Update Saechsische Zeitung

recipes/saechsische.recipe

@@ -1,22 +1,21 @@
 #!/usr/bin/env python
 ##
-# Written:      March 2020
-# Version:      1.0
-# Last update:  2020-03-27
+## Written:      March 2020
+## Version:      1.1
+## Last update:  2023-03-31
 ##
 from __future__ import unicode_literals, division, absolute_import, print_function
+
 '''
 Fetch RSS-Feeds from saechsische.de
 '''
 
 from calibre.web.feeds.news import BasicNewsRecipe
 
-
 def classes(classes):
     q = frozenset(classes.split(' '))
-    return dict(
-        attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}
-    )
+    return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)})
+
 
 
 class Saechsische(BasicNewsRecipe):
@@ -32,19 +31,23 @@ class Saechsische(BasicNewsRecipe):
     no_stylesheets = True
     remove_javascript = True
     remove_empty_feeds = True
+    compress_news_images = True
+    compress_news_images_auto_size = 8
     scale_news_images_to_device = True
+    delay = 1
     ignore_duplicate_articles = {'title', 'url'}
+
     cover_url             = 'https://www.saechsische.de/img/logo.svg'
 
     feeds = [
         ('Dresden', 'feed://www.saechsische.de/rss/dresden'),
         ('Sachsen', 'feed://saechsische.de/rss/sachsen'),
-        ('Dynamo', 'feed://www.saechsische.de/rss/dynamo'),
+        ('Deutschland und Welt', 'feed://www.saechsische.de/rss/deutschland-welt'),
         ('Politik', 'feed://www.saechsische.de/rss/politik'),
         ('Wirtschaft', 'feed://www.saechsische.de/rss/wirtschaft'),
         ('Feuilleton', 'feed://www.saechsische.de/rss/feuilleton'),
         ('Sport', 'feed://www.saechsische.de/rss/sport'),
-        ('Deutschland und Welt', 'feed://www.saechsische.de/rss/deutschland-welt'),
+        #('Dynamo', 'feed://www.saechsische.de/rss/dynamo'),
         #('Bautzen', 'feed://www.saechsische.de/rss/bautzen'),
         #('Bischofswerda', 'feed://www.saechsische.de/rss/bischofswerda'),
         #('Dippoldiswalde', 'feed://www.saechsische.de/rss/dippoldiswalde'),
@@ -64,13 +67,59 @@ class Saechsische(BasicNewsRecipe):
         #('Zittau', 'feed://www.saechsische.de/rss/zittau'),
     ]
 
+    template_css = '''
+.article_date { color: gray; font-family: monospace;}
+.article_description { text-indent: 0pt; }
+a.article { font-weight: bold; text-align:left; }
+a.feed { font-weight: bold; }
+.calibre_navbar { font-size: 200% !important; }
+'''
+
+    extra_css = '''
+        h2 {margin-top: 0em;}
+    '''
     keep_only_tags = [
                         dict(name='article', attrs={'class':'article-detail'}),
                       ]
 
-    remove_tags = [
-        classes('article-fill'),
-        dict(name='div', attrs={'class': 'article-related-container'}),
-        dict(name='div', attrs={'id': 'article-header'}),
-        dict(name='span', attrs={'class': 'article-plus'}),
+    remove_tags = [ classes('article-fill'),
+                    dict(name='div', attrs={'class':'related-articles'}),
+                    dict(name='a', attrs={'class':'article-remember-link'}),
+                    dict(name='a', attrs={'href':'https://www.saechsische.de/dresden'}),
+                    dict(name='a', attrs={'href':'https://www.saechsische.de/content/newsletter-lp?utm_content=dresden_kompakt'}),
+                    dict(name='div', attrs={'class':'article-detail-socials'}),
+                    dict(name='div', attrs={'class':'d-desktop-none'}),
+                    dict(name='div', attrs={'class':'floating-share-icon'}),
                       ]
+
+    def parse_feeds(self):
+        # Call parent's method.
+        feeds = BasicNewsRecipe.parse_feeds(self)
+        # Loop through all feeds.
+        for feed in feeds:
+            # Loop through all articles in feed.
+            for article in feed.articles[:]:
+                # Remove articles with '...' in the url.
+                if '/anzeige/' in article.url:
+                    print('Removing:',article.title)
+                    feed.articles.remove(article)
+                elif 'newsletter-dresden' in article.url:
+                    print('Removing:',article.title)
+                    feed.articles.remove(article)
+                # Remove articles with '...' in the title.
+                elif 'Newsblog' in article.title:
+                    print('Removing:',article.title)
+                    feed.articles.remove(article)
+                elif 'Podcast' in article.title:
+                    print('Removing:',article.title)
+                    feed.articles.remove(article)
+        return feeds
+
+    def preprocess_raw_html(self, raw, url):
+        # remove Newsblogs, articles requiring login and advertisements
+        unwanted_article_keywords = ['unser Newsblog', 'Zum Login', '00:00 Uhr',]
+        for keyword in unwanted_article_keywords:
+            if keyword in raw:
+                print('Skipping unwanted article with keyword(s):',keyword)
+                self.abort_article('Skipping unwanted article')
+        return raw