Upload 2 files

app.py

@@ -0,0 +1,83 @@
+import requests
+from bs4 import BeautifulSoup
+import pandas as pd
+import gradio as gr
+
+def scrape_crunchbase(url):
+    response = requests.get(url)
+    soup = BeautifulSoup(response.content, 'html.parser')
+    
+    # Extract relevant information
+    company_name = soup.find('h1').text.strip() if soup.find('h1') else 'N/A'
+    short_description = soup.find('meta', attrs={'name': 'description'})['content'] if soup.find('meta', attrs={'name': 'description'}) else 'N/A'
+    founded_on = soup.find('span', text='Founded').find_next('span').text.strip() if soup.find('span', text='Founded') else 'N/A'
+    ipo_status = soup.find('span', text='IPO Status').find_next('span').text.strip() if soup.find('span', text='IPO Status') else 'N/A'
+    contact_email = soup.find('a', href=lambda href: href and 'mailto:' in href)['href'].replace('mailto:', '') if soup.find('a', href=lambda href: href and 'mailto:' in href) else 'N/A'
+    legal_name = soup.find('span', text='Legal Name').find_next('span').text.strip() if soup.find('span', text='Legal Name') else 'N/A'
+    website = soup.find('a', href=lambda href: href and 'http' in href)['href'] if soup.find('a', href=lambda href: href and 'http' in href) else 'N/A'
+    city = soup.find('span', text='City').find_next('span').text.strip() if soup.find('span', text='City') else 'N/A'
+    region = soup.find('span', text='Region').find_next('span').text.strip() if soup.find('span', text='Region') else 'N/A'
+    country = soup.find('span', text='Country').find_next('span').text.strip() if soup.find('span', text='Country') else 'N/A'
+    continent = soup.find('span', text='Continent').find_next('span').text.strip() if soup.find('span', text='Continent') else 'N/A'
+    rank_org_company = soup.find('span', text='Rank Org Company').find_next('span').text.strip() if soup.find('span', text='Rank Org Company') else 'N/A'
+    operating_status = soup.find('span', text='Operating Status').find_next('span').text.strip() if soup.find('span', text='Operating Status') else 'N/A'
+    last_funding_type = soup.find('span', text='Last Funding Type').find_next('span').text.strip() if soup.find('span', text='Last Funding Type') else 'N/A'
+    total_rounds = soup.find('span', text='Total Rounds').find_next('span').text.strip() if soup.find('span', text='Total Rounds') else 'N/A'
+    total_investors = soup.find('span', text='Total Investors').find_next('span').text.strip() if soup.find('span', text='Total Investors') else 'N/A'
+    total_money_raised_usd = soup.find('span', text='Total Money Raised USD').find_next('span').text.strip() if soup.find('span', text='Total Money Raised USD') else 'N/A'
+    last_round_money_raised_usd = soup.find('span', text='Last Round Money Raised USD').find_next('span').text.strip() if soup.find('span', text='Last Round Money Raised USD') else 'N/A'
+    most_recent_funding_date = soup.find('span', text='Most Recent Funding Date').find_next('span').text.strip() if soup.find('span', text='Most Recent Funding Date') else 'N/A'
+    industries = soup.find('span', text='Industries').find_next('span').text.strip() if soup.find('span', text='Industries') else 'N/A'
+    similar_companies_permalinks = soup.find('span', text='Similar Companies Permalinks').find_next('span').text.strip() if soup.find('span', text='Similar Companies Permalinks') else 'N/A'
+    min_employees = soup.find('span', text='Min Employees').find_next('span').text.strip() if soup.find('span', text='Min Employees') else 'N/A'
+    max_employees = soup.find('span', text='Max Employees').find_next('span').text.strip() if soup.find('span', text='Max Employees') else 'N/A'
+    max_score = soup.find('span', text='Max Score').find_next('span').text.strip() if soup.find('span', text='Max Score') else 'N/A'
+    
+    # Create a dictionary with the extracted data
+    data = {
+        'Url': url,
+        'Company Name': company_name,
+        'Short Description': short_description,
+        'Founded On': founded_on,
+        'Ipo Status': ipo_status,
+        'Contact Email': contact_email,
+        'Legal Name': legal_name,
+        'Website': website,
+        'City': city,
+        'Region': region,
+        'Country': country,
+        'Continent': continent,
+        'Rank Org Company': rank_org_company,
+        'Operating Status': operating_status,
+        'Last Funding Type': last_funding_type,
+        'Total Rounds': total_rounds,
+        'Total Investors': total_investors,
+        'Total Money Raised USD': total_money_raised_usd,
+        'Last Round Money Raised USD': last_round_money_raised_usd,
+        'Most Recent Funding Date': most_recent_funding_date,
+        'Industries': industries,
+        'Similar Companies Permalinks': similar_companies_permalinks,
+        'Min Employees': min_employees,
+        'Max Employees': max_employees,
+        'Max Score': max_score
+    }
+    
+    # Convert the dictionary to a DataFrame
+    df = pd.DataFrame([data])
+    
+    return df
+
+def scrape_and_display(url):
+    df = scrape_crunchbase(url)
+    return df
+
+# Create a Gradio interface
+iface = gr.Interface(
+    fn=scrape_and_display,
+    inputs="text",
+    outputs="dataframe",
+    title="Crunchbase Scraper",
+    description="Enter a Crunchbase URL to scrape company information."
+)
+
+iface.launch()

requirements.txt

@@ -0,0 +1,4 @@
+requests
+beautifulsoup4
+pandas
+gradio