CSV to timestamped Souncloud URLs for Nerdland Podcast

csv_to_html_timestamps.py

# This is a script that takes Audobe Audition CSV file output from a project and combines them with a Souncloud URL to generate a list of clickable topic - timestamp entries
# Jeroen Baert - jeroen [at] nerdland [dot]

from datetime import datetime, timedelta
import csv
import sys

# Import CSV file as a list-of-lists
def import_csv(filename):
	with open(filename) as csv_file:
		csv_reader = csv.reader(csv_file, delimiter='\t')
		csv_list = list(csv_reader)
	return csv_list

# Convert Adobe Audition time strings to list of hour, minute second
def to_timestamp(time):
	# find out if the input contains hours or not by counting the ":"
	if time.count(":") == 2:
		t = datetime.strptime(time, "%H:%M:%S.%f")
	else:
		t = datetime.strptime(time, "%M:%S.%f")
	timestamp = [t.hour, t.minute, t.second]
	return timestamp

# Create soundcloud timestamped url from base url and list with H, M, S
def to_soundcloud_href(url, timestamp):
	timestamp_parameter = "#t=" + f'{timestamp[0]:02d}' + ":" + f'{timestamp[1]:02d}' + ":" + f'{timestamp[2]:02d}'
	link = url + timestamp_parameter
	href = "<a target=\"_blank\" href=\"" + link + "\">" + f'{timestamp[0]:02d}' + ":" + f'{timestamp[1]:02d}' + ":" + f'{timestamp[2]:02d}' + "</a>"
	return href

# Convert list of processed CSV markers to HTML <ul>
def to_html(sc_url, marker_list):
	html_output = ["<ul>"]
	for i in marker_list:
		topic = i[0].strip()
		href = to_soundcloud_href(sc_url,i[1])
		html_output.append("<li>" + topic + " - " + href + "</li>")
	html_output.append("</ul>")
	return html_output
	
def main():
	if (len(sys.argv) != 3):
	   print("ERROR: I need two arguments: <path to csv file> and <base soundcloud URL>")
	   return

	file = sys.argv[1]
	url = sys.argv[2]

	# import CSV output from Adobe Audition
	marker_list = import_csv(file)
	# get rid of first line (columns)
	marker_list = marker_list[1:]
	# only retain first two items per line (item name and timestamp)
	processed_marker_list = []
	for i in marker_list:
		i[1] = to_timestamp(i[1])
		processed_marker_list.append(i[0:2])
	html_list = to_html(url, processed_marker_list)
	for i in html_list:
		print(i)

if __name__ == "__main__":
	main()