theKrew APIthekrew.ai ↗

"""
theKrew.ai Website Content API Client
Get your API key from: https://parse.bot/settings
"""

import os
import requests
from typing import Optional, Dict, Any, List


class ParseClient:
    """Client for theKrew.ai Website Content API"""
    
    def __init__(self, api_key: Optional[str] = None):
        self.base_url = "https://api.parse.bot"
        self.scraper_id = "7e946b30-46d5-44dd-a12b-a1ed3239b09d"
        self.api_key = api_key or os.getenv("PARSE_API_KEY")
        
        if not self.api_key:
            raise ValueError("API key not provided. Set PARSE_API_KEY environment variable or pass it as argument.")
    
    def _call(self, endpoint: str, method: str = "POST", **params) -> Dict[str, Any]:
        """Make API call to Parse bot"""
        url = f"{self.base_url}/scraper/{self.scraper_id}/{endpoint}"
        headers = {
            "X-API-Key": self.api_key,
            "Content-Type": "application/json"
        }
        
        if method == "GET":
            response = requests.get(url, headers=headers, params=params)
        elif method == "POST":
            response = requests.post(url, headers=headers, json=params)
        else:
            raise ValueError(f"Unsupported method: {method}")
        
        response.raise_for_status()
        return response.json()
    
    def list_pages(self) -> Dict[str, Any]:
        """List all pages on thekrew.ai from the sitemap.
        
        Returns:
            Dictionary with total page count and list of page objects containing
            url, path, last_modified, and priority fields.
        """
        return self._call("list_pages", method="GET")
    
    def get_page(self, path: str = "/") -> Dict[str, Any]:
        """Get the full content of a page by its path.
        
        Args:
            path: URL path of the page (e.g., '/pricing/', '/about/').
                  Defaults to homepage.
        
        Returns:
            Dictionary with page metadata (title, description, keywords, og_data,
            structured_data) and full text content.
        """
        return self._call("get_page", method="GET", path=path)
    
    def list_blog_posts(self, category: Optional[str] = None) -> Dict[str, Any]:
        """List all blog posts with metadata.
        
        Args:
            category: Optional filter by category (case-insensitive partial match).
                     Known categories: AI for Business, Growth Strategy, Founder Lessons,
                     Behind the Build, Business Growth, Team Efficiency.
        
        Returns:
            Dictionary with total post count and list of blog post objects containing
            slug, title, category, read_time, excerpt, date, and url.
        """
        params = {}
        if category:
            params["category"] = category
        return self._call("list_blog_posts", method="GET", **params)
    
    def get_blog_post(self, slug: str) -> Dict[str, Any]:
        """Get the full content of a blog post by its slug.
        
        Args:
            slug: Blog post slug from the URL (e.g., 'ai-content-marketing-drives-sales').
        
        Returns:
            Dictionary with blog post metadata (title, description, keywords, read_time,
            article_meta with author and dates) and full text content.
        """
        return self._call("get_blog_post", method="GET", slug=slug)
    
    def list_case_studies(self) -> Dict[str, Any]:
        """List all case studies with titles and subtitles.
        
        Returns:
            Dictionary with total case study count and list of case study objects
            containing slug, title, subtitle, and url.
        """
        return self._call("list_case_studies", method="GET")
    
    def get_faq(self) -> Dict[str, Any]:
        """Get all FAQ content organized by section.
        
        Returns:
            Dictionary with total sections and questions count, plus sections array
            where each section contains section name and questions with answers.
        """
        return self._call("get_faq", method="GET")


def main():
    """Practical workflow example: Research blog posts by category and compile insights"""
    
    # Initialize client
    client = ParseClient()
    
    print("=" * 70)
    print("theKrew.ai Content Analysis - Blog Posts by Category")
    print("=" * 70)
    
    # Step 1: Get all blog posts to understand available categories
    print("\n1. Fetching all blog posts...")
    all_posts_response = client.list_blog_posts()
    total_posts = all_posts_response.get("total", 0)
    all_posts = all_posts_response.get("posts", [])
    print(f"   Found {total_posts} total blog posts")
    
    # Step 2: Extract unique categories
    categories = set()
    for post in all_posts:
        if post.get("category"):
            categories.add(post["category"])
    
    print(f"   Categories found: {', '.join(sorted(categories))}")
    
    # Step 3: Filter and analyze posts from "AI for Business" category
    print("\n2. Analyzing 'AI for Business' category posts...")
    business_posts_response = client.list_blog_posts(category="AI for Business")
    business_posts = business_posts_response.get("posts", [])
    print(f"   Found {len(business_posts)} posts in this category")
    
    # Step 4: Get detailed content for first 2 posts and extract key insights
    print("\n3. Fetching detailed content for sample posts...")
    sample_insights = []
    
    for i, post in enumerate(business_posts[:2]):
        slug = post.get("slug")
        print(f"\n   Post {i+1}: {post.get('title')}")
        print(f"   Date: {post.get('date')} | Read time: {post.get('read_time')}")
        print(f"   Excerpt: {post.get('excerpt', 'N/A')[:100]}...")
        
        # Get full blog post content
        full_post = client.get_blog_post(slug=slug)
        
        # Extract author info
        article_meta = full_post.get("article_meta", {})
        author = article_meta.get("author", "Unknown")
        
        # Get first 150 chars of content for snippet
        content = full_post.get("content", "")
        content_snippet = content[:150].replace('\n', ' ') + "..." if len(content) > 150 else content
        
        insight = {
            "title": post.get("title"),
            "author": author,
            "date": article_meta.get("date_published"),
            "read_time": post.get("read_time"),
            "content_preview": content_snippet
        }
        sample_insights.append(insight)
    
    # Step 5: Get FAQ information for context about the platform
    print("\n4. Fetching FAQ sections...")
    faq_response = client.get_faq()
    total_sections = faq_response.get("total_sections", 0)
    total_questions = faq_response.get("total_questions", 0)
    print(f"   Found {total_sections} FAQ sections with {total_questions} total questions")
    
    # Display first question from each section for overview
    sections = faq_response.get("sections", [])
    for section in sections[:3]:
        section_name = section.get("section", "")
        questions = section.get("questions", [])
        if questions:
            first_q = questions[0].get("question", "")
            print(f"   • {section_name}: {first_q}")
    
    # Step 6: Get homepage content for overall platform understanding
    print("\n5. Fetching homepage content for platform overview...")
    homepage = client.get_page(path="/")
    homepage_title = homepage.get("title", "")
    homepage_desc = homepage.get("description", "")
    print(f"   Title: {homepage_title}")
    print(f"   Description: {homepage_desc[:120]}...")
    
    # Final summary
    print("\n" + "=" * 70)
    print("ANALYSIS SUMMARY")
    print("=" * 70)
    print(f"✓ Blog Posts Analyzed: {len(sample_insights)} detailed articles reviewed")
    print(f"✓ Categories Explored: {', '.join(sorted(categories))}")
    print(f"✓ FAQ Coverage: {total_questions} questions across {total_sections} sections")
    print(f"✓ Platform Pages: {total_posts + 85} total pages available")
    
    print("\nSample Blog Post Authors:")
    for insight in sample_insights:
        print(f"  • {insight['author']} - '{insight['title'][:50]}...'")
    
    print("\n" + "=" * 70)


if __name__ == "__main__":
    main()