簡體   English   中英

使用phantomJS抓取JavaScript網頁

[英]Scraping javascript webpage with phantomJS

我正在嘗試使用phantomJS抓取動態網頁。 以下是我要抓取的代碼和網址。 該代碼可用於其他網址,但該網址始終以空白html文檔的形式返回。 有誰知道如何解決這一問題?

我對javascript不太熟悉,因此這段代碼是從其他地方復制的。 我已將超時時間從2.5s增加到30s,但沒有改變。

var url ='https://www.amazon.com/gp/profile/amzn1.account.AFJ6MBZ5CSY4R6K4USNMQ7JWEQCA/';
var page = new WebPage()
var fs = require('fs');


page.open(url, function (status) {
        just_wait();
});

function just_wait() {
    setTimeout(function() {
            fs.write('page.html', page.content, 'w');
        phantom.exit();
    }, 30000);
}

這就是我解決此類問題的方法。

app.js

var url ='https://www.amazon.com/gp/profile/amzn1.account.AFJ6MBZ5CSY4R6K4USNMQ7JWEQCA/';
var steps=[];
var testindex = 0;
var loadInProgress = false;

//This is set to true when a page is still loading
/*********SETTINGS*********************/
var settings   = require('./settings');
var webPage = require('webpage');
var page = webPage.create();
var fs = require('fs');
page.settings.userAgent = settings.userAgents.desktop;
page.settings.javascriptEnabled = true;
page.settings.loadImages = false;
//Script is much faster with this field set to false
phantom.cookiesEnabled = true;
phantom.javascriptEnabled = true;

page.viewportSize = {
  width: settings.viewport.desktop.width,
  height: settings.viewport.desktop.height
};

/*********SETTINGS END*****************/
console.log('All settings Loaded, Start With Execution');
/**********DEFINE STEPS THAT PHANTOM SHOULD DO***********************/
steps = [
    function(){
      console.log("Step 1 - Load Page => "+url);
      page.open(url, function(status){
        if(status === 'success'){
          console.log('Loaded');
        }else{
          console.log('Error Loading Page. Try Logging In Again');
          phantom.exit(0);
        }
      });
    },
    function(){
      page.render('./test.png');
    },
];

/**********END STEPS THAT PHANTOM SHOULD DO***********************/
interval = setInterval(executeRequestsStepByStep, 3000);
function executeRequestsStepByStep(){
  if(loadInProgress == false && typeof steps[testindex] == "function") {
    steps[testindex]();
    testindex++;
    return;
  }

  if(typeof steps[testindex] != "function") {
    console.log("Quiting");
    fs.write('page.html', page.content, 'w');
    phantom.exit(0);
  }
}
/*
 * These listeners are very important in order to phantom work properly.
 * Using these listeners, we control loadInProgress marker which controls, weather a page is fully loaded.
 * Without this, we will get content of the page, even a page is not fully loaded.
 */

page.onLoadStarted = function() {
    loadInProgress = true;
};
page.onLoadFinished = function() {
    loadInProgress = false;
};
page.onConsoleMessage = function(msg) {
    // console.log(msg);
};

phantom.onError = function(msg, trace) {
  var msgStack = ['PHANTOM ERROR: ' + msg];
  if (trace && trace.length) {
    msgStack.push('TRACE:');
    trace.forEach(function(t) {
      msgStack.push(' -> ' + (t.file || t.sourceURL) + ': ' + t.line + (t.function ? ' (in function ' + t.function +')' : ''));
    });
  }
  console.error(msgStack.join('\n'));
  phantom.exit(1);
};

settings.js

module.exports = {
  viewport: {
    desktop: {
      height: 663,
      width: 1200
    }
  },
  userAgents: {
    desktop: 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.116 Safari/537.36'
  }
};

我已經對此進行了測試,並且效果很好。

暫無
暫無

聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.

 
粵ICP備18138465號  © 2020-2024 STACKOOM.COM