nodeJs爬虫使用步骤详解

const log4js = require('log4js');
log4js.configure({
 appenders: {
 cheese: {
 type: 'dateFile',
 filename: 'cheese.log',
 pattern: '-yyyy-MM-dd.log',
 // 包含模型
 alwaysIncludePattern: true,
 maxLogSize: 1024,
 backups: 3 }
 },
 categories: { default: { appenders: ['cheese'], level: 'info' } }
});
const logger = log4js.getLogger('cheese');
logger.level = 'INFO';
module.exports = logger;

 superagent.get(cityItemUrl).end((err, res) => {
 if (err) {
 return console.error(err);
 }
 const $ = cheerio.load(res.text);
 // 解析当前页面,获取当前页面的城市链接地址
 const cityInfoEle = $('.newslist1 li a');
 cityInfoEle.each((idx, element) => {
 const $element = $(element);
 const sceneURL = $element.attr('href'); // 页面地址
 const sceneName = $element.attr('title'); // 城市名称
 if (!sceneName) {
 return;
 }
 logger.info(`当前解析到的目的地是: ${sceneName}, 对应的地址为: ${sceneURL}`);
 getDesInfos(sceneURL, sceneName); // 获取城市详细信息
 ep.after('getDirInfoComplete', cityInfoEle.length, (dirInfos) => {
 const content = JSON.parse(fs.readFileSync(path.join(dirname, './imgs.json')));
 dirInfos.forEach((element) => {
 logger.info(`本条数据为:${JSON.stringify(element)}`);
 Object.assign(content, element);
 });
 fs.writeFileSync(path.join(dirname, './imgs.json'), JSON.stringify(content));
 });
 });
 });