web scraping BS4 table located but empty findall [duplicate] - python

This question already has an answer here:
HTML tag appears empty when parsing it with BeautifulSoup but has content when opened in browser
(1 answer)
Closed 2 years ago.
I am trying to scrape a table from a website:
After importing the url
print(soup.prettify())
<!DOCTYPE html>
<html lang="en">
<head>
<meta content="noindex" name="robots"/>
<meta charset="utf-8"/>
<meta content="width=device-width,initial-scale=1,shrink-to-fit=no" name="viewport"/>
<link href="https://d9mzsvqupf0ma.cloudfront.net/0367505b9e/static/react/favicon.ico" rel="shortcut icon"/>
<title>
Reonomy
</title>
<script src="/static/react/env.js?1592498512097">
</script>
<script onerror='console.error("Error loading Google Maps. Please check your firewall, proxy, or ad blocker settings.")' src="//maps.googleapis.com/maps/api/js?v=3&libraries=places,drawing,geometry&client=gme-scryerinc">
</script>
<script type="text/javascript">
!function(){if(void 0!==window.env&&"production"===window.env.REACT_APP_ENVIRONMENT){var i=window.analytics=window.analytics||[];if(!i.initialize)if(i.invoked)window.console&&console.error&&console.error("Segment snippet included twice.");else{i.invoked=!0,i.methods=["trackSubmit","trackClick","trackLink","trackForm","pageview","identify","reset","group","track","ready","alias","debug","page","once","off","on"],i.factory=function(t){return function(){var e=Array.prototype.slice.call(arguments);return e.unshift(t),i.push(e),i}};for(var e=0;e<i.methods.length;e++){var t=i.methods[e];i[t]=i.factory(t)}i.load=function(e,t){var n=document.createElement("script");n.type="text/javascript",n.async=!0,n.src="https://cdn.segment.com/analytics.js/v1/"+e+"/analytics.min.js";var o=document.getElementsByTagName("script")[0];o.parentNode.insertBefore(n,o),i._loadOptions=t},i.SNIPPET_VERSION="4.1.0",i.load("Jb0xYxcgY3BJTcGWoAmtUP9qwhM9V2pp")}}}()
</script>
<link href="https://d9mzsvqupf0ma.cloudfront.net/0367505b9e/static/react/static/css/main.4f4bf592.chunk.css" rel="stylesheet"/>
</head>
<body>
<noscript>
You need to enable JavaScript to run this app.
</noscript>
<div id="root">
</div>
<script>
!function(d){function e(e){for(var t,r,n=e[0],c=e[1],o=e[2],a=0,f=[];a<n.length;a++)r=n[a],Object.prototype.hasOwnProperty.call(s,r)&&s[r]&&f.push(s[r][0]),s[r]=0;for(t in c)Object.prototype.hasOwnProperty.call(c,t)&&(d[t]=c[t]);for(h&&h(e);f.length;)f.shift()();return i.push.apply(i,o||[]),u()}function u(){for(var e,t=0;t<i.length;t++){for(var r=i[t],n=!0,c=1;c<r.length;c++){var o=r[c];0!==s[o]&&(n=!1)}n&&(i.splice(t--,1),e=p(p.s=r[0]))}return e}var r={},l={5:0},s={5:0},i=[];function p(e){if(r[e])return r[e].exports;var t=r[e]={i:e,l:!1,exports:{}};return d[e].call(t.exports,t,t.exports,p),t.l=!0,t.exports}p.e=function(i){var e=[];l[i]?e.push(l[i]):0!==l[i]&&{20:1,21:1,24:1,25:1}[i]&&e.push(l[i]=new Promise(function(e,n){for(var t="static/css/"+({}[i]||i)+"."