Question

使用casperjs后，当我启动此代码时：

var casper = require('casper').create();
var url = 'https://www.youtube.com/robots.txt';

casper.start(url, function() {
    var js = this.evaluate(function() {
        return document; 
    }); 
    this.echo(js.all[0].innerHTML); 
});
casper.run();

而不是得到这个：

# robots.txt file for YouTube
# Created in the distant future (the year 2000) after
# the robotic uprising of the mid 90's which wiped out all humans.

User-agent: Mediapartners-Google*
Disallow:

User-agent: *
Disallow: /bulletin
Disallow: /comment
Disallow: /forgot
Disallow: /get_video
Disallow: /get_video_info
Disallow: /login
Disallow: /results
Disallow: /signup
Disallow: /t/terms
Disallow: /t/privacy
Disallow: /verify_age
Disallow: /videos
Disallow: /watch_ajax
Disallow: /watch_popup
Disallow: /watch_queue_ajax

我得到了这个结果：

<head></head><body><pre style="word-wrap: break-word; white-space: pre-wrap;"># robots.txt file for YouTube
# Created in the distant future (the year 2000) after
# the robotic uprising of the mid 90's which wiped out all humans.

User-agent: Mediapartners-Google*
Disallow:

User-agent: *
Disallow: /bulletin
Disallow: /comment
Disallow: /forgot
Disallow: /get_video
Disallow: /get_video_info
Disallow: /login
Disallow: /results
Disallow: /signup
Disallow: /t/terms
Disallow: /t/privacy
Disallow: /verify_age
Disallow: /videos
Disallow: /watch_ajax
Disallow: /watch_popup
Disallow: /watch_queue_ajax
</pre></body>

似乎casperjs正在添加html标签。如何将纯文本文件完全作为源文件获取？

Answer 1

download功能怎么样？

脚本成为

var casper = require('casper').create();
var url = 'https://www.youtube.com/robots.txt';

casper.start(url, function() {
     this.download(url, 'robots.txt'); 
});
casper.run();

<强>更新

如果要将远程文件内容存储到字符串中，请使用base64encode

var casper = require('casper').create();
var url = 'https://www.youtube.com/robots.txt';
var contents;
casper.start(url, function() {
    contents = atob(this.base64encode(url));
    console.log(contents);
});

casper.run();

使用casperjs检索远程txt文件的内容，不带html标记

1 个答案: