\u0438\u0439\u0441\u043A\u043E\u0433\u043E \u0431\u0438\u0437\u043D\u0435\u0441\u0430 \u0438 \u043F\u043E\u043B\u0438\u0442\u0438\u043A\u0438.'
publisher = '\u0410\u041E \u00AB\u0420\u0421-\u0411\u0430\u043B\u0442\u00BB'
category = 'newspaper'
cover_url = u'https://i.ytimg.com/vi/eeMqJGbjuY0/maxresdefault.jpg'
language = 'ru'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 100
remove_tags_before = dict(name='div', attrs={'class': 'main-content'})
remove_tags_after = dict(name='div', attrs={'class': 'newstext'})
remove_tags = [
dict(name='nav'),
dict(name='aside'),
dict(name='div', attrs={'class': 'news-left'}),
dict(name='div', attrs={'class': 'rkngov'}),
dict(name='div', attrs={'class': 'eye'})
]
feeds = [
('\u0420\u043E\u0441\u0431\u0430\u043B\u0442', 'https://www.rosbalt.ru/feed/')
]
Debunking Denialism: blog about pseudoscience in everyday life. 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 Bellingcat(BasicNewsRecipe):
title = 'Debunking Denialism'
__author__ = 'bugmen00t'
description = 'Debunking Denialism is a website dedicated to the refutation of pseudoscience and denialism by applying scientific skepticism and defending evidence-based science. Fighting pseudoscience and quackery with reason and evidence.'
publisher = 'Debunking Denialism'
category = 'blog'
cover_url = u'https://i0.wp.com/debunkingdenialism.com/wp-content/uploads/2017/06/cropped-newestblavatar.jpg'
language = 'en'
no_stylesheets = True
remove_javascript = False
auto_cleanup = False
oldest_article = 60
max_articles_per_feed = 10
remove_tags_before = dict(name='article')
remove_tags_after = dict(name='article')
remove_tags = [
dict(name='div', attrs={'class': 'above-entry-meta'}),
dict(name='time', attrs={'class': 'updated'}),
dict(name='p', attrs={'class': 'ddtag'}),
dict(name='div', attrs={'class': 'sharedaddy sd-sharing-enabled'}),
dict(name='div', attrs={'class': 'sharedaddy sd-block sd-like jetpack-likes-widget-wrapper jetpack-likes-widget-unloaded'})
]
feeds = [
('Debunking Denialism', 'https://debunkingdenialism.com/feed/')
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-orig-file': True}):
img['src'] = img['data-orig-file']
return soup
Last edited by bugmen00t; 08-10-2022 at 08:18 AM. |
|
|
|
|
08-15-2022, 02:20 PM
|
#23 |
|
Connoisseur
Posts: 65
Karma: 100000
Join Date: Aug 2015
Device: Kindle Keyboard + Kindle Voyage WiFi + Kindle PW11 Kids
|
New recipes (part 11 of ??)
More Russian and Ukrainian sources.
Cвободное пространство: news aggregator from "Novaya Gazeta" editors team. Favicon replacemet. Fixes needed:
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 NovayaGazeta(BasicNewsRecipe):
title = '\u0421\u0432\u043E\u0431\u043E\u0434\u043D\u043E\u0435 \u043F\u0440\u043E\u0441\u0442\u0440\u0430\u043D\u0441\u0442\u0432\u043E'
__author__ = 'bugmen00t'
description = '\u041E\u0442\u043A\u0440\u044B\u0442\u044B\u0439 \u043A\u043E\u043D\u0441\u0442\u0440\u0443\u043A\u0442\u043E\u0440 \u043A\u043E\u043D\u0442\u0435\u043D\u0442\u0430, \u043F\u043E\u0434\u0433\u043E\u0442\u043E\u0432\u043B\u0435\u043D\u043D\u044B\u0439 \u0440\u043E\u0441\u0441\u0438\u0439\u0441\u043A\u043E\u0439 \u0440\u0435\u0434\u0430\u043A\u0446\u0438\u0435\u0439 \u00AB\u041D\u043E\u0432\u043E\u0439 \u0433\u0430\u0437\u0435\u0442\u044B\u00BB, \u0434\u0435\u0442\u0430\u043B\u0438 \u043A\u043E\u0442\u043E\u0440\u043E\u0433\u043E \u043A\u0430\u0436\u0434\u044B\u0439 \u0438\u0437 \u0447\u0438\u0442\u0430\u0442\u0435\u043B\u0435\u0439 \u0441\u043E\u0431\u0438\u0440\u0430\u0435\u0442 \u0434\u043B\u044F \u0441\u0435\u0431\u044F \u0441\u0430\u043C. \u041A\u043E\u043D\u0441\u0442\u0440\u0443\u043A\u0442\u043E\u0440 \u2014 \u044D\u0442\u043E \u043D\u043E\u0432\u044B\u0439 \u0441\u043F\u043E\u0441\u043E\u0431 \u0447\u0438\u0442\u0430\u0442\u044C \u043C\u0430\u0442\u0435\u0440\u0438\u0430\u043B\u044B \u0436\u0443\u0440\u043D\u0430\u043B\u0438\u0441\u0442\u043E\u0432 \u00AB\u041D\u043E\u0432\u043E\u0439 \u0433\u0430\u0437\u0435\u0442\u044B\u00BB \u0438 \u0432\u0441\u0435 \u043E\u0441\u043D\u043E\u0432\u043D\u044B\u0435 \u043F\u043E\u0442\u043E\u043A\u0438 \u043A\u043E\u043D\u0442\u0435\u043D\u0442\u0430: \u043B\u044E\u0431\u044B\u0435 \u0432\u0435\u0431-\u0441\u0430\u0439\u0442\u044B, Telegram-\u043A\u0430\u043D\u0430\u043B\u044B, Youtube-\u043A\u0430\u043D\u0430\u043B\u044B.'
publisher = '\u0420\u0435\u0434\u0430\u043A\u0446\u0438\u043E\u043D\u043D\u044B\u0439 \u043A\u043E\u043B\u043B\u0435\u043A\u0442\u0438\u0432 \u00AB\u041D\u043E\u0432\u043E\u0439 \u0433\u0430\u0437\u0435\u0442\u044B\u00BB'
category = 'newspaper'
cover_url = u'https://novaya.media/ic_puzzle_footer.svg'
language = 'ru'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 30
remove_tags_before = dict(name='h1', attrs={'class': 'Header_title__2zxwH'})
remove_tags_after = dict(name='div', attrs={'class': 'Post_contentInnerWrapper__3GWHl'})
feeds = [
('\u0421\u0432\u043E\u0431\u043E\u0434\u043D\u043E\u0435 \u043F\u0440\u043E\u0441\u0442\u0440\u0430\u043D\u0441\u0442\u0432\u043E', 'https://novaya.media/feed/rss')
]
def print_version(self, url):
return url + '?print=true'
KyivPost: Ukraine’s English-language newspaper. Favicon. Fixes needed:
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 KyivPost(BasicNewsRecipe):
title = 'Kyiv Post'
__author__ = 'bugmen00t'
description = 'The Kyiv Post is Ukraine\u2019s English-language newspaper. The newspaper\u2019s first print edition came out on Oct. 18, 1995, and went online in 1997. The newspaper\u2019s motto is \u201CUkraine\u2019s Global Voice,\u201D which in 2018 replaced the previous motto of \u201CIndependence. Community. Trust.\u201D Both slogans reflect the newspaper\u2019s commitment to the highest journalistic and ethical standards.'
publisher = 'BIZNESGRUPP TOV'
category = 'newspaper'
cover_url = u'https://www.kyivpost.com/wp-content/themes/kyivpost/assets/img/svg/logo-foot.svg'
language = 'en_UK'
no_stylesheets = False
remove_javascript = True
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 10
remove_tags_before = dict(name='article', attrs={'class': 'article'})
remove_tags_after = dict(name='article', attrs={'class': 'article'})
remove_tags = [
dict(name='div', attrs={'class': 'entry-footer hide_post_header'})
]
feeds = [
('News', 'https://www.kyivpost.com/feed')
]
Ukrainian version: 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 KyivPost(BasicNewsRecipe):
title = 'Kyiv Post'
__author__ = 'bugmen00t'
description = '\u0423\u043A\u0440\u0430\u0457\u043D\u0441\u044C\u043A\u0430 \u0430\u043D\u0433\u043B\u043E\u043C\u043E\u0432\u043D\u0430 \u0433\u0430\u0437\u0435\u0442\u0430, \u043D\u0430\u0433\u043E\u0440\u043E\u0434\u0436\u0435\u043D\u0430 \u0443 2014 \u0440\u043E\u043A\u0443. \u041F\u0435\u0440\u0448\u0438\u0439 \u0434\u0440\u0443\u043A\u043E\u0432\u0430\u043D\u0438\u0439 \u043F\u0440\u0438\u043C\u0456\u0440\u043D\u0438\u043A \u0433\u0430\u0437\u0435\u0442\u0438 \u0432\u0438\u0439\u0448\u043E\u0432 18 \u0436\u043E\u0432\u0442\u043D\u044F 1995 \u0440\u043E\u043A\u0443, \u0430 \u0432 \u0406\u043D\u0442\u0435\u0440\u043D\u0435\u0442-\u0432\u0430\u0440\u0456\u0430\u043D\u0442\u0456 Kyiv Post \u0437\u2019\u044F\u0432\u0438\u043B\u0430\u0441\u044C \u0432 1997 \u0440\u043E\u0446\u0456. \u0414\u0435\u0432\u0456\u0437 \u0433\u0430\u0437\u0435\u0442\u0438: \u00AB\u0413\u043B\u043E\u0431\u0430\u043B\u044C\u043D\u0438\u0439 \u0433\u043E\u043B\u043E\u0441 \u0423\u043A\u0440\u0430\u0457\u043D\u0438\u00BB, \u044F\u043A\u0438\u0439 \u0443 2018 \u0440\u043E\u0446\u0456 \u0437\u0430\u043C\u0456\u043D\u0438\u0432 \u043F\u043E\u043F\u0435\u0440\u0435\u0434\u043D\u0456\u0439 \u0434\u0435\u0432\u0456\u0437 \u00AB\u041D\u0435\u0437\u0430\u043B\u0435\u0436\u043D\u0456\u0441\u0442\u044C. \u0421\u043F\u0456\u043B\u044C\u043D\u043E\u0442\u0430. \u0414\u043E\u0432\u0456\u0440\u0430.\u00BB \u041E\u0431\u0438\u0434\u0432\u0430 \u0433\u0430\u0441\u043B\u0430 \u0432\u0456\u0434\u043E\u0431\u0440\u0430\u0436\u0430\u044E\u0442\u044C \u0442\u0435, \u0449\u043E \u0443 \u0432\u0438\u0434\u0430\u043D\u043D\u0456 \u0434\u043E\u0442\u0440\u0438\u043C\u0443\u044E\u0442\u044C\u0441\u044F \u043D\u0430\u0439\u0432\u0438\u0449\u0438\u0445 \u0436\u0443\u0440\u043D\u0430\u043B\u0456\u0441\u0442\u0441\u044C\u043A\u0438\u0445 \u0442\u0430 \u0435\u0442\u0438\u0447\u043D\u0438\u0445 \u0441\u0442\u0430\u043D\u0434\u0430\u0440\u0442\u0456\u0432.'