+{0:"31d6cfe0",1:"31d6cfe0",2:"31d6cfe0",3:"31d6cfe0",7:"31d6cfe0",8:"31d6cfe0",9:"31d6cfe0",10:"31d6cfe0",11:"31d6cfe0",12:"31d6cfe0",13:"31d6cfe0",14:"31d6cfe0",15:"31d6cfe0",16:"31d6cfe0",17:"31d6cfe0",18:"31d6cfe0",19:"31d6cfe0",20:"7bbd82a1",21:"989321a7",22:"31d6cfe0",23:"31d6cfe0",24:"d608a43c",25:"36cb7054",26:"31d6cfe0",27:"31d6cfe0",28:"31d6cfe0",29:"31d6cfe0",30:"31d6cfe0",31:"31d6cfe0",32:"31d6cfe0"}[i]+".chunk.css",c=p.p+t,r=document.getElementsByTagName("link"),o=0;o<r.length;o++){var a=(d=r[o]).getAttribute("data-href")||d.getAttribute("href");if("stylesheet"===d.rel&&(a===t||a===c))return e()}var f=document.getElementsByTagName("style");for(o=0;o<f.length;o++){var d;if((a=(d=f[o]).getAttribute("data-href"))===t||a===c)return e()}var u=document.createElement("link");u.rel="stylesheet",u.type="text/css",u.onload=e,u.onerror=function(e){var t=e&&e.target&&e.target.src||c,r=new Error("Loading CSS chunk "+i+" failed.\n("+t+")");r.code="CSS_CHUNK_LOAD_FAILED",r.request=t,delete l[i],u.parentNode.removeChild(u),n(r)},u.href=c,document.getElementsByTagName("head")[0].appendChild(u)}).then(function(){l[i]=0}));var r=s[i];if(0!==r)if(r)e.push(r[2]);else{var t=new Promise(function(e,t){r=s[i]=[e,t]});e.push(r[2]=t);var n,c=document.createElement("script");c.charset="utf-8",c.timeout=120,p.nc&&c.setAttribute("nonce",p.nc),c.src=p.p+"static/js/"+({}[i]||i)+"."+{0:"ca0cfe7f",1:"1f775947",2:"f3aa526c",3:"8e92118a",7:"8821eefa",8:"e17401b1",9:"6e4ba317",10:"24f1a107",11:"96c5e7b8",12:"7a6ef661",13:"e539811a",14:"37c1ffc4",15:"dc8d4356",16:"2d61de04",17:"23eefbbb",18:"51a9cf50",19:"7f8a5cf4",20:"c409a0e9",21:"00e0dc95",22:"de275a36",23:"114fe889",24:"a1c29240",25:"b1426e77",26:"2eaf037b",27:"cf150351",28:"ac391d82",29:"b2c0bc67",30:"4b510904",31:"5a5b63b1",32:"f8a3d31f"}[i]+".chunk.js";var o=new Error;n=function(e){c.onerror=c.onload=null,clearTimeout(a);var t=s[i];if(0!==t){if(t){var r=e&&("load"===e.type?"missing":e.type),n=e&&e.target&&e.target.src;o.message="Loading chunk "+i+" failed.\n("+r+": "+n+")",o.name="ChunkLoadError",o.type=r,o.request=n,t[1](o)}s[i]=void 0}};var a=setTimeout(function(){n({type:"timeout",target:c})},12e4);c.onerror=c.onload=n,document.head.appendChild(c)}return Promise.all(e)},p.m=d,p.c=r,p.d=function(e,t,r){p.o(e,t)||Object.defineProperty(e,t,{enumerable:!0,get:r})},p.r=function(e){"undefined"!=typeof Symbol&&Symbol.toStringTag&&Object.defineProperty(e,Symbol.toStringTag,{value:"Module"}),Object.defineProperty(e,"__esModule",{value:!0})},p.t=function(t,e){if(1&e&&(t=p(t)),8&e)return t;if(4&e&&"object"==typeof t&&t&&t.__esModule)return t;var r=Object.create(null);if(p.r(r),Object.defineProperty(r,"default",{enumerable:!0,value:t}),2&e&&"string"!=typeof t)for(var n in t)p.d(r,n,function(e){return t[e]}.bind(null,n));return r},p.n=function(e){var t=e&&e.__esModule?function(){return e.default}:function(){return e};return p.d(t,"a",t),t},p.o=function(e,t){return Object.prototype.hasOwnProperty.call(e,t)},p.p="https://d9mzsvqupf0ma.cloudfront.net/0367505b9e/static/react/",p.oe=function(e){throw console.error(e),e};var t=this.webpackJsonpfrontend=this.webpackJsonpfrontend||[],n=t.push.bind(t);t.push=e,t=t.slice();for(var c=0;c<t.length;c++)e(t[c]);var h=n;u()}([])
</script>
<script src="https://d9mzsvqupf0ma.cloudfront.net/0367505b9e/static/react/static/js/6.41e506b7.chunk.js">
</script>
<script src="https://d9mzsvqupf0ma.cloudfront.net/0367505b9e/static/react/static/js/main.e68cecb8.chunk.js">
</script>
</body>
</html>
When I inspect the website, I see that my table is there between tags:
Still when I use :
print(soup.find_all('td'))
It returns me an empty list. Can someone point out what I did wrong ?


