from scrapegraph_py import Client
from pydantic import BaseModel, Field
from typing import List, Optional

class ContactInfo(BaseModel):
    name: str = Field(description="Contact person's full name")
    email: Optional[str] = Field(description="Email address if available")
    role: Optional[str] = Field(description="Job role or position")
    phone: Optional[str] = Field(description="Phone number if available")
    department: Optional[str] = Field(description="Department or team")

class CompanyContacts(BaseModel):
    contacts: List[ContactInfo] = Field(description="List of contact information")
    company_name: str = Field(description="Company name")

# Initialize the client
client = Client(api_key="your-api-key")

# Scrape company website
response = client.smartscraper(
    website_url="https://company.com/about",
    user_prompt="Extract all contact information for decision makers and leadership team",
    output_schema=CompanyContacts
)

# Process and store leads
for contact in response.contacts:
    if contact.email and contact.role and "manager" in contact.role.lower():
        leads_db.add(contact)

from scrapegraph_py import Client
from pydantic import BaseModel, Field
from typing import List, Optional

class BusinessInfo(BaseModel):
    """Schema for business information"""
    name: str = Field(description="Business name")
    website: str = Field(description="Company website URL")
    description: Optional[str] = Field(description="Business description")
    location: Optional[str] = Field(description="Business location")
    industry: Optional[str] = Field(description="Industry or category")
    size: Optional[str] = Field(description="Company size if available")
    contact_email: Optional[str] = Field(description="Primary contact email")
    phone: Optional[str] = Field(description="Business phone number")

class BusinessSearchResults(BaseModel):
    """Schema for search results"""
    businesses: List[BusinessInfo] = Field(description="List of found businesses")
    total_results: Optional[int] = Field(description="Total number of businesses found")

# Initialize the client
client = Client(api_key="your-api-key")

try:
    # Search for businesses in a specific category
    search_results = client.searchscraper(
        user_prompt="Find software companies in San Francisco with their contact details",
        output_schema=BusinessSearchResults,
        num_results=10,  # Number of websites to search (3-20)
        extraction_mode=True  # Use AI extraction mode for structured data
    )

    # Extract and validate leads
    valid_leads = []
    for business in search_results.businesses:
        if not business.website:
            continue
            
        try:
            # Get more detailed information from company website
            details = client.smartscraper(
                website_url=business.website,
                user_prompt="Extract detailed company information including team size, tech stack, and all contact methods",
                output_schema=CompanyContacts  # Defined earlier in the file
            )
            
            if validate_lead(details):  # Your validation logic here
                valid_leads.append(details)
                
        except Exception as e:
            print(f"Error processing {business.name}: {str(e)}")
            continue

    print(f"Found {len(valid_leads)} valid leads out of {len(search_results.businesses)} businesses")

except Exception as e:
    print(f"Error during search: {str(e)}")