Description #

Video metadata extraction operator

Key features #

• Supports multiple video file formats
• Extracts complete video metadata information
• Uses the ffprobe tool for metadata extraction
• Supports local files, remote files (TOS/S3), and HTTP/HTTPS links

Extracted information #

• Basic information: duration, format, bitrate
• Video information: resolution, frame rate, encoder
• Audio information: sample rate, number of channels, encoder

Operator parameters #

Input #

Output #

Array of structs containing metadata

Parameters #

If a parameter does not have a default value, it is required

Examples #

The following code demonstrates how to use Daft (in distributed environments) to run the operator and extract metadata information from video files.

from __future__ import annotations

import os

import daft
from daft import col
from daft.las.functions.udf import las_udf
from daft.las.functions.video import VideoExtractMetadata

if __name__ == "__main__":
    TOS_TEST_DIR_URL = os.getenv("TOS_TEST_DIR_URL", "las-cn-beijing-public-online.tos-cn-beijing.volces.com")

    if os.getenv("DAFT_RUNNER", "native") == "ray":
        import logging

        import ray

        def configure_logging():
            logging.basicConfig(
                level=logging.INFO,
                format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
                datefmt="%Y-%m-%d %H:%M:%S",
            )
            logging.getLogger("tracing.span").setLevel(logging.WARNING)
            logging.getLogger("daft_io.stats").setLevel(logging.WARNING)
            logging.getLogger("DaftStatisticsManager").setLevel(logging.WARNING)
            logging.getLogger("DaftFlotillaScheduler").setLevel(logging.WARNING)
            logging.getLogger("DaftFlotillaDispatcher").setLevel(logging.WARNING)

        ray.init(dashboard_host="0.0.0.0", runtime_env={"worker_process_setup_hook": configure_logging})
        daft.set_runner_ray()

    daft.set_execution_config(actor_udf_ready_timeout=600)
    daft.set_execution_config(min_cpu_per_task=0)

    samples = {
        "input_path": [
            f"https://{TOS_TEST_DIR_URL}/public/archive/video_extract_metadata/music_sample.mp4",
        ],
    }
    ds = daft.from_pydict(samples)

    # Using Daft to extract video metadata
    constructor_kwargs = {
        "timeout": 600,
    }

    ds = ds.with_column(
        "metadata",
        las_udf(
            VideoExtractMetadata,
            construct_args=constructor_kwargs,
            num_cpus=1,
            concurrency=1,
            batch_size=1,
        )(col("input_path")),
    )

    ds.show()
    # ╭────────────────────────────────┬─────────────────────────────────────────────────────╮
    # │ input_path                     ┆ metadata                                            │
    # │ ---                            ┆ ---                                                 │
    # │ Utf8                           ┆ Struct                                              │
    # ╞════════════════════════════════╪═════════════════════════════════════════════════════╡
    # │ https://las-public-data-qa.to… ┆ {duration: 7.367, format_name: "mov,mp4,m4a,3gp... │
    # ╰────────────────────────────────┴─────────────────────────────────────────────────────╯