Beautifulsoup, doesn't evaluate javascript.
It looks like all those tables are being generated by Javascript. You could use dryscape to evaluate the page before passing it on to beautiful soup.

Related

Splash not parse JS before returning HTML response

in my crawler consisting of Scrapy and a Splash server I am having problems on this site: https://www.lavoropiu.it/offerte
The problem is related to Splash downloading the site's HTML without parsed JS. The site is an Angular app.
I have tried with different splash settings:
splash.private_mode_enabled = false
splash.js_enabled = true
The returned HTML is this:
<!DOCTYPE html><html lang="en"><head>
<meta charset="utf-8">
<title>Lavoropiu</title>
<base href="/">
<meta name="viewport" content="width=device-width, initial-scale=1">
<link rel="icon" type="image/x-icon" href="favicon.ico">
<link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/chphsalvo/front-end-framework#0.9.3/dist/css/style.min.css">
<!-- Global site tag (gtag.js) - Google Analytics -->
<script type="text/javascript" async="" src="https://www.google- analytics.com/analytics.js"></script><script async="" src="https://www.googletagmanager.com/gtag/js?id=UA-173597693-1"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag(){dataLayer.push(arguments);}
gtag('js', new Date());
gtag('config', 'UA-173597693-1', { send_page_view: false});
</script>
<link rel="stylesheet" href="styles.66ab468982a30141059e.css">
</head>
<body>
<script src="runtime.d6c52737d4587c65265f.js" defer=""></script>
<script src="polyfills.f782e0cdb7e1242a13e4.js" defer=""></script>
<script src="vendor.82696fd86eeed5072685.js" defer=""></script>
<script src="main.076dbf684e565ed2798b.js" defer=""></script>
<app-root></app-root>
</body>
</html>
As you can see Splash does not execute the scripts on the page before returning the HTML.
Is this an issue related with Splash or I am missing some setting?
Thanks for your help.

Splash fails to load the javascript. This is a common problem encountered when doing scraping with Splash. Check the issue page of Splash and do some searching, there's a lot report about the javascript loading problem.
The default engine for Splash is Webkit. It behaves differently with common Web browser engines in Chrome, Firefox. For web scraping, you'd better choose headless Chrome to download pages with javascript.
For async integration with scrapy, try playwright, or puppeteer. The former has a scrapy plugin scrapy-playwright, which is currently maintained.
Update: Scrapy API render.html has support for switching engine to "chromium". But it's experimental. You can have a try.

Download PDF with chrome plugin in python selenium

I'm trying to extract a PDF from this site that uses the native Google Chrome pdf viewer tool to open the pdf in the first place, it's content type is /application/pdf. The issue is that the site URLs that I get aren't actually links to the PDF but rather to a .zul site where the js will load the pdf, or fetch it.
Here's my download code below:
def download_pdf(url, idx, save_dir):
options = webdriver.ChromeOptions()
profile = {"plugins.plugins_list": [{"enabled":False,"name":"Chrome PDF Viewer"}],
"download.default_directory" : save_dir}
options.add_experimental_option("prefs",profile)
driver = webdriver.Chrome("/usr/lib/chromium-browser/chromedriver", chrome_options=options)
driver.get(url)
The problem that Im encountering with the above code is that I get the following readout from driver.source_page:
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta http-equiv="Pragma" content="no-cache" />
<meta http-equiv="Expires" content="-1" />
<title>Document Viewer</title>
<link rel="stylesheet" type="text/css" href="/eSMARTContracts/zkau/web/9776a7f0/zul/css/zk.wcs;jsessionid=088DC94ECA6804AF717A0E997E4F1444.node1"/>
<script type="text/javascript" src="/eSMARTContracts/zkau/web/9776a7f0/js/zk.wpd;jsessionid=088DC94ECA6804AF717A0E997E4F1444.node1" charset="UTF-8">
</script>
<script type="text/javascript" src="/eSMARTContracts/zkau/web/9776a7f0/js/zul.lang.wpd;jsessionid=088DC94ECA6804AF717A0E997E4F1444.node1" charset="UTF-8">
</script>
<!-- ZK 6.0.2 EE 2012072410 -->
</head>
<body>
<div id="j4AP_" class="z-temp"></div>
<script class="z-runonce" type="text/javascript">zk.pi=1;zkmx(
[0,'j4AP_',{dt:'z_2m1',cu:'/eSMARTContracts;jsessionid=088DC94ECA6804AF717A0E997E4F1444.node1',uu:'/eSMARTContracts/zkau;jsessionid=088DC94ECA6804AF717A0E997E4F1444.node1',ru:'/service/dpsweb/ViewDPSWeb.zul'},[
['zul.wnd.Window','j4AP0',{$$onSize:false,$$onMaximize:false,$$onOpen:false,$$onMinimize:false,$$onZIndex:false,$onClose:true,$$onMove:false,width:'100%',height:'100%',prolog:'\
'},[]]]]);
</script>
<noscript>
<div class="noscript"><p>Sorry, JavaScript must be enabled.<br/>Change your browser options, then try again.</p></div>
</noscript>
</body>
</html>
EDIT: Included the link

