Trying to GET from api after posting API issues

2019-06-07 12:00发布

问题:

Hi developers I am back again with a question,

I am trying to get some data from this website https://www.iamsterdam.com/nl/uit-in-amsterdam/uit/agenda. First did I crawl the website but when doing that it came to mind that they have a api and that will be a lot faster. So I tried to get the data from the api I tried this:

get-website.js:

var webPage = require('webpage');
var page = webPage.create();
var settings = {
  operation: "POST",
  encoding: "utf8",
  headers: {
    "Content-Type": "application/json"
  },
  data: JSON.stringify({
    DateFilter: 03112016,
    PageId: "3418a37d-b907-4c80-9d67-9fec68d96568",
    Take: 2,
    Skip: 12,
    ViewMode: 1
  })
};

page.open('https://www.iamsterdam.com/api/AgendaApi/', settings, function(status) {
  console.log(page.content);
  phantom.exit();
});

get-website.php

$phantom_script= 'get-website.js'; 

$response =  exec ('phantomjs ' . $phantom_script);

echo  $response;

But what I get back doesn't look good:

Message":"An error has occurred.","ExceptionMessage":"Page could not be found","ExceptionType":"System.ApplicationException","StackTrace":" at Axendo.SC.AM.Iamsterdam.Controllers.Api.AgendaApiController.GetResultsInternal(RequestModel requestModel)\r\n at lambda_method(Closure , Object , Object[] )\r\n
etc.

Here is a picture of firebug:

I hope someone can help me.

回答1:

Interesting question. I was a bit surprised that the site would honor AJAX-request in a browser and even in cURL, but not in PhantomJS. In such cases you have to study and replicate request very carefully, because one of little details probably greatly affects the server's response.

Turned out, it was a cookie and form content-type that had to be set accordingly.

var webPage = require('webpage');
var page = webPage.create();

// courtesy of http://stackoverflow.com/a/1714899/2715393
var serialize = function(obj) {
  var str = [];
  for(var p in obj)
    if (obj.hasOwnProperty(p)) {
      str.push(encodeURIComponent(p) + "=" + encodeURIComponent(obj[p]));
    }
  return str.join("&");
}

var settings = {
    operation: "POST",
    encoding: "utf8",
    headers: {
        "accept-encoding" : "identity", // https://github.com/ariya/phantomjs/issues/10930#issuecomment-81541618
        "x-requested-with" : "XMLHttpRequest",
        "accept-language" : "en;q=0.8,en-US;q=0.6",
        "authority" : "www.iamsterdam.com",
        "accept":"application/json, text/javascript, */*; q=0.01",
        "content-type" : "application/x-www-form-urlencoded; charset=UTF-8",
        "cookie" : "website#lang=nl"        
    },
    data: serialize({
        Genre: '',
        DateFilter: '03112016',
        DayPart: '',
        SearchTerm: '', 
        Neighbourhoud: '',
        DayRange: '',
        ViewMode: 1, 
        LastMinuteTickets : '',
        PageId: '3418a37d-b907-4c80-9d67-9fec68d96568',
        Skip: 0,
        Take: 12
    }) 
};

page.open('https://www.iamsterdam.com/api/AgendaApi/', settings, function(status) {
    console.log(page.content);
    phantom.exit();
});