Python数据匹配教程：利用正则表达式关联JSON与文本文件信息

{
    "results": [
        {
            "url": "https://api.server.com/cables/100/",
            "termination_a": {
                "url": "https://api.server.com/interfaces/250/",
                "device": {
                    "url": "https://api.server.com/devices/10/",
                    "display": "device-number1-2023-08 myname (1718)",
                    "name": "device-number1-2023-08 myname"
                }
            }
        },
        {
            "url": "https://api.server.com/cables/200/",
            "termination_a": {
                "url": "https://api.server.com/interfaces/160/",
                "device": {
                    "url": "https://api.server.com/devices/22/",
                    "display": "device-number3-2023-08 myname (2245)",
                    "name": "device-number1-2023-08 myname1"
                }
            }
        },
        {
            "url": "https://api.server.com/cables/300/",
            "termination_a": {
                "url": "https://api.server.com/interfaces/260/",
                "device": {
                    "url": "https://api.server.com/devices/73/",
                    "display": "device-number8-2023-08 myname (3678)",
                    "name": "device-number8-2023-08 myname"
                }
            }
        }
    ]
}

this is device-number1-2023-08 myname1 and it is good.
this is device-number3-2023-08 myname3 and it is not good.
this is device-number8-2023-08 myname8 and it is.

import json
import re

# 1. 加载数据
try:
    with open("test.json", "r", encoding="utf-8") as json_file:
        json_data = json.load(json_file)
except FileNotFoundError:
    print("错误：test.json 文件未找到。")
    exit()
except json.JSONDecodeError:
    print("错误：test.json 文件格式不正确。")
    exit()

try:
    with open("test.txt", "r", encoding="utf-8") as text_file:
        text_content = text_file.read()
except FileNotFoundError:
    print("错误：test.txt 文件未找到。")
    exit()

# 2. 从文本文件中提取设备名称
# 定义正则表达式模式来匹配设备名称，例如 "device-number1-2023-08 myname1"
# 模式解释:
# device-: 匹配字面字符串 "device-"
# \w+: 匹配一个或多个字母、数字或下划线 (例如 "number1", "2023", "08", "myname")
# \d+: 匹配一个或多个数字
# \s: 匹配一个空格
# ()：捕获组，re.findall 将返回匹配到的组内容
device_name_pattern = r"(device-\w+-\d+-\d+\s\w+)"
txt_device_names = re.findall(device_name_pattern, text_content)

print(f"从文本文件中提取到的设备名称: {txt_device_names}\n")

# 3. 在JSON数据中查找匹配项并提取信息
# 4. 提取并输出关联信息
if "results" in json_data and isinstance(json_data["results"], list):
    found_matches = False
    for item in json_data["results"]:
        try:
            json_device_name = item["termination_a"]["device"]["name"]

            # 检查JSON中的设备名称是否在文本文件中提取到的名称列表中
            if json_device_name in txt_device_names:
                found_matches = True
                print(f"找到匹配设备: {json_device_name}")
                print(f"  主URL: {item['url']}")
                print(f"  终止A URL: {item['termination_a']['url']}")
                print(f"  终止A设备URL: {item['termination_a']['device']['url']}\n")
        except KeyError as e:
            print(f"警告：JSON数据结构不完整，缺少键 '{e}'。跳过此项。")
            continue

    if not found_matches:
        print("未找到任何匹配的设备名称。")
else:
    print("错误：JSON数据结构不符合预期，缺少 'results' 列表。")