how to copy all the code of a URL with python

I want to copy all the code of an URL (http://modelseed.org/biochem/reactions/rxn00001) using Python 3.6, but I can only copy part of the code, and I don't know why.
So far, I tried with "requests" module
import requests
page = requests.get("http://modelseed.org/biochem/reactions/rxn00001")
print(page.content)
and "urllib"
import urllib.request
site = urllib.request.urlopen("http://modelseed.org/biochem/reactions/rxn00001")
print(site.read())
The part of the code with information of the "Reaction Details", like "Name", "ID" and "Abbreviation" are missing, but they are visible if I inspect the code on the developer bar of Chrome.
The code I'm able to download using the two codes above is:
<!DOCTYPE html>
<html lang="en" ng-app="ModelSEED">
<head>
<base href="/"/>
<meta content="text/html; charset=utf-8" http-equiv="Content-Type"/>
<meta content="IE=edge" http-equiv="X-UA-Compatible"/>
<meta content="initial-scale=1, maximum-scale=1, user-scalable=no" name="viewport">
<meta content="The ModelSEED is a resource for the reconstruction, exploration, comparison, and analysis of metabolic models." name="description"/>
<link href="/img/ModelSEED-favicon.png?v=2.0" rel="shortcut icon"/>
<meta content="nconrad" name="author"/>
<title>
ModelSEED
</title>
<link href="components/angular-material/angular-material.css" rel="stylesheet"/>
<link href="components/bootstrap/dist/css/bootstrap.min.css" rel="stylesheet"/>
<!-- to be removed -->
<link href="components/font-awesome/css/font-awesome.min.css" rel="stylesheet"/>
<link href="icomoon/style.css" rel="stylesheet"/>
<link href="https://fonts.googleapis.com/icon?family=Material+Icons" rel="stylesheet"/>
<link href="http://fonts.googleapis.com/css?family=Montserrat:400,700" rel="stylesheet" type="text/css"/>
<link href="build/style.css" rel="stylesheet"/>
<!--<script src="https://cdn.socket.io/socket.io-1.3.7.js"></script>-->
<script src="build/site.js">
</script>
<!-- HTML5 Shim and Respond.js IE8 support of HTML5 elements and media queries -->
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
<!--[if lt IE 9]>
<script src="https://oss.maxcdn.com/libs/html5shiv/3.7.0/html5shiv.js"></script>
<script src="https://oss.maxcdn.com/libs/respond.js/1.4.2/respond.min.js"></script>
<![endif]-->
</meta>
</head>
<body>
<div style="height: 100%;" ui-view="">
</div>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
})(window,document,'script','//www.google-analytics.com/analytics.js','ga');
ga('create', 'UA-67412611-1', 'auto');
ga('send', 'pageview');
</script>
</body>
</html>
Anyone has any hint why the code between < div style="height: 100%;" ui-view="" > and (just after < body > and before < script >) is not downloaded?
Thank you.

