如何在 Selenium 中处理 Firefox 打印对话框

Question

我有以下代码：

from selenium.webdriver import Firefox
from selenium.webdriver.common.keys import Keys
url = 'https://finance.yahoo.com/'
driver_path = 'geckodriver.exe'

browser = Firefox(executable_path = driver_path)
browser.get(url)
profile.set_preference("browser.helperApps.neverAsk.saveToDisk", "application/pdf")
profile.set_preference("browser.helperApps.neverAsk.openFile", "application/pdf")
search_field_id = 'yfin-usr-qry'

element_search_field = browser.find_element_by_id(search_field_id)
element_search_field.clear()
element_search_field.send_keys('TSLA')
element_search_field.send_keys(Keys.ENTER)
from selenium.webdriver import ActionChains
action_chains = ActionChains(browser)
action_chains.key_down(Keys.CONTROL).send_keys('V').key_up(Keys.CONTROL).perform()
xpath_string = '/html/body/div[1]/div/div/div[1]/div/div[2]/div/div/div[6]/div/div/section/div/ul/li[2]/a/span'
element = browser.find_element_by_xpath(xpath_string)
action_chains.move_to_element(element).click().perform()
browser.execute_script('window.print();')

Firefox 会弹出一个打印对话框。我想知道我怎么能接受它。有没有办法绕过这个对话框直接打印，因为这不是系统对话框而是火狐的。

编辑： 根据@Prophet 的输入，我的完整更新代码

from selenium.webdriver import Firefox
from selenium.webdriver.common.keys import Keys
from selenium.webdriver import ActionChains
from selenium.webdriver.support.ui import Select
from selenium.webdriver.firefox.options import Options
from selenium.webdriver.firefox.firefox_profile import FirefoxProfile
import time
from fake_useragent import UserAgent
from selenium import webdriver
from selenium.webdriver import DesiredCapabilities
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver.common.keys import Keys
ua = UserAgent()
userAgent = ua.random

url = 'https://finance.yahoo.com/'
driver_path = 'geckodriver.exe'

profile = FirefoxProfile('C:\\Users\\\\AppData\\Roaming\\Mozilla\\Firefox\\Profiles\\tp3cz5dm.default-release')
profile.set_preference("general.useragent.override", userAgent)

browser = Firefox(executable_path = driver_path)
browser.get(url)
profile.set_preference("browser.helperApps.neverAsk.saveToDisk", "application/pdf")
profile.set_preference("browser.helperApps.neverAsk.openFile", "application/pdf")
search_field_id = 'yfin-usr-qry'

element_search_field = browser.find_element_by_id(search_field_id)
element_search_field.clear()
element_search_field.send_keys('TSLA')
element_search_field.send_keys(Keys.ENTER)
from selenium.webdriver import ActionChains
action_chains = ActionChains(browser)
action_chains.key_down(Keys.CONTROL).send_keys('V').key_up(Keys.CONTROL).perform()
# xpath_string = '/html/body/div[1]/div/div/div[1]/div/div[2]/div/div/div[6]/div/div/section/div/ul/li[2]/a/span'
# element = browser.find_element_by_xpath(xpath_string)
# action_chains.move_to_element(element).click().perform()
browser.execute_script('window.print();')

browser.switch_to.window(browser.window_handles[-1])
time.sleep(0.5)
actionButton = browser.execute_script(
"return document.querySelector('print-preview-app').shadowRoot.querySelector('#sidebar').shadowRoot.querySelector('print-preview-button-strip').shadowRoot.querySelector('.action-button')")
cancelButton.click()
# switch back to main window
browser.switch_to.window(driver.window_handles[0])

当我运行这个时，我得到了错误：

JavascriptException: TypeError: document.querySelector(...) is null

Answer 1

以下两个解决方案都设计为不启动print dialog. 这些解决方案会将活动网页打印到本地打印机或 PDF 文件，而无需处理对话框.

2021 年 8 月 19 日更新后

---

我想将输出保存为 PDF，而不是打印到纸上。我很震惊使用geckodriver 和selenium 打印到PDF 是多么困难。使用“chromedriver”，您可以拨打function 'execute_cdp_cmd' and pass Page.printToPDF。 geckodriver 没有“execute_cdp_cmd”。

当我通过Stack Overflow 寻找灵感时，我发现了多个关于使用geckodriver 和selenium 打印pdf 的未解决问题。在看到这是一个问题后，我查看了selenium 中的问题和mozilla 的错误报告。这又是其他人遇到的问题。

一些错误报告提到打印过程中使用的某些开关不再起作用。

profile.set_preference("print.print_to_file", True)
profile.set_preference("print.print_to_filename", "/tmp/file.pdf")

