feat: add tests of rss convertor

src/markitdown/_markitdown.py

@@ -271,7 +271,7 @@ class RSSConverter(DocumentConverter):
                 entry_content = self._get_data_by_tag_name(entry, "content")
                 
                 if entry_title:
-                    md_text += f"## {entry_title}\n"
+                    md_text += f"\n## {entry_title}\n"
                 if entry_updated:
                     md_text += f"Updated on: {entry_updated}\n"
                 if entry_summary:
@@ -313,7 +313,7 @@ class RSSConverter(DocumentConverter):
                 content = self._get_data_by_tag_name(item, "content:encoded")
                 
                 if title:
-                    md_text += f"## {title}\n"
+                    md_text += f"\n## {title}\n"
                 if pubDate:
                     md_text += f"Published on: {pubDate}\n"
                 if description:

tests/test_markitdown.py

@@ -78,6 +78,13 @@ BLOG_TEST_STRINGS = [
     "an example where high cost can easily prevent a generic complex",
 ]
 
+
+RSS_TEST_STRINGS = [
+    "The Official Microsoft Blog",
+    "In the case of AI, it is absolutely true that the industry is moving incredibly fast",
+]
+    
+
 WIKIPEDIA_TEST_URL = "https://en.wikipedia.org/wiki/Microsoft"
 WIKIPEDIA_TEST_STRINGS = [
     "Microsoft entered the operating system (OS) business in 1980 with its own version of [Unix]",
@@ -207,6 +214,12 @@ def test_markitdown_local() -> None:
         assert test_string not in text_content
     for test_string in SERP_TEST_STRINGS:
         assert test_string in text_content
+        
+    # Test RSS processing
+    result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test_rss.xml"))
+    text_content = result.text_content.replace("\\", "")
+    for test_string in RSS_TEST_STRINGS:
+        assert test_string in text_content
 
     ## Test non-UTF-8 encoding
     result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test_mskanji.csv"))