utils/wiki_api.py

import requests
import json
from typing import Optional, Dict, Any
import time

class WikiAPI:
    """Wikipedia and Wikidata API client"""
    
    def __init__(self):
        self.wikipedia_base_url = "https://en.wikipedia.org/api/rest_v1"
        self.wikidata_base_url = "https://www.wikidata.org/w/api.php"
        self.session = requests.Session()
        self.session.headers.update({
            'User-Agent': 'TriviaVerse/1.0 (https://github.com/your-repo/triviaverse)'
        })
    
    def fetch_content(self, topic: str, language: str = 'en') -> Optional[str]:
        """Fetch content from Wikipedia"""
        try:
            # First, search for the article
            search_results = self._search_wikipedia(topic, language)
            if not search_results:
                return None
            
            # Get the first result
            page_title = search_results[0]['title']
            
            # Fetch the full content
            content = self._get_wikipedia_content(page_title, language)
            return content
            
        except Exception as e:
            print(f"Error fetching content: {e}")
            return None
    
    def _search_wikipedia(self, query: str, language: str = 'en') -> Optional[list]:
        """Search Wikipedia for articles"""
        
        # Map language codes to Wikipedia domains
        lang_domains = {
            'en': 'en.wikipedia.org',
            'hi': 'hi.wikipedia.org',
            'te': 'te.wikipedia.org',
            'ta': 'ta.wikipedia.org',
            'kn': 'kn.wikipedia.org',
            'bn': 'bn.wikipedia.org'
        }
        
        domain = lang_domains.get(language, 'en.wikipedia.org')
        
        url = f"https://{domain}/api/rest_v1/page/search/{query}"
        
        try:
            response = self.session.get(url, timeout=10)
            response.raise_for_status()
            
            data = response.json()
            return data.get('pages', [])
            
        except Exception as e:
            print(f"Search error: {e}")
            return None
    
    def _get_wikipedia_content(self, page_title: str, language: str = 'en') -> Optional[str]:
        """Get full content of a Wikipedia page"""
        
        # Map language codes to Wikipedia domains
        lang_domains = {
            'en': 'en.wikipedia.org',
            'hi': 'hi.wikipedia.org',
            'te': 'te.wikipedia.org',
            'ta': 'ta.wikipedia.org',
            'kn': 'kn.wikipedia.org',
            'bn': 'bn.wikipedia.org'
        }
        
        domain = lang_domains.get(language, 'en.wikipedia.org')
        
        # Get page summary first
        summary_url = f"https://{domain}/api/rest_v1/page/summary/{page_title}"
        
        try:
            response = self.session.get(summary_url, timeout=10)
            response.raise_for_status()
            
            summary_data = response.json()
            extract = summary_data.get('extract', '')
            
            # Try to get more detailed content
            content_url = f"https://{domain}/w/api.php"
            params = {
                'action': 'query',
                'format': 'json',
                'titles': page_title,
                'prop': 'extracts',
                'exintro': True,
                'explaintext': True,
                'exsectionformat': 'plain'
            }
            
            response = self.session.get(content_url, params=params, timeout=10)
            response.raise_for_status()
            
            data = response.json()
            pages = data.get('query', {}).get('pages', {})
            
            for page_id, page_data in pages.items():
                if 'extract' in page_data:
                    full_extract = page_data['extract']
                    # Return the longer content
                    return full_extract if len(full_extract) > len(extract) else extract
            
            return extract
            
        except Exception as e:
            print(f"Content fetch error: {e}")
            return None
    
    def get_wikidata_info(self, topic: str) -> Optional[Dict[str, Any]]:
        """Get structured data from Wikidata"""
        try:
            # Search for Wikidata entity
            search_url = f"{self.wikidata_base_url}"
            params = {
                'action': 'wbsearchentities',
                'search': topic,
                'language': 'en',
                'format': 'json'
            }
            
            response = self.session.get(search_url, params=params, timeout=10)
            response.raise_for_status()
            
            data = response.json()
            entities = data.get('search', [])
            
            if not entities:
                return None
            
            entity_id = entities[0]['id']
            
            # Get entity data
            entity_url = f"{self.wikidata_base_url}"
            params = {
                'action': 'wbgetentities',
                'ids': entity_id,
                'format': 'json',
                'languages': 'en'
            }
            
            response = self.session.get(entity_url, params=params, timeout=10)
            response.raise_for_status()
            
            data = response.json()
            entity_data = data.get('entities', {}).get(entity_id, {})
            
            return self._process_wikidata_entity(entity_data)
            
        except Exception as e:
            print(f"Wikidata error: {e}")
            return None
    
    def _process_wikidata_entity(self, entity_data: Dict[str, Any]) -> Dict[str, Any]:
        """Process Wikidata entity to extract useful information"""
        
        processed_data = {
            'label': '',
            'description': '',
            'claims': {},
            'aliases': []
        }
        
        # Extract label
        labels = entity_data.get('labels', {})
        if 'en' in labels:
            processed_data['label'] = labels['en']['value']
        
        # Extract description
        descriptions = entity_data.get('descriptions', {})
        if 'en' in descriptions:
            processed_data['description'] = descriptions['en']['value']
        
        # Extract aliases
        aliases = entity_data.get('aliases', {})
        if 'en' in aliases:
            processed_data['aliases'] = [alias['value'] for alias in aliases['en']]
        
        # Extract some important claims
        claims = entity_data.get('claims', {})
        important_properties = [
            'P31',   # instance of
            'P279',  # subclass of
            'P17',   # country
            'P569',  # date of birth
            'P570',  # date of death
            'P571',  # inception
            'P576',  # dissolved
        ]
        
        for prop in important_properties:
            if prop in claims:
                processed_data['claims'][prop] = claims[prop]
        
        return processed_data
    
    def get_related_topics(self, topic: str, limit: int = 5) -> list:
        """Get related topics for additional content"""
        try:
            # This is a simplified implementation
            # In a real app, you might use Wikipedia's "See also" sections
            # or Wikidata relationships
            
            search_results = self._search_wikipedia(topic)
            if not search_results:
                return []
            
            # Return related pages from search results
            related = []
            for result in search_results[1:limit+1]:  # Skip first result (exact match)
                related.append({
                    'title': result['title'],
                    'description': result.get('description', ''),
                    'url': result.get('content_urls', {}).get('desktop', {}).get('page', '')
                })
            
            return related
            
        except Exception as e:
            print(f"Related topics error: {e}")
            return []
    
    def get_random_article(self, language: str = 'en') -> Optional[Dict[str, str]]:
        """Get a random Wikipedia article"""
        
        lang_domains = {
            'en': 'en.wikipedia.org',
            'hi': 'hi.wikipedia.org',
            'te': 'te.wikipedia.org',
            'ta': 'ta.wikipedia.org',
            'kn': 'kn.wikipedia.org',
            'bn': 'bn.wikipedia.org'
        }
        
        domain = lang_domains.get(language, 'en.wikipedia.org')
        
        try:
            url = f"https://{domain}/api/rest_v1/page/random/summary"
            response = self.session.get(url, timeout=10)
            response.raise_for_status()
            
            data = response.json()
            return {
                'title': data.get('title', ''),
                'extract': data.get('extract', ''),
                'url': data.get('content_urls', {}).get('desktop', {}).get('page', '')
            }
            
        except Exception as e:
            print(f"Random article error: {e}")
            return None