Add Ruhr Nachrichten

docs/supported_publishers.md

@@ -309,6 +309,23 @@
       <td>&#160;</td>
       <td>&#160;</td>
     </tr>
+    <tr>
+      <td>
+        <code>RuhrNachrichten</code>
+      </td>
+      <td>
+        <div>Ruhr Nachrichten</div>
+      </td>
+      <td>
+        <a href="https://www.ruhrnachrichten.de/">
+          <span>www.ruhrnachrichten.de</span>
+        </a>
+      </td>
+      <td>
+        <code>topics</code>
+      </td>
+      <td>&#160;</td>
+    </tr>
     <tr>
       <td>
         <code>SpiegelOnline</code>

src/fundus/publishers/de/__init__.py

@@ -26,6 +26,7 @@
 from .tagesschau import TagesschauParser
 from .taz import TazParser
 from .waz import WAZParser
+from .rn import RuhrNachrichtenParser
 
 
 # noinspection PyPep8Naming
@@ -240,3 +241,14 @@ class DE(PublisherEnum):
         ],
         parser=RheinischePostParser,
     )
+
+    RuhrNachrichten = PublisherSpec(
+        name="Ruhr Nachrichten",
+        domain="https://www.ruhrnachrichten.de/",
+        sources=[
+            RSSFeed("https://www.ruhrnachrichten.de/service/feed/"),
+            Sitemap("https://www.ruhrnachrichten.de/sitemap_index.xml"),
+            NewsMap("https://www.ruhrnachrichten.de/news-sitemap.xml"),
+        ],
+        parser=RuhrNachrichtenParser,
+    )

src/fundus/publishers/de/rn.py

@@ -0,0 +1,35 @@
+import datetime
+from typing import List, Optional
+
+from lxml.cssselect import CSSSelector
+
+from fundus.parser import ArticleBody, BaseParser, ParserProxy, attribute
+from fundus.parser.utility import (
+    extract_article_body_with_selector,
+    generic_author_parsing,
+    generic_date_parsing,
+)
+
+class RuhrNachrichtenParser(ParserProxy):
+    class V1(BaseParser):
+        _paragraph_selector = CSSSelector("div[class*=article-body] > p")
+
+        @attribute
+        def body(self) -> ArticleBody:
+            return extract_article_body_with_selector(
+                self.precomputed.doc,
+                paragraph_selector=self._paragraph_selector,
+            )
+
+        @attribute
+        def publishing_date(self) -> Optional[datetime.datetime]:
+            return generic_date_parsing(self.precomputed.ld.bf_search("datePublished"))
+
+        @attribute
+        def authors(self) -> List[str]:
+            return generic_author_parsing(self.precomputed.ld.bf_search("author"))
+
+        @attribute
+        def title(self) -> Optional[str]:
+            return self.precomputed.meta.get("og:title")
+