Develop Reference

Printing a PDF with Selenium Chrome Driver in headless mode

I have no problems printing without headless mode, however once I enable headless mode, it just refuses to print a PDF. I'm currently working on an app with a GUI, so I'd rather not have the Selenium webdriver visible to the end user if possible.
For this project I'm using an older version of Selenium, 4.2.0. That coupled with Python 3.9.
import os
from os.path import exists
import json
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver import Chrome, ChromeOptions
# Paths
dir_path = os.getcwd()
download_path = os.path.join(dir_path, "letters")
chrome_path = os.path.join(dir_path, "chromium\\app\\Chrome-bin\\chrome.exe")
user_data_path = os.path.join(dir_path, "sessions")
website = "https://www.google.com/"
def main():
print_settings = {
"recentDestinations": [{
"id": "Save as PDF",
"origin": "local",
"account": "",
}],
"selectedDestinationId": "Save as PDF",
"version": 2,
"isHeaderFooterEnabled": False,
"isLandscapeEnabled": True
}
options = ChromeOptions()
options.binary_location = chrome_path
options.add_argument("--start-maximized")
options.add_argument('--window-size=1920,1080')
options.add_argument(f"user-data-dir={user_data_path}")
options.add_argument("--headless")
options.add_argument('--enable-print-browser')
options.add_experimental_option("prefs", {
"printing.print_preview_sticky_settings.appState": json.dumps(print_settings),
"savefile.default_directory": download_path, # Change default directory for downloads
"download.default_directory": download_path, # Change default directory for downloads
"download.prompt_for_download": False, # To auto download the file
"download.directory_upgrade": True,
"profile.default_content_setting_values.automatic_downloads": 1,
"safebrowsing.enabled": True
})
options.add_argument("--kiosk-printing")
driver = Chrome(service=Service(ChromeDriverManager().install()), options=options)
driver.get(website)
driver.execute_script("window.print();")
if exists(os.path.join(user_data_path, "Google.pdf")):
print("YAY!")
else:
print(":(")
if __name__ == '__main__':
main()

For anyone else coming across this with a similar issue, I fixed it by using the print method described here: Selenium print PDF in A4 format
Using my example from above, I replaced:
driver.execute_script("window.print();")
with:
pdf_data = driver.execute_cdp_cmd("Page.printToPDF", print_settings)
with open('Google.pdf', 'wb') as file:
file.write(base64.b64decode(pdf_data['data']))
And that worked just fine for me.

python selenium Access to script at https://sitesA.com from origin https://sitesB.com has been blocked by CORS policy only in headless mode

I'm building a python program that using selenium and chrome driver to download .xml and .pdf files from a website, it's running fine, but when i turn the driver into headless mode then "CORS policy occur", I already try adding "disable-web-security" and "--disable-site-isolation-trials" after spend alot of time searching on internet but still no luck,So anyone please tell me what am I missing? What am I doing wrong? this is how I implement chrome driver:
options = webdriver.ChromeOptions()
options.add_argument('no-sandbox')
options.add_argument('--disable-gpu')
options.add_argument('--disable-extensions')
options.add_argument('--disable-dev-shm-usage')
options.add_argument('--disable-blink-features=AutomationControlled')
options.add_argument('--safebrowsing-disable-download-protection')
options.add_argument('--start-maximized')
options.headless = True
extset = ['enable-automation', 'ignore-certificate-errors']
options.add_experimental_option('excludeSwitches', extset)
options.add_experimental_option('useAutomationExtension', False)
options.add_argument('--ignore-certificate-errors')
options.add_argument('--allow-insecure-localhost')
options.add_argument('--safebrowsing-disable-download-protection')
options.add_argument('--disable-web-security')
options.add_argument('--disable-site-isolation-trials')
options.add_argument('safebrowsing-disable-extension-blacklist')
prefs = {
'download.default_directory' : DOWNLOAD_DIRECTORY, # set up download directory
'safebrowsing.enabled': True, # disable xml download asking
'profile.default_content_setting_values.automatic_downloads': 1, # allow multiple files download
'download.prompt_for_download': False
}
if rpa.get('options') == 'AUTO_DOWNLOAD_PDF':
prefs.update({ 'plugins.plugins_list': [{ 'enabled': False, 'name': 'Chrome PDF Viewer' }] })
prefs.update({ 'plugins.always_open_pdf_externally': True })
prefs.update({ 'browser.helperApps.neverAsk.saveToDisk': 'application/pdf,application/vnd.adobe.xfdf,application/vnd.fdf,application/vnd.adobe.xdp+xml' })
options.add_experimental_option('prefs', prefs)
driver = webdriver.Chrome(os.getcwd()+'\\webdriver\\chromedriver.exe', options=options)

