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

# Schema for research paper data
class ResearchPaper(BaseModel):
    title: str = Field(description="Paper title")
    abstract: str = Field(description="Paper abstract")
    authors: List[str] = Field(description="Paper authors")
    publication_date: str = Field(description="Publication date")
    journal: Optional[str] = Field(description="Journal name")
    keywords: Optional[List[str]] = Field(description="Research keywords")
    citations: Optional[int] = Field(description="Citation count")
    doi: Optional[str] = Field(description="Digital Object Identifier")
    url: str = Field(description="Paper URL")
    pdf_url: Optional[str] = Field(description="PDF download URL")

# Schema for research collection results
class ResearchCollectionResult(BaseModel):
    papers: List[ResearchPaper] = Field(description="List of research papers")
    total_papers: int = Field(description="Total number of papers found")
    query: str = Field(description="Search query used")
    collection_date: str = Field(description="Date of collection")

client = Client()

# Search and collect research papers
response = client.search(
    query="Find recent research papers on machine learning applications in healthcare, focusing on papers published in the last year. Extract complete paper details including abstract, citations, and DOI.",
    num_results=15,  # Number of papers to collect
    output_schema=ResearchCollectionResult
)

# Process and analyze research papers
print(f"Query: {response.query}")
print(f"Papers Found: {response.total_papers}")
print(f"Collection Date: {response.collection_date}\n")

for paper in response.papers:
    print(f"Title: {paper.title}")
    print(f"Authors: {', '.join(paper.authors)}")
    if paper.journal:
        print(f"Journal: {paper.journal}")
    print(f"Published: {paper.publication_date}")
    print(f"Citations: {paper.citations or 'N/A'}")
    if paper.keywords:
        print(f"Keywords: {', '.join(paper.keywords)}")
    if paper.doi:
        print(f"DOI: {paper.doi}")
    print(f"URL: {paper.url}")
    if paper.pdf_url:
        print(f"PDF: {paper.pdf_url}")
    print(f"\nAbstract: {paper.abstract}\n")

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

# Schema for company profile data
class CompanyProfile(BaseModel):
    name: str = Field(description="Company name")
    market_share: Optional[float] = Field(description="Market share percentage")
    revenue: Optional[str] = Field(description="Annual revenue")
    employees: Optional[str] = Field(description="Number of employees")
    headquarters: Optional[str] = Field(description="Company headquarters")
    key_products: Optional[List[str]] = Field(description="Key products or services")

# Schema for market metrics
class MarketMetrics(BaseModel):
    size: str = Field(description="Total market size")
    growth_rate: float = Field(description="Annual growth rate percentage")
    cagr: Optional[float] = Field(description="Compound Annual Growth Rate")
    forecast_period: str = Field(description="Market forecast period")
    segments: Dict[str, float] = Field(description="Market segments and their shares")

# Schema for industry analysis
class IndustryAnalysis(BaseModel):
    sector: str = Field(description="Industry sector name")
    subsector: Optional[str] = Field(description="Industry subsector")
    market_metrics: MarketMetrics = Field(description="Market size and growth metrics")
    trends: List[str] = Field(description="Key industry trends")
    key_players: List[CompanyProfile] = Field(description="Major companies in the sector")
    challenges: Optional[List[str]] = Field(description="Industry challenges")
    opportunities: Optional[List[str]] = Field(description="Growth opportunities")
    technologies: Optional[List[str]] = Field(description="Emerging technologies")
    regulations: Optional[List[str]] = Field(description="Key regulations and policies")

client = Client()

# Collect industry analysis data
response = client.extract(
    url="https://industry-research-site.com/sector-analysis",
    prompt="Extract comprehensive industry analysis including detailed market metrics, company profiles, trends, and regulatory factors. Focus on quantitative data where available.",
    output_schema=IndustryAnalysis
)

# Generate insights report
print(f"Industry Analysis: {response.sector}")
if response.subsector:
    print(f"Subsector: {response.subsector}")

print("\nMarket Overview:")
print(f"Size: {response.market_metrics.size}")
print(f"Growth Rate: {response.market_metrics.growth_rate}%")
if response.market_metrics.cagr:
    print(f"CAGR: {response.market_metrics.cagr}%")
print(f"Forecast Period: {response.market_metrics.forecast_period}")

print("\nMarket Segments:")
for segment, share in response.market_metrics.segments.items():
    print(f"- {segment}: {share}%")

print("\nKey Players:")
for player in response.key_players:
    print(f"\nCompany: {player.name}")
    if player.market_share:
        print(f"Market Share: {player.market_share}%")
    if player.revenue:
        print(f"Revenue: {player.revenue}")
    if player.key_products:
        print(f"Key Products: {', '.join(player.key_products)}")

print("\nIndustry Trends:")
for trend in response.trends:
    print(f"- {trend}")

if response.technologies:
    print("\nEmerging Technologies:")
    for tech in response.technologies:
        print(f"- {tech}")

if response.regulations:
    print("\nKey Regulations:")
    for reg in response.regulations:
        print(f"- {reg}")