docs: Update README.md with changelog for show_progress

This commit updates the `README.md` file to include a changelog for the newly added `show_progress` feature. It also updates the example usage to demonstrate the new parameter.

Author: google-labs-jules[bot]

README.md

@@ -7,6 +7,9 @@
 
 LocalSiteMap is an open-source Python package designed for generating sitemaps from local files. It tracks `HTML` and `HTM` files, and generates complete sitemaps for the root website, including directories.
 
+### Changes in version 1.0.1:
+- Added `show_progress` boolean to print out mapping progress, pages mapped, and files found.
+
 ### Changes in version 1.0.0:
 - Added initial package code, with automatic directory crawling to generate the `sitemap.xml` file.
 
@@ -59,7 +62,7 @@ base_url_of_your_website = "https://example.com"
 excluded = ["auth", "forms", "template.html", "media", ".git", ".vscode", "node_modules"]  # Example exclusions
 
 # Generate the sitemap
-generate_sitemap(root_directory, base_url_of_your_website, "sitemap.xml", excluded)
+generate_sitemap(root_directory, base_url_of_your_website, "sitemap.xml", excluded, show_progress=True)
 print("Sitemap generated in sitemap.xml")
 ```
 

localsitemap/__init__.py

@@ -3,7 +3,7 @@
 from xml.etree.ElementTree import Element, SubElement, tostring
 from xml.dom import minidom
 
-def generate_sitemap(root_path, base_url, output_file="sitemap.xml", excluded_paths=None):
+def generate_sitemap(root_path, base_url, output_file="sitemap.xml", excluded_paths=None, show_progress=False):
     """
     Generates a sitemap XML file by crawling a directory structure.
 
@@ -27,6 +27,8 @@ def generate_sitemap(root_path, base_url, output_file="sitemap.xml", excluded_pa
             full_dir_path = os.path.join(root, dir_name)
             if any(excluded in full_dir_path for excluded in excluded_paths):
                 continue
+            if show_progress:
+                print(f"Mapping directory: {full_dir_path}")
             relative_dir_path = os.path.relpath(full_dir_path, root_path)
             url = os.path.join(base_url, relative_dir_path).replace("\\", "/") + "/"
             lastmod = datetime.datetime.fromtimestamp(os.path.getmtime(full_dir_path)).isoformat()
@@ -40,6 +42,10 @@ def generate_sitemap(root_path, base_url, output_file="sitemap.xml", excluded_pa
         for file in files:
             if file.endswith((".html", ".htm")):
                 full_path = os.path.join(root, file)
+
+                if show_progress:
+                    print(f"Found file: {full_path}")
+
                 relative_path = os.path.relpath(full_path, root_path)
 
                 # Check if the file should be excluded
@@ -68,5 +74,9 @@ def generate_sitemap(root_path, base_url, output_file="sitemap.xml", excluded_pa
     reparsed = minidom.parseString(xml_string)
     pretty_xml = reparsed.toprettyxml(indent="  ")
 
+    if show_progress:
+        print(f"Total pages mapped: {len(urlset)}")
+        print(f"Saving sitemap to {output_file}...")
+
     with open(output_file, "w", encoding="utf-8") as f:
         f.write(pretty_xml)