Spaces:
Sleeping
Sleeping
| from pytube import YouTube | |
| from youtube_transcript_api import YouTubeTranscriptApi | |
| import re | |
| import os | |
| def download_video_transcript(video_url): | |
| try: | |
| video_id = re.search(r"(?<=v=)[\w-]+", video_url) | |
| if video_id: | |
| video_id = video_id.group() | |
| yt = YouTube(video_url) | |
| stream = yt.streams.get_highest_resolution() | |
| print(f'Downloading {yt.title}...') | |
| modified_title = yt.title.replace(" ", "_") | |
| download_path = 'CS370_Milestone5/videos' # Updated path to CS370_Milestone5 repository | |
| captions_path = 'CS370_Milestone5/captions' # Updated path to CS370_Milestone5 repository | |
| # Create directories if they don't exist | |
| os.makedirs(download_path, exist_ok=True) | |
| os.makedirs(captions_path, exist_ok=True) | |
| video_file = f'{download_path}/{modified_title}.mp4' | |
| stream.download(output_path=download_path, filename=modified_title + '.mp4') | |
| print('Download completed!') | |
| transcript_list = YouTubeTranscriptApi.list_transcripts(video_id) | |
| transcript = transcript_list.find_generated_transcript(['en']).fetch() | |
| captions = "" | |
| for i, line in enumerate(transcript): | |
| start_time = line['start'] | |
| formatted_time = f"{int(start_time // 60):02d}:{int(start_time % 60):02d}" | |
| captions += f"{formatted_time} {line['text']}\n" | |
| with open(f'{captions_path}/{modified_title}.txt', 'w', encoding='utf-8') as file: | |
| file.write(captions) | |
| # Delete video file after captions are saved | |
| os.remove(video_file) | |
| return captions | |
| else: | |
| print("Video ID not found in URL.") | |
| return None | |
| except Exception as e: | |
| print("Error:", e) | |
| return None | |