Created
February 27, 2019 14:14
-
-
Save bliiir/ba516b9a574a74728468e9df7f4302ec to your computer and use it in GitHub Desktop.
Native Instrument Traktor Playlist csv converter
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
#!/usr/bin/env python3 | |
# coding: utf-8 | |
import pandas as pd | |
import lxml | |
import html5lib | |
import bs4 | |
# Get filename and path from user | |
print('Filepath and name') | |
print('Example: /Users/rg/Dropbox/00 Privat/Audio/30_playlists_xml_etc/20181210.html') | |
filename = input('please enter here: ') | |
# Extract path, title and extension from filename | |
file_path = filename.split('.')[0] | |
file_extension = filename.split('.')[-1] | |
file_name = file_path.split('/')[-1] | |
# Read html | |
l = pd.read_html(filename, header=0) | |
# Create a list of dataframes from the tables in the html file | |
df = l[0] | |
# Remove duplicates | |
df = df.drop_duplicates(subset='Title') | |
# Subset for export | |
df_export = df[['Title', 'Artist']] | |
# Export to csv | |
df_export.to_csv(f'{file_name}.csv', index=False) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment