学习 node爬虫丁香园疫情

电玩女神 2023-07-18 14:17 9阅读 0赞

#### 前提准备： ####

你需要 : **cnpm i** 安装这些包

##### package.json #####

{ 
      "name": "test",
      "version": "1.0.0",
      "description": "",
      "main": "index.js",
      "scripts": { 
        "test": "echo \"Error: no test specified\" && exit 1"
      },
      "keywords": [],
      "author": "",
      "license": "ISC",
      "dependencies": { 
        "cheerio": "^1.0.0-rc.3",
        "express": "^4.17.1",
        "requests": "^0.3.0"
      }
    }

##### index.js #####

*  执行命令：node index.js
 *  得到html

let requests = require('requests');
    let fs = require('fs') //fs模块
    let path = require('path') //path模块
    
    requests('https://ncov.dxy.cn/ncovh5/view/pneumonia?from=timeline&isappinstalled=0')
        .on('data', function(chunk) { 
            fs.writeFile(path.resolve(__dirname, 'data.html'), chunk, () => {  //得到html字符串
                console.log('保存成功');
            })
        })

##### data.html #####

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3d1ajE5MzU_size_16_color_FFFFFF_t_70]

--------------------

##### index.js #####

*  执行命令：node index.js
 *  得到html结构，再得到里面的省份信息

##### data.json![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3d1ajE5MzU_size_16_color_FFFFFF_t_70 1] #####

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3d1ajE5MzU_size_16_color_FFFFFF_t_70]: /images/20230528/704fc3f03c774efdab0b04bc8efc7e1e.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3d1ajE5MzU_size_16_color_FFFFFF_t_70 1]: /images/20230528/d302f27f22b147c7a1c5807e21f8e442.png