how to download a file using selenium in python? - python-3.x

Question

I wanted to download files using python but I am not able to do it. I tried searching for the ways to do it but i dint find any relevant resource.
Here is my code:
from selenium import webdriver
driver = webdriver.Chrome('/home/user/Downloads/chromedriver')
#The below link is a pdf file and not an HTML file. I want to download this file directly.
driver.get("https://authlink-files-storage.ams3.digitaloceanspaces.com/authlink/transfered_certificates_related_docs/supporting_docs_17_2020_07_24_06_25_764ffb965d1b4ae287a0d3cc01c8dd03")
Now I want to download this file but i am not able to do it.

Answer 1

If direct download doesn't work you can always workaround using the printing functionality:
Need to use chrome options --kiosk-printing which will automatically click on print button once print dialog is opened
options = webdriver.ChromeOptions()
options.add_argument("--kiosk-printing")
Define chrome preferences as JSON string
prefs = {"savefile.default_directory": "your destination path", "printing.default_destination_selection_rules": {"kind": "local", "idPattern": ".*", "namePattern": "Save as PDF"}}
In above prefs, default directory will be used to save your pdf in required location. second pref will select the "save as pdf" option from print dialog automatically
Add pref as experimental options
options.add_experimental_option("prefs", prefs)
Define driver using chrome options and prefs
driver = webdriver.Chrome(chrome_options=options)
Once the pdf is opened in url, you can open print dialog using javascript
driver.execute_script("window.print()")
Your pdf will be saved in the destination path with the same title

Answer 2

Try This Code
from selenium import webdriver
download_dir = "C:\\Temp\\Dowmload" # for linux/*nix, download_dir="/usr/Public"
options = webdriver.ChromeOptions()
profile = {"plugins.plugins_list": [{"enabled": False, "name": "Chrome PDF Viewer"}], # Disable Chrome's PDF Viewer
"download.default_directory": download_dir , "download.extensions_to_open": "applications/pdf"}
options.add_experimental_option("prefs", profile)
driver = webdriver.Chrome('//Server/Apps/chrome_driver/chromedriver.exe', chrome_options=options)
driver.get("https://authlink-files-storage.ams3.digitaloceanspaces.com/authlink/transfered_certificates_related_docs/supporting_docs_17_2020_07_24_06_25_764ffb965d1b4ae287a0d3cc01c8dd03")

Answer 3

The solution to your problem is simple. To explain it better let me help you with a consideration of a scenario like downloading a file without clicking on the save as button in a present framework folder and then deleting the file after verification.
from selenium import webdriver
import os
From selenium.webdriver.common.by import By
From webdriver_manager.chrome import ChromeDriverManager
op = webdriver.ChromeOptions()
op.add_argument('--no-sandbox')
op.add_argument('--verbose')
op.add_argument("--disable-notifications")
op.add_experimental_option("prefs", {"download.default_directory":
"G:/Python/Download/","download.prompt_for_download":
False,"download.directory_upgrade": True,"safebrowsing.enabled": True})
op.add_argument('--disable-gpu')
op.add_argument('--disable-software-rasterizer')
driver = webdriver.Chrome(ChromeDriverManager().install(),
chrome_options=op)
driver.find_element(By.XPATH, “//span[#type = ‘button’]”).click()
def download_file_verify(self,filename):
dir_path = "G:/Python/Download/"
res = os.listdir(dir_path)
try:
name = os.path.isfile("Download/" + res[0])
if res[0].__contains__(filename):
print("file downloaded successfully")
except "file is not downloaded":
name = False
return name
def delete_previous_file(self,filename):
try:
d_path = "G:/Python/Download/"
list = os.listdir(d_path)
for file in list:
print("present file is: " + file)
path = ("Download/" + file)
if file.__contains__(filename):
os.remove(path)
print("Present file is deleted")
except:
pass