import requests
from bs4 import BeautifulSoup
import streamlit as st

def get_github_data(url: str):
    """Fetches user profile and all public repo data from a GitHub URL."""
    if not url or "github.com" not in url:
        return None
    try:
        # Get profile info from main page
        response = requests.get(url)
        response.raise_for_status()
        soup = BeautifulSoup(response.content, "html.parser")
        
        profile_name_el = soup.find("span", class_="p-name")
        profile_name = profile_name_el.get_text(strip=True) if profile_name_el else ""
        
        profile_bio_el = soup.find("div", class_="p-note")
        profile_bio = profile_bio_el.get_text(strip=True) if profile_bio_el else ""
        
        # Get all repositories from the repositories tab
        repos_url = f"{url}?tab=repositories"
        all_repos = []
        
        while repos_url:
            print(f"Scraping: {repos_url}")
            repos_response = requests.get(repos_url)
            repos_response.raise_for_status()
            repos_soup = BeautifulSoup(repos_response.content, "html.parser")
            
            repo_list = repos_soup.find("ul", {"id": "user-repositories-list"})
            if repo_list:
                for repo_item in repo_list.find_all("li"):
                    repo_name_el = repo_item.find("a", itemprop="name codeRepository")
                    repo_name = repo_name_el.get_text(strip=True) if repo_name_el else "Unnamed Repo"
                    
                    repo_desc_el = repo_item.find("p", itemprop="description")
                    repo_desc = repo_desc_el.get_text(strip=True) if repo_desc_el else "No description."
                    
                    all_repos.append(f"Repo: {repo_name}\nDescription: {repo_desc}")

            # Check for next page
            next_button = repos_soup.find("a", class_="next_page")
            if next_button and next_button.get('href'):
                repos_url = f"https://github.com{next_button.get('href')}"
            else:
                repos_url = None

        return {
            "name": profile_name,
            "bio": profile_bio,
            "repositories": "\n\n".join(all_repos)
        }
    except Exception as e:
        st.error(f"Failed to fetch GitHub data: {e}")
        return None