Script to convert ArtsEdge XML data to CSV

gistfile1.py

import csv
from lxml import etree


FIELDS = (
    "Ages",
    "Assessments",
    "Audiences",
    "CreatedDate",
    "Description",
    "Duration",
    "Grades",
    "Groupings",
    "Keywords",
    "Languages",
    "Partner",
    "PhysicalSpaces",
    "RelatedURLs",
    "RequiredTechnologies",
    "ResourceTypes",
    "Subjects",
    "TeachingMethods",
    "Title",
    "URL",
    "WorldRegions",
)


def run():
    xml_file = open("ArtsEdgeData20120625.xml")
    xml = xml_file.read()
    xml_file.close()
    root = etree.XML(xml)
    data = []
    for record in root:
        record_data = dict()
        for field in record:
            if field.tag == "Ages":
                record_data["Ages"] = []
                for lookup in field:
                    for value in lookup:
                        record_data["Ages"].append(value.text)
            elif field.tag == "Assessments":
                record_data["Assessments"] = []
                for lookup in field:
                    for value in lookup:
                        record_data["Assessments"].append(value.text)
            elif field.tag == "Audiences":
                record_data["Audiences"] = []
                for lookup in field:
                    for value in lookup:
                        record_data["Audiences"].append(value.text)
            elif field.tag == "CreatedDate":
                record_data["CreatedDate"] = field.text
            elif field.tag == "Description":
                record_data["Description"] = field.text
            elif field.tag == "Duration":
                record_data["Duration"] = field.text
            elif field.tag == "Grades":
                record_data["Grades"] = []
                for lookup in field:
                    for value in lookup:
                        record_data["Grades"].append(value.text)
            elif field.tag == "Groupings":
                record_data["Groupings"] = []
                for lookup in field:
                    for value in lookup:
                        record_data["Groupings"].append(value.text)
            elif field.tag == "Keywords":
                record_data["Keywords"] = []
                for lookup in field:
                    for value in lookup:
                        record_data["Keywords"].append(value.text)
            elif field.tag == "Languages":
                record_data["Languages"] = []
                for lookup in field:
                    for value in lookup:
                        record_data["Languages"].append(value.text)
            elif field.tag == "Partner":
                for tag in field:
                    if tag.tag == "Value":
                        record_data["Partner"] = tag.text
            elif field.tag == "PhysicalSpaces":
                record_data["PhysicalSpaces"] = []
                for lookup in field:
                    for value in lookup:
                        record_data["PhysicalSpaces"].append(value.text)
            elif field.tag == "RelatedURLs":
                record_data["RelatedURLs"] = []
                for related_url in field:
                    for url in related_url:
                        record_data["RelatedURLs"].append(url.text)
            elif field.tag == "RequiredTechnologies":
                record_data["RequiredTechnologies"] = []
                for lookup in field:
                    for value in lookup:
                        record_data["RequiredTechnologies"].append(value.text)
            elif field.tag == "ResourceTypes":
                record_data["ResourceTypes"] = []
                for lookup in field:
                    for value in lookup:
                        record_data["ResourceTypes"].append(value.text)
            elif field.tag == "TeachingMethods":
                record_data["TeachingMethods"] = []
                for subject in field:
                    for name in subject:
                        record_data["TeachingMethods"].append(name.text)
            elif field.tag == "ResourceTypes":
                record_data["ResourceTypes"] = []
                for lookup in field:
                    for value in lookup:
                        record_data["ResourceTypes"].append(value.text)
            elif field.tag == "Title":
                record_data["Title"] = field.text
            elif field.tag == "URL":
                record_data["URL"] = field.text
            elif field.tag == "WorldRegions":
                record_data["WorldRegions"] = []
                for lookup in field:
                    for value in lookup:
                        record_data["WorldRegions"].append(value.text)

        data.append(record_data)

    writer = csv.writer(open("ArtsEdgeData20120625.csv", "w+"))

    writer.writerow(FIELDS)

    for record in data:
        row = []
        for field in FIELDS:
            value = record.get(field) or u""
            if isinstance(value, list):
                value = u"|".join(value)
            value = value.encode("utf-8")
            row.append(value)
        writer.writerow(row)