【发布时间】:2015-08-09 08:13:47
【问题描述】:
当我解析静态 html 页面时,我的 node.js 应用程序运行良好。但是,当 url 是 JavaScript 生成的页面时,应用程序将无法运行。如何抓取 JavaScript 生成的网页?
我的 app.js
var express = require('express'),
fs = require('fs'),
request = require('request'),
cheerio = require('cheerio'),
app = express();
app.get('/scrape', function( req, res ) {
url = 'http://www.apache.org/';
request( url, function( error, response, html ) {
if( !error ) {
var $ = cheerio.load(html);
var title, release, rating;
var json = { title : "" };
$('body').filter(function() {
var data = $(this);
title = data.find('.panel-title').text();
json.title = title;
})
}
fs.writeFile('output.json', JSON.stringify(json, null, 4), function(err) {
console.log( 'File successfully written! - Check your project directory for the output.json file' );
});
// Finally, we'll just send out a message to the browser reminding you that this app does not have a UI.
res.send( 'Check your console!' );
});
});
app.listen('8081');
console.log('Magic happens on port 8081');
exports = module.exports = app;
【问题讨论】:
标签: javascript node.js express web-scraping cheerio