publisher = 'BIZNESGRUPP TOV'
category = 'newspaper'
cover_url = u'https://www.kyivpost.com/wp-content/themes/kyivpost/assets/img/svg/logo-foot.svg'
language = 'uk'
no_stylesheets = False
remove_javascript = True
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 10
remove_tags_before = dict(name='article', attrs={'class': 'article'})
remove_tags_after = dict(name='article', attrs={'class': 'article'})
remove_tags = [
dict(name='div', attrs={'class': 'entry-footer hide_post_header'})
]
feeds = [
('\u041D\u043E\u0432\u0438\u043D\u0438', 'https://www.kyivpost.com/uk/feed')
]
Arabic version (not sure if output is correct as the text is not RTL)  :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 KyivPost(BasicNewsRecipe):
title = '\u0643\u064A\u064A\u0641 \u0628\u0648\u0633\u062A (Kyiv Post)'
__author__ = 'bugmen00t'
description = '\u0643\u064A\u064A\u0641 \u0628\u0648\u0633\u062A \u0647\u064A \u0635\u062D\u064A\u0641\u0629 \u0623\u0648\u0643\u0631\u0627\u0646\u064A\u0629 \u062A\u0635\u062F\u0631 \u0628\u0627\u0644\u0644\u063A\u0629 \u0627\u0644\u0625\u0646\u062C\u0644\u064A\u0632\u064A\u0629 \u0648\u0647\u064A \u0641\u0627\u0626\u0632\u0629 \u0628\u0645\u064A\u062F\u0627\u0644\u064A\u0629 Missouri Honor 2014 \u0644\u0644\u062E\u062F\u0645\u0629 \u0627\u0644\u0645\u062A\u0645\u064A\u0632\u0629 \u0641\u064A \u0627\u0644\u0635\u062D\u0627\u0641\u0629. \u0635\u062F\u0631\u062A \u0627\u0644\u0646\u0633\u062E\u0629 \u0627\u0644\u0645\u0637\u0628\u0648\u0639\u0629 \u0627\u0644\u0623\u0648\u0644\u0649 \u0645\u0646 \u0627\u0644\u0635\u062D\u064A\u0641\u0629 \u0641\u064A 18 \u0623\u0643\u062A\u0648\u0628\u0631 1995\u060C \u0648\u062A\u0645 \u0646\u0634\u0631\u0647\u0627 \u0639\u0644\u0649 \u0627\u0644\u0625\u0646\u062A\u0631\u0646\u062A \u0641\u064A \u0639\u0627\u0645 1997. \u0648\u0643\u0627\u0646 \u062C\u0645\u0647\u0648\u0631\u0647\u0627 \u0627\u0644\u0639\u0627\u0644\u0645\u064A \u064A\u0646\u0645\u0648 \u0628\u0627\u0637\u0631\u0627\u062F \u0645\u0646\u0630 \u0630\u0644\u0643 \u0627\u0644\u062D\u064A\u0646 \u060C \u0648\u0628\u0644\u063A \u0630\u0631\u0648\u062A\u0647 \u0628\u0623\u0643\u062B\u0631 \u0645\u0646 65 \u0645\u0644\u064A\u0648\u0646 \u0645\u0634\u0627\u0647\u062F\u0629 \u0644\u0644\u0635\u0641\u062D\u0629 \u0641\u064A \u0639\u0627\u0645 2014. \u0634\u0639\u0627\u0631 \u0627\u0644\u0635\u062D\u064A\u0641\u0629 \u0647\u0648 \u201C\u0635\u0648\u062A \u0623\u0648\u0643\u0631\u0627\u0646\u064A\u0627 \u0644\u0644\u0639\u0627\u0644\u0645\u201D\u060C \u0648\u0627\u0644\u0630\u064A \u062D\u0644 \u0641\u064A \u0639\u0627\u0645 2018 \u0645\u062D\u0644 \u0627\u0644\u0634\u0639\u0627\u0631 \u0627\u0644\u0633\u0627\u0628\u0642 \u201C\u0627\u0644\u0627\u0633\u062A\u0642\u0644\u0627\u0644. \u062A\u0648\u0627\u0635\u0644 \u0627\u062C\u062A\u0645\u0627\u0639\u064A. \u0627\u0644\u062B\u0642\u0629\u201D. \u0643\u0644\u0627 \u0627\u0644\u0634\u0639\u0627\u0631\u064A\u0646 \u064A\u0639\u0643\u0633\u0627\u0646 \u0627\u0644\u062A\u0632\u0627\u0645 \u0627\u0644\u0635\u062D\u064A\u0641\u0629 \u0628\u0623\u0639\u0644\u0649 \u0627\u0644\u0645\u0639\u0627\u064A\u064A\u0631 \u0627\u0644\u0635\u062D\u0641\u064A\u0629 \u0648\u0627\u0644\u0623\u062E\u0644\u0627\u0642\u064A\u0629.'
publisher = 'BIZNESGRUPP TOV'
category = 'newspaper'
cover_url = u'https://www.kyivpost.com/wp-content/themes/kyivpost/assets/img/svg/logo-foot.svg'
language = 'ar'
no_stylesheets = False
remove_javascript = True
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 10
remove_tags_before = dict(name='article', attrs={'class': 'article'})
remove_tags_after = dict(name='article', attrs={'class': 'article'})
remove_tags = [
dict(name='div', attrs={'class': 'entry-footer hide_post_header'})
]
feeds = [
('\u0627\u0644\u0625\u062E\u0628\u0627\u0631\u064A\u0629', 'https://www.kyivpost.com/ar/feed')
]
The Moscow Times: English- and Russian-language online newspaper. Favicon. Russain version: 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 MoscowTimes(BasicNewsRecipe):
title = 'The Moscow Times'
__author__ = 'bugmen00t'
description = '\u0410\u043D\u0433\u043B\u043E\u044F\u0437\u044B\u0447\u043D\u043E\u0435 \u0438\u0437\u0434\u0430\u043D\u0438\u0435 \u043E \u0420\u043E\u0441\u0441\u0438\u0438. \u041D\u0430\u0448\u0430 \u0440\u0435\u0434\u0430\u043A\u0446\u0438\u044F \u0434\u0435\u043B\u0438\u0442\u0441\u044F \u0441 \u0447\u0438\u0442\u0430\u0442\u0435\u043B\u044F\u043C\u0438 \u043F\u043E \u0432\u0441\u0435\u043C\u0443 \u043C\u0438\u0440\u0443 \u043F\u043E\u0441\u043B\u0435\u0434\u043D\u0438\u043C\u0438 \u043D\u043E\u0432\u043E\u0441\u0442\u044F\u043C\u0438 \u0438 \u0441\u0430\u043C\u044B\u043C\u0438 \u0438\u043D\u0442\u0435\u0440\u0435\u0441\u043D\u044B\u043C\u0438 \u0441\u043E\u0431\u044B\u0442\u0438\u044F\u043C\u0438 \u0441\u0430\u043C\u043E\u0439 \u0431\u043E\u043B\u044C\u0448\u043E\u0439 \u0441\u0442\u0440\u0430\u043D\u044B \u043D\u0430 \u0417\u0435\u043C\u043B\u0435.'
publisher = '\u041E\u041E\u041E \u0422\u0438\u044D\u043C\u0442\u0438'
category = 'newspaper'
cover_url = u'https://static.themoscowtimes.com/img/share_default.jpg'
language = 'ru'
no_stylesheets = False
remove_javascript = True
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 50
remove_tags_before = dict(name='article')
remove_tags_after = dict(name='div', attrs={'class': 'article__bottom'})
remove_tags = [
dict(name='div', attrs={'class': 'social'}),
dict(name='div', attrs={'class': 'related-article__content'})
]
feeds = [
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://www.moscowtimes.ru/rss/news'),
('\u041C\u043D\u0435\u043D\u0438\u044F', 'https://www.moscowtimes.ru/rss/opinion'),
('\u041F\u0435\u0440\u0435\u0432\u043E\u0434\u044B Financial Times', 'https://www.moscowtimes.ru/rss/ft')
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src']
return soup
English version: 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 MoscowTimes(BasicNewsRecipe):
title = 'The Moscow Times'
__author__ = 'bugmen00t'
description = 'The Moscow Times is Russia’s leading, independent English-language media outlet. Our team of Russian and English journalists provide readers across the world with breaking news, engaging stories and balanced reporting about the largest country on Earth.'
publisher = 'Tiamti LLC'
category = 'newspaper'
cover_url = u'https://static.themoscowtimes.com/img/share_default.jpg'
language = 'en_RU'
no_stylesheets = False
remove_javascript = True
auto_cleanup = False
oldest_article = 14
max_articles_per_feed = 50
remove_tags_before = dict(name='article')
remove_tags_after = dict(name='div', attrs={'class': 'article__tags'})
remove_tags = [
dict(name='aside'),
dict(name='footer'),
dict(name='section', attrs={'class': 'cluster'}),
dict(name='div', attrs={'class': 'article__tags'}),
dict(name='div', attrs={'class': 'social'}),
dict(name='div', attrs={'class': 'related-article__content'})
]
feeds = [
('News', 'https://www.themoscowtimes.com/rss/news'),
('Opinion', 'https://www.themoscowtimes.com/rss/opinion'),
('Arts and Life', 'https://www.themoscowtimes.com/rss/city'),
('Meanwhile', 'https://www.themoscowtimes.com/rss/meanwhile')
]
Довод: local news from Vladimir city & local regions. Favicon. Fixes needed:
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 Dovod(BasicNewsRecipe):
title = '\u0414\u043E\u0432\u043E\u0434'
__author__ = 'bugmen00t'
description = '\u0421\u0430\u0439\u0442 \u00AB\u0414\u043E\u0432\u043E\u0434\u00BB \u043F\u043E\u043B\u0443\u0447\u0438\u043B \u0441\u0432\u043E\u0451 \u043D\u0430\u0437\u0432\u0430\u043D\u0438\u0435 \u0432 \u0447\u0435\u0441\u0442\u044C \u0440\u0430\u043D\u0435\u0435 \u0441\u043E\u0437\u0434\u0430\u043D\u043D\u043E\u0433\u043E \u043F\u0440\u043E\u0435\u043A\u0442\u0430 \u00AB\u0414\u043E\u0432\u043E\u0434 \u2014 \u0412\u043B\u0430\u0434\u0438\u043C\u0438\u0440\u0441\u043A\u0438\u0435 \u043E\u0431\u0449\u0435\u0441\u0442\u0432\u0435\u043D\u043D\u044B\u0435 \u0434\u0438\u0441\u043A\u0443\u0441\u0441\u0438\u0438\u00BB. \u041D\u0430\u0448\u0430 \u0446\u0435\u043B\u044C \u2014 \u043E\u0441\u0432\u0435\u0449\u0435\u043D\u0438\u0435 \u0430\u043A\u0442\u0443\u0430\u043B\u044C\u043D\u044B\u0445 \u043E\u0431\u0449\u0435\u0441\u0442\u0432\u0435\u043D\u043D\u043E-\u043F\u043E\u043B\u0438\u0442\u0438\u0447\u0435\u0441\u043A\u0438\u0445 \u0432\u043E\u043F\u0440\u043E\u0441\u043E\u0432 \u0438 \u0438\u0445 \u043E\u0442\u043A\u0440\u043E\u0432\u0435\u043D\u043D\u043E\u0435 \u0438 \u043E\u0441\u043C\u044B\u0441\u043B\u0435\u043D\u043D\u043E\u0435 \u043E\u0431\u0441\u0443\u0436\u0434\u0435\u043D\u0438\u0435.'
publisher = '\u0418\u043B\u044C\u044F \u041A\u043E\u0441\u044B\u0433\u0438\u043D, \u041A\u0438\u0440\u0438\u043B\u043B \u0418\u0448\u0443\u0442\u0438\u043D'
category = 'blog'
cover_url = u'https://pbs.twimg.com/profile_images/1498229545505284099/l9V1l59Z_400x400.jpg'
language = 'ru'
no_stylesheets = True
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 10
remove_tags_before = dict(name='article')
remove_tags_after = dict(name='div', attrs={'class': 'entry-content'})
feeds = [
('\u0414\u043E\u0432\u043E\u0434', 'https://www.dovod.online/feed/')
]
Last edited by bugmen00t; 08-17-2022 at 09:16 AM. |
|
|
|
|
08-17-2022, 08:02 AM
|
#24 |
|
Connoisseur
Posts: 65
Karma: 100000
Join Date: Aug 2015
Device: Kindle Keyboard + Kindle Voyage WiFi + Kindle PW11 Kids
|
New recipes (part 12 of ??)
Another bunch of Russian and Ukrainian sources.
