DEV Community

BK ☕
BK ☕

Posted on • Updated on

Automate Taking Website Screenshots With Selenium in Python

Update 09/11/2020

Updated Title for more clarity
Published on https://bilalkhoukhi.com/blog/automate-taking-website-screenshots-with-selenium-in-python

Update 01/01/2019

Here is a Node.js app doing the same work, it is using a React front-end. Node.js App with Selenium and React

Update 12/26/2018

If you wish to run the job using Headless Chrome, either on Windows, Mac, Linux (Desktop or through SSH), I have added a new section at the end of the post.

Original Post

A not too long story short I dread doing repeated tasks manually and that's why I'd rather spend minutes (hours when doing it for the first time) to write a script that automates the process for me. Otherwise I cannot focus, and if you're also horrible at focusing just like I am, I recommend reading Deep Work by Cal Newport.

Problem:

I have a Photoshop mock-up of a laptop, stablet and a phone that I need to use to showcase a website.

Image

That's an easy and quick job, 3 screenshots and 2 minutes later, you're done. But what if you have 10, 20, or 100 websites, and you have to supply screenshots of different screen sizes (a desktop, a mobile and a tablet)?

Solution:

Selenium is the solution. And since I've only used it with Python, I choose to do this tutorial with Python, it is also faster for me to setup compared to a Node.js project, but the functionality should be similar.

Let's start:

If you don't have Python installed in your system already, get it from here: Python 3.6+
You will also need Chrome Webdriver

Once you have Python setup, install Selenium by running the command:

$ pip install selenium
Enter fullscreen mode Exit fullscreen mode

It's easy to get started with python, all you need is a single file that imports the modules you will be using, selenium and perhaps time which will allow us to delay/wait a few seconds after the page is loaded before we take the screenshot.

We will also make use of the time module, which is part of the Python standard library..

Next, Create a file with the extension .py and open it with your favorite editor.

First we'll start by importing webdriver from selenium and time.

from selenium import webdriver
import time
Enter fullscreen mode Exit fullscreen mode

Now let's define a list of links we want to take screenshots of

links = ['dev.to', 'twitter.com', 'github.com']
Enter fullscreen mode Exit fullscreen mode

It's import to note that the webdriver does not consider the links above as valid since they do not have the https:// protocol. We will be adding it later, and the reason I added them without the protocol is so that I can use the above as file names.

We can start using the webdriver by calling webdrive.chrome(/path/to/chromedriver) as follows

with webdriver.Chrome("C:/chromedriver_win32/chromedriver") as driver:
    # code goes here using driver
Enter fullscreen mode Exit fullscreen mode

The above reads as with this function defined as driver.. do things with driver
Which is somewhat equivalent to

driver = webdriver.Chrome("C:/chromedriver_win32/chromedriver")
# code goes here using driver
Enter fullscreen mode Exit fullscreen mode

As far as I can tell, the difference is that the first method will automatically close the browser once it is done doing its job, unlike the second one, which you would have to explicitly call driver.close() to close the browser. If anyone knows other reasons, please let me know in the comments.

For this tutorial I will be using the first method.
For those new to Python, it is important to note that the following lines will be indented, as they're contained in the statement above, similar to how you would use curly braces to contain a function/class body in C++, JavaScript and other languages.

For the purpose of taking a screenshot, we will be using 3 commands: set_window_size(), get() and save_screenshot()

driver.set_window_size(width, height) # takes two arguments, width and height of the browser and it has to be called before using get()
driver.get(url) # takes one argument, which is the url of the website you want to open
driver.save_screenshot(/output-dir/file_name.png) # this one takes one argument which is the path and filename all concatenated. Important: the filename should end with .png 
Enter fullscreen mode Exit fullscreen mode

To learn more about these commands head to the Webdriver API documentation

Let's put it all together, we will need to loop through the list of links we created above, and define some variables to use for filename, width and height, and the link with the https:// protocol

with webdriver.Chrome("C:/chromedriver_win32/chromedriver") as driver:
    for link in links:
        desktop = {'output': str(link) + '-desktop.png',
                   'width': 2200,
                   'height': 1800}
        tablet = {'output': str(link) + '-tablet.png',
                  'width': 1200,
                  'height': 1400}
        mobile = {'output': str(link) + '-mobile.png',
                  'width': 680,
                  'height': 1200}
        linkWithProtocol = 'https://' + str(link)
Enter fullscreen mode Exit fullscreen mode

We have defined 3 dictionaries that contain the output filename, width and height for every screen size we need, you can change the dimensions based on your needs.

Now we can start using the commands explained above

        # set the window size for desktop
        driver.set_window_size(desktop['width'], desktop['height'])
        driver.get(linkWithProtocol)
        time.sleep(s)
        driver.save_screenshot(desktop['output'])
Enter fullscreen mode Exit fullscreen mode

Noticed that we have used time.sleep(1), what that means is that we asked python to delay the execution of the next line until 2 seconds pass. Even without the sleep command, the driver will wait for the page to fully load before it takes the screenshot, however, if you have any animation, you may want to wait for things to settle down, if that's not needed, then you can get rid of the line.

and this is how the tablet and mobile will look like:

        # set the window size for tablet
        driver.set_window_size(tablet['width'], tablet['height'])
        driver.get(linkWithProtocol)
        time.sleep(2)
        driver.save_screenshot(tablet['output'])

        # set the window size for mobile
        driver.set_window_size(mobile['width'], mobile['height'])
        driver.get(linkWithProtocol)
        time.sleep(2)
        driver.save_screenshot(mobile['output'])
Enter fullscreen mode Exit fullscreen mode

And with that, all you need to do is run the script from the command line

python script.py
Enter fullscreen mode Exit fullscreen mode

This will open Chrome browser, resize it, take the screenshot each time and output the file at the same directory you have script.py until it is done.

