Various new ru/uk news sources by bugmen00t

recipes/habr.recipe

@@ -0,0 +1,36 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+
+class Habr(BasicNewsRecipe):
+    title = 'Habr'
+    __author__ = 'bugmen00t'
+    description = 'Russian collaborative blog about IT, computer science and anything related to the Internet'
+    publisher = 'Habr Blockchain Publishing LTD'
+    category = 'blog'
+    cover_url = u'https://hsto.org/webt/f1/lq/ka/f1lqkaveikdfqkb_rip_4vq4s_8.png'
+    language = 'en_RU'
+    no_stylesheets = True
+    remove_javascript = False
+    auto_cleanup = False
+    oldest_article = 30
+    max_articles_per_feed = 30
+
+    remove_tags_before = dict(name='h1')
+
+    remove_tags_after = dict(name='div', attrs={'class': 'tm-misprint-area'})
+
+    remove_tags = [
+        dict(name='div', attrs={'class': 'tm-article-presenter__meta'}),
+        dict(name='div', attrs={'class': 'tm-article-poll'})
+    ]
+
+    feeds = [('News', 'https://habr.com/en/rss/news/?fl=en'),
+             ('All materials', 'https://habr.com/en/rss/all?fl=en')]
+
+    def preprocess_html(self, soup):
+        for img in soup.findAll('img', attrs={'data-src': True}):
+            img['src'] = img['data-src']
+        return soup

recipes/habr_ru.recipe

@@ -0,0 +1,60 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+
+class Habr(BasicNewsRecipe):
+    title = '\u0425\u0430\u0431\u0440'
+    __author__ = 'bugmen00t'
+    description = '\u041D\u0430 \u200B\u0425\u0430\u0431\u0440\u0435 \u200B\u0434\u0443\u043C\u0430\u044E\u0449\u0438\u0435 \u200B\u043B\u044E\u0434\u0438 \u200B\u0434\u0435\u043B\u044F\u0442\u0441\u044F \u200B\u0443\u043D\u0438\u043A\u0430\u043B\u044C\u043D\u044B\u043C \u200B\u200B\u043E\u043F\u044B\u0442\u043E\u043C. \u200B\u200B\u0417\u0434\u0435\u0441\u044C \u0431\u0443\u0434\u0435\u0442 \u200B\u200B\u043E\u0434\u0438\u043D\u0430\u043A\u043E\u0432\u043E \u200B\u0438\u043D\u0442\u0435\u0440\u0435\u0441\u043D\u043E \u200B\u043F\u0440\u043E\u0433\u0440\u0430\u043C\u043C\u0438\u0441\u0442\u0430\u043C \u200B\u0438 \u0436\u0443\u0440\u043D\u0430\u043B\u0438\u0441\u0442\u0430\u043C, \u200B\u200B\u0430\u0434\u043C\u0438\u043D\u0430\u043C \u200B\u0438 \u0440\u0435\u043A\u043B\u0430\u043C\u0449\u0438\u043A\u0430\u043C, \u200B\u0430\u043D\u0430\u043B\u0438\u0442\u0438\u043A\u0430\u043C \u200B\u0438 \u0434\u0438\u0437\u0430\u0439\u043D\u0435\u0440\u0430\u043C, \u200B\u043C\u0435\u043D\u0435\u0434\u0436\u0435\u0440\u0430\u043C \u200B\u0432\u044B\u0441\u0448\u0435\u0433\u043E \u200B\u0438 \u0441\u0440\u0435\u0434\u043D\u0435\u0433\u043E \u200B\u0437\u0432\u0435\u043D\u0430, \u200B\u0432\u043B\u0430\u0434\u0435\u043B\u044C\u0446\u0430\u043C \u200B\u043A\u0440\u0443\u043F\u043D\u044B\u0445 \u200B\u043A\u043E\u043C\u043F\u0430\u043D\u0438\u0439 \u200B\u0438 \u043D\u0435\u0431\u043E\u043B\u044C\u0448\u0438\u0445 \u200B\u0444\u0438\u0440\u043C, \u200B\u0430 \u0442\u0430\u043A\u0436\u0435 \u200B\u0432\u0441\u0435\u043C \u200B\u0442\u0435\u043C, \u200B\u0434\u043B\u044F \u043A\u043E\u0433\u043E \u200BIT \u2014 \u200B\u044D\u0442\u043E \u043D\u0435 \u043F\u0440\u043E\u0441\u0442\u043E \u200B\u0434\u0432\u0435 \u0431\u0443\u043A\u0432\u044B \u200B\u0430\u043B\u0444\u0430\u0432\u0438\u0442\u0430.'  # noqa
+    publisher = 'Habr Blockchain Publishing LTD'
+    category = 'blog'
+    cover_url = u'https://habr.com/img/habr_ru.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='h1')
+
+    remove_tags_after = dict(name='div', attrs={'class': 'tm-misprint-area'})
+
+    remove_tags = [
+        dict(name='div', attrs={'class': 'tm-article-presenter__meta'}),
+        dict(name='div', attrs={'class': 'tm-article-poll'})
+    ]
+
+    feeds = [
+        (
+            '\u041D\u043E\u0432\u043E\u0441\u0442\u0438',
+            'https://habr.com/ru/rss/news/?fl=ru'
+        ),
+        (
+            '\u0412\u0441\u0435 \u043C\u0430\u0442\u0435\u0440\u0438\u0430\u043B\u044B',
+            'https://habr.com/ru/rss/all/all/?fl=ru'
+        ),
+        (
+            '\u0420\u0435\u0439\u0442\u0438\u043D\u0433 \u226510',
+            'https://habr.com/ru/rss/all/top10/?fl=ru'
+        ),
+        (
+            '\u0420\u0435\u0439\u0442\u0438\u043D\u0433 \u226525',
+            'https://habr.com/ru/rss/all/top25/?fl=ru'
+        ),
+        (
+            '\u0420\u0435\u0439\u0442\u0438\u043D\u0433 \u226550',
+            'https://habr.com/ru/rss/all/top50/?fl=ru'
+        ),
+        (
+            '\u0420\u0435\u0439\u0442\u0438\u043D\u0433 \u2265100',
+            'https://habr.com/ru/rss/all/top100/?fl=ru'
+        ),
+    ]
+
+    def preprocess_html(self, soup):
+        for img in soup.findAll('img', attrs={'data-src': True}):
+            img['src'] = img['data-src']
+        return soup

