Scrape Website Url From Tripadvisor.co.uk

[allcapone1912 7]

hi,

can not get website url from tripadvisor.co.uk

 

For ex:

http://www.tripadvisor.co.uk/Restaurant_Review-g1016887-d1847312-Reviews-Wild_Boar_Restaurant_at_Sitwell_Arms_Hotel-Renishaw_Derbyshire_England.html

 

As results should be "http://www.sitwellarms.com/restaurant.html#_=_"

 

I dont see url in site code

[pftg4 102]

there is a parameter $url does that not work???

[allcapone1912 7]

i dont want to get current url,i need to get company website

http://s28.postimg.org/4x7zzt2gt/Untitled.png

[pash 504]

Try.

allow popups("In New Window")
navigate("http://www.tripadvisor.co.uk/Restaurant_Review-g1016887-d1847312-Reviews-Wild_Boar_Restaurant_at_Sitwell_Arms_Hotel-Renishaw_Derbyshire_England.html","Wait")
wait for browser event("Everything Loaded","")
wait(1)
click(<onclick=w"*\', \'isAsdf\':true\})">,"Left Click","No")
wait(4)
in popup {
    alert($url)
    close page
}

[deliter 203]

I found finding by that button too difficult,but for the email link,it shows the email address in the document text,so you can just modify the email address,

excuse my regex,I am awful at regex,maybe if this method doesn't return a result than use Pash's method above for a definite result

 

set(#yrd,$document text,"Global")
set(#find regular,$find regular expression(#yrd,"\\.checkEmailAction\',event,this,\'.+?@.+?\'"),"Global")
set(#result,$replace regular expression($find regular expression(#find regular,"\'.+?@.+?\'$"),"\',event,this,",""),"Global")
set(#result,"http://www.{$replace regular expression($find regular expression(#result,"@.+"),"@|\'","")}","Global")

[Pete 121]

Or go mobile

 

clear cookies
set user agent("Android")
navigate("http://www.tripadvisor.co.uk/Restaurant_Review-g1016887-d1847312-Reviews-Wild_Boar_Restaurant_at_Sitwell_Arms_Hotel-Renishaw_Derbyshire_England.html","Wait")
wait for element(<class="close_button">,300,"Appear")
click(<class="close_button">,"Left Click","No")
click(<class=" noDivider ">,"Left Click","No")
alert($url)

[allcapone1912 7]

Thanks everyone for help

[allcapone1912 7]

 

Try.

allow popups("In New Window")
navigate("http://www.tripadvisor.co.uk/Restaurant_Review-g1016887-d1847312-Reviews-Wild_Boar_Restaurant_at_Sitwell_Arms_Hotel-Renishaw_Derbyshire_England.html","Wait")
wait for browser event("Everything Loaded","")
wait(1)
click(<onclick=w"*\', \'isAsdf\':true\})">,"Left Click","No")
wait(4)
in popup {
    alert($url)
    close page
}

great,

finally its work

interesting method

[allcapone1912 7]

I found finding by that button too difficult,but for the email link,it shows the email address in the document text,so you can just modify the email address,

excuse my regex,I am awful at regex,maybe if this method doesn't return a result than use Pash's method above for a definite result

 

set(#yrd,$document text,"Global")

set(#find regular,$find regular expression(#yrd,"\\.checkEmailAction\',event,this,\'.+?@.+?\'"),"Global")

set(#result,$replace regular expression($find regular expression(#find regular,"\'.+?@.+?\'$"),"\',event,this,",""),"Global")

set(#result,"http://www.{$replace regular expression($find regular expression(#result,"@.+"),"@|\'","")}","Global")

i've used this method in past and not always get the right url,sometime email have free domain(yahoo.gmail or other domain that not match url)

[allcapone1912 7]

Or go mobile

 

clear cookies

set user agent("Android")

navigate("http://www.tripadvisor.co.uk/Restaurant_Review-g1016887-d1847312-Reviews-Wild_Boar_Restaurant_at_Sitwell_Arms_Hotel-Renishaw_Derbyshire_England.html","Wait")

wait for element(<class="close_button">,300,"Appear")

click(<class="close_button">,"Left Click","No")

click(<class=" noDivider ">,"Left Click","No")

alert($url)

thanks for your code

good idea to go mobile

[deliter 203]

