用chromedriver用Selenium Python进行全页截图

Question

在尝试了各种方法之后...我偶然发现了这个页面，用chromedriver、selenium和Python进行了全页截图。

原始代码在这里。（我在下面的帖子中复制了代码）

它使用PIL，它的工作很好！然而，有一个问题...也就是说，它捕获固定的标题和整个页面的重复，并且在页面更改期间遗漏页面的某些部分。获取截图的示例url：

"""
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

Answer 1

topnav = driver.find_element_by_id("topnav")
driver.execute_script("arguments[0].setAttribute('style', 'position: absolute; top: 0px;')", topnav) 

driver.execute_script("document.getElementById('topnav').setAttribute('style', 'position: absolute; top: 0px;');")

driver.execute_script("window.scrollTo({0}, {1})".format(rectangle[0], rectangle[1]))
driver.execute_script("document.getElementById('topnav').setAttribute('style', 'position: absolute; top: 0px;');")

如果站点使用header标记，则可以使用find_element_by_tag_name（“header”）