{}
# Online Python compiler (interpreter) to run Python online.
# Write Python 3 code in this online editor and run it.
import requests
from bs4 import BeautifulSoup
import pandas as pd
import json
def scrape_bu_facts(url='http://www.bu.edu/president/boston-university-facts-stats/'):
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
facts = {}
for li in soup.select('.facts li'):
text = li.get_text(strip=True)
if ':' in text:
key, value = text.split(':', 1)
facts[key.strip()] = value.strip()
with open('bu_facts.json', 'w') as f:
json.dump(facts, f, indent=2)
print("✅ Saved: bu_facts.json")
def scrape_uci_datasets(url='https://archive.ics.uci.edu/ml/datasets.php'):
try:
tables = pd.read_html(url)
datasets = tables[0] # first table is usually the main one
datasets.to_json('uci_datasets.json', orient='records', indent=2)
print("✅ Saved: uci_datasets.json")
except Exception as e:
print("❌ UCI scraping failed:", e)
def scrape_us_presidents(url='https://en.wikipedia.org/wiki/List_of_presidents_of_the_United_States'):
try:
tables = pd.read_html(url)
presidents = tables[0]
# Simplify multi-level headers if needed
presidents.columns = [col if not isinstance(col, tuple) else col[-1] for col in presidents.columns]
presidents.to_json('us_presidents.json', orient='records', indent=2)
print("✅ Saved: us_presidents.json")
except Exception as e:
print("❌ Presidents scraping failed:", e)
def main():
print("🔍 Scraping BU facts...")
scrape_bu_facts()
print("🔍 Scraping UCI datasets...")
scrape_uci_datasets()
print("🔍 Scraping U.S. Presidents list...")
scrape_us_presidents()
if __name__ == '__main__':
main()