Robocorp selenium fails to open pdf in chrome browser

I am trying to automate clicking through a website and currently have the following code
def open_site(self, url, headless=True, **kwargs):
options = webdriver.ChromeOptions()
options.add_argument("--incognito")
options.add_argument("--disable-popup-blocking")
options.add_experimental_option("excludeSwitches", ["enable-automation"])
options.add_experimental_option('useAutomationExtension', False)
options.add_argument("--start-maximized")
options.add_argument("--disable-extensions")
options.add_argument('--disable-infobars')
options.add_argument("--disable-web-security")
options.add_argument("--allow-running-insecure-content")
options.add_experimental_option('prefs', {
"download.default_directory": str(Path(self.download_dir).resolve()), # Change default directory for downloads
"download.prompt_for_download": False, # To auto download the file
"download.directory_upgrade": True,
"plugins.always_open_pdf_externally": True, # It will not show PDF directly in chrome
"download.extensions_to_open": "applications/pdf",
"profile.default_content_settings.popups": 1
})
self.create_webdriver('Chrome', desired_capabilities=options.to_capabilities(), executable_path="/path/to/chrome/driver")
self.go_to(url=url)
However, when the website opens I get stuck at the point of loading the pdf. It seems as though chrome fails on the aspx part. The website does load the pdf in Safari but this can only be used locally. Firefox isint supported at all by the website. Chrome is the only option. pdf image and click through image. Any assistance would be appreciated.

Download file in Headless Chrome, (python)

I tried everything to download a file in headless chrome but nothing works, I'm using Chrome version 86.0.4240.75 while ChromeDriver version: 86.0.4240.22, I've already tried any solution and none of them worked
download_dir = "/tmp/"
options.add_argument("--start--minimized")
options.add_experimental_option("prefs", {
"download.default_directory": download_dir,
"download.prompt_for_download": False,
})
browser.get(www.download.com)
browser.command_executor._commands["send_command"] = ("POST", '/session/$sessionId/chromium/send_command')
params = {'cmd': 'Page.setDownloadBehavior', 'params': {'behavior': 'allow', 'downloadPath': download_dir}}
command_result = browser.execute("send_command", params)
When I try to specify the download directory as well without headless mode it gives me a common download chrome error

My use case is a little different - I'm navigating to a page and submitting a form - but I am getting working downloads with this code:
chrome_options = Options()
chrome_options.add_argument("--headless")
chrome_options.add_argument("--no-sandbox")
chrome_options.add_argument("--disable-dev-shm-usage")
chrome_prefs = {"download.default_directory": "/root/Downloads"}
chrome_options.experimental_options["prefs"] = chrome_prefs
chrome_prefs["profile.default_content_settings"] = {"images": 2}
driver = webdriver.Chrome(options=chrome_options)
driver.get('https://...redacted...')
WebDriverWait(driver, 10).until(
EC.presence_of_element_located((By.XPATH, "//a[contains(text(),'ContractOp')]")))
submit_button = driver.find_element_by_xpath("//button[contains(.,'Submit')]")
submit_button.click()
# wait for download to finish
Hope this is helpful for you.

File Not Saving While Downloading File in Headless chrome using Selenium in python

I am able to download file in normal chrome mode. where as, i am not able to see the download happening in headless chrome using selenium python.
I hope it is not saving the file downloaded
Tried with solutions provided by many users in internet but none of them works
options = Options()
options.add_argument('--headless')
options.add_argument('--disable-gpu')
prefs = {'download.default_directory' :'/Users/nrpss/Downloads'}
options.add_experimental_option('prefs', prefs)
download_path = '/Users/nrpss/Downloads'
browser = webdriver.Chrome('chromedriver.exe', options=options)
browser.command_executor._commands["send_command"] = ("POST", '/session/$sessionId/chromium/send_command')
params = {'cmd': 'Page.setDownloadBehavior', 'params': {'behavior': 'allow', 'downloadPath': download_path}}
command_result = browser.execute("send_command", params)
print ("Headless Chrome Initiated")
### Below is ID for the Download link on webpage
browser.find_element_by_id('downloadExportLink').click()
time.sleep(50)
def download_completed():
for i in os.listdir('/Users/nrpss/Downloads'):
if ".crdownload" in i:
time.sleep(1)
download_completed()
Expected result: File should be downloaded and saved in downloads folder.

Try adding download.prompt_for_download = False and download.directory_upgrade = True you car set safebrowsing_for_trusted_sources_enabled to False as well as safebrowsing.enabled.
try changing your prefs to:
prefs = {'download.default_directory' :'/Users/nrpss/Downloads',
"download.prompt_for_download": False,
"download.directory_upgrade": True,
"safebrowsing_for_trusted_sources_enabled": False,
"safebrowsing.enabled": False
}
options.add_experimental_option('prefs', prefs)
Hope this helps you!

to enable headless downloads in Python:
from selenium.webdriver import Chrome
from selenium.webdriver.chrome.options import Options
options = Options()
options.headless = True
driver = Chrome(options=options)
params = {'behavior': 'allow', 'downloadPath': '/path/for/download'}
driver.execute_cdp_cmd('Page.setDownloadBehavior', params)