Basic processing xlsx into a xml with fixed column names and many supositions about filwriting.

requirements.txt

@@ -0,0 +1,2 @@
+pandas
+openpyxl

src/__main__.py

@@ -0,0 +1,97 @@
+import os
+import zipfile
+import numpy as np
+import pandas as pd
+from pathlib import Path
+import xml.etree.ElementTree as xmltree
+from xml.dom import minidom
+
+
+def load_kmz(kmz_file_path):
+    print(Path(kmz_file_path).resolve())
+    print(Path(kmz_file_path).resolve().exists())
+    file_to_extract = 'doc.kml'
+    xml = None
+    try:
+        with zipfile.ZipFile(kmz_file_path) as z:
+            xml = xmltree.fromstring(z.read(file_to_extract))
+    except:
+        print("Invalid file")
+    return xml
+
+
+def load_xlsx(xlsx_file_path):
+    df = pd.read_excel(xlsx_file_path)
+    return df.to_dict('records')
+
+
+def remove_all_current_placemarkers(xml):
+    doc_elements = xml.find('{http://www.opengis.net/kml/2.2}Document')
+    for stuff in doc_elements.findall('{http://www.opengis.net/kml/2.2}Placemark'):
+        doc_elements.remove(stuff)
+    return xml
+
+
+def append_placemarks_to_xml(xml, placemarks):
+    doc = xml.find('{http://www.opengis.net/kml/2.2}Document')
+    for placemark in placemarks:
+        doc.append(placemark)
+    return xml
+
+
+def map_dit(dict_list):
+    items = list()
+    name_columns = ['Price',  'Includes Bills']
+    description_columns = ['Url', 'Min Satay', 'Notes']
+    location_column = 'Location'
+    for item in dict_list:
+        name = ' '.join([str(item[x]) for x in name_columns])
+        description = '\n'.join([str(item[x]) for x in description_columns if item[x] is not np.nan])
+        location = parse_location(item[location_column])
+        items.append(dict(name=name, description=description, location=location))
+    return items
+
+
+def parse_location(text_location):
+    location_coordinates = text_location.replace(' ', '').split(',')
+    location_coordinates = [location_coordinates[1] , location_coordinates[0]]
+    location_coordinates.append('0')
+    location = ','.join(location_coordinates)
+    return location
+
+
+def map_dict_element_to_placemark_xml(element: dict):
+    xml_element = xmltree.Element('{http://www.opengis.net/kml/2.2}Placemark')
+    xml_name = xmltree.SubElement(xml_element, '{http://www.opengis.net/kml/2.2}name')
+    xml_name.text = element['name']
+    xml_description = xmltree.SubElement(xml_element, '{http://www.opengis.net/kml/2.2}description')
+    xml_description.text = element['description']
+    xml_style_url = xmltree.SubElement(xml_element, '{http://www.opengis.net/kml/2.2}styleUrl')
+    xml_style_url.text = '#icon-1603-E65100'
+    xml_point = xmltree.SubElement(xml_element, '{http://www.opengis.net/kml/2.2}Point')
+    xml_coordinates = xmltree.SubElement(xml_point, '{http://www.opengis.net/kml/2.2}coordinates')
+    xml_coordinates.text = element['location']
+    return xml_element
+
+
+def main():
+    dict_elements = map_dit(load_xlsx('data/housing.xlsx'))
+    placemarks = [map_dict_element_to_placemark_xml(dict_element) for dict_element in dict_elements]
+
+    kmz_xml = load_kmz('data/Acoomodations.kmz')
+    kmz_xml = remove_all_current_placemarkers(kmz_xml)
+    kmz_xml = append_placemarks_to_xml(kmz_xml, placemarks)
+
+    xmltree.register_namespace("", 'http://www.opengis.net/kml/2.2') 
+    tree = xmltree.ElementTree(kmz_xml)
+
+    with open ('testoutput.kml', "w") as file:
+        rough_string = xmltree.tostring(kmz_xml, 'utf-8')
+        reparsed = minidom.parseString(rough_string)
+        content = reparsed.toprettyxml(indent="\t")
+        file.write(content)
+
+
+
+if __name__ == '__main__':
+    main()