Hey

 

A very helpful man I got to know on the internet,had a look at this topic and posted me the solution,which is pure JS,so you might be like me and not really know what it is happening here,but its nice to have an idea,the href variable is my code,thats why it looks a bit worse than the rest ha

 

sorry I posted it but it wouldn'twork,maybe parsing it to the page

 

make a set set(#url,$eval(""),"Global")

 

and go to node view,and paste this code below into the eval

var href = document.querySelectorAll("span.taLnk.hvrIE6")
var href = href[0].onclick.toString().match(/{'aHref':'.+?'/).toString().split("{'aHref':'").join("").split("'").join("")

var url =  decodeURIComponent( asdf(href) );
console.log( url );
url = url.replace(/__5F____5F__(..)__5F____5F__/g,"%\$1");
console.log( url );
url = decodeURIComponent( url );
console.log( url );
url = url.replace(/.*a_url\.(.*?)-a_url.*/,"\$1");
console.log( url );

function getOffset(a) {
    if (a >= 97 && a <= 122) {
        return a - 61
    }
    if (a >= 65 && a <= 90) {
        return a - 55
    }
    if (a >= 48 && a <= 71) {
        return a - 48
    }
    return -1
}
function asdf(d) {
    var h = {"": ["&", "=", "p", "6", "?", "H", "%", "B", ".com", "k", "9", ".html", "n", "M", "r", "www.", "h", "b", "t", "a", "0", "/", "d", "O", "j", "http://", "_", "L", "i", "f", "1", "e", "-", "2", ".", "N", "m", "A", "l", "4", "R", "C", "y", "S", "o", "+", "7", "I", "3", "c", "5", "u", 0, "T", "v", "s", "w", "8", "P", 0, "g", 0],q: [0, "__3F__", 0, "Photos", 0, "https://", ".edu", "*", "Y", ">", 0, 0, 0, 0, 0, 0, "`", "__2D__", "X", "<", "slot", 0, "ShowUrl", "Owners", 0, "[", "q", 0, "MemberProfile", 0, "ShowUserReviews", '"', "Hotel", 0, 0, "Expedia", "Vacation", "Discount", 0, "UserReview", "Thumbnail", 0, "__2F__", "Inspiration", "V", "Map", ":", "@", 0, "F", "help", 0, 0, "Rental", 0, "Picture", 0, 0, 0, "hotels", 0, "ftp://"],x: [0, 0, "J", 0, 0, "Z", 0, 0, 0, ";", 0, "Text", 0, "(", "x", "GenericAds", "U", 0, "careers", 0, 0, 0, "D", 0, "members", "Search", 0, 0, 0, "Post", 0, 0, 0, "Q", 0, "$", 0, "K", 0, "W", 0, "Reviews", 0, ",", "__2E__", 0, 0, 0, 0, 0, 0, 0, "{", "}", 0, "Cheap", ")", 0, 0, 0, "#", ".org"],z: [0, "Hotels", 0, 0, "Icon", 0, 0, 0, 0, ".net", 0, 0, "z", 0, 0, "pages", 0, "geo", 0, 0, 0, "cnt", "~", 0, 0, "]", "|", 0, "tripadvisor", "Images", "BookingBuddy", 0, "Commerce", 0, 0, "partnerKey", 0, "area", 0, "Deals", "from", "\\", 0, "urlKey", 0, "'", 0, "WeatherUnderground", 0, "MemberSign", "Maps", 0, "matchID", "Packages", "E", "Amenities", "Travel", ".htm", 0, "!", "^", "G"]};
    var b = "";
    for (var a = 0; a < d.length; a++) {
        var j = d.charAt(a);
        var f = j;
        if (h[j] && a + 1 < d.length) {
            a++;
            f += d.charAt(a)
        } else {
            j = ""
        }
        var g = getOffset(d.charCodeAt(a));
        if (g < 0 || typeof h[j][g] == "String") {
            b += f
        } else {
            b += h[j][g]
        }
    }
    return b
}
url