transcript_processor.py

import requests
import os
from youtube_transcript_api import YouTubeTranscriptApi
from youtube_transcript_api.formatters import TextFormatter

API_URL = "https://api-inference.huggingface.co/models/SamLowe/roberta-base-go_emotions"
headers = {"Authorization": os.getenv('BEARER')}

def query(payload):
		"""
		Sends a request to the Hugging Face API with the given payload.

		Args:
				payload (dict): The payload to send in the request.

		Returns:
				dict: The JSON response from the API.
		"""
		try:
				response = requests.post(API_URL, headers=headers, json=payload)
				response.raise_for_status()  # Raise an exception for HTTP errors

				print(response.json())
				return response.json()
		except requests.exceptions.RequestException as e:
				return {"error": str(e)}

def get_youtube_transcript(video_id):
		"""
		Retrieves and formats the transcript of a YouTube video.

		Args:
				video_id (str): The ID of the YouTube video.

		Returns:
				str: The formatted transcript text truncated to 800 characters.
		"""
		try:
				transcript = YouTubeTranscriptApi.get_transcript(video_id)
				
				formatter = TextFormatter()
				formatted_transcript = formatter.format_transcript(transcript).replace('\r', '').replace('\n', '')
				
				# Truncate text to 800 characters to deal with limitations of the model
				print(formatted_transcript)
				return formatted_transcript[:800]
		except Exception as e:
				return str(e)