我正在尝试使用以下代码从网站下载csv文件(广告报告)。问题是,它将下载HTML页面而不是csv文件。我无法提供登录后面的URL,但是当您从以下URL下载Firefox时类似的情况
http://www.mozilla.org/en-US/firefox/new/
这是一个GET请求,当我检查元素Network Tab时,get请求被取消。我是Casper的新手,不知道如何处理这些请求。任何帮助将不胜感激
casper.then(function() {
var downloadURL = "";
this.evaluate(function() {
var downloadURL = "http://www.lijit.com"+jQuery("#dailyCSV").attr('href');
});
this.download(downloadURL, '/Users/Ujwal/Downloads/caspertests/stats.csv');
});
响应标题
Age:0
Cache-Control:max-age=0
Connection:keep-alive
Content-Disposition:attachment; filename=stats.csv
Content-Encoding:gzip
Content-Length:1634
Content-Type:text/x-csv
Date:Sat, 05 Oct 2013 15:28:21 GMT
Expires:Sat, 05 Oct 2013 15:28:21 GMT
P3P:CP="CUR ADM OUR NOR STA NID"
Server:PWS/8.0.16
Vary:Accept-Encoding
X-Px:ms h0-s28.p9-jfk ( h0-s62.p9-jfk), ms h0-s62.p9-jfk ( origin>CONN)
答案 0 :(得分:16)
回答了我自己的问题,这是解决方案
参考:https://github.com/knorrium/google-books-downloader/blob/master/gbd.js
//Download the daily csv
casper.then(function() {
this.click('#dailyCSV');
});
casper.on('resource.received', function (resource) {
"use strict";
if ((resource.url.indexOf("publisherCSV/?startDate=") !== -1) ) {
this.echo(resource.url);
var url, file;
url = resource.url;
file = "stats.csv";
try {
this.echo("Attempting to download file " + file);
var fs = require('fs');
casper.download(resource.url, fs.workingDirectory+'/'+file);
} catch (e) {
this.echo(e);
}
}
});