HH/apps/social/scrapers/facebook.py

"""
Facebook comment scraper using Facebook Graph API.
"""
import logging
import requests
from typing import List, Dict, Any

from .base import BaseScraper


class FacebookScraper(BaseScraper):
    """
    Scraper for Facebook comments using Facebook Graph API.
    Extracts comments from posts.
    """
    
    BASE_URL = "https://graph.facebook.com/v19.0"
    
    def __init__(self, config: Dict[str, Any]):
        """
        Initialize Facebook scraper.
        
        Args:
            config: Dictionary with 'access_token' and optionally 'page_id'
        """
        super().__init__(config)
        self.access_token = config.get('access_token')
        if not self.access_token:
            raise ValueError(
                "Facebook access token is required. "
                "Set FACEBOOK_ACCESS_TOKEN in your .env file."
            )
        
        self.page_id = config.get('page_id')
        if not self.page_id:
            self.logger.warning(
                "Facebook page_id not provided. "
                "Set FACEBOOK_PAGE_ID in your .env file to specify which page to scrape."
            )
        
        self.logger = logging.getLogger(self.__class__.__name__)
    
    def scrape_comments(self, page_id: str = None, **kwargs) -> List[Dict[str, Any]]:
        """
        Scrape comments from all posts on a Facebook page.
        
        Args:
            page_id: Facebook page ID to scrape comments from
            
        Returns:
            List of standardized comment dictionaries
        """
        page_id = page_id or self.page_id
        if not page_id:
            raise ValueError("Facebook page ID is required")
        
        all_comments = []
        
        self.logger.info(f"Starting Facebook comment extraction for page: {page_id}")
        
        # Get all posts from the page
        posts = self._fetch_all_posts(page_id)
        self.logger.info(f"Found {len(posts)} posts to process")
        
        # Get comments for each post
        for post in posts:
            post_id = post['id']
            post_comments = self._fetch_post_comments(post_id, post)
            all_comments.extend(post_comments)
            self.logger.info(f"Fetched {len(post_comments)} comments for post {post_id}")
        
        self.logger.info(f"Completed Facebook scraping. Total comments: {len(all_comments)}")
        return all_comments
    
    def _fetch_all_posts(self, page_id: str) -> List[Dict[str, Any]]:
        """
        Fetch all posts from a Facebook page.
        
        Args:
            page_id: Facebook page ID
            
        Returns:
            List of post dictionaries
        """
        url = f"{self.BASE_URL}/{page_id}/feed"
        params = {
            'access_token': self.access_token,
            'fields': 'id,message,created_time,permalink_url'
        }
        
        all_posts = []
        while url:
            try:
                response = requests.get(url, params=params)
                data = response.json()
                
                if 'error' in data:
                    self.logger.error(f"Facebook API error: {data['error']['message']}")
                    break
                
                all_posts.extend(data.get('data', []))
                
                # Check for next page
                url = data.get('paging', {}).get('next')
                params = {}  # Next URL already contains params
                
            except Exception as e:
                self.logger.error(f"Error fetching posts: {e}")
                break
        
        return all_posts
    
    def _fetch_post_comments(self, post_id: str, post_data: Dict[str, Any]) -> List[Dict[str, Any]]:
        """
        Fetch all comments for a specific Facebook post.
        
        Args:
            post_id: Facebook post ID
            post_data: Post data dictionary
            
        Returns:
            List of standardized comment dictionaries
        """
        url = f"{self.BASE_URL}/{post_id}/comments"
        params = {
            'access_token': self.access_token,
            'fields': 'id,message,from,created_time,like_count'
        }
        
        all_comments = []
        while url:
            try:
                response = requests.get(url, params=params)
                data = response.json()
                
                if 'error' in data:
                    self.logger.error(f"Facebook API error: {data['error']['message']}")
                    break
                
                # Process comments
                for comment_data in data.get('data', []):
                    comment = self._extract_comment(comment_data, post_id, post_data)
                    if comment:
                        all_comments.append(comment)
                
                # Check for next page
                url = data.get('paging', {}).get('next')
                params = {}  # Next URL already contains params
                
            except Exception as e:
                self.logger.error(f"Error fetching comments for post {post_id}: {e}")
                break
        
        return all_comments
    
    def _extract_comment(self, comment_data: Dict[str, Any], post_id: str, post_data: Dict[str, Any]) -> Dict[str, Any]:
        """
        Extract and standardize a Facebook comment.
        
        Args:
            comment_data: Facebook API comment data
            post_id: Post ID
            post_data: Post data dictionary
            
        Returns:
            Standardized comment dictionary
        """
        try:
            from_data = comment_data.get('from', {})
            
            comment = {
                'comment_id': comment_data['id'],
                'comments': comment_data.get('message', ''),
                'author': from_data.get('name', ''),
                'published_at': self._parse_timestamp(comment_data.get('created_time')),
                'like_count': comment_data.get('like_count', 0),
                'reply_count': 0,  # Facebook API doesn't provide reply count easily
                'post_id': post_id,
                'media_url': post_data.get('permalink_url'),
                'raw_data': comment_data
            }
            
            return self._standardize_comment(comment)
            
        except Exception as e:
            self.logger.error(f"Error extracting Facebook comment: {e}")
            return None