Selenium 4+GeckoDriver：用page.printtopdf将网页打印成PDF格式

Question

使用Selenium4和chromedriver，我成功地将网站打印成具有自定义页面大小的PDF（请参见下面的Python代码）。我想知道用GeckoDriver/Firefox实现这一功能的等价物。

def send_devtools(driver, cmd, params={}):
resource = "/session/%s/chromium/send_command_and_get_result" % driver.session_id
url = driver.command_executor._url + resource
body = json.dumps({'cmd': cmd, 'params': params})
response = driver.command_executor._request('POST', url, body)
if (response.get('value') is not None):
    return response.get('value')
else:
    return None

def save_as_pdf(driver, path, options={}):
    result = send_devtools(driver, "Page.printToPDF", options)
    if (result is not None):
        with open(path, 'wb') as file:
        file.write(base64.b64decode(result['data']))
        return True
    else:
        return False

options = webdriver.ChromeOptions()
# headless setting is mandatory, otherwise saving tp pdf won't work
options.add_argument("--headless")

driver = webdriver.Chrome(executable_path='/usr/local/bin/chromedriver', options=options)
# chrome has to operate in headless mode to procuce PDF
driver.get(r'https://example.my')

send_devtools(driver, "Emulation.setEmulatedMedia", {'media': 'screen'})
pdf_options = { 'paperHeight': 92, 'paperWidth': 8, 'printBackground': True }
save_as_pdf(driver, 'myfilename.pdf', pdf_options)

Answer 1

如果要使用Firefox或Geckodriver继续执行相同的任务，显然上面提到的写入文件的代码存在一些问题，导致无法保存目标文档。

因此，我对代码进行了调整，现在使用Firefox上的Geckdriver打开网站，并使用函数find_element_by_tag_name()为主体元素获取截图，该函数后来被转换为RGB模式，截图的维度随后使用Pillow保存为PDF文档

from PIL import Image
from io import BytesIO
from selenium import webdriver

driverOptions = webdriver.FirefoxOptions()
# Uncomment the below line and change the path according to your configurations if you encounter an error like "Expected browser binary location ..."
# driverOptions.binary_location = '/Applications/Firefox.app/Contents/MacOS/firefox'
driverOptions.add_argument("--headless")
webDriver = webdriver.Firefox(executable_path = '/usr/local/bin/geckodriver', options = driverOptions)
webDriver.get(f'https://stackoverflow.com')
websiteScreenshot = Image.open(BytesIO(webDriver.find_element_by_tag_name('body').screenshot_as_png))
rgbImage = Image.new('RGB', websiteScreenshot.size, (255, 255, 255))
rgbImage.paste(websiteScreenshot, mask=websiteScreenshot.split()[3])
rgbImage.save('fileName.pdf', "PDF", resolution=100)
webDriver.quit()

• 浏览器二进制位置问题
• 将截图转换为PDF