After trying out various approaches... I have stumbled upon this page to take full-page screenshot with chromedriver, selenium and python.
The original code is here. (and I copy the code in this posting below)
It uses PIL and it works great! However, there is one issue... which is it captures fixed headers and repeats for the whole page and also misses some parts of the page during page change. sample url to take a screenshot:
http://www.w3schools.com/js/default.asp
How to avoid the repeated headers with this code... Or is there any better option which uses python only... ( i don't know java and do not want to use java).
Please see the screenshot of the current result and sample code below.
test.py
"""
This script uses a simplified version of the one here:
https://snipt.net/restrada/python-selenium-workaround-for-full-page-screenshot-using-chromedriver-2x/
It contains the *crucial* correction added in the comments by Jason Coutu.
"""
import sys
from selenium import webdriver
import unittest
import util
class Test(unittest.TestCase):
""" Demonstration: Get Chrome to generate fullscreen screenshot """
def setUp(self):
self.driver = webdriver.Chrome()
def tearDown(self):
self.driver.quit()
def test_fullpage_screenshot(self):
''' Generate document-height screenshot '''
#url = "http://effbot.org/imagingbook/introduction.htm"
url = "http://www.w3schools.com/js/default.asp"
self.driver.get(url)
util.fullpage_screenshot(self.driver, "test.png")
if __name__ == "__main__":
unittest.main(argv=[sys.argv[0]])
util.py
import os
import time
from PIL import Image
def fullpage_screenshot(driver, file):
print("Starting chrome full page screenshot workaround ...")
total_width = driver.execute_script("return document.body.offsetWidth")
total_height = driver.execute_script("return document.body.parentNode.scrollHeight")
viewport_width = driver.execute_script("return document.body.clientWidth")
viewport_height = driver.execute_script("return window.innerHeight")
print("Total: ({0}, {1}), Viewport: ({2},{3})".format(total_width, total_height,viewport_width,viewport_height))
rectangles = []
i = 0
while i < total_height:
ii = 0
top_height = i + viewport_height
if top_height > total_height:
top_height = total_height
while ii < total_width:
top_width = ii + viewport_width
if top_width > total_width:
top_width = total_width
print("Appending rectangle ({0},{1},{2},{3})".format(ii, i, top_width, top_height))
rectangles.append((ii, i, top_width,top_height))
ii = ii + viewport_width
i = i + viewport_height
stitched_image = Image.new('RGB', (total_width, total_height))
previous = None
part = 0
for rectangle in rectangles:
if not previous is None:
driver.execute_script("window.scrollTo({0}, {1})".format(rectangle[0], rectangle[1]))
print("Scrolled To ({0},{1})".format(rectangle[0], rectangle[1]))
time.sleep(0.2)
file_name = "part_{0}.png".format(part)
print("Capturing {0} ...".format(file_name))
driver.get_screenshot_as_file(file_name)
screenshot = Image.open(file_name)
if rectangle[1] + viewport_height > total_height:
offset = (rectangle[0], total_height - viewport_height)
else:
offset = (rectangle[0], rectangle[1])
print("Adding to stitched image with offset ({0}, {1})".format(offset[0],offset[1]))
stitched_image.paste(screenshot, offset)
del screenshot
os.remove(file_name)
part = part + 1
previous = rectangle
stitched_image.save(file)
print("Finishing chrome full page screenshot workaround...")
return True
This answer improves upon prior answers by am05mhz and Javed Karim.
It assumes headless mode, and that a window-size option was not initially set. Before calling this function, ensure the page has loaded fully or sufficiently.
It attempts to set the width and height both to what is necessary. The screenshot of the entire page can sometimes include a needless vertical scrollbar. One way to generally avoid the scrollbar is by taking a screenshot of the body element instead. After saving a screenshot, it reverts the size to what it was originally, failing which the size for the next screenshot may not set correctly.
Ultimately this technique may still not work perfectly well for some examples.
from selenium import webdriver
def save_screenshot(driver: webdriver.Chrome, path: str = '/tmp/screenshot.png') -> None:
# Ref: https://stackoverflow.com/a/52572919/
original_size = driver.get_window_size()
required_width = driver.execute_script('return document.body.parentNode.scrollWidth')
required_height = driver.execute_script('return document.body.parentNode.scrollHeight')
driver.set_window_size(required_width, required_height)
# driver.save_screenshot(path) # has scrollbar
driver.find_element_by_tag_name('body').screenshot(path) # avoids scrollbar
driver.set_window_size(original_size['width'], original_size['height'])
If using Python older than 3.6, remove the type annotations from the function definition.