【点选验证码】整理生成的txt文件错误数据

#--------------------删除不规则数据:\data不在一行开头，将\data以及本行之前的都删除
import re

def process_file(input_file, output_file):
    with open(input_file, 'r') as infile:
        with open(output_file, 'w') as outfile:
            for line in infile:
                # 使用正则表达式匹配行中的 /data/lh123/lh/，但不在行开头的情况
                pattern = re.compile(r'(?<!^)/data')  # 使用 (?<!^) 限制不在行开头
                match = pattern.search(line)
                if match:
                    index = match.start()
                    line = line[index + len('/data'):]
                outfile.write(line)

if __name__ == "__main__":
    input_path = "/data/lh123/lh/train.txt"
    output_path = "/data/lh123/lh/train1.txt"
    process_file(input_path, output_path)

# 进行上一步的原因是还可以尽可能的多保存数据
# ----------不是标准格式的删除---删除力度大
import json

def is_valid_line(line):
    try:
        # 检查行是否以指定路径开头
        if not line.startswith('/data/lh123/lh/verification_code/PaddleOCR-release-2.6/train_data/train/'):
            return False

        # 获取JSON部分并解析
        json_data = line.split('\t')[1]
        annotations = json.loads(json_data)

        # 检查JSON是否包含所需字段
        for annotation in annotations:
            if "transcription" not in annotation or "points" not in annotation:
                return False

    except Exception as e:
        return False

    return True

def process_file(input_file, output_file):
    with open(input_file, 'r') as infile:
        with open(output_file, 'w') as outfile:
            for line in infile:
                if is_valid_line(line):
                    outfile.write(line)

if __name__ == "__main__":
    input_path = "/data/lh123/lh/train2.txt"
    output_path = "/data/lh123/lh/train3.txt"
    process_file(input_path, output_path)