zbparse/flask_app/main/投标人须知正文提取指定内容.py

import json
import re


# 对于每个target_value元素，如果有完美匹配json_data中的键，那就加入这个完美匹配的键名，否则，把全部模糊匹配到的键名都加入
def find_keys_by_value(target_value, json_data):
    matched_keys = [k for k, v in json_data.items() if v == target_value]  #首先检查 JSON 中的每个键值对，如果值完全等于目标值，则将这些键收集起来。
    if not matched_keys:
        matched_keys = [k for k, v in json_data.items() if isinstance(v, str) and v.startswith(target_value)] #如果没有找到完全匹配的键，它会检查字符串类型的值是否以目标值开头，并收集这些键。
    return matched_keys      # eg:[3.1,3.1.1,3.1.2,3.2...]


# 定义查找以特定前缀开始的键的函数，eg:若match_keys中有3.1，那么以3.1为前缀的键都会被找出来，如3.1.1 3.1.2...
def find_keys_with_prefix(key_prefix, json_data):
    subheadings = [k for k in json_data if k.startswith(key_prefix)]
    return subheadings


# 从文件中读取JSON数据，并提取特定内容
def extract_json(data, target_values):
    results = {}
    for target_value in target_values:
        matched_keys = find_keys_by_value(target_value, data)
        for key in matched_keys:
            key_and_subheadings = find_keys_with_prefix(key, data)
            for subkey in key_and_subheadings:
                if "." in subkey:
                    parent_key = subkey.rsplit('.', 1)[0]
                    top_level_key = parent_key.split('.')[0] + '.'
                    # 特别处理定标相关的顶级键，确保不会重复添加其他键
                    if top_level_key not in results:
                        results[top_level_key] = target_value
                    # 添加或更新父级键
                    if parent_key not in results:
                        if parent_key in data:
                            results[parent_key] = data[parent_key]
                # 添加当前键
                results[subkey] = data[subkey]
    return results

def sort_clean_data_keys(data):
    # 预处理：删除键名中的空格
    def preprocess_key(key):
        return re.sub(r'\s+', '', key)

    # 将键转换成由整数构成的元组，作为排序依据
    def key_func(key):
        return tuple(int(part) for part in re.split(r'\D+', key) if part)

    # 创建一个新的字典，键名经过预处理
    preprocessed_data = {preprocess_key(key): value for key, value in data.items()}

    # 对预处理后的字典键进行排序
    sorted_keys = sorted(preprocessed_data.keys(), key=key_func)

    # 创建一个新的字典，按照排序后的键添加键值对
    sorted_data = {key: preprocessed_data[key] for key in sorted_keys}

    return sorted_data

# 转换结构化的JSON数据
def transform_json(data):
    result = {}
    temp = {0: result}  # 初始化根字典

    # 首先，创建一个临时字典用于检查是否存在三级标题
    has_subkey = {}
    for key in data.keys():
        parts = key.split('.')
        if len(parts) > 2 and parts[1]:
            parent_key = parts[0] + '.' + parts[1]
            has_subkey[parent_key] = True

    for key, value in data.items():
        match = re.match(r'(\d+)(?:\.(\d+))?(?:\.(\d+))?', key)
        if match:
            levels = [int(l) for l in match.groups() if l is not None]
            if (len(levels) - 1) in temp:
                parent = temp[len(levels) - 1]
            else:
                print(f"No parent found at level {len(levels) - 1} for key '{key}'. Check the data structure.")
                continue

            if len(levels) == len(match.groups()):
                if isinstance(parent, list):
                    parent.append(value)
                else:
                    # 对于根级别，使用完整的值作为键
                    if len(levels) == 1:
                        parent[value] = {}
                        temp[len(levels)] = parent[value]
                    else:
                        parent[value.split()[0]] = value
            else:
                new_key = value
                if '\n' in value and len(levels) == 2 and f"{levels[0]}.{levels[1]}" not in has_subkey:
                    new_key, new_value = value.split('\n', 1)
                    new_key = new_key.strip()
                    new_value = new_value.strip()
                    if isinstance(parent, list):
                        if len(parent) == 0 or not isinstance(parent[-1], dict):
                            parent.append({})
                        parent[-1][new_key] = new_value
                    else:
                        parent[new_key] = new_value
                else:
                    if isinstance(parent, list):
                        if len(parent) == 0 or not isinstance(parent[-1], dict):
                            parent.append({})
                        parent = parent[-1]
                    if new_key not in parent:
                        parent[new_key] = []
                    temp[len(levels)] = parent[new_key]

    def remove_single_item_lists(node):
        if isinstance(node, dict):
            for key in list(node.keys()):
                node[key] = remove_single_item_lists(node[key])
                if isinstance(node[key], list) and not node[key]:
                    node[key] = ""
        elif isinstance(node, list) and len(node) == 1:
            return remove_single_item_lists(node[0])
        return node

    return remove_single_item_lists(result)


# 读取JSON数据，提取内容，转换结构，并打印结果
def extract_from_notice(clause_path, type):
    if type == 1:
        target_values = ["投标","投标文件"]
    elif type == 2:
        target_values = ["开标", "评标", "定标"]
    elif type == 3:
        target_values = ["重新招标、不再招标和终止招标", "重新招标", "不再招标", "终止招标"]
    else:
        raise ValueError("Invalid type specified. Use 1 for '投标文件, 投标' or 2 for '开标, 评标, 定标'or 3 for '重新招标'")
    with open(clause_path, 'r', encoding='utf-8') as file:
        data = json.load(file)
        extracted_data = extract_json(data, target_values)  # 读取json
        sorted_data=sort_clean_data_keys(extracted_data)    #对键进行排序
        transformed_data = transform_json(sorted_data)
        return transformed_data


# 假设原始数据文件路径
if __name__ == "__main__":
    file_path = 'C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\tmp\\clause1.json'
    # file_path='C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\clause1.json'
    try:
        res = extract_from_notice(file_path, 2)  # 可以改变此处的 type 参数测试不同的场景
        res2=json.dumps(res,ensure_ascii=False,indent=4)
        print(res2)
    except ValueError as e:
        print(e)