It's being inserted by a javascript script, therefore, either requests nor urllib would find it, you would need to use a browser for this, you should try with selenium or PhantomJS
something like:
from selenium import webdriver
driver = webdriver.Chrome('./chromedriver')
driver.get(url)
driver.page_source

Try getting this url instead: https://www.patricbrc.org/api/model_reaction/?http_accept=application/json&eq(id,rxn00001)

Python scraping of dynamic content (visual different from html source code)

I'm a big fan of stackoverflow and typically find solutions to my problems through this website. However, the following problem has bothered me for so long that it forced me to create an account here and ask directly:
I'm trying to scape this link: https://permid.org/1-21475776041 What i want is the row "TRCS Asset Class" and "Currency".
For starters, I'm using this code:
from bs4 import BeautifulSoup
import urllib2
url = 'https://permid.org/1-21475776041'
req = urllib2.urlopen(url)
raw = req.read()
soup = BeautifulSoup(raw)
print soup.prettify()
The html code returned (see below) is different from what you can see in your browser upon clicking the link:
<!DOCTYPE html>
<!--[if lt IE 7]> <html ng-app="tmsMdaasApp" class="no-js lt-ie9 lt-ie8 lt-ie7"> <![endif]-->
<!--[if IE 7]> <html ng-app="tmsMdaasApp" class="no-js lt-ie9 lt-ie8"> <![endif]-->
<!--[if IE 8]> <html ng-app="tmsMdaasApp" class="no-js lt-ie9"> <![endif]-->
<!--[if gt IE 8]><!-->
<html class="no-js" ng-app="tmsMdaasApp">
<!--<![endif]-->
<head>
<meta content="text/html; charset=utf-8" http-equiv="content-type"/>
<meta charset="utf-8"/>
<meta content="ie=edge" http-equiv="x-ua-compatible"/>
<meta content="max-age=0,no-cache" http-equiv="Cache-Control"/>
<base href="/"/>
<title ng-bind="PageTitle">
Thomson Reuters | PermID
</title>
<meta content="" name="description"/>
<meta content="width=device-width, initial-scale=1" name="viewport"/>
<meta content="#ff8000" name="theme-color"/>
<!-- Place favicon.ico and apple-touch-icon.png in the root directory -->
<link href="app/vendor.daf96efe.css" rel="stylesheet"/>
<link href="app/app.1405210f.css" rel="stylesheet"/>
<link href="favicon.ico" rel="icon"/>
<!-- Typekit -->
<script src="//use.typekit.net/gnw2rmh.js">
</script>
<script>
try{Typekit.load({async:true});}catch(e){}
</script>
<!-- // Typekit -->
<!-- Google Tag Manager Data Layer -->
<!--<script>
analyticsEvent = function() {};
analyticsSocial = function() {};
analyticsForm = function() {};
dataLayer = [];
</script>-->
<!-- // Google Tag Manager Data Layer -->
</head>
<body class="theme-grey" id="top" ng-esc="">
<!--[if lt IE 7]>
<p class="browserupgrade">You are using an <strong>outdated</strong> browser. Please upgrade your browser to improve your experience.</p>
<![endif]-->
<!-- Add your site or application content here -->
<navbar class="tms-navbar">
</navbar>
<div id="body" role="main" ui-view="">
</div>
<div id="footer-wrapper" ng-show="!params.elementsToHide">
<footer id="main-footer">
</footer>
</div>
<!--[if lt IE 9]>
<script src="bower_components/es5-shim/es5-shim.js"></script>
<script src="bower_components/json3/lib/json3.min.js"></script>
<![endif]-->
<script src="app/vendor.8cc12370.js">
</script>
<script src="app/app.6e5f6ce8.js">
</script>
</body>
</html>
Does anyone know what I'm missing here and how I could get it to work?

