node实现的爬虫功能示例

var http = require("http");
var url = "http://www.cnblogs.com";
http.get(url, function (res) {
  var html = "";
  res.on("data", function (data) {
    html += data;
  });
  res.on("end", function () {
    console.log(html);
  });
}).on("error", function () {
  console.log("获取课程结果错误！");
});

cnpm install cheerio --save-dev

var http = require("http");
var cheerio = require("cheerio");
var url = "http://www.cnblogs.com";
function filterData(html) {
  var $ = cheerio.load(html); 
  var items = $(".post_item");
  var result = [];
  items.each(function (item) {
    var tit = $(this).find(".titlelnk").text();
    var aut = $(this).find(".lightblue").text();
    var one = {
      title: tit,
      author: aut
    };
    result.push(one);
  });
  return result;
}
function printInfos(allInfos) {
  allInfos.forEach(function (item) {
    console.log("文章题目 " + item["title"] + '\n' + "文章作者 " + item["author"] + '\n'+ '\n');
  });
}
http.get(url, function (res) {
  var html = "";
  res.on("data", function (data) {
    html += data;
  });
  res.on("end", function (data) {
    var allInfos = filterData(html);
    printInfos(allInfos);
  });
}).on("error", function () {
  console.log("爬取博客园首页失败")
});