recipes/interfax.recipe

@@ -0,0 +1,34 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+
+class InterfaxUAEN(BasicNewsRecipe):
+    title = 'Interfax-Ukraine'
+    __author__ = 'bugmen00t'
+    description = 'The Interfax-Ukraine News Agency, founded in 1992, is subsidiary of Interfax Information Services.'
+    publisher = 'Interfax-Ukraine News Agency'
+    category = 'newspaper'
+    cover_url = u'https://interfax.com.ua/static/articles/images/interfax_ukraine_logo_eng.svg'
+    language = 'en_UK'
+    no_stylesheets = True
+    remove_javascript = False
+    auto_cleanup = False
+    oldest_article = 3
+    max_articles_per_feed = 30
+
+    remove_tags_before = dict(
+        name='article', attrs={'class': 'article article-content-view'}
+    )
+
+    remove_tags_after = dict(
+        name='article', attrs={'class': 'article article-content-view'}
+    )
+
+    remove_tags = [
+        dict(name='div', attrs={'class': 'grid article-content-secondary-header'}),
+        dict(name='div', attrs={'class': 'article-tags'}),
+    ]
+
+    feeds = [('Latest news', 'https://en.interfax.com.ua/news/last.rss')]

recipes/interfax_uk.recipe

@@ -0,0 +1,37 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+
+class InterfaxUARU(BasicNewsRecipe):
+    title = '\u0418\u043D\u0442\u0435\u0440\u0444\u0430\u043A\u0441-\u0423\u043A\u0440\u0430\u0438\u043D\u0430'
+    __author__ = 'bugmen00t'
+    description = '\u0418\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u044F \u043E \u043F\u043E\u0441\u043B\u0435\u0434\u043D\u0438\u0445 \u0441\u043E\u0431\u044B\u0442\u0438\u044F\u0445 \u0432 \u043F\u043E\u043B\u0438\u0442\u0438\u043A\u0435 \u0423\u043A\u0440\u0430\u0438\u043D\u044B, \u043A\u043B\u044E\u0447\u0435\u0432\u044B\u0435 \u0443\u043A\u0440\u0430\u0438\u043D\u0441\u043A\u0438\u0435 \u044D\u043A\u043E\u043D\u043E\u043C\u0438\u0447\u0435\u0441\u043A\u0438\u0435 \u043D\u043E\u0432\u043E\u0441\u0442\u0438 \u0438 \u043E\u0441\u043D\u043E\u0432\u043D\u044B\u0435 \u0441\u043E\u0431\u044B\u0442\u0438\u044F \u0432 \u0441\u0442\u0440\u0430\u043D\u0430\u0445 \u0421\u041D\u0413 \u0438 \u043C\u0438\u0440\u0430.'  # noqa
+    publisher = '\u0418\u043D\u0444\u043E\u0440\u043C\u0430\u0446\u0438\u043E\u043D\u043D\u043E\u0435 \u0430\u0433\u0435\u043D\u0442\u0441\u0442\u0432\u043E \u00AB\u0418\u043D\u0442\u0435\u0440\u0444\u0430\u043A\u0441-\u0423\u043A\u0440\u0430\u0438\u043D\u0430\u00BB'  # noqa
+    category = 'newspaper'
+    cover_url = u'https://interfax.com.ua/static/articles/images/interfax_ukraine_logo_rus.svg'
+    language = 'ru_UK'
+    no_stylesheets = True
+    remove_javascript = False
+    auto_cleanup = False
+    oldest_article = 2
+    max_articles_per_feed = 30
+
+    remove_tags_before = dict(
+        name='article', attrs={'class': 'article article-content-view'}
+    )
+
+    remove_tags_after = dict(
+        name='article', attrs={'class': 'article article-content-view'}
+    )
+
+    remove_tags = [
+        dict(name='div', attrs={'class': 'grid article-content-secondary-header'}),
+        dict(name='div', attrs={'class': 'article-tags'}),
+    ]
+
+    feeds = [(
+        '\u041D\u043E\u0432\u043E\u0441\u0442\u0438',
+        'https://ru.interfax.com.ua/news/last.rss'
+    )]

recipes/knife_media.recipe

@@ -0,0 +1,41 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+
+class KnifeMedia(BasicNewsRecipe):
+    title = '\u041D\u043E\u0436'
+    __author__ = 'bugmen00t'
+    description = '\u0418\u043D\u0442\u0435\u043B\u043B\u0435\u043A\u0442\u0443\u0430\u043B\u044C\u043D\u044B\u0439 \u0436\u0443\u0440\u043D\u0430\u043B \u043E \u043A\u0443\u043B\u044C\u0442\u0443\u0440\u0435 \u0438 \u043E\u0431\u0449\u0435\u0441\u0442\u0432\u0435'  # noqa
+    publisher = '\u041C\u0438\u0445\u0430\u0438\u043B \u0426\u044B\u0433\u0430\u043D, \u0422\u0430\u0442\u044C\u044F\u043D\u0430 \u041A\u043E\u044D\u043D'
+    category = 'blog'
+    cover_url = u'https://knife.media/feature/pdd/img/knife_logo.33a98aee.svg'
+    language = 'ru'
+    no_stylesheets = False
+    remove_javascript = False
+    auto_cleanup = False
+    oldest_article = 14
+    max_articles_per_feed = 30
+
+    remove_tags_before = dict(name='div', attrs={'class': 'entry-header'})
+
+    remove_tags_after = dict(name='div', attrs={'class': 'entry-content'})
+
+    remove_tags = [
+        dict(name='aside'),
+        dict(name='div', attrs={'class': 'entry-header__share share'}),
+        dict(name='div', attrs={'class': 'entry-comments'}),
+        dict(name='div', attrs={'class': 'entry-footer'}),
+        dict(name='div', attrs={'class': 'entry-bottom'}),
+        dict(name='figure', attrs={'class': 'figure figure--similar'})
+    ]
+
+    feeds = [(
+        '\u041B\u043E\u043D\u0433\u0440\u0438\u0434\u044B',
+        'https://knife.media/category/longreads/feed/'
+    ),
+             (
+                 '\u041D\u043E\u0432\u043E\u0441\u0442\u0438',
+                 'https://knife.media/category/news/feed/'
+             )]

