废话不多说,直接给大家贴node.js抓取html页面内容的核心代码了。
具体代码如下所示:
var http = require("http");
var iconv = require('iconv-lite');
var option = {
hostname: "stockdata.stock.hexun.com",
path: "/gszl/s601398.shtml"
};
var req = http.request(option, function(res) {
res.on("data", function(chunk) {
console.log(iconv.decode(chunk, "gbk"));
});
}).on("error", function(e) {
console.log(e.message);
});
req.end();
下面再看下面一种nodejs抓取网页内容
function loadPage(url) {
var http = require('http');
var pm = new Promise(function (resolve, reject) {
http.get(url, function (res) {
var html = '';
res.on('data', function (d) {
html += d.toString()
});
res.on('end', function () {
resolve(html);
});
}).on('error', function (e) {
reject(e)
});
});
return pm;
}
loadPage('http://www.baidu.com').then(function (d) {
console.log(d);
});