Spaces:
Sleeping
Sleeping
def preprocess_text(text):
Browse files
app.py
CHANGED
@@ -393,6 +393,18 @@ def process_web_link(link):
|
|
393 |
return soup.get_text()
|
394 |
|
395 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
396 |
|
397 |
# get video_id_summary.json content
|
398 |
def get_video_id_summary(video_id, df_string):
|
@@ -406,7 +418,9 @@ def get_video_id_summary(video_id, df_string):
|
|
406 |
exists, file_id = check_file_exists(service, folder_id, file_name)
|
407 |
if not exists:
|
408 |
summary = generate_summarise(df_string)
|
409 |
-
|
|
|
|
|
410 |
summary_text = json.dumps(summary_json, ensure_ascii=False, indent=2)
|
411 |
file_id = upload_content_directly(service, file_name, folder_id, summary_text)
|
412 |
print("summary已上传到Google Drive")
|
|
|
393 |
return soup.get_text()
|
394 |
|
395 |
|
396 |
+
def preprocess_text(text):
|
397 |
+
# 预处理文本以便在 JSON 中使用
|
398 |
+
json_text = text.replace("\n", "\\n")
|
399 |
+
json_text = json_text.replace('"', '\\"')
|
400 |
+
json_text = json_text.replace("'", "\\'")
|
401 |
+
json_text = json_text.replace("\t", "\\t")
|
402 |
+
json_text = json_text.replace("\r", "\\r")
|
403 |
+
json_text = json_text.replace("\f", "\\f")
|
404 |
+
json_text = json_text.replace("\b", "\\b")
|
405 |
+
json_text = json_text.replace("\v", "\\v")
|
406 |
+
return json_text
|
407 |
+
|
408 |
|
409 |
# get video_id_summary.json content
|
410 |
def get_video_id_summary(video_id, df_string):
|
|
|
418 |
exists, file_id = check_file_exists(service, folder_id, file_name)
|
419 |
if not exists:
|
420 |
summary = generate_summarise(df_string)
|
421 |
+
# preprocess_text to json value acceptable
|
422 |
+
processed_summary = preprocess_text(summary)
|
423 |
+
summary_json = {"summary": processed_summary}
|
424 |
summary_text = json.dumps(summary_json, ensure_ascii=False, indent=2)
|
425 |
file_id = upload_content_directly(service, file_name, folder_id, summary_text)
|
426 |
print("summary已上传到Google Drive")
|