Теплица социальных технологий: IT- & tech building project for non-government organisations. 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 Teplitsa(BasicNewsRecipe):
title = '\u0422\u0435\u043F\u043B\u0438\u0446\u0430 \u0441\u043E\u0446\u0438\u0430\u043B\u044C\u043D\u044B\u0445 \u0442\u0435\u0445\u043D\u043E\u043B\u043E\u0433\u0438\u0439'
__author__ = 'bugmen00t'
description = '\u0422\u0435\u043F\u043B\u0438\u0446\u0430 \u0441\u043E\u0446\u0438\u0430\u043B\u044C\u043D\u044B\u0445 \u0442\u0435\u0445\u043D\u043E\u043B\u043E\u0433\u0438\u0439 \u2014 \u043D\u0435\u0437\u0430\u0432\u0438\u0441\u0438\u043C\u044B\u0439 \u043F\u0440\u043E\u0441\u0432\u0435\u0442\u0438\u0442\u0435\u043B\u044C\u0441\u043A\u0438\u0439 \u0438 \u0440\u0430\u0437\u0432\u0438\u0432\u0430\u044E\u0449\u0438\u0439 \u043F\u0440\u043E\u0435\u043A\u0442, \u043C\u0438\u0441\u0441\u0438\u044F \u043A\u043E\u0442\u043E\u0440\u043E\u0433\u043E \u2014 \u0443\u0441\u0438\u043B\u0438\u0442\u044C \u0440\u043E\u0441\u0441\u0438\u0439\u0441\u043A\u043E\u0435 \u0433\u0440\u0430\u0436\u0434\u0430\u043D\u0441\u043A\u043E\u0435 \u043E\u0431\u0449\u0435\u0441\u0442\u0432\u043E \u0441 \u043F\u043E\u043C\u043E\u0449\u044C\u044E \u0438\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u043E\u043D\u043D\u044B\u0445 \u0442\u0435\u0445\u043D\u043E\u043B\u043E\u0433\u0438\u0439.'
publisher = '\u0410\u041D\u041E \u00AB\u0410\u0433\u0435\u043D\u0442\u0441\u0442\u0432\u043E \u0441\u043E\u0446\u0438\u0430\u043B\u044C\u043D\u043E\u0439 \u0438\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u0438\u00BB'
category = 'blog'
cover_url = u'https://te-st.ru/wp-content/uploads/2014/05/logo_test.png'
language = 'ru'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
remove_empty_feeds = True
oldest_article = 30
max_articles_per_feed = 15
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='article')
remove_tags = [
dict(name='div', attrs={'class': 'post-reading-time'}),
dict(name='div', attrs={'class': 'read-more'}),
dict(name='p', attrs={'class': 'author-name'}),
dict(name='p', attrs={'class': 'author-about'}),
dict(name='footer')
]
feeds = [
('\u0412\u0441\u0435 \u043C\u0430\u0442\u0435\u0440\u0438\u0430\u043B\u044B', 'https://te-st.ru/feed'),
('\u0416\u0443\u0440\u043D\u0430\u043B', 'https://te-st.ru/section/journal/feed/'),
('\u041F\u0440\u0430\u043A\u0442\u0438\u043A\u0430', 'https://te-st.ru/section/practice/feed/'),
('\u0412\u0441\u0442\u0440\u0435\u0447\u0438', 'https://te-st.ru/section/events/feed/'),
('\u0410\u0440\u0445\u0438\u0432', 'https://te-st.ru/section/archive/feed/'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u044C', 'https://te-st.ru/format/news-2/feed/'),
('\u0421\u0442\u0430\u0442\u044C\u0438', 'https://te-st.ru/format/article/feed/'),
('\u0418\u043D\u0442\u0435\u0440\u0432\u044C\u044E', 'https://te-st.ru/format/interview/feed/'),
('\u041A\u0435\u0439\u0441\u044B', 'https://te-st.ru/format/case/feed/'),
('\u0421\u043F\u0438\u0441\u043A\u0438', 'https://te-st.ru/format/list/feed/'),
('\u0418\u0441\u0442\u043E\u0440\u0438\u0438', 'https://te-st.ru/format/story/feed/'),
('\u0418\u043D\u0441\u0442\u0440\u0443\u043A\u0446\u0438\u0438', 'https://te-st.ru/format/guide/feed/'),
('\u041E\u0431\u0437\u043E\u0440\u044B', 'https://te-st.ru/format/overview/feed/'),
('\u0410\u043D\u0430\u043B\u0438\u0442\u0438\u043A\u0430', 'https://te-st.ru/tag/analytics/feed'),
('\u0410\u043D\u0442\u0438\u0432\u043E\u0435\u043D\u043D\u044B\u0435 \u043A\u0430\u043C\u043F\u0430\u043D\u0438\u0438', 'https://te-st.ru/tag/antivoennye-kampanii/feed'),
('\u0411\u043B\u043E\u043A\u0447\u0435\u0439\u043D', 'https://te-st.ru/tag/blockchain/feed'),
('\u0411\u043E\u0440\u044C\u0431\u0430 \u0441 \u0431\u0435\u0434\u043D\u043E\u0441\u0442\u044C\u044E', 'https://te-st.ru/tag/poverty/feed'),
('\u0412\u0430\u043A\u0430\u043D\u0441\u0438\u0438 \u0432 \u041D\u041A\u041E', 'https://te-st.ru/tag/vacancies/feed'),
('\u0412\u0438\u0437\u0443\u0430\u043B\u0438\u0437\u0430\u0446\u0438\u044F', 'https://te-st.ru/tag/visualization/feed'),
('\u0413\u0435\u043D\u0434\u0435\u0440\u043D\u043E\u0435 \u043D\u0430\u0441\u0438\u043B\u0438\u0435', 'https://te-st.ru/tag/gender-violence/feed'),
('\u0413\u0440\u0430\u0436\u0434\u0430\u043D\u0441\u043A\u0438\u0435 \u0442\u0435\u0445\u043D\u043E\u043B\u043E\u0433\u0438\u0438', 'https://te-st.ru/tag/civictech/feed'),
('\u0418\u043C\u043F\u0430\u043A\u0442-\u0438\u043D\u0432\u0435\u0441\u0442\u0438\u0440\u043E\u0432\u0430\u043D\u0438\u0435', 'https://te-st.ru/tag/impact-investing/feed'),
('\u0418\u043D\u043A\u043B\u044E\u0437\u0438\u0432\u043D\u044B\u0439 \u0434\u0438\u0437\u0430\u0439\u043D', 'https://te-st.ru/tag/inclusive-design/feed'),
('\u0418\u043D\u0441\u0442\u0440\u0443\u043C\u0435\u043D\u0442\u044B \u0438 \u043F\u0440\u0438\u043B\u043E\u0436\u0435\u043D\u0438\u044F', 'https://te-st.ru/tag/tools/feed'),
('\u0418\u043D\u0444\u043E\u0431\u0438\u0437\u043D\u0435\u0441', 'https://te-st.ru/tag/infobusiness/feed'),
('\u0418\u0441\u0441\u043B\u0435\u0434\u043E\u0432\u0430\u043D\u0438\u044F \u0432 \u041D\u041A\u041E', 'https://te-st.ru/tag/research/feed'),
('\u0418\u0442\u043E\u0433\u0438 \u0433\u043E\u0434\u0430', 'https://te-st.ru/tag/results-of-the-year/feed'),
('\u041A\u0430\u043D\u0434\u0438\u043D\u0441\u043A\u0438\u0439', 'https://te-st.ru/tag/kandinsky/feed'),
('\u041A\u0430\u0440\u0442\u044B \u0438 \u043A\u0430\u0440\u0442\u043E\u0433\u0440\u0430\u0444\u0438\u044F', 'https://te-st.ru/tag/maps/feed'),
('\u041A\u043E\u043C\u043C\u0443\u043D\u0438\u043A\u0430\u0446\u0438\u044F', 'https://te-st.ru/tag/discussion/feed'),
('\u041A\u043E\u0440\u043E\u043D\u0430\u0432\u0438\u0440\u0443\u0441', 'https://te-st.ru/tag/coronavirus/feed'),
('\u041A\u0440\u0430\u0443\u0434\u0441\u043E\u0440\u0441\u0438\u043D\u0433', 'https://te-st.ru/tag/crowdsourcing/feed'),
('\u041A\u0440\u0430\u0443\u0434\u0444\u0430\u043D\u0434\u0438\u043D\u0433', 'https://te-st.ru/tag/crowdfunding/feed'),
('\u041A\u0443\u043B\u044C\u0442\u0443\u0440\u0430 \u0438 \u0442\u0435\u0445\u043D\u043E\u043B\u043E\u0433\u0438\u0438', 'https://te-st.ru/tag/tech-culture/feed'),
('\u041B\u0430\u0431\u043E\u0440\u0430\u0442\u043E\u0440\u0438\u044F', 'https://te-st.ru/tag/laboratory/feed'),
('\u041B\u0438\u0434\u0435\u0440\u0441\u0442\u0432\u043E', 'https://te-st.ru/tag/leadership/feed'),
('\u041C\u0430\u0440\u043A\u0435\u0442\u0438\u043D\u0433', 'https://te-st.ru/tag/marketing/feed'),
('\u041C\u0430\u0448\u0438\u043D\u043D\u043E\u0435 \u043E\u0431\u0443\u0447\u0435\u043D\u0438\u0435', 'https://te-st.ru/tag/machine-learning/feed'),
('\u041C\u0435\u0434\u0438\u0446\u0438\u043D\u0441\u043A\u0438\u0435 \u0442\u0435\u0445\u043D\u043E\u043B\u043E\u0433\u0438\u0438', 'https://te-st.ru/tag/medtech/feed'),
('\u041C\u0435\u043D\u0435\u0434\u0436\u043C\u0435\u043D\u0442', 'https://te-st.ru/tag/management/feed'),
('\u041C\u0435\u0441\u0441\u0435\u043D\u0434\u0436\u0435\u0440\u044B', 'https://te-st.ru/tag/messengers/feed'),
('\u041C\u043E\u0431\u0438\u043B\u044C\u043D\u044B\u0435 \u0440\u0435\u0448\u0435\u043D\u0438\u044F', 'https://te-st.ru/tag/mobile/feed'),
('\u041E\u0431\u0449\u0435\u0441\u0442\u0432\u0435\u043D\u043D\u044B\u0435 \u043A\u0430\u043C\u043F\u0430\u043D\u0438\u0438', 'https://te-st.ru/tag/campaigning/feed'),
('\u041E\u043D\u043B\u0430\u0439\u043D-\u041B\u0435\u0439\u043A\u0430', 'https://te-st.ru/tag/online-leyka/feed'),
('\u041E\u043D\u043B\u0430\u0439\u043D-\u043E\u0431\u0440\u0430\u0437\u043E\u0432\u0430\u043D\u0438\u0435', 'https://te-st.ru/tag/education-online/feed'),
('\u041E\u0442\u043A\u0440\u044B\u0442\u044B\u0435 \u0434\u0430\u043D\u043D\u044B\u0435', 'https://te-st.ru/tag/open-data/feed'),
('\u041E\u0442\u043A\u0440\u044B\u0442\u044B\u0439 \u043A\u043E\u0434', 'https://te-st.ru/tag/opensource/feed'),
('\u041F\u0430\u0441\u0435\u043A\u0430', 'https://te-st.ru/tag/paseka/feed'),
('\u041F\u0440\u0430\u0432\u043E\u0432\u0430\u044F \u0431\u0430\u0437\u0430', 'https://te-st.ru/tag/regulations/feed'),
('\u041F\u0440\u043E\u0433\u0440\u0430\u043C\u043C\u0438\u0440\u043E\u0432\u0430\u043D\u0438\u0435', 'https://te-st.ru/tag/programming/feed'),
('\u0420\u0435\u043B\u0438\u0437\u044B \u00AB\u041B\u0435\u0439\u043A\u0438\u00BB', 'https://te-st.ru/tag/leyka-release/feed'),
('\u0421\u0435\u043D\u0441\u043E\u0440\u044B', 'https://te-st.ru/tag/sensors/feed'),
('\u0421\u043E\u0437\u0434\u0430\u043D\u0438\u0435 \u0432\u0438\u0434\u0435\u043E', 'https://te-st.ru/tag/video/feed'),
('\u0421\u043E\u0446\u0438\u0430\u043B\u044C\u043D\u043E-\u043E\u0440\u0438\u0435\u043D\u0442\u0438\u0440\u043E\u0432\u0430\u043D\u043D\u044B\u0439 \u0434\u0438\u0437\u0430\u0439\u043D', 'https://te-st.ru/tag/responsible-design/feed'),
('\u0421\u043E\u0446\u0438\u0430\u043B\u044C\u043D\u043E\u0435 \u043F\u0440\u0435\u0434\u043F\u0440\u0438\u043D\u0438\u043C\u0430\u0442\u0435\u043B\u044C\u0441\u0442\u0432\u043E', 'https://te-st.ru/tag/social-entrepreneurship/feed'),
