more russian and ukranian news sources by bugmen00t

recipes/dovod.recipe

@@ -0,0 +1,25 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
+
+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.'  # noqa
+    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/')]

recipes/kyivpost_ar.recipe

@@ -0,0 +1,32 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
+
+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.'  # noqa
+    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'
+    )]

recipes/kyivpost_en.recipe

@@ -0,0 +1,29 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
+
+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.'  # noqa
+    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')]

recipes/kyivpost_ua.recipe

@@ -0,0 +1,31 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
+
+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.'  # noqa
+    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')
+    ]

recipes/moscowtimes_en.recipe

@@ -0,0 +1,39 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
+
+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.'  # noqa
+    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')
+        ]

recipes/moscowtimes_ru.recipe

@@ -0,0 +1,50 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
+
+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.'  # noqa
+    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='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 = [(
+        '\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

recipes/novaya_media.recipe

@@ -0,0 +1,33 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
+
+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.'  # noqa
+    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'  # noqa
+    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'