The whole code put together can be found here on Github

Final note

Selenium is capable of great things, it can manipulate pages with CSS and JavaScript, fill out forms and submit them, etc... Learn it and put it to good use.

How to use Selenium with Headless Chrome

It can be annoying to have the browser open and close so many times while you're trying to finish other work. The solution is to use Headless Chrome.

Not much will change from the code above.
We need to define our ChromeOptions() and add an argument to it using add_argument() command as follows:

options = webdriver.ChromeOptions() # define options
options.add_argument("headless") # pass headless argument to the options
Enter fullscreen mode Exit fullscreen mode

Then we will pass a new argument to the command we defined before:

with webdriver.Chrome("C:/chromedriver_win32/chromedriver") as driver:
    # code here
Enter fullscreen mode Exit fullscreen mode

becomes

with webdriver.Chrome("C:/chromedriver_win32/chromedriver", chrome_options=options) as driver:
    # code here
Enter fullscreen mode Exit fullscreen mode

This is all you will need for Mac and Windows which I have tested. Linux desktop have not been tested, but I assume it will work as well.

Linux Server through SSH

Things work differently between Linux Desktop and Server, the latter has no screen, and I am sure it is stripped from so many drivers it does not need, and for that reason, we will have to pass a few more arguments to make it work.
As I have not tested this on Linux Desktop, if the solution above does not work, then treat it like we will treat Linux Server

First install Chrome Browser (I never thought I'd need it here)

sudo apt-get install -y chromium-browser # BTW I use Ubuntu (says a non-Arch user)
Enter fullscreen mode Exit fullscreen mode

Then we add these arguments

options = webdriver.ChromeOptions() # define options
options.add_argument("headless") # pass headless argument to the options
options.binary_location = '/usr/bin/chromium-browser' # location of the Chrome Browser binary
options.add_argument("disable-infobars") # disabling infobars
options.add_argument("--disable-extensions") # disabling extensions
options.add_argument("--disable-gpu") # applicable to windows os only
options.add_argument("--disable-dev-shm-usage") # overcome limited resource problems
options.add_argument("--no-sandbox") # Bypass OS security model
# thanks to https://stackoverflow.com/a/50642913/2291648, this answer helped debug the issue

Enter fullscreen mode Exit fullscreen mode

And just like we did above, pass the chrome_options=options to the webdriver.Chrome(...,webdriver.Chrome) as a second argument.

This worked for me, and I hope it does for you as well.

Github link (updated repo)

Top comments (10)

Collapse
 
rhymes profile image
rhymes

Hey Bilal, nice overview. I noted something odd that I wanted to ask you about. The module time is in the standard library as time and so is time.sleep(). I'm not sure wat you're installing through pip. I checked on pypi but it's not clear.

Collapse
 
bk profile image
BK ☕

Hello rhymes, thank you for noticing that. I double checked, and indeed the time module is part of the standard library. docs.python.org/3/library/time.html
I have edited the post. Your feedback is appreciated.

Collapse
 
smirza profile image
Suhail

Thanks a lot, Bilal for sharing this. Curious to know if this solution is OS dependent.

Collapse
 
bk profile image
BK ☕ • Edited

Hello Suhail, you're very welcome.
I am on my Mac right now, so I had the chance to do a quick test.
All I had to do is download Chrome Webdriver for MacOS from the link provided in the post, installed selenium with pip. Of course I had the change the path to the webdriver, I ran the python script and it worked with no additional tweaking.

Another tip, if you'd like to run the job with Chrome headless:

# imports here
# links = [array of links]

options = webdriver.ChromeOptions()
options.add_argument('headless')

with webdriver.Chrome('/Users/userName/chromedriver', chrome_options=options) as driver:
    # code here

I tested the headless on MacOS, I am trying to test this on Ubuntu on a remote server. I'll update the post if I succeed.

Collapse
 
smirza profile image
Suhail

Nice work Bilal, Thanks a lot for the effort.

Collapse
 
bk profile image
BK ☕

Suhail, I have updated my post if you're interested in Headless Chrome.

Collapse
 
smirza profile image
Suhail

Thanks a ton Bilal :)

Collapse
 
mutale85 profile image
Mutale85 • Edited

using the solutions you provided here, I have been able to add a few things.

  1. Get Urls from Mysql database
  2. Skip broken links or url that return no response Thanks a lot , this has been my foundation to starting Selenium. My code is hosted here. mutamuls.medium.com/screenshot-url...
Collapse
 
mutale85 profile image
Mutale85

Hello Sir. Thanks for this tutorial. I have learnt a lot.

Collapse
 
sambathlim86 profile image
Sambat LIM

for new version of chrome webdriver, you should change your url from "google.com" to "google.com".