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

# Schema for rich result data
class RichResult(BaseModel):
    type: str = Field(description="Type of rich result (featured snippet, knowledge panel, etc.)")
    content: str = Field(description="Rich result content")
    position: int = Field(description="Position in SERP")
    url: Optional[str] = Field(description="Source URL if available")

# Schema for SERP result
class SearchResult(BaseModel):
    position: int = Field(description="SERP position")
    title: str = Field(description="Page title")
    url: str = Field(description="Page URL")
    description: str = Field(description="Meta description")
    breadcrumbs: Optional[List[str]] = Field(description="URL breadcrumbs")
    sitelinks: Optional[List[Dict[str, str]]] = Field(description="Sitelinks data")
    featured_snippet: Optional[bool] = Field(description="Is featured snippet")
    rich_results: Optional[List[RichResult]] = Field(description="Rich results data")

# Schema for SERP analysis
class SERPAnalysis(BaseModel):
    keyword: str = Field(description="Target keyword")
    results: List[SearchResult] = Field(description="Search results")
    total_results: int = Field(description="Total number of results")
    ads_count: Optional[int] = Field(description="Number of ads")
    rich_results_count: Optional[int] = Field(description="Number of rich results")
    analysis_date: str = Field(description="Analysis timestamp")
    device: str = Field(description="Device type (mobile/desktop)")
    location: Optional[str] = Field(description="Search location")

client = Client()

# Track SERP positions for keywords
target_keywords = [
    "your target keyword",
    "another keyword"
]

for keyword in target_keywords:
    # Analyze SERP data
    response = client.extract(
        url=f"https://www.google.com/search?q={keyword}",
        prompt="Extract detailed search results including positions, titles, descriptions, and all rich results. Also analyze ad presence and total result counts.",
        output_schema=SERPAnalysis
    )
    
    # Process SERP data
    print(f"\nKeyword Analysis: {response.keyword}")
    print(f"Date: {response.analysis_date}")
    print(f"Device: {response.device}")
    if response.location:
        print(f"Location: {response.location}")
    print(f"Total Results: {response.total_results:,}")
    if response.ads_count:
        print(f"Ads: {response.ads_count}")
    if response.rich_results_count:
        print(f"Rich Results: {response.rich_results_count}")
    
    print("\nSearch Results:")
    for result in response.results:
        print(f"\nPosition: {result.position}")
        print(f"Title: {result.title}")
        print(f"URL: {result.url}")
        print(f"Description: {result.description}")
        
        if result.featured_snippet:
            print("Featured Snippet: Yes")
        
        if result.rich_results:
            print("\nRich Results:")
            for rich in result.rich_results:
                print(f"- Type: {rich.type}")
                print(f"  Position: {rich.position}")
        
        if result.sitelinks:
            print("\nSitelinks:")
            for link in result.sitelinks:
                print(f"- {link['title']}: {link['url']}")

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

# Schema for heading data
class HeadingData(BaseModel):
    text: str = Field(description="Heading text")
    level: int = Field(description="Heading level (1-6)")
    word_count: int = Field(description="Words in heading")

# Schema for meta data
class MetaData(BaseModel):
    title: str = Field(description="Meta title")
    description: str = Field(description="Meta description")
    robots: Optional[str] = Field(description="Robots meta tag")
    canonical: Optional[str] = Field(description="Canonical URL")
    og_tags: Optional[Dict[str, str]] = Field(description="OpenGraph tags")
    twitter_tags: Optional[Dict[str, str]] = Field(description="Twitter card tags")

# Schema for content metrics
class ContentMetrics(BaseModel):
    url: str = Field(description="Page URL")
    title: str = Field(description="Page title")
    meta_data: MetaData = Field(description="Meta tag information")
    word_count: int = Field(description="Content word count")
    headings: List[HeadingData] = Field(description="Page headings structure")
    keywords: List[str] = Field(description="Target keywords")
    images: List[Dict[str, str]] = Field(description="Image data including alt text")
    internal_links: List[str] = Field(description="Internal link URLs")
    external_links: List[str] = Field(description="External link URLs")
    social_shares: Optional[Dict[str, int]] = Field(description="Social share counts")
    schema_markup: Optional[List[Dict]] = Field(description="Structured data markup")
    content_score: Optional[float] = Field(description="Content quality score (0-100)")

client = Client()

# Analyze content performance
target_urls = [
    "https://your-site.com/page1",
    "https://your-site.com/page2"
]

for url in target_urls:
    # Extract content metrics
    response = client.extract(
        url=url,
        prompt="Perform comprehensive content analysis including meta tags, headings structure, internal/external links, and structured data. Calculate content quality score based on best practices.",
        output_schema=ContentMetrics
    )
    
    # Generate content insights report
    print(f"\nContent Analysis for: {response.url}")
    print(f"Title: {response.title}")
    print(f"Content Score: {response.content_score:.1f}/100" if response.content_score else "Score: N/A")
    
    print("\nMeta Information:")
    print(f"Title Tag: {response.meta_data.title}")
    print(f"Description: {response.meta_data.description}")
    if response.meta_data.canonical:
        print(f"Canonical: {response.meta_data.canonical}")
    
    print("\nContent Statistics:")
    print(f"Word Count: {response.word_count}")
    print(f"Internal Links: {len(response.internal_links)}")
    print(f"External Links: {len(response.external_links)}")
    print(f"Images: {len(response.images)}")
    
    print("\nHeading Structure:")
    for heading in response.headings:
        print(f"H{heading.level}: {heading.text} ({heading.word_count} words)")
    
    print("\nTarget Keywords:")
    for keyword in response.keywords:
        print(f"- {keyword}")
    
    if response.social_shares:
        print("\nSocial Engagement:")
        for platform, count in response.social_shares.items():
            print(f"{platform}: {count:,}")
    
    if response.schema_markup:
        print("\nStructured Data:")
        for schema in response.schema_markup:
            print(f"- Type: {schema.get('type', 'Unknown')}")
    
    print("\nImage Analysis:")
    missing_alt = sum(1 for img in response.images if not img.get('alt'))
    print(f"Images Missing Alt Text: {missing_alt} of {len(response.images)}")