multipleidsitesuniquedownload

import requests
import pandas as pd
from datetime import datetime, timedelta

# Function to generate a list of dates between two dates
def generate_dates(start_date, end_date):
    date_list = []
    current_date = start_date
    while current_date <= end_date:
        date_list.append(current_date.strftime('%Y-%m-%d'))
        current_date += timedelta(days=1)
    return date_list

# Function to fetch data from the API with a given date, offset, and idSite
def fetch_data(date, offset, id_site):
    url = f"https://demo.matomo.cloud/index.php?module=API&format=JSON&idSite={id_site}&period=day&date={date}&method=Live.getLastVisitsDetails&expanded=1&token_auth=anonymous&showColumns=actionDetails&filter_limit=10000&filter_offset={offset}"
    response = requests.get(url)
    if response.status_code == 200:
        return response.json()
    else:
        print(f"Failed to fetch data for idSite {id_site}, date {date} with offset {offset}")
        return []

# Main function
def main():
    # User inputs
    start_date_str = input("Enter the starting date (YYYY-MM-DD): ")
    end_date_str = input("Enter the ending date (YYYY-MM-DD): ")
    max_offset = int(input("Enter the maximum number of visits in a day: "))
    id_sites = input("Enter a list of idSite values, separated by commas: ").split(',')

    # Parse dates
    start_date = datetime.strptime(start_date_str, '%Y-%m-%d')
    end_date = datetime.strptime(end_date_str, '%Y-%m-%d')

    # Generate list of dates
    dates = generate_dates(start_date, end_date)

    # Loop through each idSite
    for id_site in id_sites:
        id_site = id_site.strip()
        print(f"Processing data for idSite {id_site}")

        # Initialize a list to store concatenated data
        all_data = []

        # Loop through dates and fetch data with incremental offsets
        for date in dates:
            offset = 0
            while offset <= max_offset:
                data = fetch_data(date, offset, id_site)
                if not data:
                    break
                all_data.extend(data)
                offset += 10000

        # Extract URLs and counts where type is 'download'
        download_count = {}
        unique_download_count = {}

        for visit in all_data:
            # Use a set to track unique downloads per visit
            unique_urls_in_visit = set()
            if 'actionDetails' in visit:
                for action in visit['actionDetails']:
                    if action.get('type') == 'download':
                        url = action.get('url')
                        if url in download_count:
                            download_count[url] += 1
                        else:
                            download_count[url] = 1

                        # Track unique download counts
                        unique_urls_in_visit.add(url)

            # Update unique download counts for this visit
            for url in unique_urls_in_visit:
                if url in unique_download_count:
                    unique_download_count[url] += 1
                else:
                    unique_download_count[url] = 1

        # Create DataFrame including total and unique counts
        data = {
            'URL': [],
            'Unique': [],
            'Total': []
        }

        for url, total_count in download_count.items():
            data['URL'].append(url)
            data['Unique'].append(unique_download_count.get(url, 0))
            data['Total'].append(total_count)

        df = pd.DataFrame(data)
        df = df.sort_values(by='Total', ascending=False)

        # Calculate total count and unique count, insert as first and last row
        total_row = pd.DataFrame([['Total', df['Unique'].sum(), df['Total'].sum()]], columns=['URL', 'Unique', 'Total'])
        df = pd.concat([total_row, df, total_row], ignore_index=True)

        # Save to CSV with a file name specific to the idSite
        output_path = f'download_totals_with_unique_idSite_{id_site}.csv'
        df.to_csv(output_path, index=False)

        print(f"CSV file for idSite {id_site} saved at: {output_path}")

if __name__ == "__main__":
    main()