('\u0421\u0442\u0430\u0440\u0442\u0430\u043F\u044B', 'https://te-st.ru/tag/startups/feed'),
('\u0422\u0435\u043F\u043B\u0438\u0446\u0430.\u041A\u0443\u0440\u0441\u044B', 'https://te-st.ru/tag/teplitsa-kursy/feed'),
('\u0422\u0435\u0445\u043D\u043E\u043B\u043E\u0433\u0438\u0438 \u0432 \u0431\u043E\u0440\u044C\u0431\u0435 \u0441 \u0440\u0430\u043A\u043E\u043C', 'https://te-st.ru/tag/cancer/feed'),
('\u0422\u0435\u0445\u043D\u043E\u043B\u043E\u0433\u0438\u0438 \u0434\u043B\u044F \u043F\u043E\u0436\u0438\u043B\u044B\u0445', 'https://te-st.ru/tag/itforelderly/feed'),
('\u0422\u043E\u043A\u0438\u043E', 'https://te-st.ru/tag/tokio/feed'),
('\u0423\u0434\u0430\u043B\u0435\u043D\u043D\u0430\u044F \u0440\u0430\u0431\u043E\u0442\u0430', 'https://te-st.ru/tag/remote-work/feed'),
('\u0424\u0430\u043D\u0434\u0440\u0430\u0439\u0437\u0438\u043D\u0433', 'https://te-st.ru/tag/fundraising/feed'),
('\u0424\u043E\u0442\u043E\u0433\u0440\u0430\u0444\u0438\u0438', 'https://te-st.ru/tag/photo/feed'),
('\u0426\u0438\u0444\u0440\u043E\u0432\u0430\u044F \u0431\u0435\u0437\u043E\u043F\u0430\u0441\u043D\u043E\u0441\u0442\u044C', 'https://te-st.ru/tag/digital-security/feed'),
('\u0426\u0438\u0444\u0440\u043E\u0432\u0430\u044F \u0442\u0440\u0430\u043D\u0441\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u044F', 'https://te-st.ru/tag/digital-transformation/feed'),
('\u0426\u0438\u0444\u0440\u043E\u0432\u044B\u0435 \u043F\u0440\u0430\u0432\u0430', 'https://te-st.ru/tag/digital-rights/feed'),
('\u0427\u0430\u0442-\u0431\u043E\u0442\u044B', 'https://te-st.ru/tag/chatbots/feed'),
('\u042D\u043A\u043E\u043B\u043E\u0433\u0438\u044F', 'https://te-st.ru/tag/ecology/feed'),
('\u042D\u0442\u0438\u043A\u0430 \u0432 \u0442\u0435\u0445\u043D\u043E\u043B\u043E\u0433\u0438\u044F\u0445', 'https://te-st.ru/tag/ethics/feed'),
('IT-\u0432\u043E\u043B\u043E\u043D\u0442\u0435\u0440', 'https://te-st.ru/tag/itv/feed'),
('Meet and code', 'https://te-st.ru/tag/meet-and-code/feed'),
('PhilTech', 'https://te-st.ru/tag/philtech/feed'),
('Scrum', 'https://te-st.ru/tag/scrum/feed'),
('TeploDigital', 'https://te-st.ru/tag/teplodigital/feed'),
('UX/UI \u0434\u0438\u0437\u0430\u0439\u043D', 'https://te-st.ru/tag/uxui/feed'),
('VR/AR \u0442\u0435\u0445\u043D\u043E\u043B\u043E\u0433\u0438\u0438', 'https://te-st.ru/tag/arvr/feed'),
('WordPress', 'https://te-st.ru/tag/wordpress/feed')
]
Такие дела: social journalism & fundraising platform for charitable projects. 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 TakieDela(BasicNewsRecipe):
title = '\u0422\u0430\u043A\u0438\u0435 \u0434\u0435\u043B\u0430'
__author__ = 'bugmen00t'
description = '\u0418\u0437\u0434\u0430\u043D\u0438\u0435 \u00AB\u0422\u0430\u043A\u0438\u0435 \u0434\u0435\u043B\u0430\u00BB \u043E\u0441\u0432\u0435\u0449\u0430\u0435\u0442 \u0441\u043E\u0446\u0438\u0430\u043B\u044C\u043D\u044B\u0435 \u043F\u0440\u043E\u0431\u043B\u0435\u043C\u044B, \u043F\u0438\u0448\u0435\u0442 \u043E \u043F\u0440\u043E\u0431\u043B\u0435\u043C\u0430\u0445 \u043B\u044E\u0434\u0435\u0439 \u0441 \u0440\u0435\u0434\u043A\u0438\u043C\u0438 \u0437\u0430\u0431\u043E\u043B\u0435\u0432\u0430\u043D\u0438\u044F\u043C\u0438 \u0438 \u0438\u043D\u0432\u0430\u043B\u0438\u0434\u043D\u043E\u0441\u0442\u044C\u044E, \u043E \u0441\u043E\u0441\u0442\u043E\u044F\u043D\u0438\u0438 \u0440\u043E\u0441\u0441\u0438\u0439\u0441\u043A\u043E\u0439 \u043C\u0435\u0434\u0438\u0446\u0438\u043D\u044B, \u0430 \u0442\u0430\u043A\u0436\u0435 \u043E \u0431\u043B\u0430\u0433\u043E\u0442\u0432\u043E\u0440\u0438\u0442\u0435\u043B\u044C\u043D\u043E\u0441\u0442\u0438 \u0438 \u0441\u043E\u0446\u0438\u0430\u043B\u044C\u043D\u043E\u0439 \u043E\u0431\u0441\u0442\u0430\u043D\u043E\u0432\u043A\u0435 \u0432 \u0420\u043E\u0441\u0441\u0438\u0438. \u0422\u0430\u043A\u0436\u0435 \u0438\u0437\u0434\u0430\u043D\u0438\u0435 \u0432\u0437\u0430\u0438\u043C\u043E\u0434\u0435\u0439\u0441\u0442\u0432\u0443\u0435\u0442 \u0441 \u043D\u0435\u043A\u043E\u043C\u043C\u0435\u0440\u0447\u0435\u0441\u043A\u0438\u043C\u0438 \u043E\u0440\u0433\u0430\u043D\u0438\u0437\u0430\u0446\u0438\u044F\u043C\u0438, \u0441\u043E\u0431\u0438\u0440\u0430\u044F \u0438\u0441\u0442\u043E\u0440\u0438\u0438 \u043E \u0431\u043B\u0430\u0433\u043E\u0442\u0432\u043E\u0440\u0438\u0442\u0435\u043B\u044C\u043D\u044B\u0445 \u043F\u0440\u043E\u0435\u043A\u0442\u0430\u0445, \u0438 \u0437\u0430\u043D\u0438\u043C\u0430\u0435\u0442\u0441\u044F \u0441\u0431\u043E\u0440\u043E\u043C \u0441\u0440\u0435\u0434\u0441\u0442\u0432 (\u043A\u0440\u0430\u0443\u0434\u0444\u0430\u043D\u0434\u0438\u043D\u0433\u043E\u043C) \u0434\u043B\u044F \u0444\u043E\u043D\u0434\u0430 \u00AB\u041D\u0443\u0436\u043D\u0430 \u043F\u043E\u043C\u043E\u0449\u044C\u00BB.'
publisher = '\u0411\u043B\u0430\u0433\u043E\u0442\u0432\u043E\u0440\u0438\u0442\u0435\u043B\u044C\u043D\u044B\u0439 \u0444\u043E\u043D\u0434 \u00AB\u041D\u0443\u0436\u043D\u0430 \u041F\u043E\u043C\u043E\u0449\u044C\u00BB'
category = 'blog'
cover_url = u'https://takiedela.ru/wp-content/themes/takiedela/assets/image/share/td.jpg'
language = 'ru'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
remove_empty_feeds = True
oldest_article = 30
max_articles_per_feed = 10
remove_tags_before = dict(name='header')
remove_tags_after = dict(name='article')
remove_tags = [
dict(name='section', attrs={'class': 'b-post__materials b-line b-line_p-60 b-line_grey b-line_nomb'}),
dict(name='section', attrs={'class': 'b-post-material__other b-line b-line_p-60 b-line_bg b-line_nomb'}),
dict(name='div', attrs={'class': 'b-single__case-closed'}),
dict(name='div', attrs={'class': 'b-line b-total-sum'}),
dict(name='section', attrs={'class': 'b-post-material__help b-line b-line_p-60 b-line_grey b-line_nomb'}),
dict(name='section', attrs={'class': 'b-line b-line_p-60 b-line_bg b-line_nopb b-line_nomb '}),
dict(name='header', attrs={'class': 'np-header js-np-header'}),
dict(name='div', attrs={'class': 'b-post__head-info__block b-post__head-info__block_views in-tablet'}),
dict(name='div', attrs={'class': 'np-donate-form__bg np-donate-form__bg_border'}),
dict(name='div', attrs={'class': 'b-photostory-help i-photostory-help'}),
dict(name='div', attrs={'class': 'mistape_caption'}),
dict(name='div', attrs={'class': 'b-photostory__inner'}),
dict(name='div', attrs={'class': 'b-single__extra i-single__extra'}),
dict(name='div', attrs={'class': 'b-post__help'}),
dict(name='div', attrs={'class': 'b-post__other b-post__other_right'}),
dict(name='div', attrs={'class': 'b-soc i-soc b-soc_blog b-soc_noscroll'}),
dict(name='div', attrs={'class': 'np-socials np-socials_grid js-np-socials'}),
dict(name='ul', attrs={'class': 'b-post__head-tags in-tablet-sm'}),
dict(name='ul', attrs={'class': 'b-single__text__categories'}),
dict(name='div', attrs={'class': 'b-donate-info js-donate-info'}),
dict(name='div', attrs={'class': 'b-404__materials b-line b-line_grey'}),
dict(name='div', attrs={'class': 'b-404__funds b-line'}),
dict(name='div', attrs={'class': 'overlay'}),
dict(name='div', attrs={'class': 'b-help-info-sticky'}),
dict(name='div', attrs={'id': 'mistape_dialog'}),
dict(name='footer'),
dict(name='form', attrs={'id': 'help'}),
dict(name='form', attrs={'id': 'form-3dsecure'})
]
feeds = [
('\u0412\u0441\u0435 \u043C\u0430\u0442\u0435\u0440\u0438\u0430\u043B\u044B', 'https://takiedela.ru/feed/'),
('\u041F\u043E\u043C\u043E\u0433\u0430\u0435\u043C', 'https://takiedela.ru/topics/feed/'),
('\u041A\u043E\u043B\u043E\u043D\u043A\u0438', 'https://takiedela.ru/rubrics/columns/feed/'),
('\u041E\u0431\u044A\u044F\u0441\u043D\u0435\u043D\u0438\u044F', 'https://takiedela.ru/rubrics/explanations/feed/'),
('\u0424\u043E\u0442\u043E\u0438\u0441\u0442\u043E\u0440\u0438\u0438', 'https://takiedela.ru/rubrics/photo/feed/'),
('\u041F\u043E\u0440\u0442\u0440\u0435\u0442\u044B', 'https://takiedela.ru/rubrics/portret/feed/'),
('\u0420\u0430\u0441\u0441\u043B\u0435\u0434\u043E\u0432\u0430\u043D\u0438\u044F', 'https://takiedela.ru/rubrics/rassledovaniya/feed/'),
('\u0421\u043B\u0443\u0447\u0430\u0438', 'https://takiedela.ru/genre/cases/feed/'),
('\u041A\u043E\u043D\u0442\u0435\u043A\u0441\u0442', 'https://takiedela.ru/genre/context/feed/'),
('\u0414\u0440\u0430\u043C\u044B', 'https://takiedela.ru/genre/drama/feed/'),
('\u0413\u0435\u0440\u043E\u0438', 'https://takiedela.ru/genre/heroes/feed/'),
('\u0421\u043E\u0445\u0440\u0430\u043D\u0435\u043D\u0438\u0435 \u043D\u0430\u0441\u043B\u0435\u0434\u0438\u044F \u0438 \u0438\u0441\u0442\u043E\u0440\u0438\u0447\u0435\u0441\u043A\u043E\u0439 \u043F\u0430\u043C\u044F\u0442\u0438', 'https://takiedela.ru/category/cultural/feed/'),
('\u0414\u0435\u0442\u0441\u0442\u0432\u043E', 'https://takiedela.ru/category/deti/feed/'),
('\u0414\u0435\u0442\u0438 \u0441 \u043E\u0441\u043E\u0431\u0435\u043D\u043D\u043E\u0441\u0442\u044F\u043C\u0438 \u0440\u0430\u0437\u0432\u0438\u0442\u0438\u044F', 'https://takiedela.ru/category/deti-s-osobennostyami-razvitiya/feed/'),
