Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,98 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import requests
+from bs4 import BeautifulSoup
+import pandas as pd
+import re
+import urllib3
+import time
+
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+
+st.set_page_config(page_title="Faculty Scraper", layout="wide")
+
+st.title("🎓 Universal Faculty Scraper")
+st.write("Enter any faculty page URL to extract Name, Email, and Phone.")
+
+# -------- INPUT --------
+url = st.text_input("Enter Faculty Page URL")
+
+# -------- REGEX --------
+email_regex = r"[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}"
+phone_regex = r"\+?\d[\d\s\-]{8,15}"
+
+# -------- SCRAPER FUNCTION --------
+def scrape_faculty(url):
+    headers = {"User-Agent": "Mozilla/5.0"}
+
+    try:
+        response = requests.get(url, headers=headers, verify=False, timeout=10)
+    except:
+        return pd.DataFrame(), "❌ Failed to load page"
+
+    soup = BeautifulSoup(response.text, "html.parser")
+
+    faculty_data = []
+
+    blocks = soup.find_all(["div", "li", "tr", "section"])
+
+    for block in blocks:
+        text = block.get_text(" ", strip=True)
+
+        if len(text) < 30:
+            continue
+
+        email_match = re.search(email_regex, text)
+        email = email_match.group() if email_match else None
+
+        phone_match = re.search(phone_regex, text)
+        phone = phone_match.group() if phone_match else None
+
+        name = None
+        for tag in block.find_all(["h1", "h2", "h3", "h4", "strong", "b"]):
+            candidate = tag.get_text(strip=True)
+
+            if 3 < len(candidate) < 60 and not re.search(email_regex, candidate):
+                name = candidate
+                break
+
+        if name or email or phone:
+            faculty_data.append([
+                name if name else "Not Available",
+                email if email else "Not Available",
+                phone if phone else "Not Available"
+            ])
+
+    df = pd.DataFrame(faculty_data, columns=["Name", "Email", "Phone"])
+    df = df.drop_duplicates()
+
+    df = df[
+        (df["Email"] != "Not Available") |
+        (df["Phone"] != "Not Available")
+    ]
+
+    return df, "✅ Success"
+
+
+# -------- BUTTON --------
+if st.button("Scrape Data"):
+    if url:
+        with st.spinner("Scraping in progress..."):
+            df, status = scrape_faculty(url)
+
+        st.success(status)
+
+        if not df.empty:
+            st.dataframe(df)
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+            # Download button
+            csv = df.to_csv(index=False).encode("utf-8")
+            st.download_button(
+                "📥 Download CSV",
+                csv,
+                "faculty_data.csv",
+                "text/csv"
+            )
+        else:
+            st.warning("No data found. Try another URL.")
+    else:
+        st.warning("Please enter a URL.")