使用 Python 时不从 YouTube 捕获字幕

Question

我正在尝试制作一个简单的 Python 脚本来打印字幕。我有一个 API 并启用了相关的 YouTube API。脚本运行但它没有捕获成绩单，即使我可以看到视频有成绩单。

如有任何建议，我将不胜感激！

import os
import google.auth
import google.auth.transport.requests
import google.oauth2.credentials
from googleapiclient.discovery import build
from googleapiclient.errors import HttpError
import urllib.request
import re

# Prompt the user for the video ID
video_id = input(": Enter the YouTube video ID: ")

# Set up the YouTube API client
api_service_name = "youtube"
api_version = "v3"
api_key = ""

from google.oauth2 import service_account

credentials = service_account.Credentials.from_service_account_file(
r"")

youtube = build(api_service_name, api_version, credentials=credentials)

try:
    # Call the YouTube API to retrieve the video caption tracks
    caption_request = youtube.captions().list(
        part="snippet",
        videoId=video_id
    )
    caption_response = caption_request.execute()

    # Check if an asr caption track was found
    asr_track_id = None
    for item in caption_response["items"]:
        if item["snippet"]["trackKind"] == "asr":
            asr_track_id = item["id"]
            break

    if asr_track_id is None:
        print("ASR caption track not available.")
    else:
        # Call the YouTube API to download the caption track in "srt" format
        caption_url = "https://www.youtube.com/api/timedtext?v={}&lang=en&fmt=srv3&id={}".format(video_id, asr_track_id)
        response = urllib.request.urlopen(caption_url)
        caption_data = response.read().decode("utf-8")

        # Parse the "srt" caption data to extract the transcript
        pattern = r"\d+\n\d\d:\d\d:\d\d,\d\d\d --> \d\d:\d\d:\d\d,\d\d\d\n(.+?)(?:\n\n|\Z)"
        matches = re.findall(pattern, caption_data)
        if matches:
            transcript = " ".join(matches).replace("\n", " ")
        else:
            transcript = ""

        if not transcript:
            print("Transcript not available.")
        else:
            print(transcript)

            # Split the transcript into paragraphs of no more than three sentences each
            sentences = transcript.split(". ")
            paragraphs = []
            current_paragraph = ""
            for sentence in sentences:
                if len(current_paragraph.split(". ")) < 3:
                    current_paragraph += sentence + ". "
                else:
                    paragraphs.append(current_paragraph)
                    current_paragraph = sentence + ". "
            if current_paragraph:
                paragraphs.append(current_paragraph)

            # Print the formatted transcript
            for paragraph in paragraphs:
                print(paragraph + "\n")
except HttpError as e:
    print("An HTTP error occurred: %s" % e)
except Exception as e:
    print("An error occurred: %s" % e)

当视频有文字记录时，它运行但不显示任何文字记录。