import requests
import json
from datetime import datetime, timezone
import pytz
import csv

# Function to convert local time to UTC format with specific time
def convert_to_utc(date_str, time_str, local_tz):
    dt = datetime.strptime(date_str + ' ' + time_str, '%Y-%m-%d %H:%M:%S')
    local_dt = local_tz.localize(dt)
    dt_utc = local_dt.astimezone(timezone.utc)
    return dt_utc.isoformat()

# Replace these variables with your actual values
access_token = 'YOUR-ACCESS-KEY'
base_url = 'https://YOUR-INSTANCE.instructure.com/api/v1'
# print("enter User ID:")
user_id = 'USER-ID-NUMBER' # replace number with "input()" after testing
# print("Enter start date, formatted yyy-mm-dd:")
start_date = '2025-02-18' # replace date with "input()" after testing
# print("Enter end date, formatted yyy-mm-dd:")
end_date = '2025-02-18' # replace date with "input()" after testing
local_tz = pytz.timezone('America/Chicago')

start_date_utc = convert_to_utc(start_date, '00:00:00', local_tz)
end_date_utc = convert_to_utc(end_date, '23:59:59', local_tz)

headers = {
    'Authorization': f'Bearer {access_token}'
}

def get_pageviews(user_id, start_date, end_date):
    url = f'{base_url}/users/{user_id}/page_views'
    params = {
        'start_time': start_date,
        'end_time': end_date,
        'per_page': 100
    }
    pageviews = []
    
    while url:
        try:
            print(f"Request URL: {url}")  # Debug print
            response = requests.get(url, headers=headers, params=params)
            response.raise_for_status()
            data = response.json()
            pageviews.extend(data)
            
            if 'next' in response.links:
                url = response.links['next']['url']
                params = None  # Clear params for subsequent requests
            else:
                url = None
        except requests.exceptions.RequestException as e:
            print(f"An error occurred: {e}")
            break
    
    return pageviews

pageviews = get_pageviews(user_id, start_date_utc, end_date_utc)

# Write the results to a CSV file
with open('pageviews.csv', mode='w', newline='') as file:
    writer = csv.writer(file)
    
    # Write the header
    writer.writerow(['id', 'created_at', 'url', 'context_type', 'asset_type', 'user_agent'])
    
    # Write the data rows
    for pageview in pageviews:
        writer.writerow([
            pageview.get('id'),
            pageview.get('created_at'),
            pageview.get('url'),
            pageview.get('context_type'),
            pageview.get('asset_type'),
            pageview.get('user_agent')
        ])

print("The results have been written to pageviews.csv")