recipes/pravda_uk.recipe

@@ -0,0 +1,76 @@
+#!/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 PravdaUAUA(BasicNewsRecipe):
+    title = '\u0423\u043A\u0440\u0430\u0457\u043D\u0441\u044C\u043A\u0430 \u043F\u0440\u0430\u0432\u0434\u0430'
+    __author__ = 'bugmen00t'
+    description = '\u0423\u043A\u0440\u0430\u0457\u043D\u0441\u044C\u043A\u0435 \u0441\u0443\u0441\u043F\u0456\u043B\u044C\u043D\u043E-\u043F\u043E\u043B\u0456\u0442\u0438\u0447\u043D\u0435 \u0456\u043D\u0442\u0435\u0440\u043D\u0435\u0442-\u0417\u041C\u0406'  # noqa
+    publisher = 'pravda.com.ua'
+    category = 'newspaper'
+    cover_url = u'https://img.pravda.com/images/up_for_fb.gif'
+    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='article', attrs={'class': 'post'})
+
+    remove_tags = [
+        dict(name='footer'),
+        dict(name='div', attrs={'class': 'nts-video-wrapper'}),
+        dict(name='div', attrs={'class': 'post-report'}),
+        dict(name='div', attrs={'class': 'post__report'}),
+        dict(name='div', attrs={'class': 'social_item'}),
+        dict(name='div', attrs={'class': 'sidebar'}),
+        dict(
+            name='div',
+            attrs={
+                'class':
+                'article-announcement-photo article-announcement-photo-block-1'
+            }
+        ),
+        dict(
+            name='div',
+            attrs={'class': 'statistic-bottom-block statistic-top-block'}
+        ),
+        dict(name='div', attrs={'class': 'modal modal_search modal_white'}),
+        dict(name='div', attrs={'class': 'modal_auth modal_white'}),
+        dict(name='div', attrs={'class': 'main_logo'}),
+        dict(name='div', attrs={'class': 'footer_banner'}),
+        dict(name='nav', attrs={'class': 'block block_menu'}),
+        dict(name='div', attrs={'class': 'pagewrap page-point'}),
+        dict(name='div', attrs={'class': 'modal fade search-popup'}),
+        dict(name='div', attrs={'data-vr-zone': 'Mobile main menu'}),
+        dict(name='aside'),
+        dict(name='div', attrs={'class': 'block_related'}),
+        dict(name='div', attrs={'class': 'block_comments'}),
+        dict(name='div', attrs={'class': 'post_tags'}),
+        dict(name='div', attrs={'class': 'post__tags'})
+    ]
+
+    feeds = [
+        (
+            '\u0412\u0441\u0456 \u043C\u0430\u0442\u0435\u0440\u0456\u0430\u043B\u0438',
+            'https://www.pravda.com.ua/rss/'
+        ),
+        (
+            '\u041D\u0430\u0439\u0432\u0430\u0436\u043B\u0438\u0432\u0456\u0448\u0456 \u043D\u043E\u0432\u0438\u043D\u0438',
+            'https://www.pravda.com.ua/rss/view_mainnews/'
+        ),
+        (
+            '\u041D\u043E\u0432\u0438\u043D\u0438',
+            'https://www.pravda.com.ua/rss/view_news/'
+        ),
+        (
+            '\u041F\u0443\u0431\u043B\u0456\u043A\u0430\u0446\u0456\u0457',
+            'https://www.pravda.com.ua/rss/view_pubs/'
+        ),
+    ]

recipes/pravda_ukraine.recipe

@@ -0,0 +1,61 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+
+class PravdaUAEN(BasicNewsRecipe):
+    title = 'Ukrainska Pravda'
+    __author__ = 'bugmen00t'
+    description = ' Ukrainian online newspaper founded by Georgiy Gongadze with an emphasis on the politics of Ukraine. '
+    publisher = 'pravda.com.ua'
+    category = 'newspaper'
+    cover_url = u'https://img.pravda.com/images/up_for_fb.gif'
+    language = 'en_UK'
+    no_stylesheets = False
+    remove_javascript = False
+    auto_cleanup = False
+    oldest_article = 30
+    max_articles_per_feed = 30
+
+    remove_tags_before = dict(name='h1')
+
+    remove_tags_after = dict(name='article', attrs={'class': 'post'})
+
+    remove_tags = [
+        dict(name='footer'),
+        dict(name='div', attrs={'class': 'nts-video-wrapper'}),
+        dict(name='div', attrs={'class': 'post-report'}),
+        dict(name='div', attrs={'class': 'post__report'}),
+        dict(name='div', attrs={'class': 'social_item'}),
+        dict(name='div', attrs={'class': 'sidebar'}),
+        dict(
+            name='div',
+            attrs={
+                'class':
+                'article-announcement-photo article-announcement-photo-block-1'
+            }
+        ),
+        dict(
+            name='div',
+            attrs={'class': 'statistic-bottom-block statistic-top-block'}
+        ),
+        dict(name='div', attrs={'class': 'modal modal_search modal_white'}),
+        dict(name='div', attrs={'class': 'modal_auth modal_white'}),
+        dict(name='div', attrs={'class': 'main_logo'}),
+        dict(name='div', attrs={'class': 'footer_banner'}),
+        dict(name='nav', attrs={'class': 'block block_menu'}),
+        dict(name='div', attrs={'class': 'pagewrap page-point'}),
+        dict(name='div', attrs={'class': 'modal fade search-popup'}),
+        dict(name='div', attrs={'data-vr-zone': 'Mobile main menu'}),
+        dict(name='aside'),
+        dict(name='div', attrs={'class': 'block_related'}),
+        dict(name='div', attrs={'class': 'block_comments'}),
+        dict(name='div', attrs={'class': 'post_tags'}),
+        dict(name='div', attrs={'class': 'post__tags'})
+    ]
+
+    feeds = [('All materials', 'https://www.pravda.com.ua/eng/rss/'),
+             ('Top news', 'https://www.pravda.com.ua/eng/rss/view_mainnews/'),
+             ('News', 'https://www.pravda.com.ua/eng/rss/view_news/'),
+             ('Articles', 'https://www.pravda.com.ua/eng/rss/view_pubs/')]

