nodeJs爬虫的技术点总结

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));
   });
  });
 });

function mkdirSync(dirname) {
 if (fs.existsSync(dirname)) {
  return true;
 }
 if (mkdirSync(path.dirname(dirname))) {
  fs.mkdirSync(dirname);
  return true;
 }

 return false;
}

   const content = JSON.parse(fs.readFileSync(path.join(__dirname, './dir.json')));

   dirInfos.forEach((element) => {
    logger.info(`本条数据为:${JSON.stringify(element)}`);
    Object.assign(content, element);
   });

   fs.writeFileSync(path.join(__dirname, './dir.json'), JSON.stringify(content));

const Bagpipe = require('bagpipe');

const bagpipe = new Bagpipe(10);

  bagpipe.push(downloadImage, url, dstpath, (err, data) => {
   if (err) {
    console.log(err);
    return;
   }
   console.log(`[${dstpath}]: ${data}`);
  });

function downloadImage(src, dest, callback) {
 request.head(src, (err, res, body) => {
  if (src && src.indexOf('http') > -1 || src.indexOf('https') > -1) {
   request(src).pipe(fs.createWriteStream(dest)).on('close', () => {
    callback(null, dest);
   });
  }
 });
}

const $ = cheerio.load(buf, { decodeEntities: false });

const reg = /<.*?>/g;