Update pages/6.Data Collection.py

pages/6.Data Collection.py

@@ -150,3 +150,56 @@ if format_selected == "CSV":
                 file_name="CSV_guide.ipynb",
                 mime="application/octet-stream",
             )
+
+# Main Section
+st.title("XML Data Format Guide")
+
+# XML Explanation Sections
+st.write("#### a. What is XML?")
+st.write("""
+XML (eXtensible Markup Language) is a markup language designed to store and transport data. 
+It uses a hierarchical structure and tags, making it both human-readable and machine-readable.
+""")
+
+st.write("#### b. How to Read XML Files")
+st.code("""
+import xml.etree.ElementTree as ET
+
+# Parse an XML file
+tree = ET.parse("file.xml")
+root = tree.getroot()
+
+# Access elements
+for child in root:
+    print(child.tag, child.text)
+""", language="python")
+
+st.write("#### c. Issues Encountered When Handling XML Files")
+st.write("""
+1. **Complex Structures:** XML files may have deeply nested hierarchies.
+2. **Large File Sizes:** Memory-intensive parsing for large files.
+3. **Data Inconsistency:** Missing or unexpected tags may cause parsing errors.
+4. **Encoding Issues:** Files with non-standard encodings can fail to parse.
+""")
+
+st.write("#### d. How to Overcome These Issues")
+st.code("""
+from lxml import etree
+
+# Handle large XML files using event-driven parsing
+for event, element in etree.iterparse("large_file.xml", events=("end",)):
+    print(element.tag, element.text)
+    element.clear()
+""", language="python")
+
+# Downloadable Guide Button
+st.markdown("### Download Coding Guide")
+if st.button("Download XML Guide"):
+    file_path = "XML_guide.ipynb"  # Replace with the actual file path
+    with open(file_path, "rb") as file:
+        st.download_button(
+            label="Download XML Guide",
+            data=file,
+            file_name="XML_guide.ipynb",
+            mime="application/octet-stream",
+        )