python 使用headless chrome滚动截图
from selenium import webdriver from selenium.webdriver.chrome.options import Options import util chrome_options = Options() #chrome_options.add_argument('--headless') chrome_options.add_argument('--disable-gpu') chrome_options.add_argument('--disable-infobars') chrome_options.binary_location = r"C:\Program Files (x86)\Google\Chrome\Application\chrome.exe" driver=webdriver.Chrome(chrome_options=chrome_options) driver.get("http://www.mizuhobank.co.jp/sp/loan/card/index.html") #driver.execute_script("window.scrollTo(0, document.body.scrollHeight);") util.fullpage_screenshot(driver, "3.png") driver.close() driver.quit()
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