Add application file

app.py

@@ -0,0 +1,77 @@
+import streamlit as st
+import snscrape.modules.twitter as sntwitter
+import pandas as pd
+import plotly.express as px
+import os
+
+st.set_page_config(page_title="Scraping Twitter")
+
+st.title('Scraping Twitter')
+
+# Input query and number of tweets to scrape
+query = st.text_input('Enter a search query:', 'data science')
+num_tweets = st.number_input(
+    'Number of tweets to scrape:', min_value=1, max_value=1000000, step=1)
+
+# Scrape tweets and store data in a dataframe
+
+
+def scrape_tweets(query, num_tweets):
+    tweets_list = []
+    for i, tweet in enumerate(sntwitter.TwitterSearchScraper(query + ' lang:id').get_items()):
+        if i >= num_tweets:
+            break
+        tweets_list.append([tweet.id, tweet.date, tweet.content, tweet.user.username,
+                           tweet.user.followersCount, tweet.url, tweet.user.id])
+    tweets_df = pd.DataFrame(tweets_list, columns=[
+                             'Tweet Id', 'Datetime', 'Text', 'Username', 'Followers', 'URL', 'User Id'])
+    return tweets_df
+
+
+if st.button('Scrape Tweets'):
+    tweets_df = scrape_tweets(query, num_tweets)
+    st.success('Scraping done!')
+
+    # Display data
+    st.write(tweets_df)
+
+    # Line plot of tweet count over time
+    tweets_df['Date'] = tweets_df['Datetime'].dt.date
+    tweets_by_date = tweets_df.groupby(
+        ['Date'])['Tweet Id'].count().reset_index()
+    fig = px.line(tweets_by_date, x='Date', y='Tweet Id')
+    st.plotly_chart(fig)
+
+    # Scatter plot of followers vs tweet count
+    fig = px.scatter(tweets_df, x='Followers', y='Tweet Id')
+    st.plotly_chart(fig)
+
+    # Username selection and interaction count
+    st.sidebar.title('Username and Interaction Count')
+    selected_username = st.sidebar.selectbox(
+        'Select a username:', options=tweets_df['Username'].unique())
+    st.sidebar.write(
+        f'Interactions with @{selected_username}: {tweets_df[tweets_df["Username"] == selected_username].shape[0]}')
+
+    # Interaction count by username
+    interactions_by_user = tweets_df.groupby(['Username'])['Tweet Id'].count(
+    ).reset_index().sort_values(by=['Tweet Id'], ascending=False)
+    fig = px.bar(interactions_by_user, x='Username', y='Tweet Id')
+    st.plotly_chart(fig)
+
+    # Interaction count with selected username over time
+    tweets_by_date = tweets_df[tweets_df['Username'] == selected_username].groupby(
+        ['Date'])['Tweet Id'].count().reset_index()
+    fig = px.line(tweets_by_date, x='Date', y='Tweet Id')
+    st.plotly_chart(fig)
+
+    # Tweets involving selected username
+    st.write(f'Tweets involving @{selected_username}:')
+    st.write(tweets_df[tweets_df['Username'] == selected_username])
+
+    # Save tweets as CSV file in data folder
+    if not os.path.exists("data"):
+        os.mkdir("data")
+    file_name = f"data/tweets_{query.replace(' ', '_')}.csv"
+    tweets_df.to_csv(file_name, index=False)
+    st.write(f"Tweets saved as {file_name}")