scrapeGoogleImages_file1

scrapeGoogleImages.js

var url ='https://www.google.de/search?q=Yahoo+logo&source=lnms&tbm=isch&sa=X';
   var page = new WebPage()
    var fs = require('fs');

var vWidth = 1080;
var vHeight = 1920; 

page.viewportSize = {
    width: vWidth ,
    height: vHeight 
};

//Scroll throu!
var s = 0;
var sBase = page.evaluate(function () { return document.body.scrollHeight; });
page.scrollPosition = {
    top: sBase,
    left: 0
};

function sc() {
    var sBase2 = page.evaluate(function () { return document.body.scrollHeight; });
    if (sBase2 != sBase) {
        sBase = sBase2;
    }
    if (s> sBase) {
        page.viewportSize = {width: vWidth, height: vHeight};
        return;
    }
    page.scrollPosition = {
        top: s,
        left: 0
    };
    page.viewportSize = {width: vWidth, height: s};
    s += Math.min(sBase/20,400);
    setTimeout(sc, 110);
}

function just_wait() {
    setTimeout(function() {
            fs.write('1.html', page.content, 'w');
            phantom.exit();
    }, 2500);
}

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

scrapeGoogleImages.r

library(plyr)
library(reshape2)
require(rvest)


scrapeJSSite <- function(searchTerm){
  url <- paste0("https://www.google.de/search?q=",searchTerm, "&source=lnms&tbm=isch&sa=X")
  
  lines <- readLines("imageScrape.js")
  lines[1] <- paste0("var url ='", url ,"';")
  writeLines(lines, "imageScrape.js")
  
  ## Download website
  system("phantomjs imageScrape.js")
  
  pg <- read_html("1.html")
  files <- pg %>% html_nodes("img") %>% html_attr("src")
  df <- data.frame(images=files, search=searchTerm)
  return(df)
}


downloadImages <- function(files, brand, outPath="images"){
  for(i in 1:length(files)){
    download.file(files[i], destfile = paste0(outPath, "/", brand, "_", i, ".jpg"), mode = 'wb')
  }
  
}

### exchange the search terms here!
gg <- scrapeJSSite(searchTerm = "Adidas+logo")
downloadImages(as.character(gg$images), i)