a python parser for `mediainfo` output

mediainfo_xml_parse.py

import json
import subprocess
from xml.etree import ElementTree
import boto3
from . import settings

S3 = boto3.client(
    's3',
    endpoint_url=settings.AWS_SERVICE_ENDPOINTS['s3'],
)
DEFAULT_EXPIRESIN_SECONDS = 300


def get_presigned_url(bucket, key, expires_in_seconds: int = DEFAULT_EXPIRESIN_SECONDS) -> str:
    """
    Generate a pre-signed URL
    """
    presigned_url = S3.generate_presigned_url(
        'get_object',
        Params={'Bucket': bucket, 'Key': key},
        ExpiresIn=expires_in_seconds
    )
    return presigned_url


def _convert_xml_to_dict(xmldata: str) -> dict:
    def parse_xml_to_dict(xml) -> dict:
        children = []
        for child in xml:
            response = {}
            key = child.tag.strip()
            # remove namespace
            key = key.split('}', 1)[-1]
            if len(list(child)) > 0:
                response[key] = {}
                response[key]['attrib'] = child.attrib
                values = parse_xml_to_dict(child)
                response[key]['values'] = values
            else:
                response[key] = child.text or ''
            children.append(response)
        return children
    xml = ElementTree.fromstring(xmldata)
    parsed = parse_xml_to_dict(xml)
    return parsed


def get_mediainfo_from_url(url: str) -> dict:
    output = subprocess.check_output(["./mediainfo", "--full", "--output=XML", url])
    return json.loads(output)