(self)
| 37 | |
| 38 | @pyqtSlot() |
| 39 | def run(self): |
| 40 | if self.transcription_task.source == FileTranscriptionTask.Source.URL_IMPORT: |
| 41 | cookiefile = os.getenv("BUZZ_DOWNLOAD_COOKIEFILE") |
| 42 | |
| 43 | # First extract info to get the video title |
| 44 | extract_options = { |
| 45 | "logger": logging.getLogger(), |
| 46 | } |
| 47 | if cookiefile: |
| 48 | extract_options["cookiefile"] = cookiefile |
| 49 | |
| 50 | try: |
| 51 | with YoutubeDL(extract_options) as ydl_info: |
| 52 | info = ydl_info.extract_info(self.transcription_task.url, download=False) |
| 53 | video_title = info.get("title", "audio") |
| 54 | except Exception as exc: |
| 55 | logging.debug(f"Error extracting video info: {exc}") |
| 56 | video_title = "audio" |
| 57 | |
| 58 | # Sanitize title for use as filename |
| 59 | video_title = YoutubeDL.sanitize_info({"title": video_title})["title"] |
| 60 | # Remove characters that are problematic in filenames |
| 61 | for char in ['/', '\\', ':', '*', '?', '"', '<', '>', '|']: |
| 62 | video_title = video_title.replace(char, '_') |
| 63 | |
| 64 | # Create temp directory and use video title as filename |
| 65 | temp_dir = tempfile.mkdtemp() |
| 66 | temp_output_path = os.path.join(temp_dir, video_title) |
| 67 | wav_file = temp_output_path + ".wav" |
| 68 | wav_file = str(Path(wav_file).resolve()) |
| 69 | |
| 70 | options = { |
| 71 | "format": "bestaudio/best", |
| 72 | "progress_hooks": [self.on_download_progress], |
| 73 | "outtmpl": temp_output_path, |
| 74 | "logger": logging.getLogger(), |
| 75 | } |
| 76 | |
| 77 | if cookiefile: |
| 78 | options["cookiefile"] = cookiefile |
| 79 | |
| 80 | ydl = YoutubeDL(options) |
| 81 | |
| 82 | try: |
| 83 | logging.debug(f"Downloading audio file from URL: {self.transcription_task.url}") |
| 84 | ydl.download([self.transcription_task.url]) |
| 85 | except Exception as exc: |
| 86 | logging.debug(f"Error downloading audio: {exc.msg}") |
| 87 | self.error.emit(exc.msg) |
| 88 | return |
| 89 | |
| 90 | cmd = [ |
| 91 | "ffmpeg", |
| 92 | "-nostdin", |
| 93 | "-threads", "0", |
| 94 | "-i", temp_output_path, |
| 95 | "-ac", "1", |
| 96 | "-ar", str(whisper_audio.SAMPLE_RATE), |
no test coverage detected