trends_rss.py

import requests
import xml.etree.ElementTree as ET
from datetime import datetime
from googletrans import Translator
import re

def contains_hebrew(text):
    """Check if the text contains Hebrew characters"""
    hebrew_pattern = re.compile(r'[\u0590-\u05FF\uFB1D-\uFB4F]')
    return bool(hebrew_pattern.search(text))

def contains_russian(text):
    """Check if the text contains Russian characters"""
    russian_pattern = re.compile(r'[\u0400-\u04FF]')
    return bool(russian_pattern.search(text))

def fetch_google_trends():
    # Initialize translator
    translator = Translator()
    
    # URL of the Google Trends RSS feed for Israel
    url = "https://trends.google.com/trends/trendingsearches/daily/rss?geo=IL"
    
    try:
        # Fetch the RSS feed
        response = requests.get(url)
        response.raise_for_status()
        
        # Register the namespace
        ET.register_namespace('ht', 'https://trends.google.com/trends/trendingsearches/daily')
        
        # Parse the XML content
        root = ET.fromstring(response.content)
        
        # Find all item elements
        items = root.findall('./channel/item')
        
        print(f"\nGoogle Trends in Israel - {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
        print("-" * 60)
        
        # Extract and print each trending topic
        for idx, item in enumerate(items, 1):
            title = item.find('title').text
            link = item.find('link').text
            
            # Find news items using the correct namespace
            news_items = item.findall('.//{https://trends.google.com/trends/trendingsearches/daily}news_item')
            
            # Handle Hebrew text
            if contains_hebrew(title):
                translation = translator.translate(title, dest='en')
                print(f"{idx}. {title} (Hebrew)")
                print(f"   Translation: {translation.text}")
            # Handle Russian text
            elif contains_russian(title):
                translation = translator.translate(title, dest='en')
                print(f"{idx}. {title} (Russian)")
                print(f"   Translation: {translation.text}")
            else:
                print(f"{idx}. {title}")
            
            # print(f"   Link: {link}")
            
            # Print news items if available
            if news_items:
                for i, news_item in enumerate(news_items, 1):
                    news_title = news_item.find('.//{https://trends.google.com/trends/trendingsearches/daily}news_item_title')
                    news_source = news_item.find('.//{https://trends.google.com/trends/trendingsearches/daily}news_item_source')
                    news_url = news_item.find('.//{https://trends.google.com/trends/trendingsearches/daily}news_item_url')
                    
                    if news_source is not None:
                        print(f"   News {i} Source: {news_source.text}")
                    if news_url is not None:
                        print(f"   News {i} URL: {news_url.text}")
            print()

    except requests.RequestException as e:
        print(f"Error fetching the RSS feed: {e}")
    except ET.ParseError as e:
        print(f"Error parsing the XML content: {e}")
    except Exception as e:
        print(f"An unexpected error occurred: {e}")
        import traceback
        print(traceback.format_exc())

if __name__ == "__main__":
    fetch_google_trends()