google_trends.py

import logging
from pytrends.request import TrendReq
import pandas as pd

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

# Initialize pytrends
pytrends = TrendReq(hl='en-US', tz=360)

# Example normalization factors
population = {
    "New York": 8419000,
    "Amsterdam": 821752,
    "Rio de Janeiro": 6748000,
    "Hong Kong": 7507000
}

internet_penetration = {
    "New York": 0.95,
    "Amsterdam": 0.98,
    "Rio de Janeiro": 0.70,
    "Hong Kong": 0.93
}

# Define city information
city_info = {
    "New York": {
        "geo_code": "US-NY",
        "keywords": ["Climate change", "Global warming", "Renewable energy", "Carbon footprint", "Paris Agreement"]
    },
    "Amsterdam": {
        "geo_code": "NL-NH",
        "keywords": ["Klimaatverandering", "Opwarming van de aarde", "Hernieuwbare energie", "Koolstofvoetafdruk", "Klimaatakkoord van Parijs"]
    },
    "Rio de Janeiro": {
        "geo_code": "BR-RJ",
        "keywords": ["Mudança climática", "Aquecimento global", "Energia renovável", "Pegada de carbono", "Acordo de Paris"]
    },
    "Hong Kong": {
        "geo_code": "HK",
        "keywords": ["氣候變化", "全球暖化", "可再生能源", "碳足跡", "巴黎協定"]
    }
}

# Collect and normalize data for each city
for city, info in city_info.items():
    try:
        # Fetch data
        pytrends.build_payload(kw_list=info["keywords"], timeframe="2004-01-01 2024-12-31", geo=info["geo_code"])
        trends_data = pytrends.interest_over_time()

        if not trends_data.empty:
            trends_data = trends_data[info["keywords"]]
            trends_data.reset_index(inplace=True)
            trends_data["City"] = city

            # Normalize data
            for keyword in info["keywords"]:
                trends_data[f"{keyword}_normalized"] = trends_data[keyword] / (population[city] * internet_penetration[city])

            # Save normalized data
            trends_data.to_csv(f"{city.lower().replace(' ', '_')}_trends_normalized.csv", index=False)
            print(f"Normalized data successfully collected for {city}.")
        else:
            print(f"No data available for {city}.")
    except Exception as e:
        print(f"Error collecting data for {city}: {e}")