('\u0414\u0435\u0442\u0441\u043A\u0438\u0439 \u0434\u043E\u043C', 'https://takiedela.ru/category/detskiy-dom/feed/'),
('\u041A\u0430\u0442\u0430\u0441\u0442\u0440\u043E\u0444\u044B \u0438 \u0441\u0442\u0438\u0445\u0438\u0439\u043D\u044B\u0435 \u0431\u0435\u0434\u0441\u0442\u0432\u0438\u044F', 'https://takiedela.ru/category/disaster/feed/'),
('\u0425\u0440\u043E\u043D\u0438\u0447\u0435\u0441\u043A\u0438\u0435 \u0438 \u043D\u0435\u0438\u0437\u043B\u0435\u0447\u0438\u043C\u044B\u0435 \u0437\u0430\u0431\u043E\u043B\u0435\u0432\u0430\u043D\u0438\u044F', 'https://takiedela.ru/category/illness/feed/'),
('\u0420\u0430\u0437\u0432\u0438\u0442\u0438\u0435 \u043A\u0443\u043B\u044C\u0442\u0443\u0440\u044B \u0438 \u0438\u0441\u043A\u0443\u0441\u0441\u0442\u0432\u0430', 'https://takiedela.ru/category/kultura/feed/'),
('\u041C\u0430\u0442\u0435\u0440\u0438 \u0438 \u0434\u0435\u0442\u0438', 'https://takiedela.ru/category/materi-i-deti/feed/'),
('\u041C\u0435\u0434\u0438\u0446\u0438\u043D\u0441\u043A\u0430\u044F \u043F\u043E\u043C\u043E\u0449\u044C', 'https://takiedela.ru/category/medical/feed/'),
('\u041C\u0435\u0434\u0438\u0446\u0438\u043D\u0430', 'https://takiedela.ru/category/medicina/feed/'),
('\u041B\u0413\u0411\u0422+', 'https://takiedela.ru/category/minorities/feed/'),
('\u041E\u0431\u0449\u0435\u0441\u0442\u0432\u043E', 'https://takiedela.ru/category/obshhestvo/feed/'),
('\u041E\u043D\u043A\u043E\u043B\u043E\u0433\u0438\u044F', 'https://takiedela.ru/category/onkologiya/feed/'),
('\u0421\u0438\u0440\u043E\u0442\u0441\u0442\u0432\u043E', 'https://takiedela.ru/category/orphan/feed/'),
('\u0414\u0440\u0443\u0433\u043E\u0435', 'https://takiedela.ru/category/other/feed/'),
('\u041F\u043E\u043B\u0438\u0446\u0438\u044F', 'https://takiedela.ru/category/policiya/feed/'),
('\u041F\u0440\u0430\u0432\u043E\u0437\u0430\u0449\u0438\u0442\u0430', 'https://takiedela.ru/category/pravozashhita/feed/'),
('\u041F\u0441\u0438\u0445\u043E\u043B\u043E\u0433\u0438\u044F', 'https://takiedela.ru/category/psikhologiya/feed/'),
('\u0416\u0435\u0440\u0442\u0432\u044B \u043D\u0430\u0441\u0438\u043B\u0438\u044F', 'https://takiedela.ru/category/rape/feed/'),
('\u0416\u0435\u0440\u0442\u0432\u044B \u0432\u043E\u0435\u043D\u043D\u044B\u0445 \u0434\u0435\u0439\u0441\u0442\u0432\u0438\u0439', 'https://takiedela.ru/category/victims-of-war/feed/'),
('\u042D\u043A\u043E\u043B\u043E\u0433\u0438\u044F', 'https://takiedela.ru/category/yekologiya/feed/'),
('\u042E\u0440\u0438\u0434\u0438\u0447\u0435\u0441\u043A\u0430\u044F \u043F\u043E\u043C\u043E\u0449\u044C', 'https://takiedela.ru/category/yuridicheskaya-pomoshh/feed/'),
('\u0416\u0435\u043D\u0449\u0438\u043D\u044B', 'https://takiedela.ru/category/zhenshhiny/feed/'),
('\u0416\u0438\u0432\u043E\u0442\u043D\u044B\u0435', 'https://takiedela.ru/category/zhivotnye/feed/')
]
Грани.Ру: daily internet newspaper. Favicon. The website is blocked in Russia, so content is being downloaded from mirror site. 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 Grani(BasicNewsRecipe):
title = '\u0413\u0440\u0430\u043D\u0438.\u0420\u0443'
__author__ = 'bugmen00t'
description = '\u0415\u0436\u0435\u0434\u043D\u0435\u0432\u043D\u0430\u044F \u0438\u043D\u0442\u0435\u0440\u043D\u0435\u0442-\u0433\u0430\u0437\u0435\u0442\u0430. \u041E\u0431\u0437\u043E\u0440\u044B \u0438 \u0430\u043D\u0430\u043B\u0438\u0437 \u0440\u043E\u0441\u0441\u0438\u0439\u0441\u043A\u0438\u0445 \u0438 \u043C\u0438\u0440\u043E\u0432\u044B\u0445 \u043F\u043E\u043B\u0438\u0442\u0438\u0447\u0435\u0441\u043A\u0438\u0445 \u0441\u043E\u0431\u044B\u0442\u0438\u0439, \u0441\u0442\u0430\u0442\u044C\u0438 \u0438 \u0432\u0438\u0434\u0435\u043E \u043E \u043F\u043E\u043B\u0438\u0442\u0438\u0447\u0435\u0441\u043A\u0438\u0445 \u0437\u0430\u043A\u043B\u044E\u0447\u0451\u043D\u043D\u044B\u0445.'
publisher = '\u041E\u041E\u041E "\u0424\u043B\u0430\u0432\u0443\u0441"'
category = 'newspaper'
cover_url = u'https://graniru.org/files/96172.png'
language = 'ru'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
remove_empty_feeds = True
oldest_article = 30
max_articles_per_feed = 50
remove_tags_before = dict(name='h3')
remove_tags_after = dict(name='div', attrs={'class': 'main-text clearfix'}),
# Original feeds
# feeds = [
# ('\u0412\u0441\u0435 \u043C\u0430\u0442\u0435\u0440\u0438\u0430\u043B\u044B', 'https://graniru.org/export/all-atom.xml'),
# ('\u0421\u0442\u0430\u0442\u044C\u0438', 'https://graniru.org/export/articles-atom.xml')
# ]
# Feeds from mirror site
feeds = [
('\u0412\u0441\u0435 \u043C\u0430\u0442\u0435\u0440\u0438\u0430\u043B\u044B', 'https://grani2.appspot.com/export/all-atom.xml'),
('\u0421\u0442\u0430\u0442\u044C\u0438', 'https://grani2.appspot.com/export/articles-atom.xml'),
]
# Mirror site feeds transformation
def print_version(self, url):
return url.replace('https://graniru.org/', 'https://grani2.appspot.com/')
]
Зеркало недели: online Ukrainian analytical newspaper and news website. Favicon. Russian version 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 Zerkalo(BasicNewsRecipe):
title = '\u0417\u0435\u0440\u043A\u0430\u043B\u043E \u043D\u0435\u0434\u0435\u043B\u0438. \u0423\u043A\u0440\u0430\u0438\u043D\u0430'
__author__ = 'bugmen00t'
description = '\u041E\u0431\u0449\u0435\u0441\u0442\u0432\u0435\u043D\u043D\u043E-\u043F\u043E\u043B\u0438\u0442\u0438\u0447\u0435\u0441\u043A\u0438\u0439 \u0438\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u043E\u043D\u043D\u043E-\u0430\u043D\u0430\u043B\u0438\u0442\u0438\u0447\u0435\u0441\u043A\u0438\u0439 \u0435\u0436\u0435\u043D\u0435\u0434\u0435\u043B\u044C\u043D\u0438\u043A.'
publisher = '\u00AB\u0417\u0435\u0440\u043A\u0430\u043B\u043E \u043D\u0435\u0434\u0435\u043B\u0438. \u0423\u043A\u0440\u0430\u0438\u043D\u0430\u00BB'
category = 'newspaper'
cover_url = u'https://zn.ua/user/img/zn_no_photo_amp.png'
language = 'ru_UK'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
remove_empty_feeds = True
oldest_article = 7
max_articles_per_feed = 200
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': 'article_body'}),
remove_tags = [
dict(name='span', attrs={'class': 'print print-art-js'}),
dict(name='div', attrs={'class': 'questionnaire '}),
dict(name='div', attrs={'class': 'nts-video-wrapper'}),
dict(name='div', attrs={'class': 'telegram'}),
dict(name='div', attrs={'class': 'mist_block'}),
dict(name='div', attrs={'class': 'auth_articles_block'}),
dict(name='div', attrs={'class': 'special_theme_news_block'}),
dict(name='div', attrs={'class': 'article_attached acenter'}),
dict(name='div', attrs={'class': 'article_left'}),
dict(name='div', attrs={'class': 'top_social_holder'})
]
feeds = [
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://zn.ua/rus/rss/full.rss'),
# ('\u0421\u0442\u0430\u0442\u044C\u0438', 'https://zn.ua/rus/rss/articles.rss')
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src']
return soup
Ukrainian version 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 Zerkalo(BasicNewsRecipe):
title = '\u0414\u0437\u0435\u0440\u043A\u0430\u043B\u043E \u0442\u0438\u0436\u043D\u044F. \u0423\u043A\u0440\u0430\u0457\u043D\u0430'
__author__ = 'bugmen00t'
description = '\u0423\u043A\u0440\u0430\u0457\u043D\u0441\u044C\u043A\u0435 \u0456\u043D\u0442\u0435\u0440\u043D\u0435\u0442-\u0432\u0438\u0434\u0430\u043D\u043D\u044F, \u0441\u0443\u0441\u043F\u0456\u043B\u044C\u043D\u043E-\u043F\u043E\u043B\u0456\u0442\u0438\u0447\u043D\u0438\u0439 \u0442\u0438\u0436\u043D\u0435\u0432\u0438\u043A.'
publisher = '\u0414\u0437\u0435\u0440\u043A\u0430\u043B\u043E \u0442\u0438\u0436\u043D\u044F. \u0423\u043A\u0440\u0430\u0457\u043D\u0430'
category = 'newspaper'
cover_url = u'https://zn.ua/user/img/zn_no_photo_amp.png'
language = 'uk'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
remove_empty_feeds = True
oldest_article = 7
max_articles_per_feed = 200
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': 'article_body'}),
remove_tags = [
dict(name='span', attrs={'class': 'print print-art-js'}),
dict(name='div', attrs={'class': 'questionnaire '}),
dict(name='div', attrs={'class': 'nts-video-wrapper'}),
dict(name='div', attrs={'class': 'telegram'}),
dict(name='div', attrs={'class': 'mist_block'}),
dict(name='div', attrs={'class': 'auth_articles_block'}),
dict(name='div', attrs={'class': 'special_theme_news_block'}),
dict(name='div', attrs={'class': 'article_attached acenter'}),
dict(name='div', attrs={'class': 'article_left'}),
dict(name='div', attrs={'class': 'top_social_holder'})
]
feeds = [
('\u041D\u043E\u0432\u0438\u043D\u0438', 'https://zn.ua/ukr/rss/full.rss'),
# ('\u0421\u0442\u0430\u0442\u0442\u0456', 'https://zn.ua/ukr/rss/articles.rss')
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src']
return soup
|
|
|
|
|
08-26-2022, 08:29 AM
|
#25 |
|
Connoisseur
Posts: 65
Karma: 100000
Join Date: Aug 2015
Device: Kindle Keyboard + Kindle Voyage WiFi + Kindle PW11 Kids
|
New recipes (part 13 of ??)