Thanks, Teemu Risikko - a comment (albeit not the solution) of the website you linked got me on the right path.
In case someone else is bumping into the same problem, here is my solution: I'm getting the data via requests and not via traditional "scraping" (e.g. BeautifulSoup or lxml).
Navigate to the website using Google Chrome.
Right-click on the website and select "Inspect".
On the top navigation bar select "Network".
Limit network monitor to "XHR".
One of the entries (market with an arrow) shows the link that can be used with the requests library.
import requests
url = 'https://permid.org/api/mdaas/getEntityById/21475776041'
headers = {'X-AG-Access-Token': YOUR_ACCESS_TOKEN}
r = requests.get(url, headers=headers)
r.json()
Which gets me this:
{u'Asset Class': [u'Units'],
u'Asset Class URL': [u'https://permid.org/1-302043'],
u'Currency': [u'CAD'],
u'Currency URL': [u'https://permid.org/1-500140'],
u'Exchange': [u'TOR'],
u'IsQuoteOf.mdaas': [{u'Is Quote Of': [u'Convertible Debentures Income Units'],
u'URL': [u'https://permid.org/1-21475768667'],
u'quoteOfInstrument': [u'21475768667'],
u'quoteOfInstrument URL': [u'https://permid.org/1-21475768667']}],
u'Mic': [u'XTSE'],
u'PERM ID': [u'21475776041'],
u'Quote Name': [u'CONVERTIBLE DEBENTURES INCOME UNT'],
u'Quote Type': [u'equity'],
u'RIC': [u'OCV_u.TO'],
u'Ticker': [u'OCV.UN'],
u'entityType': [u'Quote']}

Using the default user-agent with a lot of pages will give you a different looking page because it is using an outdated user-agent. This is what your output is telling you.
Reference on Changing user-agents
Thought this may be your problem, it does not exactly answer the question about getting dynamically applied changes on a webpage. To get the dynamically changed data you need to emulate the javascript requests that the page is making on load. If you make the requests that the javascript is making you will get the data that the javascript is getting.

Access to valid youtube link is denied after being parsed with Projekktor

I have this html file, downloaded from Projekktor:
<!DOCTYPE HTML>
<html>
<head>
<title>Projekktor Version 8 Test</title>
<link rel="stylesheet" href="theme/style.css" type="text/css" media="screen" />
<script type="text/javascript" src="projekktor/jquery.min.js"></script> <!-- Load jquery -->
<script type="text/javascript" src="projekktor/projekktor.min.js"></script> <!-- load projekktor -->
</head>
<body>
<video id="player_a" class="projekktor" poster="intro.png" title="this is projekktor" width="640" height="360" controls>
<source src="" />
</video>
<script type="text/javascript">
$(document).ready(function() {
projekktor('#player_a', {
volume: 0.8,
playerFlashMP4: 'http://www.localhost:8000/StrobeMediaPlayback.swf',
playerFlashMP3: 'http://www.localhost:8000/StrobeMediaPlayback.swf'
});
});
</script>
</body>
</html>
Then I am obtaining the url for an youtube video via an API call (I have credentials), in order to replace src=''with the result form the following code
import lxml.html as LH
link = youtube_call(id)
def parse_html(link):
filename = 'projekktor.html'
f = LH.parse(filename)
for el in f.iter('video'):
el.attrib['src'] = link
# have also tried
# el.attrib['src'] = link.replace('amp;', '')
new_html = LH.tostring(f, pretty_print=True)
print (new_html)
but when I print it, a nasty amp; is added to src=, and access to link is denied. ( I broke the link here into newlines for readability purposes)
https://r3---sn-oxunxg8pjvn-bpbs.googlevideo.com/videoplayback?expire=1485418386&
amp;mv=m&
amp;mt=1485396620&
amp;ms=au&
amp;clen=13475559&
amp;mn=sn-oxunxg8pjvn-bpbs&
amp;mm=31&
amp;ipbits=0&
amp;requiressl=yes&
amp;itag=18&id=o-AG-dux-Jvtia_DsWZcyRfNpbMlzulsNn6I3SXyi0SI1B&
amp;lmt=1458188966300704&
amp;signature=BDC946187F74386CE00C5452CD703F9B13E4E30F.766549AB6A7C1811899CCC04742353B5BD0153D7&dur=266.448&key=yt6&
amp;ip=177.142.138.140&
amp;sparams=clen%2Cdur%2Cei%2Cgir%2Cid%2Cinitcwndbps%2Cip%2Cipbits%2Citag%2Clmt%2Cmime%2Cmm%2Cmn%2Cms%2Cmv%2Cpl%2Cratebypass%2Crequiressl%2Csource%2Cupn%2Cexpire&
amp;ei=MluJWO_aEIr_-AXHx6GwDA&
amp;mime=video%2Fmp4&
amp;upn=aFGwEwwIS1o&pl=20&source=youtube&
amp;ratebypass=yes&initcwndbps=1178750&
amp;gir=yes
Remove all amp; and the link is valid, but I've tried link.replace('amp;', '') does not work.
Is there any workaround this?

Categories