I have trying to download the kaggle dataset by using python. However i was facing issues by using the request method and the downloaded output .csv files is a corrupted html files.
import requests# The direct link to the Kaggle data setdata_url = 'https://www.kaggle.com/crawford/gene-expression/downloads/actual.csv'# The local path where the data set is saved.local_filename = "actsual.csv"# Kaggle Username and Passwordkaggle_info = {'UserName': "myUsername", 'Password': "myPassword"}# Attempts to download the CSV file. Gets rejected because we are not logged in.r = requests.get(data_url)# Login to Kaggle and retrieve the data.r = requests.post(r.url, data = kaggle_info)# Writes the data to a local file one chunk at a time.f = open(local_filename, 'wb')for chunk in r.iter_content(chunk_size = 512 * 1024): # Reads 512KB at a time into memory if chunk: # filter out keep-alive new chunks f.write(chunk)f.close()Output file
<!DOCTYPE html><html><head><title>Gene expression dataset (Golub et al.) | Kaggle</title><meta charset="utf-8" /><meta name="robots" content="index, follow"/><meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, minimum-scale=1.0"> <meta name="theme-color" content="#008ABC" /><link rel="dns-prefetch" href="https://www.google-analytics.com" /><link rel="dns-prefetch" href="https://stats.g.doubleclick.net" /><link rel="dns-prefetch" href="https://js.intercomcdn.com" /><link rel="preload" href="https://az416426.vo.msecnd.net/scripts/a/ai.0.js" as=script /><link rel="dns-prefetch" href="https://kaggle2.blob.core.windows.net" /><link href="/content/v/d420a040e581/kaggle/favicon.ico" rel="shortcut icon" type="image/x-icon" /><link rel="manifest" href="/static/json/manifest.json"><link href="//fonts.googleapis.com/css?family=Open+Sans:400,300,300italic,400italic,600,600italic,700,700italic" rel='stylesheet' type='text/css'><link rel="stylesheet" type="text/css" href="/static/assets/vendor.css?v=72f4ef2ebe4f"/><link rel="stylesheet" type="text/css" href="/static/assets/app.css?v=d997fa977b65"/><script> (function () { var originalError = window.onerror; window.onerror = function (message, url, lineNumber, columnNumber, error) { var handled = originalError && originalError(message, url, lineNumber, columnNumber, error); var blockedByCors = message && message.toLowerCase().indexOf("script error") >= 0; return handled || blockedByCors; }; })();</script><script> var appInsights=window.appInsights||function(config){ function i(config){t[config]=function(){var i=arguments;t.queue.push(function(){t[config].apply(t,i)})}}var t={config:config},u=document,e=window,o="script",s="AuthenticatedUserContext",h="start",c="stop",l="Track",a=l+"Event",v=l+"Page",y=u.createElement(o),r,f;y.src=config.url||"https://az416426.vo.msecnd.net/scripts/a/ai.0.js";u.getElementsByTagName(o)[0].parentNode.appendChild(y);try{t.cookie=u.cookie}catch(p){}for(t.queue=[],t.version="1.0",r=["Event","Exception","Metric","PageView","Trace","Dependency"];r.length;)i("track"+r.pop());return i("set"+s),i("clear"+s),i(h+a),i(c+a),i(h+v),i(c+v),i("flush"),config.disableExceptionTracking||(r="onerror",i("_"+r),f=e[r],e[r]=function(config,i,u,e,o){var s=f&&f(config,i,u,e,o);return s!==!0&&t["_"+r](config,i,u,e,o),s}),t }({ instrumentationKey:"5b3d6014-f021-4304-8366-3cf961d5b90f", disableAjaxTracking: true }); window.appInsights=appInsights; appInsights.trackPageView();</script>