Update pages/6_Semi_structured_data.py

pages/6_Semi_structured_data.py

@@ -427,4 +427,26 @@ elif file_type == "JSON":
 
     ''')
     
+elif file_type == "HTML":
+    st.title("HTML")
+    st.markdown('''
+    - HTML **(Hypertext Markup Language)**
+    - HTML (HyperText Markup Language) is the standard language used to create and structure content on the web, using tags to define elements such as text, images, links, and other multimedia.
+    ''')
+    st.subheader("How to read and get the tabular data from the URLs?...")
+    st.code('''import pandas as pd
+    data = pd.read_html("https://en.wikipedia.org/wiki/Indian_Premier_League")
+    data
+    ''')
+    st.markdown('''
+    - It gives all the tables related to Indian_Premier_League
+    - But if we want to get one particular table amongst all tables we need to give unique word related to that particular table we needed
+    ''')
+    st.code('''import pandas as pd
+    data = pd.read_html("https://en.wikipedia.org/wiki/Indian_Premier_League",match="Mitchell Starc")
+    data
+    ''')
+    st.matkdown('''
+    - It gives the particular table which has the word matching as "Mitchell Starc"
+    ''')