我决定查看source code for mozilla gecko-dev 寻找潜在的解决方案。经过数小时的研究，我发现上面的开关被新的开关替换了，另一个打印机变量也被替换了。经过一些测试，我能够将您的网页保存为 PDF。

下面的代码将启用所有链接的网页打印为 PDF。我建议在代码中添加一些错误处理。我需要改进文件名部分的代码的一部分。您应该能够添加一个重命名文件的函数，这将允许您在单个会话中打印任意数量的文件。

from time import sleep
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.firefox.options import Options
from selenium.webdriver.firefox.options import FirefoxProfile

firefox_options = Options()
firefox_options.add_argument("--disable-infobars")
firefox_options.add_argument("--disable-extensions")
firefox_options.add_argument("--disable-popup-blocking")

profile_options = FirefoxProfile()
user_agent = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 11.5; rv:90.0) Gecko/20100101 Firefox/90.0'
profile_options.set_preference('profile_options = FirefoxProfile()', user_agent)
profile_options.set_preference("print_printer", "Mozilla Save to PDF")
profile_options.set_preference("print.always_print_silent", True)
profile_options.set_preference("print.show_print_progress", False)
profile_options.set_preference('print.save_as_pdf.links.enabled', True)
profile_options.set_preference("print.printer_Mozilla_Save_to_PDF.print_to_file", True)

# set your own file path
profile_options.set_preference('print.printer_Mozilla_Save_to_PDF.print_to_filename',
                               "tmp/testprint.pdf")


driver = webdriver.Firefox(executable_path='/usr/local/bin/geckodriver', options=firefox_options,
                           firefox_profile=profile_options)


URL = 'https://finance.yahoo.com/'


driver.get(URL)

sleep(10)

search_field_id = 'yfin-usr-qry'

element_search_field = driver.find_element_by_id(search_field_id)
element_search_field.clear()
element_search_field.send_keys('TSLA')
element_search_field.send_keys(Keys.ENTER)

sleep(10)

driver.execute_script("window.print()")

sleep(20)

driver.quit()

2021 年 8 月 18 日原帖

---

我决定查看您的问题，因为我对 selenium 功能感兴趣。

我查看了geckodriver的源代码，发现printUtils.js，其中提供了打印过程中使用的开关的详细信息，例如：

firefox_options.set_preference("print.always_print_silent", True)
firefox_options.set_preference("print.show_print_progress", False)

删除一些代码并添加一些代码后，我能够使用以下代码打印到我的 HP 打印机，而无需处理打印对话框：

from time import sleep
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.firefox.options import Options
from selenium.webdriver.firefox.options import FirefoxProfile

firefox_options = Options()
firefox_options.add_argument("--disable-infobars")
firefox_options.add_argument("--disable-extensions")
firefox_options.add_argument("--disable-popup-blocking")

profile_options = FirefoxProfile()
user_agent = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 11.5; rv:90.0) Gecko/20100101 Firefox/90.0'
firefox_options.set_preference('profile_options = FirefoxProfile()', user_agent)
firefox_options.set_preference("print.always_print_silent", True)
firefox_options.set_preference("print.show_print_progress", False)
firefox_options.set_preference("pdfjs.disabled", True)

driver = webdriver.Firefox(executable_path='/usr/local/bin/geckodriver', options=firefox_options)

URL = 'https://finance.yahoo.com/'

driver.get(URL)

sleep(10)

search_field_id = 'yfin-usr-qry'

element_search_field = driver.find_element_by_id(search_field_id)
element_search_field.clear()
element_search_field.send_keys('TSLA')
element_search_field.send_keys(Keys.ENTER)

sleep(10)
driver.execute_script("window.print()")

----------------------------------------
My system information
----------------------------------------
Platform:    Apple
OS:          10.15.7
Python:      3.9
Selenium:    3.141
Firefox:     90.0.2
Geckodriver: 0.29.0

----------------------------------------

Answer 2

添加这些配置文件首选项应避免出现此弹出窗口：

profile.set_preference("print.always_print_silent", True)
profile.set_preference("print.show_print_progress", False)

UPD
涉及打印对话框后，请尝试通过此代码接受它：

# switch to print preview window
driver.switch_to.window(driver.window_handles[-1])
time.sleep(0.5)
actionButton = driver.execute_script(
"return document.querySelector('print-preview-app').shadowRoot.querySelector('#sidebar').shadowRoot.querySelector('print-preview-button-strip').shadowRoot.querySelector('.action-button')")
cancelButton.click()
# switch back to main window
driver.switch_to.window(driver.window_handles[0])