Ukrainian sources.
Радіо Свобода: Prague-based Ukrainian-language TV channel founded by RFE/RL. Favicon. Fixes needed:
Spoiler:
Code:
#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe, classes
class RadioSvoboda(BasicNewsRecipe):
title = '\u0420\u0430\u0434\u0456\u043E \u0421\u0432\u043E\u0431\u043E\u0434\u0430'
__author__ = 'bugmen00t'
description = '\u0420\u0430\u0434\u0456\u043E\u0441\u0442\u0430\u043D\u0446\u0456\u044F \u0442\u0430 \u0456\u043D\u0442\u0435\u0440\u043D\u0435\u0442-\u0432\u0438\u0434\u0430\u043D\u043D\u044F, \u044F\u043A\u0430 \u043F\u043E\u0437\u0438\u0446\u0456\u043E\u043D\u0443\u0454 \u0441\u0435\u0431\u0435 \u044F\u043A \u043F\u0440\u0438\u0432\u0430\u0442\u043D\u0438\u0439 \u043D\u0435\u043A\u043E\u043C\u0435\u0440\u0446\u0456\u0439\u043D\u0438\u0439 \u0456\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0456\u0439\u043D\u043E-\u043D\u043E\u0432\u0438\u043D\u043D\u0438\u0439 \u0437\u0430\u0441\u0456\u0431 \u043C\u0430\u0441\u043E\u0432\u043E\u0457 \u0456\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0456\u0457.'
publisher = '\u0420\u0430\u0434\u0456\u043E \u0412\u0456\u043B\u044C\u043D\u0430 \u0404\u0432\u0440\u043E\u043F\u0430/\u0420\u0430\u0434\u0456\u043E \u0421\u0432\u043E\u0431\u043E\u0434\u0430 (\u0420\u0412\u0404/\u0420\u0421)'
category = 'newspaper'
cover_url = u'https://www.radiosvoboda.org/Content/responsive/RFE/uk-UA/img/top_logo_news.png'
language = 'uk'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
remove_empty_feeds = True
oldest_article = 7
max_articles_per_feed = 20
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'id': 'article-content'})
remove_tags = [
dict(name='p', attrs={'class': 'buttons btn--load-more'}),
dict(name='div', attrs={'class': 'share--box'}),
dict(name='div', attrs={'class': 'c-author__btns m-t-md'}),
dict(name='div', attrs={'class': 'col-xs-12 col-md-4 pull-left live-blog-left'}),
dict(name='aside'),
dict(name='div', attrs={'class': 'c-blockquote c-blockquote--has-quote'}),
dict(name='div', attrs={'class': 'media-block also-read'}),
dict(name='div', attrs={'class': 'media-block-wrap'}),
dict(name='div', attrs={'class': 'wsw__embed'}),
dict(name='div', attrs={'id': 'comments'}),
]
feeds = [
('\u0413\u043E\u043B\u043E\u0432\u043D\u0456 \u043D\u043E\u0432\u0438\u043D\u0438', 'https://www.radiosvoboda.org/api/zrqiteuuir'),
('\u041D\u043E\u0432\u0438\u043D\u0438: \u041A\u043E\u0440\u043E\u043D\u0430\u0432\u0456\u0440\u0443\u0441', 'https://www.radiosvoboda.org/api/zqk_myekpymv'),
('\u041C\u0456\u0436\u043D\u0430\u0440\u043E\u0434\u043D\u0456 \u043D\u043E\u0432\u0438\u043D\u0438', 'https://www.radiosvoboda.org/api/zipkqejjki'),
('\u041D\u043E\u0432\u0438\u043D\u0438: \u041F\u043E\u043B\u0456\u0442\u0438\u043A\u0430', 'https://www.radiosvoboda.org/api/zppkoe-jkp'),
('\u041D\u043E\u0432\u0438\u043D\u0438: \u0415\u043A\u043E\u043D\u043E\u043C\u0456\u043A\u0430', 'https://www.radiosvoboda.org/api/zvpk_eo-kt'),
('\u041D\u043E\u0432\u0438\u043D\u0438: \u0421\u0443\u0441\u043F\u0456\u043B\u044C\u0441\u0442\u0432\u043E', 'https://www.radiosvoboda.org/api/zjmkreybko'),
('\u041D\u043E\u0432\u0438\u043D\u0438: \u041F\u043E\u0434\u0456\u0457', 'https://www.radiosvoboda.org/api/ztpkyei-kr'),
('\u041D\u043E\u0432\u0438\u043D\u0438: \u0421\u0432\u043E\u0431\u043E\u0434\u0430 \u0441\u043B\u043E\u0432\u0430', 'https://www.radiosvoboda.org/api/zmrjoebtjo'),
('\u041D\u043E\u0432\u0438\u043D\u0438: \u041A\u043E\u0440\u0443\u043F\u0446\u0456\u044F', 'https://www.radiosvoboda.org/api/zbobpoetgbpi'),
('\u041D\u043E\u0432\u0438\u043D\u0438: \u0412\u0430\u0436\u043B\u0438\u0432\u0456', 'https://www.radiosvoboda.org/api/zmyqmvebromr'),
('\u041D\u043E\u0432\u0438\u043D\u0438: \u0421\u043F\u043E\u0440\u0442', 'https://www.radiosvoboda.org/api/ztpmmyei-mmy'),
('\u041F\u0443\u0431\u043B\u0456\u043A\u0430\u0446\u0456\u0457', 'https://www.radiosvoboda.org/api/ziibp_ejgbpy'),
('\u041F\u043E\u043B\u0456\u0442\u0438\u043A\u0430', 'https://www.radiosvoboda.org/api/ziqioejuip'),
('\u0421\u0443\u0441\u043F\u0456\u043B\u044C\u0441\u0442\u0432\u043E', 'https://www.radiosvoboda.org/api/z_qi_erkiy'),
('\u0415\u043A\u043E\u043D\u043E\u043C\u0456\u043A\u0430', 'https://www.radiosvoboda.org/api/zpyp_e-rm_'),
('\u041A\u0443\u043B\u044C\u0442\u0443\u0440\u0430', 'https://www.radiosvoboda.org/api/zmqipebui_'),
('\u0423\u043A\u0440\u0430\u0457\u043D\u0430', 'https://www.radiosvoboda.org/api/zqqirekuiq'),
('\u0421\u0432\u0456\u0442', 'https://www.radiosvoboda.org/api/zoqiqeguii'),
('\u0412\u0430\u0436\u043B\u0438\u0432\u0435 \u043D\u0430 \u0421\u0432\u043E\u0431\u043E\u0434\u0456', 'https://www.radiosvoboda.org/api/zkk-iqemmbii'),
('\u0412\u0456\u0439\u043D\u0430', 'https://www.radiosvoboda.org/api/zijqpqej_opi'),
('\u0414\u043E\u043D\u0431\u0430\u0441', 'https://www.radiosvoboda.org/api/z_rppyeruppy'),
('\u041A\u0440\u0438\u043C', 'https://www.radiosvoboda.org/api/zbypmietqmmi'),
('\u0422\u043E\u0447\u043A\u0430 \u0437\u043E\u0440\u0443', 'https://www.radiosvoboda.org/api/zpqiie-uim'),
('\u041A\u043E\u0440\u043E\u043D\u0430\u0432\u0456\u0440\u0443\u0441', 'https://www.radiosvoboda.org/api/zok_mvegpymt'),
('\u0421\u043F\u043E\u0440\u0442', 'https://www.radiosvoboda.org/api/z-q_mpevk_m_'),
('\u041A\u0438\u0442\u0430\u0439: \u0432\u0438\u043A\u043B\u0438\u043A\u0438', 'https://www.radiosvoboda.org/api/zkyymqemqvmo'),
('\u0406\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0456\u0439\u043D\u0430 \u0432\u0456\u0439\u043D\u0430', 'https://www.radiosvoboda.org/api/zuoppyepgppv'),
('\u0420\u0430\u0434\u0456\u043E \u0421\u0432\u043E\u0431\u043E\u0434\u0430 Weekly', 'https://www.radiosvoboda.org/api/zb_rmyetrqmv'),
('\u041D\u043E\u0432\u0438\u043D\u0438 \u041F\u0440\u0438\u0430\u0437\u043E\u0432\u2019\u044F', 'https://www.radiosvoboda.org/api/zkkvmyemmtmy'),
('\u041F\u043E\u0434\u0456\u0457', 'https://www.radiosvoboda.org/api/z-ppp_ev-ppv'),
('\u0421\u0445\u0435\u043C\u0438', 'https://www.radiosvoboda.org/api/z-miprevbipo'),
('\u0421\u0445\u0435\u043C\u0438: \u0420\u043E\u0437\u0441\u043B\u0456\u0434\u0443\u0432\u0430\u043D\u043D\u044F', 'https://www.radiosvoboda.org/api/ztvppoeiompo'),
('\u0421\u0445\u0435\u043C\u0438: \u041D\u043E\u0432\u0438\u043D\u0438', 'https://www.radiosvoboda.org/api/zyibpreqjbpo')
]
Вікна: news program of Ukrainian TV-channel STB. Favicon. Fixes needed:
Spoiler:
Code:
#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe, classes
class ViknaSTB(BasicNewsRecipe):
title = '\u0412\u0438\u043A\u043D\u0430-\u043D\u043E\u0432\u043E\u0441\u0442\u0438'
__author__ = 'bugmen00t'
description = '\u0423\u043A\u0440\u0430\u0438\u043D\u0441\u043A\u0430\u044F \u0438\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u043E\u043D\u043D\u0430\u044F \u043F\u0440\u043E\u0433\u0440\u0430\u043C\u043C\u0430 \u0442\u0435\u043B\u0435\u043A\u0430\u043D\u0430\u043B\u0430 \u00AB\u0421\u0422\u0411\u00BB.'
publisher = '\u041E\u041E\u041E \u201C\u0421\u041B\u041C \u041D\u043E\u0432\u043E\u0441\u0442\u0438\u201D'
category = 'newspaper'
cover_url = u'https://yt3.ggpht.com/QZxhLPDcqhjMitCDPWbzk-Zs-ILbGo3ww1iuV9SIE1k0iqjoOIctT2d4BdyEsSAR6yWsbKbGWg=s900-c-k-c0x00ffffff-no-rj'
language = 'ru_UK'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
remove_empty_feeds = True
oldest_article = 3
max_articles_per_feed = 20
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': 'content-wrapper'})
remove_tags = [
dict(name='div', attrs={'class': 'share-content-wrapper flex-wrapper'}),
dict(name='div', attrs={'class': 'sticky-wrapper'}),
dict(name='div', attrs={'class': 'promo-wrapper'}),
dict(name='div', attrs={'class': 'mn-wrapper'}),
dict(name='div', attrs={'class': 'news-tags border-btm-grey'})
]
feeds = [
('\u0412\u0456\u043A\u043D\u0430', 'https://vikna.tv/ru/feed/')
]
Ukrainian version Spoiler:
Code:
#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe, classes
class ViknaSTB(BasicNewsRecipe):
title = '\u0412\u0456\u043A\u043D\u0430-\u043D\u043E\u0432\u0438\u043D\u0438'
__author__ = 'bugmen00t'
description = '\u0423\u043A\u0440\u0430\u0457\u043D\u0441\u044C\u043A\u0430 \u0456\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0456\u0439\u043D\u0430 \u043F\u0440\u043E\u0433\u0440\u0430\u043C\u0430 \u0442\u0435\u043B\u0435\u043A\u0430\u043D\u0430\u043B\u0443 \u00AB\u0421\u0422\u0411\u00BB.'
