extract.py

import json
import csv

project_folder = "airflow_extractions/BTRIS_CB_Color_Coding_08192025_100349/"

path_to_action_steps = f"{project_folder}action_steps.json"

with open(path_to_action_steps, "r") as f:
    data = json.load(f)

with open("lineage_steps.csv", "w", newline="") as csvfile:
    writer = csv.writer(csvfile)
    writer.writerow(["step_number", "script_path", "input_files", "output_files", "project_folder"])

    for step_number, step_data in data["steps"].items():
        script_path = project_folder + step_data.get("script_path", "")
        input_files = [project_folder + file for file in step_data.get("input_files", [])]
        input_files = " ".join(input_files)
        output_files = [project_folder + file for file in step_data.get("output_files", [])]
        output_files = " ".join(output_files)

        writer.writerow([step_number, script_path, input_files, output_files, project_folder])

Update project folder (keep the trailing slash). Run the code, then copy and paste lineage_steps.csv to https://docs.google.com/spreadsheets/d/1_fJxmG1MR0gOXZ56YleeHGfHzroF6cAlQCeEDCs_5_w/edit?gid=131833823#gid=131833823 (Duplicate the first sheet, select A1, paste, then select "Split text to columns").