FB Spam Remover

import facebook
import time
import logging
import nltk
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
import string
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline

# Set up logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

# Set up the Facebook Graph API
graph = facebook.GraphAPI(access_token='YOUR_ACCESS_TOKEN', version='YOUR_API_VERSION')

# Example post ID
post_id = 'POST_ID'

# Download NLTK resources
nltk.download('punkt')
nltk.download('stopwords')
nltk.download('wordnet')

# Initialize NLTK components
lemmatizer = WordNetLemmatizer()
stop_words = set(stopwords.words('english'))

# Initialize the TF-IDF vectorizer
vectorizer = TfidfVectorizer(tokenizer=word_tokenize, stop_words=stop_words)

# Initialize the logistic regression model
model = LogisticRegression()

# Create a pipeline
pipeline = Pipeline([
    ('vectorizer', vectorizer),
    ('model', model)
])

def fetch_comments(post_id):
    try:
        # Fetch comments
        comments = graph.get_object(id=post_id, fields='comments')['comments']['data']
        return comments
    except facebook.GraphAPIError as e:
        logging.error(f"Error fetching comments: {e}")
        return []

def preprocess_text(text):
    # Tokenize text
    tokens = word_tokenize(text.lower())
    # Remove punctuation and stop words, and lemmatize tokens
    cleaned_tokens = [lemmatizer.lemmatize(token) for token in tokens if token not in string.punctuation and token not in stop_words]
    return ' '.join(cleaned_tokens)

def is_spam(comment):
    preprocessed_text = preprocess_text(comment['message'])
    # Use the trained model to predict if the comment is spam
    prediction = pipeline.predict([preprocessed_text])[0]
    return prediction == 1

def remove_spam(comments):
    for comment in comments:
        if is_spam(comment):
            try:
                graph.delete_object(id=comment['id'])
                logging.info(f"Removed spam comment: {comment['message']}")
            except facebook.GraphAPIError as e:
                logging.error(f"Error removing comment: {e}")

while True:
    comments = fetch_comments(post_id)
    remove_spam(comments)
    time.sleep(60)  # Check every minute (adjust as needed)