Created
January 7, 2018 15:44
-
-
Save rsirres/f600e1bd698a7c80693f61bd278e7340 to your computer and use it in GitHub Desktop.
Python3 Script (without dependencies) to parse XML File incrementally and transform it to key-value pairs
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?xml version="1.0"?> | |
<data> | |
<country name="Liechtenstein"> | |
<rank>1</rank> | |
<year>2008</year> | |
<gdppc>141100</gdppc> | |
<neighbor name="Austria" direction="E"/> | |
<neighbor name="Switzerland" direction="W"/> | |
</country> | |
<country name="Singapore"> | |
<rank>4</rank> | |
<year>2011</year> | |
<gdppc>59900</gdppc> | |
<neighbor name="Malaysia" direction="N"/> | |
</country> | |
<country name="Panama"> | |
<rank>68</rank> | |
<year>2011</year> | |
<gdppc>13600</gdppc> | |
<neighbor name="Costa Rica" direction="W"/> | |
<neighbor name="Colombia" direction="E"/> | |
</country> | |
</data> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import xml.etree.ElementTree as ET | |
from collections import defaultdict | |
# Path to XML file | |
file_path = "/Users/Raphael/Downloads/sample4.xml" | |
# Result Container | |
result = defaultdict(list) | |
# XMl Namespaces Mapping the Fully Qualified Namespace to its prefix | |
# h -> http://www.w3.org/HTML/1998/html4 | |
namespaces = {} | |
# Path to current processed xml element | |
xml_path = [] | |
# Flag | |
remove_namespaces = True | |
### Helper | |
def remove_namespace(tag): | |
if "}" in tag: | |
tag = tag.split("}")[1] | |
return tag | |
def shorten_namespace(tag): | |
for k, v in namespaces.items(): | |
pass | |
for event, elem in ET.iterparse(file_path, events=("start-ns", "start", "end")): | |
if event == 'start': | |
tag = elem.tag | |
if remove_namespaces: | |
tag = remove_namespace(elem.tag) | |
xml_path.append(tag) | |
elif event == 'end': | |
# process the tag | |
if elem.text and elem.text.strip(): | |
key = ".".join(xml_path) | |
result[key].append(elem.text) | |
if elem.attrib: | |
prefix = ".".join(xml_path) | |
for attribute, value in elem.attrib.items(): | |
key = prefix + ".@" + attribute | |
result[key].append(value) | |
xml_path.pop() | |
elem.clear() | |
elif event == "start-ns": | |
namespaces[ "{" + elem[1] + "}"] = elem[0] | |
for k, v in namespaces.items(): | |
print(k, " ", v) | |
for k, v in result.items(): | |
print(k, " ", v) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment