mirror of
https://github.com/danielmiessler/fabric
synced 2024-11-10 07:10:31 +00:00
118 lines
4.1 KiB
Python
118 lines
4.1 KiB
Python
#!/usr/bin/env python3
|
|
|
|
import re
|
|
from googleapiclient.discovery import build
|
|
from googleapiclient.errors import HttpError
|
|
from youtube_transcript_api import YouTubeTranscriptApi
|
|
from dotenv import load_dotenv
|
|
import os
|
|
import json
|
|
import isodate
|
|
import argparse
|
|
import sys
|
|
|
|
def get_video_id(url):
|
|
# Extract video ID from URL
|
|
pattern = r'(?:https?:\/\/)?(?:www\.)?(?:youtube\.com\/(?:[^\/\n\s]+\/\S+\/|(?:v|e(?:mbed)?)\/|\S*?[?&]v=)|youtu\.be\/)([a-zA-Z0-9_-]{11})'
|
|
match = re.search(pattern, url)
|
|
return match.group(1) if match else None
|
|
|
|
|
|
def main_function(url, options):
|
|
# Load environment variables from .env file
|
|
load_dotenv(os.path.expanduser('~/.config/fabric/.env'))
|
|
|
|
# Get YouTube API key from environment variable
|
|
api_key = os.getenv('YOUTUBE_API_KEY')
|
|
if not api_key:
|
|
print("Error: YOUTUBE_API_KEY not found in ~/.config/fabric/.env")
|
|
return
|
|
|
|
# Extract video ID from URL
|
|
video_id = get_video_id(url)
|
|
if not video_id:
|
|
print("Invalid YouTube URL")
|
|
return
|
|
|
|
try:
|
|
# Initialize the YouTube API client
|
|
youtube = build('youtube', 'v3', developerKey=api_key)
|
|
|
|
# Get video details
|
|
video_response = youtube.videos().list(
|
|
id=video_id,
|
|
part='contentDetails'
|
|
).execute()
|
|
|
|
# Extract video duration and convert to minutes
|
|
duration_iso = video_response['items'][0]['contentDetails']['duration']
|
|
duration_seconds = isodate.parse_duration(duration_iso).total_seconds()
|
|
duration_minutes = round(duration_seconds / 60)
|
|
|
|
# Get video transcript language
|
|
try:
|
|
transcript_available = False
|
|
transcript_options = ''
|
|
transcript_list = YouTubeTranscriptApi.list_transcripts(video_id)
|
|
for transcript in transcript_list:
|
|
if options.language == transcript.language_code:
|
|
transcript_available = True
|
|
else:
|
|
transcript_options += transcript.language + ' (' + \
|
|
transcript.language_code + '); '
|
|
|
|
if not transcript_available:
|
|
# exit with existing languages, cause get_transcript will fail
|
|
sys.exit('"' + options.language + '" not available. ' + \
|
|
'Following languages exists: ' + transcript_options)
|
|
|
|
except Exception as e:
|
|
print(e)
|
|
|
|
# Get video transcript
|
|
try:
|
|
transcript_list = YouTubeTranscriptApi.get_transcript(video_id, languages=[options.language])
|
|
transcript_text = ' '.join([item['text']
|
|
for item in transcript_list])
|
|
transcript_text = transcript_text.replace('\n', ' ')
|
|
except Exception as e:
|
|
transcript_text = "Transcript not available."
|
|
|
|
# Output based on options
|
|
if options.duration:
|
|
print(duration_minutes)
|
|
elif options.transcript:
|
|
print(transcript_text)
|
|
else:
|
|
# Create JSON object
|
|
output = {
|
|
"transcript": transcript_text,
|
|
"duration": duration_minutes
|
|
}
|
|
# Print JSON object
|
|
print(json.dumps(output))
|
|
except HttpError as e:
|
|
print("Error: Failed to access YouTube API. Please check your YOUTUBE_API_KEY and ensure it is valid.")
|
|
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser(
|
|
description='vm (video meta) extracts metadata about a video, such as the transcript and the video\'s duration. By Daniel Miessler.')
|
|
parser.add_argument('url', nargs='?', help='YouTube video URL')
|
|
parser.add_argument('-l', '--language',
|
|
help='Set transcript language (default en)', default='en')
|
|
parser.add_argument('--duration', action='store_true',
|
|
help='Output only the duration')
|
|
parser.add_argument('--transcript', action='store_true',
|
|
help='Output only the transcript')
|
|
args = parser.parse_args()
|
|
|
|
if args.url:
|
|
main_function(args.url, args)
|
|
else:
|
|
parser.print_help()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|