Hugging Face's logo

Spaces:
jayanth-2005
/
New
Runtime error

App Files Community
New
File size: 3,619 Bytes
aca6a88
831a22a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
aca6a88
831a22a
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
import streamlit as st
import pandas as pd
import re
import time

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from bs4 import BeautifulSoup

st.set_page_config(page_title="Faculty Scraper", layout="wide")
st.title("🎓 Universal Faculty Scraper (Clean + Smart)")

EMAIL_REGEX = r"[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}"

# -------- DRIVER --------
def get_driver():
    options = Options()
    options.binary_location = "/usr/bin/chromium"

    options.add_argument("--headless")
    options.add_argument("--no-sandbox")
    options.add_argument("--disable-dev-shm-usage")

    driver = webdriver.Chrome(options=options)
    return driver


# -------- NAME CLEANING --------
def name_from_email(email):
    name_part = email.split("@")[0]

    # Replace separators
    name_part = re.sub(r"[._]", " ", name_part)

    # Split camel case
    name_part = re.sub(r'([a-z])([A-Z])', r'\1 \2', name_part)

    # Remove numbers
    name_part = re.sub(r'\d+', '', name_part)

    words = name_part.split()

    return " ".join([w.capitalize() for w in words if len(w) > 1])


# -------- PHONE CLEANING --------
def clean_phone(text):
    phones = re.findall(r"\+?\d[\d\s\-]{8,15}", text)

    for p in phones:
        p_clean = p.replace(" ", "")

        # Reject year-like values
        if re.search(r"\d{4}-\d{2}", p_clean):
            continue

        digits = re.sub(r"\D", "", p_clean)

        # Accept only realistic phone lengths
        if 10 <= len(digits) <= 13:
            return p_clean

    return "Not Available"


# -------- MAIN SCRAPER --------
def scrape_faculty(url):
    driver = get_driver()
    driver.get(url)

    time.sleep(5)

    soup = BeautifulSoup(driver.page_source, "html.parser")
    driver.quit()

    data = []

    blocks = soup.find_all(["tr", "div", "li", "section"])

    for block in blocks:
        text = block.get_text(" ", strip=True)

        if len(text) < 20:
            continue

        # -------- EMAIL --------
        email_match = re.search(EMAIL_REGEX, text)
        if not email_match:
            mail = block.find("a", href=re.compile("mailto:", re.I))
            if mail:
                email = mail.get("href").replace("mailto:", "").strip()
            else:
                continue
        else:
            email = email_match.group()

        # -------- NAME --------
        name = None

        # Try headings
        h = block.find(["h1", "h2", "h3", "h4", "strong", "b"])
        if h:
            name = h.get_text(strip=True)

        # Fallback
        if not name or len(name) < 3:
            name = name_from_email(email)

        # -------- PHONE --------
        phone = clean_phone(text)

        data.append([name, email, phone])

    df = pd.DataFrame(data, columns=["Name", "Email", "Phone"])

    # -------- REMOVE DUPLICATES --------
    df = df.drop_duplicates(subset=["Email"])

    return df


# -------- UI --------
url = st.text_input("🔗 Enter Faculty Page URL")

if st.button("🚀 Scrape Data"):
    if not url:
        st.warning("Please enter a URL")
    else:
        with st.spinner("Scraping intelligently..."):
            df = scrape_faculty(url)

        if not df.empty:
            st.success("✅ Data Extracted Successfully")

            st.dataframe(df, use_container_width=True)

            csv = df.to_csv(index=False).encode("utf-8")

            st.download_button(
                "📥 Download CSV",
                csv,
                "faculty_data.csv",
                "text/csv"
            )
        else:
            st.error("❌ No data found")