learning-python/src/LoadXMLFile.py at main · fjay-dev/learning-python · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
# Not needed unless running locally
# !wget https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-PY0101EN-SkillsNetwork/labs/Module%205/data/Sample-employee-XML-file.xml

import xml.etree.ElementTree as etree
import pandas as pd

filename = "https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-PY0101EN-SkillsNetwork/labs/Module%205/data/Sample-employee-XML-file.xml"

async def download(url, filename):
    response = await pyfetch(url)
    if response.status == 200:
        with open(filename, "wb") as f:
            f.write(await response.bytes())

await download(filename, "Sample-employee-XML-file.xml")


tree = etree.parse("Sample-employee-XML-file.xml")

root = tree.getroot()
columns = ["firstname", "lastname", "title", "division", "building","room"]

datatframe = pd.DataFrame(columns = columns)

for node in root:

    firstname = node.find("firstname").text

    lastname = node.find("lastname").text

    title = node.find("title").text

    division = node.find("division").text

    building = node.find("building").text

    room = node.find("room").text

    datatframe = pd.concat([datatframe, pd.Series([firstname, lastname, title, division, building, room], index = columns)], ignore_index = True)

    df=pd.read_xml("Sample-employee-XML-file.xml", xpath="/employees/details")

    datatframe.to_csv("employee.csv", index=False)