对于electron以及nodejs开发,是一只小菜鸟,第一次想做个应用
只能边学边做,遇到各种各样的问题。
1、不想把所有的主进程函数放到一个文件中,这样文件比较乱,并且不好处理
想法:将另一个js文件引入到该文件中,进行调用等
问题:js不存在互相调用的功能
解决方案:
自定义nodejs模块,并在main.js中导入,然后进行处理(以下代码来自网络)
1 'use strict'; 2 const electron = require('electron'); 3 const app = electron.app; 4 const CrawlService = require('./libs/crawlService'); 5 6 //start crawl service 7 CrawlService.start(); 8 9 // adds debug features like hotkeys for triggering dev tools and reload 10 require('electron-debug')(); 11 12 // prevent window being garbage collected 13 let mainWindow; 14 15 function onClosed() { 16 // dereference the window 17 // for multiple windows store them in an array 18 mainWindow = null; 19 } 20 21 function createMainWindow() { 22 const win = new electron.BrowserWindow({ 23 width: 1200, 24 height: 800 25 }); 26 27 win.loadURL(`file://${__dirname}/static/index.html`); 28 win.openDevTools(); 29 win.on('closed', onClosed); 30 31 return win; 32 } 33 34 app.on('window-all-closed', () => { 35 if (process.platform !== 'darwin') { 36 app.quit(); 37 } 38 }); 39 40 app.on('activate', () => { 41 if (!mainWindow) { 42 mainWindow = createMainWindow(); 43 } 44 }); 45 46 app.on('ready', () => { 47 mainWindow = createMainWindow(); 48 })以上代码中的4、5、6、7行就是引入自定义模块进行处理,自定义模块代码为
const request = require('request'), async = require('async'), ipcMain = require('electron').ipcMain, db = require('./dbService'), cheerio = require('cheerio'); const CrawlService = { start: function () { ipcMain.on('search-keyword', function (event, keyword) { console.log('channel "search-keyword" on msg:' + keyword); let match = {$regex: eval('/' + keyword + '/')}; var query = keyword ? {$or: [{title: match}, {content: match}]} : {}; db.find(query).sort({publishDate: -1}).limit(100).exec(function (err, mails) { event.sender.send('search-reply', {mails: mails}); }); }); ipcMain.on('start-crawl', (event, arg) => { console.log('channel "start-crawl" on msg:' + arg); var updater = { sender: event.sender, channel: arg, updateProgress: function (progress) { this.sender.send(this.channel, {progress: progress}); } }; crawler(updater); }); } }; function UrlCrawler(targetUrl) { return { targetUrl: targetUrl, startCrawl: function (processDom) { request(this.targetUrl, (err, response, body) => { if (err) throw err; var $ = cheerio.load(body); processDom($) }); } }; } function pageCrawl(page, totalPage, updater, crawlNextPage, crawProgress) { new UrlCrawler('http://12345.chengdu.gov.cn/moreMail?page=' + page).startCrawl(($) => { var $pageMails = $('div.left5 ul li.f12px'), sameMailsInPage = 0; async.eachOfLimit($pageMails, 10, function iteratee(item, key, nextMail) { if(crawProgress.skip){ return nextMail(); } let $item = $(item), mailDetailUrl = $item.find('a').prop('href'), divs = $item.find('div'); var mail = { _id: mailDetailUrl.match(/\d+/g)[0], title: $(divs[0]).text().trim(), sender: $(divs[1]).text().trim(), receiveUnit: $(divs[2]).text().trim(), status: $(divs[3]).text().trim(), category: $(divs[4]).text().trim(), views: $(divs[5]).text().trim() }; new UrlCrawler('http://12345.chengdu.gov.cn/' + mailDetailUrl).startCrawl(($) => {// crawl mail detail mail.content = $($('.rightside1 td.td2')[1]).text().trim(); mail.result = $('.rightside1 tbody tr:last-child').text().trim(); mail.publishDate = $($('.rightside1 td.td32')[0]).text().trim() || $($('.rightside1 td.td32')[1]).text().trim(); console.log(mail._id); db.update({_id: mail._id}, mail, {upsert: true, returnUpdatedDocs: true}, function (err, numReplaced, affectedDocuments, upsert) { if (err) { throw err; } if(!upsert && affectedDocuments.result == mail.result){//if a mail are not update if(++sameMailsInPage == 15){ //if all mails in one page are note update. crawProgress.skip = true; } } }); nextMail(); }); }, function done() { crawlNextPage(); updater.updateProgress(Math.floor(page * 100 / totalPage)); }); }); } /** * 1. get total page size * 2. iterator from page 1 to totalSize * 2.1 fetch mails summary list on 1 page * 2.2 iterator from mails 1 to maxItems mails summary in 1 page * 2.2.1 fetch mails detail from url * 2.2.2 save mail to db * 2.3 test if none of mails in current page updated? if none, stop crawling or continue step 2. * * @param url */ function crawler(updater) { new UrlCrawler('http://12345.chengdu.gov.cn/moreMail').startCrawl(($) => { var totalSize = $('div.pages script').html().match(/iRecCount = \d+/g)[0].match(/\d+/g)[0], totalPageSize = Math.ceil(totalSize / 15), pagesCollection = [], crawProgress = {skip: false}; for (let i = 1; i <= totalPageSize; i++) { pagesCollection.push(i); } async.eachSeries(pagesCollection, function (page, crawlNextPage) { pageCrawl(page, totalPageSize, updater, crawlNextPage, crawProgress); }) }); } module.exports = CrawlService;
转载于:https://www.cnblogs.com/xbotao/p/6118616.html
相关资源:淘宝自定义模块生成工具