노드 크롤링 데이터의 예: 소설 장을 크롤링하는 방법에 대해 이야기해 보겠습니다.

request = https.request(TestUrl, { encoding:'utf-8' }, (res)=>{
    let chunks = ''
    res.on('data', (chunk)=>{
        chunks += chunk
    })
    res.on('end',function(){
        console.log('请求结束');
    })
})

const fs = require('fs')
const cheerio = require('cheerio');

// 引入读取方法
const { getFile, writeFun } = require('./requestNovel')

let hasIndexPromise = getFile('./hasGetfile/index.html');

let bookArray = [];

hasIndexPromise.then((res)=>{
    let htmlstr = res;
    let $ = cheerio.load(htmlstr);

    $(".listmain dl dd a").map((index, item)=>{
        let name = $(item).text(), href = 'https://www.shuquge.com/txt/147032/' + $(item).attr('href')
        if (index > 11){
            bookArray.push({ name, href })
        }
        
    })
    // console.log(bookArray)
    writeFun('./hasGetfile/hrefList.txt', JSON.stringify(bookArray), 'w')
})

// 爬取某一章节的内容方法
function getOneChapter(n) {
    return new Promise((resolve, reject)=>{
        if (n >= bookArray.length) {
            reject('未能找到')
        }
        let name = bookArray[n].name;
        request = https.request(bookArray[n].href, { encoding:'gbk' }, (res)=>{
            let html = ''
            res.on('data', chunk=>{
                html += chunk;
            })
            res.on('end', ()=>{           
                let $ = cheerio.load(html);
                let content = $("#content").text();
                if (content) {
                    // 写成txt
                    writeFun(`./hasGetfile/${name}.txt`, content, 'w')
                    resolve(content);
                } else {
                    reject('未能找到')
                }
            })
        })
        request.end();
    })
}

getOneChapter(10)

const express = require('express'); 
const IO = express();
const { getAllChapter, getOneChapter } = require('./readIndex')
// 获取章节超链接链表
getAllChapter();

IO.use('/book',function(req, res) {
    // 参数
    let query = req.query;
    if (query.n) {
        // 获取某一章节数据
        let promise = getOneChapter(parseInt(query.n - 1));
        promise.then((d)=>{
            res.json({ d: d })
        }, (d)=>{
            res.json({ d: d })
        })
    } else {
        res.json({ d: 404 })
    }
    
})

//服务器本地主机的数字
IO.listen('7001',function(){
    console.log("启动了。。。");
})