nodejs爬取笔趣阁小说

Category : 工具 Views : 2096 Comments : 0 Posted on : 2019-08-30

多说无益，直接上代码

var http = require("http");
var express = require("express");
var request = require('request');
var async = require("async");
var fs = require('fs');
var iconv = require('iconv-lite');
var cheerio = require('cheerio');
var app = express();
let k = 1;
let breakNum = 1;
down(k)
async function down(i) {
    let old = 0;
    request({
        url: "https://www.biqugex.com/book_" + i + "/",//请求路径
        method: "GET",//请求方式，默认为get
        headers: {
            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3",
            "Accept-Language": "zh-CN,zh;q=0.9",
            "Cache-Control": "max-age=0",
            "Connection": "keep - alive",
            "Host": "www.biqugex.com",
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36",
        },
        encoding: null,
    }, await function (err, res, body) {
        //转码
        let html = iconv.decode(body, "gb2312");
        //小说名

        let bookName = html.match(/<h2>.*<\/h2>/)[0].replace(/<(\S*?)[^>]*>.*?|<.*? \/>/g, "");
        //获取小说章节元素
        let textBody = html.split("</dt>")[2].split("</dl>")[0];
        //拆分元素获取地址
        let url = textBody.split('"');
        let urlList = [];
        console.log(urlList.length)
        for (let i = 1; i < url.length; i += 2) {
            //把地址存入数组
            urlList.push("https://www.biqugex.com" + url[i])
        }
        console.log(urlList.length)
        fs.mkdir(__dirname + "/" + bookName + "/", function (err) {
            if (err) {
                return console.error(err);
            }
            console.log("目录创建成功。");
        });
        async.mapLimit(urlList, 50, function (url, callback) {
            request({
                url: url,//请求路径
                method: "GET",//请求方式，默认为get
                headers: {
                    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3",
                    "Accept-Language": "zh-CN,zh;q=0.9",
                    "Cache-Control": "max-age=0",
                    "Connection": "keep - alive",
                    "Host": "www.biqugex.com",
                    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36",
                },
                encoding: null,
            }, function (err, res, body) {
                
                if (err) {
                    if (err.code == "ENOTFOUND") {
                        breakNum++
                        return
                    }
                    console.log(url)
                    console.log(body)
                    console.log(err)
                }
                console.log(old, urlList.length - 1)
                if (old == urlList.length - breakNum) {
                    console.log(121212)
                    if (k > 100) {
                        return
                    }
                    k++;
                    down(k)
                }
                let htmlBody = iconv.decode(body, "gb2312");
                let $ = cheerio.load(htmlBody);
                //过滤本章地址
                let title = $("h1").text()
                let testText = $("#content").text().replace(/(https?|ftp|file):\/\/[-A-Za-z0-9+&@#\/%?=~_|!:,.;]+[-A-Za-z0-9+&@#\/%=~_|]/g, "");
                //过滤笔趣阁广告
                let text = testText.replace("请记住本书首发域名：www.biqugex.com。笔趣阁手机版阅读网址：m.biqugex.com", "")
                old++
                fs.writeFile('./' + bookName + '/' + title + ".txt", text, function (err) {
                })
                callback(null, url)
            })
        }, function (error, results) {
            console.log("result :");
            console.log(results);
        })
    })
}
app.listen(3000);

一步一个坑的走过来的，虽然不到一百行代码，写起来可真是要命

Posted by : lyhq Tags : 本文未设置标签

所有原创文章采用知识共享署名-非商业性使用 4.0 国际许可协议进行许可。
您可以自由的转载和修改，但请务必注明文章来源并且不可用于商业目的。
本站部分内容收集于互联网，如果有侵权内容、不妥之处，请联系我们删除。敬请谅解！

Previous post gojs恢复页面内存

Next post Axios封装

nodejs爬取笔趣阁小说

添加新评论