Update warc_wat_url_processor.py

2024-01-28 09:10:17 +00:00 · 2024-01-28 09:10:17 +00:00 · d0fa7c84f4
commit d0fa7c84f4
parent 875082e8d9
1 changed files with 1 additions and 0 deletions
--- a/warc_wat_url_processor.py
+++ b/warc_wat_url_processor.py
@ -48,6 +48,7 @@ def process_file(file_path):

        # Extract URLs from the gzipped file
        urls = extract_urls_from_file(file_path)
+        print(f"Extracted {len(urls)} URLs from {file_path}")

        # Create the output file path with '_urls.txt' extension
        output_file_path = os.path.splitext(file_path)[0] + '_urls.txt'