Parsing XMLs with XPath and ElementTree XML API

parseXML.py

"""
The ElementTree documentation shows how to parse XML using XPath:
https://docs.python.org/3.4/library/xml.etree.elementtree.html#example
"""

import xml.etree.ElementTree as ET

root = ET.fromstring(countrydata)

# Top-level elements
root.findall(".")

# All 'neighbor' grand-children of 'country' children of the top-level elements
root.findall("./country/neighbor")

# Nodes with name='Singapore' that have a 'year' child
root.findall(".//year/..[@name='Singapore']")

# 'year' nodes that are children of nodes with name='Singapore'
root.findall(".//*[@name='Singapore']/year")

# All 'neighbor' nodes that are the second child of their parent
root.findall(".//neighbor[2]")

"""
Knowing this, I wrote a funtion to parse XMLs, 
and had the script iterate over XMLs in a directory:
"""

from lxml import etree
import csv
import os 

# open csv, create writer, then write headers
f1 = open('1.csv', 'w', encoding='utf8', newline='')
wf1 = csv.writer(f1, delimiter=',')
wf1.writerow(['Status', 'AantalInwoners']) # headers

# function to parse xml
def parse(text):
    tree = etree.fromstring(text) 
    try: # using .strip() 'cause its string
        Status = tree.xpath('//Status/text()')[0].strip() 
    except:
        Status = ''
    try: # no .strip() since its an integer
        AantalInwoners = tree.xpath("//AantalInwoners/text()")[0]
    except:
        AantalInwoners = ''
    # write data to csv
    wf1.writerow([Status, AantalInwoners,])
  
# loop over files in directory 'xmls'
for name in os.listdir('xmls'):
    q = open('xmls/{}'.format(name), 'rb')
    text = q.read()
    q.close()
    try:
        parse(text)
    except Exception as ex: # exception? print filename
        print(name, ':', ex)