Update FC_tool_main.py

FC_tool_main.py

@@ -24,6 +24,7 @@ import os
 import openai
 import json
 from typing import List, Dict, Any, Union, Type
+import requests
 from youtube_transcript_api import YouTubeTranscriptApi
 from langchain_core.pydantic_v1 import BaseModel, Field
 from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
@@ -39,6 +40,7 @@ from langchain.memory import ConversationBufferWindowMemory
 
 # _ = load_dotenv(find_dotenv()) # read local .env file
 openai.api_key = os.getenv('OPENAI_API_KEY') #os.environ['OPENAI_API_KEY']
+rapid_api_key = os.getenv('RAPID_API_KEY')
 
 def get_temperature():
     return 0  #Default value
@@ -108,7 +110,7 @@ class YouTubeTranscriptPointsExtractor:
     @staticmethod
     def _fetch_transcript(youtube_video_id: str) -> str:
         """
-        Fetches the transcript for a YouTube video.
+        Fetches the transcript for a YouTube video using a third-party API.
 
         Args:
             youtube_video_id (str): The ID of the YouTube video.
@@ -120,8 +122,21 @@ class YouTubeTranscriptPointsExtractor:
             Exception: If there's an error fetching the transcript.
         """
         try:
-            transcript_json = YouTubeTranscriptApi.get_transcript(youtube_video_id)
-            transcript_data = [f"{entry['start']:.2f}: {entry['text']} " for entry in transcript_json]
+            details_url = "https://youtube-media-downloader.p.rapidapi.com/v2/video/details"
+            subtitles_url = "https://youtube-media-downloader.p.rapidapi.com/v2/video/subtitles"
+            querystring = {"videoId": youtube_video_id}
+            headers = {
+                "x-rapidapi-key": rapid_api_key,
+                "x-rapidapi-host": "youtube-media-downloader.p.rapidapi.com"
+            }
+            details_response = requests.get(details_url, headers=headers, params=querystring)
+            print(details_response)
+            sub_url = details_response.json()['subtitles']['items'][0]['url']
+            querystring = {"subtitleUrl": sub_url, "format": "json"}
+            subtitles_response = requests.get(subtitles_url, headers=headers, params=querystring)
+
+            transcript_json = subtitles_response.json()
+            transcript_data = [f"{entry['startMs']/1000:.2f}: {entry['text']} " for entry in transcript_json]
             return "".join(transcript_data)
         except Exception as e:
             raise
@@ -265,9 +280,22 @@ class QuestionAnswerExtractor:
             Exception: If there's an error fetching the transcript.
         """
         try:
-            transcript_json = YouTubeTranscriptApi.get_transcript(youtube_video_id)
-            transcript_data = [entry['text'] for entry in transcript_json]
-            return " ".join(transcript_data)
+            details_url = "https://youtube-media-downloader.p.rapidapi.com/v2/video/details"
+            subtitles_url = "https://youtube-media-downloader.p.rapidapi.com/v2/video/subtitles"
+            querystring = {"videoId": youtube_video_id}
+            headers = {
+                "x-rapidapi-key": rapid_api_key,
+                "x-rapidapi-host": "youtube-media-downloader.p.rapidapi.com"
+            }
+            details_response = requests.get(details_url, headers=headers, params=querystring)
+            print(details_response)
+            sub_url = details_response.json()['subtitles']['items'][0]['url']
+            querystring = {"subtitleUrl": sub_url, "format": "json"}
+            subtitles_response = requests.get(subtitles_url, headers=headers, params=querystring)
+
+            transcript_json = subtitles_response.json()
+            transcript_data = [f"{entry['startMs']/1000:.2f}: {entry['text']} " for entry in transcript_json]
+            return "".join(transcript_data)
         except Exception as e:
             raise