🏢 Company Information

from pydantic import BaseModel, Field
from typing import List
from scrapegraph_py import ScrapeGraphAI

# Schema for founder information
class FounderSchema(BaseModel):
    name: str = Field(description="Name of the founder")
    role: str = Field(description="Role of the founder in the company")
    linkedin: str = Field(description="LinkedIn profile of the founder")

# Schema for pricing plans
class PricingPlanSchema(BaseModel):
    tier: str = Field(description="Name of the pricing tier")
    price: str = Field(description="Price of the plan")
    credits: int = Field(description="Number of credits included in the plan")

# Schema for social links
class SocialLinksSchema(BaseModel):
    linkedin: str = Field(description="LinkedIn page of the company")
    twitter: str = Field(description="Twitter page of the company")
    github: str = Field(description="GitHub page of the company")

# Schema for company information
class CompanyInfoSchema(BaseModel):
    company_name: str = Field(description="Name of the company")
    description: str = Field(description="Brief description of the company")
    founders: List[FounderSchema] = Field(description="List of company founders")
    logo: str = Field(description="Logo URL of the company")
    partners: List[str] = Field(description="List of company partners")
    pricing_plans: List[PricingPlanSchema] = Field(description="Details of pricing plans")
    contact_emails: List[str] = Field(description="Contact emails of the company")
    social_links: SocialLinksSchema = Field(description="Social links of the company")
    privacy_policy: str = Field(description="URL to the privacy policy")
    terms_of_service: str = Field(description="URL to the terms of service")
    api_status: str = Field(description="API status page URL")

sgai = ScrapeGraphAI(api_key="your-api-key")

res = sgai.extract(
    "Extract info about the company",
    url="https://scrapegraphai.com/",
    schema=CompanyInfoSchema.model_json_schema(),
)

if res.status == "success":
    print(res.data.json_data)
else:
    print("Failed:", res.error)

{
    "company_name": "ScrapeGraphAI",
    "description": "AI-powered web scraping API for structured data extraction",
    "founders": [
        {
            "name": "John Doe",
            "role": "CEO",
            "linkedin": "https://linkedin.com/in/johndoe"
        }
    ],
    "logo": "https://scrapegraphai.com/logo.png",
    "partners": ["OpenAI", "Anthropic"],
    "pricing_plans": [
        {
            "tier": "Starter",
            "price": "$49/month",
            "credits": 1000
        }
    ],
    "contact_emails": ["contact@scrapegraphai.com"],
    "social_links": {
        "linkedin": "https://linkedin.com/company/scrapegraphai",
        "twitter": "https://twitter.com/scrapegraphai",
        "github": "https://github.com/ScrapeGraphAI"
    },
    "privacy_policy": "https://scrapegraphai.com/privacy",
    "terms_of_service": "https://scrapegraphai.com/terms",
    "api_status": "https://status.scrapegraphai.com"
}