publisher = '\u0422\u041E\u0412 \u201C\u0421\u041B\u041C \u041D\u043E\u0432\u0438\u043D\u0438\u201D'
category = 'newspaper'
cover_url = u'https://yt3.ggpht.com/QZxhLPDcqhjMitCDPWbzk-Zs-ILbGo3ww1iuV9SIE1k0iqjoOIctT2d4BdyEsSAR6yWsbKbGWg=s900-c-k-c0x00ffffff-no-rj'
language = 'uk'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
remove_empty_feeds = True
oldest_article = 3
max_articles_per_feed = 20
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': 'content-wrapper'})
remove_tags = [
dict(name='div', attrs={'class': 'share-content-wrapper flex-wrapper'}),
dict(name='div', attrs={'class': 'sticky-wrapper'}),
dict(name='div', attrs={'class': 'promo-wrapper'}),
dict(name='div', attrs={'class': 'mn-wrapper'}),
dict(name='div', attrs={'class': 'news-tags border-btm-grey'})
]
feeds = [
('\u0412\u0456\u043A\u043D\u0430', 'https://vikna.tv/feed/')
]
Gazeta.ua: web-wersion of Ukrainian newspaper covering politics, economics, culture, sport, arts, and other different topics. Favicon. Fixes needed:
Spoiler:
Code:
#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe, classes
class GazetaUA(BasicNewsRecipe):
title = 'Gazeta.ua'
__author__ = 'bugmen00t'
description = '\u0412\u0441\u0435\u0443\u043A\u0440\u0430\u0438\u043D\u0441\u043A\u0430\u044F \u043E\u043D-\u043B\u0430\u0439\u043D \u0433\u0430\u0437\u0435\u0442\u0430. \u041E\u043F\u0435\u0440\u0430\u0442\u0438\u0432\u043D\u044B\u0435 \u043D\u043E\u0432\u043E\u0441\u0442\u0438 \u0432 \u0423\u043A\u0440\u0430\u0438\u043D\u0435 \u0438 \u0432 \u043C\u0438\u0440\u0435: \u0441\u043E\u0431\u044B\u0442\u0438\u044F, \u043F\u043E\u043B\u0438\u0442\u0438\u043A\u0430, \u0441\u043F\u043E\u0440\u0442, \u043A\u0443\u043B\u044C\u0442\u0443\u0440\u0430.'
publisher = '\u0418\u0437\u0434\u0430\u0442\u0435\u043B\u044C\u0441\u043A\u0430\u044F \u0433\u0440\u0443\u043F\u043F\u0430 "\u041D\u043E\u0432\u0430 \u0456\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0456\u044F"'
category = 'newspaper'
cover_url = u'https://static2.gazeta.ua/img2/cache/preview/1064/1064219_w_450.jpg'
language = 'ru_UK'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
remove_empty_feeds = True
oldest_article = 3
max_articles_per_feed = 50
remove_tags_before = dict(name='article')
remove_tags_after = dict(name='section', attrs={'class': 'article-content clearfix'})
remove_tags = [
dict(name='div', attrs={'class': 'mt5'}),
dict(name='p', attrs={'id': 'mce_0'}),
dict(name='p', attrs={'id': 'mce_1'}),
dict(name='p', attrs={'id': 'mce_2'}),
dict(name='p', attrs={'id': 'mce_3'}),
dict(name='p', attrs={'id': 'mce_4'}),
dict(name='p', attrs={'id': 'mce_5'}),
dict(name='p', attrs={'id': 'mce_6'}),
dict(name='p', attrs={'id': 'mce_7'}),
dict(name='p', attrs={'id': 'mce_8'}),
dict(name='p', attrs={'id': 'mce_9'}),
dict(name='p', attrs={'id': 'mce_10'}),
dict(name='p', attrs={'id': 'mce_11'}),
dict(name='p', attrs={'id': 'mce_12'}),
dict(name='p', attrs={'id': 'mce_13'}),
dict(name='p', attrs={'id': 'mce_14'}),
dict(name='p', attrs={'id': 'mce_15'}),
dict(name='p', attrs={'id': 'mce_16'}),
dict(name='section', attrs={'class': 'w-marker-photo lg'})
]
feeds = [
('Gazeta.ua', 'https://gazeta.ua/ru/rss')
]
Ukrainian version Spoiler:
Code:
#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe, classes
class GazetaUA(BasicNewsRecipe):
title = 'Gazeta.ua'
__author__ = 'bugmen00t'
description = '\u0412\u0441\u0435\u0443\u043A\u0440\u0430\u0457\u043D\u0441\u044C\u043A\u0430 \u043E\u043D-\u043B\u0430\u0439\u043D \u0433\u0430\u0437\u0435\u0442\u0430. \u041E\u043F\u0435\u0440\u0430\u0442\u0438\u0432\u043D\u0456 \u043D\u043E\u0432\u0438\u043D\u0438 \u0437 \u0423\u043A\u0440\u0430\u0457\u043D\u0438 \u0456 \u0441\u0432\u0456\u0442\u0443: \u043F\u043E\u0434\u0456\u0457, \u043F\u043E\u043B\u0456\u0442\u0438\u043A\u0430, \u0441\u043F\u043E\u0440\u0442, \u043A\u0443\u043B\u044C\u0442\u0443\u0440\u0430.'
publisher = '\u0422\u041E\u0412 "\u0412\u0438\u0434\u0430\u0432\u043D\u0438\u0447\u0430 \u043A\u043E\u043C\u043F\u0430\u043D\u0456\u044F "\u041D\u043E\u0432\u0430 \u0456\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0456\u044F"'
category = 'newspaper'
cover_url = u'https://static2.gazeta.ua/img2/cache/preview/1064/1064219_w_450.jpg'
language = 'uk'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
remove_empty_feeds = True
oldest_article = 3
max_articles_per_feed = 50
remove_tags_before = dict(name='article')
remove_tags_after = dict(name='section', attrs={'class': 'article-content clearfix'})
remove_tags = [
dict(name='div', attrs={'class': 'mt5'}),
dict(name='p', attrs={'id': 'mce_0'}),
dict(name='p', attrs={'id': 'mce_1'}),
dict(name='p', attrs={'id': 'mce_2'}),
dict(name='p', attrs={'id': 'mce_3'}),
dict(name='p', attrs={'id': 'mce_4'}),
dict(name='p', attrs={'id': 'mce_5'}),
dict(name='p', attrs={'id': 'mce_6'}),
dict(name='p', attrs={'id': 'mce_7'}),
dict(name='p', attrs={'id': 'mce_8'}),
dict(name='p', attrs={'id': 'mce_9'}),
dict(name='p', attrs={'id': 'mce_10'}),
dict(name='p', attrs={'id': 'mce_11'}),
dict(name='p', attrs={'id': 'mce_12'}),
dict(name='p', attrs={'id': 'mce_13'}),
dict(name='p', attrs={'id': 'mce_14'}),
dict(name='p', attrs={'id': 'mce_15'}),
dict(name='p', attrs={'id': 'mce_16'}),
dict(name='section', attrs={'class': 'w-marker-photo lg'})
]
feeds = [
('Gazeta.ua', 'https://gazeta.ua/rss')
]
Fix for Новая Вкладка (newtab.recipe): updated RSS URL. Spoiler:
Code:
#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe
class NewTab(BasicNewsRecipe):
title = '\u041D\u043E\u0432\u0430\u044F \u0432\u043A\u043B\u0430\u0434\u043A\u0430'
__author__ = 'bugmen00t'
description = '\u041F\u043B\u043E\u0449\u0430\u0434\u043A\u0430 \u0434\u043B\u044F \u043F\u0443\u0431\u043B\u0438\u043A\u0430\u0446\u0438\u0438 \u0440\u0435\u043F\u043E\u0440\u0442\u0430\u0436\u0435\u0439 \u0438 \u0437\u0430\u043C\u0435\u0442\u043E\u043A \u043E \u0442\u043E\u043C, \u043A\u0430\u043A \u043C\u0435\u043D\u044F\u044E\u0442\u0441\u044F \u0440\u0435\u0433\u0438\u043E\u043D\u044B \u0420\u043E\u0441\u0441\u0438\u0438 \u043F\u043E\u0441\u043B\u0435 24 \u0444\u0435\u0432\u0440\u0430\u043B\u044F 2022 \u0433\u043E\u0434\u0430.'
publisher = '\u041C\u0438\u0445\u0430\u0438\u043B \u0414\u0430\u043D\u0438\u043B\u043E\u0432\u0438\u0447'
category = 'blog'
cover_url = u'https://static.tildacdn.com/tild3765-3961-4337-b366-323437626331/thenewtab-sn.jpg'
language = 'ru'
no_stylesheets = True
remove_javascript = False
auto_cleanup = False
oldest_article = 30
max_articles_per_feed = 10
remove_tags_before = dict(name='h1')
remove_tags = [
dict(name='div', attrs={'class': 't-popup'}),
dict(name='div', attrs={'class': 't185'}),
dict(name='div', attrs={'class': 't403'}),
dict(name='div', attrs={'class': 't404'}),
dict(name='div', attrs={'class': 't134'}),
dict(name='div', attrs={'class': 'sp-form-fields-wrapper'})
]
feeds = [
('\u041D\u043E\u0432\u0430\u044F \u0432\u043A\u043B\u0430\u0434\u043A\u0430','https://thenewtab.io/feed/')
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-original': True}):
img['src'] = img['data-original']
return soup
|
|
|
|
|
10-02-2022, 03:58 AM
|
#26 |
|
Connoisseur
Posts: 65
Karma: 100000
Join Date: Aug 2015
Device: Kindle Keyboard + Kindle Voyage WiFi + Kindle PW11 Kids
|
Not-so-quick fixes
Fix for Russian and Ukrainian editions of Gazeta.ua (gazetaua_ua.recipe & gazetaua_ru.recipe) as I somehow managed to upload empty files last time.
 Fix for English version of Холод (kholod_en.recipe): updated RSS URL. Language code fix for Dingoo A320. Русский ресурс (dingoo_a320.recipe) and Ria Novosti (rian_eng.recipe). They're dead for many years though. Language code fix for The Moscow Times by Darko Miletic and Sujata Raman (moscow_times.recipe). There're two different recipes in Calibre now (this one with text-only content and my own with text & images), so I dared to add "(light version)" to the original title of this recipe. |
|
|
|
|
08-08-2023, 11:25 AM
|
#27 |
|
Connoisseur
Posts: 65
Karma: 100000
Join Date: Aug 2015
Device: Kindle Keyboard + Kindle Voyage WiFi + Kindle PW11 Kids
|
New/fixed Russian and Ukrainian recipes (part 14)
UA-Футбол: soccer news from Ukraine and around the world. Favicon.
Fixes needed:
Spoiler:
Code:
#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe, classes
class UAFootball(BasicNewsRecipe):
#Russian version
# title = 'UA-\u0424\u0443\u0442\u0431\u043E\u043B'
# description = '\u0410\u043A\u0442\u0443\u0430\u043B\u044C\u043D\u044B\u0435 \u0442\u0435\u043C\u044B \u0444\u0443\u0442\u0431\u043E\u043B\u044C\u043D\u043E\u0439 \u0436\u0438\u0437\u043D\u0438 \u0423\u043A\u0440\u0430\u0438\u043D\u044B \u0438 \u0432\u0441\u0435\u0433\u043E \u043C\u0438\u0440\u0430.'
