Harrison/sitemap local (#4704)

Co-authored-by: Lukas Bauer <lukas.bauer@mayflower.de>

tests/integration_tests/document_loaders/test_sitemap.py

@@ -1,3 +1,4 @@
+from pathlib import Path
 from typing import Any
 
 import pytest
@@ -122,3 +123,12 @@ def test_sitemap_metadata_default() -> None:
     assert len(documents) > 1
     assert "source" in documents[0].metadata
     assert "loc" in documents[0].metadata
+
+
+def test_local_sitemap() -> None:
+    """Test sitemap loader."""
+    file_path = Path(__file__).parent.parent / "examples/sitemap.xml"
+    loader = SitemapLoader(str(file_path))
+    documents = loader.load()
+    assert len(documents) > 1
+    assert "🦜🔗" in documents[0].page_content

tests/integration_tests/examples/sitemap.xml

@@ -0,0 +1,35 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+        xmlns:xhtml="http://www.w3.org/1999/xhtml">
+  
+  <url>
+    <loc>https://python.langchain.com/en/stable/</loc>
+    
+    
+    <lastmod>2023-05-04T16:15:31.377584+00:00</lastmod>
+    
+    <changefreq>weekly</changefreq>
+    <priority>1</priority>
+  </url>
+  
+  <url>
+    <loc>https://python.langchain.com/en/latest/</loc>
+    
+    
+    <lastmod>2023-05-05T07:52:19.633878+00:00</lastmod>
+    
+    <changefreq>daily</changefreq>
+    <priority>0.9</priority>
+  </url>
+  
+  <url>
+    <loc>https://python.langchain.com/en/harrison-docs-refactor-3-24/</loc>
+    
+    
+    <lastmod>2023-03-27T02:32:55.132916+00:00</lastmod>
+    
+    <changefreq>monthly</changefreq>
+    <priority>0.8</priority>
+  </url>
+  
+</urlset>