Node爬虫

• 使用cheerio爬虫模块
  抓取页面后获取元素信息跟jQuery基本一样

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

/**
 * @method 提取起点此资源信息
 * @param id 小说id(从列表页爬取到的)
 * @returns {Function}
 */
seachInfo(id) {
    return function (cb) {
        co(function* () {
            let result = yield Util.req.sendReq('http://book.qidian.com/info/' + id, 'GET', '', 'crawler');// 发送请求的工具类
            let $ = cheerio.load(result, {decodeEntities: false}); //采用cheerio模块解析html
            let novels = {};
            novels.img = $(".book-information .book-img img").attr('src');
            novels.name = $(".book-information .book-info h1 em").html();
            novels.author = $(".book-information .book-info .writer").html();
            let wordsNum = $(".book-information .book-info p em").eq(0).html();
            novels.wordsNum = parseInt(wordsNum) * 10000;
            novels.summary = $('.book-intro p').text();
            cb(null, novels);
        }).catch(function (err) {
            cb(new Error(err.message), null);
        })
    }
}