# language = 'ru_UK'
# feeds = [
# ('\u041D\u043E\u0432\u043E\u0441\u0442\u0438 \u0444\u0443\u0442\u0431\u043E\u043B\u0430', 'https://www.ua-football.com/rss/all.xml')
# ]
#Ukrainian version
title = 'UA-\u0424\u0443\u0442\u0431\u043E\u043B'
description = '\u0410\u043A\u0442\u0443\u0430\u043B\u044C\u043D\u0456 \u0442\u0435\u043C\u0438 \u0444\u0443\u0442\u0431\u043E\u043B\u044C\u043D\u043E\u0433\u043E \u0436\u0438\u0442\u0442\u044F \u0423\u043A\u0440\u0430\u0457\u043D\u0438 \u0442\u0430 \u0432\u0441\u044C\u043E\u0433\u043E \u0441\u0432\u0456\u0442\u0443.'
language = 'uk'
feeds = [
('\u041D\u043E\u0432\u0438\u043D\u0438', 'https://www.ua-football.com/ua/rss/all.xml')
]
__author__ = 'bugmen00t'
publisher = '1766 TEAM EOOD'
category = 'news'
cover_url = u'https://yt3.googleusercontent.com/11FSvKeWcjFhzKrO7nXZdc-I__UeZ0mhZwbwyOHtnx_1-q6d0zQ2LbOt2duNCY06JVg2cGXS-g=s900-c-k-c0x00ffffff-no-rj'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
remove_empty_feeds = True
oldest_article = 7
max_articles_per_feed = 200
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class': 'show-post'})
remove_tags = [
dict(name='form'),
dict(name='iframe'),
dict(name='div', attrs={'class': 'language'}),
dict(name='div', attrs={'class': 'article__read-also'}),
dict(name='div', attrs={'class': 'card-player'}),
dict(name='div', attrs={'class': 'show-post-socials'})
]
# Replacing articles in Ukraininan for RU-feed
# def print_version(self, url):
# return url.replace('ua-football.com/ua/', 'ua-football.com/')
Football.ua: soccer news portal from Ukraine. Favicon. Spoiler:
Code:
#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe, classes
class FootballUA(BasicNewsRecipe):
title = 'Football.UA'
__author__ = 'bugmen00t'
description = '\u0421\u043F\u043E\u0440\u0442\u0438\u0432\u043D\u0438\u0439 \u043F\u043E\u0440\u0442\u0430\u043B \u0432 \u0423\u043A\u0440\u0430\u0457\u043D\u0456, \u043F\u0440\u0438\u0441\u0432\u044F\u0447\u0435\u043D\u0438\u0439 \u043B\u0438\u0448\u0435 \u0444\u0443\u0442\u0431\u043E\u043B\u0443.'
publisher = 'United Media Holding group'
category = 'news'
cover_url = u'https://s.ill.in.ua/i/news/570x380/212/212438.jpg'
language = 'uk'
no_stylesheets = False
remove_javascript = False
auto_cleanup = False
remove_empty_feeds = True
oldest_article = 3
max_articles_per_feed = 20
remove_tags_before = dict(name='article')
remove_tags_after = dict(name='article')
remove_tags = [
dict(name='div', attrs={'class': 'bottom-info'}),
dict(name='div', attrs={'class': 'social-buttons'})
]
feeds = [
('\u041D\u043E\u0432\u0438\u043D\u0438', 'https://football.ua/rss2.ashx'),
]
UNIAN.net: Ukrainian Independent News Agency of News, one of the most cited source of news from across Ukraine. Favicon Russian version (fixed) Spoiler:
Code:
#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe
class Unian(BasicNewsRecipe):
title = '\u0423\u041D\u0418\u0410\u041D '
description = 'Украинское Независимое Информационное Агентство Новостей – первое в Украине и самое большое независимое информационное агентство, основанное в 1993 году, лидер среди новостных медиа страны, самый цитируемый источник новостей о событиях в стране.' # noqa
__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'}),
dict(name='div', attrs={'class': 'nts-video-wrapper'})
]
feeds = [
(u'\u0423\u041D\u0418\u0410\u041D', u'https://rss.unian.net/site/news_rus.rss')
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src']
return soup
Ukrainian version Spoiler:
Code:
#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe
class Unian(BasicNewsRecipe):
title = '\u0423\u041D\u0406\u0410\u041D'
description = '\u0423\u041D\u0406\u0410\u041D (\u0423\u043A\u0440\u0430\u0457\u043D\u0441\u044C\u043A\u0435 \u041D\u0435\u0437\u0430\u043B\u0435\u0436\u043D\u0435 \u0406\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0456\u0439\u043D\u0435 \u0410\u0433\u0435\u043D\u0442\u0441\u0442\u0432\u043E \u041D\u043E\u0432\u0438\u043D) - \u043F\u0435\u0440\u0448\u0435 \u0432 \u0423\u043A\u0440\u0430\u0457\u043D\u0456 \u0442\u0430 \u043D\u0430\u0439\u0431\u0456\u043B\u044C\u0448\u0435 \u043D\u0435\u0437\u0430\u043B\u0435\u0436\u043D\u0435 \u0456\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0456\u0439\u043D\u0435 \u0430\u0433\u0435\u043D\u0442\u0441\u0442\u0432\u043E, \u0437\u0430\u0441\u043D\u043E\u0432\u0430\u043D\u0435 1993 \u0440\u043E\u043A\u0443, \u043B\u0456\u0434\u0435\u0440 \u0441\u0435\u0440\u0435\u0434 \u043D\u043E\u0432\u0438\u043D\u043D\u0438\u0445 \u043C\u0435\u0434\u0456\u0430 \u043A\u0440\u0430\u0457\u043D\u0438, \u043D\u0430\u0439\u0431\u0456\u043B\u044C\u0448 \u0446\u0438\u0442\u043E\u0432\u0430\u043D\u0435 \u0434\u0436\u0435\u0440\u0435\u043B\u043E \u043D\u043E\u0432\u0438\u043D \u043F\u0440\u043E \u043F\u043E\u0434\u0456\u0457 \u0432 \u043A\u0440\u0430\u0457\u043D\u0456.'
__author__ = 'bugmen00t'
publication_type = 'newspaper'
oldest_article = 7
max_articles_per_feed = 100
language = 'uk'
cover_url = 'https://www.unian.ua/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'}),
dict(name='div', attrs={'class': 'nts-video-wrapper'})
]
feeds = [
(u'\u0423\u041D\u0406\u0410\u041D', u'https://rss.unian.net/site/news_ukr.rss')
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src']
return soup
English version (no updates since April 2023) Spoiler:
Code:
#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe
class Unian(BasicNewsRecipe):
title = 'UNIAN'
description = 'UNIAN (Ukrainian Independent News Agency of News) is the largest independent news agency, first in Ukraine, founded in 1993, remaining the leader among the country\'s news media, being the most cited source of news from across Ukraine.'
__author__ = 'bugmen00t'
publication_type = 'newspaper'
oldest_article = 30
max_articles_per_feed = 100
language = 'en_UK'
cover_url = 'https://www.unian.info/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'}),
dict(name='div', attrs={'class': 'nts-video-wrapper'})
]
feeds = [
(u'News Agency UNIAN', u'https://rss.unian.net/site/news_eng.rss')
]
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src']
return soup
ЭХО: reincarnated news portal by former Echo Moskvy journalists. Favicon. Replacememt for older defunct recipe Fixes needed:
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 EchoMsk(BasicNewsRecipe):
title = '\u042D\u0425\u041E'
__author__ = 'bugmen00t'
description = '\u042D\u0425\u041E - \u043A\u0430\u043A \u043D\u0430 \u0441\u0442\u0430\u0440\u043E\u043C \u0434\u043E\u0431\u0440\u043E\u043C \u0440\u0430\u0434\u0438\u043E'
publisher = 'Radio Echo GmbH'
category = 'news'
cover_url = u'https://echofm.online/logo.png'
language = 'ru'
no_stylesheets = True
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 50
remove_tags_before = dict(name='article')
remove_tags_after = dict(name='article')
remove_tags = [
dict(name='span', attrs={'class': 'sc-7b4cbb79-0 guzUFC'}),
dict(name='div', attrs={'class': 'sc-f94c4ef5-0 frGiYu'}),
dict(name='div', attrs={'class': 'sc-f94c4ef5-0 frGiYu'})
]
feeds = [
('\u0413\u043B\u0430\u0432\u043D\u043E\u0435', 'https://echofm.online/feed'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://echofm.online/news/feed'),
('\u041C\u043D\u0435\u043D\u0438\u044F', 'https://echofm.online/opinions/feed'),
('\u0414\u043E\u043A\u0443\u043C\u0435\u043D\u0442\u044B', 'https://echofm.online/documents/feed')
]
Продолжение следует: digital media founded by Novaya Gazeta journalist Dmitry Kanygin. Favicon. Fixes needed:
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 ProSleduet(BasicNewsRecipe):
title = '\u041F\u0440\u043E\u0434\u043E\u043B\u0436\u0435\u043D\u0438\u0435 \u0441\u043B\u0435\u0434\u0443\u0435\u0442'
__author__ = 'bugmen00t'
description = '\u0414\u0438\u0434\u0436\u0438\u0442\u0430\u043B-\u043F\u0440\u043E\u0435\u043A\u0442 \u0436\u0443\u0440\u043D\u0430\u043B\u0438\u0441\u0442\u043E\u0432 \u00AB\u041D\u043E\u0432\u043E\u0439 \u0433\u0430\u0437\u0435\u0442\u044B\u00BB'
publisher = 'Pavel Kanygin, Natalia Zhdanova'
category = 'news'
cover_url = u'https://prosleduet.media/wp-content/themes/prosle/assets/img/logo.svg'
language = 'ru'
no_stylesheets = True
remove_javascript = False
auto_cleanup = False
oldest_article = 7
max_articles_per_feed = 20
remove_tags_before = dict(name='div', attrs={'class': 'container'})
remove_tags_after = dict(name='div', attrs={'class': 'container'})
remove_tags = [
dict(name='div', attrs={'class': 'ya-share2 ya-share2_inited'})
]
feeds = [
# ('\u041F\u0440\u043E\u0434\u043E\u043B\u0436\u0435\u043D\u0438\u0435 \u0441\u043B\u0435\u0434\u0443\u0435\u0442', 'https://prosleduet.media/feed/'),
('\u041D\u043E\u0432\u043E\u0441\u0442\u0438', 'https://prosleduet.media/category/news/feed/'),
('\u041B\u044E\u0434\u0438', 'https://prosleduet.media/category/people/feed/'),
('\u0421\u044E\u0436\u0435\u0442\u044B', 'https://prosleduet.media/category/syuzhety/feed/'),
('\u041F\u043E\u0434\u043A\u0430\u0441\u0442\u044B', 'https://prosleduet.media/category/podcasts/feed/'),
('\u0420\u0430\u0437\u0431\u043E\u0440\u044B', 'https://prosleduet.media/category/details/feed/'),
('\u0413\u043B\u0443\u0431\u0438\u043D\u043D\u0430\u044F \u0420\u043E\u0441\u0441\u0438\u044F', 'https://prosleduet.media/category/glubinnaya-rossiya/feed/')
]
|
|
|
|
|
| Tags |
fixes, russain, ukraninan  |
«
Previous Thread
|
Next Thread
»
|
Similar Threads
|
||||
| Thread | Thread Starter | Forum | Replies | Last Post |
| New and updated recipes for Ukrainian media | rpalyvoda | Recipes | 2 | 06-12-2015 04:56 PM |
| New recipes for a couple of Ukrainian media | rpalyvoda | Recipes | 1 | 06-11-2015 05:31 PM |
| looking for built-in recipes | Bobus | Recipes | 4 | 09-26-2011 03:31 PM |
| customizing built in recipes | jrasmussen | Calibre | 2 | 02-15-2010 11:26 PM |
All times are GMT -4. The time now is 06:04 PM.