{
  "info": {
    "schema_version": "1.1",
    "dataset": "Extreme",
    "description": "Exported from Extreme at Visual Layer",
    "dataset_url": "http://app.visual-layer.com/dataset/42e3b7ae-dd5e-11ef-9fca-1a226f3de670/data",
    "export_time": "2025-02-15T18:23:34.164184",
    "dataset_creation_time": "2025-01-24T18:35:57.719308",
    "exported_by": "Danny Bickson",
    "total_media_items": 56
  },
  "media_items": [
    {
      "media_id": "8621054d-1d23-4ca7-a7ca-65feb2c83eb1",
      "media_type": "video_frame",
      "file_name": "output_000001.jpg",
      "file_path": "7370082532203988000_7450129782785756438_2024-12-19_14:28:36.mp4/output_000001.jpg",
      "file_size": "48.27KB",
      "uniqueness_score": 0.4989460029187489,
      "height": 720,
      "width": 576,
      "url": "http://app.visual-layer.com/dataset/42e3b7ae-dd5e-11ef-9fca-1a226f3de670/data/image/8621054d-1d23-4ca7-a7ca-65feb2c83eb1",
      "cluster_id": "49997382-b7c3-4c83-83a3-fa4e0a586f2b",
      "metadata_items": [
        {
          "type": "video_info",
          "properties": {
            "video_name": "7370082532203988000_7450129782785756438_2024-12-19_14:28:36.mp4",
            "frame_timestamp": 0.0
          }
        },
        {
          "type": "issue",
          "properties": {
            "issue_type": "duplicates",
            "confidence": 0.977624,
            "duplicate_group_id": "35395121-5cb1-4a92-906f-dd4cb9ff62d3",
            "duplicate_threshold": 0.96
          }
        }
        // ...
      ]
    },
    {
      "media_id": "09848999-125f-4be9-8850-82dc16d23459",
      "media_type": "video_frame",
      "file_name": "output_000001.jpg",
      "file_path": "7370082532203988000_7461337604009495810_2025-01-18_19:20:39.mp4/output_000001.jpg",
      "file_size": "48.11KB",
      "uniqueness_score": 0.021566401816095697,
      "height": 720,
      "width": 576,
      "url": "http://app.visual-layer.com/dataset/42e3b7ae-dd5e-11ef-9fca-1a226f3de670/data/image/09848999-125f-4be9-8850-82dc16d23459",
      "cluster_id": "49997382-b7c3-4c83-83a3-fa4e0a586f2b",
      "metadata_items": [
        {
          "type": "video_info",
          "properties": {
            "video_name": "7370082532203988000_7461337604009495810_2025-01-18_19:20:39.mp4",
            "frame_timestamp": 0.0
          }
        },
        {
          "type": "issue",
          "properties": {
            "issue_type": "duplicates",
            "confidence": 0.977624,
            "duplicate_group_id": "35395121-5cb1-4a92-906f-dd4cb9ff62d3",
            "duplicate_threshold": 0.96
          }
        }
        // ...
      ]
    }
    // ...
  ]
}

import json  
import pandas as pd  
import re

## Load JSON file

with open("metadata 8.json", "r") as f:  
    data = json.load(f)

## Prepare list for DataFrame

records = []

## Iterate over media items

for item in data.get("media_items", []):  
    video_name = None  
    frame_timestamp = None  
    categories = []  
    file_name = item.get("file_name", "")

	for metadata in item.get("metadata_items", []):
	    if metadata["type"] == "video_info":
 	        video_name = metadata["properties"].get("video_name")
 	        frame_timestamp = metadata["properties"].get("frame_timestamp")
 	    elif metadata["type"] == "image_label":
    	    categories.append(metadata["properties"].get("category_name"))

	# Extract frame number from file name
	match = re.search(r'output_(\d+).jpg', file_name)
	frame_number = int(match.group(1)) if match else None

	# Append record with categories as a list
	records.append({
	    "video_name": video_name,
	    "file_name": file_name,
	    "frame_number": frame_number,
	    "time_in_video": frame_timestamp,
	    "categories": categories
	})

## Convert to DataFrame

df = pd.DataFrame(records)  
print(df.tail())