Created
January 21, 2015 14:44
-
-
Save benosteen/822fef58c6c92b120fff to your computer and use it in GitHub Desktop.
Pulling metadata together from id3 tag XML files
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 os | |
from xml.etree import ElementTree as ET | |
import csv | |
OUTPUT = "/path/to/output.csv" | |
PATH = "/path/to/root/folder/that/has/all/the/xmls" | |
HEADERS = ['ALBUM', 'TITLE', 'ARTIST', 'GENRE', 'TRACKNUMBER', 'COMMENTS', 'YEAR', 'id3v2', 'PATH', 'FROM_FILENAME', 'id3v2'] | |
# Assuming UTF-8... | |
ENC = "utf-8" | |
def to_row(path, filename, doc): | |
row = {} | |
for tag in doc.findall("tag"): | |
row[tag.get('name')] = tag.get('value') | |
row['PATH'] = path | |
row['FROM_FILENAME'] = filename | |
for k in row.keys(): | |
if k not in HEADERS: | |
print k | |
return row | |
with open(OUTPUT, "w") as o: | |
spool = csv.DictWriter(o, fieldnames=HEADERS) | |
spool.writeheader() | |
for (root, dir, files) in os.walk(PATH): | |
print("{0} --> {1} files".format(root, str(len(files)))) | |
for filename in [f for f in files if f.endswith("xml")]: | |
try: | |
with open(os.path.join(root, filename), "r") as src: | |
doc = ET.fromstring(src.read().decode(ENC)) | |
row = to_row(root, filename, doc) | |
spool.writerow(row) | |
except Exception as e: | |
print e |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment