Sample: Get pages with most sessions from GA4 with Python and Google Analytics Data API v1

sample-ga-data-api.py

"""A sample to get sessions with Python and Google Analytics Data API v1.

with: google-analytics-data = "^0.16.0"
"""
from pathlib import Path

from google.analytics.data_v1beta import BetaAnalyticsDataClient
from google.analytics.data_v1beta.types import (
    DateRange,
    Dimension,
    Metric,
    RunReportRequest,
    OrderBy,
)

# Changes these values:
CREDENTIALS_PATH = Path(__file__).resolve().parent / "credentials.json"
PROPERTY_ID = "XXX"
MAX_ROWS = 20


def main():
    client = BetaAnalyticsDataClient.from_service_account_file(CREDENTIALS_PATH)

    request = build_report_request(PROPERTY_ID, MAX_ROWS)
    response = client.run_report(request)

    print("Report result:")
    show_report(response)


def build_report_request(property_id: str, size: int):
    return RunReportRequest(
        property=f"properties/{property_id}",
        dimensions=[Dimension(name="pagePath"), Dimension(name="pageTitle")],
        metrics=[Metric(name="sessions")],
        date_ranges=[DateRange(start_date="30daysAgo", end_date="today")],
        order_bys=[
            OrderBy(metric=OrderBy.MetricOrderBy(metric_name="sessions"), desc=True),
        ],
        limit=size,
    )


def show_report(response):
    dimension_headers = response.dimension_headers
    metric_headers = response.metric_headers
    for row in response.rows:
        dim_map = _map_of_values(dimension_headers, row.dimension_values)
        met_map = _map_of_values(metric_headers, row.metric_values)
        print(dim_map)
        print(met_map)


def _map_of_values(headers, values) -> dict:
    return {k: v for k, v in zip((x.name for x in headers), (x.value for x in values))}


if __name__ == "__main__":
    main()

Prerequisites

• Python 3.11
• google-analytics-data ^0.16.0
• service account key file (put in the same directory as credentials.json)

Usage

Install google-analytics-data

python -m pip install google-analytics-data

Change the following constants in the script:

• PROPERTY_ID
• CREDENTIALS_PATH (if necessary)
• MAX_ROWS

Run the script:

python sample-ga-data-api.py