Pure python and GDAL metadata extractor

pure_python_and_gdal_metadata_parser.py

from xml.etree import cElementTree as ElementTree
from osgeo import gdal

imgpath = '???????????<put the image path here>????????????'

###############################################
# XML to dict parsing code get from:
# https://stackoverflow.com/questions/2148119/how-to-convert-an-xml-string-to-a-dictionary
class XmlListConfig(list):
    def __init__(self, aList):
        for element in aList:
            if element:
                # treat like dict
                if len(element) == 1 or element[0].tag != element[1].tag:
                    self.append(XmlDictConfig(element))
                # treat like list
                elif element[0].tag == element[1].tag:
                    self.append(XmlListConfig(element))
            elif element.text:
                text = element.text.strip()
                if text:
                    self.append(text)


class XmlDictConfig(dict):
    '''
    Example usage:

    >>> tree = ElementTree.parse('your_file.xml')
    >>> root = tree.getroot()
    >>> xmldict = XmlDictConfig(root)

    Or, if you want to use an XML string:

    >>> root = ElementTree.XML(xml_string)
    >>> xmldict = XmlDictConfig(root)

    And then use xmldict for what it is... a dict.
    '''
    def __init__(self, parent_element):
        if parent_element.items():
            self.update(dict(parent_element.items()))
        for element in parent_element:
            if element:
                # treat like dict - we assume that if the first two tags
                # in a series are different, then they are all different.
                if len(element) == 1 or element[0].tag != element[1].tag:
                    aDict = XmlDictConfig(element)
                # treat like list - we assume that if the first two tags
                # in a series are the same, then the rest are the same.
                else:
                    # here, we put the list in dictionary; the key is the
                    # tag name the list elements all share in common, and
                    # the value is the list itself 
                    aDict = {element[0].tag: XmlListConfig(element)}
                # if the tag has attributes, add those to the dict
                if element.items():
                    aDict.update(dict(element.items()))
                self.update({element.tag: aDict})
            # this assumes that if you've got an attribute in a tag,
            # you won't be having any text. This may or may not be a 
            # good idea -- time will tell. It works for the way we are
            # currently doing XML configuration files...
            elif element.items():
                self.update({element.tag: dict(element.items())})
            # finally, if there are no child tags and no attributes, extract
            # the text
            else:
                self.update({element.tag: element.text})
                
###############################################


gdal.UseExceptions()
dataFrame = gdal.Open(imgpath, gdal.GA_ReadOnly)
domains = dataFrame.GetMetadataDomainList()
exif = dataFrame.GetMetadata()
for key, value in exif.items():
    print("EXIF --", key, ":", value)
    pass
for domain in domains:
    metadata = dataFrame.GetMetadata(domain)
    if isinstance(metadata, dict):
        for key, value in metadata.items():
            print(domain, "--", key, ":", value)
            pass
    if isinstance(metadata, list):
        if domain == 'xml:XMP':
            # parse xml
            root = ElementTree.XML(metadata[0])
            xmldict = XmlDictConfig(root)
            #print(xmldict)
            # skip first two element
            subdict = list(xmldict.values())[0]
            subdict = list(subdict.values())[0]
            
            # parse XMP stuffs
            for key, value in subdict.items():
                print(domain, '--', key, value)