Update web.py

web.py

@@ -216,6 +216,8 @@ def web_data():
             style="margin-top: 20px;",
         ),
         H3("1. Document Preparation"),
+        
+        button( Div(
         H4("1.1 Text Extraction"),
         P("""
         Common Crawl provides webpage texts via two formats: WARC (Web ARChive format) and WET (WARC Encapsulated Text). 
@@ -224,7 +226,8 @@ def web_data():
         we found WET files to include boilerplate content like navigation menus, ads, and other irrelevant texts. 
         Accordingly, our pipeline starts from raw WARC files, reads with the warcio library, and extracts texts using trafilatura.
         """),
-        DV2("data/sample_wet.json", "data/sample_warc.json", 3),
+        DV2("data/sample_wet.json", "data/sample_warc.json", 3),), cls="collapsible"),
+        
         H4("1.2 Language Identification"),
         P("""
         After text extraction, the non-English texts are then filtered out by fastText language identifier with a threshold of 0.65.