Spaces:
Running
Running
if is_new_transcript:
Browse files
app.py
CHANGED
@@ -489,6 +489,7 @@ def process_transcript_and_screenshots_on_gcs(video_id):
|
|
489 |
transcript_file_name = f'{video_id}_transcript.json'
|
490 |
transcript_blob_name = f"{video_id}/{transcript_file_name}"
|
491 |
# 检查逐字稿是否存在
|
|
|
492 |
is_transcript_exists = GCS_SERVICE.check_file_exists(bucket_name, transcript_blob_name)
|
493 |
if not is_transcript_exists:
|
494 |
# 从YouTube获取逐字稿并上传
|
@@ -507,6 +508,7 @@ def process_transcript_and_screenshots_on_gcs(video_id):
|
|
507 |
|
508 |
transcript_text = json.dumps(transcript, ensure_ascii=False, indent=2)
|
509 |
upload_file_to_gcs_with_json_string(gcs_client, bucket_name, transcript_blob_name, transcript_text)
|
|
|
510 |
else:
|
511 |
# 逐字稿已存在,下载逐字稿内容
|
512 |
print("逐字稿已存在于GCS中")
|
@@ -542,15 +544,19 @@ def process_transcript_and_screenshots_on_gcs(video_id):
|
|
542 |
img_file_id = upload_img_and_get_public_url(gcs_client, bucket_name, screenshot_blob_name, screenshot_path)
|
543 |
entry['img_file_id'] = img_file_id
|
544 |
print(f"截图已上传到GCS: {img_file_id}")
|
545 |
-
|
546 |
-
|
547 |
-
|
548 |
-
|
549 |
-
|
550 |
-
|
551 |
-
|
552 |
-
|
553 |
-
|
|
|
|
|
|
|
|
|
554 |
|
555 |
return updated_transcript_json
|
556 |
|
|
|
489 |
transcript_file_name = f'{video_id}_transcript.json'
|
490 |
transcript_blob_name = f"{video_id}/{transcript_file_name}"
|
491 |
# 检查逐字稿是否存在
|
492 |
+
is_new_transcript = False
|
493 |
is_transcript_exists = GCS_SERVICE.check_file_exists(bucket_name, transcript_blob_name)
|
494 |
if not is_transcript_exists:
|
495 |
# 从YouTube获取逐字稿并上传
|
|
|
508 |
|
509 |
transcript_text = json.dumps(transcript, ensure_ascii=False, indent=2)
|
510 |
upload_file_to_gcs_with_json_string(gcs_client, bucket_name, transcript_blob_name, transcript_text)
|
511 |
+
is_new_transcript = True
|
512 |
else:
|
513 |
# 逐字稿已存在,下载逐字稿内容
|
514 |
print("逐字稿已存在于GCS中")
|
|
|
544 |
img_file_id = upload_img_and_get_public_url(gcs_client, bucket_name, screenshot_blob_name, screenshot_path)
|
545 |
entry['img_file_id'] = img_file_id
|
546 |
print(f"截图已上传到GCS: {img_file_id}")
|
547 |
+
is_new_transcript = True
|
548 |
+
|
549 |
+
if is_new_transcript:
|
550 |
+
# 更新逐字稿文件
|
551 |
+
print("===更新逐字稿文件===")
|
552 |
+
print(transcript)
|
553 |
+
print("===更新逐字稿文件===")
|
554 |
+
updated_transcript_text = json.dumps(transcript, ensure_ascii=False, indent=2)
|
555 |
+
upload_file_to_gcs_with_json_string(gcs_client, bucket_name, transcript_blob_name, updated_transcript_text)
|
556 |
+
print("逐字稿已更新,包括截图链接")
|
557 |
+
updated_transcript_json = json.loads(updated_transcript_text)
|
558 |
+
else:
|
559 |
+
updated_transcript_json = transcript
|
560 |
|
561 |
return updated_transcript_json
|
562 |
|