get_yt_video_durations.py

#!/bin/python3

import json
import requests
import isodate

def extract_data(json_data):
    """Extract id, title and duration"""
    id = json_data["id"]
    title = json_data["snippet"]["title"]
    description = json_data["snippet"]["description"][0:120]
    publishedAt = json_data["snippet"]["publishedAt"]
    duration_iso = json_data["contentDetails"]["duration"]
    
    # convert stuff like "PT3M14S" to 03:14 - crashes for videos longer than an hour...
    duration_numbers = duration_iso[2:-1].split("M")
    duration = isodate.parse_duration(duration_iso)
    
    return {
        "videoId": id, "title": title, "description": description, "publishedAt": publishedAt, "duration": str(duration)
    }

def get_data(video_ids):
    url = f"https://www.googleapis.com/youtube/v3/videos?part=snippet,contentDetails&id={','.join(video_ids)}&key={api_key}"
    print(str(url))
    response = requests.get(url)

    data = json.loads(response.text)

    # format and show entire response including all the irrelevant stuff
    #print(str(json.dumps(data, indent=2)))

    return list(map(extract_data, data["items"]))

api_key = "your-api-key"

ids_file = open('video_ids.txt', 'r')
video_id_lines = ids_file.readlines()
video_ids = list(map(str.strip, video_id_lines))

video_data = ""

for i in range(0, len(video_ids), 50):
    next_fifty_ids = video_ids[i:i + 50]
    video_data += (json.dumps(get_data(next_fifty_ids), indent=2))

output_file = open("video_data.json", "w")
output_file.write(video_data)
output_file.close()