0

我正在使用 Diffbot 分析 API 来检测页面类型，我想要这样的结果

{"stats":{"times": {"docParseTime":0,"docGlobalsTime":0,"fetchAndRenderTime":586,"typeTime":0},"fromCache":true,"types":{"recipe":0,"discussion":0,"audio":0,"error":0,"location":0,"faq":0,"image":0,"job":0,"download":0,"game":0,"product":0,"frontpage":0,"document":1,"article":0,"event":0,"chart":0,"serp":0,"reviewslist":0,"video":0,"profile":0}},"request":{"pageUrl":"http://www.irs.gov/pub/irs-pdf/fw4.pdf","api":"analyze","version":3,"options":["stats"]},"type":"other","objects":[]}

但目前我正在变得这样

{"request":{"pageUrl":"http://static.nfl.com/static/content/public/image/rulebook/pdfs/2013%20-%20Rule%20Book.pdf","api":"analyze","version":3},"type":"other","objects":[]}

我必须在请求中传递“统计”参数。但是在请求的地方，我可以传递这个论点。谢谢，

4

1 回答 1

0

嗨，我知道了，这是解决方案，只需自定义 Diffbot lib 文件或在文件中写入由您决定，这是代码

var diffbot = new Diffbot('xxxxxxxxxxxxxxxxx');
diffbot.analyze({
uri: "http://www.visitcalifornia.in/media/pages/getting_around/maps/ORANGE-COUNTY.pdf",
html: true,
comments: true,
stats: true
}, function(err, response) {
}

这是自定义库代码

Diffbot.prototype.analyze = function (options, callback) {
  for (var i in options) {
   this[i] = options[i];
  }

  var options = this;
  // support 'url'
  if (options.url) {
    options.uri = options.url;
    delete options.url;
  }

  if (!options.uri) {
    throw new Error("the URI is required.");
  }

  var diffbot_url = "http://api.diffbot.com/v3/analyze?token=" + this.token + "&url=" +  encodeURIComponent(options.uri)+"&fields=stats"; 
  if (options.stats) {
     diffbot_url += "&stats=1";
  }

  request({uri: diffbot_url}, function(error, response, body) {
     if (error) {
       callback(error, undefined);
     } else {
      callback(false, JSON.parse(body));
     }
  });
}

它就像魅力一样！

于 2014-10-21T07:00:42.583 回答