Update app.py

app.py

@@ -1,65 +1,53 @@
 import streamlit as st
 import os
-import re
-from xml.etree import ElementTree
+import xml.etree.ElementTree as ET
 
-# Function to create a search URL for Wikipedia based on dataset name
-def create_search_url_wikipedia(dataset_name):
+# Function to create search URL on Wikipedia
+def create_search_url_wikipedia(search_query):
     base_url = "https://www.wikipedia.org/search-redirect.php?family=wikipedia&language=en&search="
-    return base_url + dataset_name.replace(' ', '+').replace('–', '%E2%80%93').replace('&', 'and')
+    return base_url + search_query.replace(' ', '+').replace('–', '%E2%80%93').replace('&', 'and')
 
-# Function to scan current directory for XML files and extract URLs
-def scan_xml_for_urls():
-    urls = []
-    for file in os.listdir('.'):
-        if file.endswith('.xml'):
-            try:
-                tree = ElementTree.parse(file)
-                root = tree.getroot()
-                # Assuming that URLs might be within 'url' tags for simplicity
-                for url in root.iter('url'):
-                    urls.append(url.text)
-            except ElementTree.ParseError:
-                st.error(f"Error parsing {file}")
-    return urls
+# Function to scan for XML files and generate Wikipedia links for organizations
+def scan_for_xml_files_and_generate_links():
+    xml_files = [f for f in os.listdir('.') if f.endswith('.xml')]
+    for xml_file in xml_files:
+        tree = ET.parse(xml_file)
+        root = tree.getroot()
+        # Assuming the XML structure provided is consistent across files
+        for org in root.findall(".//nc:Organization", namespaces={'nc': 'http://niem.gov/niem/niem-core/2.0'}):
+            short_name = org.find("nc:OrganizationAbbreviationText", namespaces={'nc': 'http://niem.gov/niem/niem-core/2.0'}).text
+            long_name = org.find("nc:OrganizationName", namespaces={'nc': 'http://niem.gov/niem/niem-core/2.0'}).text
+            st.markdown(f"- **{short_name}**: [Wikipedia]({create_search_url_wikipedia(short_name)})")
+            st.markdown(f"- **{long_name}**: [Wikipedia]({create_search_url_wikipedia(long_name)})")
 
-# Main application
-def main():
-    st.title("Freedom of Information Act (FOIA) 📜 and Open Data 🌍")
-    
-    # Description of FOIA
-    st.markdown("""
-    The Freedom of Information Act (FOIA) 🇺🇸 is a law that keeps citizens in the know about their government. By allowing full or partial disclosure of previously unreleased information and documents controlled by the United States government, FOIA strengthens the principle of transparency and accountability. Datasets created or used by federal programs, and thus made publicly available under FOIA, are invaluable resources for researchers, developers, and the curious minds alike! 🕵️‍♂️🔍✨
+# Streamlit UI
+def app():
+    st.title("Freedom of Information Act (FOIA) Open Data 🌍📊")
+    st.write("""
+    The Freedom of Information Act (FOIA) empowers individuals by granting access to previously unreleased information and documents controlled by the United States government. Championing transparency and accountability, FOIA serves as a foundation for democratic engagement and open government initiatives. 🎉✨
+
+    Below is a list of datasets available under FOIA, alongside guessed Wikipedia URLs for more information. 📚🔍
     """)
-    
-    # List of datasets under FOIA with guessed Wikipedia URLs
+
+    # Example datasets under FOIA
     datasets = [
         "Provider Taxonomy",
         "Consumer Complaint Database",
-        "National Bridge Inventory",
         "Medicare Provider Utilization and Payment Data",
-        "College Scorecard",
+        "Global Terrorism Database",
+        "National Nutrient Database",
+        "Patent Grant Full Text Data",
         "Toxic Release Inventory",
-        "Veterans Data",
-        "Public Access to Court Electronic Records (PACER)"
+        "Residential Energy Consumption Survey",
     ]
-    
-    st.markdown("## FOIA Datasets and Their Wikipedia URLs 🌐")
-    st.markdown("| Dataset | Wikipedia URL |")
-    st.markdown("| ------- | ------------- |")
+
+    # Displaying the datasets table
+    st.markdown("### FOIA Datasets and Wikipedia URLs")
     for dataset in datasets:
-        url = create_search_url_wikipedia(dataset)
-        st.markdown(f"| {dataset} | [Link]({url}) |")
-    
-    # Scan for XML files and display URLs
-    st.markdown("## Detected URLs in Local XML Files 📁🔗")
-    urls = scan_xml_for_urls()
-    if urls:
-        for url in urls:
-            st.markdown(f"- [URL]({url})")
-    else:
-        st.markdown("No XML files with URLs found in the current directory.")
+        st.markdown(f"- **{dataset}**: [Wikipedia]({create_search_url_wikipedia(dataset)})")
+
+    st.markdown("### Organizations in Found XML Files")
+    scan_for_xml_files_and_generate_links()
 
-# Run the main application
 if __name__ == "__main__":
-    main()
+    app()