app.py

# Import necessary libraries
import streamlit as st
import textrazor
import matplotlib.pyplot as plt
import pandas as pd
import re

# Set TextRazor API key using Streamlit Secrets
textrazor.api_key = st.secrets["textrazer_api"]

# Streamlit app title and input for URL
st.title("TextRazor Entities Analysis")
url_input = st.text_input("Enter URL to Analyze")

# Check if URL is provided
if url_input:
    # Create TextRazor client and analyze URL
    client = textrazor.TextRazor(extractors=["entities", "topics"])
    response = client.analyze_url(url_input)

    # Create dataframe and lists
    df = pd.DataFrame(columns=['Entity ID', 'Entity Relevance', 'Entity Confidence', 'Entity Freebase'])
    new_entityid = []
    new_relevance = []
    new_confidence = []
    new_freebase = []

    # Loop entities and append to list
    for entity in response.entities():
        entity_id = re.sub(r'\d+', '', entity.id)
        new_entityid.append(entity_id)
        new_relevance.append(entity.relevance_score)
        new_confidence.append(entity.confidence_score)
        new_freebase.append(entity.freebase_types)

    # Assign columns values from lists to dataframe
    df['Entity ID'] = new_entityid
    df['Entity Relevance'] = new_relevance
    df['Entity Confidence'] = new_confidence
    df['Entity Freebase'] = new_freebase

    # Save data to CSV
    df.to_csv('textrazor_v1_entities.csv')

    # Display dataframe
    st.write("Top 25 Entities:")
    st.write(df.head(25))

    # Plot the top 10 entities
    st.bar_chart(df['Entity ID'].value_counts().nlargest(10))

    # Add labels and title to the chart
    plt.xlabel('Entity')
    plt.ylabel('Frequency')
    plt.title('Top 10 Entities by frequency')

    # Show the plot in Streamlit
    st.pyplot(plt)
else:
    st.warning("Please enter a URL to analyze.")