|
Connoisseur
Posts: 82
Karma: 100000
Join Date: Aug 2015
Device: Kindle Keyboard 3G + Kindle Voyage WiFi + Kindle PW11 Kids WiFi
|
New recipes (part 13 of ??)
Ukrainian sources.
Радіо Свобода: Prague-based Ukrainian-language TV channel founded by RFE/RL. Favicon.
Fixes needed: - In most of the aticles some images are missing
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: Russian version
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: - Thumbnails instead of full-size images in images set
- Could not handle Telegram redirects and inlines
- Minor in-text ads
Russian 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\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
|