NodeJS请求Swiggy API遇403及无效JSON错误求助

我是NodeJS新手，尝试使用以下代码从Swiggy在线API获取JSON响应：

// server.js
const express = require('express');
const cors = require('cors');
const fetch = require('node-fetch');

const app = express();
const port = process.env.PORT || 3001;

app.use(cors());

app.get('/api/data', async (req, res) => {
  try {
    const apiUrl = "https://www.swiggy.com/dapi/restaurants/list/v5?lat=28.6083697&lng=77.293112&page_type=DESKTOP_WEB_LISTING"; // Replace with the actual API URL
    const response = await fetch(apiUrl);
    const data = await response.json();
    return res.json(data);
  } catch (error) {
    console.error('Error fetching data:', error);
    return res.status(500).json({ error: 'Internal Server Error' });
  }
});

app.listen(port, () => {
  console.log(`Server is running on port ${port}`);
});

发起GET请求时，控制台出现如下错误：

Server is running on port 3001
Error fetching data: FetchError: invalid json response body at https://www.swiggy.com/dapi/restaurants/list/v5?lat=28.6083697&lng=77.293112&page_type=DESKTOP_WEB_LISTING reason: Unexpected token '<', "<html lang"... is not valid JSON
    at /home/priya/Documents/server/node_modules/node-fetch/lib/index.js:273:32
    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
    at async /home/priya/Documents/server/index.js:15:18 {
  type: 'invalid-json'
}

我尝试打印响应信息，结果如下：

Response {
  size: 0,
  timeout: 0,
  [Symbol(Body internals)]: {
    body: PassThrough {
      _events: [Object],
      _readableState: [ReadableState],
      _writableState: [WritableState],
      allowHalfOpen: true,
      _maxListeners: undefined,
      _eventsCount: 5,
      [Symbol(shapeMode)]: true,
      [Symbol(kCapture)]: false,
      [Symbol(kCallback)]: null
    },
    disturbed: false,
    error: null
  },
  [Symbol(Response internals)]: {
    url: 'https://www.swiggy.com/dapi/restaurants/list/v5?lat=28.6083697&lng=77.293112&page_type=DESKTOP_WEB_LISTING',
    status: 403,
    statusText: 'Forbidden',
    headers: Headers { [Symbol(map)]: [Object: null prototype] },
    counter: 0
  }
}

解决方案 #

问题根源 #

1. 403状态码说明Swiggy服务器拒绝了请求，默认node-fetch发起的请求缺少浏览器标识的请求头，被服务器识别为非合法请求拦截。
2. 解析JSON失败是因为403返回的是HTML错误页面，而非预期的JSON数据，因此解析时抛出"Unexpected token '<'"错误。

修改后的代码 #

// server.js
const express = require('express');
const cors = require('cors');
const fetch = require('node-fetch');

const app = express();
const port = process.env.PORT || 3001;

app.use(cors());

app.get('/api/data', async (req, res) => {
  try {
    const apiUrl = "https://www.swiggy.com/dapi/restaurants/list/v5?lat=28.6083697&lng=77.293112&page_type=DESKTOP_WEB_LISTING";
    // 添加模拟浏览器的请求头，避免被拦截
    const requestHeaders = {
      'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36',
      'Accept': 'application/json, text/plain, */*'
    };
    
    const response = await fetch(apiUrl, { headers: requestHeaders });
    
    // 先验证响应状态，再解析JSON
    if (!response.ok) {
      throw new Error(`请求失败，状态码：${response.status} ${response.statusText}`);
    }
    
    const data = await response.json();
    return res.json(data);
  } catch (error) {
    console.error('获取数据失败:', error);
    return res.status(500).json({ error: error.message || '服务器内部错误' });
  }
});

app.listen(port, () => {
  console.log(`Server is running on port ${port}`);
});

关键修改点 #

• 添加User-Agent和Accept请求头，模拟浏览器的请求特征，绕过Swiggy的基础反爬拦截。
• 增加响应状态码校验，在解析JSON前先判断请求是否成功，避免无效解析抛出异常。

内容的提问来源于stack exchange，提问作者priya jha