Update Аргументы и Факты

recipes/aif_ru.recipe

@@ -1,37 +1,45 @@
-__license__ = 'GPL v3'
+#!/usr/bin/env python
-__copyright__ = '2010 - 2014, Darko Miletic <darko.miletic at gmail.com>'
+# vim:fileencoding=utf-8
-'''
+from __future__ import with_statement, unicode_literals
-www.aif.ru
-'''
-
 from calibre.web.feeds.news import BasicNewsRecipe
 
 
-class AIF_ru(BasicNewsRecipe):
+class AdvancedUserRecipe1592177429(BasicNewsRecipe):
-    title = 'Arguments & Facts - Russian'
+    title = 'Аргументы и Факты'
-    __author__ = 'Darko Miletic'
-    description = 'News from Russia'
-    publisher = 'AIF'
-    category = 'news, politics, Russia'
-    oldest_article = 2
-    max_articles_per_feed = 100
-    no_stylesheets = True
-    use_embedded_content = False
     encoding = 'utf8'
     language = 'ru'
-    publication_type = 'magazine'
+    oldest_article = 7
-    masthead_url = 'http://static3.aif.ru/glossy/index/i/logo.png'
+    max_articles_per_feed = 25
-    extra_css             = """
+    verbose = 3
-                                body{font-family: Verdana,Arial,Helvetica,sans1,sans-serif}
-                                img{display: block}
-                            """
-    keep_only_tags = [
-        dict(name='h1', attrs={'class': 'title'}), dict(name='div', attrs={'class': 'prew_tags'}), dict(
-            name='article', attrs={'class': lambda x: x and 'articl_body' in x.split()})
-    ]
-    remove_tags = [
-        dict(name=['iframe', 'object', 'link', 'base', 'input', 'meta']), dict(name='div', attrs={'class': 'in-topic'}), dict(name='div', attrs={
-            'class': lambda x: x and 'related_article' in x.split()}), dict(name='div', attrs={'class': lambda x: x and 'articl_tag' in x.split()})
-    ]
 
-    feeds = [(u'News', u'http://www.aif.ru/rss/all.php')]
+    feeds = [
+        ('AIF', 'https://www.aif.ru/rss/all.php'),
+    ]
+    INDEX = 'https://www.aif.ru/rss/all.php'
+
+    def parse_index(self):
+        feeds = []
+        section_title = 'aif'
+        articles = []
+        soup = self.index_to_soup(self.INDEX)
+        ii = 0
+        for item in soup.findAll('item'):
+            if ii < self.max_articles_per_feed:
+                try:
+                    ii = ii + 1
+                    A = str(item)
+                    i = A.find(u'link')
+                    j = A.find(u'description')
+                    ZZ = item.find('description')
+                    ZZ1 = str(ZZ)  # bs4.element.Tag to str
+                    ZZ2 = ZZ1[24:-19]
+                    AU = A[i:j]
+                    try:
+                        articles.append({'url':AU[6:-2], 'title':ZZ2})
+                    except Exception:
+                        pass
+                except Exception:
+                    self.log("Exception handled!")
+        if articles:
+            feeds.append((section_title, articles))
+        return feeds