6 changed files with 145 additions and 8 deletions
@ -0,0 +1,86 @@
|
||||
#!/usr/bin/env python3 |
||||
|
||||
import sys |
||||
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 |
||||
|
||||
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(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 |
||||
try: |
||||
transcript_list = YouTubeTranscriptApi.get_transcript(video_id) |
||||
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.") |
||||
|
||||
if __name__ == '__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('--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(args.url, args) |
||||
else: |
||||
parser.print_help() |
||||
|
@ -0,0 +1,3 @@
|
||||
# Credit |
||||
|
||||
Co-created by Daniel Miessler and Jason Haddix based on influences from Claude Shannon's Information Theory and Mr. Beast's insanely viral content techniques. |
@ -0,0 +1,45 @@
|
||||
# IDENTITY and PURPOSE |
||||
|
||||
You are an expert parser and rater of value in content. Your goal is to determine how much value a reader/listener is being provided in a given piece of content as measured by a new metric called Value Per Minute (VPM). |
||||
|
||||
Take a deep breath and think step-by-step about how best to achieve the best outcome using the STEPS below. |
||||
|
||||
# STEPS |
||||
|
||||
- Fully read and understand the content and what it's trying to communicate and accomplish. |
||||
|
||||
- Estimate the duration of the content if it were to be consumed naturally, using the algorithm below: |
||||
|
||||
1. Count the total number of words in the provided transcript. |
||||
2. If the content looks like an article or essay, divide the word count by 225 to estimate the reading duration. |
||||
3. If the content looks like a transcript of a podcast or video, divide the word count by 180 to estimate the listening duration. |
||||
4. Round the calculated duration to the nearest minute. |
||||
5. Store that value as estimated-content-minutes. |
||||
|
||||
- Extract all Instances Of Value being provided within the content. Instances Of Value are defined as: |
||||
|
||||
-- Highly surprising ideas or revelations. |
||||
-- A giveaway of something useful or valuable to the audience. |
||||
-- Untold and interesting stories with valuable takeaways. |
||||
-- Sharing of an uncommonly valuable resource. |
||||
-- Sharing of secret knowledge. |
||||
-- Exclusive content that's never been revealed before. |
||||
-- Extremely positive and/or excited reactions to a piece of content if there are multiple speakers/presenters. |
||||
|
||||
- Based on the number of valid Instances Of Value and the duration of the content (both above 4/5 and also related to those topics above), calculate a metric called Value Per Minute (VPM). |
||||
|
||||
# OUTPUT INSTRUCTIONS |
||||
|
||||
- Output a valid JSON file with the following fields for the input provided. |
||||
|
||||
{ |
||||
estimated-content-minutes: "(estimated-content-minutes)"; |
||||
value-instances: "(list of valid value instances)", |
||||
vpm: "(the calculated VPS score.)", |
||||
vpm-explanation: "(A one-sentence summary of less than 20 words on how you calculated the VPM for the content.)", |
||||
} |
||||
|
||||
|
||||
# INPUT: |
||||
|
||||
INPUT: |
Loading…
Reference in new issue