recipes/pravda_ukraine_ru.recipe

@@ -0,0 +1,75 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+
+class PravdaUARU(BasicNewsRecipe):
+    title = '\u0423\u043A\u0440\u0430\u0438\u043D\u0441\u043A\u0430\u044F \u043F\u0440\u0430\u0432\u0434\u0430'
+    __author__ = 'bugmen00t'
+    description = '\u0418\u043D\u0442\u0435\u0440\u043D\u0435\u0442-\u0438\u0437\u0434\u0430\u043D\u0438\u0435, \u043E\u0441\u043D\u043E\u0432\u043D\u0430\u044F \u0442\u0435\u043C\u0430\u0442\u0438\u043A\u0430 \u2014 \u043F\u043E\u043B\u0438\u0442\u0438\u043A\u0430, \u0441\u043E\u0446\u0438\u0430\u043B\u044C\u043D\u044B\u0435 \u043F\u0440\u043E\u0431\u043B\u0435\u043C\u044B, \u044D\u043A\u043E\u043D\u043E\u043C\u0438\u043A\u0430. '  # noqa
+    publisher = 'pravda.com.ua'
+    category = 'newspaper'
+    cover_url = u'https://img.pravda.com/images/up_for_fb.gif'
+    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='article', attrs={'class': 'post'})
+
+    remove_tags = [
+        dict(name='footer'),
+        dict(name='div', attrs={'class': 'nts-video-wrapper'}),
+        dict(name='div', attrs={'class': 'post-report'}),
+        dict(name='div', attrs={'class': 'post__report'}),
+        dict(name='div', attrs={'class': 'social_item'}),
+        dict(name='div', attrs={'class': 'sidebar'}),
+        dict(
+            name='div',
+            attrs={
+                'class':
+                'article-announcement-photo article-announcement-photo-block-1'
+            }
+        ),
+        dict(
+            name='div',
+            attrs={'class': 'statistic-bottom-block statistic-top-block'}
+        ),
+        dict(name='div', attrs={'class': 'modal modal_search modal_white'}),
+        dict(name='div', attrs={'class': 'modal_auth modal_white'}),
+        dict(name='div', attrs={'class': 'main_logo'}),
+        dict(name='div', attrs={'class': 'footer_banner'}),
+        dict(name='nav', attrs={'class': 'block block_menu'}),
+        dict(name='div', attrs={'class': 'pagewrap page-point'}),
+        dict(name='div', attrs={'class': 'modal fade search-popup'}),
+        dict(name='div', attrs={'data-vr-zone': 'Mobile main menu'}),
+        dict(name='aside'),
+        dict(name='div', attrs={'class': 'block_related'}),
+        dict(name='div', attrs={'class': 'block_comments'}),
+        dict(name='div', attrs={'class': 'post_tags'}),
+        dict(name='div', attrs={'class': 'post__tags'})
+    ]
+
+    feeds = [
+        (
+            '\u0412\u0441\u0435 \u043C\u0430\u0442\u0435\u0440\u0438\u0430\u043B\u044B',
+            'https://www.pravda.com.ua/rus/rss/'
+        ),
+        (
+            '\u0413\u043B\u0430\u0432\u043D\u044B\u0435 \u043D\u043E\u0432\u043E\u0441\u0442\u0438',
+            'https://www.pravda.com.ua/rus/rss/view_mainnews/'
+        ),
+        (
+            '\u041D\u043E\u0432\u043E\u0441\u0442\u0438',
+            'https://www.pravda.com.ua/rus/rss/view_news/'
+        ),
+        (
+            '\u041F\u0443\u0431\u043B\u0438\u043A\u0430\u0446\u0438\u0438',
+            'https://www.pravda.com.ua/rus/rss/view_pubs/'
+        ),
+    ]