PhantomJS- open page with LocalStorage by default

2019-01-19 21:44发布

问题:

I'm using PhantomJS to get the generated source of a web page after JavaScript DOM manipulations have taken place. This web page has JUST a <body> and nothing else.

Important: This web page uses browser's localStorage to generate the page.

I want to change LocalStorage in PhantomJS before opening the page.

App.js:

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

page.open("https://sample.com")
setTimeout(function(){
    // Where you want to save it    
    page.render("screenshoot.png")  
    // You can access its content using jQuery
    var fbcomments = page.evaluate(function(){
        return $("body").contents().find(".content") 
    }) 
    phantom.exit();
}, 1000)

回答1:

localStorage for a particular domain is only available when you open a page on that domain. You can

  1. open some URL on the domain you're interested in,
  2. change localStorage according to your needs,
  3. open your target URL on the same domain.

This can look like this:

page.open("https://sample.com/asdfasdf", function(){
    page.evaluate(function(){
        localStorage.setItem("something", "whatever");
    });

    page.open("https://sample.com", function(){
        setTimeout(function(){
            // Where you want to save it    
            page.render("screenshoot.png")  
            // You can access its content using jQuery
            var fbcomments = page.evaluate(function(){
                return $("body").contents().find(".content") 
            }) 
            phantom.exit();
        },1000)
    });    
});

It's also possible not to open a full page in step 1. You can also use dummy page with some URL.

page.setContent("", "https://sample.com"); // doesn't actually open any page

page.evaluate(function(){
    localStorage.setItem("something", "whatever");
});

page.open("https://sample.com", function(){
    setTimeout(function(){
        // Where you want to save it    
        page.render("screenshoot.png")  
        // You can access its content using jQuery
        var fbcomments = page.evaluate(function(){
            return $("body").contents().find(".content") 
        }) 
        phantom.exit();
    }, 1000)
});    


回答2:

I solved my problem with Friend's Help. My solution is:

Notice: I set Timeout 10000(10 seconds) for complete load page.

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

page.open("https://sample.com", function(){
    page.evaluate(function(){
        var i = 0,
        oJson = jsonData,
        sKey;
        localStorage.clear();

        for (; sKey = Object.keys(oJson)[i]; i++) {
            localStorage.setItem(sKey,oJson[sKey])
        }
    });

    page.open("https://sample.com", function(){
        setTimeout(function(){
         page.render("screenshoot.png") 
            // Where you want to save it    
           console.log(page.content); //page source
            // You can access its content using jQuery
            var fbcomments = page.evaluate(function(){
                return $("body").contents().find(".content") 
            }) 
            phantom.exit();
        },10000)
    });    
});