JSONDecodeError: Extra data: line 2 column 1 (char 863)

JSONDecodeError: Expecting value: line 2 column 1 (char 2)

json에 저장이 잘못되어

[

	{
	
		input1 : answer1
		
		input2 : answer2
		
	}
	
]

로 저장되었는데

각 줄마다 읽어와서 데이터 없다고 에러발생 (그러니까위 코드 기준 [ 만 나온셈)

구분자 separators를 설정하고 [] 대신 \n으로 구분해서 json 저장하여

{"is_spoiler":true,"review_text":"Awesome movie\nnyc\nvery goodddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddd"}

이 형태로 잘 저장했다!

아래는 실제 활용 코드

import json

# Define file paths
input_file_path = "C:/Users/SSAFY/Desktop/Common_AI/movieData/IMDB_reviews.json"  # Input file containing JSON lines
output_file_path = 'C:/Users/SSAFY/Desktop/Common_AI/movieData/filtered_reviews.json'  # Output file to save the filtered JSON lines

# Open the input file and read it line by line
with open(input_file_path, 'r') as input_file:
    with open(output_file_path, 'w') as output_file:
        for line in input_file:
            try:
                # Parse the JSON object from the line
                json_obj = json.loads(line)
                
                # Extract specific fields with default values
                transformed_obj = {
                    "is_spoiler": json_obj.get("is_spoiler", ""),
                    "review_text": json_obj.get("review_text", "").strip()
                }
                if 'review_text' in transformed_obj and len(transformed_obj['review_text']) <= 700:
                    # Write each transformed JSON object as a single line in the output file
                    json.dump(transformed_obj, output_file, separators=(',', ':'))
                    output_file.write('\n')  # Add a newline character after each JSON object

            except json.JSONDecodeError as e:
                print(f"Error decoding JSON line: {e}")

print(f'Transformed data saved to {output_file_path}')
import json

def txt_to_json(txt_filename, json_filename):
    # Read the entire text file
    with open(txt_filename, 'r', encoding='utf-8') as txt_file:
        with open(json_filename, 'w', encoding='utf-8') as json_file:
            content = txt_file.read().strip()
        
            # Split content by double newlines to get individual reviews
            lines = content.split('\n\n')
        
            for line in lines:
                # Create a list of dictionaries for each review
                data = {'is_spoiler': True, 'review_text': line.strip()}
                    
                # Write the list of dictionaries to a JSON file
                json.dump(data, json_file, ensure_ascii=False,  separators=(',', ':'))
                json_file.write('\n') 

# Usage
txt_to_json(r'C:\Users\SSAFY\Desktop\104_reviews.txt', r'C:\Users\SSAFY\Desktop\data.json')